Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,14 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+<|im_start|>assistant
+{{ else if eq .Role "assistant" }}{{ .Content }}<|im_end|>
+{{ end }}{{ end }}"""
+
+PARAMETER stop "<|im_end|>"
+PARAMETER num_ctx 4096

README.md

@@ -0,0 +1,92 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-30B-A3B
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: Qwen3-30B-A3B-alpaca-th-52k-dolly-th-15k-wangchan-instruct-seed-2405
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen3-30B-A3B-alpaca-th-52k-dolly-th-15k-wangchan-instruct-seed-2405
+
+This model is a fine-tuned version of [Qwen/Qwen3-30B-A3B](https://huggingface.co//Qwen/Qwen3-30B-A3B) on the alpaca-th-52k, the dolly-th-15k and the wangchan-instruct datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.6547
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 2405
+- distributed_type: multi-GPU
+- num_devices: 64
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 1024
+- total_eval_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9539        | 0.1149 | 10   | 0.9961          |
+| 0.8283        | 0.2299 | 20   | 0.8131          |
+| 0.7525        | 0.3448 | 30   | 0.7719          |
+| 0.7418        | 0.4598 | 40   | 0.7480          |
+| 0.7291        | 0.5747 | 50   | 0.7320          |
+| 0.7244        | 0.6897 | 60   | 0.7189          |
+| 0.721         | 0.8046 | 70   | 0.7085          |
+| 0.6964        | 0.9195 | 80   | 0.6999          |
+| 0.6965        | 1.0345 | 90   | 0.6928          |
+| 0.6856        | 1.1494 | 100  | 0.6869          |
+| 0.6812        | 1.2644 | 110  | 0.6803          |
+| 0.6734        | 1.3793 | 120  | 0.6736          |
+| 0.658         | 1.4943 | 130  | 0.6697          |
+| 0.6703        | 1.6092 | 140  | 0.6661          |
+| 0.6814        | 1.7241 | 150  | 0.6631          |
+| 0.6688        | 1.8391 | 160  | 0.6607          |
+| 0.6781        | 1.9540 | 170  | 0.6587          |
+| 0.618         | 2.0690 | 180  | 0.6582          |
+| 0.6575        | 2.1839 | 190  | 0.6572          |
+| 0.6372        | 2.2989 | 200  | 0.6563          |
+| 0.617         | 2.4138 | 210  | 0.6558          |
+| 0.6152        | 2.5287 | 220  | 0.6552          |
+| 0.6407        | 2.6437 | 230  | 0.6549          |
+| 0.6498        | 2.7586 | 240  | 0.6548          |
+| 0.6365        | 2.8736 | 250  | 0.6547          |
+| 0.6532        | 2.9885 | 260  | 0.6547          |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.3
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d58e2b6c01895039653c8fe1689add6f3c21939ce9ab3b61882dc632067568b
+size 1696378232

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6547390818595886,
+    "eval_runtime": 593.5859,
+    "eval_samples_per_second": 16.675,
+    "eval_steps_per_second": 0.131,
+    "total_flos": 4.878497427033686e+19,
+    "train_loss": 0.6974607110023499,
+    "train_runtime": 68284.7248,
+    "train_samples_per_second": 3.914,
+    "train_steps_per_second": 0.004
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B
+library_name: peft
+---
+
+# 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 0.15.2

checkpoint-200/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,1594 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2988505747126435,
+  "eval_steps": 10,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011494252873563218,
+      "grad_norm": 0.45773613452911377,
+      "learning_rate": 0.0,
+      "loss": 1.065,
+      "step": 1
+    },
+    {
+      "epoch": 0.022988505747126436,
+      "grad_norm": 0.4720604717731476,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.1025,
+      "step": 2
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.4526257812976837,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 1.067,
+      "step": 3
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.44910383224487305,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 1.0694,
+      "step": 4
+    },
+    {
+      "epoch": 0.05747126436781609,
+      "grad_norm": 0.4383523762226105,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 1.0767,
+      "step": 5
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.4290314018726349,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 1.0414,
+      "step": 6
+    },
+    {
+      "epoch": 0.08045977011494253,
+      "grad_norm": 0.4098808467388153,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.021,
+      "step": 7
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.4100661277770996,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 1.0113,
+      "step": 8
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 0.37694185972213745,
+      "learning_rate": 5.925925925925926e-05,
+      "loss": 0.9566,
+      "step": 9
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 0.3378658890724182,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.9539,
+      "step": 10
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "eval_loss": 0.9960598945617676,
+      "eval_runtime": 605.6954,
+      "eval_samples_per_second": 16.342,
+      "eval_steps_per_second": 0.129,
+      "step": 10
+    },
+    {
+      "epoch": 0.12643678160919541,
+      "grad_norm": 0.29339659214019775,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.9163,
+      "step": 11
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.23120510578155518,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.8886,
+      "step": 12
+    },
+    {
+      "epoch": 0.14942528735632185,
+      "grad_norm": 0.18651129305362701,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.8748,
+      "step": 13
+    },
+    {
+      "epoch": 0.16091954022988506,
+      "grad_norm": 0.14475475251674652,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.8235,
+      "step": 14
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.11758769303560257,
+      "learning_rate": 0.0001037037037037037,
+      "loss": 0.8539,
+      "step": 15
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.10646044462919235,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.8363,
+      "step": 16
+    },
+    {
+      "epoch": 0.19540229885057472,
+      "grad_norm": 0.10539838671684265,
+      "learning_rate": 0.00011851851851851852,
+      "loss": 0.819,
+      "step": 17
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.11887332051992416,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 0.8069,
+      "step": 18
+    },
+    {
+      "epoch": 0.21839080459770116,
+      "grad_norm": 0.1281956136226654,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.8042,
+      "step": 19
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.1338774859905243,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 0.8283,
+      "step": 20
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "eval_loss": 0.813089907169342,
+      "eval_runtime": 601.317,
+      "eval_samples_per_second": 16.461,
+      "eval_steps_per_second": 0.13,
+      "step": 20
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 0.12568038702011108,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.8142,
+      "step": 21
+    },
+    {
+      "epoch": 0.25287356321839083,
+      "grad_norm": 0.11528006941080093,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.794,
+      "step": 22
+    },
+    {
+      "epoch": 0.26436781609195403,
+      "grad_norm": 0.10474701225757599,
+      "learning_rate": 0.00016296296296296295,
+      "loss": 0.8231,
+      "step": 23
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.09240291267633438,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.7874,
+      "step": 24
+    },
+    {
+      "epoch": 0.28735632183908044,
+      "grad_norm": 0.07213829457759857,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.8075,
+      "step": 25
+    },
+    {
+      "epoch": 0.2988505747126437,
+      "grad_norm": 0.0564056895673275,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 0.779,
+      "step": 26
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 0.04973220080137253,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 0.7878,
+      "step": 27
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.04492342844605446,
+      "learning_rate": 0.0002,
+      "loss": 0.7876,
+      "step": 28
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.050321951508522034,
+      "learning_rate": 0.00019999098778567212,
+      "loss": 0.7686,
+      "step": 29
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.05602027848362923,
+      "learning_rate": 0.00019996395276708856,
+      "loss": 0.7525,
+      "step": 30
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "eval_loss": 0.7719228863716125,
+      "eval_runtime": 606.7346,
+      "eval_samples_per_second": 16.314,
+      "eval_steps_per_second": 0.129,
+      "step": 30
+    },
+    {
+      "epoch": 0.3563218390804598,
+      "grad_norm": 0.055378761142492294,
+      "learning_rate": 0.00019991889981715698,
+      "loss": 0.777,
+      "step": 31
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.052891045808792114,
+      "learning_rate": 0.00019985583705641418,
+      "loss": 0.7797,
+      "step": 32
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 0.044340070337057114,
+      "learning_rate": 0.00019977477585156252,
+      "loss": 0.7744,
+      "step": 33
+    },
+    {
+      "epoch": 0.39080459770114945,
+      "grad_norm": 0.037772953510284424,
+      "learning_rate": 0.00019967573081342103,
+      "loss": 0.7631,
+      "step": 34
+    },
+    {
+      "epoch": 0.40229885057471265,
+      "grad_norm": 0.03553105518221855,
+      "learning_rate": 0.0001995587197942919,
+      "loss": 0.7512,
+      "step": 35
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.0346490740776062,
+      "learning_rate": 0.0001994237638847428,
+      "loss": 0.7567,
+      "step": 36
+    },
+    {
+      "epoch": 0.42528735632183906,
+      "grad_norm": 0.03471450135111809,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 0.7723,
+      "step": 37
+    },
+    {
+      "epoch": 0.4367816091954023,
+      "grad_norm": 0.03868038207292557,
+      "learning_rate": 0.00019910011792459087,
+      "loss": 0.77,
+      "step": 38
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 0.04141271859407425,
+      "learning_rate": 0.00019891148620932318,
+      "loss": 0.7764,
+      "step": 39
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.04017995670437813,
+      "learning_rate": 0.00019870502626379127,
+      "loss": 0.7418,
+      "step": 40
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "eval_loss": 0.7480100393295288,
+      "eval_runtime": 601.4446,
+      "eval_samples_per_second": 16.457,
+      "eval_steps_per_second": 0.13,
+      "step": 40
+    },
+    {
+      "epoch": 0.47126436781609193,
+      "grad_norm": 0.04055652394890785,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.7487,
+      "step": 41
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.03968408331274986,
+      "learning_rate": 0.00019823877374156647,
+      "loss": 0.7417,
+      "step": 42
+    },
+    {
+      "epoch": 0.4942528735632184,
+      "grad_norm": 0.03533465415239334,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 0.7437,
+      "step": 43
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.03385720029473305,
+      "learning_rate": 0.00019770169650018172,
+      "loss": 0.7752,
+      "step": 44
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.030534420162439346,
+      "learning_rate": 0.00019740671762355548,
+      "loss": 0.7363,
+      "step": 45
+    },
+    {
+      "epoch": 0.5287356321839081,
+      "grad_norm": 0.02837216667830944,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 0.74,
+      "step": 46
+    },
+    {
+      "epoch": 0.5402298850574713,
+      "grad_norm": 0.02879689820110798,
+      "learning_rate": 0.00019676414519013781,
+      "loss": 0.7246,
+      "step": 47
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.02807699516415596,
+      "learning_rate": 0.00019641666745335624,
+      "loss": 0.7465,
+      "step": 48
+    },
+    {
+      "epoch": 0.5632183908045977,
+      "grad_norm": 0.029897579923272133,
+      "learning_rate": 0.00019605181116313724,
+      "loss": 0.721,
+      "step": 49
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "grad_norm": 0.028458919376134872,
+      "learning_rate": 0.00019566964208274254,
+      "loss": 0.7291,
+      "step": 50
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "eval_loss": 0.7319945096969604,
+      "eval_runtime": 601.7402,
+      "eval_samples_per_second": 16.449,
+      "eval_steps_per_second": 0.13,
+      "step": 50
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.028347671031951904,
+      "learning_rate": 0.00019527022909596536,
+      "loss": 0.7396,
+      "step": 51
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.028352508321404457,
+      "learning_rate": 0.00019485364419471454,
+      "loss": 0.733,
+      "step": 52
+    },
+    {
+      "epoch": 0.6091954022988506,
+      "grad_norm": 0.025768019258975983,
+      "learning_rate": 0.00019441996246603846,
+      "loss": 0.7378,
+      "step": 53
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.0259398240596056,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.7293,
+      "step": 54
+    },
+    {
+      "epoch": 0.632183908045977,
+      "grad_norm": 0.024649152532219887,
+      "learning_rate": 0.0001935016242685415,
+      "loss": 0.7287,
+      "step": 55
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.026843328028917313,
+      "learning_rate": 0.00019301713332493386,
+      "loss": 0.7354,
+      "step": 56
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.028928296640515327,
+      "learning_rate": 0.00019251587657449236,
+      "loss": 0.7376,
+      "step": 57
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.027994588017463684,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 0.7389,
+      "step": 58
+    },
+    {
+      "epoch": 0.6781609195402298,
+      "grad_norm": 0.027422698214650154,
+      "learning_rate": 0.00019146343005342547,
+      "loss": 0.7275,
+      "step": 59
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.02938409335911274,
+      "learning_rate": 0.0001909124299802724,
+      "loss": 0.7244,
+      "step": 60
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "eval_loss": 0.7189474701881409,
+      "eval_runtime": 605.038,
+      "eval_samples_per_second": 16.359,
+      "eval_steps_per_second": 0.129,
+      "step": 60
+    },
+    {
+      "epoch": 0.7011494252873564,
+      "grad_norm": 0.02854277938604355,
+      "learning_rate": 0.00019034504346103823,
+      "loss": 0.7339,
+      "step": 61
+    },
+    {
+      "epoch": 0.7126436781609196,
+      "grad_norm": 0.028162814676761627,
+      "learning_rate": 0.0001897613727639014,
+      "loss": 0.7349,
+      "step": 62
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.027026742696762085,
+      "learning_rate": 0.0001891615230921703,
+      "loss": 0.7008,
+      "step": 63
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.02867995575070381,
+      "learning_rate": 0.000188545602565321,
+      "loss": 0.7404,
+      "step": 64
+    },
+    {
+      "epoch": 0.7471264367816092,
+      "grad_norm": 0.025570319965481758,
+      "learning_rate": 0.00018791372219950948,
+      "loss": 0.7203,
+      "step": 65
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.026673492044210434,
+      "learning_rate": 0.00018726599588756145,
+      "loss": 0.7188,
+      "step": 66
+    },
+    {
+      "epoch": 0.7701149425287356,
+      "grad_norm": 0.028060389682650566,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.7129,
+      "step": 67
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.025640789419412613,
+      "learning_rate": 0.0001859234752562217,
+      "loss": 0.7081,
+      "step": 68
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.026264475658535957,
+      "learning_rate": 0.00018522892291850335,
+      "loss": 0.6971,
+      "step": 69
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "grad_norm": 0.028900163248181343,
+      "learning_rate": 0.0001845190085543795,
+      "loss": 0.721,
+      "step": 70
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "eval_loss": 0.7084506154060364,
+      "eval_runtime": 603.3937,
+      "eval_samples_per_second": 16.404,
+      "eval_steps_per_second": 0.129,
+      "step": 70
+    },
+    {
+      "epoch": 0.8160919540229885,
+      "grad_norm": 0.02878301776945591,
+      "learning_rate": 0.00018379386012185814,
+      "loss": 0.7192,
+      "step": 71
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.028177903965115547,
+      "learning_rate": 0.00018305360832480117,
+      "loss": 0.7258,
+      "step": 72
+    },
+    {
+      "epoch": 0.8390804597701149,
+      "grad_norm": 0.027689015492796898,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 0.7327,
+      "step": 73
+    },
+    {
+      "epoch": 0.8505747126436781,
+      "grad_norm": 0.027420515194535255,
+      "learning_rate": 0.00018152833103995443,
+      "loss": 0.7007,
+      "step": 74
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.02628767490386963,
+      "learning_rate": 0.0001807435804746807,
+      "loss": 0.7106,
+      "step": 75
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.027107784524559975,
+      "learning_rate": 0.00017994427634035015,
+      "loss": 0.7056,
+      "step": 76
+    },
+    {
+      "epoch": 0.8850574712643678,
+      "grad_norm": 0.026692209765315056,
+      "learning_rate": 0.0001791305627069662,
+      "loss": 0.6898,
+      "step": 77
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.02739943191409111,
+      "learning_rate": 0.00017830258624176225,
+      "loss": 0.71,
+      "step": 78
+    },
+    {
+      "epoch": 0.9080459770114943,
+      "grad_norm": 0.027159228920936584,
+      "learning_rate": 0.00017746049618276545,
+      "loss": 0.7104,
+      "step": 79
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.027961738407611847,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.6964,
+      "step": 80
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "eval_loss": 0.6998673677444458,
+      "eval_runtime": 599.046,
+      "eval_samples_per_second": 16.523,
+      "eval_steps_per_second": 0.13,
+      "step": 80
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.028458958491683006,
+      "learning_rate": 0.00017573458492761801,
+      "loss": 0.7048,
+      "step": 81
+    },
+    {
+      "epoch": 0.9425287356321839,
+      "grad_norm": 0.0295415036380291,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 0.7089,
+      "step": 82
+    },
+    {
+      "epoch": 0.9540229885057471,
+      "grad_norm": 0.027641592547297478,
+      "learning_rate": 0.00017395407322802372,
+      "loss": 0.7184,
+      "step": 83
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.029828142374753952,
+      "learning_rate": 0.00017304374183977033,
+      "loss": 0.6878,
+      "step": 84
+    },
+    {
+      "epoch": 0.9770114942528736,
+      "grad_norm": 0.029184194281697273,
+      "learning_rate": 0.00017212024473438147,
+      "loss": 0.7223,
+      "step": 85
+    },
+    {
+      "epoch": 0.9885057471264368,
+      "grad_norm": 0.02929309941828251,
+      "learning_rate": 0.00017118374836693406,
+      "loss": 0.6936,
+      "step": 86
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.03450490161776543,
+      "learning_rate": 0.00017023442153554777,
+      "loss": 0.6906,
+      "step": 87
+    },
+    {
+      "epoch": 1.0114942528735633,
+      "grad_norm": 0.03116275928914547,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 0.6915,
+      "step": 88
+    },
+    {
+      "epoch": 1.0229885057471264,
+      "grad_norm": 0.03145065903663635,
+      "learning_rate": 0.00016829796320568416,
+      "loss": 0.6792,
+      "step": 89
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.03122427873313427,
+      "learning_rate": 0.00016731118074275704,
+      "loss": 0.6965,
+      "step": 90
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "eval_loss": 0.6928127408027649,
+      "eval_runtime": 606.6499,
+      "eval_samples_per_second": 16.316,
+      "eval_steps_per_second": 0.129,
+      "step": 90
+    },
+    {
+      "epoch": 1.0459770114942528,
+      "grad_norm": 0.030179064720869064,
+      "learning_rate": 0.00016631226582407952,
+      "loss": 0.6726,
+      "step": 91
+    },
+    {
+      "epoch": 1.0574712643678161,
+      "grad_norm": 0.029219962656497955,
+      "learning_rate": 0.0001653013984983585,
+      "loss": 0.6792,
+      "step": 92
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.02873355709016323,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.6921,
+      "step": 93
+    },
+    {
+      "epoch": 1.0804597701149425,
+      "grad_norm": 0.029455283656716347,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 0.6829,
+      "step": 94
+    },
+    {
+      "epoch": 1.0919540229885056,
+      "grad_norm": 0.030247965827584267,
+      "learning_rate": 0.0001621989146838704,
+      "loss": 0.6737,
+      "step": 95
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.029829107224941254,
+      "learning_rate": 0.00016114208080920123,
+      "loss": 0.6852,
+      "step": 96
+    },
+    {
+      "epoch": 1.1149425287356323,
+      "grad_norm": 0.031125420704483986,
+      "learning_rate": 0.0001600742264237979,
+      "loss": 0.6863,
+      "step": 97
+    },
+    {
+      "epoch": 1.1264367816091954,
+      "grad_norm": 0.029601775109767914,
+      "learning_rate": 0.00015899554400231232,
+      "loss": 0.6785,
+      "step": 98
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.031090950593352318,
+      "learning_rate": 0.0001579062279710879,
+      "loss": 0.7001,
+      "step": 99
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 0.030084125697612762,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 0.6856,
+      "step": 100
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "eval_loss": 0.686887264251709,
+      "eval_runtime": 599.4005,
+      "eval_samples_per_second": 16.513,
+      "eval_steps_per_second": 0.13,
+      "step": 100
+    },
+    {
+      "epoch": 1.160919540229885,
+      "grad_norm": 0.03157448023557663,
+      "learning_rate": 0.00015569648233264394,
+      "loss": 0.6836,
+      "step": 101
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.032123371958732605,
+      "learning_rate": 0.00015457645101945046,
+      "loss": 0.6827,
+      "step": 102
+    },
+    {
+      "epoch": 1.1839080459770115,
+      "grad_norm": 0.03208347037434578,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 0.6823,
+      "step": 103
+    },
+    {
+      "epoch": 1.1954022988505748,
+      "grad_norm": 0.030994586646556854,
+      "learning_rate": 0.00015230708076495775,
+      "loss": 0.6729,
+      "step": 104
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.03224639222025871,
+      "learning_rate": 0.00015115815086468102,
+      "loss": 0.6778,
+      "step": 105
+    },
+    {
+      "epoch": 1.2183908045977012,
+      "grad_norm": 0.030437005683779716,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.674,
+      "step": 106
+    },
+    {
+      "epoch": 1.2298850574712643,
+      "grad_norm": 0.030820753425359726,
+      "learning_rate": 0.00014883283692099112,
+      "loss": 0.6799,
+      "step": 107
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.03301486000418663,
+      "learning_rate": 0.0001476568720021308,
+      "loss": 0.6851,
+      "step": 108
+    },
+    {
+      "epoch": 1.2528735632183907,
+      "grad_norm": 0.033183734863996506,
+      "learning_rate": 0.00014647231720437686,
+      "loss": 0.7094,
+      "step": 109
+    },
+    {
+      "epoch": 1.264367816091954,
+      "grad_norm": 0.03154841437935829,
+      "learning_rate": 0.00014527938603696376,
+      "loss": 0.6812,
+      "step": 110
+    },
+    {
+      "epoch": 1.264367816091954,
+      "eval_loss": 0.6802834868431091,
+      "eval_runtime": 597.3843,
+      "eval_samples_per_second": 16.569,
+      "eval_steps_per_second": 0.131,
+      "step": 110
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.03554477170109749,
+      "learning_rate": 0.00014407829351891857,
+      "loss": 0.679,
+      "step": 111
+    },
+    {
+      "epoch": 1.2873563218390804,
+      "grad_norm": 0.03362204134464264,
+      "learning_rate": 0.00014286925614030542,
+      "loss": 0.6722,
+      "step": 112
+    },
+    {
+      "epoch": 1.2988505747126438,
+      "grad_norm": 0.032853253185749054,
+      "learning_rate": 0.00014165249182320402,
+      "loss": 0.6879,
+      "step": 113
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.033823542296886444,
+      "learning_rate": 0.0001404282198824305,
+      "loss": 0.6627,
+      "step": 114
+    },
+    {
+      "epoch": 1.3218390804597702,
+      "grad_norm": 0.0326109379529953,
+      "learning_rate": 0.00013919666098600753,
+      "loss": 0.6751,
+      "step": 115
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.03431953117251396,
+      "learning_rate": 0.00013795803711538966,
+      "loss": 0.6827,
+      "step": 116
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.03328808769583702,
+      "learning_rate": 0.00013671257152545277,
+      "loss": 0.6648,
+      "step": 117
+    },
+    {
+      "epoch": 1.3563218390804597,
+      "grad_norm": 0.035666704177856445,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.6771,
+      "step": 118
+    },
+    {
+      "epoch": 1.367816091954023,
+      "grad_norm": 0.03441452234983444,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.6623,
+      "step": 119
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.03363391384482384,
+      "learning_rate": 0.00013293737524320797,
+      "loss": 0.6734,
+      "step": 120
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "eval_loss": 0.6736027002334595,
+      "eval_runtime": 601.0855,
+      "eval_samples_per_second": 16.467,
+      "eval_steps_per_second": 0.13,
+      "step": 120
+    },
+    {
+      "epoch": 1.3908045977011494,
+      "grad_norm": 0.03441128134727478,
+      "learning_rate": 0.00013166679938014726,
+      "loss": 0.6625,
+      "step": 121
+    },
+    {
+      "epoch": 1.4022988505747127,
+      "grad_norm": 0.03332269564270973,
+      "learning_rate": 0.0001303905157574247,
+      "loss": 0.6738,
+      "step": 122
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.03411813825368881,
+      "learning_rate": 0.00012910875441787128,
+      "loss": 0.6511,
+      "step": 123
+    },
+    {
+      "epoch": 1.4252873563218391,
+      "grad_norm": 0.034489769488573074,
+      "learning_rate": 0.0001278217463916453,
+      "loss": 0.6579,
+      "step": 124
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "grad_norm": 0.03562283143401146,
+      "learning_rate": 0.0001265297236545901,
+      "loss": 0.6508,
+      "step": 125
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.034433409571647644,
+      "learning_rate": 0.00012523291908642217,
+      "loss": 0.6867,
+      "step": 126
+    },
+    {
+      "epoch": 1.4597701149425286,
+      "grad_norm": 0.034091442823410034,
+      "learning_rate": 0.0001239315664287558,
+      "loss": 0.6609,
+      "step": 127
+    },
+    {
+      "epoch": 1.471264367816092,
+      "grad_norm": 0.034659866243600845,
+      "learning_rate": 0.00012262590024297225,
+      "loss": 0.6708,
+      "step": 128
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.03355137258768082,
+      "learning_rate": 0.0001213161558679416,
+      "loss": 0.6853,
+      "step": 129
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "grad_norm": 0.03497845306992531,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 0.658,
+      "step": 130
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "eval_loss": 0.6697064638137817,
+      "eval_runtime": 595.4108,
+      "eval_samples_per_second": 16.624,
+      "eval_steps_per_second": 0.131,
+      "step": 130
+    },
+    {
+      "epoch": 1.5057471264367817,
+      "grad_norm": 0.03422487527132034,
+      "learning_rate": 0.00011868537753842051,
+      "loss": 0.6688,
+      "step": 131
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.034450776875019073,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.6828,
+      "step": 132
+    },
+    {
+      "epoch": 1.528735632183908,
+      "grad_norm": 0.034574706107378006,
+      "learning_rate": 0.00011604112808577603,
+      "loss": 0.6776,
+      "step": 133
+    },
+    {
+      "epoch": 1.5402298850574714,
+      "grad_norm": 0.03596516326069832,
+      "learning_rate": 0.00011471454708317162,
+      "loss": 0.6276,
+      "step": 134
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.035429686307907104,
+      "learning_rate": 0.00011338531386752618,
+      "loss": 0.6427,
+      "step": 135
+    },
+    {
+      "epoch": 1.5632183908045976,
+      "grad_norm": 0.033536769449710846,
+      "learning_rate": 0.0001120536680255323,
+      "loss": 0.652,
+      "step": 136
+    },
+    {
+      "epoch": 1.5747126436781609,
+      "grad_norm": 0.03417116403579712,
+      "learning_rate": 0.00011071984957874479,
+      "loss": 0.6725,
+      "step": 137
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.03480486571788788,
+      "learning_rate": 0.00010938409894031794,
+      "loss": 0.6479,
+      "step": 138
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "grad_norm": 0.03562786802649498,
+      "learning_rate": 0.00010804665687167262,
+      "loss": 0.6681,
+      "step": 139
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "grad_norm": 0.034858204424381256,
+      "learning_rate": 0.00010670776443910024,
+      "loss": 0.6703,
+      "step": 140
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "eval_loss": 0.6661256551742554,
+      "eval_runtime": 590.9429,
+      "eval_samples_per_second": 16.75,
+      "eval_steps_per_second": 0.132,
+      "step": 140
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.03447253257036209,
+      "learning_rate": 0.00010536766297031215,
+      "loss": 0.6643,
+      "step": 141
+    },
+    {
+      "epoch": 1.632183908045977,
+      "grad_norm": 0.03508715331554413,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 0.6583,
+      "step": 142
+    },
+    {
+      "epoch": 1.6436781609195403,
+      "grad_norm": 0.0343579463660717,
+      "learning_rate": 0.00010268479928100614,
+      "loss": 0.6753,
+      "step": 143
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.0350567027926445,
+      "learning_rate": 0.00010134252063133975,
+      "loss": 0.6493,
+      "step": 144
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.034686826169490814,
+      "learning_rate": 0.0001,
+      "loss": 0.6515,
+      "step": 145
+    },
+    {
+      "epoch": 1.6781609195402298,
+      "grad_norm": 0.035702142864465714,
+      "learning_rate": 9.865747936866027e-05,
+      "loss": 0.6638,
+      "step": 146
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.034140318632125854,
+      "learning_rate": 9.73152007189939e-05,
+      "loss": 0.6496,
+      "step": 147
+    },
+    {
+      "epoch": 1.7011494252873565,
+      "grad_norm": 0.038083408027887344,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 0.6893,
+      "step": 148
+    },
+    {
+      "epoch": 1.7126436781609196,
+      "grad_norm": 0.03810959309339523,
+      "learning_rate": 9.463233702968783e-05,
+      "loss": 0.6728,
+      "step": 149
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.033978622406721115,
+      "learning_rate": 9.329223556089975e-05,
+      "loss": 0.6814,
+      "step": 150
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "eval_loss": 0.6631415486335754,
+      "eval_runtime": 596.1091,
+      "eval_samples_per_second": 16.604,
+      "eval_steps_per_second": 0.131,
+      "step": 150
+    },
+    {
+      "epoch": 1.735632183908046,
+      "grad_norm": 0.03391426429152489,
+      "learning_rate": 9.195334312832742e-05,
+      "loss": 0.6421,
+      "step": 151
+    },
+    {
+      "epoch": 1.7471264367816093,
+      "grad_norm": 0.03562890738248825,
+      "learning_rate": 9.061590105968208e-05,
+      "loss": 0.6739,
+      "step": 152
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.03706149384379387,
+      "learning_rate": 8.928015042125523e-05,
+      "loss": 0.6579,
+      "step": 153
+    },
+    {
+      "epoch": 1.7701149425287355,
+      "grad_norm": 0.03591468557715416,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.645,
+      "step": 154
+    },
+    {
+      "epoch": 1.7816091954022988,
+      "grad_norm": 0.03639413043856621,
+      "learning_rate": 8.661468613247387e-05,
+      "loss": 0.6594,
+      "step": 155
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 0.03598083183169365,
+      "learning_rate": 8.528545291682838e-05,
+      "loss": 0.6723,
+      "step": 156
+    },
+    {
+      "epoch": 1.8045977011494254,
+      "grad_norm": 0.03628537803888321,
+      "learning_rate": 8.395887191422397e-05,
+      "loss": 0.6715,
+      "step": 157
+    },
+    {
+      "epoch": 1.8160919540229885,
+      "grad_norm": 0.03826047480106354,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.6767,
+      "step": 158
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.03769649192690849,
+      "learning_rate": 8.131462246157953e-05,
+      "loss": 0.6552,
+      "step": 159
+    },
+    {
+      "epoch": 1.839080459770115,
+      "grad_norm": 0.03599262982606888,
+      "learning_rate": 7.999743062239557e-05,
+      "loss": 0.6688,
+      "step": 160
+    },
+    {
+      "epoch": 1.839080459770115,
+      "eval_loss": 0.6607028245925903,
+      "eval_runtime": 589.6737,
+      "eval_samples_per_second": 16.786,
+      "eval_steps_per_second": 0.132,
+      "step": 160
+    },
+    {
+      "epoch": 1.8505747126436782,
+      "grad_norm": 0.03584510087966919,
+      "learning_rate": 7.868384413205842e-05,
+      "loss": 0.672,
+      "step": 161
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 0.03545341268181801,
+      "learning_rate": 7.73740997570278e-05,
+      "loss": 0.6629,
+      "step": 162
+    },
+    {
+      "epoch": 1.8735632183908046,
+      "grad_norm": 0.035858072340488434,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 0.6391,
+      "step": 163
+    },
+    {
+      "epoch": 1.8850574712643677,
+      "grad_norm": 0.035794083029031754,
+      "learning_rate": 7.476708091357782e-05,
+      "loss": 0.6516,
+      "step": 164
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.03674920275807381,
+      "learning_rate": 7.347027634540993e-05,
+      "loss": 0.6624,
+      "step": 165
+    },
+    {
+      "epoch": 1.9080459770114944,
+      "grad_norm": 0.034701887518167496,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.6574,
+      "step": 166
+    },
+    {
+      "epoch": 1.9195402298850575,
+      "grad_norm": 0.03606560826301575,
+      "learning_rate": 7.089124558212871e-05,
+      "loss": 0.6668,
+      "step": 167
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.03570757061243057,
+      "learning_rate": 6.960948424257532e-05,
+      "loss": 0.6358,
+      "step": 168
+    },
+    {
+      "epoch": 1.9425287356321839,
+      "grad_norm": 0.034459397196769714,
+      "learning_rate": 6.833320061985277e-05,
+      "loss": 0.6294,
+      "step": 169
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "grad_norm": 0.035828083753585815,
+      "learning_rate": 6.706262475679205e-05,
+      "loss": 0.6781,
+      "step": 170
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "eval_loss": 0.6586677432060242,
+      "eval_runtime": 590.832,
+      "eval_samples_per_second": 16.753,
+      "eval_steps_per_second": 0.132,
+      "step": 170
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.03741836175322533,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 0.6679,
+      "step": 171
+    },
+    {
+      "epoch": 1.9770114942528736,
+      "grad_norm": 0.03573041409254074,
+      "learning_rate": 6.453951129574644e-05,
+      "loss": 0.6805,
+      "step": 172
+    },
+    {
+      "epoch": 1.9885057471264367,
+      "grad_norm": 0.03586418181657791,
+      "learning_rate": 6.328742847454724e-05,
+      "loss": 0.6606,
+      "step": 173
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.03636249899864197,
+      "learning_rate": 6.204196288461037e-05,
+      "loss": 0.6962,
+      "step": 174
+    },
+    {
+      "epoch": 2.0114942528735633,
+      "grad_norm": 0.04032210260629654,
+      "learning_rate": 6.080333901399251e-05,
+      "loss": 0.6426,
+      "step": 175
+    },
+    {
+      "epoch": 2.0229885057471266,
+      "grad_norm": 0.039117176085710526,
+      "learning_rate": 5.957178011756952e-05,
+      "loss": 0.6418,
+      "step": 176
+    },
+    {
+      "epoch": 2.0344827586206895,
+      "grad_norm": 0.037345871329307556,
+      "learning_rate": 5.834750817679606e-05,
+      "loss": 0.6406,
+      "step": 177
+    },
+    {
+      "epoch": 2.045977011494253,
+      "grad_norm": 0.03830842301249504,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.6262,
+      "step": 178
+    },
+    {
+      "epoch": 2.057471264367816,
+      "grad_norm": 0.037265144288539886,
+      "learning_rate": 5.59217064810814e-05,
+      "loss": 0.6385,
+      "step": 179
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.03784786909818649,
+      "learning_rate": 5.472061396303629e-05,
+      "loss": 0.618,
+      "step": 180
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "eval_loss": 0.6581570506095886,
+      "eval_runtime": 593.2384,
+      "eval_samples_per_second": 16.685,
+      "eval_steps_per_second": 0.131,
+      "step": 180
+    },
+    {
+      "epoch": 2.0804597701149423,
+      "grad_norm": 0.03711731731891632,
+      "learning_rate": 5.3527682795623146e-05,
+      "loss": 0.6354,
+      "step": 181
+    },
+    {
+      "epoch": 2.0919540229885056,
+      "grad_norm": 0.037277545779943466,
+      "learning_rate": 5.234312799786921e-05,
+      "loss": 0.631,
+      "step": 182
+    },
+    {
+      "epoch": 2.103448275862069,
+      "grad_norm": 0.040995873510837555,
+      "learning_rate": 5.116716307900893e-05,
+      "loss": 0.631,
+      "step": 183
+    },
+    {
+      "epoch": 2.1149425287356323,
+      "grad_norm": 0.038000449538230896,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.6691,
+      "step": 184
+    },
+    {
+      "epoch": 2.1264367816091956,
+      "grad_norm": 0.03552795201539993,
+      "learning_rate": 4.884184913531902e-05,
+      "loss": 0.6147,
+      "step": 185
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 0.03610774129629135,
+      "learning_rate": 4.7692919235042255e-05,
+      "loss": 0.6259,
+      "step": 186
+    },
+    {
+      "epoch": 2.1494252873563218,
+      "grad_norm": 0.038160186260938644,
+      "learning_rate": 4.6553417387219886e-05,
+      "loss": 0.6375,
+      "step": 187
+    },
+    {
+      "epoch": 2.160919540229885,
+      "grad_norm": 0.03843645006418228,
+      "learning_rate": 4.542354898054953e-05,
+      "loss": 0.6329,
+      "step": 188
+    },
+    {
+      "epoch": 2.1724137931034484,
+      "grad_norm": 0.03745341673493385,
+      "learning_rate": 4.430351766735609e-05,
+      "loss": 0.6379,
+      "step": 189
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "grad_norm": 0.03651278465986252,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.6575,
+      "step": 190
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "eval_loss": 0.657158374786377,
+      "eval_runtime": 591.1387,
+      "eval_samples_per_second": 16.744,
+      "eval_steps_per_second": 0.132,
+      "step": 190
+    },
+    {
+      "epoch": 2.1954022988505746,
+      "grad_norm": 0.03700386360287666,
+      "learning_rate": 4.209377202891212e-05,
+      "loss": 0.643,
+      "step": 191
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 0.038101959973573685,
+      "learning_rate": 4.100445599768774e-05,
+      "loss": 0.6349,
+      "step": 192
+    },
+    {
+      "epoch": 2.218390804597701,
+      "grad_norm": 0.036965154111385345,
+      "learning_rate": 3.99257735762021e-05,
+      "loss": 0.6404,
+      "step": 193
+    },
+    {
+      "epoch": 2.2298850574712645,
+      "grad_norm": 0.03756578266620636,
+      "learning_rate": 3.885791919079878e-05,
+      "loss": 0.6615,
+      "step": 194
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.035037923604249954,
+      "learning_rate": 3.7801085316129615e-05,
+      "loss": 0.6237,
+      "step": 195
+    },
+    {
+      "epoch": 2.2528735632183907,
+      "grad_norm": 0.03736288473010063,
+      "learning_rate": 3.675546244046228e-05,
+      "loss": 0.6482,
+      "step": 196
+    },
+    {
+      "epoch": 2.264367816091954,
+      "grad_norm": 0.03758701682090759,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.6101,
+      "step": 197
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.03676440194249153,
+      "learning_rate": 3.469860150164152e-05,
+      "loss": 0.6499,
+      "step": 198
+    },
+    {
+      "epoch": 2.2873563218390807,
+      "grad_norm": 0.03628651425242424,
+      "learning_rate": 3.36877341759205e-05,
+      "loss": 0.629,
+      "step": 199
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.03841525688767433,
+      "learning_rate": 3.268881925724297e-05,
+      "loss": 0.6372,
+      "step": 200
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "eval_loss": 0.6563421487808228,
+      "eval_runtime": 591.4937,
+      "eval_samples_per_second": 16.734,
+      "eval_steps_per_second": 0.132,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 261,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.740316645323702e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-261/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B
+library_name: peft
+---
+
+# 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 0.15.2

