Upload trained model checkpoint

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-140/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-144/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-148/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-52/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+base_model: meta-llama/Llama-3.2-3B-Instruct
+library_name: peft
+model_name: llama-8b-instruct-medical-reward-10epochs-2e-5-64-128-1024
+tags:
+- base_model:adapter:meta-llama/Llama-3.2-3B-Instruct
+- lora
+- reward-trainer
+- transformers
+- trl
+licence: license
+---
+
+# Model Card for llama-8b-instruct-medical-reward-10epochs-2e-5-64-128-1024
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with Reward.
+
+### Framework versions
+
+- PEFT 0.17.1
+- TRL: 0.23.0
+- Transformers: 4.56.2
+- Pytorch: 2.8.0
+- Datasets: 4.1.1
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b49d5e057de69f8ed7a4c013d00bdace13c61865daf01987f0f5b08e3ced21a
+size 97313784

chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

checkpoint-140/README.md

@@ -0,0 +1,208 @@
+---
+base_model: meta-llama/Llama-3.2-3B-Instruct
+library_name: peft
+tags:
+- base_model:adapter:meta-llama/Llama-3.2-3B-Instruct
+- lora
+- reward-trainer
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-140/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-140/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8187be24f605af9ccf2bd744ca60d62dc6c9dac9fdd51da61f7fc975782f71
+size 97313784

checkpoint-140/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

checkpoint-140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19009a029f2ed301a5abedfa1d8d80a2328bacb83d997ef17a8b0ff99295f34
+size 194859518

checkpoint-140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a96c34cc1647eb2f442fc276b49d2b4c3ff1349c168a68a71e300e0b4567189
+size 14645

checkpoint-140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680615ec7166a9d03abca560c4fa0bd7bd1b62d608c7464bf6c1a7eb815fb43e
+size 1465

checkpoint-140/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoint-140/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52716f60c3ad328509fa37cdded9a2f1196ecae463f5480f5d38c66a25e7a7dc
+size 17210019

checkpoint-140/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-140/trainer_state.json

