Upload folder using huggingface_hub

README.md

@@ -0,0 +1,156 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: Qwen/Qwen1.5-7B
+model-index:
+- name: home/yujia/home/CN_Hateful/trained_models/qwen/toxi/3e-5/
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+# base_model: Qwen/Qwen-7B
+base_model: Qwen/Qwen1.5-7B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+trust_remote_code: true
+
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+
+datasets:
+  # - path: mhenrichsen/alpaca_2k_test
+  - path: /home/yujia/home/CN_Hateful/train_toxiCN.json
+    ds_type: json
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/toxi/3e-5/
+
+sequence_len: 256  # supports up to 8192
+sample_packing: false
+pad_to_sequence_len:
+
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.00003
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention:
+
+warmup_steps: 10
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 20
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# home/yujia/home/CN_Hateful/trained_models/qwen/toxi/3e-5/
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0527
+
+## 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: 3e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.4697        | 0.0   | 1    | 3.5475          |
+| 0.0788        | 0.25  | 142  | 0.0807          |
+| 0.0973        | 0.5   | 284  | 0.0657          |
+| 0.0454        | 0.75  | 426  | 0.0627          |
+| 0.0263        | 1.0   | 568  | 0.0547          |
+| 0.0819        | 1.26  | 710  | 0.0521          |
+| 0.0552        | 1.51  | 852  | 0.0530          |
+| 0.0764        | 1.76  | 994  | 0.0523          |
+| 0.0503        | 2.01  | 1136 | 0.0514          |
+| 0.0221        | 2.26  | 1278 | 0.0519          |
+| 0.0267        | 2.51  | 1420 | 0.0534          |
+| 0.0213        | 2.76  | 1562 | 0.0527          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a097c80438fd539fdb284377d15cbebc4e0d969cffd1eefe5c6b6886f397ae
+size 319977674

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-1130/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-7B
+---
+
+# 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 0.10.0

checkpoint-1130/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1130/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b705c44b05d7a90e2b92905f21d2ef5b42a8bd68b95a84a3a5d30a0b0caaff2b
+size 319876032

checkpoint-1130/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-1130/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a091798c6d1d114e21a6afb2bb7b77841e5a55180921545994a7fa5096c1d1f9
+size 160736532

checkpoint-1130/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b5ce99929bf679c66efd3571d6d16ec2bc09d695d01903fcacc74246e288546
+size 14512

checkpoint-1130/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87959f9259619b31ece50de4d6f6e1852b421537d8bf5f40923f2b9835361944
+size 14512

checkpoint-1130/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f42673594cc7781d7fffeba69a36051db67a8044ccd535621ac2ad6f941d43
+size 1064

checkpoint-1130/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1130/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1130/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222c6d9f6232f31ff9a258358b395f70d592023a50d4056572ccf3372d2fda1
+size 5752

checkpoint-1695/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-7B
+---
+
+# 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 0.10.0

checkpoint-1695/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1695/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59750990282387d3dd367c425540b1955a4f635528b0162a1b41bd22d057c993
+size 319876032

checkpoint-1695/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-1695/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb9dd174a4cf15daa9fcdba73306715199b5be7e1b71840b099ebc0d2e234be5
+size 160736532

checkpoint-1695/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be619f0408a46b7c595a0e16467ed349083b4f5fc49d2bda7b06933a47f2d79
+size 14512

checkpoint-1695/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b912b56538b0daf0219944e37db6b66e8b297d0c8462672d5a4f11b2365846f0
+size 14512

checkpoint-1695/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d404034bd23dacfb15a16af02850f46cff58637fce8451371ec4b18135418a7a
+size 1064

checkpoint-1695/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1695/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1695/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222c6d9f6232f31ff9a258358b395f70d592023a50d4056572ccf3372d2fda1
+size 5752

checkpoint-565/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-7B
+---
+
+# 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 0.10.0

checkpoint-565/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-7B",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-565/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeaa950e86fcb74b4004e9e16ff704679b2c93d7d5c7e611c5f5f21a8050e3f1
+size 319876032

checkpoint-565/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-565/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca5b5a9fe92c7b94358c0f1b63f7c37adfe1065250b9616c18bad46747a21c1
+size 160736532

checkpoint-565/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ed7c1ca047ccc61dec57205e4e352265f27f08faafcef79a62d8c8620de4e3
+size 14512

checkpoint-565/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a120d0d1b40b3da51cdbdb6991575094a50cabc516b462c83d578e06a5a986
+size 14512

checkpoint-565/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f77f45d57377e8bda860399d12ebd45b17ac6789ceccd671eb4c3cc6e5f990
+size 1064

checkpoint-565/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-565/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-565/trainer_state.json