checkpoint-261/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/project/lt200252-wcbart/pumet/models/Qwen3-30B-A3B",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-261/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-261/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-261/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-261/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-261/trainer_state.json

@@ -0,0 +1,2069 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 261,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011494252873563218,
+      "grad_norm": 0.45773613452911377,
+      "learning_rate": 0.0,
+      "loss": 1.065,
+      "step": 1
+    },
+    {
+      "epoch": 0.022988505747126436,
+      "grad_norm": 0.4720604717731476,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.1025,
+      "step": 2
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.4526257812976837,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 1.067,
+      "step": 3
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.44910383224487305,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 1.0694,
+      "step": 4
+    },
+    {
+      "epoch": 0.05747126436781609,
+      "grad_norm": 0.4383523762226105,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 1.0767,
+      "step": 5
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.4290314018726349,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 1.0414,
+      "step": 6
+    },
+    {
+      "epoch": 0.08045977011494253,
+      "grad_norm": 0.4098808467388153,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.021,
+      "step": 7
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.4100661277770996,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 1.0113,
+      "step": 8
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 0.37694185972213745,
+      "learning_rate": 5.925925925925926e-05,
+      "loss": 0.9566,
+      "step": 9
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 0.3378658890724182,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.9539,
+      "step": 10
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "eval_loss": 0.9960598945617676,
+      "eval_runtime": 605.6954,
+      "eval_samples_per_second": 16.342,
+      "eval_steps_per_second": 0.129,
+      "step": 10
+    },
+    {
+      "epoch": 0.12643678160919541,
+      "grad_norm": 0.29339659214019775,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.9163,
+      "step": 11
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.23120510578155518,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.8886,
+      "step": 12
+    },
+    {
+      "epoch": 0.14942528735632185,
+      "grad_norm": 0.18651129305362701,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.8748,
+      "step": 13
+    },
+    {
+      "epoch": 0.16091954022988506,
+      "grad_norm": 0.14475475251674652,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.8235,
+      "step": 14
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.11758769303560257,
+      "learning_rate": 0.0001037037037037037,
+      "loss": 0.8539,
+      "step": 15
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.10646044462919235,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.8363,
+      "step": 16
+    },
+    {
+      "epoch": 0.19540229885057472,
+      "grad_norm": 0.10539838671684265,
+      "learning_rate": 0.00011851851851851852,
+      "loss": 0.819,
+      "step": 17
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.11887332051992416,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 0.8069,
+      "step": 18
+    },
+    {
+      "epoch": 0.21839080459770116,
+      "grad_norm": 0.1281956136226654,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.8042,
+      "step": 19
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.1338774859905243,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 0.8283,
+      "step": 20
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "eval_loss": 0.813089907169342,
+      "eval_runtime": 601.317,
+      "eval_samples_per_second": 16.461,
+      "eval_steps_per_second": 0.13,
+      "step": 20
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 0.12568038702011108,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.8142,
+      "step": 21
+    },
+    {
+      "epoch": 0.25287356321839083,
+      "grad_norm": 0.11528006941080093,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.794,
+      "step": 22
+    },
+    {
+      "epoch": 0.26436781609195403,
+      "grad_norm": 0.10474701225757599,
+      "learning_rate": 0.00016296296296296295,
+      "loss": 0.8231,
+      "step": 23
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.09240291267633438,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.7874,
+      "step": 24
+    },
+    {
+      "epoch": 0.28735632183908044,
+      "grad_norm": 0.07213829457759857,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.8075,
+      "step": 25
+    },
+    {
+      "epoch": 0.2988505747126437,
+      "grad_norm": 0.0564056895673275,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 0.779,
+      "step": 26
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 0.04973220080137253,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 0.7878,
+      "step": 27
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.04492342844605446,
+      "learning_rate": 0.0002,
+      "loss": 0.7876,
+      "step": 28
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.050321951508522034,
+      "learning_rate": 0.00019999098778567212,
+      "loss": 0.7686,
+      "step": 29
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.05602027848362923,
+      "learning_rate": 0.00019996395276708856,
+      "loss": 0.7525,
+      "step": 30
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "eval_loss": 0.7719228863716125,
+      "eval_runtime": 606.7346,
+      "eval_samples_per_second": 16.314,
+      "eval_steps_per_second": 0.129,
+      "step": 30
+    },
+    {
+      "epoch": 0.3563218390804598,
+      "grad_norm": 0.055378761142492294,
+      "learning_rate": 0.00019991889981715698,
+      "loss": 0.777,
+      "step": 31
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.052891045808792114,
+      "learning_rate": 0.00019985583705641418,
+      "loss": 0.7797,
+      "step": 32
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 0.044340070337057114,
+      "learning_rate": 0.00019977477585156252,
+      "loss": 0.7744,
+      "step": 33
+    },
+    {
+      "epoch": 0.39080459770114945,
+      "grad_norm": 0.037772953510284424,
+      "learning_rate": 0.00019967573081342103,
+      "loss": 0.7631,
+      "step": 34
+    },
+    {
+      "epoch": 0.40229885057471265,
+      "grad_norm": 0.03553105518221855,
+      "learning_rate": 0.0001995587197942919,
+      "loss": 0.7512,
+      "step": 35
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.0346490740776062,
+      "learning_rate": 0.0001994237638847428,
+      "loss": 0.7567,
+      "step": 36
+    },
+    {
+      "epoch": 0.42528735632183906,
+      "grad_norm": 0.03471450135111809,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 0.7723,
+      "step": 37
+    },
+    {
+      "epoch": 0.4367816091954023,
+      "grad_norm": 0.03868038207292557,
+      "learning_rate": 0.00019910011792459087,
+      "loss": 0.77,
+      "step": 38
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 0.04141271859407425,
+      "learning_rate": 0.00019891148620932318,
+      "loss": 0.7764,
+      "step": 39
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.04017995670437813,
+      "learning_rate": 0.00019870502626379127,
+      "loss": 0.7418,
+      "step": 40
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "eval_loss": 0.7480100393295288,
+      "eval_runtime": 601.4446,
+      "eval_samples_per_second": 16.457,
+      "eval_steps_per_second": 0.13,
+      "step": 40
+    },
+    {
+      "epoch": 0.47126436781609193,
+      "grad_norm": 0.04055652394890785,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.7487,
+      "step": 41
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.03968408331274986,
+      "learning_rate": 0.00019823877374156647,
+      "loss": 0.7417,
+      "step": 42
+    },
+    {
+      "epoch": 0.4942528735632184,
+      "grad_norm": 0.03533465415239334,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 0.7437,
+      "step": 43
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.03385720029473305,
+      "learning_rate": 0.00019770169650018172,
+      "loss": 0.7752,
+      "step": 44
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.030534420162439346,
+      "learning_rate": 0.00019740671762355548,
+      "loss": 0.7363,
+      "step": 45
+    },
+    {
+      "epoch": 0.5287356321839081,
+      "grad_norm": 0.02837216667830944,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 0.74,
+      "step": 46
+    },
+    {
+      "epoch": 0.5402298850574713,
+      "grad_norm": 0.02879689820110798,
+      "learning_rate": 0.00019676414519013781,
+      "loss": 0.7246,
+      "step": 47
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.02807699516415596,
+      "learning_rate": 0.00019641666745335624,
+      "loss": 0.7465,
+      "step": 48
+    },
+    {
+      "epoch": 0.5632183908045977,
+      "grad_norm": 0.029897579923272133,
+      "learning_rate": 0.00019605181116313724,
+      "loss": 0.721,
+      "step": 49
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "grad_norm": 0.028458919376134872,
+      "learning_rate": 0.00019566964208274254,
+      "loss": 0.7291,
+      "step": 50
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "eval_loss": 0.7319945096969604,
+      "eval_runtime": 601.7402,
+      "eval_samples_per_second": 16.449,
+      "eval_steps_per_second": 0.13,
+      "step": 50
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.028347671031951904,
+      "learning_rate": 0.00019527022909596536,
+      "loss": 0.7396,
+      "step": 51
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.028352508321404457,
+      "learning_rate": 0.00019485364419471454,
+      "loss": 0.733,
+      "step": 52
+    },
+    {
+      "epoch": 0.6091954022988506,
+      "grad_norm": 0.025768019258975983,
+      "learning_rate": 0.00019441996246603846,
+      "loss": 0.7378,
+      "step": 53
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.0259398240596056,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.7293,
+      "step": 54
+    },
+    {
+      "epoch": 0.632183908045977,
+      "grad_norm": 0.024649152532219887,
+      "learning_rate": 0.0001935016242685415,
+      "loss": 0.7287,
+      "step": 55
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.026843328028917313,
+      "learning_rate": 0.00019301713332493386,
+      "loss": 0.7354,
+      "step": 56
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.028928296640515327,
+      "learning_rate": 0.00019251587657449236,
+      "loss": 0.7376,
+      "step": 57
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.027994588017463684,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 0.7389,
+      "step": 58
+    },
+    {
+      "epoch": 0.6781609195402298,
+      "grad_norm": 0.027422698214650154,
+      "learning_rate": 0.00019146343005342547,
+      "loss": 0.7275,
+      "step": 59
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.02938409335911274,
+      "learning_rate": 0.0001909124299802724,
+      "loss": 0.7244,
+      "step": 60
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "eval_loss": 0.7189474701881409,
+      "eval_runtime": 605.038,
+      "eval_samples_per_second": 16.359,
+      "eval_steps_per_second": 0.129,
+      "step": 60
+    },
+    {
+      "epoch": 0.7011494252873564,
+      "grad_norm": 0.02854277938604355,
+      "learning_rate": 0.00019034504346103823,
+      "loss": 0.7339,
+      "step": 61
+    },
+    {
+      "epoch": 0.7126436781609196,
+      "grad_norm": 0.028162814676761627,
+      "learning_rate": 0.0001897613727639014,
+      "loss": 0.7349,
+      "step": 62
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.027026742696762085,
+      "learning_rate": 0.0001891615230921703,
+      "loss": 0.7008,
+      "step": 63
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.02867995575070381,
+      "learning_rate": 0.000188545602565321,
+      "loss": 0.7404,
+      "step": 64
+    },
+    {
+      "epoch": 0.7471264367816092,
+      "grad_norm": 0.025570319965481758,
+      "learning_rate": 0.00018791372219950948,
+      "loss": 0.7203,
+      "step": 65
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.026673492044210434,
+      "learning_rate": 0.00018726599588756145,
+      "loss": 0.7188,
+      "step": 66
+    },
+    {
+      "epoch": 0.7701149425287356,
+      "grad_norm": 0.028060389682650566,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.7129,
+      "step": 67
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.025640789419412613,
+      "learning_rate": 0.0001859234752562217,
+      "loss": 0.7081,
+      "step": 68
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.026264475658535957,
+      "learning_rate": 0.00018522892291850335,
+      "loss": 0.6971,
+      "step": 69
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "grad_norm": 0.028900163248181343,
+      "learning_rate": 0.0001845190085543795,
+      "loss": 0.721,
+      "step": 70
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "eval_loss": 0.7084506154060364,
+      "eval_runtime": 603.3937,
+      "eval_samples_per_second": 16.404,
+      "eval_steps_per_second": 0.129,
+      "step": 70
+    },
+    {
+      "epoch": 0.8160919540229885,
+      "grad_norm": 0.02878301776945591,
+      "learning_rate": 0.00018379386012185814,
+      "loss": 0.7192,
+      "step": 71
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.028177903965115547,
+      "learning_rate": 0.00018305360832480117,
+      "loss": 0.7258,
+      "step": 72
+    },
+    {
+      "epoch": 0.8390804597701149,
+      "grad_norm": 0.027689015492796898,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 0.7327,
+      "step": 73
+    },
+    {
+      "epoch": 0.8505747126436781,
+      "grad_norm": 0.027420515194535255,
+      "learning_rate": 0.00018152833103995443,
+      "loss": 0.7007,
+      "step": 74
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.02628767490386963,
+      "learning_rate": 0.0001807435804746807,
+      "loss": 0.7106,
+      "step": 75
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.027107784524559975,
+      "learning_rate": 0.00017994427634035015,
+      "loss": 0.7056,
+      "step": 76
+    },
+    {
+      "epoch": 0.8850574712643678,
+      "grad_norm": 0.026692209765315056,
+      "learning_rate": 0.0001791305627069662,
+      "loss": 0.6898,
+      "step": 77
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.02739943191409111,
+      "learning_rate": 0.00017830258624176225,
+      "loss": 0.71,
+      "step": 78
+    },
+    {
+      "epoch": 0.9080459770114943,
+      "grad_norm": 0.027159228920936584,
+      "learning_rate": 0.00017746049618276545,
+      "loss": 0.7104,
+      "step": 79
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.027961738407611847,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.6964,
+      "step": 80
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "eval_loss": 0.6998673677444458,
+      "eval_runtime": 599.046,
+      "eval_samples_per_second": 16.523,
+      "eval_steps_per_second": 0.13,
+      "step": 80
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.028458958491683006,
+      "learning_rate": 0.00017573458492761801,
+      "loss": 0.7048,
+      "step": 81
+    },
+    {
+      "epoch": 0.9425287356321839,
+      "grad_norm": 0.0295415036380291,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 0.7089,
+      "step": 82
+    },
+    {
+      "epoch": 0.9540229885057471,
+      "grad_norm": 0.027641592547297478,
+      "learning_rate": 0.00017395407322802372,
+      "loss": 0.7184,
+      "step": 83
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.029828142374753952,
+      "learning_rate": 0.00017304374183977033,
+      "loss": 0.6878,
+      "step": 84
+    },
+    {
+      "epoch": 0.9770114942528736,
+      "grad_norm": 0.029184194281697273,
+      "learning_rate": 0.00017212024473438147,
+      "loss": 0.7223,
+      "step": 85
+    },
+    {
+      "epoch": 0.9885057471264368,
+      "grad_norm": 0.02929309941828251,
+      "learning_rate": 0.00017118374836693406,
+      "loss": 0.6936,
+      "step": 86
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.03450490161776543,
+      "learning_rate": 0.00017023442153554777,
+      "loss": 0.6906,
+      "step": 87
+    },
+    {
+      "epoch": 1.0114942528735633,
+      "grad_norm": 0.03116275928914547,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 0.6915,
+      "step": 88
+    },
+    {
+      "epoch": 1.0229885057471264,
+      "grad_norm": 0.03145065903663635,
+      "learning_rate": 0.00016829796320568416,
+      "loss": 0.6792,
+      "step": 89
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.03122427873313427,
+      "learning_rate": 0.00016731118074275704,
+      "loss": 0.6965,
+      "step": 90
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "eval_loss": 0.6928127408027649,
+      "eval_runtime": 606.6499,
+      "eval_samples_per_second": 16.316,
+      "eval_steps_per_second": 0.129,
+      "step": 90
+    },
+    {
+      "epoch": 1.0459770114942528,
+      "grad_norm": 0.030179064720869064,
+      "learning_rate": 0.00016631226582407952,
+      "loss": 0.6726,
+      "step": 91
+    },
+    {
+      "epoch": 1.0574712643678161,
+      "grad_norm": 0.029219962656497955,
+      "learning_rate": 0.0001653013984983585,
+      "loss": 0.6792,
+      "step": 92
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.02873355709016323,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.6921,
+      "step": 93
+    },
+    {
+      "epoch": 1.0804597701149425,
+      "grad_norm": 0.029455283656716347,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 0.6829,
+      "step": 94
+    },
+    {
+      "epoch": 1.0919540229885056,
+      "grad_norm": 0.030247965827584267,
+      "learning_rate": 0.0001621989146838704,
+      "loss": 0.6737,
+      "step": 95
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.029829107224941254,
+      "learning_rate": 0.00016114208080920123,
+      "loss": 0.6852,
+      "step": 96
+    },
+    {
+      "epoch": 1.1149425287356323,
+      "grad_norm": 0.031125420704483986,
+      "learning_rate": 0.0001600742264237979,
+      "loss": 0.6863,
+      "step": 97
+    },
+    {
+      "epoch": 1.1264367816091954,
+      "grad_norm": 0.029601775109767914,
+      "learning_rate": 0.00015899554400231232,
+      "loss": 0.6785,
+      "step": 98
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.031090950593352318,
+      "learning_rate": 0.0001579062279710879,
+      "loss": 0.7001,
+      "step": 99
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 0.030084125697612762,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 0.6856,
+      "step": 100
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "eval_loss": 0.686887264251709,
+      "eval_runtime": 599.4005,
+      "eval_samples_per_second": 16.513,
+      "eval_steps_per_second": 0.13,
+      "step": 100
+    },
+    {
+      "epoch": 1.160919540229885,
+      "grad_norm": 0.03157448023557663,
+      "learning_rate": 0.00015569648233264394,
+      "loss": 0.6836,
+      "step": 101
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.032123371958732605,
+      "learning_rate": 0.00015457645101945046,
+      "loss": 0.6827,
+      "step": 102
+    },
+    {
+      "epoch": 1.1839080459770115,
+      "grad_norm": 0.03208347037434578,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 0.6823,
+      "step": 103
+    },
+    {
+      "epoch": 1.1954022988505748,
+      "grad_norm": 0.030994586646556854,
+      "learning_rate": 0.00015230708076495775,
+      "loss": 0.6729,
+      "step": 104
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.03224639222025871,
+      "learning_rate": 0.00015115815086468102,
+      "loss": 0.6778,
+      "step": 105
+    },
+    {
+      "epoch": 1.2183908045977012,
+      "grad_norm": 0.030437005683779716,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.674,
+      "step": 106
+    },
+    {
+      "epoch": 1.2298850574712643,
+      "grad_norm": 0.030820753425359726,
+      "learning_rate": 0.00014883283692099112,
+      "loss": 0.6799,
+      "step": 107
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.03301486000418663,
+      "learning_rate": 0.0001476568720021308,
+      "loss": 0.6851,
+      "step": 108
+    },
+    {
+      "epoch": 1.2528735632183907,
+      "grad_norm": 0.033183734863996506,
+      "learning_rate": 0.00014647231720437686,
+      "loss": 0.7094,
+      "step": 109
+    },
+    {
+      "epoch": 1.264367816091954,
+      "grad_norm": 0.03154841437935829,
+      "learning_rate": 0.00014527938603696376,
+      "loss": 0.6812,
+      "step": 110
+    },
+    {
+      "epoch": 1.264367816091954,
+      "eval_loss": 0.6802834868431091,
+      "eval_runtime": 597.3843,
+      "eval_samples_per_second": 16.569,
+      "eval_steps_per_second": 0.131,
+      "step": 110
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.03554477170109749,
+      "learning_rate": 0.00014407829351891857,
+      "loss": 0.679,
+      "step": 111
+    },
+    {
+      "epoch": 1.2873563218390804,
+      "grad_norm": 0.03362204134464264,
+      "learning_rate": 0.00014286925614030542,
+      "loss": 0.6722,
+      "step": 112
+    },
+    {
+      "epoch": 1.2988505747126438,
+      "grad_norm": 0.032853253185749054,
+      "learning_rate": 0.00014165249182320402,
+      "loss": 0.6879,
+      "step": 113
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.033823542296886444,
+      "learning_rate": 0.0001404282198824305,
+      "loss": 0.6627,
+      "step": 114
+    },
+    {
+      "epoch": 1.3218390804597702,
+      "grad_norm": 0.0326109379529953,
+      "learning_rate": 0.00013919666098600753,
+      "loss": 0.6751,
+      "step": 115
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.03431953117251396,
+      "learning_rate": 0.00013795803711538966,
+      "loss": 0.6827,
+      "step": 116
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.03328808769583702,
+      "learning_rate": 0.00013671257152545277,
+      "loss": 0.6648,
+      "step": 117
+    },
+    {
+      "epoch": 1.3563218390804597,
+      "grad_norm": 0.035666704177856445,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.6771,
+      "step": 118
+    },
+    {
+      "epoch": 1.367816091954023,
+      "grad_norm": 0.03441452234983444,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.6623,
+      "step": 119
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.03363391384482384,
+      "learning_rate": 0.00013293737524320797,
+      "loss": 0.6734,
+      "step": 120
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "eval_loss": 0.6736027002334595,
+      "eval_runtime": 601.0855,
+      "eval_samples_per_second": 16.467,
+      "eval_steps_per_second": 0.13,
+      "step": 120
+    },
+    {
+      "epoch": 1.3908045977011494,
+      "grad_norm": 0.03441128134727478,
+      "learning_rate": 0.00013166679938014726,
+      "loss": 0.6625,
+      "step": 121
+    },
+    {
+      "epoch": 1.4022988505747127,
+      "grad_norm": 0.03332269564270973,
+      "learning_rate": 0.0001303905157574247,
+      "loss": 0.6738,
+      "step": 122
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.03411813825368881,
+      "learning_rate": 0.00012910875441787128,
+      "loss": 0.6511,
+      "step": 123
+    },
+    {
+      "epoch": 1.4252873563218391,
+      "grad_norm": 0.034489769488573074,
+      "learning_rate": 0.0001278217463916453,
+      "loss": 0.6579,
+      "step": 124
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "grad_norm": 0.03562283143401146,
+      "learning_rate": 0.0001265297236545901,
+      "loss": 0.6508,
+      "step": 125
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.034433409571647644,
+      "learning_rate": 0.00012523291908642217,
+      "loss": 0.6867,
+      "step": 126
+    },
+    {
+      "epoch": 1.4597701149425286,
+      "grad_norm": 0.034091442823410034,
+      "learning_rate": 0.0001239315664287558,
+      "loss": 0.6609,
+      "step": 127
+    },
+    {
+      "epoch": 1.471264367816092,
+      "grad_norm": 0.034659866243600845,
+      "learning_rate": 0.00012262590024297225,
+      "loss": 0.6708,
+      "step": 128
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.03355137258768082,
+      "learning_rate": 0.0001213161558679416,
+      "loss": 0.6853,
+      "step": 129
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "grad_norm": 0.03497845306992531,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 0.658,
+      "step": 130
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "eval_loss": 0.6697064638137817,
+      "eval_runtime": 595.4108,
+      "eval_samples_per_second": 16.624,
+      "eval_steps_per_second": 0.131,
+      "step": 130
+    },
+    {
+      "epoch": 1.5057471264367817,
+      "grad_norm": 0.03422487527132034,
+      "learning_rate": 0.00011868537753842051,
+      "loss": 0.6688,
+      "step": 131
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.034450776875019073,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.6828,