@@ -0,0 +1,1469 @@
+{
+  "best_global_step": 52,
+  "best_metric": 1.0,
+  "best_model_checkpoint": "/home/jovyan/RLHFBackdoor/alignment-handbook/save/llama-8b-instruct-medical-reward-10epochs-2e-5-64-128-1024/checkpoint-52",
+  "epoch": 9.347826086956522,
+  "eval_steps": 4,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06956521739130435,
+      "grad_norm": 16.051664352416992,
+      "learning_rate": 0.0,
+      "loss": 0.5155,
+      "step": 1
+    },
+    {
+      "epoch": 0.1391304347826087,
+      "grad_norm": 16.695077896118164,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.5624,
+      "step": 2
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 20.069669723510742,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.4644,
+      "step": 3
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "grad_norm": 18.166921615600586,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.52,
+      "step": 4
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "eval_accuracy": 0.82,
+      "eval_chosen_reward_mean": 0.7202807664871216,
+      "eval_loss": 0.44523465633392334,
+      "eval_rejected_reward_mean": 0.2797192633152008,
+      "eval_reward_diff_mean": 0.4405614733695984,
+      "eval_reward_diff_std": 0.48559921979904175,
+      "eval_runtime": 4.4816,
+      "eval_samples_per_second": 22.983,
+      "eval_steps_per_second": 5.802,
+      "step": 4
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 18.02265167236328,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.3831,
+      "step": 5
+    },
+    {
+      "epoch": 0.41739130434782606,
+      "grad_norm": 19.39177894592285,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5606,
+      "step": 6
+    },
+    {
+      "epoch": 0.48695652173913045,
+      "grad_norm": 21.10468292236328,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4886,
+      "step": 7
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "grad_norm": 15.2007417678833,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.432,
+      "step": 8
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "eval_accuracy": 0.86,
+      "eval_chosen_reward_mean": 0.7534962296485901,
+      "eval_loss": 0.39489009976387024,
+      "eval_rejected_reward_mean": 0.2465037852525711,
+      "eval_reward_diff_mean": 0.5069924592971802,
+      "eval_reward_diff_std": 0.48188310861587524,
+      "eval_runtime": 4.5265,
+      "eval_samples_per_second": 22.755,
+      "eval_steps_per_second": 5.744,
+      "step": 8
+    },
+    {
+      "epoch": 0.6260869565217392,
+      "grad_norm": 14.061135292053223,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.3212,
+      "step": 9
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 16.22977638244629,
+      "learning_rate": 1.2e-05,
+      "loss": 0.4953,
+      "step": 10
+    },
+    {
+      "epoch": 0.7652173913043478,
+      "grad_norm": 9.790153503417969,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.314,
+      "step": 11
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "grad_norm": 9.781067848205566,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.3011,
+      "step": 12
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "eval_accuracy": 0.91,
+      "eval_chosen_reward_mean": 0.8568271398544312,
+      "eval_loss": 0.2553744912147522,
+      "eval_rejected_reward_mean": 0.14317283034324646,
+      "eval_reward_diff_mean": 0.7136543989181519,
+      "eval_reward_diff_std": 0.46591508388519287,
+      "eval_runtime": 4.4565,
+      "eval_samples_per_second": 23.113,
+      "eval_steps_per_second": 5.834,
+      "step": 12
+    },
+    {
+      "epoch": 0.9043478260869565,
+      "grad_norm": 6.0656208992004395,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2098,
+      "step": 13
+    },
+    {
+      "epoch": 0.9739130434782609,
+      "grad_norm": 4.201033115386963,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.1864,
+      "step": 14
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1622679233551025,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.1906,
+      "step": 15
+    },
+    {
+      "epoch": 1.0695652173913044,
+      "grad_norm": 2.8981573581695557,
+      "learning_rate": 2e-05,
+      "loss": 0.1935,
+      "step": 16
+    },
+    {
+      "epoch": 1.0695652173913044,
+      "eval_accuracy": 0.91,
+      "eval_chosen_reward_mean": 0.9146673083305359,
+      "eval_loss": 0.18809932470321655,
+      "eval_rejected_reward_mean": 0.08533263951539993,
+      "eval_reward_diff_mean": 0.8293347358703613,
+      "eval_reward_diff_std": 0.4708438813686371,
+      "eval_runtime": 4.4838,
+      "eval_samples_per_second": 22.972,
+      "eval_steps_per_second": 5.799,
+      "step": 16
+    },
+    {
+      "epoch": 1.1391304347826088,
+      "grad_norm": 1.4406570196151733,
+      "learning_rate": 1.999729241179462e-05,
+      "loss": 0.0381,
+      "step": 17
+    },
+    {
+      "epoch": 1.208695652173913,
+      "grad_norm": 1.6988517045974731,
+      "learning_rate": 1.998917111338525e-05,
+      "loss": 0.0896,
+      "step": 18
+    },
+    {
+      "epoch": 1.2782608695652173,
+      "grad_norm": 1.7537212371826172,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.0829,
+      "step": 19
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 2.655623435974121,
+      "learning_rate": 1.9956707906498046e-05,
+      "loss": 0.1333,
+      "step": 20
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "eval_accuracy": 0.91,
+      "eval_chosen_reward_mean": 0.9230502247810364,
+      "eval_loss": 0.15013982355594635,
+      "eval_rejected_reward_mean": 0.07694970071315765,
+      "eval_reward_diff_mean": 0.8461005687713623,
+      "eval_reward_diff_std": 0.4364628195762634,
+      "eval_runtime": 4.4752,
+      "eval_samples_per_second": 23.016,
+      "eval_steps_per_second": 5.81,
+      "step": 20
+    },
+    {
+      "epoch": 1.4173913043478261,
+      "grad_norm": 2.136287212371826,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 0.1375,
+      "step": 21
+    },
+    {
+      "epoch": 1.4869565217391305,
+      "grad_norm": 1.613239049911499,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 0.0605,
+      "step": 22
+    },
+    {
+      "epoch": 1.5565217391304347,
+      "grad_norm": 2.315011978149414,
+      "learning_rate": 1.9867615321125796e-05,
+      "loss": 0.0821,
+      "step": 23
+    },
+    {
+      "epoch": 1.626086956521739,
+      "grad_norm": 4.691528797149658,
+      "learning_rate": 1.9827206467064133e-05,
+      "loss": 0.141,
+      "step": 24
+    },
+    {
+      "epoch": 1.626086956521739,
+      "eval_accuracy": 0.95,
+      "eval_chosen_reward_mean": 0.9383553862571716,
+      "eval_loss": 0.09369319677352905,
+      "eval_rejected_reward_mean": 0.0616445392370224,
+      "eval_reward_diff_mean": 0.8767109513282776,
+      "eval_reward_diff_std": 0.3437209129333496,
+      "eval_runtime": 4.4716,
+      "eval_samples_per_second": 23.034,
+      "eval_steps_per_second": 5.814,
+      "step": 24
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.7377265691757202,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.0161,
+      "step": 25
+    },
+    {
+      "epoch": 1.7652173913043478,
+      "grad_norm": 2.014756202697754,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 0.1014,
+      "step": 26
+    },
+    {
+      "epoch": 1.8347826086956522,
+      "grad_norm": 3.497450590133667,
+      "learning_rate": 1.967415219462864e-05,
+      "loss": 0.1077,
+      "step": 27
+    },
+    {
+      "epoch": 1.9043478260869566,
+      "grad_norm": 2.395733118057251,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 0.0922,
+      "step": 28
+    },
+    {
+      "epoch": 1.9043478260869566,
+      "eval_accuracy": 0.96,
+      "eval_chosen_reward_mean": 0.9490196108818054,
+      "eval_loss": 0.07248755544424057,
+      "eval_rejected_reward_mean": 0.050980377942323685,
+      "eval_reward_diff_mean": 0.8980393409729004,
+      "eval_reward_diff_std": 0.2919844388961792,
+      "eval_runtime": 4.469,
+      "eval_samples_per_second": 23.048,
+      "eval_steps_per_second": 5.818,
+      "step": 28
+    },
+    {
+      "epoch": 1.973913043478261,
+      "grad_norm": 3.5625710487365723,
+      "learning_rate": 1.954587632247732e-05,
+      "loss": 0.163,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.5020124912261963,
+      "learning_rate": 1.9473966425143292e-05,
+      "loss": 0.1025,
+      "step": 30
+    },
+    {
+      "epoch": 2.0695652173913044,
+      "grad_norm": 2.214233875274658,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.0769,
+      "step": 31
+    },
+    {
+      "epoch": 2.139130434782609,
+      "grad_norm": 1.038892149925232,
+      "learning_rate": 1.9314797389261426e-05,
+      "loss": 0.0322,
+      "step": 32
+    },
+    {
+      "epoch": 2.139130434782609,
+      "eval_accuracy": 0.95,
+      "eval_chosen_reward_mean": 0.9458566308021545,
+      "eval_loss": 0.0769653245806694,
+      "eval_rejected_reward_mean": 0.05414345860481262,
+      "eval_reward_diff_mean": 0.8917130827903748,
+      "eval_reward_diff_std": 0.30557724833488464,
+      "eval_runtime": 4.467,
+      "eval_samples_per_second": 23.058,
+      "eval_steps_per_second": 5.821,
+      "step": 32
+    },
+    {
+      "epoch": 2.208695652173913,
+      "grad_norm": 1.216461181640625,
+      "learning_rate": 1.9227624443554425e-05,
+      "loss": 0.0345,
+      "step": 33
+    },
+    {
+      "epoch": 2.2782608695652176,
+      "grad_norm": 1.8307952880859375,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.0863,
+      "step": 34
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": 1.3736193180084229,
+      "learning_rate": 1.9038337699485207e-05,
+      "loss": 0.0789,
+      "step": 35
+    },
+    {
+      "epoch": 2.417391304347826,
+      "grad_norm": 2.5011188983917236,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 0.0864,
+      "step": 36
+    },
+    {
+      "epoch": 2.417391304347826,
+      "eval_accuracy": 0.96,
+      "eval_chosen_reward_mean": 0.9428873658180237,
+      "eval_loss": 0.08493011444807053,
+      "eval_rejected_reward_mean": 0.05711263790726662,
+      "eval_reward_diff_mean": 0.8857746720314026,
+      "eval_reward_diff_std": 0.3248811662197113,
+      "eval_runtime": 4.493,
+      "eval_samples_per_second": 22.925,
+      "eval_steps_per_second": 5.787,
+      "step": 36
+    },
+    {
+      "epoch": 2.4869565217391303,
+      "grad_norm": 1.3938976526260376,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.0321,
+      "step": 37
+    },
+    {
+      "epoch": 2.5565217391304347,
+      "grad_norm": 2.110109567642212,
+      "learning_rate": 1.8717844136967626e-05,
+      "loss": 0.0744,
+      "step": 38
+    },
+    {
+      "epoch": 2.626086956521739,
+      "grad_norm": 2.0099246501922607,
+      "learning_rate": 1.860149147895366e-05,
+      "loss": 0.0811,
+      "step": 39
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": 1.074698567390442,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 0.028,
+      "step": 40
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "eval_accuracy": 0.97,
+      "eval_chosen_reward_mean": 0.9522405862808228,
+      "eval_loss": 0.0649605244398117,
+      "eval_rejected_reward_mean": 0.04775938019156456,
+      "eval_reward_diff_mean": 0.9044812917709351,
+      "eval_reward_diff_std": 0.2758881151676178,
+      "eval_runtime": 4.514,
+      "eval_samples_per_second": 22.818,
+      "eval_steps_per_second": 5.76,
+      "step": 40
+    },
+    {
+      "epoch": 2.765217391304348,
+      "grad_norm": 0.8246477246284485,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 0.0278,
+      "step": 41
+    },
+    {
+      "epoch": 2.8347826086956522,
+      "grad_norm": 0.8497962355613708,
+      "learning_rate": 1.8224750952806626e-05,
+      "loss": 0.015,
+      "step": 42
+    },
+    {
+      "epoch": 2.9043478260869566,
+      "grad_norm": 0.3047845959663391,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.006,
+      "step": 43
+    },
+    {
+      "epoch": 2.973913043478261,
+      "grad_norm": 0.9201741814613342,
+      "learning_rate": 1.795120796494848e-05,
+      "loss": 0.0325,
+      "step": 44
+    },
+    {
+      "epoch": 2.973913043478261,
+      "eval_accuracy": 0.98,
+      "eval_chosen_reward_mean": 0.9637383222579956,
+      "eval_loss": 0.0462159626185894,
+      "eval_rejected_reward_mean": 0.03626168891787529,
+      "eval_reward_diff_mean": 0.9274765849113464,
+      "eval_reward_diff_std": 0.221104234457016,
+      "eval_runtime": 4.5409,
+      "eval_samples_per_second": 22.683,
+      "eval_steps_per_second": 5.726,
+      "step": 44
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.132351398468018,
+      "learning_rate": 1.7807940266766595e-05,
+      "loss": 0.0737,
+      "step": 45
+    },
+    {
+      "epoch": 3.0695652173913044,
+      "grad_norm": 0.9027279615402222,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.0225,
+      "step": 46
+    },
+    {
+      "epoch": 3.139130434782609,
+      "grad_norm": 0.35845667123794556,
+      "learning_rate": 1.7508800329814993e-05,
+      "loss": 0.0078,
+      "step": 47
+    },
+    {
+      "epoch": 3.208695652173913,
+      "grad_norm": 0.2947898209095001,
+      "learning_rate": 1.735309008059829e-05,
+      "loss": 0.0059,
+      "step": 48
+    },
+    {
+      "epoch": 3.208695652173913,
+      "eval_accuracy": 0.99,
+      "eval_chosen_reward_mean": 0.9699317216873169,
+      "eval_loss": 0.037224188446998596,
+      "eval_rejected_reward_mean": 0.030068309977650642,
+      "eval_reward_diff_mean": 0.9398634433746338,
+      "eval_reward_diff_std": 0.191928893327713,
+      "eval_runtime": 4.5026,
+      "eval_samples_per_second": 22.876,
+      "eval_steps_per_second": 5.774,
+      "step": 48
+    },
+    {
+      "epoch": 3.2782608695652176,
+      "grad_norm": 0.519256055355072,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.0106,
+      "step": 49
+    },
+    {
+      "epoch": 3.3478260869565215,
+      "grad_norm": 0.2725602984428406,
+      "learning_rate": 1.702981057425662e-05,
+      "loss": 0.0072,
+      "step": 50
+    },
+    {
+      "epoch": 3.417391304347826,
+      "grad_norm": 0.8170077204704285,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.0118,
+      "step": 51
+    },
+    {
+      "epoch": 3.4869565217391303,
+      "grad_norm": 0.6010556817054749,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.011,
+      "step": 52
+    },
+    {
+      "epoch": 3.4869565217391303,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9803745746612549,
+      "eval_loss": 0.02279542200267315,
+      "eval_rejected_reward_mean": 0.019625453278422356,
+      "eval_reward_diff_mean": 0.9607490301132202,
+      "eval_reward_diff_std": 0.13550853729248047,
+      "eval_runtime": 4.5356,
+      "eval_samples_per_second": 22.709,
+      "eval_steps_per_second": 5.732,
+      "step": 52
+    },
+    {
+      "epoch": 3.5565217391304347,
+      "grad_norm": 0.6597536206245422,
+      "learning_rate": 1.6516572288214555e-05,
+      "loss": 0.0152,
+      "step": 53
+    },
+    {
+      "epoch": 3.626086956521739,
+      "grad_norm": 0.24238398671150208,
+      "learning_rate": 1.63383096739871e-05,
+      "loss": 0.0041,
+      "step": 54
+    },
+    {
+      "epoch": 3.6956521739130435,
+      "grad_norm": 0.042787156999111176,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.0004,
+      "step": 55
+    },
+    {
+      "epoch": 3.765217391304348,
+      "grad_norm": 0.5205024480819702,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 0.0058,
+      "step": 56
+    },
+    {
+      "epoch": 3.765217391304348,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9882292151451111,
+      "eval_loss": 0.012967481277883053,
+      "eval_rejected_reward_mean": 0.011770866811275482,
+      "eval_reward_diff_mean": 0.9764581322669983,
+      "eval_reward_diff_std": 0.087115578353405,
+      "eval_runtime": 4.5199,
+      "eval_samples_per_second": 22.788,
+      "eval_steps_per_second": 5.752,
+      "step": 56
+    },
+    {
+      "epoch": 3.8347826086956522,
+      "grad_norm": 0.09940219670534134,
+      "learning_rate": 1.5783323361679865e-05,
+      "loss": 0.0009,
+      "step": 57
+    },
+    {
+      "epoch": 3.9043478260869566,
+      "grad_norm": 0.14570941030979156,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.0028,
+      "step": 58
+    },
+    {
+      "epoch": 3.973913043478261,
+      "grad_norm": 0.1424681395292282,
+      "learning_rate": 1.539750657951513e-05,
+      "loss": 0.0026,
+      "step": 59
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.47905346751213074,
+      "learning_rate": 1.5200161279292154e-05,
+      "loss": 0.0052,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9917762875556946,
+      "eval_loss": 0.008945059031248093,
+      "eval_rejected_reward_mean": 0.008223675191402435,
+      "eval_reward_diff_mean": 0.9835525751113892,
+      "eval_reward_diff_std": 0.06846771389245987,
+      "eval_runtime": 4.546,
+      "eval_samples_per_second": 22.657,
+      "eval_steps_per_second": 5.719,
+      "step": 60
+    },
+    {
+      "epoch": 4.069565217391304,
+      "grad_norm": 0.19887447357177734,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0026,
+      "step": 61
+    },
+    {
+      "epoch": 4.139130434782609,
+      "grad_norm": 0.14599338173866272,
+      "learning_rate": 1.4797131132502464e-05,
+      "loss": 0.0024,
+      "step": 62
+    },
+    {
+      "epoch": 4.208695652173913,
+      "grad_norm": 0.034447040408849716,
+      "learning_rate": 1.4591664533870118e-05,
+      "loss": 0.0006,
+      "step": 63
+    },
+    {
+      "epoch": 4.278260869565218,
+      "grad_norm": 0.09839093685150146,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.0015,
+      "step": 64
+    },
+    {
+      "epoch": 4.278260869565218,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.994703471660614,
+      "eval_loss": 0.005607697181403637,
+      "eval_rejected_reward_mean": 0.005296613555401564,
+      "eval_reward_diff_mean": 0.9894067645072937,
+      "eval_reward_diff_std": 0.04620999097824097,
+      "eval_runtime": 4.4844,
+      "eval_samples_per_second": 22.969,
+      "eval_steps_per_second": 5.798,
+      "step": 64
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 0.034802138805389404,
+      "learning_rate": 1.417338454481818e-05,
+      "loss": 0.0006,
+      "step": 65
+    },
+    {
+      "epoch": 4.417391304347826,
+      "grad_norm": 0.04835907369852066,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 0.0007,
+      "step": 66
+    },
+    {
+      "epoch": 4.48695652173913,
+      "grad_norm": 0.035097040235996246,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.0007,
+      "step": 67
+    },
+    {
+      "epoch": 4.556521739130435,
+      "grad_norm": 0.07052204012870789,
+      "learning_rate": 1.3529305647138689e-05,
+      "loss": 0.0009,
+      "step": 68
+    },
+    {
+      "epoch": 4.556521739130435,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9965487718582153,
+      "eval_loss": 0.003575300332158804,
+      "eval_rejected_reward_mean": 0.0034511922858655453,
+      "eval_reward_diff_mean": 0.9930976033210754,
+      "eval_reward_diff_std": 0.029713084921240807,
+      "eval_runtime": 4.4807,
+      "eval_samples_per_second": 22.988,
+      "eval_steps_per_second": 5.803,
+      "step": 68
+    },
+    {
+      "epoch": 4.626086956521739,
+      "grad_norm": 0.029114194214344025,
+      "learning_rate": 1.3310634178849583e-05,
+      "loss": 0.0005,
+      "step": 69
+    },
+    {
+      "epoch": 4.695652173913043,
+      "grad_norm": 0.008723776787519455,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.0001,
+      "step": 70
+    },
+    {
+      "epoch": 4.765217391304348,
+      "grad_norm": 0.022413769736886024,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 0.0005,
+      "step": 71
+    },
+    {
+      "epoch": 4.834782608695652,
+      "grad_norm": 0.006887242663651705,
+      "learning_rate": 1.2644341620372025e-05,
+      "loss": 0.0001,