@@ -0,0 +1,4008 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9995577178239717,
+  "eval_steps": 142,
+  "global_step": 565,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 5.333217144012451,
+      "learning_rate": 3e-06,
+      "loss": 3.4697,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 3.547457695007324,
+      "eval_runtime": 14.4761,
+      "eval_samples_per_second": 32.882,
+      "eval_steps_per_second": 8.22,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 5.45876932144165,
+      "learning_rate": 6e-06,
+      "loss": 3.4361,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.8387346267700195,
+      "learning_rate": 9e-06,
+      "loss": 3.6111,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.629228591918945,
+      "learning_rate": 1.2e-05,
+      "loss": 3.468,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.132396697998047,
+      "learning_rate": 1.5e-05,
+      "loss": 3.4794,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.605806350708008,
+      "learning_rate": 1.8e-05,
+      "loss": 3.4557,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.7556891441345215,
+      "learning_rate": 2.1e-05,
+      "loss": 3.4051,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.8776655197143555,
+      "learning_rate": 2.4e-05,
+      "loss": 3.1824,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.992830753326416,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 3.0846,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.38725471496582,
+      "learning_rate": 3e-05,
+      "loss": 2.8616,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.4103684425354,
+      "learning_rate": 2.9999973928796923e-05,
+      "loss": 2.5679,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.2000298500061035,
+      "learning_rate": 2.999989571527831e-05,
+      "loss": 2.2378,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.7659687995910645,
+      "learning_rate": 2.9999765359716046e-05,
+      "loss": 1.8411,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.1735832691192627,
+      "learning_rate": 2.999958286256327e-05,
+      "loss": 1.519,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.7938477993011475,
+      "learning_rate": 2.9999348224454367e-05,
+      "loss": 1.2343,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.5651497840881348,
+      "learning_rate": 2.9999061446204985e-05,
+      "loss": 1.0183,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.3572280406951904,
+      "learning_rate": 2.9998722528812e-05,
+      "loss": 0.7906,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.2292940616607666,
+      "learning_rate": 2.9998331473453557e-05,
+      "loss": 0.6625,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.9572314023971558,
+      "learning_rate": 2.9997888281489015e-05,
+      "loss": 0.5271,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.7180088758468628,
+      "learning_rate": 2.9997392954458985e-05,
+      "loss": 0.4319,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.5089068412780762,
+      "learning_rate": 2.9996845494085306e-05,
+      "loss": 0.351,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.2355144023895264,
+      "learning_rate": 2.999624590227103e-05,
+      "loss": 0.2994,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.7736936211585999,
+      "learning_rate": 2.9995594181100443e-05,
+      "loss": 0.1704,
+      "step": 23
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.5642102956771851,
+      "learning_rate": 2.9994890332839027e-05,
+      "loss": 0.1217,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.34946027398109436,
+      "learning_rate": 2.9994134359933476e-05,
+      "loss": 0.0992,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.24627894163131714,
+      "learning_rate": 2.999332626501167e-05,
+      "loss": 0.0828,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.28634899854660034,
+      "learning_rate": 2.9992466050882673e-05,
+      "loss": 0.0945,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.1457609236240387,
+      "learning_rate": 2.9991553720536733e-05,
+      "loss": 0.0924,
+      "step": 28
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3852764964103699,
+      "learning_rate": 2.9990589277145254e-05,
+      "loss": 0.0868,
+      "step": 29
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.28345659375190735,
+      "learning_rate": 2.9989572724060797e-05,
+      "loss": 0.0845,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.24844343960285187,
+      "learning_rate": 2.998850406481707e-05,
+      "loss": 0.0756,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.2215878665447235,
+      "learning_rate": 2.9987383303128887e-05,
+      "loss": 0.0799,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.20273327827453613,
+      "learning_rate": 2.9986210442892215e-05,
+      "loss": 0.099,
+      "step": 33
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.23849628865718842,
+      "learning_rate": 2.9984985488184086e-05,
+      "loss": 0.0709,
+      "step": 34
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.28950855135917664,
+      "learning_rate": 2.9983708443262656e-05,
+      "loss": 0.0736,
+      "step": 35
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4729451537132263,
+      "learning_rate": 2.9982379312567126e-05,
+      "loss": 0.0898,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.26402196288108826,
+      "learning_rate": 2.998099810071777e-05,
+      "loss": 0.0989,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.21811941266059875,
+      "learning_rate": 2.9979564812515906e-05,
+      "loss": 0.0816,
+      "step": 38
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.4151253402233124,
+      "learning_rate": 2.9978079452943875e-05,
+      "loss": 0.0646,
+      "step": 39
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.5114066004753113,
+      "learning_rate": 2.9976542027165016e-05,
+      "loss": 0.0986,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.23638691008090973,
+      "learning_rate": 2.9974952540523676e-05,
+      "loss": 0.0929,
+      "step": 41
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.18284691870212555,
+      "learning_rate": 2.997331099854516e-05,
+      "loss": 0.0707,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.415445476770401,
+      "learning_rate": 2.9971617406935735e-05,
+      "loss": 0.0875,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.35435256361961365,
+      "learning_rate": 2.9969871771582596e-05,
+      "loss": 0.0917,
+      "step": 44
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5223746299743652,
+      "learning_rate": 2.996807409855385e-05,
+      "loss": 0.0839,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.2852335274219513,
+      "learning_rate": 2.99662243940985e-05,
+      "loss": 0.0581,
+      "step": 46
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.19847406446933746,
+      "learning_rate": 2.9964322664646412e-05,
+      "loss": 0.0581,
+      "step": 47
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.42156773805618286,
+      "learning_rate": 2.9962368916808308e-05,
+      "loss": 0.0949,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.1932952105998993,
+      "learning_rate": 2.9960363157375724e-05,
+      "loss": 0.0936,
+      "step": 49
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.28940048813819885,
+      "learning_rate": 2.9958305393321e-05,
+      "loss": 0.1074,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4381609857082367,
+      "learning_rate": 2.995619563179726e-05,
+      "loss": 0.1053,
+      "step": 51
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.16727806627750397,
+      "learning_rate": 2.9954033880138368e-05,
+      "loss": 0.0825,
+      "step": 52
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3134240210056305,
+      "learning_rate": 2.995182014585892e-05,
+      "loss": 0.0565,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.16883538663387299,
+      "learning_rate": 2.9949554436654215e-05,
+      "loss": 0.0805,
+      "step": 54
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.4369119107723236,
+      "learning_rate": 2.994723676040022e-05,
+      "loss": 0.079,
+      "step": 55
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.22722230851650238,
+      "learning_rate": 2.9944867125153548e-05,
+      "loss": 0.0707,
+      "step": 56
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.2767599821090698,
+      "learning_rate": 2.9942445539151432e-05,
+      "loss": 0.0877,
+      "step": 57
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.2087458074092865,
+      "learning_rate": 2.9939972010811693e-05,
+      "loss": 0.0746,
+      "step": 58
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.2058565467596054,
+      "learning_rate": 2.993744654873272e-05,
+      "loss": 0.0783,
+      "step": 59
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2181982547044754,
+      "learning_rate": 2.993486916169341e-05,
+      "loss": 0.0764,
+      "step": 60
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.18020497262477875,
+      "learning_rate": 2.9932239858653183e-05,
+      "loss": 0.0675,
+      "step": 61
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2599628269672394,
+      "learning_rate": 2.992955864875192e-05,
+      "loss": 0.0957,
+      "step": 62
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2814478576183319,
+      "learning_rate": 2.9926825541309928e-05,
+      "loss": 0.0926,
+      "step": 63
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.21382613480091095,
+      "learning_rate": 2.9924040545827936e-05,
+      "loss": 0.0944,
+      "step": 64
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.16025784611701965,
+      "learning_rate": 2.9921203671987025e-05,
+      "loss": 0.0727,
+      "step": 65
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.22130753099918365,
+      "learning_rate": 2.9918314929648637e-05,
+      "loss": 0.0906,
+      "step": 66
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.16255636513233185,
+      "learning_rate": 2.991537432885449e-05,
+      "loss": 0.057,
+      "step": 67
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.3057488203048706,
+      "learning_rate": 2.991238187982659e-05,
+      "loss": 0.0866,
+      "step": 68
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.24336600303649902,
+      "learning_rate": 2.9909337592967176e-05,
+      "loss": 0.0509,
+      "step": 69
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.25192490220069885,
+      "learning_rate": 2.9906241478858666e-05,
+      "loss": 0.0677,
+      "step": 70
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.6552413105964661,
+      "learning_rate": 2.990309354826366e-05,
+      "loss": 0.1014,
+      "step": 71
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.22106248140335083,
+      "learning_rate": 2.9899893812124862e-05,
+      "loss": 0.0779,
+      "step": 72
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.2502892017364502,
+      "learning_rate": 2.989664228156507e-05,
+      "loss": 0.0759,
+      "step": 73
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.23127524554729462,
+      "learning_rate": 2.9893338967887128e-05,
+      "loss": 0.0735,
+      "step": 74
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.22794046998023987,
+      "learning_rate": 2.988998388257388e-05,
+      "loss": 0.048,
+      "step": 75
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.2867235541343689,
+      "learning_rate": 2.988657703728815e-05,
+      "loss": 0.0449,
+      "step": 76
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.28723156452178955,
+      "learning_rate": 2.9883118443872662e-05,
+      "loss": 0.0525,
+      "step": 77
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.21423418819904327,
+      "learning_rate": 2.9879608114350064e-05,
+      "loss": 0.0684,
+      "step": 78
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.22717736661434174,