+      "step": 132
+    },
+    {
+      "epoch": 1.528735632183908,
+      "grad_norm": 0.034574706107378006,
+      "learning_rate": 0.00011604112808577603,
+      "loss": 0.6776,
+      "step": 133
+    },
+    {
+      "epoch": 1.5402298850574714,
+      "grad_norm": 0.03596516326069832,
+      "learning_rate": 0.00011471454708317162,
+      "loss": 0.6276,
+      "step": 134
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.035429686307907104,
+      "learning_rate": 0.00011338531386752618,
+      "loss": 0.6427,
+      "step": 135
+    },
+    {
+      "epoch": 1.5632183908045976,
+      "grad_norm": 0.033536769449710846,
+      "learning_rate": 0.0001120536680255323,
+      "loss": 0.652,
+      "step": 136
+    },
+    {
+      "epoch": 1.5747126436781609,
+      "grad_norm": 0.03417116403579712,
+      "learning_rate": 0.00011071984957874479,
+      "loss": 0.6725,
+      "step": 137
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.03480486571788788,
+      "learning_rate": 0.00010938409894031794,
+      "loss": 0.6479,
+      "step": 138
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "grad_norm": 0.03562786802649498,
+      "learning_rate": 0.00010804665687167262,
+      "loss": 0.6681,
+      "step": 139
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "grad_norm": 0.034858204424381256,
+      "learning_rate": 0.00010670776443910024,
+      "loss": 0.6703,
+      "step": 140
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "eval_loss": 0.6661256551742554,
+      "eval_runtime": 590.9429,
+      "eval_samples_per_second": 16.75,
+      "eval_steps_per_second": 0.132,
+      "step": 140
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.03447253257036209,
+      "learning_rate": 0.00010536766297031215,
+      "loss": 0.6643,
+      "step": 141
+    },
+    {
+      "epoch": 1.632183908045977,
+      "grad_norm": 0.03508715331554413,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 0.6583,
+      "step": 142
+    },
+    {
+      "epoch": 1.6436781609195403,
+      "grad_norm": 0.0343579463660717,
+      "learning_rate": 0.00010268479928100614,
+      "loss": 0.6753,
+      "step": 143
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.0350567027926445,
+      "learning_rate": 0.00010134252063133975,
+      "loss": 0.6493,
+      "step": 144
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.034686826169490814,
+      "learning_rate": 0.0001,
+      "loss": 0.6515,
+      "step": 145
+    },
+    {
+      "epoch": 1.6781609195402298,
+      "grad_norm": 0.035702142864465714,
+      "learning_rate": 9.865747936866027e-05,
+      "loss": 0.6638,
+      "step": 146
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.034140318632125854,
+      "learning_rate": 9.73152007189939e-05,
+      "loss": 0.6496,
+      "step": 147
+    },
+    {
+      "epoch": 1.7011494252873565,
+      "grad_norm": 0.038083408027887344,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 0.6893,
+      "step": 148
+    },
+    {
+      "epoch": 1.7126436781609196,
+      "grad_norm": 0.03810959309339523,
+      "learning_rate": 9.463233702968783e-05,
+      "loss": 0.6728,
+      "step": 149
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.033978622406721115,
+      "learning_rate": 9.329223556089975e-05,
+      "loss": 0.6814,
+      "step": 150
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "eval_loss": 0.6631415486335754,
+      "eval_runtime": 596.1091,
+      "eval_samples_per_second": 16.604,
+      "eval_steps_per_second": 0.131,
+      "step": 150
+    },
+    {
+      "epoch": 1.735632183908046,
+      "grad_norm": 0.03391426429152489,
+      "learning_rate": 9.195334312832742e-05,
+      "loss": 0.6421,
+      "step": 151
+    },
+    {
+      "epoch": 1.7471264367816093,
+      "grad_norm": 0.03562890738248825,
+      "learning_rate": 9.061590105968208e-05,
+      "loss": 0.6739,
+      "step": 152
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.03706149384379387,
+      "learning_rate": 8.928015042125523e-05,
+      "loss": 0.6579,
+      "step": 153
+    },
+    {
+      "epoch": 1.7701149425287355,
+      "grad_norm": 0.03591468557715416,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.645,
+      "step": 154
+    },
+    {
+      "epoch": 1.7816091954022988,
+      "grad_norm": 0.03639413043856621,
+      "learning_rate": 8.661468613247387e-05,
+      "loss": 0.6594,
+      "step": 155
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 0.03598083183169365,
+      "learning_rate": 8.528545291682838e-05,
+      "loss": 0.6723,
+      "step": 156
+    },
+    {
+      "epoch": 1.8045977011494254,
+      "grad_norm": 0.03628537803888321,
+      "learning_rate": 8.395887191422397e-05,
+      "loss": 0.6715,
+      "step": 157
+    },
+    {
+      "epoch": 1.8160919540229885,
+      "grad_norm": 0.03826047480106354,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.6767,
+      "step": 158
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.03769649192690849,
+      "learning_rate": 8.131462246157953e-05,
+      "loss": 0.6552,
+      "step": 159
+    },
+    {
+      "epoch": 1.839080459770115,
+      "grad_norm": 0.03599262982606888,
+      "learning_rate": 7.999743062239557e-05,
+      "loss": 0.6688,
+      "step": 160
+    },
+    {
+      "epoch": 1.839080459770115,
+      "eval_loss": 0.6607028245925903,
+      "eval_runtime": 589.6737,
+      "eval_samples_per_second": 16.786,
+      "eval_steps_per_second": 0.132,
+      "step": 160
+    },
+    {
+      "epoch": 1.8505747126436782,
+      "grad_norm": 0.03584510087966919,
+      "learning_rate": 7.868384413205842e-05,
+      "loss": 0.672,
+      "step": 161
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 0.03545341268181801,
+      "learning_rate": 7.73740997570278e-05,
+      "loss": 0.6629,
+      "step": 162
+    },
+    {
+      "epoch": 1.8735632183908046,
+      "grad_norm": 0.035858072340488434,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 0.6391,
+      "step": 163
+    },
+    {
+      "epoch": 1.8850574712643677,
+      "grad_norm": 0.035794083029031754,
+      "learning_rate": 7.476708091357782e-05,
+      "loss": 0.6516,
+      "step": 164
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.03674920275807381,
+      "learning_rate": 7.347027634540993e-05,
+      "loss": 0.6624,
+      "step": 165
+    },
+    {
+      "epoch": 1.9080459770114944,
+      "grad_norm": 0.034701887518167496,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.6574,
+      "step": 166
+    },
+    {
+      "epoch": 1.9195402298850575,
+      "grad_norm": 0.03606560826301575,
+      "learning_rate": 7.089124558212871e-05,
+      "loss": 0.6668,
+      "step": 167
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.03570757061243057,
+      "learning_rate": 6.960948424257532e-05,
+      "loss": 0.6358,
+      "step": 168
+    },
+    {
+      "epoch": 1.9425287356321839,
+      "grad_norm": 0.034459397196769714,
+      "learning_rate": 6.833320061985277e-05,
+      "loss": 0.6294,
+      "step": 169
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "grad_norm": 0.035828083753585815,
+      "learning_rate": 6.706262475679205e-05,
+      "loss": 0.6781,
+      "step": 170
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "eval_loss": 0.6586677432060242,
+      "eval_runtime": 590.832,
+      "eval_samples_per_second": 16.753,
+      "eval_steps_per_second": 0.132,
+      "step": 170
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.03741836175322533,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 0.6679,
+      "step": 171
+    },
+    {
+      "epoch": 1.9770114942528736,
+      "grad_norm": 0.03573041409254074,
+      "learning_rate": 6.453951129574644e-05,
+      "loss": 0.6805,
+      "step": 172
+    },
+    {
+      "epoch": 1.9885057471264367,
+      "grad_norm": 0.03586418181657791,
+      "learning_rate": 6.328742847454724e-05,
+      "loss": 0.6606,
+      "step": 173
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.03636249899864197,
+      "learning_rate": 6.204196288461037e-05,
+      "loss": 0.6962,
+      "step": 174
+    },
+    {
+      "epoch": 2.0114942528735633,
+      "grad_norm": 0.04032210260629654,
+      "learning_rate": 6.080333901399251e-05,
+      "loss": 0.6426,
+      "step": 175
+    },
+    {
+      "epoch": 2.0229885057471266,
+      "grad_norm": 0.039117176085710526,
+      "learning_rate": 5.957178011756952e-05,
+      "loss": 0.6418,
+      "step": 176
+    },
+    {
+      "epoch": 2.0344827586206895,
+      "grad_norm": 0.037345871329307556,
+      "learning_rate": 5.834750817679606e-05,
+      "loss": 0.6406,
+      "step": 177
+    },
+    {
+      "epoch": 2.045977011494253,
+      "grad_norm": 0.03830842301249504,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.6262,
+      "step": 178
+    },
+    {
+      "epoch": 2.057471264367816,
+      "grad_norm": 0.037265144288539886,
+      "learning_rate": 5.59217064810814e-05,
+      "loss": 0.6385,
+      "step": 179
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.03784786909818649,
+      "learning_rate": 5.472061396303629e-05,
+      "loss": 0.618,
+      "step": 180
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "eval_loss": 0.6581570506095886,
+      "eval_runtime": 593.2384,
+      "eval_samples_per_second": 16.685,
+      "eval_steps_per_second": 0.131,
+      "step": 180
+    },
+    {
+      "epoch": 2.0804597701149423,
+      "grad_norm": 0.03711731731891632,
+      "learning_rate": 5.3527682795623146e-05,
+      "loss": 0.6354,
+      "step": 181
+    },
+    {
+      "epoch": 2.0919540229885056,
+      "grad_norm": 0.037277545779943466,
+      "learning_rate": 5.234312799786921e-05,
+      "loss": 0.631,
+      "step": 182
+    },
+    {
+      "epoch": 2.103448275862069,
+      "grad_norm": 0.040995873510837555,
+      "learning_rate": 5.116716307900893e-05,
+      "loss": 0.631,
+      "step": 183
+    },
+    {
+      "epoch": 2.1149425287356323,
+      "grad_norm": 0.038000449538230896,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.6691,
+      "step": 184
+    },
+    {
+      "epoch": 2.1264367816091956,
+      "grad_norm": 0.03552795201539993,
+      "learning_rate": 4.884184913531902e-05,
+      "loss": 0.6147,
+      "step": 185
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 0.03610774129629135,
+      "learning_rate": 4.7692919235042255e-05,
+      "loss": 0.6259,
+      "step": 186
+    },
+    {
+      "epoch": 2.1494252873563218,
+      "grad_norm": 0.038160186260938644,
+      "learning_rate": 4.6553417387219886e-05,
+      "loss": 0.6375,
+      "step": 187
+    },
+    {
+      "epoch": 2.160919540229885,
+      "grad_norm": 0.03843645006418228,
+      "learning_rate": 4.542354898054953e-05,
+      "loss": 0.6329,
+      "step": 188
+    },
+    {
+      "epoch": 2.1724137931034484,
+      "grad_norm": 0.03745341673493385,
+      "learning_rate": 4.430351766735609e-05,
+      "loss": 0.6379,
+      "step": 189
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "grad_norm": 0.03651278465986252,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.6575,
+      "step": 190
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "eval_loss": 0.657158374786377,
+      "eval_runtime": 591.1387,
+      "eval_samples_per_second": 16.744,
+      "eval_steps_per_second": 0.132,
+      "step": 190
+    },
+    {
+      "epoch": 2.1954022988505746,
+      "grad_norm": 0.03700386360287666,
+      "learning_rate": 4.209377202891212e-05,
+      "loss": 0.643,
+      "step": 191
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 0.038101959973573685,
+      "learning_rate": 4.100445599768774e-05,
+      "loss": 0.6349,
+      "step": 192
+    },
+    {
+      "epoch": 2.218390804597701,
+      "grad_norm": 0.036965154111385345,
+      "learning_rate": 3.99257735762021e-05,
+      "loss": 0.6404,
+      "step": 193
+    },
+    {
+      "epoch": 2.2298850574712645,
+      "grad_norm": 0.03756578266620636,
+      "learning_rate": 3.885791919079878e-05,
+      "loss": 0.6615,
+      "step": 194
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.035037923604249954,
+      "learning_rate": 3.7801085316129615e-05,
+      "loss": 0.6237,
+      "step": 195
+    },
+    {
+      "epoch": 2.2528735632183907,
+      "grad_norm": 0.03736288473010063,
+      "learning_rate": 3.675546244046228e-05,
+      "loss": 0.6482,
+      "step": 196
+    },
+    {
+      "epoch": 2.264367816091954,
+      "grad_norm": 0.03758701682090759,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.6101,
+      "step": 197
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.03676440194249153,
+      "learning_rate": 3.469860150164152e-05,
+      "loss": 0.6499,
+      "step": 198
+    },
+    {
+      "epoch": 2.2873563218390807,
+      "grad_norm": 0.03628651425242424,
+      "learning_rate": 3.36877341759205e-05,
+      "loss": 0.629,
+      "step": 199
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.03841525688767433,
+      "learning_rate": 3.268881925724297e-05,
+      "loss": 0.6372,
+      "step": 200
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "eval_loss": 0.6563421487808228,
+      "eval_runtime": 591.4937,
+      "eval_samples_per_second": 16.734,
+      "eval_steps_per_second": 0.132,
+      "step": 200
+    },
+    {
+      "epoch": 2.310344827586207,
+      "grad_norm": 0.03878968209028244,
+      "learning_rate": 3.170203679431584e-05,
+      "loss": 0.6417,
+      "step": 201
+    },
+    {
+      "epoch": 2.32183908045977,
+      "grad_norm": 0.03762966766953468,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.6434,
+      "step": 202
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.03814293071627617,
+      "learning_rate": 2.976557846445225e-05,
+      "loss": 0.643,
+      "step": 203
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 0.03540797904133797,
+      "learning_rate": 2.881625163306596e-05,
+      "loss": 0.6374,
+      "step": 204
+    },
+    {
+      "epoch": 2.3563218390804597,
+      "grad_norm": 0.03709061071276665,
+      "learning_rate": 2.7879755265618555e-05,
+      "loss": 0.6418,
+      "step": 205
+    },
+    {
+      "epoch": 2.367816091954023,
+      "grad_norm": 0.03803767263889313,
+      "learning_rate": 2.6956258160229695e-05,
+      "loss": 0.632,
+      "step": 206
+    },
+    {
+      "epoch": 2.3793103448275863,
+      "grad_norm": 0.03654790297150612,
+      "learning_rate": 2.6045926771976303e-05,
+      "loss": 0.6538,
+      "step": 207
+    },
+    {
+      "epoch": 2.3908045977011496,
+      "grad_norm": 0.03603474050760269,
+      "learning_rate": 2.514892518288988e-05,
+      "loss": 0.6145,
+      "step": 208
+    },
+    {
+      "epoch": 2.4022988505747125,
+      "grad_norm": 0.036107271909713745,
+      "learning_rate": 2.4265415072382016e-05,
+      "loss": 0.6222,
+      "step": 209
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.036303840577602386,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.617,
+      "step": 210
+    },
+    {
+      "epoch": 2.413793103448276,
+      "eval_loss": 0.6558452248573303,
+      "eval_runtime": 595.1508,
+      "eval_samples_per_second": 16.631,
+      "eval_steps_per_second": 0.131,
+      "step": 210
+    },
+    {
+      "epoch": 2.425287356321839,
+      "grad_norm": 0.037371959537267685,
+      "learning_rate": 2.2539503817234553e-05,
+      "loss": 0.654,
+      "step": 211
+    },
+    {
+      "epoch": 2.4367816091954024,
+      "grad_norm": 0.037925343960523605,
+      "learning_rate": 2.1697413758237784e-05,
+      "loss": 0.6322,
+      "step": 212
+    },
+    {
+      "epoch": 2.4482758620689653,
+      "grad_norm": 0.03855719789862633,
+      "learning_rate": 2.0869437293033835e-05,
+      "loss": 0.6335,
+      "step": 213
+    },
+    {
+      "epoch": 2.4597701149425286,
+      "grad_norm": 0.037308286875486374,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.6184,
+      "step": 214
+    },
+    {
+      "epoch": 2.471264367816092,
+      "grad_norm": 0.03688681870698929,
+      "learning_rate": 1.9256419525319313e-05,
+      "loss": 0.627,
+      "step": 215
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 0.038670193403959274,
+      "learning_rate": 1.8471668960045574e-05,
+      "loss": 0.6487,
+      "step": 216
+    },
+    {
+      "epoch": 2.4942528735632186,
+      "grad_norm": 0.03826979547739029,
+      "learning_rate": 1.7701613410634365e-05,
+      "loss": 0.6337,
+      "step": 217
+    },
+    {
+      "epoch": 2.5057471264367814,
+      "grad_norm": 0.03768225386738777,
+      "learning_rate": 1.6946391675198836e-05,
+      "loss": 0.6356,
+      "step": 218
+    },
+    {
+      "epoch": 2.5172413793103448,
+      "grad_norm": 0.037600524723529816,
+      "learning_rate": 1.620613987814189e-05,
+      "loss": 0.6237,
+      "step": 219
+    },
+    {
+      "epoch": 2.528735632183908,
+      "grad_norm": 0.036940865218639374,
+      "learning_rate": 1.5480991445620542e-05,
+      "loss": 0.6152,
+      "step": 220
+    },
+    {
+      "epoch": 2.528735632183908,
+      "eval_loss": 0.655238926410675,
+      "eval_runtime": 592.9652,
+      "eval_samples_per_second": 16.692,
+      "eval_steps_per_second": 0.132,
+      "step": 220
+    },
+    {
+      "epoch": 2.5402298850574714,
+      "grad_norm": 0.03826668858528137,
+      "learning_rate": 1.4771077081496654e-05,
+      "loss": 0.6511,
+      "step": 221
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 0.0361490473151207,
+      "learning_rate": 1.4076524743778319e-05,
+      "loss": 0.6311,
+      "step": 222
+    },
+    {
+      "epoch": 2.5632183908045976,
+      "grad_norm": 0.03727561607956886,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.6324,
+      "step": 223
+    },
+    {
+      "epoch": 2.574712643678161,
+      "grad_norm": 0.038558244705200195,
+      "learning_rate": 1.2734004112438568e-05,
+      "loss": 0.6568,
+      "step": 224
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.03707597777247429,
+      "learning_rate": 1.2086277800490554e-05,
+      "loss": 0.649,
+      "step": 225
+    },
+    {
+      "epoch": 2.5977011494252875,
+      "grad_norm": 0.037075500935316086,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.6603,
+      "step": 226
+    },
+    {
+      "epoch": 2.609195402298851,
+      "grad_norm": 0.03692416474223137,
+      "learning_rate": 1.083847690782972e-05,
+      "loss": 0.6295,
+      "step": 227
+    },
+    {
+      "epoch": 2.6206896551724137,
+      "grad_norm": 0.03675093874335289,
+      "learning_rate": 1.0238627236098619e-05,
+      "loss": 0.6209,
+      "step": 228
+    },
+    {
+      "epoch": 2.632183908045977,
+      "grad_norm": 0.03640436753630638,
+      "learning_rate": 9.65495653896179e-06,
+      "loss": 0.6339,
+      "step": 229
+    },
+    {
+      "epoch": 2.6436781609195403,
+      "grad_norm": 0.037452854216098785,
+      "learning_rate": 9.08757001972762e-06,
+      "loss": 0.6407,
+      "step": 230
+    },
+    {
+      "epoch": 2.6436781609195403,
+      "eval_loss": 0.6549434065818787,
+      "eval_runtime": 592.4603,
+      "eval_samples_per_second": 16.707,
+      "eval_steps_per_second": 0.132,
+      "step": 230
+    },
+    {
+      "epoch": 2.655172413793103,
+      "grad_norm": 0.03795592859387398,
+      "learning_rate": 8.536569946574546e-06,
+      "loss": 0.6534,
+      "step": 231
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.03788486495614052,
+      "learning_rate": 8.002055634117578e-06,
+      "loss": 0.6507,
+      "step": 232
+    },
+    {
+      "epoch": 2.67816091954023,
+      "grad_norm": 0.03641374036669731,
+      "learning_rate": 7.4841234255076495e-06,
+      "loss": 0.6282,
+      "step": 233
+    },
+    {
+      "epoch": 2.689655172413793,
+      "grad_norm": 0.03832123428583145,
+      "learning_rate": 6.9828666750661795e-06,
+      "loss": 0.6276,
+      "step": 234
+    },
+    {
+      "epoch": 2.7011494252873565,
+      "grad_norm": 0.03677581995725632,
+      "learning_rate": 6.498375731458528e-06,
+      "loss": 0.639,
+      "step": 235
+    },
+    {
+      "epoch": 2.7126436781609193,
+      "grad_norm": 0.03623311221599579,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.6425,
+      "step": 236
+    },
+    {
+      "epoch": 2.7241379310344827,
+      "grad_norm": 0.036890316754579544,
+      "learning_rate": 5.580037533961546e-06,
+      "loss": 0.6438,
+      "step": 237
+    },
+    {
+      "epoch": 2.735632183908046,
+      "grad_norm": 0.03658117353916168,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.6275,
+      "step": 238
+    },
+    {
+      "epoch": 2.7471264367816093,
+      "grad_norm": 0.03849633410573006,
+      "learning_rate": 4.729770904034647e-06,
+      "loss": 0.6357,
+      "step": 239
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.03720705956220627,
+      "learning_rate": 4.3303579172574885e-06,
+      "loss": 0.6498,
+      "step": 240
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "eval_loss": 0.6547917723655701,
+      "eval_runtime": 593.6976,
+      "eval_samples_per_second": 16.672,
+      "eval_steps_per_second": 0.131,
+      "step": 240
+    },
+    {
+      "epoch": 2.7701149425287355,
+      "grad_norm": 0.03713015094399452,
+      "learning_rate": 3.948188836862776e-06,
+      "loss": 0.63,
+      "step": 241
+    },
+    {
+      "epoch": 2.781609195402299,
+      "grad_norm": 0.03703474998474121,
+      "learning_rate": 3.5833325466437694e-06,
+      "loss": 0.6267,
+      "step": 242
+    },
+    {
+      "epoch": 2.793103448275862,
+      "grad_norm": 0.0391690619289875,
+      "learning_rate": 3.2358548098621932e-06,
+      "loss": 0.6297,
+      "step": 243
+    },
+    {
+      "epoch": 2.8045977011494254,
+      "grad_norm": 0.03748522326350212,
+      "learning_rate": 2.905818257394799e-06,
+      "loss": 0.6289,
+      "step": 244
+    },
+    {
+      "epoch": 2.8160919540229887,
+      "grad_norm": 0.036214690655469894,
+      "learning_rate": 2.5932823764445392e-06,
+      "loss": 0.6274,
+      "step": 245
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.03697674348950386,
+      "learning_rate": 2.2983034998182997e-06,
+      "loss": 0.6205,
+      "step": 246
+    },
+    {
+      "epoch": 2.839080459770115,
+      "grad_norm": 0.0381477065384388,
+      "learning_rate": 2.0209347957732328e-06,
+      "loss": 0.6585,
+      "step": 247
+    },
+    {
+      "epoch": 2.8505747126436782,
+      "grad_norm": 0.03660466521978378,
+      "learning_rate": 1.7612262584335237e-06,
+      "loss": 0.6215,
+      "step": 248
+    },
+    {
+      "epoch": 2.862068965517241,
+      "grad_norm": 0.03698161989450455,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.6454,
+      "step": 249
+    },
+    {
+      "epoch": 2.873563218390805,
+      "grad_norm": 0.037139616906642914,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.6365,
+      "step": 250
+    },
+    {
+      "epoch": 2.873563218390805,
+      "eval_loss": 0.6547266840934753,
+      "eval_runtime": 593.9462,
+      "eval_samples_per_second": 16.665,
+      "eval_steps_per_second": 0.131,
+      "step": 250
+    },
+    {
+      "epoch": 2.8850574712643677,
+      "grad_norm": 0.03719855844974518,
+      "learning_rate": 1.0885137906768372e-06,
+      "loss": 0.628,
+      "step": 251
+    },
+    {
+      "epoch": 2.896551724137931,
+      "grad_norm": 0.03709800913929939,
+      "learning_rate": 8.998820754091531e-07,
+      "loss": 0.6447,
+      "step": 252
+    },
+    {
+      "epoch": 2.9080459770114944,
+      "grad_norm": 0.03928203135728836,
+      "learning_rate": 7.291125901946027e-07,
+      "loss": 0.6615,
+      "step": 253
+    },
+    {
+      "epoch": 2.9195402298850572,
+      "grad_norm": 0.03835693374276161,
+      "learning_rate": 5.762361152572115e-07,
+      "loss": 0.6382,
+      "step": 254
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 0.037969332188367844,
+      "learning_rate": 4.412802057081278e-07,
+      "loss": 0.6339,
+      "step": 255
+    },
+    {
+      "epoch": 2.942528735632184,
+      "grad_norm": 0.0369732528924942,
+      "learning_rate": 3.2426918657900704e-07,
+      "loss": 0.6557,
+      "step": 256
+    },
+    {
+      "epoch": 2.954022988505747,
+      "grad_norm": 0.03954119607806206,
+      "learning_rate": 2.2522414843748618e-07,
+      "loss": 0.6419,
+      "step": 257
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 0.03722945228219032,
+      "learning_rate": 1.4416294358582384e-07,
+      "loss": 0.6224,
+      "step": 258
+    },
+    {
+      "epoch": 2.9770114942528734,
+      "grad_norm": 0.037498198449611664,
+      "learning_rate": 8.110018284304133e-08,
+      "loss": 0.6472,
+      "step": 259
+    },
+    {
+      "epoch": 2.9885057471264367,
+      "grad_norm": 0.03706786781549454,
+      "learning_rate": 3.60472329114625e-08,
+      "loss": 0.6532,
+      "step": 260
+    },
+    {
+      "epoch": 2.9885057471264367,
+      "eval_loss": 0.6546847820281982,
+      "eval_runtime": 591.4156,
+      "eval_samples_per_second": 16.736,
+      "eval_steps_per_second": 0.132,
+      "step": 260
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.0390935055911541,
+      "learning_rate": 9.012214327897006e-09,
+      "loss": 0.6416,
+      "step": 261
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 261,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.878497427033686e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