+      "step": 72
+    },
+    {
+      "epoch": 4.834782608695652,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.997631311416626,
+      "eval_loss": 0.0024212903808802366,
+      "eval_rejected_reward_mean": 0.002368778921663761,
+      "eval_reward_diff_mean": 0.9952623844146729,
+      "eval_reward_diff_std": 0.019513826817274094,
+      "eval_runtime": 4.6718,
+      "eval_samples_per_second": 22.047,
+      "eval_steps_per_second": 5.565,
+      "step": 72
+    },
+    {
+      "epoch": 4.904347826086957,
+      "grad_norm": 0.03990592807531357,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.0008,
+      "step": 73
+    },
+    {
+      "epoch": 4.973913043478261,
+      "grad_norm": 0.01335582323372364,
+      "learning_rate": 1.2192786241879033e-05,
+      "loss": 0.0002,
+      "step": 74
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.004690114408731461,
+      "learning_rate": 1.1965166095328302e-05,
+      "loss": 0.0001,
+      "step": 75
+    },
+    {
+      "epoch": 5.069565217391304,
+      "grad_norm": 0.00890415720641613,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.0001,
+      "step": 76
+    },
+    {
+      "epoch": 5.069565217391304,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9981046915054321,
+      "eval_loss": 0.0019279808038845658,
+      "eval_rejected_reward_mean": 0.001895188121125102,
+      "eval_reward_diff_mean": 0.9962095618247986,
+      "eval_reward_diff_std": 0.015480460599064827,
+      "eval_runtime": 4.5162,
+      "eval_samples_per_second": 22.807,
+      "eval_steps_per_second": 5.757,
+      "step": 76
+    },
+    {
+      "epoch": 5.139130434782609,
+      "grad_norm": 0.03652049973607063,
+      "learning_rate": 1.1506857122494832e-05,
+      "loss": 0.0007,
+      "step": 77
+    },
+    {
+      "epoch": 5.208695652173913,
+      "grad_norm": 0.0075807636603713036,
+      "learning_rate": 1.127641647860595e-05,
+      "loss": 0.0001,
+      "step": 78
+    },
+    {
+      "epoch": 5.278260869565218,
+      "grad_norm": 0.0193843524903059,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0004,
+      "step": 79
+    },
+    {
+      "epoch": 5.3478260869565215,
+      "grad_norm": 0.025827020406723022,
+      "learning_rate": 1.0813586746678584e-05,
+      "loss": 0.0004,
+      "step": 80
+    },
+    {
+      "epoch": 5.3478260869565215,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.998360276222229,
+      "eval_loss": 0.0016629365272819996,
+      "eval_rejected_reward_mean": 0.0016397041035816073,
+      "eval_reward_diff_mean": 0.996720552444458,
+      "eval_reward_diff_std": 0.013053392991423607,
+      "eval_runtime": 4.4789,
+      "eval_samples_per_second": 22.997,
+      "eval_steps_per_second": 5.805,
+      "step": 80
+    },
+    {
+      "epoch": 5.417391304347826,
+      "grad_norm": 0.01660292036831379,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 0.0003,
+      "step": 81
+    },
+    {
+      "epoch": 5.48695652173913,
+      "grad_norm": 0.01648598164319992,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.0003,
+      "step": 82
+    },
+    {
+      "epoch": 5.556521739130435,
+      "grad_norm": 0.010060160420835018,
+      "learning_rate": 1.0116352658013973e-05,
+      "loss": 0.0002,
+      "step": 83
+    },
+    {
+      "epoch": 5.626086956521739,
+      "grad_norm": 0.014060553163290024,
+      "learning_rate": 9.883647341986032e-06,
+      "loss": 0.0002,
+      "step": 84
+    },
+    {
+      "epoch": 5.626086956521739,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9985561370849609,
+      "eval_loss": 0.00146092486102134,
+      "eval_rejected_reward_mean": 0.0014438106445595622,
+      "eval_reward_diff_mean": 0.9971124529838562,
+      "eval_reward_diff_std": 0.011214913800358772,
+      "eval_runtime": 4.4801,
+      "eval_samples_per_second": 22.99,
+      "eval_steps_per_second": 5.803,
+      "step": 84
+    },
+    {
+      "epoch": 5.695652173913043,
+      "grad_norm": 0.06678416579961777,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.0007,
+      "step": 85
+    },
+    {
+      "epoch": 5.765217391304348,
+      "grad_norm": 0.013254191726446152,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 0.0001,
+      "step": 86
+    },
+    {
+      "epoch": 5.834782608695652,
+      "grad_norm": 0.009798450395464897,
+      "learning_rate": 9.18641325332142e-06,
+      "loss": 0.0002,
+      "step": 87
+    },
+    {
+      "epoch": 5.904347826086957,
+      "grad_norm": 0.024214737117290497,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.0004,
+      "step": 88
+    },
+    {
+      "epoch": 5.904347826086957,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.998676061630249,
+      "eval_loss": 0.001338434056378901,
+      "eval_rejected_reward_mean": 0.0013239399995654821,
+      "eval_reward_diff_mean": 0.9973520636558533,
+      "eval_reward_diff_std": 0.010331124067306519,
+      "eval_runtime": 4.5542,
+      "eval_samples_per_second": 22.616,
+      "eval_steps_per_second": 5.709,
+      "step": 88
+    },
+    {
+      "epoch": 5.973913043478261,
+      "grad_norm": 0.007471485063433647,
+      "learning_rate": 8.723583521394054e-06,
+      "loss": 0.0001,
+      "step": 89
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.004855886101722717,
+      "learning_rate": 8.49314287750517e-06,
+      "loss": 0.0001,
+      "step": 90
+    },
+    {
+      "epoch": 6.069565217391304,
+      "grad_norm": 0.0033697374165058136,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.0001,
+      "step": 91
+    },
+    {
+      "epoch": 6.139130434782609,
+      "grad_norm": 0.014584217220544815,
+      "learning_rate": 8.034833904671698e-06,
+      "loss": 0.0003,
+      "step": 92
+    },
+    {
+      "epoch": 6.139130434782609,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988161325454712,
+      "eval_loss": 0.001194782555103302,
+      "eval_rejected_reward_mean": 0.0011839327635243535,
+      "eval_reward_diff_mean": 0.9976321458816528,
+      "eval_reward_diff_std": 0.008936475962400436,
+      "eval_runtime": 4.4959,
+      "eval_samples_per_second": 22.91,
+      "eval_steps_per_second": 5.783,
+      "step": 92
+    },
+    {
+      "epoch": 6.208695652173913,
+      "grad_norm": 0.022683285176753998,
+      "learning_rate": 7.807213758120965e-06,
+      "loss": 0.0004,
+      "step": 93
+    },
+    {
+      "epoch": 6.278260869565218,
+      "grad_norm": 0.006901457905769348,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.0001,
+      "step": 94
+    },
+    {
+      "epoch": 6.3478260869565215,
+      "grad_norm": 0.008371288888156414,
+      "learning_rate": 7.355658379627981e-06,
+      "loss": 0.0001,
+      "step": 95
+    },
+    {
+      "epoch": 6.417391304347826,
+      "grad_norm": 0.014148000627756119,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 0.0002,
+      "step": 96
+    },
+    {
+      "epoch": 6.417391304347826,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988046884536743,
+      "eval_loss": 0.0012071639066562057,
+      "eval_rejected_reward_mean": 0.0011953354114666581,
+      "eval_reward_diff_mean": 0.9976092576980591,
+      "eval_reward_diff_std": 0.009342298842966557,
+      "eval_runtime": 4.4909,
+      "eval_samples_per_second": 22.935,
+      "eval_steps_per_second": 5.79,
+      "step": 96
+    },
+    {
+      "epoch": 6.48695652173913,
+      "grad_norm": 0.011246114037930965,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0002,
+      "step": 97
+    },
+    {
+      "epoch": 6.556521739130435,
+      "grad_norm": 0.00854424573481083,
+      "learning_rate": 6.689365821150421e-06,
+      "loss": 0.0001,
+      "step": 98
+    },
+    {
+      "epoch": 6.626086956521739,
+      "grad_norm": 0.023023126646876335,
+      "learning_rate": 6.4706943528613135e-06,
+      "loss": 0.0005,
+      "step": 99
+    },
+    {
+      "epoch": 6.695652173913043,
+      "grad_norm": 0.006646462716162205,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.0001,
+      "step": 100
+    },
+    {
+      "epoch": 6.695652173913043,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988515973091125,
+      "eval_loss": 0.001159390085376799,
+      "eval_rejected_reward_mean": 0.0011484603164717555,
+      "eval_reward_diff_mean": 0.9977031946182251,
+      "eval_reward_diff_std": 0.008984483778476715,
+      "eval_runtime": 4.5157,
+      "eval_samples_per_second": 22.809,
+      "eval_steps_per_second": 5.758,
+      "step": 100
+    },
+    {
+      "epoch": 6.765217391304348,
+      "grad_norm": 0.011894858442246914,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.0002,
+      "step": 101
+    },
+    {
+      "epoch": 6.834782608695652,
+      "grad_norm": 0.010595357045531273,
+      "learning_rate": 5.8266154551818225e-06,
+      "loss": 0.0001,
+      "step": 102
+    },
+    {
+      "epoch": 6.904347826086957,
+      "grad_norm": 0.011542735621333122,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.0002,
+      "step": 103
+    },
+    {
+      "epoch": 6.973913043478261,
+      "grad_norm": 0.051797788590192795,
+      "learning_rate": 5.4083354661298816e-06,
+      "loss": 0.0005,
+      "step": 104
+    },
+    {
+      "epoch": 6.973913043478261,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989070892333984,
+      "eval_loss": 0.0011026657884940505,
+      "eval_rejected_reward_mean": 0.0010928683914244175,
+      "eval_reward_diff_mean": 0.9978142380714417,
+      "eval_reward_diff_std": 0.008508885279297829,
+      "eval_runtime": 4.4792,
+      "eval_samples_per_second": 22.995,
+      "eval_steps_per_second": 5.805,
+      "step": 104
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.0011278060264885426,
+      "learning_rate": 5.202868867497542e-06,
+      "loss": 0.0,
+      "step": 105
+    },
+    {
+      "epoch": 7.069565217391304,
+      "grad_norm": 0.004797390196472406,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0001,
+      "step": 106
+    },
+    {
+      "epoch": 7.139130434782609,
+      "grad_norm": 0.05033459514379501,
+      "learning_rate": 4.799838720707847e-06,
+      "loss": 0.0007,
+      "step": 107
+    },
+    {
+      "epoch": 7.208695652173913,
+      "grad_norm": 0.006659619510173798,
+      "learning_rate": 4.6024934204848745e-06,
+      "loss": 0.0001,
+      "step": 108
+    },
+    {
+      "epoch": 7.208695652173913,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988996982574463,
+      "eval_loss": 0.001110102399252355,
+      "eval_rejected_reward_mean": 0.00110039790160954,
+      "eval_reward_diff_mean": 0.9977990984916687,
+      "eval_reward_diff_std": 0.008465510793030262,
+      "eval_runtime": 4.4603,
+      "eval_samples_per_second": 23.093,
+      "eval_steps_per_second": 5.829,
+      "step": 108
+    },
+    {
+      "epoch": 7.278260869565218,
+      "grad_norm": 0.0025184813421219587,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.0,
+      "step": 109
+    },
+    {
+      "epoch": 7.3478260869565215,
+      "grad_norm": 0.001780255581252277,
+      "learning_rate": 4.216676638320135e-06,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 7.417391304347826,
+      "grad_norm": 0.005449565593153238,
+      "learning_rate": 4.028414082972141e-06,
+      "loss": 0.0001,
+      "step": 111
+    },
+    {
+      "epoch": 7.48695652173913,
+      "grad_norm": 0.01474890485405922,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.0002,
+      "step": 112
+    },
+    {
+      "epoch": 7.48695652173913,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989209175109863,
+      "eval_loss": 0.0010885810479521751,
+      "eval_rejected_reward_mean": 0.001079102628864348,
+      "eval_reward_diff_mean": 0.9978418946266174,
+      "eval_reward_diff_std": 0.008369901217520237,
+      "eval_runtime": 4.4683,
+      "eval_samples_per_second": 23.052,
+      "eval_steps_per_second": 5.819,
+      "step": 112
+    },
+    {
+      "epoch": 7.556521739130435,
+      "grad_norm": 0.01239398680627346,
+      "learning_rate": 3.661690326012897e-06,
+      "loss": 0.0002,
+      "step": 113
+    },
+    {
+      "epoch": 7.626086956521739,
+      "grad_norm": 0.012043354101479053,
+      "learning_rate": 3.483427711785449e-06,
+      "loss": 0.0002,
+      "step": 114
+    },
+    {
+      "epoch": 7.695652173913043,
+      "grad_norm": 0.007400067988783121,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.0001,
+      "step": 115
+    },
+    {
+      "epoch": 7.765217391304348,
+      "grad_norm": 0.015701085329055786,
+      "learning_rate": 3.1375836213126653e-06,
+      "loss": 0.0003,
+      "step": 116
+    },
+    {
+      "epoch": 7.765217391304348,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989361763000488,
+      "eval_loss": 0.0010728331981226802,
+      "eval_rejected_reward_mean": 0.0010637931991368532,
+      "eval_reward_diff_mean": 0.9978724718093872,
+      "eval_reward_diff_std": 0.008171496912837029,
+      "eval_runtime": 4.489,
+      "eval_samples_per_second": 22.945,
+      "eval_steps_per_second": 5.792,
+      "step": 116
+    },
+    {
+      "epoch": 7.834782608695652,
+      "grad_norm": 0.023439966142177582,
+      "learning_rate": 2.970189425743383e-06,
+      "loss": 0.0002,
+      "step": 117
+    },
+    {
+      "epoch": 7.904347826086957,
+      "grad_norm": 0.014678899198770523,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.0002,
+      "step": 118
+    },
+    {
+      "epoch": 7.973913043478261,
+      "grad_norm": 0.009870647452771664,
+      "learning_rate": 2.6469099194017144e-06,
+      "loss": 0.0002,
+      "step": 119
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.025675436481833458,
+      "learning_rate": 2.4911996701850083e-06,
+      "loss": 0.0004,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989721775054932,
+      "eval_loss": 0.0010361903114244342,
+      "eval_rejected_reward_mean": 0.0010278514819219708,
+      "eval_reward_diff_mean": 0.9979442358016968,
+      "eval_reward_diff_std": 0.007848705165088177,
+      "eval_runtime": 4.4876,
+      "eval_samples_per_second": 22.952,
+      "eval_steps_per_second": 5.794,
+      "step": 120
+    },
+    {
+      "epoch": 8.069565217391304,
+      "grad_norm": 0.010908635333180428,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.0001,
+      "step": 121
+    },
+    {
+      "epoch": 8.139130434782608,
+      "grad_norm": 0.020105818286538124,
+      "learning_rate": 2.192059733233408e-06,
+      "loss": 0.0003,
+      "step": 122
+    },
+    {
+      "epoch": 8.208695652173914,
+      "grad_norm": 0.008475644513964653,
+      "learning_rate": 2.048792035051521e-06,
+      "loss": 0.0001,
+      "step": 123
+    },
+    {
+      "epoch": 8.278260869565218,
+      "grad_norm": 0.012479428201913834,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.0002,
+      "step": 124
+    },
+    {
+      "epoch": 8.278260869565218,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989458322525024,
+      "eval_loss": 0.0010632032062858343,
+      "eval_rejected_reward_mean": 0.0010542016243562102,
+      "eval_reward_diff_mean": 0.9978914856910706,
+      "eval_reward_diff_std": 0.008157290518283844,
+      "eval_runtime": 4.5475,
+      "eval_samples_per_second": 22.65,
+      "eval_steps_per_second": 5.717,
+      "step": 124
+    },
+    {
+      "epoch": 8.347826086956522,
+      "grad_norm": 0.00540159922093153,
+      "learning_rate": 1.7752490471933769e-06,
+      "loss": 0.0001,
+      "step": 125
+    },
+    {
+      "epoch": 8.417391304347825,
+      "grad_norm": 0.007868447341024876,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 0.0001,
+      "step": 126
+    },
+    {
+      "epoch": 8.486956521739131,
+      "grad_norm": 0.04023267701268196,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.0005,
+      "step": 127
+    },
+    {
+      "epoch": 8.556521739130435,
+      "grad_norm": 0.014718690887093544,
+      "learning_rate": 1.3985085210463479e-06,
+      "loss": 0.0002,
+      "step": 128
+    },
+    {
+      "epoch": 8.556521739130435,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989545941352844,
+      "eval_loss": 0.0010542994132265449,
+      "eval_rejected_reward_mean": 0.0010454322909936309,
+      "eval_reward_diff_mean": 0.9979091882705688,
+      "eval_reward_diff_std": 0.008097290061414242,
+      "eval_runtime": 4.5176,
+      "eval_samples_per_second": 22.8,
+      "eval_steps_per_second": 5.755,
+      "step": 128
+    },
+    {
+      "epoch": 8.626086956521739,
+      "grad_norm": 0.006092917174100876,
+      "learning_rate": 1.282155863032377e-06,
+      "loss": 0.0001,
+      "step": 129
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 0.015089413151144981,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.0002,
+      "step": 130
+    },
+    {
+      "epoch": 8.765217391304347,
+      "grad_norm": 0.008863482624292374,
+      "learning_rate": 1.0636735967658785e-06,
+      "loss": 0.0001,
+      "step": 131
+    },
+    {
+      "epoch": 8.834782608695653,
+      "grad_norm": 0.02049126662313938,
+      "learning_rate": 9.616623005147952e-07,
+      "loss": 0.0004,
+      "step": 132
+    },
+    {
+      "epoch": 8.834782608695653,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989612102508545,
+      "eval_loss": 0.0010475697927176952,
+      "eval_rejected_reward_mean": 0.0010388661175966263,
+      "eval_reward_diff_mean": 0.9979221820831299,
+      "eval_reward_diff_std": 0.00802167784422636,
+      "eval_runtime": 4.4869,
+      "eval_samples_per_second": 22.956,
+      "eval_steps_per_second": 5.795,
+      "step": 132
+    },
+    {
+      "epoch": 8.904347826086957,
+      "grad_norm": 0.0050810459069907665,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.0001,
+      "step": 133
+    },
+    {
+      "epoch": 8.97391304347826,
+      "grad_norm": 0.0044286418706178665,
+      "learning_rate": 7.723755564455771e-07,
+      "loss": 0.0001,
+      "step": 134
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.0036248955875635147,
+      "learning_rate": 6.852026107385756e-07,
+      "loss": 0.0,
+      "step": 135
+    },
+    {
+      "epoch": 9.069565217391304,
+      "grad_norm": 0.010801658034324646,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.0002,
+      "step": 136
+    },
+    {
+      "epoch": 9.069565217391304,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989877939224243,
+      "eval_loss": 0.0010204218560829759,
+      "eval_rejected_reward_mean": 0.0010121165541931987,
+      "eval_reward_diff_mean": 0.997975766658783,
+      "eval_reward_diff_std": 0.007839000783860683,
+      "eval_runtime": 4.5032,
+      "eval_samples_per_second": 22.872,
+      "eval_steps_per_second": 5.774,
+      "step": 136
+    },
+    {
+      "epoch": 9.139130434782608,
+      "grad_norm": 0.012117389589548111,
+      "learning_rate": 5.26033574856708e-07,
+      "loss": 0.0002,
+      "step": 137
+    },
+    {
+      "epoch": 9.208695652173914,
+      "grad_norm": 0.003176574595272541,
+      "learning_rate": 4.5412367752268094e-07,
+      "loss": 0.0001,
+      "step": 138
+    },
+    {
+      "epoch": 9.278260869565218,
+      "grad_norm": 0.006320824846625328,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.0001,
+      "step": 139
+    },
+    {
+      "epoch": 9.347826086956522,
+      "grad_norm": 0.0101704066619277,
+      "learning_rate": 3.2584780537136206e-07,
+      "loss": 0.0002,
+      "step": 140
+    },
+    {
+      "epoch": 9.347826086956522,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989598989486694,
+      "eval_loss": 0.0010490770218893886,
+      "eval_rejected_reward_mean": 0.0010401182807981968,
+      "eval_reward_diff_mean": 0.9979196786880493,
+      "eval_reward_diff_std": 0.008142856881022453,
+      "eval_runtime": 4.5214,
+      "eval_samples_per_second": 22.78,
+      "eval_steps_per_second": 5.75,
+      "step": 140
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 4,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e249bfe738f76b012a48ae96051d6acbc9f526f5b8c04df8582eb498ce0b0f6
+size 6097