+      "learning_rate": 2.9876046060922803e-05,
+      "loss": 0.0496,
+      "step": 79
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.52623051404953,
+      "learning_rate": 2.987243229597316e-05,
+      "loss": 0.1125,
+      "step": 80
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.41985878348350525,
+      "learning_rate": 2.9868766832063156e-05,
+      "loss": 0.1115,
+      "step": 81
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.5244089365005493,
+      "learning_rate": 2.986504968193454e-05,
+      "loss": 0.1185,
+      "step": 82
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.4969002604484558,
+      "learning_rate": 2.9861280858508712e-05,
+      "loss": 0.1123,
+      "step": 83
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.31229168176651,
+      "learning_rate": 2.9857460374886717e-05,
+      "loss": 0.082,
+      "step": 84
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.34874776005744934,
+      "learning_rate": 2.985358824434916e-05,
+      "loss": 0.0732,
+      "step": 85
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.33042728900909424,
+      "learning_rate": 2.984966448035619e-05,
+      "loss": 0.0719,
+      "step": 86
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.9238921403884888,
+      "learning_rate": 2.9845689096547442e-05,
+      "loss": 0.1171,
+      "step": 87
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.24976597726345062,
+      "learning_rate": 2.9841662106741986e-05,
+      "loss": 0.0875,
+      "step": 88
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.23768329620361328,
+      "learning_rate": 2.983758352493829e-05,
+      "loss": 0.0821,
+      "step": 89
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.1419605314731598,
+      "learning_rate": 2.983345336531415e-05,
+      "loss": 0.0696,
+      "step": 90
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.15112988650798798,
+      "learning_rate": 2.9829271642226665e-05,
+      "loss": 0.0958,
+      "step": 91
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.11599217355251312,
+      "learning_rate": 2.9825038370212183e-05,
+      "loss": 0.0838,
+      "step": 92
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.34909361600875854,
+      "learning_rate": 2.982075356398623e-05,
+      "loss": 0.0922,
+      "step": 93
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.3156541585922241,
+      "learning_rate": 2.9816417238443482e-05,
+      "loss": 0.106,
+      "step": 94
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.21198609471321106,
+      "learning_rate": 2.9812029408657698e-05,
+      "loss": 0.0832,
+      "step": 95
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.17507284879684448,
+      "learning_rate": 2.9807590089881687e-05,
+      "loss": 0.0736,
+      "step": 96
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.09285402297973633,
+      "learning_rate": 2.980309929754722e-05,
+      "loss": 0.0816,
+      "step": 97
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.21642349660396576,
+      "learning_rate": 2.9798557047265023e-05,
+      "loss": 0.0806,
+      "step": 98
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.20919114351272583,
+      "learning_rate": 2.979396335482469e-05,
+      "loss": 0.0852,
+      "step": 99
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.1738620400428772,
+      "learning_rate": 2.9789318236194618e-05,
+      "loss": 0.079,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.19599463045597076,
+      "learning_rate": 2.9784621707521993e-05,
+      "loss": 0.0635,
+      "step": 101
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.18762755393981934,
+      "learning_rate": 2.97798737851327e-05,
+      "loss": 0.0863,
+      "step": 102
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.15935586392879486,
+      "learning_rate": 2.977507448553128e-05,
+      "loss": 0.0692,
+      "step": 103
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.25695595145225525,
+      "learning_rate": 2.9770223825400872e-05,
+      "loss": 0.0914,
+      "step": 104
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.17666970193386078,
+      "learning_rate": 2.9765321821603143e-05,
+      "loss": 0.0617,
+      "step": 105
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.1571740359067917,
+      "learning_rate": 2.9760368491178244e-05,
+      "loss": 0.0797,
+      "step": 106
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.13504642248153687,
+      "learning_rate": 2.9755363851344753e-05,
+      "loss": 0.0647,
+      "step": 107
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.12887655198574066,
+      "learning_rate": 2.9750307919499595e-05,
+      "loss": 0.0662,
+      "step": 108
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.22609621286392212,
+      "learning_rate": 2.9745200713218002e-05,
+      "loss": 0.0809,
+      "step": 109
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.2685830295085907,
+      "learning_rate": 2.9740042250253443e-05,
+      "loss": 0.084,
+      "step": 110
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.18346565961837769,
+      "learning_rate": 2.973483254853756e-05,
+      "loss": 0.0568,
+      "step": 111
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.4906081259250641,
+      "learning_rate": 2.9729571626180116e-05,
+      "loss": 0.0911,
+      "step": 112
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.28486496210098267,
+      "learning_rate": 2.972425950146891e-05,
+      "loss": 0.0671,
+      "step": 113
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.35737311840057373,
+      "learning_rate": 2.9718896192869758e-05,
+      "loss": 0.1005,
+      "step": 114
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.27113574743270874,
+      "learning_rate": 2.9713481719026368e-05,
+      "loss": 0.0655,
+      "step": 115
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.17216627299785614,
+      "learning_rate": 2.970801609876032e-05,
+      "loss": 0.0463,
+      "step": 116
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.1476421356201172,
+      "learning_rate": 2.9702499351070992e-05,
+      "loss": 0.0534,
+      "step": 117
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.3753887116909027,
+      "learning_rate": 2.969693149513548e-05,
+      "loss": 0.0763,
+      "step": 118
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.22127705812454224,
+      "learning_rate": 2.969131255030855e-05,
+      "loss": 0.0548,
+      "step": 119
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.18454331159591675,
+      "learning_rate": 2.9685642536122545e-05,
+      "loss": 0.0494,
+      "step": 120
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.24991334974765778,
+      "learning_rate": 2.9679921472287358e-05,
+      "loss": 0.089,
+      "step": 121
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.17822043597698212,
+      "learning_rate": 2.967414937869031e-05,
+      "loss": 0.0337,
+      "step": 122
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.19183677434921265,
+      "learning_rate": 2.9668326275396133e-05,
+      "loss": 0.0627,
+      "step": 123
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.1919647753238678,
+      "learning_rate": 2.966245218264687e-05,
+      "loss": 0.0549,
+      "step": 124
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.3507068455219269,
+      "learning_rate": 2.96565271208618e-05,
+      "loss": 0.0802,
+      "step": 125
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.3020438253879547,
+      "learning_rate": 2.9650551110637397e-05,
+      "loss": 0.0803,
+      "step": 126
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.951285183429718,
+      "learning_rate": 2.964452417274723e-05,
+      "loss": 0.1049,
+      "step": 127
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.6102455258369446,
+      "learning_rate": 2.96384463281419e-05,
+      "loss": 0.0711,
+      "step": 128
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.3394455313682556,
+      "learning_rate": 2.9632317597948968e-05,
+      "loss": 0.0704,
+      "step": 129
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.296131432056427,
+      "learning_rate": 2.9626138003472884e-05,
+      "loss": 0.0726,
+      "step": 130
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.37837737798690796,
+      "learning_rate": 2.9619907566194915e-05,
+      "loss": 0.092,
+      "step": 131
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.7398345470428467,
+      "learning_rate": 2.9613626307773055e-05,
+      "loss": 0.1055,
+      "step": 132
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.18485528230667114,
+      "learning_rate": 2.9607294250041965e-05,
+      "loss": 0.0615,
+      "step": 133
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4245338439941406,
+      "learning_rate": 2.96009114150129e-05,
+      "loss": 0.0938,
+      "step": 134
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.25269758701324463,
+      "learning_rate": 2.959447782487361e-05,
+      "loss": 0.0686,
+      "step": 135
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.1531674861907959,
+      "learning_rate": 2.9587993501988292e-05,
+      "loss": 0.0515,
+      "step": 136
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.1748104691505432,
+      "learning_rate": 2.958145846889749e-05,
+      "loss": 0.0841,
+      "step": 137
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.16989848017692566,
+      "learning_rate": 2.957487274831803e-05,
+      "loss": 0.0822,
+      "step": 138
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.16533434391021729,
+      "learning_rate": 2.9568236363142927e-05,
+      "loss": 0.0676,
+      "step": 139
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.12993450462818146,
+      "learning_rate": 2.9561549336441333e-05,
+      "loss": 0.0837,
+      "step": 140
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.23538929224014282,
+      "learning_rate": 2.955481169145841e-05,
+      "loss": 0.0784,
+      "step": 141
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.1557569056749344,
+      "learning_rate": 2.95480234516153e-05,
+      "loss": 0.0788,
+      "step": 142
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.08073563128709793,
+      "eval_runtime": 14.7663,
+      "eval_samples_per_second": 32.236,
+      "eval_steps_per_second": 8.059,
+      "step": 142
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.217232346534729,
+      "learning_rate": 2.9541184640509015e-05,
+      "loss": 0.0598,
+      "step": 143
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2527540326118469,
+      "learning_rate": 2.953429528191236e-05,
+      "loss": 0.0604,
+      "step": 144
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.1690036803483963,
+      "learning_rate": 2.9527355399773847e-05,
+      "loss": 0.0815,
+      "step": 145
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.15807238221168518,
+      "learning_rate": 2.9520365018217622e-05,
+      "loss": 0.0695,
+      "step": 146
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.12181195616722107,
+      "learning_rate": 2.951332416154337e-05,
+      "loss": 0.0869,
+      "step": 147
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.27408546209335327,
+      "learning_rate": 2.9506232854226242e-05,
+      "loss": 0.0725,
+      "step": 148
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.1542072892189026,
+      "learning_rate": 2.9499091120916757e-05,
+      "loss": 0.0616,
+      "step": 149
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.31103819608688354,
+      "learning_rate": 2.9491898986440726e-05,
+      "loss": 0.0791,
+      "step": 150
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.15201374888420105,
+      "learning_rate": 2.9484656475799164e-05,
+      "loss": 0.0681,
+      "step": 151
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.33369091153144836,