dataset/dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train", "validation"]}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.6547390818595886,
+    "eval_runtime": 593.5859,
+    "eval_samples_per_second": 16.675,
+    "eval_steps_per_second": 0.131
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.3"
+}

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a01351bcac657eaefc2e9e3d11e7999fb5115d36a7004d8288fd1c6afd8e06
+size 4997644048

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1faf7c204cb065e66a53906eeb6fef480fa0b0044300b4a21fa65e12226110f
+size 4997644048

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef940744ed95155d49513103d22a5073896b5c08525a5d7c95c23bf7870f553
+size 4997644648

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7138da6ef1ecb61ffee51f8a8fcf474a22f9c1f8ca62047d9a6bdafa7aefe43b
+size 4997644832

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9727935a1a96ff61603f1164fc77806cff43722a727667e846bddf593a1db5f3
+size 4997644832

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc78b560528b3b5fb99c5cd9be191b3653cd8e99ddb52cef6495e5a1c380a587
+size 4997644840

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fdbbe99e9a28b55d93d2bbe39c575666124318924e053c8c9fc0c796ce5e7d7
+size 4997644832

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5154600e305de315d7e6f655fbfb92f5bb41a8a11bcadcfa052f6f9552f5d58
+size 4997644832

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0cef068500a654df502bf5e7ab4e8e6a6e822afa96d4af8fcc58ab2bc08f05
+size 4997644832

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058bd9f0d364dbe675f7dd3833975ccc8bfab333952c64c9d58e71bad998b3d5
+size 4997644832

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d253c4f4094f8ededaede25589e9ddbe117b676cf79d43a0aeec1a075a86ee95
+size 4997644832

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 4.878497427033686e+19,
+    "train_loss": 0.6974607110023499,
+    "train_runtime": 68284.7248,
+    "train_samples_per_second": 3.914,
+    "train_steps_per_second": 0.004
+}