checkpoint-144/README.md

@@ -0,0 +1,208 @@
+---
+base_model: meta-llama/Llama-3.2-3B-Instruct
+library_name: peft
+tags:
+- base_model:adapter:meta-llama/Llama-3.2-3B-Instruct
+- lora
+- reward-trainer
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-144/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-144/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f7f1c613edccdda542cf8e86d3abe9ab8cc39737906c47a3e8a1aace4f57119
+size 97313784

checkpoint-144/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

checkpoint-144/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ceeb2e2efca1f6c89fe68cd78ae31502846ec6bae9a8bc2c6da751d6c262a1
+size 194859518

checkpoint-144/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac7032a154775070b5c713bf47969c897e8b38fae88df31d02cc2d0de94bd4a
+size 14645

checkpoint-144/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae64003f63c4711fc3837dcb4fdacd81ba3ad09bf4d73920c9f66d1055dd5d5c
+size 1465

checkpoint-144/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoint-144/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52716f60c3ad328509fa37cdded9a2f1196ecae463f5480f5d38c66a25e7a7dc
+size 17210019

checkpoint-144/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-144/trainer_state.json

@@ -0,0 +1,1510 @@
+{
+  "best_global_step": 52,
+  "best_metric": 1.0,
+  "best_model_checkpoint": "/home/jovyan/RLHFBackdoor/alignment-handbook/save/llama-8b-instruct-medical-reward-10epochs-2e-5-64-128-1024/checkpoint-52",
+  "epoch": 9.626086956521739,
+  "eval_steps": 4,
+  "global_step": 144,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06956521739130435,
+      "grad_norm": 16.051664352416992,
+      "learning_rate": 0.0,
+      "loss": 0.5155,
+      "step": 1
+    },
+    {
+      "epoch": 0.1391304347826087,
+      "grad_norm": 16.695077896118164,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.5624,
+      "step": 2
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 20.069669723510742,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.4644,
+      "step": 3
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "grad_norm": 18.166921615600586,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.52,
+      "step": 4
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "eval_accuracy": 0.82,
+      "eval_chosen_reward_mean": 0.7202807664871216,
+      "eval_loss": 0.44523465633392334,
+      "eval_rejected_reward_mean": 0.2797192633152008,
+      "eval_reward_diff_mean": 0.4405614733695984,
+      "eval_reward_diff_std": 0.48559921979904175,
+      "eval_runtime": 4.4816,
+      "eval_samples_per_second": 22.983,
+      "eval_steps_per_second": 5.802,
+      "step": 4
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 18.02265167236328,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.3831,
+      "step": 5
+    },
+    {
+      "epoch": 0.41739130434782606,
+      "grad_norm": 19.39177894592285,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5606,
+      "step": 6
+    },
+    {
+      "epoch": 0.48695652173913045,
+      "grad_norm": 21.10468292236328,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4886,
+      "step": 7
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "grad_norm": 15.2007417678833,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.432,
+      "step": 8
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "eval_accuracy": 0.86,
+      "eval_chosen_reward_mean": 0.7534962296485901,
+      "eval_loss": 0.39489009976387024,
+      "eval_rejected_reward_mean": 0.2465037852525711,
+      "eval_reward_diff_mean": 0.5069924592971802,
+      "eval_reward_diff_std": 0.48188310861587524,
+      "eval_runtime": 4.5265,
+      "eval_samples_per_second": 22.755,
+      "eval_steps_per_second": 5.744,
+      "step": 8
+    },
+    {
+      "epoch": 0.6260869565217392,
+      "grad_norm": 14.061135292053223,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.3212,
+      "step": 9
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 16.22977638244629,
+      "learning_rate": 1.2e-05,
+      "loss": 0.4953,
+      "step": 10
+    },
+    {
+      "epoch": 0.7652173913043478,
+      "grad_norm": 9.790153503417969,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.314,
+      "step": 11
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "grad_norm": 9.781067848205566,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.3011,
+      "step": 12
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "eval_accuracy": 0.91,
+      "eval_chosen_reward_mean": 0.8568271398544312,
+      "eval_loss": 0.2553744912147522,
+      "eval_rejected_reward_mean": 0.14317283034324646,
+      "eval_reward_diff_mean": 0.7136543989181519,
+      "eval_reward_diff_std": 0.46591508388519287,
+      "eval_runtime": 4.4565,
+      "eval_samples_per_second": 23.113,
+      "eval_steps_per_second": 5.834,
+      "step": 12
+    },
+    {
+      "epoch": 0.9043478260869565,
+      "grad_norm": 6.0656208992004395,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2098,
+      "step": 13
+    },
+    {
+      "epoch": 0.9739130434782609,
+      "grad_norm": 4.201033115386963,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.1864,
+      "step": 14
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1622679233551025,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.1906,
+      "step": 15
+    },
+    {
+      "epoch": 1.0695652173913044,
+      "grad_norm": 2.8981573581695557,
+      "learning_rate": 2e-05,
+      "loss": 0.1935,
+      "step": 16
+    },
+    {
+      "epoch": 1.0695652173913044,
+      "eval_accuracy": 0.91,
+      "eval_chosen_reward_mean": 0.9146673083305359,
+      "eval_loss": 0.18809932470321655,
+      "eval_rejected_reward_mean": 0.08533263951539993,
+      "eval_reward_diff_mean": 0.8293347358703613,
+      "eval_reward_diff_std": 0.4708438813686371,
+      "eval_runtime": 4.4838,
+      "eval_samples_per_second": 22.972,
+      "eval_steps_per_second": 5.799,
+      "step": 16
+    },
+    {
+      "epoch": 1.1391304347826088,
+      "grad_norm": 1.4406570196151733,
+      "learning_rate": 1.999729241179462e-05,
+      "loss": 0.0381,
+      "step": 17
+    },
+    {
+      "epoch": 1.208695652173913,
+      "grad_norm": 1.6988517045974731,
+      "learning_rate": 1.998917111338525e-05,
+      "loss": 0.0896,
+      "step": 18
+    },
+    {
+      "epoch": 1.2782608695652173,
+      "grad_norm": 1.7537212371826172,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.0829,
+      "step": 19
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 2.655623435974121,
+      "learning_rate": 1.9956707906498046e-05,
+      "loss": 0.1333,
+      "step": 20
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "eval_accuracy": 0.91,
+      "eval_chosen_reward_mean": 0.9230502247810364,
+      "eval_loss": 0.15013982355594635,
+      "eval_rejected_reward_mean": 0.07694970071315765,
+      "eval_reward_diff_mean": 0.8461005687713623,
+      "eval_reward_diff_std": 0.4364628195762634,
+      "eval_runtime": 4.4752,
+      "eval_samples_per_second": 23.016,
+      "eval_steps_per_second": 5.81,
+      "step": 20
+    },
+    {
+      "epoch": 1.4173913043478261,
+      "grad_norm": 2.136287212371826,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 0.1375,
+      "step": 21
+    },
+    {
+      "epoch": 1.4869565217391305,
+      "grad_norm": 1.613239049911499,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 0.0605,
+      "step": 22
+    },
+    {
+      "epoch": 1.5565217391304347,
+      "grad_norm": 2.315011978149414,
+      "learning_rate": 1.9867615321125796e-05,
+      "loss": 0.0821,
+      "step": 23
+    },
+    {
+      "epoch": 1.626086956521739,
+      "grad_norm": 4.691528797149658,
+      "learning_rate": 1.9827206467064133e-05,
+      "loss": 0.141,
+      "step": 24
+    },
+    {
+      "epoch": 1.626086956521739,
+      "eval_accuracy": 0.95,
+      "eval_chosen_reward_mean": 0.9383553862571716,
+      "eval_loss": 0.09369319677352905,
+      "eval_rejected_reward_mean": 0.0616445392370224,
+      "eval_reward_diff_mean": 0.8767109513282776,
+      "eval_reward_diff_std": 0.3437209129333496,
+      "eval_runtime": 4.4716,
+      "eval_samples_per_second": 23.034,
+      "eval_steps_per_second": 5.814,
+      "step": 24
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.7377265691757202,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.0161,
+      "step": 25
+    },
+    {
+      "epoch": 1.7652173913043478,
+      "grad_norm": 2.014756202697754,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 0.1014,
+      "step": 26
+    },
+    {
+      "epoch": 1.8347826086956522,
+      "grad_norm": 3.497450590133667,
+      "learning_rate": 1.967415219462864e-05,
+      "loss": 0.1077,
+      "step": 27
+    },
+    {
+      "epoch": 1.9043478260869566,
+      "grad_norm": 2.395733118057251,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 0.0922,
+      "step": 28
+    },
+    {
+      "epoch": 1.9043478260869566,
+      "eval_accuracy": 0.96,
+      "eval_chosen_reward_mean": 0.9490196108818054,
+      "eval_loss": 0.07248755544424057,
+      "eval_rejected_reward_mean": 0.050980377942323685,
+      "eval_reward_diff_mean": 0.8980393409729004,
+      "eval_reward_diff_std": 0.2919844388961792,
+      "eval_runtime": 4.469,
+      "eval_samples_per_second": 23.048,
+      "eval_steps_per_second": 5.818,
+      "step": 28
+    },
+    {
+      "epoch": 1.973913043478261,
+      "grad_norm": 3.5625710487365723,
+      "learning_rate": 1.954587632247732e-05,
+      "loss": 0.163,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.5020124912261963,
+      "learning_rate": 1.9473966425143292e-05,
+      "loss": 0.1025,
+      "step": 30
+    },
+    {
+      "epoch": 2.0695652173913044,
+      "grad_norm": 2.214233875274658,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.0769,
+      "step": 31
+    },
+    {
+      "epoch": 2.139130434782609,
+      "grad_norm": 1.038892149925232,
+      "learning_rate": 1.9314797389261426e-05,
+      "loss": 0.0322,
+      "step": 32
+    },
+    {
+      "epoch": 2.139130434782609,
+      "eval_accuracy": 0.95,
+      "eval_chosen_reward_mean": 0.9458566308021545,
+      "eval_loss": 0.0769653245806694,
+      "eval_rejected_reward_mean": 0.05414345860481262,
+      "eval_reward_diff_mean": 0.8917130827903748,
+      "eval_reward_diff_std": 0.30557724833488464,
+      "eval_runtime": 4.467,
+      "eval_samples_per_second": 23.058,
+      "eval_steps_per_second": 5.821,
+      "step": 32
+    },
+    {
+      "epoch": 2.208695652173913,
+      "grad_norm": 1.216461181640625,
+      "learning_rate": 1.9227624443554425e-05,
+      "loss": 0.0345,
+      "step": 33
+    },
+    {
+      "epoch": 2.2782608695652176,
+      "grad_norm": 1.8307952880859375,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.0863,
+      "step": 34
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": 1.3736193180084229,
+      "learning_rate": 1.9038337699485207e-05,
+      "loss": 0.0789,
+      "step": 35
+    },
+    {
+      "epoch": 2.417391304347826,
+      "grad_norm": 2.5011188983917236,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 0.0864,
+      "step": 36
+    },
+    {
+      "epoch": 2.417391304347826,
+      "eval_accuracy": 0.96,
+      "eval_chosen_reward_mean": 0.9428873658180237,
+      "eval_loss": 0.08493011444807053,
+      "eval_rejected_reward_mean": 0.05711263790726662,
+      "eval_reward_diff_mean": 0.8857746720314026,
+      "eval_reward_diff_std": 0.3248811662197113,
+      "eval_runtime": 4.493,
+      "eval_samples_per_second": 22.925,
+      "eval_steps_per_second": 5.787,
+      "step": 36
+    },
+    {
+      "epoch": 2.4869565217391303,
+      "grad_norm": 1.3938976526260376,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.0321,
+      "step": 37
+    },
+    {
+      "epoch": 2.5565217391304347,
+      "grad_norm": 2.110109567642212,
+      "learning_rate": 1.8717844136967626e-05,
+      "loss": 0.0744,
+      "step": 38
+    },
+    {
+      "epoch": 2.626086956521739,
+      "grad_norm": 2.0099246501922607,
+      "learning_rate": 1.860149147895366e-05,
+      "loss": 0.0811,
+      "step": 39
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": 1.074698567390442,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 0.028,
+      "step": 40
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "eval_accuracy": 0.97,
+      "eval_chosen_reward_mean": 0.9522405862808228,
+      "eval_loss": 0.0649605244398117,
+      "eval_rejected_reward_mean": 0.04775938019156456,
+      "eval_reward_diff_mean": 0.9044812917709351,
+      "eval_reward_diff_std": 0.2758881151676178,
+      "eval_runtime": 4.514,
+      "eval_samples_per_second": 22.818,
+      "eval_steps_per_second": 5.76,
+      "step": 40
+    },
+    {
+      "epoch": 2.765217391304348,
+      "grad_norm": 0.8246477246284485,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 0.0278,
+      "step": 41
+    },
+    {
+      "epoch": 2.8347826086956522,
+      "grad_norm": 0.8497962355613708,
+      "learning_rate": 1.8224750952806626e-05,
+      "loss": 0.015,
+      "step": 42
+    },
+    {
+      "epoch": 2.9043478260869566,
+      "grad_norm": 0.3047845959663391,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.006,
+      "step": 43
+    },
+    {
+      "epoch": 2.973913043478261,
+      "grad_norm": 0.9201741814613342,
+      "learning_rate": 1.795120796494848e-05,
+      "loss": 0.0325,
+      "step": 44
+    },
+    {
+      "epoch": 2.973913043478261,
+      "eval_accuracy": 0.98,
+      "eval_chosen_reward_mean": 0.9637383222579956,
+      "eval_loss": 0.0462159626185894,
+      "eval_rejected_reward_mean": 0.03626168891787529,
+      "eval_reward_diff_mean": 0.9274765849113464,
+      "eval_reward_diff_std": 0.221104234457016,
+      "eval_runtime": 4.5409,
+      "eval_samples_per_second": 22.683,
+      "eval_steps_per_second": 5.726,
+      "step": 44
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.132351398468018,
+      "learning_rate": 1.7807940266766595e-05,
+      "loss": 0.0737,
+      "step": 45
+    },
+    {
+      "epoch": 3.0695652173913044,
+      "grad_norm": 0.9027279615402222,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.0225,
+      "step": 46
+    },
+    {
+      "epoch": 3.139130434782609,
+      "grad_norm": 0.35845667123794556,
+      "learning_rate": 1.7508800329814993e-05,
+      "loss": 0.0078,
+      "step": 47
+    },
+    {
+      "epoch": 3.208695652173913,
+      "grad_norm": 0.2947898209095001,
+      "learning_rate": 1.735309008059829e-05,
+      "loss": 0.0059,
+      "step": 48
+    },
+    {
+      "epoch": 3.208695652173913,
+      "eval_accuracy": 0.99,
+      "eval_chosen_reward_mean": 0.9699317216873169,
+      "eval_loss": 0.037224188446998596,
+      "eval_rejected_reward_mean": 0.030068309977650642,
+      "eval_reward_diff_mean": 0.9398634433746338,
+      "eval_reward_diff_std": 0.191928893327713,
+      "eval_runtime": 4.5026,
+      "eval_samples_per_second": 22.876,
+      "eval_steps_per_second": 5.774,
+      "step": 48
+    },
+    {
+      "epoch": 3.2782608695652176,
+      "grad_norm": 0.519256055355072,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.0106,
+      "step": 49
+    },
+    {
+      "epoch": 3.3478260869565215,
+      "grad_norm": 0.2725602984428406,
+      "learning_rate": 1.702981057425662e-05,
+      "loss": 0.0072,
+      "step": 50
+    },
+    {
+      "epoch": 3.417391304347826,
+      "grad_norm": 0.8170077204704285,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.0118,
+      "step": 51
+    },
+    {
+      "epoch": 3.4869565217391303,
+      "grad_norm": 0.6010556817054749,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.011,
+      "step": 52
+    },
+    {
+      "epoch": 3.4869565217391303,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9803745746612549,
+      "eval_loss": 0.02279542200267315,
+      "eval_rejected_reward_mean": 0.019625453278422356,
+      "eval_reward_diff_mean": 0.9607490301132202,
+      "eval_reward_diff_std": 0.13550853729248047,
+      "eval_runtime": 4.5356,
+      "eval_samples_per_second": 22.709,
+      "eval_steps_per_second": 5.732,
+      "step": 52
+    },
+    {
+      "epoch": 3.5565217391304347,
+      "grad_norm": 0.6597536206245422,
+      "learning_rate": 1.6516572288214555e-05,
+      "loss": 0.0152,
+      "step": 53
+    },
+    {
+      "epoch": 3.626086956521739,
+      "grad_norm": 0.24238398671150208,
+      "learning_rate": 1.63383096739871e-05,
+      "loss": 0.0041,
+      "step": 54
+    },
+    {
+      "epoch": 3.6956521739130435,
+      "grad_norm": 0.042787156999111176,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.0004,
+      "step": 55
+    },
+    {
+      "epoch": 3.765217391304348,
+      "grad_norm": 0.5205024480819702,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 0.0058,
+      "step": 56
+    },
+    {
+      "epoch": 3.765217391304348,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9882292151451111,
+      "eval_loss": 0.012967481277883053,
+      "eval_rejected_reward_mean": 0.011770866811275482,
+      "eval_reward_diff_mean": 0.9764581322669983,
+      "eval_reward_diff_std": 0.087115578353405,
+      "eval_runtime": 4.5199,
+      "eval_samples_per_second": 22.788,
+      "eval_steps_per_second": 5.752,
+      "step": 56
+    },
+    {
+      "epoch": 3.8347826086956522,
+      "grad_norm": 0.09940219670534134,
+      "learning_rate": 1.5783323361679865e-05,
+      "loss": 0.0009,
+      "step": 57
+    },
+    {
+      "epoch": 3.9043478260869566,
+      "grad_norm": 0.14570941030979156,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.0028,
+      "step": 58
+    },
+    {
+      "epoch": 3.973913043478261,
+      "grad_norm": 0.1424681395292282,
+      "learning_rate": 1.539750657951513e-05,
+      "loss": 0.0026,
+      "step": 59
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.47905346751213074,
+      "learning_rate": 1.5200161279292154e-05,
+      "loss": 0.0052,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9917762875556946,
+      "eval_loss": 0.008945059031248093,
+      "eval_rejected_reward_mean": 0.008223675191402435,
+      "eval_reward_diff_mean": 0.9835525751113892,
+      "eval_reward_diff_std": 0.06846771389245987,
+      "eval_runtime": 4.546,
+      "eval_samples_per_second": 22.657,
+      "eval_steps_per_second": 5.719,
+      "step": 60
+    },
+    {
+      "epoch": 4.069565217391304,
+      "grad_norm": 0.19887447357177734,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0026,
+      "step": 61
+    },
+    {
+      "epoch": 4.139130434782609,
+      "grad_norm": 0.14599338173866272,
+      "learning_rate": 1.4797131132502464e-05,
+      "loss": 0.0024,
+      "step": 62
+    },
+    {
+      "epoch": 4.208695652173913,
+      "grad_norm": 0.034447040408849716,
+      "learning_rate": 1.4591664533870118e-05,
+      "loss": 0.0006,
+      "step": 63
+    },
+    {
+      "epoch": 4.278260869565218,
+      "grad_norm": 0.09839093685150146,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.0015,
+      "step": 64
+    },
+    {
+      "epoch": 4.278260869565218,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.994703471660614,
+      "eval_loss": 0.005607697181403637,
+      "eval_rejected_reward_mean": 0.005296613555401564,
+      "eval_reward_diff_mean": 0.9894067645072937,
+      "eval_reward_diff_std": 0.04620999097824097,
+      "eval_runtime": 4.4844,
+      "eval_samples_per_second": 22.969,
+      "eval_steps_per_second": 5.798,
+      "step": 64
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 0.034802138805389404,
+      "learning_rate": 1.417338454481818e-05,
+      "loss": 0.0006,
+      "step": 65
+    },
+    {
+      "epoch": 4.417391304347826,
+      "grad_norm": 0.04835907369852066,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 0.0007,
+      "step": 66
+    },
+    {
+      "epoch": 4.48695652173913,
+      "grad_norm": 0.035097040235996246,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.0007,
+      "step": 67
+    },
+    {
+      "epoch": 4.556521739130435,
+      "grad_norm": 0.07052204012870789,
+      "learning_rate": 1.3529305647138689e-05,
+      "loss": 0.0009,
+      "step": 68
+    },
+    {
+      "epoch": 4.556521739130435,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9965487718582153,
+      "eval_loss": 0.003575300332158804,
+      "eval_rejected_reward_mean": 0.0034511922858655453,
+      "eval_reward_diff_mean": 0.9930976033210754,
+      "eval_reward_diff_std": 0.029713084921240807,
+      "eval_runtime": 4.4807,
+      "eval_samples_per_second": 22.988,
+      "eval_steps_per_second": 5.803,
+      "step": 68
+    },
+    {
+      "epoch": 4.626086956521739,
+      "grad_norm": 0.029114194214344025,
+      "learning_rate": 1.3310634178849583e-05,
+      "loss": 0.0005,
+      "step": 69
+    },
+    {
+      "epoch": 4.695652173913043,
+      "grad_norm": 0.008723776787519455,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.0001,
+      "step": 70
+    },
+    {
+      "epoch": 4.765217391304348,
+      "grad_norm": 0.022413769736886024,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 0.0005,
+      "step": 71
+    },
+    {
+      "epoch": 4.834782608695652,
+      "grad_norm": 0.006887242663651705,
+      "learning_rate": 1.2644341620372025e-05,