+      "learning_rate": 2.9477363614168197e-05,
+      "loss": 0.0673,
+      "step": 152
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.1663801521062851,
+      "learning_rate": 2.9470020426898983e-05,
+      "loss": 0.0514,
+      "step": 153
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.3342381715774536,
+      "learning_rate": 2.946262693951762e-05,
+      "loss": 0.0824,
+      "step": 154
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.15362265706062317,
+      "learning_rate": 2.9455183177725055e-05,
+      "loss": 0.0801,
+      "step": 155
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.1435208022594452,
+      "learning_rate": 2.9447689167397e-05,
+      "loss": 0.0625,
+      "step": 156
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.23910465836524963,
+      "learning_rate": 2.944014493458383e-05,
+      "loss": 0.0977,
+      "step": 157
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.15610359609127045,
+      "learning_rate": 2.9432550505510516e-05,
+      "loss": 0.0329,
+      "step": 158
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.23283672332763672,
+      "learning_rate": 2.942490590657651e-05,
+      "loss": 0.1056,
+      "step": 159
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.21941441297531128,
+      "learning_rate": 2.9417211164355668e-05,
+      "loss": 0.0765,
+      "step": 160
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.16233329474925995,
+      "learning_rate": 2.9409466305596135e-05,
+      "loss": 0.056,
+      "step": 161
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.22437363862991333,
+      "learning_rate": 2.9401671357220297e-05,
+      "loss": 0.0845,
+      "step": 162
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.24630329012870789,
+      "learning_rate": 2.9393826346324634e-05,
+      "loss": 0.0588,
+      "step": 163
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.17304874956607819,
+      "learning_rate": 2.9385931300179675e-05,
+      "loss": 0.0582,
+      "step": 164
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.35216909646987915,
+      "learning_rate": 2.9377986246229853e-05,
+      "loss": 0.1085,
+      "step": 165
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.13712701201438904,
+      "learning_rate": 2.9369991212093462e-05,
+      "loss": 0.0451,
+      "step": 166
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.15788517892360687,
+      "learning_rate": 2.9361946225562516e-05,
+      "loss": 0.0572,
+      "step": 167
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.15666936337947845,
+      "learning_rate": 2.9353851314602676e-05,
+      "loss": 0.0528,
+      "step": 168
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.17414148151874542,
+      "learning_rate": 2.9345706507353158e-05,
+      "loss": 0.0548,
+      "step": 169
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2488938271999359,
+      "learning_rate": 2.9337511832126616e-05,
+      "loss": 0.0904,
+      "step": 170
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2884049415588379,
+      "learning_rate": 2.9329267317409053e-05,
+      "loss": 0.0721,
+      "step": 171
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.3515964150428772,
+      "learning_rate": 2.9320972991859728e-05,
+      "loss": 0.1108,
+      "step": 172
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.49220752716064453,
+      "learning_rate": 2.9312628884311048e-05,
+      "loss": 0.1056,
+      "step": 173
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1283823549747467,
+      "learning_rate": 2.9304235023768465e-05,
+      "loss": 0.062,
+      "step": 174
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.20535992085933685,
+      "learning_rate": 2.9295791439410387e-05,
+      "loss": 0.0591,
+      "step": 175
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.548753559589386,
+      "learning_rate": 2.9287298160588073e-05,
+      "loss": 0.1252,
+      "step": 176
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.17065873742103577,
+      "learning_rate": 2.927875521682551e-05,
+      "loss": 0.0717,
+      "step": 177
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.15028174221515656,
+      "learning_rate": 2.9270162637819352e-05,
+      "loss": 0.059,
+      "step": 178
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3822297751903534,
+      "learning_rate": 2.9261520453438775e-05,
+      "loss": 0.0752,
+      "step": 179
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.17701248824596405,
+      "learning_rate": 2.9252828693725404e-05,
+      "loss": 0.0872,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.1596059501171112,
+      "learning_rate": 2.9244087388893187e-05,
+      "loss": 0.051,
+      "step": 181
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.13807597756385803,
+      "learning_rate": 2.9235296569328303e-05,
+      "loss": 0.0518,
+      "step": 182
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14610590040683746,
+      "learning_rate": 2.922645626558905e-05,
+      "loss": 0.08,
+      "step": 183
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.13961593806743622,
+      "learning_rate": 2.921756650840574e-05,
+      "loss": 0.0496,
+      "step": 184
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.12945222854614258,
+      "learning_rate": 2.92086273286806e-05,
+      "loss": 0.0725,
+      "step": 185
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.16739709675312042,
+      "learning_rate": 2.9199638757487648e-05,
+      "loss": 0.0514,
+      "step": 186
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1626630425453186,
+      "learning_rate": 2.9190600826072603e-05,
+      "loss": 0.0506,
+      "step": 187
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.17024777829647064,
+      "learning_rate": 2.918151356585276e-05,
+      "loss": 0.0646,
+      "step": 188
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.12996181845664978,
+      "learning_rate": 2.9172377008416898e-05,
+      "loss": 0.0421,
+      "step": 189
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1544611155986786,
+      "learning_rate": 2.916319118552515e-05,
+      "loss": 0.0665,
+      "step": 190
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.37734368443489075,
+      "learning_rate": 2.9153956129108918e-05,
+      "loss": 0.0851,
+      "step": 191
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.28739050030708313,
+      "learning_rate": 2.9144671871270734e-05,
+      "loss": 0.0786,
+      "step": 192
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.2730344533920288,
+      "learning_rate": 2.913533844428417e-05,
+      "loss": 0.0923,
+      "step": 193
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.26277613639831543,
+      "learning_rate": 2.912595588059371e-05,
+      "loss": 0.0737,
+      "step": 194
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.15028347074985504,
+      "learning_rate": 2.9116524212814653e-05,
+      "loss": 0.0528,
+      "step": 195
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.5112478733062744,
+      "learning_rate": 2.9107043473733e-05,
+      "loss": 0.0744,
+      "step": 196
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.1651376336812973,
+      "learning_rate": 2.9097513696305304e-05,
+      "loss": 0.0421,
+      "step": 197
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.18412701785564423,
+      "learning_rate": 2.908793491365861e-05,
+      "loss": 0.0602,
+      "step": 198
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.26233047246932983,
+      "learning_rate": 2.90783071590903e-05,
+      "loss": 0.086,
+      "step": 199
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.17222779989242554,
+      "learning_rate": 2.9068630466067997e-05,
+      "loss": 0.0634,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.4317842125892639,
+      "learning_rate": 2.905890486822943e-05,
+      "loss": 0.0904,
+      "step": 201
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.1886034905910492,
+      "learning_rate": 2.9049130399382345e-05,
+      "loss": 0.0699,
+      "step": 202
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.21989533305168152,
+      "learning_rate": 2.903930709350436e-05,
+      "loss": 0.0623,
+      "step": 203
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.19172674417495728,
+      "learning_rate": 2.9029434984742866e-05,
+      "loss": 0.0956,
+      "step": 204
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.20230571925640106,
+      "learning_rate": 2.9019514107414888e-05,
+      "loss": 0.0865,
+      "step": 205
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.258619487285614,
+      "learning_rate": 2.9009544496006998e-05,
+      "loss": 0.077,
+      "step": 206
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.37927359342575073,
+      "learning_rate": 2.8999526185175155e-05,
+      "loss": 0.0955,
+      "step": 207
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.1734340786933899,
+      "learning_rate": 2.898945920974462e-05,
+      "loss": 0.0698,
+      "step": 208
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.2214702069759369,
+      "learning_rate": 2.8979343604709818e-05,
+      "loss": 0.0656,
+      "step": 209
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.13421665132045746,
+      "learning_rate": 2.8969179405234202e-05,
+      "loss": 0.0801,
+      "step": 210
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.1412036120891571,
+      "learning_rate": 2.8958966646650172e-05,
+      "loss": 0.0413,
+      "step": 211
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.14668437838554382,
+      "learning_rate": 2.894870536445891e-05,
+      "loss": 0.067,
+      "step": 212
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.17726927995681763,
+      "learning_rate": 2.893839559433028e-05,
+      "loss": 0.0572,
+      "step": 213
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.1916431039571762,
+      "learning_rate": 2.8928037372102698e-05,
+      "loss": 0.0761,
+      "step": 214
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.16705051064491272,
+      "learning_rate": 2.8917630733783004e-05,
+      "loss": 0.0604,
+      "step": 215
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.17496813833713531,
+      "learning_rate": 2.8907175715546337e-05,
+      "loss": 0.0705,
+      "step": 216
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.15736040472984314,
+      "learning_rate": 2.889667235373603e-05,
+      "loss": 0.0305,
+      "step": 217
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.274248868227005,
+      "learning_rate": 2.888612068486344e-05,
+      "loss": 0.0783,
+      "step": 218
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.24461400508880615,
+      "learning_rate": 2.887552074560787e-05,
+      "loss": 0.0643,
+      "step": 219
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.20980973541736603,
+      "learning_rate": 2.8864872572816407e-05,
+      "loss": 0.0625,
+      "step": 220
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.20946985483169556,
+      "learning_rate": 2.885417620350381e-05,
+      "loss": 0.0834,
+      "step": 221
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.16951480507850647,
+      "learning_rate": 2.8843431674852366e-05,
+      "loss": 0.0528,
+      "step": 222
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.1708109974861145,
+      "learning_rate": 2.883263902421179e-05,
+      "loss": 0.0728,
+      "step": 223
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.14461833238601685,
+      "learning_rate": 2.8821798289099054e-05,
+      "loss": 0.0421,
+      "step": 224
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.24623633921146393,
+      "learning_rate": 2.881090950719831e-05,
+      "loss": 0.0854,
+      "step": 225
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.21715879440307617,
+      "learning_rate": 2.87999727163607e-05,
+      "loss": 0.0384,