trainer_log.jsonl

@@ -0,0 +1,288 @@
+{"current_steps": 1, "total_steps": 261, "loss": 1.065, "lr": 0.0, "epoch": 0.011494252873563218, "percentage": 0.38, "elapsed_time": "0:03:31", "remaining_time": "15:16:23"}
+{"current_steps": 2, "total_steps": 261, "loss": 1.1025, "lr": 7.4074074074074075e-06, "epoch": 0.022988505747126436, "percentage": 0.77, "elapsed_time": "0:06:57", "remaining_time": "15:00:34"}
+{"current_steps": 3, "total_steps": 261, "loss": 1.067, "lr": 1.4814814814814815e-05, "epoch": 0.034482758620689655, "percentage": 1.15, "elapsed_time": "0:10:24", "remaining_time": "14:55:23"}
+{"current_steps": 4, "total_steps": 261, "loss": 1.0694, "lr": 2.2222222222222223e-05, "epoch": 0.04597701149425287, "percentage": 1.53, "elapsed_time": "0:13:50", "remaining_time": "14:49:39"}
+{"current_steps": 5, "total_steps": 261, "loss": 1.0767, "lr": 2.962962962962963e-05, "epoch": 0.05747126436781609, "percentage": 1.92, "elapsed_time": "0:17:13", "remaining_time": "14:42:13"}
+{"current_steps": 6, "total_steps": 261, "loss": 1.0414, "lr": 3.7037037037037037e-05, "epoch": 0.06896551724137931, "percentage": 2.3, "elapsed_time": "0:20:35", "remaining_time": "14:34:54"}
+{"current_steps": 7, "total_steps": 261, "loss": 1.021, "lr": 4.4444444444444447e-05, "epoch": 0.08045977011494253, "percentage": 2.68, "elapsed_time": "0:23:59", "remaining_time": "14:30:17"}
+{"current_steps": 8, "total_steps": 261, "loss": 1.0113, "lr": 5.185185185185185e-05, "epoch": 0.09195402298850575, "percentage": 3.07, "elapsed_time": "0:27:25", "remaining_time": "14:27:15"}
+{"current_steps": 9, "total_steps": 261, "loss": 0.9566, "lr": 5.925925925925926e-05, "epoch": 0.10344827586206896, "percentage": 3.45, "elapsed_time": "0:30:49", "remaining_time": "14:23:10"}
+{"current_steps": 10, "total_steps": 261, "loss": 0.9539, "lr": 6.666666666666667e-05, "epoch": 0.11494252873563218, "percentage": 3.83, "elapsed_time": "0:34:14", "remaining_time": "14:19:16"}
+{"current_steps": 10, "total_steps": 261, "eval_loss": 0.9960598945617676, "epoch": 0.11494252873563218, "percentage": 3.83, "elapsed_time": "0:44:19", "remaining_time": "18:32:39"}
+{"current_steps": 11, "total_steps": 261, "loss": 0.9163, "lr": 7.407407407407407e-05, "epoch": 0.12643678160919541, "percentage": 4.21, "elapsed_time": "0:47:43", "remaining_time": "18:04:40"}
+{"current_steps": 12, "total_steps": 261, "loss": 0.8886, "lr": 8.148148148148148e-05, "epoch": 0.13793103448275862, "percentage": 4.6, "elapsed_time": "0:51:06", "remaining_time": "17:40:22"}
+{"current_steps": 13, "total_steps": 261, "loss": 0.8748, "lr": 8.888888888888889e-05, "epoch": 0.14942528735632185, "percentage": 4.98, "elapsed_time": "0:54:28", "remaining_time": "17:19:08"}
+{"current_steps": 14, "total_steps": 261, "loss": 0.8235, "lr": 9.62962962962963e-05, "epoch": 0.16091954022988506, "percentage": 5.36, "elapsed_time": "0:57:50", "remaining_time": "17:00:35"}
+{"current_steps": 15, "total_steps": 261, "loss": 0.8539, "lr": 0.0001037037037037037, "epoch": 0.1724137931034483, "percentage": 5.75, "elapsed_time": "1:01:15", "remaining_time": "16:44:45"}
+{"current_steps": 16, "total_steps": 261, "loss": 0.8363, "lr": 0.00011111111111111112, "epoch": 0.1839080459770115, "percentage": 6.13, "elapsed_time": "1:04:38", "remaining_time": "16:29:53"}
+{"current_steps": 17, "total_steps": 261, "loss": 0.819, "lr": 0.00011851851851851852, "epoch": 0.19540229885057472, "percentage": 6.51, "elapsed_time": "1:08:04", "remaining_time": "16:16:59"}
+{"current_steps": 18, "total_steps": 261, "loss": 0.8069, "lr": 0.00012592592592592592, "epoch": 0.20689655172413793, "percentage": 6.9, "elapsed_time": "1:11:28", "remaining_time": "16:04:49"}
+{"current_steps": 19, "total_steps": 261, "loss": 0.8042, "lr": 0.00013333333333333334, "epoch": 0.21839080459770116, "percentage": 7.28, "elapsed_time": "1:14:51", "remaining_time": "15:53:22"}
+{"current_steps": 20, "total_steps": 261, "loss": 0.8283, "lr": 0.00014074074074074076, "epoch": 0.22988505747126436, "percentage": 7.66, "elapsed_time": "1:18:15", "remaining_time": "15:42:56"}
+{"current_steps": 20, "total_steps": 261, "eval_loss": 0.813089907169342, "epoch": 0.22988505747126436, "percentage": 7.66, "elapsed_time": "1:28:16", "remaining_time": "17:43:42"}
+{"current_steps": 21, "total_steps": 261, "loss": 0.8142, "lr": 0.00014814814814814815, "epoch": 0.2413793103448276, "percentage": 8.05, "elapsed_time": "1:31:38", "remaining_time": "17:27:24"}
+{"current_steps": 22, "total_steps": 261, "loss": 0.794, "lr": 0.00015555555555555556, "epoch": 0.25287356321839083, "percentage": 8.43, "elapsed_time": "1:35:04", "remaining_time": "17:12:51"}
+{"current_steps": 23, "total_steps": 261, "loss": 0.8231, "lr": 0.00016296296296296295, "epoch": 0.26436781609195403, "percentage": 8.81, "elapsed_time": "1:38:29", "remaining_time": "16:59:09"}
+{"current_steps": 24, "total_steps": 261, "loss": 0.7874, "lr": 0.00017037037037037037, "epoch": 0.27586206896551724, "percentage": 9.2, "elapsed_time": "1:41:50", "remaining_time": "16:45:43"}
+{"current_steps": 25, "total_steps": 261, "loss": 0.8075, "lr": 0.00017777777777777779, "epoch": 0.28735632183908044, "percentage": 9.58, "elapsed_time": "1:45:16", "remaining_time": "16:33:45"}
+{"current_steps": 26, "total_steps": 261, "loss": 0.779, "lr": 0.0001851851851851852, "epoch": 0.2988505747126437, "percentage": 9.96, "elapsed_time": "1:48:40", "remaining_time": "16:22:13"}
+{"current_steps": 27, "total_steps": 261, "loss": 0.7878, "lr": 0.0001925925925925926, "epoch": 0.3103448275862069, "percentage": 10.34, "elapsed_time": "1:52:05", "remaining_time": "16:11:24"}
+{"current_steps": 28, "total_steps": 261, "loss": 0.7876, "lr": 0.0002, "epoch": 0.3218390804597701, "percentage": 10.73, "elapsed_time": "1:55:29", "remaining_time": "16:01:02"}
+{"current_steps": 29, "total_steps": 261, "loss": 0.7686, "lr": 0.00019999098778567212, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "1:58:53", "remaining_time": "15:51:05"}
+{"current_steps": 30, "total_steps": 261, "loss": 0.7525, "lr": 0.00019996395276708856, "epoch": 0.3448275862068966, "percentage": 11.49, "elapsed_time": "2:02:15", "remaining_time": "15:41:26"}
+{"current_steps": 30, "total_steps": 261, "eval_loss": 0.7719228863716125, "epoch": 0.3448275862068966, "percentage": 11.49, "elapsed_time": "2:12:22", "remaining_time": "16:59:18"}
+{"current_steps": 31, "total_steps": 261, "loss": 0.777, "lr": 0.00019991889981715698, "epoch": 0.3563218390804598, "percentage": 11.88, "elapsed_time": "2:15:48", "remaining_time": "16:47:34"}
+{"current_steps": 32, "total_steps": 261, "loss": 0.7797, "lr": 0.00019985583705641418, "epoch": 0.367816091954023, "percentage": 12.26, "elapsed_time": "2:19:10", "remaining_time": "16:36:01"}
+{"current_steps": 33, "total_steps": 261, "loss": 0.7744, "lr": 0.00019977477585156252, "epoch": 0.3793103448275862, "percentage": 12.64, "elapsed_time": "2:22:40", "remaining_time": "16:25:42"}
+{"current_steps": 34, "total_steps": 261, "loss": 0.7631, "lr": 0.00019967573081342103, "epoch": 0.39080459770114945, "percentage": 13.03, "elapsed_time": "2:26:03", "remaining_time": "16:15:08"}
+{"current_steps": 35, "total_steps": 261, "loss": 0.7512, "lr": 0.0001995587197942919, "epoch": 0.40229885057471265, "percentage": 13.41, "elapsed_time": "2:29:27", "remaining_time": "16:05:02"}
+{"current_steps": 36, "total_steps": 261, "loss": 0.7567, "lr": 0.0001994237638847428, "epoch": 0.41379310344827586, "percentage": 13.79, "elapsed_time": "2:32:50", "remaining_time": "15:55:15"}
+{"current_steps": 37, "total_steps": 261, "loss": 0.7723, "lr": 0.0001992708874098054, "epoch": 0.42528735632183906, "percentage": 14.18, "elapsed_time": "2:36:14", "remaining_time": "15:45:50"}
+{"current_steps": 38, "total_steps": 261, "loss": 0.77, "lr": 0.00019910011792459087, "epoch": 0.4367816091954023, "percentage": 14.56, "elapsed_time": "2:39:38", "remaining_time": "15:36:51"}
+{"current_steps": 39, "total_steps": 261, "loss": 0.7764, "lr": 0.00019891148620932318, "epoch": 0.4482758620689655, "percentage": 14.94, "elapsed_time": "2:43:00", "remaining_time": "15:27:54"}
+{"current_steps": 40, "total_steps": 261, "loss": 0.7418, "lr": 0.00019870502626379127, "epoch": 0.45977011494252873, "percentage": 15.33, "elapsed_time": "2:46:23", "remaining_time": "15:19:19"}
+{"current_steps": 40, "total_steps": 261, "eval_loss": 0.7480100393295288, "epoch": 0.45977011494252873, "percentage": 15.33, "elapsed_time": "2:56:24", "remaining_time": "16:14:42"}
+{"current_steps": 41, "total_steps": 261, "loss": 0.7487, "lr": 0.00019848077530122083, "epoch": 0.47126436781609193, "percentage": 15.71, "elapsed_time": "2:59:48", "remaining_time": "16:04:49"}
+{"current_steps": 42, "total_steps": 261, "loss": 0.7417, "lr": 0.00019823877374156647, "epoch": 0.4827586206896552, "percentage": 16.09, "elapsed_time": "3:03:10", "remaining_time": "15:55:06"}
+{"current_steps": 43, "total_steps": 261, "loss": 0.7437, "lr": 0.00019797906520422677, "epoch": 0.4942528735632184, "percentage": 16.48, "elapsed_time": "3:06:32", "remaining_time": "15:45:44"}
+{"current_steps": 44, "total_steps": 261, "loss": 0.7752, "lr": 0.00019770169650018172, "epoch": 0.5057471264367817, "percentage": 16.86, "elapsed_time": "3:09:57", "remaining_time": "15:36:48"}
+{"current_steps": 45, "total_steps": 261, "loss": 0.7363, "lr": 0.00019740671762355548, "epoch": 0.5172413793103449, "percentage": 17.24, "elapsed_time": "3:13:22", "remaining_time": "15:28:13"}
+{"current_steps": 46, "total_steps": 261, "loss": 0.74, "lr": 0.0001970941817426052, "epoch": 0.5287356321839081, "percentage": 17.62, "elapsed_time": "3:16:46", "remaining_time": "15:19:44"}
+{"current_steps": 47, "total_steps": 261, "loss": 0.7246, "lr": 0.00019676414519013781, "epoch": 0.5402298850574713, "percentage": 18.01, "elapsed_time": "3:20:12", "remaining_time": "15:11:34"}
+{"current_steps": 48, "total_steps": 261, "loss": 0.7465, "lr": 0.00019641666745335624, "epoch": 0.5517241379310345, "percentage": 18.39, "elapsed_time": "3:23:39", "remaining_time": "15:03:43"}
+{"current_steps": 49, "total_steps": 261, "loss": 0.721, "lr": 0.00019605181116313724, "epoch": 0.5632183908045977, "percentage": 18.77, "elapsed_time": "3:27:03", "remaining_time": "14:55:52"}
+{"current_steps": 50, "total_steps": 261, "loss": 0.7291, "lr": 0.00019566964208274254, "epoch": 0.5747126436781609, "percentage": 19.16, "elapsed_time": "3:30:27", "remaining_time": "14:48:09"}
+{"current_steps": 50, "total_steps": 261, "eval_loss": 0.7319945096969604, "epoch": 0.5747126436781609, "percentage": 19.16, "elapsed_time": "3:40:29", "remaining_time": "15:30:28"}
+{"current_steps": 51, "total_steps": 261, "loss": 0.7396, "lr": 0.00019527022909596536, "epoch": 0.5862068965517241, "percentage": 19.54, "elapsed_time": "3:44:12", "remaining_time": "15:23:10"}
+{"current_steps": 52, "total_steps": 261, "loss": 0.733, "lr": 0.00019485364419471454, "epoch": 0.5977011494252874, "percentage": 19.92, "elapsed_time": "3:47:34", "remaining_time": "15:14:40"}
+{"current_steps": 53, "total_steps": 261, "loss": 0.7378, "lr": 0.00019441996246603846, "epoch": 0.6091954022988506, "percentage": 20.31, "elapsed_time": "3:51:01", "remaining_time": "15:06:38"}
+{"current_steps": 54, "total_steps": 261, "loss": 0.7293, "lr": 0.00019396926207859084, "epoch": 0.6206896551724138, "percentage": 20.69, "elapsed_time": "3:54:23", "remaining_time": "14:58:29"}
+{"current_steps": 55, "total_steps": 261, "loss": 0.7287, "lr": 0.0001935016242685415, "epoch": 0.632183908045977, "percentage": 21.07, "elapsed_time": "3:57:46", "remaining_time": "14:50:35"}
+{"current_steps": 56, "total_steps": 261, "loss": 0.7354, "lr": 0.00019301713332493386, "epoch": 0.6436781609195402, "percentage": 21.46, "elapsed_time": "4:01:09", "remaining_time": "14:42:47"}
+{"current_steps": 57, "total_steps": 261, "loss": 0.7376, "lr": 0.00019251587657449236, "epoch": 0.6551724137931034, "percentage": 21.84, "elapsed_time": "4:04:34", "remaining_time": "14:35:18"}
+{"current_steps": 58, "total_steps": 261, "loss": 0.7389, "lr": 0.00019199794436588243, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "4:07:57", "remaining_time": "14:27:50"}
+{"current_steps": 59, "total_steps": 261, "loss": 0.7275, "lr": 0.00019146343005342547, "epoch": 0.6781609195402298, "percentage": 22.61, "elapsed_time": "4:11:21", "remaining_time": "14:20:33"}
+{"current_steps": 60, "total_steps": 261, "loss": 0.7244, "lr": 0.0001909124299802724, "epoch": 0.6896551724137931, "percentage": 22.99, "elapsed_time": "4:14:45", "remaining_time": "14:13:25"}
+{"current_steps": 60, "total_steps": 261, "eval_loss": 0.7189474701881409, "epoch": 0.6896551724137931, "percentage": 22.99, "elapsed_time": "4:24:50", "remaining_time": "14:47:12"}
+{"current_steps": 61, "total_steps": 261, "loss": 0.7339, "lr": 0.00019034504346103823, "epoch": 0.7011494252873564, "percentage": 23.37, "elapsed_time": "4:28:15", "remaining_time": "14:39:33"}
+{"current_steps": 62, "total_steps": 261, "loss": 0.7349, "lr": 0.0001897613727639014, "epoch": 0.7126436781609196, "percentage": 23.75, "elapsed_time": "4:31:40", "remaining_time": "14:31:58"}
+{"current_steps": 63, "total_steps": 261, "loss": 0.7008, "lr": 0.0001891615230921703, "epoch": 0.7241379310344828, "percentage": 24.14, "elapsed_time": "4:35:04", "remaining_time": "14:24:30"}
+{"current_steps": 64, "total_steps": 261, "loss": 0.7404, "lr": 0.000188545602565321, "epoch": 0.735632183908046, "percentage": 24.52, "elapsed_time": "4:38:30", "remaining_time": "14:17:15"}
+{"current_steps": 65, "total_steps": 261, "loss": 0.7203, "lr": 0.00018791372219950948, "epoch": 0.7471264367816092, "percentage": 24.9, "elapsed_time": "4:41:55", "remaining_time": "14:10:06"}
+{"current_steps": 66, "total_steps": 261, "loss": 0.7188, "lr": 0.00018726599588756145, "epoch": 0.7586206896551724, "percentage": 25.29, "elapsed_time": "4:45:17", "remaining_time": "14:02:53"}
+{"current_steps": 67, "total_steps": 261, "loss": 0.7129, "lr": 0.00018660254037844388, "epoch": 0.7701149425287356, "percentage": 25.67, "elapsed_time": "4:48:41", "remaining_time": "13:55:55"}
+{"current_steps": 68, "total_steps": 261, "loss": 0.7081, "lr": 0.0001859234752562217, "epoch": 0.7816091954022989, "percentage": 26.05, "elapsed_time": "4:52:10", "remaining_time": "13:49:14"}
+{"current_steps": 69, "total_steps": 261, "loss": 0.6971, "lr": 0.00018522892291850335, "epoch": 0.7931034482758621, "percentage": 26.44, "elapsed_time": "4:55:35", "remaining_time": "13:42:30"}
+{"current_steps": 70, "total_steps": 261, "loss": 0.721, "lr": 0.0001845190085543795, "epoch": 0.8045977011494253, "percentage": 26.82, "elapsed_time": "4:58:57", "remaining_time": "13:35:44"}
+{"current_steps": 70, "total_steps": 261, "eval_loss": 0.7084506154060364, "epoch": 0.8045977011494253, "percentage": 26.82, "elapsed_time": "5:09:01", "remaining_time": "14:03:11"}
+{"current_steps": 71, "total_steps": 261, "loss": 0.7192, "lr": 0.00018379386012185814, "epoch": 0.8160919540229885, "percentage": 27.2, "elapsed_time": "5:12:27", "remaining_time": "13:56:08"}
+{"current_steps": 72, "total_steps": 261, "loss": 0.7258, "lr": 0.00018305360832480117, "epoch": 0.8275862068965517, "percentage": 27.59, "elapsed_time": "5:15:52", "remaining_time": "13:49:10"}
+{"current_steps": 73, "total_steps": 261, "loss": 0.7327, "lr": 0.00018229838658936564, "epoch": 0.8390804597701149, "percentage": 27.97, "elapsed_time": "5:19:16", "remaining_time": "13:42:13"}
+{"current_steps": 74, "total_steps": 261, "loss": 0.7007, "lr": 0.00018152833103995443, "epoch": 0.8505747126436781, "percentage": 28.35, "elapsed_time": "5:22:39", "remaining_time": "13:35:22"}
+{"current_steps": 75, "total_steps": 261, "loss": 0.7106, "lr": 0.0001807435804746807, "epoch": 0.8620689655172413, "percentage": 28.74, "elapsed_time": "5:26:03", "remaining_time": "13:28:37"}
+{"current_steps": 76, "total_steps": 261, "loss": 0.7056, "lr": 0.00017994427634035015, "epoch": 0.8735632183908046, "percentage": 29.12, "elapsed_time": "5:29:29", "remaining_time": "13:22:01"}
+{"current_steps": 77, "total_steps": 261, "loss": 0.6898, "lr": 0.0001791305627069662, "epoch": 0.8850574712643678, "percentage": 29.5, "elapsed_time": "5:32:56", "remaining_time": "13:15:35"}
+{"current_steps": 78, "total_steps": 261, "loss": 0.71, "lr": 0.00017830258624176225, "epoch": 0.896551724137931, "percentage": 29.89, "elapsed_time": "5:36:20", "remaining_time": "13:09:06"}
+{"current_steps": 79, "total_steps": 261, "loss": 0.7104, "lr": 0.00017746049618276545, "epoch": 0.9080459770114943, "percentage": 30.27, "elapsed_time": "5:39:43", "remaining_time": "13:02:40"}
+{"current_steps": 80, "total_steps": 261, "loss": 0.6964, "lr": 0.0001766044443118978, "epoch": 0.9195402298850575, "percentage": 30.65, "elapsed_time": "5:43:07", "remaining_time": "12:56:19"}
+{"current_steps": 80, "total_steps": 261, "eval_loss": 0.6998673677444458, "epoch": 0.9195402298850575, "percentage": 30.65, "elapsed_time": "5:53:06", "remaining_time": "13:18:55"}
+{"current_steps": 81, "total_steps": 261, "loss": 0.7048, "lr": 0.00017573458492761801, "epoch": 0.9310344827586207, "percentage": 31.03, "elapsed_time": "5:56:27", "remaining_time": "13:12:08"}
+{"current_steps": 82, "total_steps": 261, "loss": 0.7089, "lr": 0.00017485107481711012, "epoch": 0.9425287356321839, "percentage": 31.42, "elapsed_time": "5:59:51", "remaining_time": "13:05:31"}
+{"current_steps": 83, "total_steps": 261, "loss": 0.7184, "lr": 0.00017395407322802372, "epoch": 0.9540229885057471, "percentage": 31.8, "elapsed_time": "6:03:18", "remaining_time": "12:59:08"}
+{"current_steps": 84, "total_steps": 261, "loss": 0.6878, "lr": 0.00017304374183977033, "epoch": 0.9655172413793104, "percentage": 32.18, "elapsed_time": "6:06:42", "remaining_time": "12:52:41"}
+{"current_steps": 85, "total_steps": 261, "loss": 0.7223, "lr": 0.00017212024473438147, "epoch": 0.9770114942528736, "percentage": 32.57, "elapsed_time": "6:10:04", "remaining_time": "12:46:16"}
+{"current_steps": 86, "total_steps": 261, "loss": 0.6936, "lr": 0.00017118374836693406, "epoch": 0.9885057471264368, "percentage": 32.95, "elapsed_time": "6:13:27", "remaining_time": "12:39:56"}
+{"current_steps": 87, "total_steps": 261, "loss": 0.6906, "lr": 0.00017023442153554777, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "6:16:51", "remaining_time": "12:33:42"}
+{"current_steps": 88, "total_steps": 261, "loss": 0.6915, "lr": 0.00016927243535095997, "epoch": 1.0114942528735633, "percentage": 33.72, "elapsed_time": "6:20:15", "remaining_time": "12:27:33"}
+{"current_steps": 89, "total_steps": 261, "loss": 0.6792, "lr": 0.00016829796320568416, "epoch": 1.0229885057471264, "percentage": 34.1, "elapsed_time": "6:23:38", "remaining_time": "12:21:24"}
+{"current_steps": 90, "total_steps": 261, "loss": 0.6965, "lr": 0.00016731118074275704, "epoch": 1.0344827586206897, "percentage": 34.48, "elapsed_time": "6:27:03", "remaining_time": "12:15:24"}
+{"current_steps": 90, "total_steps": 261, "eval_loss": 0.6928127408027649, "epoch": 1.0344827586206897, "percentage": 34.48, "elapsed_time": "6:37:10", "remaining_time": "12:34:37"}
+{"current_steps": 91, "total_steps": 261, "loss": 0.6726, "lr": 0.00016631226582407952, "epoch": 1.0459770114942528, "percentage": 34.87, "elapsed_time": "6:40:35", "remaining_time": "12:28:20"}
+{"current_steps": 92, "total_steps": 261, "loss": 0.6792, "lr": 0.0001653013984983585, "epoch": 1.0574712643678161, "percentage": 35.25, "elapsed_time": "6:43:59", "remaining_time": "12:22:06"}
+{"current_steps": 93, "total_steps": 261, "loss": 0.6921, "lr": 0.00016427876096865394, "epoch": 1.0689655172413792, "percentage": 35.63, "elapsed_time": "6:47:23", "remaining_time": "12:15:55"}
+{"current_steps": 94, "total_steps": 261, "loss": 0.6829, "lr": 0.00016324453755953773, "epoch": 1.0804597701149425, "percentage": 36.02, "elapsed_time": "6:50:44", "remaining_time": "12:09:43"}
+{"current_steps": 95, "total_steps": 261, "loss": 0.6737, "lr": 0.0001621989146838704, "epoch": 1.0919540229885056, "percentage": 36.4, "elapsed_time": "6:54:10", "remaining_time": "12:03:42"}
+{"current_steps": 96, "total_steps": 261, "loss": 0.6852, "lr": 0.00016114208080920123, "epoch": 1.103448275862069, "percentage": 36.78, "elapsed_time": "6:57:35", "remaining_time": "11:57:43"}
+{"current_steps": 97, "total_steps": 261, "loss": 0.6863, "lr": 0.0001600742264237979, "epoch": 1.1149425287356323, "percentage": 37.16, "elapsed_time": "7:00:58", "remaining_time": "11:51:45"}
+{"current_steps": 98, "total_steps": 261, "loss": 0.6785, "lr": 0.00015899554400231232, "epoch": 1.1264367816091954, "percentage": 37.55, "elapsed_time": "7:04:27", "remaining_time": "11:45:59"}
+{"current_steps": 99, "total_steps": 261, "loss": 0.7001, "lr": 0.0001579062279710879, "epoch": 1.1379310344827587, "percentage": 37.93, "elapsed_time": "7:07:51", "remaining_time": "11:40:08"}
+{"current_steps": 100, "total_steps": 261, "loss": 0.6856, "lr": 0.00015680647467311557, "epoch": 1.1494252873563218, "percentage": 38.31, "elapsed_time": "7:11:14", "remaining_time": "11:34:18"}
+{"current_steps": 100, "total_steps": 261, "eval_loss": 0.686887264251709, "epoch": 1.1494252873563218, "percentage": 38.31, "elapsed_time": "7:21:14", "remaining_time": "11:50:23"}
+{"current_steps": 101, "total_steps": 261, "loss": 0.6836, "lr": 0.00015569648233264394, "epoch": 1.160919540229885, "percentage": 38.7, "elapsed_time": "7:24:57", "remaining_time": "11:44:52"}
+{"current_steps": 102, "total_steps": 261, "loss": 0.6827, "lr": 0.00015457645101945046, "epoch": 1.1724137931034484, "percentage": 39.08, "elapsed_time": "7:28:19", "remaining_time": "11:38:52"}
+{"current_steps": 103, "total_steps": 261, "loss": 0.6823, "lr": 0.0001534465826127801, "epoch": 1.1839080459770115, "percentage": 39.46, "elapsed_time": "7:31:43", "remaining_time": "11:32:55"}
+{"current_steps": 104, "total_steps": 261, "loss": 0.6729, "lr": 0.00015230708076495775, "epoch": 1.1954022988505748, "percentage": 39.85, "elapsed_time": "7:35:03", "remaining_time": "11:26:58"}
+{"current_steps": 105, "total_steps": 261, "loss": 0.6778, "lr": 0.00015115815086468102, "epoch": 1.206896551724138, "percentage": 40.23, "elapsed_time": "7:38:27", "remaining_time": "11:21:07"}
+{"current_steps": 106, "total_steps": 261, "loss": 0.674, "lr": 0.00015000000000000001, "epoch": 1.2183908045977012, "percentage": 40.61, "elapsed_time": "7:41:49", "remaining_time": "11:15:18"}
+{"current_steps": 107, "total_steps": 261, "loss": 0.6799, "lr": 0.00014883283692099112, "epoch": 1.2298850574712643, "percentage": 41.0, "elapsed_time": "7:45:14", "remaining_time": "11:09:35"}
+{"current_steps": 108, "total_steps": 261, "loss": 0.6851, "lr": 0.0001476568720021308, "epoch": 1.2413793103448276, "percentage": 41.38, "elapsed_time": "7:48:39", "remaining_time": "11:03:56"}
+{"current_steps": 109, "total_steps": 261, "loss": 0.7094, "lr": 0.00014647231720437686, "epoch": 1.2528735632183907, "percentage": 41.76, "elapsed_time": "7:52:02", "remaining_time": "10:58:15"}
+{"current_steps": 110, "total_steps": 261, "loss": 0.6812, "lr": 0.00014527938603696376, "epoch": 1.264367816091954, "percentage": 42.15, "elapsed_time": "7:55:26", "remaining_time": "10:52:38"}
+{"current_steps": 110, "total_steps": 261, "eval_loss": 0.6802834868431091, "epoch": 1.264367816091954, "percentage": 42.15, "elapsed_time": "8:05:23", "remaining_time": "11:06:18"}
+{"current_steps": 111, "total_steps": 261, "loss": 0.679, "lr": 0.00014407829351891857, "epoch": 1.2758620689655173, "percentage": 42.53, "elapsed_time": "8:08:45", "remaining_time": "11:00:29"}
+{"current_steps": 112, "total_steps": 261, "loss": 0.6722, "lr": 0.00014286925614030542, "epoch": 1.2873563218390804, "percentage": 42.91, "elapsed_time": "8:12:07", "remaining_time": "10:54:42"}
+{"current_steps": 113, "total_steps": 261, "loss": 0.6879, "lr": 0.00014165249182320402, "epoch": 1.2988505747126438, "percentage": 43.3, "elapsed_time": "8:15:31", "remaining_time": "10:48:59"}
+{"current_steps": 114, "total_steps": 261, "loss": 0.6627, "lr": 0.0001404282198824305, "epoch": 1.3103448275862069, "percentage": 43.68, "elapsed_time": "8:18:54", "remaining_time": "10:43:19"}
+{"current_steps": 115, "total_steps": 261, "loss": 0.6751, "lr": 0.00013919666098600753, "epoch": 1.3218390804597702, "percentage": 44.06, "elapsed_time": "8:22:20", "remaining_time": "10:37:45"}
+{"current_steps": 116, "total_steps": 261, "loss": 0.6827, "lr": 0.00013795803711538966, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "8:25:40", "remaining_time": "10:32:05"}
+{"current_steps": 117, "total_steps": 261, "loss": 0.6648, "lr": 0.00013671257152545277, "epoch": 1.3448275862068966, "percentage": 44.83, "elapsed_time": "8:29:05", "remaining_time": "10:26:33"}
+{"current_steps": 118, "total_steps": 261, "loss": 0.6771, "lr": 0.00013546048870425356, "epoch": 1.3563218390804597, "percentage": 45.21, "elapsed_time": "8:32:33", "remaining_time": "10:21:08"}
+{"current_steps": 119, "total_steps": 261, "loss": 0.6623, "lr": 0.00013420201433256689, "epoch": 1.367816091954023, "percentage": 45.59, "elapsed_time": "8:35:55", "remaining_time": "10:15:38"}
+{"current_steps": 120, "total_steps": 261, "loss": 0.6734, "lr": 0.00013293737524320797, "epoch": 1.3793103448275863, "percentage": 45.98, "elapsed_time": "8:39:22", "remaining_time": "10:10:15"}
+{"current_steps": 120, "total_steps": 261, "eval_loss": 0.6736027002334595, "epoch": 1.3793103448275863, "percentage": 45.98, "elapsed_time": "8:49:23", "remaining_time": "10:22:01"}
+{"current_steps": 121, "total_steps": 261, "loss": 0.6625, "lr": 0.00013166679938014726, "epoch": 1.3908045977011494, "percentage": 46.36, "elapsed_time": "8:52:45", "remaining_time": "10:16:24"}
+{"current_steps": 122, "total_steps": 261, "loss": 0.6738, "lr": 0.0001303905157574247, "epoch": 1.4022988505747127, "percentage": 46.74, "elapsed_time": "8:56:09", "remaining_time": "10:10:51"}
+{"current_steps": 123, "total_steps": 261, "loss": 0.6511, "lr": 0.00012910875441787128, "epoch": 1.4137931034482758, "percentage": 47.13, "elapsed_time": "8:59:34", "remaining_time": "10:05:22"}
+{"current_steps": 124, "total_steps": 261, "loss": 0.6579, "lr": 0.0001278217463916453, "epoch": 1.4252873563218391, "percentage": 47.51, "elapsed_time": "9:02:57", "remaining_time": "9:59:52"}
+{"current_steps": 125, "total_steps": 261, "loss": 0.6508, "lr": 0.0001265297236545901, "epoch": 1.4367816091954024, "percentage": 47.89, "elapsed_time": "9:06:20", "remaining_time": "9:54:25"}
+{"current_steps": 126, "total_steps": 261, "loss": 0.6867, "lr": 0.00012523291908642217, "epoch": 1.4482758620689655, "percentage": 48.28, "elapsed_time": "9:09:45", "remaining_time": "9:49:01"}
+{"current_steps": 127, "total_steps": 261, "loss": 0.6609, "lr": 0.0001239315664287558, "epoch": 1.4597701149425286, "percentage": 48.66, "elapsed_time": "9:13:08", "remaining_time": "9:43:37"}