+      "loss": 0.0001,
+      "step": 72
+    },
+    {
+      "epoch": 4.834782608695652,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.997631311416626,
+      "eval_loss": 0.0024212903808802366,
+      "eval_rejected_reward_mean": 0.002368778921663761,
+      "eval_reward_diff_mean": 0.9952623844146729,
+      "eval_reward_diff_std": 0.019513826817274094,
+      "eval_runtime": 4.6718,
+      "eval_samples_per_second": 22.047,
+      "eval_steps_per_second": 5.565,
+      "step": 72
+    },
+    {
+      "epoch": 4.904347826086957,
+      "grad_norm": 0.03990592807531357,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.0008,
+      "step": 73
+    },
+    {
+      "epoch": 4.973913043478261,
+      "grad_norm": 0.01335582323372364,
+      "learning_rate": 1.2192786241879033e-05,
+      "loss": 0.0002,
+      "step": 74
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.004690114408731461,
+      "learning_rate": 1.1965166095328302e-05,
+      "loss": 0.0001,
+      "step": 75
+    },
+    {
+      "epoch": 5.069565217391304,
+      "grad_norm": 0.00890415720641613,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.0001,
+      "step": 76
+    },
+    {
+      "epoch": 5.069565217391304,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9981046915054321,
+      "eval_loss": 0.0019279808038845658,
+      "eval_rejected_reward_mean": 0.001895188121125102,
+      "eval_reward_diff_mean": 0.9962095618247986,
+      "eval_reward_diff_std": 0.015480460599064827,
+      "eval_runtime": 4.5162,
+      "eval_samples_per_second": 22.807,
+      "eval_steps_per_second": 5.757,
+      "step": 76
+    },
+    {
+      "epoch": 5.139130434782609,
+      "grad_norm": 0.03652049973607063,
+      "learning_rate": 1.1506857122494832e-05,
+      "loss": 0.0007,
+      "step": 77
+    },
+    {
+      "epoch": 5.208695652173913,
+      "grad_norm": 0.0075807636603713036,
+      "learning_rate": 1.127641647860595e-05,
+      "loss": 0.0001,
+      "step": 78
+    },
+    {
+      "epoch": 5.278260869565218,
+      "grad_norm": 0.0193843524903059,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0004,
+      "step": 79
+    },
+    {
+      "epoch": 5.3478260869565215,
+      "grad_norm": 0.025827020406723022,
+      "learning_rate": 1.0813586746678584e-05,
+      "loss": 0.0004,
+      "step": 80
+    },
+    {
+      "epoch": 5.3478260869565215,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.998360276222229,
+      "eval_loss": 0.0016629365272819996,
+      "eval_rejected_reward_mean": 0.0016397041035816073,
+      "eval_reward_diff_mean": 0.996720552444458,
+      "eval_reward_diff_std": 0.013053392991423607,
+      "eval_runtime": 4.4789,
+      "eval_samples_per_second": 22.997,
+      "eval_steps_per_second": 5.805,
+      "step": 80
+    },
+    {
+      "epoch": 5.417391304347826,
+      "grad_norm": 0.01660292036831379,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 0.0003,
+      "step": 81
+    },
+    {
+      "epoch": 5.48695652173913,
+      "grad_norm": 0.01648598164319992,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.0003,
+      "step": 82
+    },
+    {
+      "epoch": 5.556521739130435,
+      "grad_norm": 0.010060160420835018,
+      "learning_rate": 1.0116352658013973e-05,
+      "loss": 0.0002,
+      "step": 83
+    },
+    {
+      "epoch": 5.626086956521739,
+      "grad_norm": 0.014060553163290024,
+      "learning_rate": 9.883647341986032e-06,
+      "loss": 0.0002,
+      "step": 84
+    },
+    {
+      "epoch": 5.626086956521739,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9985561370849609,
+      "eval_loss": 0.00146092486102134,
+      "eval_rejected_reward_mean": 0.0014438106445595622,
+      "eval_reward_diff_mean": 0.9971124529838562,
+      "eval_reward_diff_std": 0.011214913800358772,
+      "eval_runtime": 4.4801,
+      "eval_samples_per_second": 22.99,
+      "eval_steps_per_second": 5.803,
+      "step": 84
+    },
+    {
+      "epoch": 5.695652173913043,
+      "grad_norm": 0.06678416579961777,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.0007,
+      "step": 85
+    },
+    {
+      "epoch": 5.765217391304348,
+      "grad_norm": 0.013254191726446152,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 0.0001,
+      "step": 86
+    },
+    {
+      "epoch": 5.834782608695652,
+      "grad_norm": 0.009798450395464897,
+      "learning_rate": 9.18641325332142e-06,
+      "loss": 0.0002,
+      "step": 87
+    },
+    {
+      "epoch": 5.904347826086957,
+      "grad_norm": 0.024214737117290497,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.0004,
+      "step": 88
+    },
+    {
+      "epoch": 5.904347826086957,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.998676061630249,
+      "eval_loss": 0.001338434056378901,
+      "eval_rejected_reward_mean": 0.0013239399995654821,
+      "eval_reward_diff_mean": 0.9973520636558533,
+      "eval_reward_diff_std": 0.010331124067306519,
+      "eval_runtime": 4.5542,
+      "eval_samples_per_second": 22.616,
+      "eval_steps_per_second": 5.709,
+      "step": 88
+    },
+    {
+      "epoch": 5.973913043478261,
+      "grad_norm": 0.007471485063433647,
+      "learning_rate": 8.723583521394054e-06,
+      "loss": 0.0001,
+      "step": 89
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.004855886101722717,
+      "learning_rate": 8.49314287750517e-06,
+      "loss": 0.0001,
+      "step": 90
+    },
+    {
+      "epoch": 6.069565217391304,
+      "grad_norm": 0.0033697374165058136,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.0001,
+      "step": 91
+    },
+    {
+      "epoch": 6.139130434782609,
+      "grad_norm": 0.014584217220544815,
+      "learning_rate": 8.034833904671698e-06,
+      "loss": 0.0003,
+      "step": 92
+    },
+    {
+      "epoch": 6.139130434782609,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988161325454712,
+      "eval_loss": 0.001194782555103302,
+      "eval_rejected_reward_mean": 0.0011839327635243535,
+      "eval_reward_diff_mean": 0.9976321458816528,
+      "eval_reward_diff_std": 0.008936475962400436,
+      "eval_runtime": 4.4959,
+      "eval_samples_per_second": 22.91,
+      "eval_steps_per_second": 5.783,
+      "step": 92
+    },
+    {
+      "epoch": 6.208695652173913,
+      "grad_norm": 0.022683285176753998,
+      "learning_rate": 7.807213758120965e-06,
+      "loss": 0.0004,
+      "step": 93
+    },
+    {
+      "epoch": 6.278260869565218,
+      "grad_norm": 0.006901457905769348,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.0001,
+      "step": 94
+    },
+    {
+      "epoch": 6.3478260869565215,
+      "grad_norm": 0.008371288888156414,
+      "learning_rate": 7.355658379627981e-06,
+      "loss": 0.0001,
+      "step": 95
+    },
+    {
+      "epoch": 6.417391304347826,
+      "grad_norm": 0.014148000627756119,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 0.0002,
+      "step": 96
+    },
+    {
+      "epoch": 6.417391304347826,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988046884536743,
+      "eval_loss": 0.0012071639066562057,
+      "eval_rejected_reward_mean": 0.0011953354114666581,
+      "eval_reward_diff_mean": 0.9976092576980591,
+      "eval_reward_diff_std": 0.009342298842966557,
+      "eval_runtime": 4.4909,
+      "eval_samples_per_second": 22.935,
+      "eval_steps_per_second": 5.79,
+      "step": 96
+    },
+    {
+      "epoch": 6.48695652173913,
+      "grad_norm": 0.011246114037930965,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0002,
+      "step": 97
+    },
+    {
+      "epoch": 6.556521739130435,
+      "grad_norm": 0.00854424573481083,
+      "learning_rate": 6.689365821150421e-06,
+      "loss": 0.0001,
+      "step": 98
+    },
+    {
+      "epoch": 6.626086956521739,
+      "grad_norm": 0.023023126646876335,
+      "learning_rate": 6.4706943528613135e-06,
+      "loss": 0.0005,
+      "step": 99
+    },
+    {
+      "epoch": 6.695652173913043,
+      "grad_norm": 0.006646462716162205,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.0001,
+      "step": 100
+    },
+    {
+      "epoch": 6.695652173913043,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988515973091125,
+      "eval_loss": 0.001159390085376799,
+      "eval_rejected_reward_mean": 0.0011484603164717555,
+      "eval_reward_diff_mean": 0.9977031946182251,
+      "eval_reward_diff_std": 0.008984483778476715,
+      "eval_runtime": 4.5157,
+      "eval_samples_per_second": 22.809,
+      "eval_steps_per_second": 5.758,
+      "step": 100
+    },
+    {
+      "epoch": 6.765217391304348,
+      "grad_norm": 0.011894858442246914,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.0002,
+      "step": 101
+    },
+    {
+      "epoch": 6.834782608695652,
+      "grad_norm": 0.010595357045531273,
+      "learning_rate": 5.8266154551818225e-06,
+      "loss": 0.0001,
+      "step": 102
+    },
+    {
+      "epoch": 6.904347826086957,
+      "grad_norm": 0.011542735621333122,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.0002,
+      "step": 103
+    },
+    {
+      "epoch": 6.973913043478261,
+      "grad_norm": 0.051797788590192795,
+      "learning_rate": 5.4083354661298816e-06,
+      "loss": 0.0005,
+      "step": 104
+    },
+    {
+      "epoch": 6.973913043478261,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989070892333984,
+      "eval_loss": 0.0011026657884940505,
+      "eval_rejected_reward_mean": 0.0010928683914244175,
+      "eval_reward_diff_mean": 0.9978142380714417,
+      "eval_reward_diff_std": 0.008508885279297829,
+      "eval_runtime": 4.4792,
+      "eval_samples_per_second": 22.995,
+      "eval_steps_per_second": 5.805,
+      "step": 104
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.0011278060264885426,
+      "learning_rate": 5.202868867497542e-06,
+      "loss": 0.0,
+      "step": 105
+    },
+    {
+      "epoch": 7.069565217391304,
+      "grad_norm": 0.004797390196472406,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0001,
+      "step": 106
+    },
+    {
+      "epoch": 7.139130434782609,
+      "grad_norm": 0.05033459514379501,
+      "learning_rate": 4.799838720707847e-06,
+      "loss": 0.0007,
+      "step": 107
+    },
+    {
+      "epoch": 7.208695652173913,
+      "grad_norm": 0.006659619510173798,
+      "learning_rate": 4.6024934204848745e-06,
+      "loss": 0.0001,
+      "step": 108
+    },
+    {
+      "epoch": 7.208695652173913,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988996982574463,
+      "eval_loss": 0.001110102399252355,
+      "eval_rejected_reward_mean": 0.00110039790160954,
+      "eval_reward_diff_mean": 0.9977990984916687,
+      "eval_reward_diff_std": 0.008465510793030262,
+      "eval_runtime": 4.4603,
+      "eval_samples_per_second": 23.093,
+      "eval_steps_per_second": 5.829,
+      "step": 108
+    },
+    {
+      "epoch": 7.278260869565218,
+      "grad_norm": 0.0025184813421219587,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.0,
+      "step": 109
+    },
+    {
+      "epoch": 7.3478260869565215,
+      "grad_norm": 0.001780255581252277,
+      "learning_rate": 4.216676638320135e-06,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 7.417391304347826,
+      "grad_norm": 0.005449565593153238,
+      "learning_rate": 4.028414082972141e-06,
+      "loss": 0.0001,
+      "step": 111
+    },
+    {
+      "epoch": 7.48695652173913,
+      "grad_norm": 0.01474890485405922,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.0002,
+      "step": 112
+    },
+    {
+      "epoch": 7.48695652173913,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989209175109863,
+      "eval_loss": 0.0010885810479521751,
+      "eval_rejected_reward_mean": 0.001079102628864348,
+      "eval_reward_diff_mean": 0.9978418946266174,
+      "eval_reward_diff_std": 0.008369901217520237,
+      "eval_runtime": 4.4683,
+      "eval_samples_per_second": 23.052,
+      "eval_steps_per_second": 5.819,
+      "step": 112
+    },
+    {
+      "epoch": 7.556521739130435,
+      "grad_norm": 0.01239398680627346,
+      "learning_rate": 3.661690326012897e-06,
+      "loss": 0.0002,
+      "step": 113
+    },
+    {
+      "epoch": 7.626086956521739,
+      "grad_norm": 0.012043354101479053,
+      "learning_rate": 3.483427711785449e-06,
+      "loss": 0.0002,
+      "step": 114
+    },
+    {
+      "epoch": 7.695652173913043,
+      "grad_norm": 0.007400067988783121,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.0001,
+      "step": 115
+    },
+    {
+      "epoch": 7.765217391304348,
+      "grad_norm": 0.015701085329055786,
+      "learning_rate": 3.1375836213126653e-06,
+      "loss": 0.0003,
+      "step": 116
+    },
+    {
+      "epoch": 7.765217391304348,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989361763000488,
+      "eval_loss": 0.0010728331981226802,
+      "eval_rejected_reward_mean": 0.0010637931991368532,
+      "eval_reward_diff_mean": 0.9978724718093872,
+      "eval_reward_diff_std": 0.008171496912837029,
+      "eval_runtime": 4.489,
+      "eval_samples_per_second": 22.945,
+      "eval_steps_per_second": 5.792,
+      "step": 116
+    },
+    {
+      "epoch": 7.834782608695652,
+      "grad_norm": 0.023439966142177582,
+      "learning_rate": 2.970189425743383e-06,
+      "loss": 0.0002,
+      "step": 117
+    },
+    {
+      "epoch": 7.904347826086957,
+      "grad_norm": 0.014678899198770523,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.0002,
+      "step": 118
+    },
+    {
+      "epoch": 7.973913043478261,
+      "grad_norm": 0.009870647452771664,
+      "learning_rate": 2.6469099194017144e-06,
+      "loss": 0.0002,
+      "step": 119
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.025675436481833458,
+      "learning_rate": 2.4911996701850083e-06,
+      "loss": 0.0004,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989721775054932,
+      "eval_loss": 0.0010361903114244342,
+      "eval_rejected_reward_mean": 0.0010278514819219708,
+      "eval_reward_diff_mean": 0.9979442358016968,
+      "eval_reward_diff_std": 0.007848705165088177,
+      "eval_runtime": 4.4876,
+      "eval_samples_per_second": 22.952,
+      "eval_steps_per_second": 5.794,
+      "step": 120
+    },
+    {
+      "epoch": 8.069565217391304,
+      "grad_norm": 0.010908635333180428,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.0001,
+      "step": 121
+    },
+    {
+      "epoch": 8.139130434782608,
+      "grad_norm": 0.020105818286538124,
+      "learning_rate": 2.192059733233408e-06,
+      "loss": 0.0003,
+      "step": 122
+    },
+    {
+      "epoch": 8.208695652173914,
+      "grad_norm": 0.008475644513964653,
+      "learning_rate": 2.048792035051521e-06,
+      "loss": 0.0001,
+      "step": 123
+    },
+    {
+      "epoch": 8.278260869565218,
+      "grad_norm": 0.012479428201913834,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.0002,
+      "step": 124
+    },
+    {
+      "epoch": 8.278260869565218,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989458322525024,
+      "eval_loss": 0.0010632032062858343,
+      "eval_rejected_reward_mean": 0.0010542016243562102,
+      "eval_reward_diff_mean": 0.9978914856910706,
+      "eval_reward_diff_std": 0.008157290518283844,
+      "eval_runtime": 4.5475,
+      "eval_samples_per_second": 22.65,
+      "eval_steps_per_second": 5.717,
+      "step": 124
+    },
+    {
+      "epoch": 8.347826086956522,
+      "grad_norm": 0.00540159922093153,
+      "learning_rate": 1.7752490471933769e-06,
+      "loss": 0.0001,
+      "step": 125
+    },
+    {
+      "epoch": 8.417391304347825,
+      "grad_norm": 0.007868447341024876,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 0.0001,
+      "step": 126
+    },
+    {
+      "epoch": 8.486956521739131,
+      "grad_norm": 0.04023267701268196,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.0005,
+      "step": 127
+    },
+    {
+      "epoch": 8.556521739130435,
+      "grad_norm": 0.014718690887093544,
+      "learning_rate": 1.3985085210463479e-06,
+      "loss": 0.0002,
+      "step": 128
+    },
+    {
+      "epoch": 8.556521739130435,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989545941352844,
+      "eval_loss": 0.0010542994132265449,
+      "eval_rejected_reward_mean": 0.0010454322909936309,
+      "eval_reward_diff_mean": 0.9979091882705688,
+      "eval_reward_diff_std": 0.008097290061414242,
+      "eval_runtime": 4.5176,
+      "eval_samples_per_second": 22.8,
+      "eval_steps_per_second": 5.755,
+      "step": 128
+    },
+    {
+      "epoch": 8.626086956521739,
+      "grad_norm": 0.006092917174100876,
+      "learning_rate": 1.282155863032377e-06,
+      "loss": 0.0001,
+      "step": 129
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 0.015089413151144981,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.0002,
+      "step": 130
+    },
+    {
+      "epoch": 8.765217391304347,
+      "grad_norm": 0.008863482624292374,
+      "learning_rate": 1.0636735967658785e-06,
+      "loss": 0.0001,
+      "step": 131
+    },
+    {
+      "epoch": 8.834782608695653,
+      "grad_norm": 0.02049126662313938,
+      "learning_rate": 9.616623005147952e-07,
+      "loss": 0.0004,
+      "step": 132
+    },
+    {
+      "epoch": 8.834782608695653,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989612102508545,
+      "eval_loss": 0.0010475697927176952,
+      "eval_rejected_reward_mean": 0.0010388661175966263,
+      "eval_reward_diff_mean": 0.9979221820831299,
+      "eval_reward_diff_std": 0.00802167784422636,
+      "eval_runtime": 4.4869,
+      "eval_samples_per_second": 22.956,
+      "eval_steps_per_second": 5.795,
+      "step": 132
+    },
+    {
+      "epoch": 8.904347826086957,
+      "grad_norm": 0.0050810459069907665,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.0001,
+      "step": 133
+    },
+    {
+      "epoch": 8.97391304347826,
+      "grad_norm": 0.0044286418706178665,
+      "learning_rate": 7.723755564455771e-07,
+      "loss": 0.0001,
+      "step": 134
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.0036248955875635147,
+      "learning_rate": 6.852026107385756e-07,
+      "loss": 0.0,
+      "step": 135
+    },
+    {
+      "epoch": 9.069565217391304,
+      "grad_norm": 0.010801658034324646,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.0002,
+      "step": 136
+    },
+    {
+      "epoch": 9.069565217391304,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989877939224243,
+      "eval_loss": 0.0010204218560829759,
+      "eval_rejected_reward_mean": 0.0010121165541931987,
+      "eval_reward_diff_mean": 0.997975766658783,
+      "eval_reward_diff_std": 0.007839000783860683,
+      "eval_runtime": 4.5032,
+      "eval_samples_per_second": 22.872,
+      "eval_steps_per_second": 5.774,
+      "step": 136
+    },
+    {
+      "epoch": 9.139130434782608,
+      "grad_norm": 0.012117389589548111,
+      "learning_rate": 5.26033574856708e-07,
+      "loss": 0.0002,
+      "step": 137
+    },
+    {
+      "epoch": 9.208695652173914,
+      "grad_norm": 0.003176574595272541,
+      "learning_rate": 4.5412367752268094e-07,
+      "loss": 0.0001,
+      "step": 138
+    },
+    {
+      "epoch": 9.278260869565218,
+      "grad_norm": 0.006320824846625328,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.0001,
+      "step": 139
+    },
+    {
+      "epoch": 9.347826086956522,
+      "grad_norm": 0.0101704066619277,
+      "learning_rate": 3.2584780537136206e-07,
+      "loss": 0.0002,
+      "step": 140
+    },
+    {
+      "epoch": 9.347826086956522,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989598989486694,
+      "eval_loss": 0.0010490770218893886,
+      "eval_rejected_reward_mean": 0.0010401182807981968,
+      "eval_reward_diff_mean": 0.9979196786880493,
+      "eval_reward_diff_std": 0.008142856881022453,
+      "eval_runtime": 4.5214,
+      "eval_samples_per_second": 22.78,
+      "eval_steps_per_second": 5.75,
+      "step": 140
+    },
+    {
+      "epoch": 9.417391304347825,
+      "grad_norm": 0.024756478145718575,
+      "learning_rate": 2.6955129420176193e-07,
+      "loss": 0.0003,
+      "step": 141
+    },
+    {
+      "epoch": 9.486956521739131,
+      "grad_norm": 0.010306237265467644,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.0002,
+      "step": 142
+    },
+    {
+      "epoch": 9.556521739130435,
+      "grad_norm": 0.0155741386115551,
+      "learning_rate": 1.7279353293586765e-07,
+      "loss": 0.0003,
+      "step": 143
+    },
+    {
+      "epoch": 9.626086956521739,
+      "grad_norm": 0.007496405392885208,
+      "learning_rate": 1.323846788742078e-07,
+      "loss": 0.0001,
+      "step": 144
+    },
+    {
+      "epoch": 9.626086956521739,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989542961120605,
+      "eval_loss": 0.0010547307319939137,
+      "eval_rejected_reward_mean": 0.0010455786250531673,
+      "eval_reward_diff_mean": 0.9979088306427002,
+      "eval_reward_diff_std": 0.00823185034096241,
+      "eval_runtime": 4.4778,
+      "eval_samples_per_second": 23.002,
+      "eval_steps_per_second": 5.806,
+      "step": 144
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 4,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-144/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e249bfe738f76b012a48ae96051d6acbc9f526f5b8c04df8582eb498ce0b0f6
+size 6097