+      "step": 226
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.4943262040615082,
+      "learning_rate": 2.878898795460426e-05,
+      "loss": 0.0727,
+      "step": 227
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.21625903248786926,
+      "learning_rate": 2.8777955260113794e-05,
+      "loss": 0.0764,
+      "step": 228
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.49219760298728943,
+      "learning_rate": 2.8766874671240708e-05,
+      "loss": 0.0645,
+      "step": 229
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.48366281390190125,
+      "learning_rate": 2.8755746226502914e-05,
+      "loss": 0.0812,
+      "step": 230
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.23804642260074615,
+      "learning_rate": 2.874456996458467e-05,
+      "loss": 0.0412,
+      "step": 231
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.15954728424549103,
+      "learning_rate": 2.8733345924336448e-05,
+      "loss": 0.0319,
+      "step": 232
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.1840825229883194,
+      "learning_rate": 2.872207414477482e-05,
+      "loss": 0.0391,
+      "step": 233
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.34154170751571655,
+      "learning_rate": 2.8710754665082295e-05,
+      "loss": 0.0871,
+      "step": 234
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.28852567076683044,
+      "learning_rate": 2.8699387524607206e-05,
+      "loss": 0.0743,
+      "step": 235
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.3130442798137665,
+      "learning_rate": 2.868797276286355e-05,
+      "loss": 0.0596,
+      "step": 236
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.15511904656887054,
+      "learning_rate": 2.8676510419530875e-05,
+      "loss": 0.0345,
+      "step": 237
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.3511506915092468,
+      "learning_rate": 2.866500053445412e-05,
+      "loss": 0.0795,
+      "step": 238
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.21553099155426025,
+      "learning_rate": 2.86534431476435e-05,
+      "loss": 0.0685,
+      "step": 239
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2557514011859894,
+      "learning_rate": 2.8641838299274336e-05,
+      "loss": 0.0386,
+      "step": 240
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.22085203230381012,
+      "learning_rate": 2.863018602968695e-05,
+      "loss": 0.0741,
+      "step": 241
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.3036896884441376,
+      "learning_rate": 2.8618486379386496e-05,
+      "loss": 0.0553,
+      "step": 242
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.24089917540550232,
+      "learning_rate": 2.8606739389042838e-05,
+      "loss": 0.0699,
+      "step": 243
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.3548223376274109,
+      "learning_rate": 2.8594945099490395e-05,
+      "loss": 0.0573,
+      "step": 244
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.288339763879776,
+      "learning_rate": 2.8583103551728008e-05,
+      "loss": 0.0592,
+      "step": 245
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.3822185695171356,
+      "learning_rate": 2.857121478691881e-05,
+      "loss": 0.0788,
+      "step": 246
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.3023355305194855,
+      "learning_rate": 2.855927884639004e-05,
+      "loss": 0.08,
+      "step": 247
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.15000642836093903,
+      "learning_rate": 2.854729577163294e-05,
+      "loss": 0.053,
+      "step": 248
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.38528746366500854,
+      "learning_rate": 2.8535265604302614e-05,
+      "loss": 0.132,
+      "step": 249
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.3799440562725067,
+      "learning_rate": 2.852318838621784e-05,
+      "loss": 0.0824,
+      "step": 250
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.1958758383989334,
+      "learning_rate": 2.851106415936098e-05,
+      "loss": 0.0501,
+      "step": 251
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.47345441579818726,
+      "learning_rate": 2.8498892965877776e-05,
+      "loss": 0.076,
+      "step": 252
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.4306192398071289,
+      "learning_rate": 2.848667484807726e-05,
+      "loss": 0.0907,
+      "step": 253
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.15393877029418945,
+      "learning_rate": 2.8474409848431562e-05,
+      "loss": 0.0471,
+      "step": 254
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.1548716276884079,
+      "learning_rate": 2.8462098009575793e-05,
+      "loss": 0.0545,
+      "step": 255
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.2719079256057739,
+      "learning_rate": 2.8449739374307877e-05,
+      "loss": 0.0712,
+      "step": 256
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.14566250145435333,
+      "learning_rate": 2.8437333985588418e-05,
+      "loss": 0.0491,
+      "step": 257
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.17003220319747925,
+      "learning_rate": 2.8424881886540527e-05,
+      "loss": 0.078,
+      "step": 258
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.16778719425201416,
+      "learning_rate": 2.8412383120449707e-05,
+      "loss": 0.0688,
+      "step": 259
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.2298566699028015,
+      "learning_rate": 2.839983773076367e-05,
+      "loss": 0.0654,
+      "step": 260
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.14038778841495514,
+      "learning_rate": 2.8387245761092203e-05,
+      "loss": 0.0656,
+      "step": 261
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.2299400120973587,
+      "learning_rate": 2.8374607255207012e-05,
+      "loss": 0.0563,
+      "step": 262
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.12228001654148102,
+      "learning_rate": 2.8361922257041577e-05,
+      "loss": 0.0426,
+      "step": 263
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.2170531004667282,
+      "learning_rate": 2.8349190810690977e-05,
+      "loss": 0.0739,
+      "step": 264
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.25972139835357666,
+      "learning_rate": 2.8336412960411765e-05,
+      "loss": 0.0449,
+      "step": 265
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.16110770404338837,
+      "learning_rate": 2.8323588750621802e-05,
+      "loss": 0.0429,
+      "step": 266
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.36092159152030945,
+      "learning_rate": 2.8310718225900095e-05,
+      "loss": 0.0532,
+      "step": 267
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.13183802366256714,
+      "learning_rate": 2.8297801430986652e-05,
+      "loss": 0.0306,
+      "step": 268
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.1969520002603531,
+      "learning_rate": 2.8284838410782327e-05,
+      "loss": 0.0729,
+      "step": 269
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3288170397281647,
+      "learning_rate": 2.8271829210348657e-05,
+      "loss": 0.0657,
+      "step": 270
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.17383714020252228,
+      "learning_rate": 2.82587738749077e-05,
+      "loss": 0.0296,
+      "step": 271
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3440845310688019,
+      "learning_rate": 2.824567244984192e-05,
+      "loss": 0.055,
+      "step": 272
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5535409450531006,
+      "learning_rate": 2.8232524980693947e-05,
+      "loss": 0.0845,
+      "step": 273
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3418692946434021,
+      "learning_rate": 2.8219331513166503e-05,
+      "loss": 0.0501,
+      "step": 274
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.24258548021316528,
+      "learning_rate": 2.8206092093122195e-05,
+      "loss": 0.0572,
+      "step": 275
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.2323545515537262,
+      "learning_rate": 2.8192806766583373e-05,
+      "loss": 0.036,
+      "step": 276
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.18079668283462524,
+      "learning_rate": 2.8179475579731967e-05,
+      "loss": 0.039,
+      "step": 277
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.6126664280891418,
+      "learning_rate": 2.8166098578909315e-05,
+      "loss": 0.0964,
+      "step": 278
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.29580938816070557,
+      "learning_rate": 2.815267581061602e-05,
+      "loss": 0.0682,
+      "step": 279
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.25424325466156006,
+      "learning_rate": 2.8139207321511778e-05,
+      "loss": 0.0682,
+      "step": 280
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.20733873546123505,
+      "learning_rate": 2.8125693158415217e-05,
+      "loss": 0.0369,
+      "step": 281
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.28711849451065063,
+      "learning_rate": 2.8112133368303737e-05,
+      "loss": 0.0734,
+      "step": 282
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.18627013266086578,
+      "learning_rate": 2.809852799831334e-05,
+      "loss": 0.052,
+      "step": 283
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3224278688430786,
+      "learning_rate": 2.8084877095738477e-05,
+      "loss": 0.0973,
+      "step": 284
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.06570792198181152,
+      "eval_runtime": 14.7272,
+      "eval_samples_per_second": 32.321,
+      "eval_steps_per_second": 8.08,
+      "step": 284
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.38838616013526917,
+      "learning_rate": 2.8071180708031874e-05,
+      "loss": 0.0916,
+      "step": 285
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.24502405524253845,
+      "learning_rate": 2.8057438882804372e-05,
+      "loss": 0.0816,
+      "step": 286
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.4185783863067627,
+      "learning_rate": 2.8043651667824767e-05,
+      "loss": 0.0776,
+      "step": 287
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.2056495100259781,
+      "learning_rate": 2.8029819111019618e-05,
+      "loss": 0.0266,
+      "step": 288
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.19617842137813568,
+      "learning_rate": 2.8015941260473117e-05,
+      "loss": 0.0456,
+      "step": 289
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.3548401892185211,
+      "learning_rate": 2.8002018164426896e-05,
+      "loss": 0.0507,
+      "step": 290
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.2668496370315552,
+      "learning_rate": 2.798804987127988e-05,
+      "loss": 0.0539,
+      "step": 291
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2864347994327545,
+      "learning_rate": 2.7974036429588082e-05,
+      "loss": 0.076,
+      "step": 292
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.26988208293914795,
+      "learning_rate": 2.7959977888064484e-05,
+      "loss": 0.0599,
+      "step": 293
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.451043039560318,
+      "learning_rate": 2.7945874295578827e-05,
+      "loss": 0.0676,
+      "step": 294
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2092967927455902,
+      "learning_rate": 2.7931725701157462e-05,
+      "loss": 0.0653,
+      "step": 295
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.25097522139549255,
+      "learning_rate": 2.7917532153983176e-05,
+      "loss": 0.086,
+      "step": 296
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.1981886476278305,
+      "learning_rate": 2.790329370339501e-05,
+      "loss": 0.0616,
+      "step": 297
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.20687969028949738,
+      "learning_rate": 2.7889010398888104e-05,
+      "loss": 0.0479,
+      "step": 298
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.16657814383506775,
+      "learning_rate": 2.7874682290113514e-05,
+      "loss": 0.0432,