+{"current_steps": 128, "total_steps": 261, "loss": 0.6708, "lr": 0.00012262590024297225, "epoch": 1.471264367816092, "percentage": 49.04, "elapsed_time": "9:16:33", "remaining_time": "9:38:17"}
+{"current_steps": 129, "total_steps": 261, "loss": 0.6853, "lr": 0.0001213161558679416, "epoch": 1.4827586206896552, "percentage": 49.43, "elapsed_time": "9:19:55", "remaining_time": "9:32:56"}
+{"current_steps": 130, "total_steps": 261, "loss": 0.658, "lr": 0.00012000256937760445, "epoch": 1.4942528735632183, "percentage": 49.81, "elapsed_time": "9:23:18", "remaining_time": "9:27:38"}
+{"current_steps": 130, "total_steps": 261, "eval_loss": 0.6697064638137817, "epoch": 1.4942528735632183, "percentage": 49.81, "elapsed_time": "9:33:13", "remaining_time": "9:37:38"}
+{"current_steps": 131, "total_steps": 261, "loss": 0.6688, "lr": 0.00011868537753842051, "epoch": 1.5057471264367817, "percentage": 50.19, "elapsed_time": "9:36:35", "remaining_time": "9:32:11"}
+{"current_steps": 132, "total_steps": 261, "loss": 0.6828, "lr": 0.00011736481776669306, "epoch": 1.5172413793103448, "percentage": 50.57, "elapsed_time": "9:39:58", "remaining_time": "9:26:47"}
+{"current_steps": 133, "total_steps": 261, "loss": 0.6776, "lr": 0.00011604112808577603, "epoch": 1.528735632183908, "percentage": 50.96, "elapsed_time": "9:43:18", "remaining_time": "9:21:23"}
+{"current_steps": 134, "total_steps": 261, "loss": 0.6276, "lr": 0.00011471454708317162, "epoch": 1.5402298850574714, "percentage": 51.34, "elapsed_time": "9:46:40", "remaining_time": "9:16:01"}
+{"current_steps": 135, "total_steps": 261, "loss": 0.6427, "lr": 0.00011338531386752618, "epoch": 1.5517241379310345, "percentage": 51.72, "elapsed_time": "9:50:02", "remaining_time": "9:10:42"}
+{"current_steps": 136, "total_steps": 261, "loss": 0.652, "lr": 0.0001120536680255323, "epoch": 1.5632183908045976, "percentage": 52.11, "elapsed_time": "9:53:22", "remaining_time": "9:05:23"}
+{"current_steps": 137, "total_steps": 261, "loss": 0.6725, "lr": 0.00011071984957874479, "epoch": 1.5747126436781609, "percentage": 52.49, "elapsed_time": "9:56:43", "remaining_time": "9:00:06"}
+{"current_steps": 138, "total_steps": 261, "loss": 0.6479, "lr": 0.00010938409894031794, "epoch": 1.5862068965517242, "percentage": 52.87, "elapsed_time": "10:00:02", "remaining_time": "8:54:49"}
+{"current_steps": 139, "total_steps": 261, "loss": 0.6681, "lr": 0.00010804665687167262, "epoch": 1.5977011494252875, "percentage": 53.26, "elapsed_time": "10:03:22", "remaining_time": "8:49:34"}
+{"current_steps": 140, "total_steps": 261, "loss": 0.6703, "lr": 0.00010670776443910024, "epoch": 1.6091954022988506, "percentage": 53.64, "elapsed_time": "10:06:41", "remaining_time": "8:44:21"}
+{"current_steps": 140, "total_steps": 261, "eval_loss": 0.6661256551742554, "epoch": 1.6091954022988506, "percentage": 53.64, "elapsed_time": "10:16:32", "remaining_time": "8:52:52"}
+{"current_steps": 141, "total_steps": 261, "loss": 0.6643, "lr": 0.00010536766297031215, "epoch": 1.6206896551724137, "percentage": 54.02, "elapsed_time": "10:19:53", "remaining_time": "8:47:34"}
+{"current_steps": 142, "total_steps": 261, "loss": 0.6583, "lr": 0.00010402659401094152, "epoch": 1.632183908045977, "percentage": 54.41, "elapsed_time": "10:23:12", "remaining_time": "8:42:16"}
+{"current_steps": 143, "total_steps": 261, "loss": 0.6753, "lr": 0.00010268479928100614, "epoch": 1.6436781609195403, "percentage": 54.79, "elapsed_time": "10:26:35", "remaining_time": "8:37:02"}
+{"current_steps": 144, "total_steps": 261, "loss": 0.6493, "lr": 0.00010134252063133975, "epoch": 1.6551724137931034, "percentage": 55.17, "elapsed_time": "10:29:54", "remaining_time": "8:31:47"}
+{"current_steps": 145, "total_steps": 261, "loss": 0.6515, "lr": 0.0001, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "10:33:13", "remaining_time": "8:26:34"}
+{"current_steps": 146, "total_steps": 261, "loss": 0.6638, "lr": 9.865747936866027e-05, "epoch": 1.6781609195402298, "percentage": 55.94, "elapsed_time": "10:36:32", "remaining_time": "8:21:22"}
+{"current_steps": 147, "total_steps": 261, "loss": 0.6496, "lr": 9.73152007189939e-05, "epoch": 1.6896551724137931, "percentage": 56.32, "elapsed_time": "10:39:50", "remaining_time": "8:16:11"}
+{"current_steps": 148, "total_steps": 261, "loss": 0.6893, "lr": 9.597340598905852e-05, "epoch": 1.7011494252873565, "percentage": 56.7, "elapsed_time": "10:43:11", "remaining_time": "8:11:04"}
+{"current_steps": 149, "total_steps": 261, "loss": 0.6728, "lr": 9.463233702968783e-05, "epoch": 1.7126436781609196, "percentage": 57.09, "elapsed_time": "10:46:30", "remaining_time": "8:05:57"}
+{"current_steps": 150, "total_steps": 261, "loss": 0.6814, "lr": 9.329223556089975e-05, "epoch": 1.7241379310344827, "percentage": 57.47, "elapsed_time": "10:49:51", "remaining_time": "8:00:53"}
+{"current_steps": 150, "total_steps": 261, "eval_loss": 0.6631415486335754, "epoch": 1.7241379310344827, "percentage": 57.47, "elapsed_time": "10:59:47", "remaining_time": "8:08:14"}
+{"current_steps": 151, "total_steps": 261, "loss": 0.6421, "lr": 9.195334312832742e-05, "epoch": 1.735632183908046, "percentage": 57.85, "elapsed_time": "11:03:29", "remaining_time": "8:03:20"}
+{"current_steps": 152, "total_steps": 261, "loss": 0.6739, "lr": 9.061590105968208e-05, "epoch": 1.7471264367816093, "percentage": 58.24, "elapsed_time": "11:06:48", "remaining_time": "7:58:10"}
+{"current_steps": 153, "total_steps": 261, "loss": 0.6579, "lr": 8.928015042125523e-05, "epoch": 1.7586206896551724, "percentage": 58.62, "elapsed_time": "11:10:06", "remaining_time": "7:53:00"}
+{"current_steps": 154, "total_steps": 261, "loss": 0.645, "lr": 8.79463319744677e-05, "epoch": 1.7701149425287355, "percentage": 59.0, "elapsed_time": "11:13:26", "remaining_time": "7:47:54"}
+{"current_steps": 155, "total_steps": 261, "loss": 0.6594, "lr": 8.661468613247387e-05, "epoch": 1.7816091954022988, "percentage": 59.39, "elapsed_time": "11:16:45", "remaining_time": "7:42:48"}
+{"current_steps": 156, "total_steps": 261, "loss": 0.6723, "lr": 8.528545291682838e-05, "epoch": 1.793103448275862, "percentage": 59.77, "elapsed_time": "11:20:05", "remaining_time": "7:37:44"}
+{"current_steps": 157, "total_steps": 261, "loss": 0.6715, "lr": 8.395887191422397e-05, "epoch": 1.8045977011494254, "percentage": 60.15, "elapsed_time": "11:23:24", "remaining_time": "7:32:41"}
+{"current_steps": 158, "total_steps": 261, "loss": 0.6767, "lr": 8.263518223330697e-05, "epoch": 1.8160919540229885, "percentage": 60.54, "elapsed_time": "11:26:42", "remaining_time": "7:27:40"}
+{"current_steps": 159, "total_steps": 261, "loss": 0.6552, "lr": 8.131462246157953e-05, "epoch": 1.8275862068965516, "percentage": 60.92, "elapsed_time": "11:30:01", "remaining_time": "7:22:39"}
+{"current_steps": 160, "total_steps": 261, "loss": 0.6688, "lr": 7.999743062239557e-05, "epoch": 1.839080459770115, "percentage": 61.3, "elapsed_time": "11:33:20", "remaining_time": "7:17:40"}
+{"current_steps": 160, "total_steps": 261, "eval_loss": 0.6607028245925903, "epoch": 1.839080459770115, "percentage": 61.3, "elapsed_time": "11:43:10", "remaining_time": "7:23:52"}
+{"current_steps": 161, "total_steps": 261, "loss": 0.672, "lr": 7.868384413205842e-05, "epoch": 1.8505747126436782, "percentage": 61.69, "elapsed_time": "11:46:31", "remaining_time": "7:18:50"}
+{"current_steps": 162, "total_steps": 261, "loss": 0.6629, "lr": 7.73740997570278e-05, "epoch": 1.8620689655172413, "percentage": 62.07, "elapsed_time": "11:49:52", "remaining_time": "7:13:48"}
+{"current_steps": 163, "total_steps": 261, "loss": 0.6391, "lr": 7.606843357124426e-05, "epoch": 1.8735632183908046, "percentage": 62.45, "elapsed_time": "11:53:11", "remaining_time": "7:08:47"}
+{"current_steps": 164, "total_steps": 261, "loss": 0.6516, "lr": 7.476708091357782e-05, "epoch": 1.8850574712643677, "percentage": 62.84, "elapsed_time": "11:56:31", "remaining_time": "7:03:47"}
+{"current_steps": 165, "total_steps": 261, "loss": 0.6624, "lr": 7.347027634540993e-05, "epoch": 1.896551724137931, "percentage": 63.22, "elapsed_time": "11:59:53", "remaining_time": "6:58:50"}
+{"current_steps": 166, "total_steps": 261, "loss": 0.6574, "lr": 7.217825360835473e-05, "epoch": 1.9080459770114944, "percentage": 63.6, "elapsed_time": "12:03:14", "remaining_time": "6:53:54"}
+{"current_steps": 167, "total_steps": 261, "loss": 0.6668, "lr": 7.089124558212871e-05, "epoch": 1.9195402298850575, "percentage": 63.98, "elapsed_time": "12:06:34", "remaining_time": "6:48:58"}
+{"current_steps": 168, "total_steps": 261, "loss": 0.6358, "lr": 6.960948424257532e-05, "epoch": 1.9310344827586206, "percentage": 64.37, "elapsed_time": "12:09:54", "remaining_time": "6:44:03"}
+{"current_steps": 169, "total_steps": 261, "loss": 0.6294, "lr": 6.833320061985277e-05, "epoch": 1.9425287356321839, "percentage": 64.75, "elapsed_time": "12:13:17", "remaining_time": "6:39:11"}
+{"current_steps": 170, "total_steps": 261, "loss": 0.6781, "lr": 6.706262475679205e-05, "epoch": 1.9540229885057472, "percentage": 65.13, "elapsed_time": "12:16:36", "remaining_time": "6:34:18"}
+{"current_steps": 170, "total_steps": 261, "eval_loss": 0.6586677432060242, "epoch": 1.9540229885057472, "percentage": 65.13, "elapsed_time": "12:26:27", "remaining_time": "6:39:34"}
+{"current_steps": 171, "total_steps": 261, "loss": 0.6679, "lr": 6.579798566743314e-05, "epoch": 1.9655172413793105, "percentage": 65.52, "elapsed_time": "12:29:45", "remaining_time": "6:34:36"}
+{"current_steps": 172, "total_steps": 261, "loss": 0.6805, "lr": 6.453951129574644e-05, "epoch": 1.9770114942528736, "percentage": 65.9, "elapsed_time": "12:33:04", "remaining_time": "6:29:40"}
+{"current_steps": 173, "total_steps": 261, "loss": 0.6606, "lr": 6.328742847454724e-05, "epoch": 1.9885057471264367, "percentage": 66.28, "elapsed_time": "12:36:24", "remaining_time": "6:24:45"}
+{"current_steps": 174, "total_steps": 261, "loss": 0.6962, "lr": 6.204196288461037e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "12:39:41", "remaining_time": "6:19:50"}
+{"current_steps": 175, "total_steps": 261, "loss": 0.6426, "lr": 6.080333901399251e-05, "epoch": 2.0114942528735633, "percentage": 67.05, "elapsed_time": "12:43:00", "remaining_time": "6:14:57"}
+{"current_steps": 176, "total_steps": 261, "loss": 0.6418, "lr": 5.957178011756952e-05, "epoch": 2.0229885057471266, "percentage": 67.43, "elapsed_time": "12:46:17", "remaining_time": "6:10:05"}
+{"current_steps": 177, "total_steps": 261, "loss": 0.6406, "lr": 5.834750817679606e-05, "epoch": 2.0344827586206895, "percentage": 67.82, "elapsed_time": "12:49:36", "remaining_time": "6:05:14"}
+{"current_steps": 178, "total_steps": 261, "loss": 0.6262, "lr": 5.713074385969457e-05, "epoch": 2.045977011494253, "percentage": 68.2, "elapsed_time": "12:52:55", "remaining_time": "6:00:24"}
+{"current_steps": 179, "total_steps": 261, "loss": 0.6385, "lr": 5.59217064810814e-05, "epoch": 2.057471264367816, "percentage": 68.58, "elapsed_time": "12:56:15", "remaining_time": "5:55:36"}
+{"current_steps": 180, "total_steps": 261, "loss": 0.618, "lr": 5.472061396303629e-05, "epoch": 2.0689655172413794, "percentage": 68.97, "elapsed_time": "12:59:36", "remaining_time": "5:50:49"}
+{"current_steps": 180, "total_steps": 261, "eval_loss": 0.6581570506095886, "epoch": 2.0689655172413794, "percentage": 68.97, "elapsed_time": "13:09:29", "remaining_time": "5:55:16"}
+{"current_steps": 181, "total_steps": 261, "loss": 0.6354, "lr": 5.3527682795623146e-05, "epoch": 2.0804597701149423, "percentage": 69.35, "elapsed_time": "13:12:49", "remaining_time": "5:50:25"}
+{"current_steps": 182, "total_steps": 261, "loss": 0.631, "lr": 5.234312799786921e-05, "epoch": 2.0919540229885056, "percentage": 69.73, "elapsed_time": "13:16:10", "remaining_time": "5:45:35"}
+{"current_steps": 183, "total_steps": 261, "loss": 0.631, "lr": 5.116716307900893e-05, "epoch": 2.103448275862069, "percentage": 70.11, "elapsed_time": "13:19:30", "remaining_time": "5:40:46"}
+{"current_steps": 184, "total_steps": 261, "loss": 0.6691, "lr": 5.000000000000002e-05, "epoch": 2.1149425287356323, "percentage": 70.5, "elapsed_time": "13:22:48", "remaining_time": "5:35:57"}
+{"current_steps": 185, "total_steps": 261, "loss": 0.6147, "lr": 4.884184913531902e-05, "epoch": 2.1264367816091956, "percentage": 70.88, "elapsed_time": "13:26:08", "remaining_time": "5:31:10"}
+{"current_steps": 186, "total_steps": 261, "loss": 0.6259, "lr": 4.7692919235042255e-05, "epoch": 2.1379310344827585, "percentage": 71.26, "elapsed_time": "13:29:27", "remaining_time": "5:26:23"}
+{"current_steps": 187, "total_steps": 261, "loss": 0.6375, "lr": 4.6553417387219886e-05, "epoch": 2.1494252873563218, "percentage": 71.65, "elapsed_time": "13:32:44", "remaining_time": "5:21:37"}
+{"current_steps": 188, "total_steps": 261, "loss": 0.6329, "lr": 4.542354898054953e-05, "epoch": 2.160919540229885, "percentage": 72.03, "elapsed_time": "13:36:02", "remaining_time": "5:16:51"}
+{"current_steps": 189, "total_steps": 261, "loss": 0.6379, "lr": 4.430351766735609e-05, "epoch": 2.1724137931034484, "percentage": 72.41, "elapsed_time": "13:39:21", "remaining_time": "5:12:08"}
+{"current_steps": 190, "total_steps": 261, "loss": 0.6575, "lr": 4.3193525326884435e-05, "epoch": 2.1839080459770113, "percentage": 72.8, "elapsed_time": "13:42:39", "remaining_time": "5:07:24"}
+{"current_steps": 190, "total_steps": 261, "eval_loss": 0.657158374786377, "epoch": 2.1839080459770113, "percentage": 72.8, "elapsed_time": "13:52:30", "remaining_time": "5:11:05"}
+{"current_steps": 191, "total_steps": 261, "loss": 0.643, "lr": 4.209377202891212e-05, "epoch": 2.1954022988505746, "percentage": 73.18, "elapsed_time": "13:55:51", "remaining_time": "5:06:20"}
+{"current_steps": 192, "total_steps": 261, "loss": 0.6349, "lr": 4.100445599768774e-05, "epoch": 2.206896551724138, "percentage": 73.56, "elapsed_time": "13:59:10", "remaining_time": "5:01:34"}
+{"current_steps": 193, "total_steps": 261, "loss": 0.6404, "lr": 3.99257735762021e-05, "epoch": 2.218390804597701, "percentage": 73.95, "elapsed_time": "14:02:30", "remaining_time": "4:56:50"}
+{"current_steps": 194, "total_steps": 261, "loss": 0.6615, "lr": 3.885791919079878e-05, "epoch": 2.2298850574712645, "percentage": 74.33, "elapsed_time": "14:05:50", "remaining_time": "4:52:07"}
+{"current_steps": 195, "total_steps": 261, "loss": 0.6237, "lr": 3.7801085316129615e-05, "epoch": 2.2413793103448274, "percentage": 74.71, "elapsed_time": "14:09:09", "remaining_time": "4:47:24"}
+{"current_steps": 196, "total_steps": 261, "loss": 0.6482, "lr": 3.675546244046228e-05, "epoch": 2.2528735632183907, "percentage": 75.1, "elapsed_time": "14:12:26", "remaining_time": "4:42:41"}
+{"current_steps": 197, "total_steps": 261, "loss": 0.6101, "lr": 3.5721239031346066e-05, "epoch": 2.264367816091954, "percentage": 75.48, "elapsed_time": "14:15:45", "remaining_time": "4:38:00"}
+{"current_steps": 198, "total_steps": 261, "loss": 0.6499, "lr": 3.469860150164152e-05, "epoch": 2.2758620689655173, "percentage": 75.86, "elapsed_time": "14:19:05", "remaining_time": "4:33:20"}
+{"current_steps": 199, "total_steps": 261, "loss": 0.629, "lr": 3.36877341759205e-05, "epoch": 2.2873563218390807, "percentage": 76.25, "elapsed_time": "14:22:23", "remaining_time": "4:28:40"}
+{"current_steps": 200, "total_steps": 261, "loss": 0.6372, "lr": 3.268881925724297e-05, "epoch": 2.2988505747126435, "percentage": 76.63, "elapsed_time": "14:25:41", "remaining_time": "4:24:02"}
+{"current_steps": 200, "total_steps": 261, "eval_loss": 0.6563421487808228, "epoch": 2.2988505747126435, "percentage": 76.63, "elapsed_time": "14:35:32", "remaining_time": "4:27:02"}
+{"current_steps": 201, "total_steps": 261, "loss": 0.6417, "lr": 3.170203679431584e-05, "epoch": 2.310344827586207, "percentage": 77.01, "elapsed_time": "14:39:11", "remaining_time": "4:22:26"}
+{"current_steps": 202, "total_steps": 261, "loss": 0.6434, "lr": 3.072756464904006e-05, "epoch": 2.32183908045977, "percentage": 77.39, "elapsed_time": "14:42:35", "remaining_time": "4:17:47"}
+{"current_steps": 203, "total_steps": 261, "loss": 0.643, "lr": 2.976557846445225e-05, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "14:45:55", "remaining_time": "4:13:07"}
+{"current_steps": 204, "total_steps": 261, "loss": 0.6374, "lr": 2.881625163306596e-05, "epoch": 2.344827586206897, "percentage": 78.16, "elapsed_time": "14:49:14", "remaining_time": "4:08:27"}
+{"current_steps": 205, "total_steps": 261, "loss": 0.6418, "lr": 2.7879755265618555e-05, "epoch": 2.3563218390804597, "percentage": 78.54, "elapsed_time": "14:52:34", "remaining_time": "4:03:49"}
+{"current_steps": 206, "total_steps": 261, "loss": 0.632, "lr": 2.6956258160229695e-05, "epoch": 2.367816091954023, "percentage": 78.93, "elapsed_time": "14:55:52", "remaining_time": "3:59:11"}
+{"current_steps": 207, "total_steps": 261, "loss": 0.6538, "lr": 2.6045926771976303e-05, "epoch": 2.3793103448275863, "percentage": 79.31, "elapsed_time": "14:59:08", "remaining_time": "3:54:33"}
+{"current_steps": 208, "total_steps": 261, "loss": 0.6145, "lr": 2.514892518288988e-05, "epoch": 2.3908045977011496, "percentage": 79.69, "elapsed_time": "15:02:26", "remaining_time": "3:49:56"}
+{"current_steps": 209, "total_steps": 261, "loss": 0.6222, "lr": 2.4265415072382016e-05, "epoch": 2.4022988505747125, "percentage": 80.08, "elapsed_time": "15:05:46", "remaining_time": "3:45:21"}
+{"current_steps": 210, "total_steps": 261, "loss": 0.617, "lr": 2.339555568810221e-05, "epoch": 2.413793103448276, "percentage": 80.46, "elapsed_time": "15:09:08", "remaining_time": "3:40:47"}
+{"current_steps": 210, "total_steps": 261, "eval_loss": 0.6558452248573303, "epoch": 2.413793103448276, "percentage": 80.46, "elapsed_time": "15:19:03", "remaining_time": "3:43:11"}
+{"current_steps": 211, "total_steps": 261, "loss": 0.654, "lr": 2.2539503817234553e-05, "epoch": 2.425287356321839, "percentage": 80.84, "elapsed_time": "15:22:21", "remaining_time": "3:38:34"}
+{"current_steps": 212, "total_steps": 261, "loss": 0.6322, "lr": 2.1697413758237784e-05, "epoch": 2.4367816091954024, "percentage": 81.23, "elapsed_time": "15:25:39", "remaining_time": "3:33:56"}
+{"current_steps": 213, "total_steps": 261, "loss": 0.6335, "lr": 2.0869437293033835e-05, "epoch": 2.4482758620689653, "percentage": 81.61, "elapsed_time": "15:28:58", "remaining_time": "3:29:20"}
+{"current_steps": 214, "total_steps": 261, "loss": 0.6184, "lr": 2.0055723659649904e-05, "epoch": 2.4597701149425286, "percentage": 81.99, "elapsed_time": "15:32:15", "remaining_time": "3:24:44"}
+{"current_steps": 215, "total_steps": 261, "loss": 0.627, "lr": 1.9256419525319313e-05, "epoch": 2.471264367816092, "percentage": 82.38, "elapsed_time": "15:35:33", "remaining_time": "3:20:09"}
+{"current_steps": 216, "total_steps": 261, "loss": 0.6487, "lr": 1.8471668960045574e-05, "epoch": 2.4827586206896552, "percentage": 82.76, "elapsed_time": "15:38:50", "remaining_time": "3:15:35"}
+{"current_steps": 217, "total_steps": 261, "loss": 0.6337, "lr": 1.7701613410634365e-05, "epoch": 2.4942528735632186, "percentage": 83.14, "elapsed_time": "15:42:07", "remaining_time": "3:11:01"}
+{"current_steps": 218, "total_steps": 261, "loss": 0.6356, "lr": 1.6946391675198836e-05, "epoch": 2.5057471264367814, "percentage": 83.52, "elapsed_time": "15:45:27", "remaining_time": "3:06:29"}
+{"current_steps": 219, "total_steps": 261, "loss": 0.6237, "lr": 1.620613987814189e-05, "epoch": 2.5172413793103448, "percentage": 83.91, "elapsed_time": "15:48:45", "remaining_time": "3:01:57"}
+{"current_steps": 220, "total_steps": 261, "loss": 0.6152, "lr": 1.5480991445620542e-05, "epoch": 2.528735632183908, "percentage": 84.29, "elapsed_time": "15:52:04", "remaining_time": "2:57:25"}
+{"current_steps": 220, "total_steps": 261, "eval_loss": 0.655238926410675, "epoch": 2.528735632183908, "percentage": 84.29, "elapsed_time": "16:01:57", "remaining_time": "2:59:16"}
+{"current_steps": 221, "total_steps": 261, "loss": 0.6511, "lr": 1.4771077081496654e-05, "epoch": 2.5402298850574714, "percentage": 84.67, "elapsed_time": "16:05:15", "remaining_time": "2:54:42"}
+{"current_steps": 222, "total_steps": 261, "loss": 0.6311, "lr": 1.4076524743778319e-05, "epoch": 2.5517241379310347, "percentage": 85.06, "elapsed_time": "16:08:35", "remaining_time": "2:50:09"}
+{"current_steps": 223, "total_steps": 261, "loss": 0.6324, "lr": 1.339745962155613e-05, "epoch": 2.5632183908045976, "percentage": 85.44, "elapsed_time": "16:11:54", "remaining_time": "2:45:37"}
+{"current_steps": 224, "total_steps": 261, "loss": 0.6568, "lr": 1.2734004112438568e-05, "epoch": 2.574712643678161, "percentage": 85.82, "elapsed_time": "16:15:14", "remaining_time": "2:41:05"}
+{"current_steps": 225, "total_steps": 261, "loss": 0.649, "lr": 1.2086277800490554e-05, "epoch": 2.586206896551724, "percentage": 86.21, "elapsed_time": "16:18:31", "remaining_time": "2:36:33"}
+{"current_steps": 226, "total_steps": 261, "loss": 0.6603, "lr": 1.1454397434679021e-05, "epoch": 2.5977011494252875, "percentage": 86.59, "elapsed_time": "16:21:49", "remaining_time": "2:32:03"}
+{"current_steps": 227, "total_steps": 261, "loss": 0.6295, "lr": 1.083847690782972e-05, "epoch": 2.609195402298851, "percentage": 86.97, "elapsed_time": "16:25:09", "remaining_time": "2:27:33"}
+{"current_steps": 228, "total_steps": 261, "loss": 0.6209, "lr": 1.0238627236098619e-05, "epoch": 2.6206896551724137, "percentage": 87.36, "elapsed_time": "16:28:28", "remaining_time": "2:23:04"}
+{"current_steps": 229, "total_steps": 261, "loss": 0.6339, "lr": 9.65495653896179e-06, "epoch": 2.632183908045977, "percentage": 87.74, "elapsed_time": "16:31:47", "remaining_time": "2:18:35"}
+{"current_steps": 230, "total_steps": 261, "loss": 0.6407, "lr": 9.08757001972762e-06, "epoch": 2.6436781609195403, "percentage": 88.12, "elapsed_time": "16:35:06", "remaining_time": "2:14:07"}
+{"current_steps": 230, "total_steps": 261, "eval_loss": 0.6549434065818787, "epoch": 2.6436781609195403, "percentage": 88.12, "elapsed_time": "16:44:59", "remaining_time": "2:15:27"}
+{"current_steps": 231, "total_steps": 261, "loss": 0.6534, "lr": 8.536569946574546e-06, "epoch": 2.655172413793103, "percentage": 88.51, "elapsed_time": "16:48:18", "remaining_time": "2:10:56"}
+{"current_steps": 232, "total_steps": 261, "loss": 0.6507, "lr": 8.002055634117578e-06, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "16:51:37", "remaining_time": "2:06:27"}
+{"current_steps": 233, "total_steps": 261, "loss": 0.6282, "lr": 7.4841234255076495e-06, "epoch": 2.67816091954023, "percentage": 89.27, "elapsed_time": "16:54:57", "remaining_time": "2:01:58"}
+{"current_steps": 234, "total_steps": 261, "loss": 0.6276, "lr": 6.9828666750661795e-06, "epoch": 2.689655172413793, "percentage": 89.66, "elapsed_time": "16:58:16", "remaining_time": "1:57:29"}
+{"current_steps": 235, "total_steps": 261, "loss": 0.639, "lr": 6.498375731458528e-06, "epoch": 2.7011494252873565, "percentage": 90.04, "elapsed_time": "17:01:33", "remaining_time": "1:53:01"}
+{"current_steps": 236, "total_steps": 261, "loss": 0.6425, "lr": 6.030737921409169e-06, "epoch": 2.7126436781609193, "percentage": 90.42, "elapsed_time": "17:04:50", "remaining_time": "1:48:33"}
+{"current_steps": 237, "total_steps": 261, "loss": 0.6438, "lr": 5.580037533961546e-06, "epoch": 2.7241379310344827, "percentage": 90.8, "elapsed_time": "17:08:08", "remaining_time": "1:44:06"}
+{"current_steps": 238, "total_steps": 261, "loss": 0.6275, "lr": 5.146355805285452e-06, "epoch": 2.735632183908046, "percentage": 91.19, "elapsed_time": "17:11:25", "remaining_time": "1:39:40"}
+{"current_steps": 239, "total_steps": 261, "loss": 0.6357, "lr": 4.729770904034647e-06, "epoch": 2.7471264367816093, "percentage": 91.57, "elapsed_time": "17:14:42", "remaining_time": "1:35:14"}
+{"current_steps": 240, "total_steps": 261, "loss": 0.6498, "lr": 4.3303579172574885e-06, "epoch": 2.7586206896551726, "percentage": 91.95, "elapsed_time": "17:18:02", "remaining_time": "1:30:49"}
+{"current_steps": 240, "total_steps": 261, "eval_loss": 0.6547917723655701, "epoch": 2.7586206896551726, "percentage": 91.95, "elapsed_time": "17:27:55", "remaining_time": "1:31:41"}
+{"current_steps": 241, "total_steps": 261, "loss": 0.63, "lr": 3.948188836862776e-06, "epoch": 2.7701149425287355, "percentage": 92.34, "elapsed_time": "17:31:13", "remaining_time": "1:27:14"}
+{"current_steps": 242, "total_steps": 261, "loss": 0.6267, "lr": 3.5833325466437694e-06, "epoch": 2.781609195402299, "percentage": 92.72, "elapsed_time": "17:34:31", "remaining_time": "1:22:47"}
+{"current_steps": 243, "total_steps": 261, "loss": 0.6297, "lr": 3.2358548098621932e-06, "epoch": 2.793103448275862, "percentage": 93.1, "elapsed_time": "17:37:52", "remaining_time": "1:18:21"}
+{"current_steps": 244, "total_steps": 261, "loss": 0.6289, "lr": 2.905818257394799e-06, "epoch": 2.8045977011494254, "percentage": 93.49, "elapsed_time": "17:41:09", "remaining_time": "1:13:56"}
+{"current_steps": 245, "total_steps": 261, "loss": 0.6274, "lr": 2.5932823764445392e-06, "epoch": 2.8160919540229887, "percentage": 93.87, "elapsed_time": "17:44:27", "remaining_time": "1:09:30"}
+{"current_steps": 246, "total_steps": 261, "loss": 0.6205, "lr": 2.2983034998182997e-06, "epoch": 2.8275862068965516, "percentage": 94.25, "elapsed_time": "17:47:46", "remaining_time": "1:05:06"}
+{"current_steps": 247, "total_steps": 261, "loss": 0.6585, "lr": 2.0209347957732328e-06, "epoch": 2.839080459770115, "percentage": 94.64, "elapsed_time": "17:51:04", "remaining_time": "1:00:42"}
+{"current_steps": 248, "total_steps": 261, "loss": 0.6215, "lr": 1.7612262584335237e-06, "epoch": 2.8505747126436782, "percentage": 95.02, "elapsed_time": "17:54:25", "remaining_time": "0:56:19"}
+{"current_steps": 249, "total_steps": 261, "loss": 0.6454, "lr": 1.5192246987791981e-06, "epoch": 2.862068965517241, "percentage": 95.4, "elapsed_time": "17:57:47", "remaining_time": "0:51:56"}
+{"current_steps": 250, "total_steps": 261, "loss": 0.6365, "lr": 1.2949737362087156e-06, "epoch": 2.873563218390805, "percentage": 95.79, "elapsed_time": "18:01:06", "remaining_time": "0:47:34"}
+{"current_steps": 250, "total_steps": 261, "eval_loss": 0.6547266840934753, "epoch": 2.873563218390805, "percentage": 95.79, "elapsed_time": "18:11:00", "remaining_time": "0:48:00"}
+{"current_steps": 251, "total_steps": 261, "loss": 0.628, "lr": 1.0885137906768372e-06, "epoch": 2.8850574712643677, "percentage": 96.17, "elapsed_time": "18:14:39", "remaining_time": "0:43:36"}
+{"current_steps": 252, "total_steps": 261, "loss": 0.6447, "lr": 8.998820754091531e-07, "epoch": 2.896551724137931, "percentage": 96.55, "elapsed_time": "18:17:58", "remaining_time": "0:39:12"}