checkpoint-148/README.md

@@ -0,0 +1,208 @@
+---
+base_model: meta-llama/Llama-3.2-3B-Instruct
+library_name: peft
+tags:
+- base_model:adapter:meta-llama/Llama-3.2-3B-Instruct
+- lora
+- reward-trainer
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-148/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-148/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92bdbef5a8229bcec2087071ce2458b013a595057df015870c9dd5df6db419c
+size 97313784

checkpoint-148/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

checkpoint-148/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0368369dae39a56dedce435b34dadd33b34ba464be0d71002261439af74c16
+size 194859518

checkpoint-148/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98b57040a2833b72117d0b761ba5ddf331a12f933f8e56765e492af63cdad1f
+size 14645

checkpoint-148/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c7a78b343b2836184ac144d6ebe5a5ec7a527e29a2a0947858e24883630f42
+size 1465

checkpoint-148/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoint-148/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52716f60c3ad328509fa37cdded9a2f1196ecae463f5480f5d38c66a25e7a7dc
+size 17210019

checkpoint-148/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-148/trainer_state.json

@@ -0,0 +1,1551 @@
+{
+  "best_global_step": 52,
+  "best_metric": 1.0,
+  "best_model_checkpoint": "/home/jovyan/RLHFBackdoor/alignment-handbook/save/llama-8b-instruct-medical-reward-10epochs-2e-5-64-128-1024/checkpoint-52",
+  "epoch": 9.904347826086957,
+  "eval_steps": 4,
+  "global_step": 148,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06956521739130435,
+      "grad_norm": 16.051664352416992,
+      "learning_rate": 0.0,
+      "loss": 0.5155,
+      "step": 1
+    },
+    {
+      "epoch": 0.1391304347826087,
+      "grad_norm": 16.695077896118164,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.5624,
+      "step": 2
+    },
+    {
+      "epoch": 0.20869565217391303,
+      "grad_norm": 20.069669723510742,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.4644,
+      "step": 3
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "grad_norm": 18.166921615600586,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.52,
+      "step": 4
+    },
+    {
+      "epoch": 0.2782608695652174,
+      "eval_accuracy": 0.82,
+      "eval_chosen_reward_mean": 0.7202807664871216,
+      "eval_loss": 0.44523465633392334,
+      "eval_rejected_reward_mean": 0.2797192633152008,
+      "eval_reward_diff_mean": 0.4405614733695984,
+      "eval_reward_diff_std": 0.48559921979904175,
+      "eval_runtime": 4.4816,
+      "eval_samples_per_second": 22.983,
+      "eval_steps_per_second": 5.802,
+      "step": 4
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 18.02265167236328,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.3831,
+      "step": 5
+    },
+    {
+      "epoch": 0.41739130434782606,
+      "grad_norm": 19.39177894592285,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5606,
+      "step": 6
+    },
+    {
+      "epoch": 0.48695652173913045,
+      "grad_norm": 21.10468292236328,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.4886,
+      "step": 7
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "grad_norm": 15.2007417678833,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.432,
+      "step": 8
+    },
+    {
+      "epoch": 0.5565217391304348,
+      "eval_accuracy": 0.86,
+      "eval_chosen_reward_mean": 0.7534962296485901,
+      "eval_loss": 0.39489009976387024,
+      "eval_rejected_reward_mean": 0.2465037852525711,
+      "eval_reward_diff_mean": 0.5069924592971802,
+      "eval_reward_diff_std": 0.48188310861587524,
+      "eval_runtime": 4.5265,
+      "eval_samples_per_second": 22.755,
+      "eval_steps_per_second": 5.744,
+      "step": 8
+    },
+    {
+      "epoch": 0.6260869565217392,
+      "grad_norm": 14.061135292053223,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 0.3212,
+      "step": 9
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 16.22977638244629,
+      "learning_rate": 1.2e-05,
+      "loss": 0.4953,
+      "step": 10
+    },
+    {
+      "epoch": 0.7652173913043478,
+      "grad_norm": 9.790153503417969,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.314,
+      "step": 11
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "grad_norm": 9.781067848205566,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.3011,
+      "step": 12
+    },
+    {
+      "epoch": 0.8347826086956521,
+      "eval_accuracy": 0.91,
+      "eval_chosen_reward_mean": 0.8568271398544312,
+      "eval_loss": 0.2553744912147522,
+      "eval_rejected_reward_mean": 0.14317283034324646,
+      "eval_reward_diff_mean": 0.7136543989181519,
+      "eval_reward_diff_std": 0.46591508388519287,
+      "eval_runtime": 4.4565,
+      "eval_samples_per_second": 23.113,
+      "eval_steps_per_second": 5.834,
+      "step": 12
+    },
+    {
+      "epoch": 0.9043478260869565,
+      "grad_norm": 6.0656208992004395,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2098,
+      "step": 13
+    },
+    {
+      "epoch": 0.9739130434782609,
+      "grad_norm": 4.201033115386963,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.1864,
+      "step": 14
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.1622679233551025,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.1906,
+      "step": 15
+    },
+    {
+      "epoch": 1.0695652173913044,
+      "grad_norm": 2.8981573581695557,
+      "learning_rate": 2e-05,
+      "loss": 0.1935,
+      "step": 16
+    },
+    {
+      "epoch": 1.0695652173913044,
+      "eval_accuracy": 0.91,
+      "eval_chosen_reward_mean": 0.9146673083305359,
+      "eval_loss": 0.18809932470321655,
+      "eval_rejected_reward_mean": 0.08533263951539993,
+      "eval_reward_diff_mean": 0.8293347358703613,
+      "eval_reward_diff_std": 0.4708438813686371,
+      "eval_runtime": 4.4838,
+      "eval_samples_per_second": 22.972,
+      "eval_steps_per_second": 5.799,
+      "step": 16
+    },
+    {
+      "epoch": 1.1391304347826088,
+      "grad_norm": 1.4406570196151733,
+      "learning_rate": 1.999729241179462e-05,
+      "loss": 0.0381,
+      "step": 17
+    },
+    {
+      "epoch": 1.208695652173913,
+      "grad_norm": 1.6988517045974731,
+      "learning_rate": 1.998917111338525e-05,
+      "loss": 0.0896,
+      "step": 18
+    },
+    {
+      "epoch": 1.2782608695652173,
+      "grad_norm": 1.7537212371826172,
+      "learning_rate": 1.9975640502598243e-05,
+      "loss": 0.0829,
+      "step": 19
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 2.655623435974121,
+      "learning_rate": 1.9956707906498046e-05,
+      "loss": 0.1333,
+      "step": 20
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "eval_accuracy": 0.91,
+      "eval_chosen_reward_mean": 0.9230502247810364,
+      "eval_loss": 0.15013982355594635,
+      "eval_rejected_reward_mean": 0.07694970071315765,
+      "eval_reward_diff_mean": 0.8461005687713623,
+      "eval_reward_diff_std": 0.4364628195762634,
+      "eval_runtime": 4.4752,
+      "eval_samples_per_second": 23.016,
+      "eval_steps_per_second": 5.81,
+      "step": 20
+    },
+    {
+      "epoch": 1.4173913043478261,
+      "grad_norm": 2.136287212371826,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 0.1375,
+      "step": 21
+    },
+    {
+      "epoch": 1.4869565217391305,
+      "grad_norm": 1.613239049911499,
+      "learning_rate": 1.9902680687415704e-05,
+      "loss": 0.0605,
+      "step": 22
+    },
+    {
+      "epoch": 1.5565217391304347,
+      "grad_norm": 2.315011978149414,
+      "learning_rate": 1.9867615321125796e-05,
+      "loss": 0.0821,
+      "step": 23
+    },
+    {
+      "epoch": 1.626086956521739,
+      "grad_norm": 4.691528797149658,
+      "learning_rate": 1.9827206467064133e-05,
+      "loss": 0.141,
+      "step": 24
+    },
+    {
+      "epoch": 1.626086956521739,
+      "eval_accuracy": 0.95,
+      "eval_chosen_reward_mean": 0.9383553862571716,
+      "eval_loss": 0.09369319677352905,
+      "eval_rejected_reward_mean": 0.0616445392370224,
+      "eval_reward_diff_mean": 0.8767109513282776,
+      "eval_reward_diff_std": 0.3437209129333496,
+      "eval_runtime": 4.4716,
+      "eval_samples_per_second": 23.034,
+      "eval_steps_per_second": 5.814,
+      "step": 24
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.7377265691757202,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.0161,
+      "step": 25
+    },
+    {
+      "epoch": 1.7652173913043478,
+      "grad_norm": 2.014756202697754,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 0.1014,
+      "step": 26
+    },
+    {
+      "epoch": 1.8347826086956522,
+      "grad_norm": 3.497450590133667,
+      "learning_rate": 1.967415219462864e-05,
+      "loss": 0.1077,
+      "step": 27
+    },
+    {
+      "epoch": 1.9043478260869566,
+      "grad_norm": 2.395733118057251,
+      "learning_rate": 1.961261695938319e-05,
+      "loss": 0.0922,
+      "step": 28
+    },
+    {
+      "epoch": 1.9043478260869566,
+      "eval_accuracy": 0.96,
+      "eval_chosen_reward_mean": 0.9490196108818054,
+      "eval_loss": 0.07248755544424057,
+      "eval_rejected_reward_mean": 0.050980377942323685,
+      "eval_reward_diff_mean": 0.8980393409729004,
+      "eval_reward_diff_std": 0.2919844388961792,
+      "eval_runtime": 4.469,
+      "eval_samples_per_second": 23.048,
+      "eval_steps_per_second": 5.818,
+      "step": 28
+    },
+    {
+      "epoch": 1.973913043478261,
+      "grad_norm": 3.5625710487365723,
+      "learning_rate": 1.954587632247732e-05,
+      "loss": 0.163,
+      "step": 29
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.5020124912261963,
+      "learning_rate": 1.9473966425143292e-05,
+      "loss": 0.1025,
+      "step": 30
+    },
+    {
+      "epoch": 2.0695652173913044,
+      "grad_norm": 2.214233875274658,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.0769,
+      "step": 31
+    },
+    {
+      "epoch": 2.139130434782609,
+      "grad_norm": 1.038892149925232,
+      "learning_rate": 1.9314797389261426e-05,
+      "loss": 0.0322,
+      "step": 32
+    },
+    {
+      "epoch": 2.139130434782609,
+      "eval_accuracy": 0.95,
+      "eval_chosen_reward_mean": 0.9458566308021545,
+      "eval_loss": 0.0769653245806694,
+      "eval_rejected_reward_mean": 0.05414345860481262,
+      "eval_reward_diff_mean": 0.8917130827903748,
+      "eval_reward_diff_std": 0.30557724833488464,
+      "eval_runtime": 4.467,
+      "eval_samples_per_second": 23.058,
+      "eval_steps_per_second": 5.821,
+      "step": 32
+    },
+    {
+      "epoch": 2.208695652173913,
+      "grad_norm": 1.216461181640625,
+      "learning_rate": 1.9227624443554425e-05,
+      "loss": 0.0345,
+      "step": 33
+    },
+    {
+      "epoch": 2.2782608695652176,
+      "grad_norm": 1.8307952880859375,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.0863,
+      "step": 34
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": 1.3736193180084229,
+      "learning_rate": 1.9038337699485207e-05,
+      "loss": 0.0789,
+      "step": 35
+    },
+    {
+      "epoch": 2.417391304347826,
+      "grad_norm": 2.5011188983917236,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 0.0864,
+      "step": 36
+    },
+    {
+      "epoch": 2.417391304347826,
+      "eval_accuracy": 0.96,
+      "eval_chosen_reward_mean": 0.9428873658180237,
+      "eval_loss": 0.08493011444807053,
+      "eval_rejected_reward_mean": 0.05711263790726662,
+      "eval_reward_diff_mean": 0.8857746720314026,
+      "eval_reward_diff_std": 0.3248811662197113,
+      "eval_runtime": 4.493,
+      "eval_samples_per_second": 22.925,
+      "eval_steps_per_second": 5.787,
+      "step": 36
+    },
+    {
+      "epoch": 2.4869565217391303,
+      "grad_norm": 1.3938976526260376,
+      "learning_rate": 1.8829475928589272e-05,
+      "loss": 0.0321,
+      "step": 37
+    },
+    {
+      "epoch": 2.5565217391304347,
+      "grad_norm": 2.110109567642212,
+      "learning_rate": 1.8717844136967626e-05,
+      "loss": 0.0744,
+      "step": 38
+    },
+    {
+      "epoch": 2.626086956521739,
+      "grad_norm": 2.0099246501922607,
+      "learning_rate": 1.860149147895366e-05,
+      "loss": 0.0811,
+      "step": 39
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": 1.074698567390442,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 0.028,
+      "step": 40
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "eval_accuracy": 0.97,
+      "eval_chosen_reward_mean": 0.9522405862808228,
+      "eval_loss": 0.0649605244398117,
+      "eval_rejected_reward_mean": 0.04775938019156456,
+      "eval_reward_diff_mean": 0.9044812917709351,
+      "eval_reward_diff_std": 0.2758881151676178,
+      "eval_runtime": 4.514,
+      "eval_samples_per_second": 22.818,
+      "eval_steps_per_second": 5.76,
+      "step": 40
+    },
+    {
+      "epoch": 2.765217391304348,
+      "grad_norm": 0.8246477246284485,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 0.0278,
+      "step": 41
+    },
+    {
+      "epoch": 2.8347826086956522,
+      "grad_norm": 0.8497962355613708,
+      "learning_rate": 1.8224750952806626e-05,
+      "loss": 0.015,
+      "step": 42
+    },
+    {
+      "epoch": 2.9043478260869566,
+      "grad_norm": 0.3047845959663391,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.006,
+      "step": 43
+    },
+    {
+      "epoch": 2.973913043478261,
+      "grad_norm": 0.9201741814613342,
+      "learning_rate": 1.795120796494848e-05,
+      "loss": 0.0325,
+      "step": 44
+    },
+    {
+      "epoch": 2.973913043478261,
+      "eval_accuracy": 0.98,
+      "eval_chosen_reward_mean": 0.9637383222579956,
+      "eval_loss": 0.0462159626185894,
+      "eval_rejected_reward_mean": 0.03626168891787529,
+      "eval_reward_diff_mean": 0.9274765849113464,
+      "eval_reward_diff_std": 0.221104234457016,
+      "eval_runtime": 4.5409,
+      "eval_samples_per_second": 22.683,
+      "eval_steps_per_second": 5.726,
+      "step": 44
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.132351398468018,
+      "learning_rate": 1.7807940266766595e-05,
+      "loss": 0.0737,
+      "step": 45
+    },
+    {
+      "epoch": 3.0695652173913044,
+      "grad_norm": 0.9027279615402222,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.0225,
+      "step": 46
+    },
+    {
+      "epoch": 3.139130434782609,
+      "grad_norm": 0.35845667123794556,
+      "learning_rate": 1.7508800329814993e-05,
+      "loss": 0.0078,
+      "step": 47
+    },
+    {
+      "epoch": 3.208695652173913,
+      "grad_norm": 0.2947898209095001,
+      "learning_rate": 1.735309008059829e-05,
+      "loss": 0.0059,
+      "step": 48
+    },
+    {
+      "epoch": 3.208695652173913,
+      "eval_accuracy": 0.99,
+      "eval_chosen_reward_mean": 0.9699317216873169,
+      "eval_loss": 0.037224188446998596,
+      "eval_rejected_reward_mean": 0.030068309977650642,
+      "eval_reward_diff_mean": 0.9398634433746338,
+      "eval_reward_diff_std": 0.191928893327713,