+      "step": 299
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.1697748750448227,
+      "learning_rate": 2.786030942687805e-05,
+      "loss": 0.0624,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.17153337597846985,
+      "learning_rate": 2.7845891859144088e-05,
+      "loss": 0.035,
+      "step": 301
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.20956017076969147,
+      "learning_rate": 2.7831429637029402e-05,
+      "loss": 0.0468,
+      "step": 302
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.1893073171377182,
+      "learning_rate": 2.7816922810807e-05,
+      "loss": 0.0783,
+      "step": 303
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.24053029716014862,
+      "learning_rate": 2.7802371430904936e-05,
+      "loss": 0.0534,
+      "step": 304
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.15913282334804535,
+      "learning_rate": 2.7787775547906142e-05,
+      "loss": 0.0478,
+      "step": 305
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.3303963840007782,
+      "learning_rate": 2.7773135212548247e-05,
+      "loss": 0.0698,
+      "step": 306
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.2255176603794098,
+      "learning_rate": 2.7758450475723405e-05,
+      "loss": 0.0345,
+      "step": 307
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.20534120500087738,
+      "learning_rate": 2.774372138847812e-05,
+      "loss": 0.0668,
+      "step": 308
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.25963813066482544,
+      "learning_rate": 2.7728948002013054e-05,
+      "loss": 0.0741,
+      "step": 309
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.2108840048313141,
+      "learning_rate": 2.771413036768288e-05,
+      "loss": 0.0691,
+      "step": 310
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.18770939111709595,
+      "learning_rate": 2.769926853699606e-05,
+      "loss": 0.0701,
+      "step": 311
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.1566968858242035,
+      "learning_rate": 2.7684362561614714e-05,
+      "loss": 0.0196,
+      "step": 312
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.3223302364349365,
+      "learning_rate": 2.766941249335439e-05,
+      "loss": 0.0752,
+      "step": 313
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.21899370849132538,
+      "learning_rate": 2.765441838418393e-05,
+      "loss": 0.0703,
+      "step": 314
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.21244989335536957,
+      "learning_rate": 2.7639380286225264e-05,
+      "loss": 0.0672,
+      "step": 315
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.19558708369731903,
+      "learning_rate": 2.7624298251753232e-05,
+      "loss": 0.042,
+      "step": 316
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2814396917819977,
+      "learning_rate": 2.7609172333195406e-05,
+      "loss": 0.0434,
+      "step": 317
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2828751504421234,
+      "learning_rate": 2.75940025831319e-05,
+      "loss": 0.047,
+      "step": 318
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.18190258741378784,
+      "learning_rate": 2.7578789054295202e-05,
+      "loss": 0.0619,
+      "step": 319
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.16573399305343628,
+      "learning_rate": 2.7563531799569984e-05,
+      "loss": 0.0681,
+      "step": 320
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.23267892003059387,
+      "learning_rate": 2.75482308719929e-05,
+      "loss": 0.0518,
+      "step": 321
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.21713323891162872,
+      "learning_rate": 2.753288632475244e-05,
+      "loss": 0.0437,
+      "step": 322
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.26459431648254395,
+      "learning_rate": 2.75174982111887e-05,
+      "loss": 0.0616,
+      "step": 323
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.5927810668945312,
+      "learning_rate": 2.7502066584793243e-05,
+      "loss": 0.0931,
+      "step": 324
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.32426661252975464,
+      "learning_rate": 2.7486591499208867e-05,
+      "loss": 0.08,
+      "step": 325
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.18653956055641174,
+      "learning_rate": 2.7471073008229462e-05,
+      "loss": 0.0679,
+      "step": 326
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.3730272948741913,
+      "learning_rate": 2.7455511165799783e-05,
+      "loss": 0.0399,
+      "step": 327
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.2434634417295456,
+      "learning_rate": 2.7439906026015297e-05,
+      "loss": 0.0608,
+      "step": 328
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.27506130933761597,
+      "learning_rate": 2.742425764312197e-05,
+      "loss": 0.0586,
+      "step": 329
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.2162889540195465,
+      "learning_rate": 2.7408566071516087e-05,
+      "loss": 0.0587,
+      "step": 330
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.2727173864841461,
+      "learning_rate": 2.7392831365744074e-05,
+      "loss": 0.0774,
+      "step": 331
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.2565726339817047,
+      "learning_rate": 2.7377053580502298e-05,
+      "loss": 0.0961,
+      "step": 332
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.2756386995315552,
+      "learning_rate": 2.7361232770636856e-05,
+      "loss": 0.0465,
+      "step": 333
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.30874213576316833,
+      "learning_rate": 2.7345368991143433e-05,
+      "loss": 0.0908,
+      "step": 334
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.21297310292720795,
+      "learning_rate": 2.732946229716707e-05,
+      "loss": 0.0822,
+      "step": 335
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.21286709606647491,
+      "learning_rate": 2.7313512744001982e-05,
+      "loss": 0.0916,
+      "step": 336
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.18058332800865173,
+      "learning_rate": 2.7297520387091376e-05,
+      "loss": 0.0459,
+      "step": 337
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.1574922353029251,
+      "learning_rate": 2.7281485282027252e-05,
+      "loss": 0.048,
+      "step": 338
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.1783793717622757,
+      "learning_rate": 2.7265407484550206e-05,
+      "loss": 0.0733,
+      "step": 339
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.17018386721611023,
+      "learning_rate": 2.724928705054924e-05,
+      "loss": 0.064,
+      "step": 340
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.12130982428789139,
+      "learning_rate": 2.7233124036061575e-05,
+      "loss": 0.0603,
+      "step": 341
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.19916939735412598,
+      "learning_rate": 2.7216918497272426e-05,
+      "loss": 0.0885,
+      "step": 342
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.23629699647426605,
+      "learning_rate": 2.7200670490514865e-05,
+      "loss": 0.0696,
+      "step": 343
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.1870480626821518,
+      "learning_rate": 2.7184380072269558e-05,
+      "loss": 0.0797,
+      "step": 344
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.22087708115577698,
+      "learning_rate": 2.7168047299164614e-05,
+      "loss": 0.0755,
+      "step": 345
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.17880262434482574,
+      "learning_rate": 2.7151672227975377e-05,
+      "loss": 0.0582,
+      "step": 346
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.15626394748687744,
+      "learning_rate": 2.7135254915624213e-05,
+      "loss": 0.072,
+      "step": 347
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.11785972118377686,
+      "learning_rate": 2.711879541918034e-05,
+      "loss": 0.0515,
+      "step": 348
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.13664838671684265,
+      "learning_rate": 2.71022937958596e-05,
+      "loss": 0.0542,
+      "step": 349
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.22781230509281158,
+      "learning_rate": 2.7085750103024296e-05,
+      "loss": 0.1037,
+      "step": 350
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.1862461417913437,
+      "learning_rate": 2.7069164398182948e-05,
+      "loss": 0.0617,
+      "step": 351
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.315283864736557,
+      "learning_rate": 2.7052536738990125e-05,
+      "loss": 0.0756,
+      "step": 352
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.22472089529037476,
+      "learning_rate": 2.7035867183246247e-05,
+      "loss": 0.0792,
+      "step": 353
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.1294025033712387,
+      "learning_rate": 2.7019155788897357e-05,
+      "loss": 0.0738,
+      "step": 354
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2340669184923172,
+      "learning_rate": 2.700240261403494e-05,
+      "loss": 0.0925,
+      "step": 355
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.27781906723976135,
+      "learning_rate": 2.6985607716895727e-05,
+      "loss": 0.0793,
+      "step": 356
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.18572118878364563,
+      "learning_rate": 2.6968771155861464e-05,
+      "loss": 0.065,
+      "step": 357
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2246127426624298,
+      "learning_rate": 2.695189298945875e-05,
+      "loss": 0.0825,
+      "step": 358
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.23202070593833923,
+      "learning_rate": 2.6934973276358792e-05,
+      "loss": 0.0598,
+      "step": 359
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.16124321520328522,
+      "learning_rate": 2.6918012075377226e-05,
+      "loss": 0.0825,
+      "step": 360
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.15348608791828156,
+      "learning_rate": 2.6901009445473912e-05,
+      "loss": 0.0442,
+      "step": 361
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.18639832735061646,
+      "learning_rate": 2.6883965445752714e-05,
+      "loss": 0.0699,
+      "step": 362
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2920565605163574,
+      "learning_rate": 2.6866880135461314e-05,
+      "loss": 0.0798,
+      "step": 363
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.16075679659843445,
+      "learning_rate": 2.684975357399099e-05,
+      "loss": 0.0691,
+      "step": 364
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.17678283154964447,
+      "learning_rate": 2.683258582087641e-05,
+      "loss": 0.0386,
+      "step": 365
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.4795132875442505,
+      "learning_rate": 2.681537693579545e-05,
+      "loss": 0.0988,
+      "step": 366
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.18269479274749756,
+      "learning_rate": 2.6798126978568942e-05,
+      "loss": 0.074,
+      "step": 367
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.2764766812324524,
+      "learning_rate": 2.6780836009160514e-05,
+      "loss": 0.0565,
+      "step": 368
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.19089283049106598,
+      "learning_rate": 2.6763504087676346e-05,
+      "loss": 0.0389,
+      "step": 369
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.15806300938129425,
+      "learning_rate": 2.674613127436498e-05,
+      "loss": 0.0482,
+      "step": 370
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.2809430658817291,
+      "learning_rate": 2.6728717629617093e-05,
+      "loss": 0.0429,
+      "step": 371
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.12930545210838318,
+      "learning_rate": 2.671126321396532e-05,
+      "loss": 0.0255,
+      "step": 372
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.17408722639083862,
+      "learning_rate": 2.6693768088083994e-05,
+      "loss": 0.0703,
+      "step": 373