+{"current_steps": 253, "total_steps": 261, "loss": 0.6615, "lr": 7.291125901946027e-07, "epoch": 2.9080459770114944, "percentage": 96.93, "elapsed_time": "18:21:17", "remaining_time": "0:34:49"}
+{"current_steps": 254, "total_steps": 261, "loss": 0.6382, "lr": 5.762361152572115e-07, "epoch": 2.9195402298850572, "percentage": 97.32, "elapsed_time": "18:24:36", "remaining_time": "0:30:26"}
+{"current_steps": 255, "total_steps": 261, "loss": 0.6339, "lr": 4.412802057081278e-07, "epoch": 2.9310344827586206, "percentage": 97.7, "elapsed_time": "18:27:54", "remaining_time": "0:26:04"}
+{"current_steps": 256, "total_steps": 261, "loss": 0.6557, "lr": 3.2426918657900704e-07, "epoch": 2.942528735632184, "percentage": 98.08, "elapsed_time": "18:31:14", "remaining_time": "0:21:42"}
+{"current_steps": 257, "total_steps": 261, "loss": 0.6419, "lr": 2.2522414843748618e-07, "epoch": 2.954022988505747, "percentage": 98.47, "elapsed_time": "18:34:32", "remaining_time": "0:17:20"}
+{"current_steps": 258, "total_steps": 261, "loss": 0.6224, "lr": 1.4416294358582384e-07, "epoch": 2.9655172413793105, "percentage": 98.85, "elapsed_time": "18:37:53", "remaining_time": "0:12:59"}
+{"current_steps": 259, "total_steps": 261, "loss": 0.6472, "lr": 8.110018284304133e-08, "epoch": 2.9770114942528734, "percentage": 99.23, "elapsed_time": "18:41:13", "remaining_time": "0:08:39"}
+{"current_steps": 260, "total_steps": 261, "loss": 0.6532, "lr": 3.60472329114625e-08, "epoch": 2.9885057471264367, "percentage": 99.62, "elapsed_time": "18:44:33", "remaining_time": "0:04:19"}
+{"current_steps": 260, "total_steps": 261, "eval_loss": 0.6546847820281982, "epoch": 2.9885057471264367, "percentage": 99.62, "elapsed_time": "18:54:24", "remaining_time": "0:04:21"}
+{"current_steps": 261, "total_steps": 261, "loss": 0.6416, "lr": 9.012214327897006e-09, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "18:57:44", "remaining_time": "0:00:00"}
+{"current_steps": 261, "total_steps": 261, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "18:58:04", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2078 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 261,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011494252873563218,
+      "grad_norm": 0.45773613452911377,
+      "learning_rate": 0.0,
+      "loss": 1.065,
+      "step": 1
+    },
+    {
+      "epoch": 0.022988505747126436,
+      "grad_norm": 0.4720604717731476,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.1025,
+      "step": 2
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.4526257812976837,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 1.067,
+      "step": 3
+    },
+    {
+      "epoch": 0.04597701149425287,
+      "grad_norm": 0.44910383224487305,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 1.0694,
+      "step": 4
+    },
+    {
+      "epoch": 0.05747126436781609,
+      "grad_norm": 0.4383523762226105,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 1.0767,
+      "step": 5
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.4290314018726349,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 1.0414,
+      "step": 6
+    },
+    {
+      "epoch": 0.08045977011494253,
+      "grad_norm": 0.4098808467388153,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.021,
+      "step": 7
+    },
+    {
+      "epoch": 0.09195402298850575,
+      "grad_norm": 0.4100661277770996,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 1.0113,
+      "step": 8
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 0.37694185972213745,
+      "learning_rate": 5.925925925925926e-05,
+      "loss": 0.9566,
+      "step": 9
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "grad_norm": 0.3378658890724182,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.9539,
+      "step": 10
+    },
+    {
+      "epoch": 0.11494252873563218,
+      "eval_loss": 0.9960598945617676,
+      "eval_runtime": 605.6954,
+      "eval_samples_per_second": 16.342,
+      "eval_steps_per_second": 0.129,
+      "step": 10
+    },
+    {
+      "epoch": 0.12643678160919541,
+      "grad_norm": 0.29339659214019775,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.9163,
+      "step": 11
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.23120510578155518,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.8886,
+      "step": 12
+    },
+    {
+      "epoch": 0.14942528735632185,
+      "grad_norm": 0.18651129305362701,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.8748,
+      "step": 13
+    },
+    {
+      "epoch": 0.16091954022988506,
+      "grad_norm": 0.14475475251674652,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.8235,
+      "step": 14
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.11758769303560257,
+      "learning_rate": 0.0001037037037037037,
+      "loss": 0.8539,
+      "step": 15
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 0.10646044462919235,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.8363,
+      "step": 16
+    },
+    {
+      "epoch": 0.19540229885057472,
+      "grad_norm": 0.10539838671684265,
+      "learning_rate": 0.00011851851851851852,
+      "loss": 0.819,
+      "step": 17
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.11887332051992416,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 0.8069,
+      "step": 18
+    },
+    {
+      "epoch": 0.21839080459770116,
+      "grad_norm": 0.1281956136226654,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.8042,
+      "step": 19
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "grad_norm": 0.1338774859905243,
+      "learning_rate": 0.00014074074074074076,
+      "loss": 0.8283,
+      "step": 20
+    },
+    {
+      "epoch": 0.22988505747126436,
+      "eval_loss": 0.813089907169342,
+      "eval_runtime": 601.317,
+      "eval_samples_per_second": 16.461,
+      "eval_steps_per_second": 0.13,
+      "step": 20
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 0.12568038702011108,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.8142,
+      "step": 21
+    },
+    {
+      "epoch": 0.25287356321839083,
+      "grad_norm": 0.11528006941080093,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.794,
+      "step": 22
+    },
+    {
+      "epoch": 0.26436781609195403,
+      "grad_norm": 0.10474701225757599,
+      "learning_rate": 0.00016296296296296295,
+      "loss": 0.8231,
+      "step": 23
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.09240291267633438,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.7874,
+      "step": 24
+    },
+    {
+      "epoch": 0.28735632183908044,
+      "grad_norm": 0.07213829457759857,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.8075,
+      "step": 25
+    },
+    {
+      "epoch": 0.2988505747126437,
+      "grad_norm": 0.0564056895673275,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 0.779,
+      "step": 26
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 0.04973220080137253,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 0.7878,
+      "step": 27
+    },
+    {
+      "epoch": 0.3218390804597701,
+      "grad_norm": 0.04492342844605446,
+      "learning_rate": 0.0002,
+      "loss": 0.7876,
+      "step": 28
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.050321951508522034,
+      "learning_rate": 0.00019999098778567212,
+      "loss": 0.7686,
+      "step": 29
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.05602027848362923,
+      "learning_rate": 0.00019996395276708856,
+      "loss": 0.7525,
+      "step": 30
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "eval_loss": 0.7719228863716125,
+      "eval_runtime": 606.7346,
+      "eval_samples_per_second": 16.314,
+      "eval_steps_per_second": 0.129,
+      "step": 30
+    },
+    {
+      "epoch": 0.3563218390804598,
+      "grad_norm": 0.055378761142492294,
+      "learning_rate": 0.00019991889981715698,
+      "loss": 0.777,
+      "step": 31
+    },
+    {
+      "epoch": 0.367816091954023,
+      "grad_norm": 0.052891045808792114,
+      "learning_rate": 0.00019985583705641418,
+      "loss": 0.7797,
+      "step": 32
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 0.044340070337057114,
+      "learning_rate": 0.00019977477585156252,
+      "loss": 0.7744,
+      "step": 33
+    },
+    {
+      "epoch": 0.39080459770114945,
+      "grad_norm": 0.037772953510284424,
+      "learning_rate": 0.00019967573081342103,
+      "loss": 0.7631,
+      "step": 34
+    },
+    {
+      "epoch": 0.40229885057471265,
+      "grad_norm": 0.03553105518221855,
+      "learning_rate": 0.0001995587197942919,
+      "loss": 0.7512,
+      "step": 35
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.0346490740776062,
+      "learning_rate": 0.0001994237638847428,
+      "loss": 0.7567,
+      "step": 36
+    },
+    {
+      "epoch": 0.42528735632183906,
+      "grad_norm": 0.03471450135111809,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 0.7723,
+      "step": 37
+    },
+    {
+      "epoch": 0.4367816091954023,
+      "grad_norm": 0.03868038207292557,
+      "learning_rate": 0.00019910011792459087,
+      "loss": 0.77,
+      "step": 38
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 0.04141271859407425,
+      "learning_rate": 0.00019891148620932318,
+      "loss": 0.7764,
+      "step": 39
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "grad_norm": 0.04017995670437813,
+      "learning_rate": 0.00019870502626379127,
+      "loss": 0.7418,
+      "step": 40
+    },
+    {
+      "epoch": 0.45977011494252873,
+      "eval_loss": 0.7480100393295288,
+      "eval_runtime": 601.4446,
+      "eval_samples_per_second": 16.457,
+      "eval_steps_per_second": 0.13,
+      "step": 40
+    },
+    {
+      "epoch": 0.47126436781609193,
+      "grad_norm": 0.04055652394890785,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.7487,
+      "step": 41
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.03968408331274986,
+      "learning_rate": 0.00019823877374156647,
+      "loss": 0.7417,
+      "step": 42
+    },
+    {
+      "epoch": 0.4942528735632184,
+      "grad_norm": 0.03533465415239334,
+      "learning_rate": 0.00019797906520422677,
+      "loss": 0.7437,
+      "step": 43
+    },
+    {
+      "epoch": 0.5057471264367817,
+      "grad_norm": 0.03385720029473305,
+      "learning_rate": 0.00019770169650018172,
+      "loss": 0.7752,
+      "step": 44
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.030534420162439346,
+      "learning_rate": 0.00019740671762355548,
+      "loss": 0.7363,
+      "step": 45
+    },
+    {
+      "epoch": 0.5287356321839081,
+      "grad_norm": 0.02837216667830944,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 0.74,
+      "step": 46
+    },
+    {
+      "epoch": 0.5402298850574713,
+      "grad_norm": 0.02879689820110798,
+      "learning_rate": 0.00019676414519013781,
+      "loss": 0.7246,
+      "step": 47
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.02807699516415596,
+      "learning_rate": 0.00019641666745335624,
+      "loss": 0.7465,
+      "step": 48
+    },
+    {
+      "epoch": 0.5632183908045977,
+      "grad_norm": 0.029897579923272133,
+      "learning_rate": 0.00019605181116313724,
+      "loss": 0.721,
+      "step": 49
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "grad_norm": 0.028458919376134872,
+      "learning_rate": 0.00019566964208274254,
+      "loss": 0.7291,
+      "step": 50
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "eval_loss": 0.7319945096969604,
+      "eval_runtime": 601.7402,
+      "eval_samples_per_second": 16.449,
+      "eval_steps_per_second": 0.13,
+      "step": 50
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.028347671031951904,
+      "learning_rate": 0.00019527022909596536,
+      "loss": 0.7396,
+      "step": 51
+    },
+    {
+      "epoch": 0.5977011494252874,
+      "grad_norm": 0.028352508321404457,
+      "learning_rate": 0.00019485364419471454,
+      "loss": 0.733,
+      "step": 52
+    },
+    {
+      "epoch": 0.6091954022988506,
+      "grad_norm": 0.025768019258975983,
+      "learning_rate": 0.00019441996246603846,
+      "loss": 0.7378,
+      "step": 53
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.0259398240596056,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.7293,
+      "step": 54
+    },
+    {
+      "epoch": 0.632183908045977,
+      "grad_norm": 0.024649152532219887,
+      "learning_rate": 0.0001935016242685415,
+      "loss": 0.7287,
+      "step": 55
+    },
+    {
+      "epoch": 0.6436781609195402,
+      "grad_norm": 0.026843328028917313,
+      "learning_rate": 0.00019301713332493386,
+      "loss": 0.7354,
+      "step": 56
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.028928296640515327,
+      "learning_rate": 0.00019251587657449236,
+      "loss": 0.7376,
+      "step": 57
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.027994588017463684,
+      "learning_rate": 0.00019199794436588243,
+      "loss": 0.7389,
+      "step": 58
+    },
+    {
+      "epoch": 0.6781609195402298,
+      "grad_norm": 0.027422698214650154,
+      "learning_rate": 0.00019146343005342547,
+      "loss": 0.7275,
+      "step": 59
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.02938409335911274,
+      "learning_rate": 0.0001909124299802724,
+      "loss": 0.7244,
+      "step": 60
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "eval_loss": 0.7189474701881409,
+      "eval_runtime": 605.038,
+      "eval_samples_per_second": 16.359,
+      "eval_steps_per_second": 0.129,
+      "step": 60
+    },
+    {
+      "epoch": 0.7011494252873564,
+      "grad_norm": 0.02854277938604355,
+      "learning_rate": 0.00019034504346103823,
+      "loss": 0.7339,
+      "step": 61
+    },
+    {
+      "epoch": 0.7126436781609196,
+      "grad_norm": 0.028162814676761627,
+      "learning_rate": 0.0001897613727639014,
+      "loss": 0.7349,
+      "step": 62
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.027026742696762085,
+      "learning_rate": 0.0001891615230921703,
+      "loss": 0.7008,
+      "step": 63
+    },
+    {
+      "epoch": 0.735632183908046,
+      "grad_norm": 0.02867995575070381,
+      "learning_rate": 0.000188545602565321,
+      "loss": 0.7404,
+      "step": 64
+    },
+    {
+      "epoch": 0.7471264367816092,
+      "grad_norm": 0.025570319965481758,
+      "learning_rate": 0.00018791372219950948,
+      "loss": 0.7203,
+      "step": 65
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.026673492044210434,
+      "learning_rate": 0.00018726599588756145,
+      "loss": 0.7188,
+      "step": 66
+    },
+    {
+      "epoch": 0.7701149425287356,
+      "grad_norm": 0.028060389682650566,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.7129,
+      "step": 67
+    },
+    {
+      "epoch": 0.7816091954022989,
+      "grad_norm": 0.025640789419412613,
+      "learning_rate": 0.0001859234752562217,
+      "loss": 0.7081,
+      "step": 68
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.026264475658535957,
+      "learning_rate": 0.00018522892291850335,
+      "loss": 0.6971,
+      "step": 69
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "grad_norm": 0.028900163248181343,
+      "learning_rate": 0.0001845190085543795,
+      "loss": 0.721,
+      "step": 70
+    },
+    {
+      "epoch": 0.8045977011494253,
+      "eval_loss": 0.7084506154060364,
+      "eval_runtime": 603.3937,
+      "eval_samples_per_second": 16.404,
+      "eval_steps_per_second": 0.129,
+      "step": 70
+    },
+    {
+      "epoch": 0.8160919540229885,
+      "grad_norm": 0.02878301776945591,
+      "learning_rate": 0.00018379386012185814,
+      "loss": 0.7192,
+      "step": 71
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.028177903965115547,
+      "learning_rate": 0.00018305360832480117,
+      "loss": 0.7258,
+      "step": 72
+    },
+    {
+      "epoch": 0.8390804597701149,
+      "grad_norm": 0.027689015492796898,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 0.7327,
+      "step": 73
+    },
+    {
+      "epoch": 0.8505747126436781,
+      "grad_norm": 0.027420515194535255,
+      "learning_rate": 0.00018152833103995443,
+      "loss": 0.7007,
+      "step": 74
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.02628767490386963,
+      "learning_rate": 0.0001807435804746807,
+      "loss": 0.7106,
+      "step": 75
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 0.027107784524559975,
+      "learning_rate": 0.00017994427634035015,
+      "loss": 0.7056,
+      "step": 76
+    },
+    {
+      "epoch": 0.8850574712643678,
+      "grad_norm": 0.026692209765315056,
+      "learning_rate": 0.0001791305627069662,
+      "loss": 0.6898,
+      "step": 77
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.02739943191409111,
+      "learning_rate": 0.00017830258624176225,
+      "loss": 0.71,
+      "step": 78
+    },
+    {
+      "epoch": 0.9080459770114943,
+      "grad_norm": 0.027159228920936584,
+      "learning_rate": 0.00017746049618276545,
+      "loss": 0.7104,
+      "step": 79
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 0.027961738407611847,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.6964,
+      "step": 80
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "eval_loss": 0.6998673677444458,
+      "eval_runtime": 599.046,
+      "eval_samples_per_second": 16.523,
+      "eval_steps_per_second": 0.13,
+      "step": 80
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.028458958491683006,
+      "learning_rate": 0.00017573458492761801,
+      "loss": 0.7048,
+      "step": 81
+    },
+    {
+      "epoch": 0.9425287356321839,
+      "grad_norm": 0.0295415036380291,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 0.7089,
+      "step": 82
+    },
+    {
+      "epoch": 0.9540229885057471,
+      "grad_norm": 0.027641592547297478,
+      "learning_rate": 0.00017395407322802372,
+      "loss": 0.7184,
+      "step": 83
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.029828142374753952,
+      "learning_rate": 0.00017304374183977033,
+      "loss": 0.6878,
+      "step": 84
+    },
+    {
+      "epoch": 0.9770114942528736,
+      "grad_norm": 0.029184194281697273,
+      "learning_rate": 0.00017212024473438147,
+      "loss": 0.7223,
+      "step": 85
+    },
+    {
+      "epoch": 0.9885057471264368,
+      "grad_norm": 0.02929309941828251,
+      "learning_rate": 0.00017118374836693406,
+      "loss": 0.6936,
+      "step": 86
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.03450490161776543,
+      "learning_rate": 0.00017023442153554777,
+      "loss": 0.6906,
+      "step": 87
+    },
+    {
+      "epoch": 1.0114942528735633,
+      "grad_norm": 0.03116275928914547,
+      "learning_rate": 0.00016927243535095997,
+      "loss": 0.6915,
+      "step": 88
+    },
+    {
+      "epoch": 1.0229885057471264,
+      "grad_norm": 0.03145065903663635,
+      "learning_rate": 0.00016829796320568416,
+      "loss": 0.6792,
+      "step": 89
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.03122427873313427,
+      "learning_rate": 0.00016731118074275704,
+      "loss": 0.6965,
+      "step": 90
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "eval_loss": 0.6928127408027649,
+      "eval_runtime": 606.6499,
+      "eval_samples_per_second": 16.316,
+      "eval_steps_per_second": 0.129,
+      "step": 90
+    },
+    {
+      "epoch": 1.0459770114942528,
+      "grad_norm": 0.030179064720869064,
+      "learning_rate": 0.00016631226582407952,
+      "loss": 0.6726,
+      "step": 91
+    },
+    {
+      "epoch": 1.0574712643678161,
+      "grad_norm": 0.029219962656497955,
+      "learning_rate": 0.0001653013984983585,
+      "loss": 0.6792,
+      "step": 92
+    },
+    {
+      "epoch": 1.0689655172413792,
+      "grad_norm": 0.02873355709016323,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.6921,
+      "step": 93
+    },
+    {
+      "epoch": 1.0804597701149425,
+      "grad_norm": 0.029455283656716347,
+      "learning_rate": 0.00016324453755953773,
+      "loss": 0.6829,
+      "step": 94
+    },
+    {
+      "epoch": 1.0919540229885056,
+      "grad_norm": 0.030247965827584267,
+      "learning_rate": 0.0001621989146838704,
+      "loss": 0.6737,
+      "step": 95
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.029829107224941254,
+      "learning_rate": 0.00016114208080920123,
+      "loss": 0.6852,
+      "step": 96
+    },
+    {
+      "epoch": 1.1149425287356323,
+      "grad_norm": 0.031125420704483986,
+      "learning_rate": 0.0001600742264237979,
+      "loss": 0.6863,
+      "step": 97
+    },
+    {
+      "epoch": 1.1264367816091954,
+      "grad_norm": 0.029601775109767914,
+      "learning_rate": 0.00015899554400231232,
+      "loss": 0.6785,
+      "step": 98
+    },
+    {
+      "epoch": 1.1379310344827587,
+      "grad_norm": 0.031090950593352318,
+      "learning_rate": 0.0001579062279710879,
+      "loss": 0.7001,
+      "step": 99
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 0.030084125697612762,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 0.6856,
+      "step": 100
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "eval_loss": 0.686887264251709,
+      "eval_runtime": 599.4005,
+      "eval_samples_per_second": 16.513,
+      "eval_steps_per_second": 0.13,
+      "step": 100
+    },
+    {
+      "epoch": 1.160919540229885,
+      "grad_norm": 0.03157448023557663,
+      "learning_rate": 0.00015569648233264394,
+      "loss": 0.6836,
+      "step": 101
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.032123371958732605,
+      "learning_rate": 0.00015457645101945046,
+      "loss": 0.6827,
+      "step": 102
+    },
+    {
+      "epoch": 1.1839080459770115,
+      "grad_norm": 0.03208347037434578,
+      "learning_rate": 0.0001534465826127801,
+      "loss": 0.6823,
+      "step": 103
+    },
+    {
+      "epoch": 1.1954022988505748,
+      "grad_norm": 0.030994586646556854,
+      "learning_rate": 0.00015230708076495775,
+      "loss": 0.6729,
+      "step": 104
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 0.03224639222025871,
+      "learning_rate": 0.00015115815086468102,
+      "loss": 0.6778,
+      "step": 105
+    },
+    {
+      "epoch": 1.2183908045977012,
+      "grad_norm": 0.030437005683779716,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.674,
+      "step": 106
+    },
+    {
+      "epoch": 1.2298850574712643,
+      "grad_norm": 0.030820753425359726,
+      "learning_rate": 0.00014883283692099112,
+      "loss": 0.6799,
+      "step": 107
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.03301486000418663,
+      "learning_rate": 0.0001476568720021308,
+      "loss": 0.6851,
+      "step": 108
+    },
+    {
+      "epoch": 1.2528735632183907,
+      "grad_norm": 0.033183734863996506,
+      "learning_rate": 0.00014647231720437686,
+      "loss": 0.7094,
+      "step": 109
+    },
+    {
+      "epoch": 1.264367816091954,
+      "grad_norm": 0.03154841437935829,
+      "learning_rate": 0.00014527938603696376,
+      "loss": 0.6812,
+      "step": 110
+    },
+    {
+      "epoch": 1.264367816091954,
+      "eval_loss": 0.6802834868431091,
+      "eval_runtime": 597.3843,
+      "eval_samples_per_second": 16.569,
+      "eval_steps_per_second": 0.131,
+      "step": 110
+    },
+    {
+      "epoch": 1.2758620689655173,
+      "grad_norm": 0.03554477170109749,
+      "learning_rate": 0.00014407829351891857,
+      "loss": 0.679,
+      "step": 111
+    },
+    {
+      "epoch": 1.2873563218390804,
+      "grad_norm": 0.03362204134464264,
+      "learning_rate": 0.00014286925614030542,
+      "loss": 0.6722,
+      "step": 112
+    },
+    {
+      "epoch": 1.2988505747126438,
+      "grad_norm": 0.032853253185749054,
+      "learning_rate": 0.00014165249182320402,
+      "loss": 0.6879,
+      "step": 113
+    },
+    {
+      "epoch": 1.3103448275862069,
+      "grad_norm": 0.033823542296886444,
+      "learning_rate": 0.0001404282198824305,
+      "loss": 0.6627,
+      "step": 114
+    },
+    {
+      "epoch": 1.3218390804597702,
+      "grad_norm": 0.0326109379529953,
+      "learning_rate": 0.00013919666098600753,
+      "loss": 0.6751,
+      "step": 115
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.03431953117251396,
+      "learning_rate": 0.00013795803711538966,
+      "loss": 0.6827,
+      "step": 116
+    },
+    {
+      "epoch": 1.3448275862068966,
+      "grad_norm": 0.03328808769583702,
+      "learning_rate": 0.00013671257152545277,
+      "loss": 0.6648,
+      "step": 117
+    },
+    {
+      "epoch": 1.3563218390804597,
+      "grad_norm": 0.035666704177856445,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.6771,
+      "step": 118
+    },
+    {
+      "epoch": 1.367816091954023,
+      "grad_norm": 0.03441452234983444,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.6623,
+      "step": 119
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.03363391384482384,
+      "learning_rate": 0.00013293737524320797,
+      "loss": 0.6734,
+      "step": 120
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "eval_loss": 0.6736027002334595,
+      "eval_runtime": 601.0855,
+      "eval_samples_per_second": 16.467,
+      "eval_steps_per_second": 0.13,
+      "step": 120
+    },
+    {
+      "epoch": 1.3908045977011494,
+      "grad_norm": 0.03441128134727478,
+      "learning_rate": 0.00013166679938014726,
+      "loss": 0.6625,
+      "step": 121
+    },
+    {
+      "epoch": 1.4022988505747127,
+      "grad_norm": 0.03332269564270973,
+      "learning_rate": 0.0001303905157574247,
+      "loss": 0.6738,
+      "step": 122
+    },
+    {
+      "epoch": 1.4137931034482758,
+      "grad_norm": 0.03411813825368881,
+      "learning_rate": 0.00012910875441787128,
+      "loss": 0.6511,
+      "step": 123
+    },
+    {
+      "epoch": 1.4252873563218391,
+      "grad_norm": 0.034489769488573074,
+      "learning_rate": 0.0001278217463916453,
+      "loss": 0.6579,
+      "step": 124
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "grad_norm": 0.03562283143401146,
+      "learning_rate": 0.0001265297236545901,
+      "loss": 0.6508,
+      "step": 125
+    },
+    {
+      "epoch": 1.4482758620689655,
+      "grad_norm": 0.034433409571647644,
+      "learning_rate": 0.00012523291908642217,
+      "loss": 0.6867,
+      "step": 126
+    },
+    {
+      "epoch": 1.4597701149425286,
+      "grad_norm": 0.034091442823410034,
+      "learning_rate": 0.0001239315664287558,
+      "loss": 0.6609,
+      "step": 127
+    },
+    {
+      "epoch": 1.471264367816092,
+      "grad_norm": 0.034659866243600845,
+      "learning_rate": 0.00012262590024297225,
+      "loss": 0.6708,
+      "step": 128
+    },
+    {
+      "epoch": 1.4827586206896552,
+      "grad_norm": 0.03355137258768082,
+      "learning_rate": 0.0001213161558679416,
+      "loss": 0.6853,
+      "step": 129
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "grad_norm": 0.03497845306992531,