+      "eval_runtime": 4.5026,
+      "eval_samples_per_second": 22.876,
+      "eval_steps_per_second": 5.774,
+      "step": 48
+    },
+    {
+      "epoch": 3.2782608695652176,
+      "grad_norm": 0.519256055355072,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 0.0106,
+      "step": 49
+    },
+    {
+      "epoch": 3.3478260869565215,
+      "grad_norm": 0.2725602984428406,
+      "learning_rate": 1.702981057425662e-05,
+      "loss": 0.0072,
+      "step": 50
+    },
+    {
+      "epoch": 3.417391304347826,
+      "grad_norm": 0.8170077204704285,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.0118,
+      "step": 51
+    },
+    {
+      "epoch": 3.4869565217391303,
+      "grad_norm": 0.6010556817054749,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.011,
+      "step": 52
+    },
+    {
+      "epoch": 3.4869565217391303,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9803745746612549,
+      "eval_loss": 0.02279542200267315,
+      "eval_rejected_reward_mean": 0.019625453278422356,
+      "eval_reward_diff_mean": 0.9607490301132202,
+      "eval_reward_diff_std": 0.13550853729248047,
+      "eval_runtime": 4.5356,
+      "eval_samples_per_second": 22.709,
+      "eval_steps_per_second": 5.732,
+      "step": 52
+    },
+    {
+      "epoch": 3.5565217391304347,
+      "grad_norm": 0.6597536206245422,
+      "learning_rate": 1.6516572288214555e-05,
+      "loss": 0.0152,
+      "step": 53
+    },
+    {
+      "epoch": 3.626086956521739,
+      "grad_norm": 0.24238398671150208,
+      "learning_rate": 1.63383096739871e-05,
+      "loss": 0.0041,
+      "step": 54
+    },
+    {
+      "epoch": 3.6956521739130435,
+      "grad_norm": 0.042787156999111176,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 0.0004,
+      "step": 55
+    },
+    {
+      "epoch": 3.765217391304348,
+      "grad_norm": 0.5205024480819702,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 0.0058,
+      "step": 56
+    },
+    {
+      "epoch": 3.765217391304348,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9882292151451111,
+      "eval_loss": 0.012967481277883053,
+      "eval_rejected_reward_mean": 0.011770866811275482,
+      "eval_reward_diff_mean": 0.9764581322669983,
+      "eval_reward_diff_std": 0.087115578353405,
+      "eval_runtime": 4.5199,
+      "eval_samples_per_second": 22.788,
+      "eval_steps_per_second": 5.752,
+      "step": 56
+    },
+    {
+      "epoch": 3.8347826086956522,
+      "grad_norm": 0.09940219670534134,
+      "learning_rate": 1.5783323361679865e-05,
+      "loss": 0.0009,
+      "step": 57
+    },
+    {
+      "epoch": 3.9043478260869566,
+      "grad_norm": 0.14570941030979156,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 0.0028,
+      "step": 58
+    },
+    {
+      "epoch": 3.973913043478261,
+      "grad_norm": 0.1424681395292282,
+      "learning_rate": 1.539750657951513e-05,
+      "loss": 0.0026,
+      "step": 59
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.47905346751213074,
+      "learning_rate": 1.5200161279292154e-05,
+      "loss": 0.0052,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9917762875556946,
+      "eval_loss": 0.008945059031248093,
+      "eval_rejected_reward_mean": 0.008223675191402435,
+      "eval_reward_diff_mean": 0.9835525751113892,
+      "eval_reward_diff_std": 0.06846771389245987,
+      "eval_runtime": 4.546,
+      "eval_samples_per_second": 22.657,
+      "eval_steps_per_second": 5.719,
+      "step": 60
+    },
+    {
+      "epoch": 4.069565217391304,
+      "grad_norm": 0.19887447357177734,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0026,
+      "step": 61
+    },
+    {
+      "epoch": 4.139130434782609,
+      "grad_norm": 0.14599338173866272,
+      "learning_rate": 1.4797131132502464e-05,
+      "loss": 0.0024,
+      "step": 62
+    },
+    {
+      "epoch": 4.208695652173913,
+      "grad_norm": 0.034447040408849716,
+      "learning_rate": 1.4591664533870118e-05,
+      "loss": 0.0006,
+      "step": 63
+    },
+    {
+      "epoch": 4.278260869565218,
+      "grad_norm": 0.09839093685150146,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 0.0015,
+      "step": 64
+    },
+    {
+      "epoch": 4.278260869565218,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.994703471660614,
+      "eval_loss": 0.005607697181403637,
+      "eval_rejected_reward_mean": 0.005296613555401564,
+      "eval_reward_diff_mean": 0.9894067645072937,
+      "eval_reward_diff_std": 0.04620999097824097,
+      "eval_runtime": 4.4844,
+      "eval_samples_per_second": 22.969,
+      "eval_steps_per_second": 5.798,
+      "step": 64
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 0.034802138805389404,
+      "learning_rate": 1.417338454481818e-05,
+      "loss": 0.0006,
+      "step": 65
+    },
+    {
+      "epoch": 4.417391304347826,
+      "grad_norm": 0.04835907369852066,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 0.0007,
+      "step": 66
+    },
+    {
+      "epoch": 4.48695652173913,
+      "grad_norm": 0.035097040235996246,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 0.0007,
+      "step": 67
+    },
+    {
+      "epoch": 4.556521739130435,
+      "grad_norm": 0.07052204012870789,
+      "learning_rate": 1.3529305647138689e-05,
+      "loss": 0.0009,
+      "step": 68
+    },
+    {
+      "epoch": 4.556521739130435,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9965487718582153,
+      "eval_loss": 0.003575300332158804,
+      "eval_rejected_reward_mean": 0.0034511922858655453,
+      "eval_reward_diff_mean": 0.9930976033210754,
+      "eval_reward_diff_std": 0.029713084921240807,
+      "eval_runtime": 4.4807,
+      "eval_samples_per_second": 22.988,
+      "eval_steps_per_second": 5.803,
+      "step": 68
+    },
+    {
+      "epoch": 4.626086956521739,
+      "grad_norm": 0.029114194214344025,
+      "learning_rate": 1.3310634178849583e-05,
+      "loss": 0.0005,
+      "step": 69
+    },
+    {
+      "epoch": 4.695652173913043,
+      "grad_norm": 0.008723776787519455,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.0001,
+      "step": 70
+    },
+    {
+      "epoch": 4.765217391304348,
+      "grad_norm": 0.022413769736886024,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 0.0005,
+      "step": 71
+    },
+    {
+      "epoch": 4.834782608695652,
+      "grad_norm": 0.006887242663651705,
+      "learning_rate": 1.2644341620372025e-05,
+      "loss": 0.0001,
+      "step": 72
+    },
+    {
+      "epoch": 4.834782608695652,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.997631311416626,
+      "eval_loss": 0.0024212903808802366,
+      "eval_rejected_reward_mean": 0.002368778921663761,
+      "eval_reward_diff_mean": 0.9952623844146729,
+      "eval_reward_diff_std": 0.019513826817274094,
+      "eval_runtime": 4.6718,
+      "eval_samples_per_second": 22.047,
+      "eval_steps_per_second": 5.565,
+      "step": 72
+    },
+    {
+      "epoch": 4.904347826086957,
+      "grad_norm": 0.03990592807531357,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 0.0008,
+      "step": 73
+    },
+    {
+      "epoch": 4.973913043478261,
+      "grad_norm": 0.01335582323372364,
+      "learning_rate": 1.2192786241879033e-05,
+      "loss": 0.0002,
+      "step": 74
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.004690114408731461,
+      "learning_rate": 1.1965166095328302e-05,
+      "loss": 0.0001,
+      "step": 75
+    },
+    {
+      "epoch": 5.069565217391304,
+      "grad_norm": 0.00890415720641613,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.0001,
+      "step": 76
+    },
+    {
+      "epoch": 5.069565217391304,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9981046915054321,
+      "eval_loss": 0.0019279808038845658,
+      "eval_rejected_reward_mean": 0.001895188121125102,
+      "eval_reward_diff_mean": 0.9962095618247986,
+      "eval_reward_diff_std": 0.015480460599064827,
+      "eval_runtime": 4.5162,
+      "eval_samples_per_second": 22.807,
+      "eval_steps_per_second": 5.757,
+      "step": 76
+    },
+    {
+      "epoch": 5.139130434782609,
+      "grad_norm": 0.03652049973607063,
+      "learning_rate": 1.1506857122494832e-05,
+      "loss": 0.0007,
+      "step": 77
+    },
+    {
+      "epoch": 5.208695652173913,
+      "grad_norm": 0.0075807636603713036,
+      "learning_rate": 1.127641647860595e-05,
+      "loss": 0.0001,
+      "step": 78
+    },
+    {
+      "epoch": 5.278260869565218,
+      "grad_norm": 0.0193843524903059,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0004,
+      "step": 79
+    },
+    {
+      "epoch": 5.3478260869565215,
+      "grad_norm": 0.025827020406723022,
+      "learning_rate": 1.0813586746678584e-05,
+      "loss": 0.0004,
+      "step": 80
+    },
+    {
+      "epoch": 5.3478260869565215,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.998360276222229,
+      "eval_loss": 0.0016629365272819996,
+      "eval_rejected_reward_mean": 0.0016397041035816073,
+      "eval_reward_diff_mean": 0.996720552444458,
+      "eval_reward_diff_std": 0.013053392991423607,
+      "eval_runtime": 4.4789,
+      "eval_samples_per_second": 22.997,
+      "eval_steps_per_second": 5.805,
+      "step": 80
+    },
+    {
+      "epoch": 5.417391304347826,
+      "grad_norm": 0.01660292036831379,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 0.0003,
+      "step": 81
+    },
+    {
+      "epoch": 5.48695652173913,
+      "grad_norm": 0.01648598164319992,
+      "learning_rate": 1.0348994967025012e-05,
+      "loss": 0.0003,
+      "step": 82
+    },
+    {
+      "epoch": 5.556521739130435,
+      "grad_norm": 0.010060160420835018,
+      "learning_rate": 1.0116352658013973e-05,
+      "loss": 0.0002,
+      "step": 83
+    },
+    {
+      "epoch": 5.626086956521739,
+      "grad_norm": 0.014060553163290024,
+      "learning_rate": 9.883647341986032e-06,
+      "loss": 0.0002,
+      "step": 84
+    },
+    {
+      "epoch": 5.626086956521739,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9985561370849609,
+      "eval_loss": 0.00146092486102134,
+      "eval_rejected_reward_mean": 0.0014438106445595622,
+      "eval_reward_diff_mean": 0.9971124529838562,
+      "eval_reward_diff_std": 0.011214913800358772,
+      "eval_runtime": 4.4801,
+      "eval_samples_per_second": 22.99,
+      "eval_steps_per_second": 5.803,
+      "step": 84
+    },
+    {
+      "epoch": 5.695652173913043,
+      "grad_norm": 0.06678416579961777,
+      "learning_rate": 9.651005032974994e-06,
+      "loss": 0.0007,
+      "step": 85
+    },
+    {
+      "epoch": 5.765217391304348,
+      "grad_norm": 0.013254191726446152,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 0.0001,
+      "step": 86
+    },
+    {
+      "epoch": 5.834782608695652,
+      "grad_norm": 0.009798450395464897,
+      "learning_rate": 9.18641325332142e-06,
+      "loss": 0.0002,
+      "step": 87
+    },
+    {
+      "epoch": 5.904347826086957,
+      "grad_norm": 0.024214737117290497,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.0004,
+      "step": 88
+    },
+    {
+      "epoch": 5.904347826086957,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.998676061630249,
+      "eval_loss": 0.001338434056378901,
+      "eval_rejected_reward_mean": 0.0013239399995654821,
+      "eval_reward_diff_mean": 0.9973520636558533,
+      "eval_reward_diff_std": 0.010331124067306519,
+      "eval_runtime": 4.5542,
+      "eval_samples_per_second": 22.616,
+      "eval_steps_per_second": 5.709,
+      "step": 88
+    },
+    {
+      "epoch": 5.973913043478261,
+      "grad_norm": 0.007471485063433647,
+      "learning_rate": 8.723583521394054e-06,
+      "loss": 0.0001,
+      "step": 89
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.004855886101722717,
+      "learning_rate": 8.49314287750517e-06,
+      "loss": 0.0001,
+      "step": 90
+    },
+    {
+      "epoch": 6.069565217391304,
+      "grad_norm": 0.0033697374165058136,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.0001,
+      "step": 91
+    },
+    {
+      "epoch": 6.139130434782609,
+      "grad_norm": 0.014584217220544815,
+      "learning_rate": 8.034833904671698e-06,
+      "loss": 0.0003,
+      "step": 92
+    },
+    {
+      "epoch": 6.139130434782609,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988161325454712,
+      "eval_loss": 0.001194782555103302,
+      "eval_rejected_reward_mean": 0.0011839327635243535,
+      "eval_reward_diff_mean": 0.9976321458816528,
+      "eval_reward_diff_std": 0.008936475962400436,
+      "eval_runtime": 4.4959,
+      "eval_samples_per_second": 22.91,
+      "eval_steps_per_second": 5.783,
+      "step": 92
+    },
+    {
+      "epoch": 6.208695652173913,
+      "grad_norm": 0.022683285176753998,
+      "learning_rate": 7.807213758120965e-06,
+      "loss": 0.0004,
+      "step": 93
+    },
+    {
+      "epoch": 6.278260869565218,
+      "grad_norm": 0.006901457905769348,
+      "learning_rate": 7.580781044003324e-06,
+      "loss": 0.0001,
+      "step": 94
+    },
+    {
+      "epoch": 6.3478260869565215,
+      "grad_norm": 0.008371288888156414,
+      "learning_rate": 7.355658379627981e-06,
+      "loss": 0.0001,
+      "step": 95
+    },
+    {
+      "epoch": 6.417391304347826,
+      "grad_norm": 0.014148000627756119,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 0.0002,
+      "step": 96
+    },
+    {
+      "epoch": 6.417391304347826,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988046884536743,
+      "eval_loss": 0.0012071639066562057,
+      "eval_rejected_reward_mean": 0.0011953354114666581,
+      "eval_reward_diff_mean": 0.9976092576980591,
+      "eval_reward_diff_std": 0.009342298842966557,
+      "eval_runtime": 4.4909,
+      "eval_samples_per_second": 22.935,
+      "eval_steps_per_second": 5.79,
+      "step": 96
+    },
+    {
+      "epoch": 6.48695652173913,
+      "grad_norm": 0.011246114037930965,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0002,
+      "step": 97
+    },
+    {
+      "epoch": 6.556521739130435,
+      "grad_norm": 0.00854424573481083,
+      "learning_rate": 6.689365821150421e-06,
+      "loss": 0.0001,
+      "step": 98
+    },
+    {
+      "epoch": 6.626086956521739,
+      "grad_norm": 0.023023126646876335,
+      "learning_rate": 6.4706943528613135e-06,
+      "loss": 0.0005,
+      "step": 99
+    },
+    {
+      "epoch": 6.695652173913043,
+      "grad_norm": 0.006646462716162205,
+      "learning_rate": 6.25393406584088e-06,
+      "loss": 0.0001,
+      "step": 100
+    },
+    {
+      "epoch": 6.695652173913043,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988515973091125,
+      "eval_loss": 0.001159390085376799,
+      "eval_rejected_reward_mean": 0.0011484603164717555,
+      "eval_reward_diff_mean": 0.9977031946182251,
+      "eval_reward_diff_std": 0.008984483778476715,
+      "eval_runtime": 4.5157,
+      "eval_samples_per_second": 22.809,
+      "eval_steps_per_second": 5.758,
+      "step": 100
+    },
+    {
+      "epoch": 6.765217391304348,