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.3387722671031952,
+      "learning_rate": 2.6676232312788998e-05,
+      "loss": 0.0569,
+      "step": 374
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.25352975726127625,
+      "learning_rate": 2.6658655949037482e-05,
+      "loss": 0.0914,
+      "step": 375
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.3007981777191162,
+      "learning_rate": 2.6641039057927724e-05,
+      "loss": 0.0502,
+      "step": 376
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.20817789435386658,
+      "learning_rate": 2.662338170069885e-05,
+      "loss": 0.0408,
+      "step": 377
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.15569907426834106,
+      "learning_rate": 2.6605683938730666e-05,
+      "loss": 0.029,
+      "step": 378
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.25259971618652344,
+      "learning_rate": 2.6587945833543432e-05,
+      "loss": 0.0336,
+      "step": 379
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.13589264452457428,
+      "learning_rate": 2.6570167446797657e-05,
+      "loss": 0.0218,
+      "step": 380
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.34168577194213867,
+      "learning_rate": 2.6552348840293856e-05,
+      "loss": 0.0882,
+      "step": 381
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.26590269804000854,
+      "learning_rate": 2.6534490075972368e-05,
+      "loss": 0.0576,
+      "step": 382
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.2801959812641144,
+      "learning_rate": 2.6516591215913118e-05,
+      "loss": 0.0586,
+      "step": 383
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.3427751660346985,
+      "learning_rate": 2.6498652322335416e-05,
+      "loss": 0.0575,
+      "step": 384
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5352123975753784,
+      "learning_rate": 2.6480673457597737e-05,
+      "loss": 0.0915,
+      "step": 385
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.45933809876441956,
+      "learning_rate": 2.646265468419749e-05,
+      "loss": 0.0865,
+      "step": 386
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.14740170538425446,
+      "learning_rate": 2.6444596064770837e-05,
+      "loss": 0.0447,
+      "step": 387
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.18046963214874268,
+      "learning_rate": 2.6426497662092424e-05,
+      "loss": 0.0302,
+      "step": 388
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2271748036146164,
+      "learning_rate": 2.6408359539075204e-05,
+      "loss": 0.067,
+      "step": 389
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.345716267824173,
+      "learning_rate": 2.6390181758770208e-05,
+      "loss": 0.0461,
+      "step": 390
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2197301983833313,
+      "learning_rate": 2.6371964384366305e-05,
+      "loss": 0.0252,
+      "step": 391
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2628111243247986,
+      "learning_rate": 2.6353707479190022e-05,
+      "loss": 0.0616,
+      "step": 392
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.41908586025238037,
+      "learning_rate": 2.6335411106705283e-05,
+      "loss": 0.0599,
+      "step": 393
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.13220524787902832,
+      "learning_rate": 2.6317075330513212e-05,
+      "loss": 0.0116,
+      "step": 394
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.21840068697929382,
+      "learning_rate": 2.6298700214351922e-05,
+      "loss": 0.0413,
+      "step": 395
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.3715525269508362,
+      "learning_rate": 2.628028582209625e-05,
+      "loss": 0.0643,
+      "step": 396
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.21229352056980133,
+      "learning_rate": 2.626183221775758e-05,
+      "loss": 0.0369,
+      "step": 397
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.3171239495277405,
+      "learning_rate": 2.6243339465483605e-05,
+      "loss": 0.0712,
+      "step": 398
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.33259809017181396,
+      "learning_rate": 2.6224807629558094e-05,
+      "loss": 0.1066,
+      "step": 399
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.14465388655662537,
+      "learning_rate": 2.6206236774400684e-05,
+      "loss": 0.034,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.5533297061920166,
+      "learning_rate": 2.6187626964566644e-05,
+      "loss": 0.1046,
+      "step": 401
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.17661869525909424,
+      "learning_rate": 2.6168978264746663e-05,
+      "loss": 0.0322,
+      "step": 402
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.19023488461971283,
+      "learning_rate": 2.615029073976661e-05,
+      "loss": 0.0493,
+      "step": 403
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.1495324969291687,
+      "learning_rate": 2.6131564454587316e-05,
+      "loss": 0.0404,
+      "step": 404
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.20712687075138092,
+      "learning_rate": 2.611279947430436e-05,
+      "loss": 0.0472,
+      "step": 405
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.233810156583786,
+      "learning_rate": 2.609399586414782e-05,
+      "loss": 0.0424,
+      "step": 406
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.14824284613132477,
+      "learning_rate": 2.607515368948206e-05,
+      "loss": 0.0318,
+      "step": 407
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.3361953794956207,
+      "learning_rate": 2.60562730158055e-05,
+      "loss": 0.0763,
+      "step": 408
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.2170048952102661,
+      "learning_rate": 2.6037353908750394e-05,
+      "loss": 0.0643,
+      "step": 409
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.18919886648654938,
+      "learning_rate": 2.601839643408259e-05,
+      "loss": 0.0583,
+      "step": 410
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.42277276515960693,
+      "learning_rate": 2.5999400657701314e-05,
+      "loss": 0.0698,
+      "step": 411
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.25986483693122864,
+      "learning_rate": 2.598036664563893e-05,
+      "loss": 0.041,
+      "step": 412
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.2869338095188141,
+      "learning_rate": 2.596129446406072e-05,
+      "loss": 0.0503,
+      "step": 413
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.41842973232269287,
+      "learning_rate": 2.594218417926464e-05,
+      "loss": 0.0786,
+      "step": 414
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.4030296504497528,
+      "learning_rate": 2.592303585768111e-05,
+      "loss": 0.067,
+      "step": 415
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.31492769718170166,
+      "learning_rate": 2.590384956587277e-05,
+      "loss": 0.0479,
+      "step": 416
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.5827561020851135,
+      "learning_rate": 2.5884625370534242e-05,
+      "loss": 0.1315,
+      "step": 417
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.30939584970474243,
+      "learning_rate": 2.5865363338491916e-05,
+      "loss": 0.0759,
+      "step": 418
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.20597557723522186,
+      "learning_rate": 2.5846063536703706e-05,
+      "loss": 0.0739,
+      "step": 419
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.31797170639038086,
+      "learning_rate": 2.582672603225882e-05,
+      "loss": 0.0892,
+      "step": 420
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.4155197739601135,
+      "learning_rate": 2.5807350892377517e-05,
+      "loss": 0.13,
+      "step": 421
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.14263832569122314,
+      "learning_rate": 2.5787938184410902e-05,
+      "loss": 0.0489,
+      "step": 422
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.1489766389131546,
+      "learning_rate": 2.5768487975840655e-05,
+      "loss": 0.0638,
+      "step": 423
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.30038881301879883,
+      "learning_rate": 2.5749000334278825e-05,
+      "loss": 0.0455,
+      "step": 424
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.2359144389629364,
+      "learning_rate": 2.572947532746758e-05,
+      "loss": 0.0822,
+      "step": 425
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.16958381235599518,
+      "learning_rate": 2.570991302327897e-05,
+      "loss": 0.0454,
+      "step": 426
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.0626850351691246,
+      "eval_runtime": 14.7469,
+      "eval_samples_per_second": 32.278,
+      "eval_steps_per_second": 8.07,
+      "step": 426
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.40241333842277527,
+      "learning_rate": 2.569031348971471e-05,
+      "loss": 0.0926,
+      "step": 427
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.2126995176076889,
+      "learning_rate": 2.5670676794905915e-05,
+      "loss": 0.085,
+      "step": 428
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1960797905921936,
+      "learning_rate": 2.5651003007112892e-05,
+      "loss": 0.0853,
+      "step": 429
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.13784633576869965,
+      "learning_rate": 2.5631292194724883e-05,
+      "loss": 0.0453,
+      "step": 430
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.14578142762184143,
+      "learning_rate": 2.561154442625983e-05,
+      "loss": 0.0765,
+      "step": 431
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.14827878773212433,
+      "learning_rate": 2.559175977036415e-05,
+      "loss": 0.0594,
+      "step": 432
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.19840463995933533,
+      "learning_rate": 2.5571938295812476e-05,
+      "loss": 0.0692,
+      "step": 433
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.11538412421941757,
+      "learning_rate": 2.555208007150743e-05,
+      "loss": 0.067,
+      "step": 434
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.3484029173851013,
+      "learning_rate": 2.553218516647939e-05,
+      "loss": 0.0799,
+      "step": 435
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.20653250813484192,
+      "learning_rate": 2.5512253649886237e-05,
+      "loss": 0.0741,
+      "step": 436
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.18202582001686096,
+      "learning_rate": 2.5492285591013118e-05,
+      "loss": 0.0636,
+      "step": 437
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.17838889360427856,
+      "learning_rate": 2.5472281059272213e-05,
+      "loss": 0.067,
+      "step": 438
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.2804567217826843,
+      "learning_rate": 2.5452240124202477e-05,
+      "loss": 0.0795,
+      "step": 439
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1692652553319931,
+      "learning_rate": 2.5432162855469422e-05,
+      "loss": 0.0722,
+      "step": 440
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1247120052576065,
+      "learning_rate": 2.5412049322864847e-05,
+      "loss": 0.0332,
+      "step": 441
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1898394376039505,
+      "learning_rate": 2.539189959630662e-05,
+      "loss": 0.055,
+      "step": 442
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.20923753082752228,
+      "learning_rate": 2.537171374583843e-05,
+      "loss": 0.0728,
+      "step": 443
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.1551828235387802,
+      "learning_rate": 2.535149184162952e-05,
+      "loss": 0.0629,
+      "step": 444
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.1762448400259018,
+      "learning_rate": 2.533123395397448e-05,
+      "loss": 0.0673,
+      "step": 445
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.12544862926006317,
+      "learning_rate": 2.5310940153292978e-05,
+      "loss": 0.0311,
+      "step": 446