+      "learning_rate": 0.00012000256937760445,
+      "loss": 0.658,
+      "step": 130
+    },
+    {
+      "epoch": 1.4942528735632183,
+      "eval_loss": 0.6697064638137817,
+      "eval_runtime": 595.4108,
+      "eval_samples_per_second": 16.624,
+      "eval_steps_per_second": 0.131,
+      "step": 130
+    },
+    {
+      "epoch": 1.5057471264367817,
+      "grad_norm": 0.03422487527132034,
+      "learning_rate": 0.00011868537753842051,
+      "loss": 0.6688,
+      "step": 131
+    },
+    {
+      "epoch": 1.5172413793103448,
+      "grad_norm": 0.034450776875019073,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.6828,
+      "step": 132
+    },
+    {
+      "epoch": 1.528735632183908,
+      "grad_norm": 0.034574706107378006,
+      "learning_rate": 0.00011604112808577603,
+      "loss": 0.6776,
+      "step": 133
+    },
+    {
+      "epoch": 1.5402298850574714,
+      "grad_norm": 0.03596516326069832,
+      "learning_rate": 0.00011471454708317162,
+      "loss": 0.6276,
+      "step": 134
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 0.035429686307907104,
+      "learning_rate": 0.00011338531386752618,
+      "loss": 0.6427,
+      "step": 135
+    },
+    {
+      "epoch": 1.5632183908045976,
+      "grad_norm": 0.033536769449710846,
+      "learning_rate": 0.0001120536680255323,
+      "loss": 0.652,
+      "step": 136
+    },
+    {
+      "epoch": 1.5747126436781609,
+      "grad_norm": 0.03417116403579712,
+      "learning_rate": 0.00011071984957874479,
+      "loss": 0.6725,
+      "step": 137
+    },
+    {
+      "epoch": 1.5862068965517242,
+      "grad_norm": 0.03480486571788788,
+      "learning_rate": 0.00010938409894031794,
+      "loss": 0.6479,
+      "step": 138
+    },
+    {
+      "epoch": 1.5977011494252875,
+      "grad_norm": 0.03562786802649498,
+      "learning_rate": 0.00010804665687167262,
+      "loss": 0.6681,
+      "step": 139
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "grad_norm": 0.034858204424381256,
+      "learning_rate": 0.00010670776443910024,
+      "loss": 0.6703,
+      "step": 140
+    },
+    {
+      "epoch": 1.6091954022988506,
+      "eval_loss": 0.6661256551742554,
+      "eval_runtime": 590.9429,
+      "eval_samples_per_second": 16.75,
+      "eval_steps_per_second": 0.132,
+      "step": 140
+    },
+    {
+      "epoch": 1.6206896551724137,
+      "grad_norm": 0.03447253257036209,
+      "learning_rate": 0.00010536766297031215,
+      "loss": 0.6643,
+      "step": 141
+    },
+    {
+      "epoch": 1.632183908045977,
+      "grad_norm": 0.03508715331554413,
+      "learning_rate": 0.00010402659401094152,
+      "loss": 0.6583,
+      "step": 142
+    },
+    {
+      "epoch": 1.6436781609195403,
+      "grad_norm": 0.0343579463660717,
+      "learning_rate": 0.00010268479928100614,
+      "loss": 0.6753,
+      "step": 143
+    },
+    {
+      "epoch": 1.6551724137931034,
+      "grad_norm": 0.0350567027926445,
+      "learning_rate": 0.00010134252063133975,
+      "loss": 0.6493,
+      "step": 144
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.034686826169490814,
+      "learning_rate": 0.0001,
+      "loss": 0.6515,
+      "step": 145
+    },
+    {
+      "epoch": 1.6781609195402298,
+      "grad_norm": 0.035702142864465714,
+      "learning_rate": 9.865747936866027e-05,
+      "loss": 0.6638,
+      "step": 146
+    },
+    {
+      "epoch": 1.6896551724137931,
+      "grad_norm": 0.034140318632125854,
+      "learning_rate": 9.73152007189939e-05,
+      "loss": 0.6496,
+      "step": 147
+    },
+    {
+      "epoch": 1.7011494252873565,
+      "grad_norm": 0.038083408027887344,
+      "learning_rate": 9.597340598905852e-05,
+      "loss": 0.6893,
+      "step": 148
+    },
+    {
+      "epoch": 1.7126436781609196,
+      "grad_norm": 0.03810959309339523,
+      "learning_rate": 9.463233702968783e-05,
+      "loss": 0.6728,
+      "step": 149
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.033978622406721115,
+      "learning_rate": 9.329223556089975e-05,
+      "loss": 0.6814,
+      "step": 150
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "eval_loss": 0.6631415486335754,
+      "eval_runtime": 596.1091,
+      "eval_samples_per_second": 16.604,
+      "eval_steps_per_second": 0.131,
+      "step": 150
+    },
+    {
+      "epoch": 1.735632183908046,
+      "grad_norm": 0.03391426429152489,
+      "learning_rate": 9.195334312832742e-05,
+      "loss": 0.6421,
+      "step": 151
+    },
+    {
+      "epoch": 1.7471264367816093,
+      "grad_norm": 0.03562890738248825,
+      "learning_rate": 9.061590105968208e-05,
+      "loss": 0.6739,
+      "step": 152
+    },
+    {
+      "epoch": 1.7586206896551724,
+      "grad_norm": 0.03706149384379387,
+      "learning_rate": 8.928015042125523e-05,
+      "loss": 0.6579,
+      "step": 153
+    },
+    {
+      "epoch": 1.7701149425287355,
+      "grad_norm": 0.03591468557715416,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.645,
+      "step": 154
+    },
+    {
+      "epoch": 1.7816091954022988,
+      "grad_norm": 0.03639413043856621,
+      "learning_rate": 8.661468613247387e-05,
+      "loss": 0.6594,
+      "step": 155
+    },
+    {
+      "epoch": 1.793103448275862,
+      "grad_norm": 0.03598083183169365,
+      "learning_rate": 8.528545291682838e-05,
+      "loss": 0.6723,
+      "step": 156
+    },
+    {
+      "epoch": 1.8045977011494254,
+      "grad_norm": 0.03628537803888321,
+      "learning_rate": 8.395887191422397e-05,
+      "loss": 0.6715,
+      "step": 157
+    },
+    {
+      "epoch": 1.8160919540229885,
+      "grad_norm": 0.03826047480106354,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.6767,
+      "step": 158
+    },
+    {
+      "epoch": 1.8275862068965516,
+      "grad_norm": 0.03769649192690849,
+      "learning_rate": 8.131462246157953e-05,
+      "loss": 0.6552,
+      "step": 159
+    },
+    {
+      "epoch": 1.839080459770115,
+      "grad_norm": 0.03599262982606888,
+      "learning_rate": 7.999743062239557e-05,
+      "loss": 0.6688,
+      "step": 160
+    },
+    {
+      "epoch": 1.839080459770115,
+      "eval_loss": 0.6607028245925903,
+      "eval_runtime": 589.6737,
+      "eval_samples_per_second": 16.786,
+      "eval_steps_per_second": 0.132,
+      "step": 160
+    },
+    {
+      "epoch": 1.8505747126436782,
+      "grad_norm": 0.03584510087966919,
+      "learning_rate": 7.868384413205842e-05,
+      "loss": 0.672,
+      "step": 161
+    },
+    {
+      "epoch": 1.8620689655172413,
+      "grad_norm": 0.03545341268181801,
+      "learning_rate": 7.73740997570278e-05,
+      "loss": 0.6629,
+      "step": 162
+    },
+    {
+      "epoch": 1.8735632183908046,
+      "grad_norm": 0.035858072340488434,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 0.6391,
+      "step": 163
+    },
+    {
+      "epoch": 1.8850574712643677,
+      "grad_norm": 0.035794083029031754,
+      "learning_rate": 7.476708091357782e-05,
+      "loss": 0.6516,
+      "step": 164
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 0.03674920275807381,
+      "learning_rate": 7.347027634540993e-05,
+      "loss": 0.6624,
+      "step": 165
+    },
+    {
+      "epoch": 1.9080459770114944,
+      "grad_norm": 0.034701887518167496,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.6574,
+      "step": 166
+    },
+    {
+      "epoch": 1.9195402298850575,
+      "grad_norm": 0.03606560826301575,
+      "learning_rate": 7.089124558212871e-05,
+      "loss": 0.6668,
+      "step": 167
+    },
+    {
+      "epoch": 1.9310344827586206,
+      "grad_norm": 0.03570757061243057,
+      "learning_rate": 6.960948424257532e-05,
+      "loss": 0.6358,
+      "step": 168
+    },
+    {
+      "epoch": 1.9425287356321839,
+      "grad_norm": 0.034459397196769714,
+      "learning_rate": 6.833320061985277e-05,
+      "loss": 0.6294,
+      "step": 169
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "grad_norm": 0.035828083753585815,
+      "learning_rate": 6.706262475679205e-05,
+      "loss": 0.6781,
+      "step": 170
+    },
+    {
+      "epoch": 1.9540229885057472,
+      "eval_loss": 0.6586677432060242,
+      "eval_runtime": 590.832,
+      "eval_samples_per_second": 16.753,
+      "eval_steps_per_second": 0.132,
+      "step": 170
+    },
+    {
+      "epoch": 1.9655172413793105,
+      "grad_norm": 0.03741836175322533,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 0.6679,
+      "step": 171
+    },
+    {
+      "epoch": 1.9770114942528736,
+      "grad_norm": 0.03573041409254074,
+      "learning_rate": 6.453951129574644e-05,
+      "loss": 0.6805,
+      "step": 172
+    },
+    {
+      "epoch": 1.9885057471264367,
+      "grad_norm": 0.03586418181657791,
+      "learning_rate": 6.328742847454724e-05,
+      "loss": 0.6606,
+      "step": 173
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.03636249899864197,
+      "learning_rate": 6.204196288461037e-05,
+      "loss": 0.6962,
+      "step": 174
+    },
+    {
+      "epoch": 2.0114942528735633,
+      "grad_norm": 0.04032210260629654,
+      "learning_rate": 6.080333901399251e-05,
+      "loss": 0.6426,
+      "step": 175
+    },
+    {
+      "epoch": 2.0229885057471266,
+      "grad_norm": 0.039117176085710526,
+      "learning_rate": 5.957178011756952e-05,
+      "loss": 0.6418,
+      "step": 176
+    },
+    {
+      "epoch": 2.0344827586206895,
+      "grad_norm": 0.037345871329307556,
+      "learning_rate": 5.834750817679606e-05,
+      "loss": 0.6406,
+      "step": 177
+    },
+    {
+      "epoch": 2.045977011494253,
+      "grad_norm": 0.03830842301249504,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.6262,
+      "step": 178
+    },
+    {
+      "epoch": 2.057471264367816,
+      "grad_norm": 0.037265144288539886,
+      "learning_rate": 5.59217064810814e-05,
+      "loss": 0.6385,
+      "step": 179
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 0.03784786909818649,
+      "learning_rate": 5.472061396303629e-05,
+      "loss": 0.618,
+      "step": 180
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "eval_loss": 0.6581570506095886,
+      "eval_runtime": 593.2384,
+      "eval_samples_per_second": 16.685,
+      "eval_steps_per_second": 0.131,
+      "step": 180
+    },
+    {
+      "epoch": 2.0804597701149423,
+      "grad_norm": 0.03711731731891632,
+      "learning_rate": 5.3527682795623146e-05,
+      "loss": 0.6354,
+      "step": 181
+    },
+    {
+      "epoch": 2.0919540229885056,
+      "grad_norm": 0.037277545779943466,
+      "learning_rate": 5.234312799786921e-05,
+      "loss": 0.631,
+      "step": 182
+    },
+    {
+      "epoch": 2.103448275862069,
+      "grad_norm": 0.040995873510837555,
+      "learning_rate": 5.116716307900893e-05,
+      "loss": 0.631,
+      "step": 183
+    },
+    {
+      "epoch": 2.1149425287356323,
+      "grad_norm": 0.038000449538230896,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.6691,
+      "step": 184
+    },
+    {
+      "epoch": 2.1264367816091956,
+      "grad_norm": 0.03552795201539993,
+      "learning_rate": 4.884184913531902e-05,
+      "loss": 0.6147,
+      "step": 185
+    },
+    {
+      "epoch": 2.1379310344827585,
+      "grad_norm": 0.03610774129629135,
+      "learning_rate": 4.7692919235042255e-05,
+      "loss": 0.6259,
+      "step": 186
+    },
+    {
+      "epoch": 2.1494252873563218,
+      "grad_norm": 0.038160186260938644,
+      "learning_rate": 4.6553417387219886e-05,
+      "loss": 0.6375,
+      "step": 187
+    },
+    {
+      "epoch": 2.160919540229885,
+      "grad_norm": 0.03843645006418228,
+      "learning_rate": 4.542354898054953e-05,
+      "loss": 0.6329,
+      "step": 188
+    },
+    {
+      "epoch": 2.1724137931034484,
+      "grad_norm": 0.03745341673493385,
+      "learning_rate": 4.430351766735609e-05,
+      "loss": 0.6379,
+      "step": 189
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "grad_norm": 0.03651278465986252,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.6575,
+      "step": 190
+    },
+    {
+      "epoch": 2.1839080459770113,
+      "eval_loss": 0.657158374786377,
+      "eval_runtime": 591.1387,
+      "eval_samples_per_second": 16.744,
+      "eval_steps_per_second": 0.132,
+      "step": 190
+    },
+    {
+      "epoch": 2.1954022988505746,
+      "grad_norm": 0.03700386360287666,
+      "learning_rate": 4.209377202891212e-05,
+      "loss": 0.643,
+      "step": 191
+    },
+    {
+      "epoch": 2.206896551724138,
+      "grad_norm": 0.038101959973573685,
+      "learning_rate": 4.100445599768774e-05,
+      "loss": 0.6349,
+      "step": 192
+    },
+    {
+      "epoch": 2.218390804597701,
+      "grad_norm": 0.036965154111385345,
+      "learning_rate": 3.99257735762021e-05,
+      "loss": 0.6404,
+      "step": 193
+    },
+    {
+      "epoch": 2.2298850574712645,
+      "grad_norm": 0.03756578266620636,
+      "learning_rate": 3.885791919079878e-05,
+      "loss": 0.6615,
+      "step": 194
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 0.035037923604249954,
+      "learning_rate": 3.7801085316129615e-05,
+      "loss": 0.6237,
+      "step": 195
+    },
+    {
+      "epoch": 2.2528735632183907,
+      "grad_norm": 0.03736288473010063,
+      "learning_rate": 3.675546244046228e-05,
+      "loss": 0.6482,
+      "step": 196
+    },
+    {
+      "epoch": 2.264367816091954,
+      "grad_norm": 0.03758701682090759,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.6101,
+      "step": 197
+    },
+    {
+      "epoch": 2.2758620689655173,
+      "grad_norm": 0.03676440194249153,
+      "learning_rate": 3.469860150164152e-05,
+      "loss": 0.6499,
+      "step": 198
+    },
+    {
+      "epoch": 2.2873563218390807,
+      "grad_norm": 0.03628651425242424,
+      "learning_rate": 3.36877341759205e-05,
+      "loss": 0.629,
+      "step": 199
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.03841525688767433,
+      "learning_rate": 3.268881925724297e-05,
+      "loss": 0.6372,
+      "step": 200
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "eval_loss": 0.6563421487808228,
+      "eval_runtime": 591.4937,
+      "eval_samples_per_second": 16.734,
+      "eval_steps_per_second": 0.132,
+      "step": 200
+    },
+    {
+      "epoch": 2.310344827586207,
+      "grad_norm": 0.03878968209028244,
+      "learning_rate": 3.170203679431584e-05,
+      "loss": 0.6417,
+      "step": 201
+    },
+    {
+      "epoch": 2.32183908045977,
+      "grad_norm": 0.03762966766953468,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.6434,
+      "step": 202
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.03814293071627617,
+      "learning_rate": 2.976557846445225e-05,
+      "loss": 0.643,
+      "step": 203
+    },
+    {
+      "epoch": 2.344827586206897,
+      "grad_norm": 0.03540797904133797,
+      "learning_rate": 2.881625163306596e-05,
+      "loss": 0.6374,
+      "step": 204
+    },
+    {
+      "epoch": 2.3563218390804597,
+      "grad_norm": 0.03709061071276665,
+      "learning_rate": 2.7879755265618555e-05,
+      "loss": 0.6418,
+      "step": 205
+    },
+    {
+      "epoch": 2.367816091954023,
+      "grad_norm": 0.03803767263889313,
+      "learning_rate": 2.6956258160229695e-05,
+      "loss": 0.632,
+      "step": 206
+    },
+    {
+      "epoch": 2.3793103448275863,
+      "grad_norm": 0.03654790297150612,
+      "learning_rate": 2.6045926771976303e-05,
+      "loss": 0.6538,
+      "step": 207
+    },
+    {
+      "epoch": 2.3908045977011496,
+      "grad_norm": 0.03603474050760269,
+      "learning_rate": 2.514892518288988e-05,
+      "loss": 0.6145,
+      "step": 208
+    },
+    {
+      "epoch": 2.4022988505747125,
+      "grad_norm": 0.036107271909713745,
+      "learning_rate": 2.4265415072382016e-05,
+      "loss": 0.6222,
+      "step": 209
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 0.036303840577602386,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.617,
+      "step": 210
+    },
+    {
+      "epoch": 2.413793103448276,
+      "eval_loss": 0.6558452248573303,
+      "eval_runtime": 595.1508,
+      "eval_samples_per_second": 16.631,
+      "eval_steps_per_second": 0.131,
+      "step": 210
+    },
+    {
+      "epoch": 2.425287356321839,
+      "grad_norm": 0.037371959537267685,
+      "learning_rate": 2.2539503817234553e-05,
+      "loss": 0.654,
+      "step": 211
+    },
+    {
+      "epoch": 2.4367816091954024,
+      "grad_norm": 0.037925343960523605,
+      "learning_rate": 2.1697413758237784e-05,
+      "loss": 0.6322,
+      "step": 212
+    },
+    {
+      "epoch": 2.4482758620689653,
+      "grad_norm": 0.03855719789862633,
+      "learning_rate": 2.0869437293033835e-05,
+      "loss": 0.6335,
+      "step": 213
+    },
+    {
+      "epoch": 2.4597701149425286,
+      "grad_norm": 0.037308286875486374,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.6184,
+      "step": 214
+    },
+    {
+      "epoch": 2.471264367816092,
+      "grad_norm": 0.03688681870698929,
+      "learning_rate": 1.9256419525319313e-05,
+      "loss": 0.627,
+      "step": 215
+    },
+    {
+      "epoch": 2.4827586206896552,
+      "grad_norm": 0.038670193403959274,
+      "learning_rate": 1.8471668960045574e-05,
+      "loss": 0.6487,
+      "step": 216
+    },
+    {
+      "epoch": 2.4942528735632186,
+      "grad_norm": 0.03826979547739029,
+      "learning_rate": 1.7701613410634365e-05,
+      "loss": 0.6337,
+      "step": 217
+    },
+    {
+      "epoch": 2.5057471264367814,
+      "grad_norm": 0.03768225386738777,
+      "learning_rate": 1.6946391675198836e-05,
+      "loss": 0.6356,
+      "step": 218
+    },
+    {
+      "epoch": 2.5172413793103448,
+      "grad_norm": 0.037600524723529816,
+      "learning_rate": 1.620613987814189e-05,
+      "loss": 0.6237,
+      "step": 219
+    },
+    {
+      "epoch": 2.528735632183908,
+      "grad_norm": 0.036940865218639374,
+      "learning_rate": 1.5480991445620542e-05,
+      "loss": 0.6152,
+      "step": 220
+    },
+    {
+      "epoch": 2.528735632183908,
+      "eval_loss": 0.655238926410675,
+      "eval_runtime": 592.9652,
+      "eval_samples_per_second": 16.692,
+      "eval_steps_per_second": 0.132,
+      "step": 220
+    },
+    {
+      "epoch": 2.5402298850574714,
+      "grad_norm": 0.03826668858528137,
+      "learning_rate": 1.4771077081496654e-05,
+      "loss": 0.6511,
+      "step": 221
+    },
+    {
+      "epoch": 2.5517241379310347,
+      "grad_norm": 0.0361490473151207,
+      "learning_rate": 1.4076524743778319e-05,
+      "loss": 0.6311,
+      "step": 222
+    },
+    {
+      "epoch": 2.5632183908045976,
+      "grad_norm": 0.03727561607956886,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.6324,
+      "step": 223
+    },
+    {
+      "epoch": 2.574712643678161,
+      "grad_norm": 0.038558244705200195,
+      "learning_rate": 1.2734004112438568e-05,
+      "loss": 0.6568,
+      "step": 224
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.03707597777247429,
+      "learning_rate": 1.2086277800490554e-05,
+      "loss": 0.649,
+      "step": 225
+    },
+    {
+      "epoch": 2.5977011494252875,
+      "grad_norm": 0.037075500935316086,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.6603,
+      "step": 226
+    },
+    {
+      "epoch": 2.609195402298851,
+      "grad_norm": 0.03692416474223137,
+      "learning_rate": 1.083847690782972e-05,
+      "loss": 0.6295,
+      "step": 227
+    },
+    {
+      "epoch": 2.6206896551724137,
+      "grad_norm": 0.03675093874335289,
+      "learning_rate": 1.0238627236098619e-05,
+      "loss": 0.6209,
+      "step": 228
+    },
+    {
+      "epoch": 2.632183908045977,
+      "grad_norm": 0.03640436753630638,
+      "learning_rate": 9.65495653896179e-06,
+      "loss": 0.6339,
+      "step": 229
+    },
+    {
+      "epoch": 2.6436781609195403,
+      "grad_norm": 0.037452854216098785,
+      "learning_rate": 9.08757001972762e-06,
+      "loss": 0.6407,
+      "step": 230
+    },
+    {
+      "epoch": 2.6436781609195403,
+      "eval_loss": 0.6549434065818787,
+      "eval_runtime": 592.4603,
+      "eval_samples_per_second": 16.707,
+      "eval_steps_per_second": 0.132,
+      "step": 230
+    },
+    {
+      "epoch": 2.655172413793103,
+      "grad_norm": 0.03795592859387398,
+      "learning_rate": 8.536569946574546e-06,
+      "loss": 0.6534,
+      "step": 231
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.03788486495614052,
+      "learning_rate": 8.002055634117578e-06,
+      "loss": 0.6507,
+      "step": 232
+    },
+    {
+      "epoch": 2.67816091954023,
+      "grad_norm": 0.03641374036669731,
+      "learning_rate": 7.4841234255076495e-06,
+      "loss": 0.6282,
+      "step": 233
+    },
+    {
+      "epoch": 2.689655172413793,
+      "grad_norm": 0.03832123428583145,
+      "learning_rate": 6.9828666750661795e-06,
+      "loss": 0.6276,
+      "step": 234
+    },
+    {
+      "epoch": 2.7011494252873565,
+      "grad_norm": 0.03677581995725632,
+      "learning_rate": 6.498375731458528e-06,
+      "loss": 0.639,
+      "step": 235
+    },
+    {
+      "epoch": 2.7126436781609193,
+      "grad_norm": 0.03623311221599579,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.6425,
+      "step": 236
+    },
+    {
+      "epoch": 2.7241379310344827,
+      "grad_norm": 0.036890316754579544,
+      "learning_rate": 5.580037533961546e-06,
+      "loss": 0.6438,
+      "step": 237
+    },
+    {
+      "epoch": 2.735632183908046,
+      "grad_norm": 0.03658117353916168,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.6275,
+      "step": 238
+    },
+    {
+      "epoch": 2.7471264367816093,
+      "grad_norm": 0.03849633410573006,
+      "learning_rate": 4.729770904034647e-06,
+      "loss": 0.6357,
+      "step": 239
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.03720705956220627,
+      "learning_rate": 4.3303579172574885e-06,
+      "loss": 0.6498,
+      "step": 240
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "eval_loss": 0.6547917723655701,
+      "eval_runtime": 593.6976,
+      "eval_samples_per_second": 16.672,
+      "eval_steps_per_second": 0.131,
+      "step": 240
+    },
+    {
+      "epoch": 2.7701149425287355,
+      "grad_norm": 0.03713015094399452,
+      "learning_rate": 3.948188836862776e-06,
+      "loss": 0.63,
+      "step": 241
+    },
+    {
+      "epoch": 2.781609195402299,
+      "grad_norm": 0.03703474998474121,
+      "learning_rate": 3.5833325466437694e-06,
+      "loss": 0.6267,
+      "step": 242
+    },
+    {
+      "epoch": 2.793103448275862,
+      "grad_norm": 0.0391690619289875,
+      "learning_rate": 3.2358548098621932e-06,
+      "loss": 0.6297,
+      "step": 243
+    },
+    {
+      "epoch": 2.8045977011494254,
+      "grad_norm": 0.03748522326350212,
+      "learning_rate": 2.905818257394799e-06,
+      "loss": 0.6289,
+      "step": 244
+    },
+    {
+      "epoch": 2.8160919540229887,
+      "grad_norm": 0.036214690655469894,
+      "learning_rate": 2.5932823764445392e-06,
+      "loss": 0.6274,
+      "step": 245
+    },
+    {
+      "epoch": 2.8275862068965516,
+      "grad_norm": 0.03697674348950386,
+      "learning_rate": 2.2983034998182997e-06,
+      "loss": 0.6205,
+      "step": 246
+    },
+    {
+      "epoch": 2.839080459770115,
+      "grad_norm": 0.0381477065384388,
+      "learning_rate": 2.0209347957732328e-06,
+      "loss": 0.6585,
+      "step": 247
+    },
+    {
+      "epoch": 2.8505747126436782,
+      "grad_norm": 0.03660466521978378,
+      "learning_rate": 1.7612262584335237e-06,
+      "loss": 0.6215,
+      "step": 248
+    },
+    {
+      "epoch": 2.862068965517241,
+      "grad_norm": 0.03698161989450455,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.6454,
+      "step": 249
+    },
+    {
+      "epoch": 2.873563218390805,
+      "grad_norm": 0.037139616906642914,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.6365,
+      "step": 250
+    },
+    {
+      "epoch": 2.873563218390805,
+      "eval_loss": 0.6547266840934753,
+      "eval_runtime": 593.9462,
+      "eval_samples_per_second": 16.665,
+      "eval_steps_per_second": 0.131,
+      "step": 250
+    },
+    {
+      "epoch": 2.8850574712643677,
+      "grad_norm": 0.03719855844974518,
+      "learning_rate": 1.0885137906768372e-06,
+      "loss": 0.628,
+      "step": 251
+    },
+    {
+      "epoch": 2.896551724137931,
+      "grad_norm": 0.03709800913929939,
+      "learning_rate": 8.998820754091531e-07,
+      "loss": 0.6447,
+      "step": 252
+    },
+    {
+      "epoch": 2.9080459770114944,
+      "grad_norm": 0.03928203135728836,
+      "learning_rate": 7.291125901946027e-07,
+      "loss": 0.6615,
+      "step": 253
+    },
+    {
+      "epoch": 2.9195402298850572,
+      "grad_norm": 0.03835693374276161,
+      "learning_rate": 5.762361152572115e-07,
+      "loss": 0.6382,
+      "step": 254
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 0.037969332188367844,
+      "learning_rate": 4.412802057081278e-07,
+      "loss": 0.6339,
+      "step": 255
+    },
+    {
+      "epoch": 2.942528735632184,
+      "grad_norm": 0.0369732528924942,
+      "learning_rate": 3.2426918657900704e-07,
+      "loss": 0.6557,
+      "step": 256
+    },
+    {
+      "epoch": 2.954022988505747,
+      "grad_norm": 0.03954119607806206,
+      "learning_rate": 2.2522414843748618e-07,
+      "loss": 0.6419,
+      "step": 257
+    },
+    {
+      "epoch": 2.9655172413793105,
+      "grad_norm": 0.03722945228219032,
+      "learning_rate": 1.4416294358582384e-07,
+      "loss": 0.6224,
+      "step": 258
+    },
+    {
+      "epoch": 2.9770114942528734,
+      "grad_norm": 0.037498198449611664,
+      "learning_rate": 8.110018284304133e-08,
+      "loss": 0.6472,
+      "step": 259
+    },
+    {
+      "epoch": 2.9885057471264367,
+      "grad_norm": 0.03706786781549454,
+      "learning_rate": 3.60472329114625e-08,
+      "loss": 0.6532,
+      "step": 260
+    },
+    {
+      "epoch": 2.9885057471264367,
+      "eval_loss": 0.6546847820281982,
+      "eval_runtime": 591.4156,
+      "eval_samples_per_second": 16.736,
+      "eval_steps_per_second": 0.132,
+      "step": 260
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.0390935055911541,
+      "learning_rate": 9.012214327897006e-09,
+      "loss": 0.6416,
+      "step": 261
+    },
+    {
+      "epoch": 3.0,
+      "step": 261,
+      "total_flos": 4.878497427033686e+19,
+      "train_loss": 0.6974607110023499,
+      "train_runtime": 68284.7248,
+      "train_samples_per_second": 3.914,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 261,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.878497427033686e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476042c67583e95ad04b96c9897df6e026d7f6faea9ad3f831a1bff9b3eaf43b
+size 6161