+      "grad_norm": 0.011894858442246914,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.0002,
+      "step": 101
+    },
+    {
+      "epoch": 6.834782608695652,
+      "grad_norm": 0.010595357045531273,
+      "learning_rate": 5.8266154551818225e-06,
+      "loss": 0.0001,
+      "step": 102
+    },
+    {
+      "epoch": 6.904347826086957,
+      "grad_norm": 0.011542735621333122,
+      "learning_rate": 5.616288532109225e-06,
+      "loss": 0.0002,
+      "step": 103
+    },
+    {
+      "epoch": 6.973913043478261,
+      "grad_norm": 0.051797788590192795,
+      "learning_rate": 5.4083354661298816e-06,
+      "loss": 0.0005,
+      "step": 104
+    },
+    {
+      "epoch": 6.973913043478261,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989070892333984,
+      "eval_loss": 0.0011026657884940505,
+      "eval_rejected_reward_mean": 0.0010928683914244175,
+      "eval_reward_diff_mean": 0.9978142380714417,
+      "eval_reward_diff_std": 0.008508885279297829,
+      "eval_runtime": 4.4792,
+      "eval_samples_per_second": 22.995,
+      "eval_steps_per_second": 5.805,
+      "step": 104
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.0011278060264885426,
+      "learning_rate": 5.202868867497542e-06,
+      "loss": 0.0,
+      "step": 105
+    },
+    {
+      "epoch": 7.069565217391304,
+      "grad_norm": 0.004797390196472406,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0001,
+      "step": 106
+    },
+    {
+      "epoch": 7.139130434782609,
+      "grad_norm": 0.05033459514379501,
+      "learning_rate": 4.799838720707847e-06,
+      "loss": 0.0007,
+      "step": 107
+    },
+    {
+      "epoch": 7.208695652173913,
+      "grad_norm": 0.006659619510173798,
+      "learning_rate": 4.6024934204848745e-06,
+      "loss": 0.0001,
+      "step": 108
+    },
+    {
+      "epoch": 7.208695652173913,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9988996982574463,
+      "eval_loss": 0.001110102399252355,
+      "eval_rejected_reward_mean": 0.00110039790160954,
+      "eval_reward_diff_mean": 0.9977990984916687,
+      "eval_reward_diff_std": 0.008465510793030262,
+      "eval_runtime": 4.4603,
+      "eval_samples_per_second": 23.093,
+      "eval_steps_per_second": 5.829,
+      "step": 108
+    },
+    {
+      "epoch": 7.278260869565218,
+      "grad_norm": 0.0025184813421219587,
+      "learning_rate": 4.408070965292534e-06,
+      "loss": 0.0,
+      "step": 109
+    },
+    {
+      "epoch": 7.3478260869565215,
+      "grad_norm": 0.001780255581252277,
+      "learning_rate": 4.216676638320135e-06,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 7.417391304347826,
+      "grad_norm": 0.005449565593153238,
+      "learning_rate": 4.028414082972141e-06,
+      "loss": 0.0001,
+      "step": 111
+    },
+    {
+      "epoch": 7.48695652173913,
+      "grad_norm": 0.01474890485405922,
+      "learning_rate": 3.8433852467434175e-06,
+      "loss": 0.0002,
+      "step": 112
+    },
+    {
+      "epoch": 7.48695652173913,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989209175109863,
+      "eval_loss": 0.0010885810479521751,
+      "eval_rejected_reward_mean": 0.001079102628864348,
+      "eval_reward_diff_mean": 0.9978418946266174,
+      "eval_reward_diff_std": 0.008369901217520237,
+      "eval_runtime": 4.4683,
+      "eval_samples_per_second": 23.052,
+      "eval_steps_per_second": 5.819,
+      "step": 112
+    },
+    {
+      "epoch": 7.556521739130435,
+      "grad_norm": 0.01239398680627346,
+      "learning_rate": 3.661690326012897e-06,
+      "loss": 0.0002,
+      "step": 113
+    },
+    {
+      "epoch": 7.626086956521739,
+      "grad_norm": 0.012043354101479053,
+      "learning_rate": 3.483427711785449e-06,
+      "loss": 0.0002,
+      "step": 114
+    },
+    {
+      "epoch": 7.695652173913043,
+      "grad_norm": 0.007400067988783121,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.0001,
+      "step": 115
+    },
+    {
+      "epoch": 7.765217391304348,
+      "grad_norm": 0.015701085329055786,
+      "learning_rate": 3.1375836213126653e-06,
+      "loss": 0.0003,
+      "step": 116
+    },
+    {
+      "epoch": 7.765217391304348,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989361763000488,
+      "eval_loss": 0.0010728331981226802,
+      "eval_rejected_reward_mean": 0.0010637931991368532,
+      "eval_reward_diff_mean": 0.9978724718093872,
+      "eval_reward_diff_std": 0.008171496912837029,
+      "eval_runtime": 4.489,
+      "eval_samples_per_second": 22.945,
+      "eval_steps_per_second": 5.792,
+      "step": 116
+    },
+    {
+      "epoch": 7.834782608695652,
+      "grad_norm": 0.023439966142177582,
+      "learning_rate": 2.970189425743383e-06,
+      "loss": 0.0002,
+      "step": 117
+    },
+    {
+      "epoch": 7.904347826086957,
+      "grad_norm": 0.014678899198770523,
+      "learning_rate": 2.8066019966134907e-06,
+      "loss": 0.0002,
+      "step": 118
+    },
+    {
+      "epoch": 7.973913043478261,
+      "grad_norm": 0.009870647452771664,
+      "learning_rate": 2.6469099194017144e-06,
+      "loss": 0.0002,
+      "step": 119
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.025675436481833458,
+      "learning_rate": 2.4911996701850083e-06,
+      "loss": 0.0004,
+      "step": 120
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989721775054932,
+      "eval_loss": 0.0010361903114244342,
+      "eval_rejected_reward_mean": 0.0010278514819219708,
+      "eval_reward_diff_mean": 0.9979442358016968,
+      "eval_reward_diff_std": 0.007848705165088177,
+      "eval_runtime": 4.4876,
+      "eval_samples_per_second": 22.952,
+      "eval_steps_per_second": 5.794,
+      "step": 120
+    },
+    {
+      "epoch": 8.069565217391304,
+      "grad_norm": 0.010908635333180428,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.0001,
+      "step": 121
+    },
+    {
+      "epoch": 8.139130434782608,
+      "grad_norm": 0.020105818286538124,
+      "learning_rate": 2.192059733233408e-06,
+      "loss": 0.0003,
+      "step": 122
+    },
+    {
+      "epoch": 8.208695652173914,
+      "grad_norm": 0.008475644513964653,
+      "learning_rate": 2.048792035051521e-06,
+      "loss": 0.0001,
+      "step": 123
+    },
+    {
+      "epoch": 8.278260869565218,
+      "grad_norm": 0.012479428201913834,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.0002,
+      "step": 124
+    },
+    {
+      "epoch": 8.278260869565218,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989458322525024,
+      "eval_loss": 0.0010632032062858343,
+      "eval_rejected_reward_mean": 0.0010542016243562102,
+      "eval_reward_diff_mean": 0.9978914856910706,
+      "eval_reward_diff_std": 0.008157290518283844,
+      "eval_runtime": 4.5475,
+      "eval_samples_per_second": 22.65,
+      "eval_steps_per_second": 5.717,
+      "step": 124
+    },
+    {
+      "epoch": 8.347826086956522,
+      "grad_norm": 0.00540159922093153,
+      "learning_rate": 1.7752490471933769e-06,
+      "loss": 0.0001,
+      "step": 125
+    },
+    {
+      "epoch": 8.417391304347825,
+      "grad_norm": 0.007868447341024876,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 0.0001,
+      "step": 126
+    },
+    {
+      "epoch": 8.486956521739131,
+      "grad_norm": 0.04023267701268196,
+      "learning_rate": 1.5195190384357405e-06,
+      "loss": 0.0005,
+      "step": 127
+    },
+    {
+      "epoch": 8.556521739130435,
+      "grad_norm": 0.014718690887093544,
+      "learning_rate": 1.3985085210463479e-06,
+      "loss": 0.0002,
+      "step": 128
+    },
+    {
+      "epoch": 8.556521739130435,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989545941352844,
+      "eval_loss": 0.0010542994132265449,
+      "eval_rejected_reward_mean": 0.0010454322909936309,
+      "eval_reward_diff_mean": 0.9979091882705688,
+      "eval_reward_diff_std": 0.008097290061414242,
+      "eval_runtime": 4.5176,
+      "eval_samples_per_second": 22.8,
+      "eval_steps_per_second": 5.755,
+      "step": 128
+    },
+    {
+      "epoch": 8.626086956521739,
+      "grad_norm": 0.006092917174100876,
+      "learning_rate": 1.282155863032377e-06,
+      "loss": 0.0001,
+      "step": 129
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 0.015089413151144981,
+      "learning_rate": 1.1705240714107301e-06,
+      "loss": 0.0002,
+      "step": 130
+    },
+    {
+      "epoch": 8.765217391304347,
+      "grad_norm": 0.008863482624292374,
+      "learning_rate": 1.0636735967658785e-06,
+      "loss": 0.0001,
+      "step": 131
+    },
+    {
+      "epoch": 8.834782608695653,
+      "grad_norm": 0.02049126662313938,
+      "learning_rate": 9.616623005147952e-07,
+      "loss": 0.0004,
+      "step": 132
+    },
+    {
+      "epoch": 8.834782608695653,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989612102508545,
+      "eval_loss": 0.0010475697927176952,
+      "eval_rejected_reward_mean": 0.0010388661175966263,
+      "eval_reward_diff_mean": 0.9979221820831299,
+      "eval_reward_diff_std": 0.00802167784422636,
+      "eval_runtime": 4.4869,
+      "eval_samples_per_second": 22.956,
+      "eval_steps_per_second": 5.795,
+      "step": 132
+    },
+    {
+      "epoch": 8.904347826086957,
+      "grad_norm": 0.0050810459069907665,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.0001,
+      "step": 133
+    },
+    {
+      "epoch": 8.97391304347826,
+      "grad_norm": 0.0044286418706178665,
+      "learning_rate": 7.723755564455771e-07,
+      "loss": 0.0001,
+      "step": 134
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.0036248955875635147,
+      "learning_rate": 6.852026107385756e-07,
+      "loss": 0.0,
+      "step": 135
+    },
+    {
+      "epoch": 9.069565217391304,
+      "grad_norm": 0.010801658034324646,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.0002,
+      "step": 136
+    },
+    {
+      "epoch": 9.069565217391304,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989877939224243,
+      "eval_loss": 0.0010204218560829759,
+      "eval_rejected_reward_mean": 0.0010121165541931987,
+      "eval_reward_diff_mean": 0.997975766658783,
+      "eval_reward_diff_std": 0.007839000783860683,
+      "eval_runtime": 4.5032,
+      "eval_samples_per_second": 22.872,
+      "eval_steps_per_second": 5.774,
+      "step": 136
+    },
+    {
+      "epoch": 9.139130434782608,
+      "grad_norm": 0.012117389589548111,
+      "learning_rate": 5.26033574856708e-07,
+      "loss": 0.0002,
+      "step": 137
+    },
+    {
+      "epoch": 9.208695652173914,
+      "grad_norm": 0.003176574595272541,
+      "learning_rate": 4.5412367752268094e-07,
+      "loss": 0.0001,
+      "step": 138
+    },
+    {
+      "epoch": 9.278260869565218,
+      "grad_norm": 0.006320824846625328,
+      "learning_rate": 3.8738304061681107e-07,
+      "loss": 0.0001,
+      "step": 139
+    },
+    {
+      "epoch": 9.347826086956522,
+      "grad_norm": 0.0101704066619277,
+      "learning_rate": 3.2584780537136206e-07,
+      "loss": 0.0002,
+      "step": 140
+    },
+    {
+      "epoch": 9.347826086956522,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989598989486694,
+      "eval_loss": 0.0010490770218893886,
+      "eval_rejected_reward_mean": 0.0010401182807981968,
+      "eval_reward_diff_mean": 0.9979196786880493,
+      "eval_reward_diff_std": 0.008142856881022453,
+      "eval_runtime": 4.5214,
+      "eval_samples_per_second": 22.78,
+      "eval_steps_per_second": 5.75,
+      "step": 140
+    },
+    {
+      "epoch": 9.417391304347825,
+      "grad_norm": 0.024756478145718575,
+      "learning_rate": 2.6955129420176193e-07,
+      "loss": 0.0003,
+      "step": 141
+    },
+    {
+      "epoch": 9.486956521739131,
+      "grad_norm": 0.010306237265467644,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.0002,
+      "step": 142
+    },
+    {
+      "epoch": 9.556521739130435,
+      "grad_norm": 0.0155741386115551,
+      "learning_rate": 1.7279353293586765e-07,
+      "loss": 0.0003,
+      "step": 143
+    },
+    {
+      "epoch": 9.626086956521739,
+      "grad_norm": 0.007496405392885208,
+      "learning_rate": 1.323846788742078e-07,
+      "loss": 0.0001,
+      "step": 144
+    },
+    {
+      "epoch": 9.626086956521739,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989542961120605,
+      "eval_loss": 0.0010547307319939137,
+      "eval_rejected_reward_mean": 0.0010455786250531673,
+      "eval_reward_diff_mean": 0.9979088306427002,
+      "eval_reward_diff_std": 0.00823185034096241,
+      "eval_runtime": 4.4778,
+      "eval_samples_per_second": 23.002,
+      "eval_steps_per_second": 5.806,
+      "step": 144
+    },
+    {
+      "epoch": 9.695652173913043,
+      "grad_norm": 0.005442104302346706,
+      "learning_rate": 9.731931258429638e-08,
+      "loss": 0.0001,
+      "step": 145
+    },
+    {
+      "epoch": 9.765217391304347,
+      "grad_norm": 0.01414167508482933,
+      "learning_rate": 6.761642258056977e-08,
+      "loss": 0.0002,
+      "step": 146
+    },
+    {
+      "epoch": 9.834782608695653,
+      "grad_norm": 0.03761134669184685,
+      "learning_rate": 4.329209350195651e-08,
+      "loss": 0.0004,
+      "step": 147
+    },
+    {
+      "epoch": 9.904347826086957,
+      "grad_norm": 0.01825386844575405,
+      "learning_rate": 2.4359497401758026e-08,
+      "loss": 0.0003,
+      "step": 148
+    },
+    {
+      "epoch": 9.904347826086957,
+      "eval_accuracy": 1.0,
+      "eval_chosen_reward_mean": 0.9989739060401917,
+      "eval_loss": 0.0010345983318984509,
+      "eval_rejected_reward_mean": 0.0010260696290060878,
+      "eval_reward_diff_mean": 0.9979478716850281,
+      "eval_reward_diff_std": 0.00794169120490551,
+      "eval_runtime": 4.4631,
+      "eval_samples_per_second": 23.078,
+      "eval_steps_per_second": 5.826,
+      "step": 148
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 4,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-148/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e249bfe738f76b012a48ae96051d6acbc9f526f5b8c04df8582eb498ce0b0f6
+size 6097

checkpoint-150/README.md

@@ -0,0 +1,208 @@
+---
+base_model: meta-llama/Llama-3.2-3B-Instruct
+library_name: peft
+tags:
+- base_model:adapter:meta-llama/Llama-3.2-3B-Instruct
+- lora
+- reward-trainer
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-150/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85de884fec6504e4d599fee17b17c3ad13f8c05d74a846b11ce4ae2b12a47fd5
+size 97313784

checkpoint-150/chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22b3ddabb1caa778692aa4f8e25c239992822fc86818828831aa37f95c3b0d2
+size 194859518

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98b57040a2833b72117d0b761ba5ddf331a12f933f8e56765e492af63cdad1f
+size 14645

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f885c866d4a583bb5c55b8e50e4b81779038e1f0070d9faa7efbe59fd7bdac1f
+size 1465

checkpoint-150/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoint-150/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52716f60c3ad328509fa37cdded9a2f1196ecae463f5480f5d38c66a25e7a7dc
+size 17210019