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.15880614519119263,
+      "learning_rate": 2.5290610510129518e-05,
+      "loss": 0.0402,
+      "step": 447
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.17256905138492584,
+      "learning_rate": 2.5270245095153198e-05,
+      "loss": 0.0633,
+      "step": 448
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.1660386472940445,
+      "learning_rate": 2.524984397915747e-05,
+      "loss": 0.077,
+      "step": 449
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.13268114626407623,
+      "learning_rate": 2.5229407233059887e-05,
+      "loss": 0.0426,
+      "step": 450
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.2337772697210312,
+      "learning_rate": 2.5208934927901857e-05,
+      "loss": 0.0836,
+      "step": 451
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.13446028530597687,
+      "learning_rate": 2.5188427134848395e-05,
+      "loss": 0.0382,
+      "step": 452
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.18553531169891357,
+      "learning_rate": 2.5167883925187878e-05,
+      "loss": 0.0548,
+      "step": 453
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.25128498673439026,
+      "learning_rate": 2.51473053703318e-05,
+      "loss": 0.0766,
+      "step": 454
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.1686338186264038,
+      "learning_rate": 2.5126691541814518e-05,
+      "loss": 0.0434,
+      "step": 455
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.18022535741329193,
+      "learning_rate": 2.510604251129301e-05,
+      "loss": 0.0688,
+      "step": 456
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.17681004106998444,
+      "learning_rate": 2.5085358350546612e-05,
+      "loss": 0.0533,
+      "step": 457
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.2677585482597351,
+      "learning_rate": 2.506463913147679e-05,
+      "loss": 0.0818,
+      "step": 458
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.5509142875671387,
+      "learning_rate": 2.5043884926106873e-05,
+      "loss": 0.1005,
+      "step": 459
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.14625947177410126,
+      "learning_rate": 2.5023095806581802e-05,
+      "loss": 0.0426,
+      "step": 460
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.3046765923500061,
+      "learning_rate": 2.5002271845167896e-05,
+      "loss": 0.0515,
+      "step": 461
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.16383983194828033,
+      "learning_rate": 2.4981413114252588e-05,
+      "loss": 0.0455,
+      "step": 462
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.3099363148212433,
+      "learning_rate": 2.4960519686344168e-05,
+      "loss": 0.0924,
+      "step": 463
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.25622445344924927,
+      "learning_rate": 2.4939591634071544e-05,
+      "loss": 0.0737,
+      "step": 464
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.21525193750858307,
+      "learning_rate": 2.491862903018398e-05,
+      "loss": 0.0816,
+      "step": 465
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.18544378876686096,
+      "learning_rate": 2.4897631947550857e-05,
+      "loss": 0.0453,
+      "step": 466
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.15406207740306854,
+      "learning_rate": 2.4876600459161397e-05,
+      "loss": 0.0477,
+      "step": 467
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.21517229080200195,
+      "learning_rate": 2.4855534638124427e-05,
+      "loss": 0.0467,
+      "step": 468
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.27017998695373535,
+      "learning_rate": 2.4834434557668126e-05,
+      "loss": 0.0593,
+      "step": 469
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.24762241542339325,
+      "learning_rate": 2.4813300291139754e-05,
+      "loss": 0.0587,
+      "step": 470
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.29878756403923035,
+      "learning_rate": 2.4792131912005407e-05,
+      "loss": 0.0635,
+      "step": 471
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.18735036253929138,
+      "learning_rate": 2.4770929493849773e-05,
+      "loss": 0.0312,
+      "step": 472
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.27927571535110474,
+      "learning_rate": 2.4749693110375856e-05,
+      "loss": 0.0668,
+      "step": 473
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.19749711453914642,
+      "learning_rate": 2.4728422835404735e-05,
+      "loss": 0.0321,
+      "step": 474
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.12730471789836884,
+      "learning_rate": 2.4707118742875293e-05,
+      "loss": 0.0183,
+      "step": 475
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.2711328864097595,
+      "learning_rate": 2.4685780906843975e-05,
+      "loss": 0.0677,
+      "step": 476
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.26742562651634216,
+      "learning_rate": 2.4664409401484522e-05,
+      "loss": 0.0617,
+      "step": 477
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.5431042313575745,
+      "learning_rate": 2.4643004301087716e-05,
+      "loss": 0.1233,
+      "step": 478
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.13498014211654663,
+      "learning_rate": 2.462156568006112e-05,
+      "loss": 0.0268,
+      "step": 479
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.22139033675193787,
+      "learning_rate": 2.4600093612928812e-05,
+      "loss": 0.0493,
+      "step": 480
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.15270984172821045,
+      "learning_rate": 2.457858817433115e-05,
+      "loss": 0.0255,
+      "step": 481
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.158059224486351,
+      "learning_rate": 2.4557049439024488e-05,
+      "loss": 0.0574,
+      "step": 482
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.17642827332019806,
+      "learning_rate": 2.4535477481880923e-05,
+      "loss": 0.0351,
+      "step": 483
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.1525094211101532,
+      "learning_rate": 2.451387237788804e-05,
+      "loss": 0.0242,
+      "step": 484
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.21704228222370148,
+      "learning_rate": 2.4492234202148643e-05,
+      "loss": 0.0582,
+      "step": 485
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.2657334804534912,
+      "learning_rate": 2.44705630298805e-05,
+      "loss": 0.0458,
+      "step": 486
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.23600801825523376,
+      "learning_rate": 2.4448858936416093e-05,
+      "loss": 0.0447,
+      "step": 487
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.20092691481113434,
+      "learning_rate": 2.442712199720232e-05,
+      "loss": 0.0462,
+      "step": 488
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.23618610203266144,
+      "learning_rate": 2.4405352287800268e-05,
+      "loss": 0.0383,
+      "step": 489
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.18307435512542725,
+      "learning_rate": 2.4383549883884954e-05,
+      "loss": 0.0312,
+      "step": 490
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.20053623616695404,
+      "learning_rate": 2.4361714861245017e-05,
+      "loss": 0.0352,
+      "step": 491
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.23183472454547882,
+      "learning_rate": 2.4339847295782508e-05,
+      "loss": 0.0445,
+      "step": 492
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.554999589920044,
+      "learning_rate": 2.431794726351258e-05,
+      "loss": 0.1143,
+      "step": 493
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.3061026334762573,
+      "learning_rate": 2.4296014840563266e-05,
+      "loss": 0.0488,
+      "step": 494
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.23472747206687927,
+      "learning_rate": 2.4274050103175195e-05,
+      "loss": 0.0549,
+      "step": 495
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.36875736713409424,
+      "learning_rate": 2.42520531277013e-05,
+      "loss": 0.0472,
+      "step": 496
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.3055475950241089,
+      "learning_rate": 2.423002399060661e-05,
+      "loss": 0.0485,
+      "step": 497
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.33722659945487976,
+      "learning_rate": 2.420796276846793e-05,
+      "loss": 0.1004,
+      "step": 498
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.3110818862915039,
+      "learning_rate": 2.4185869537973613e-05,
+      "loss": 0.0893,
+      "step": 499
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.5243550539016724,
+      "learning_rate": 2.4163744375923272e-05,
+      "loss": 0.0742,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.18637774884700775,
+      "learning_rate": 2.4141587359227514e-05,
+      "loss": 0.0453,
+      "step": 501
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.11755359172821045,
+      "learning_rate": 2.4119398564907685e-05,
+      "loss": 0.0236,
+      "step": 502
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.145331472158432,
+      "learning_rate": 2.4097178070095602e-05,
+      "loss": 0.0432,
+      "step": 503
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.1340416669845581,
+      "learning_rate": 2.4074925952033263e-05,
+      "loss": 0.0339,
+      "step": 504
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.2009749859571457,
+      "learning_rate": 2.4052642288072594e-05,
+      "loss": 0.033,
+      "step": 505
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.25946885347366333,
+      "learning_rate": 2.4030327155675192e-05,
+      "loss": 0.0618,
+      "step": 506
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.338084876537323,
+      "learning_rate": 2.4007980632412034e-05,
+      "loss": 0.076,
+      "step": 507
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.16105656325817108,
+      "learning_rate": 2.398560279596323e-05,
+      "loss": 0.055,
+      "step": 508
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2381068766117096,
+      "learning_rate": 2.3963193724117715e-05,
+      "loss": 0.0847,
+      "step": 509
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.148463174700737,
+      "learning_rate": 2.394075349477302e-05,
+      "loss": 0.0404,
+      "step": 510
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.359811007976532,
+      "learning_rate": 2.3918282185934986e-05,
+      "loss": 0.0508,
+      "step": 511
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.2325233817100525,
+      "learning_rate": 2.3895779875717486e-05,
+      "loss": 0.0594,
+      "step": 512
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.18048043549060822,
+      "learning_rate": 2.3873246642342163e-05,
+      "loss": 0.0267,
+      "step": 513
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.14463412761688232,
+      "learning_rate": 2.3850682564138145e-05,
+      "loss": 0.0519,
+      "step": 514
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.17916260659694672,
+      "learning_rate": 2.3828087719541787e-05,
+      "loss": 0.0535,
+      "step": 515
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.2539409399032593,
+      "learning_rate": 2.3805462187096402e-05,
+      "loss": 0.0579,
+      "step": 516
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.20096299052238464,
+      "learning_rate": 2.3782806045451963e-05,
+      "loss": 0.0581,
+      "step": 517
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.15366317331790924,
+      "learning_rate": 2.376011937336485e-05,
+      "loss": 0.0392,
+      "step": 518
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.28773725032806396,
+      "learning_rate": 2.373740224969758e-05,
+      "loss": 0.1054,
+      "step": 519
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.18706980347633362,
+      "learning_rate": 2.371465475341852e-05,
+      "loss": 0.0422,
+      "step": 520
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.263085275888443,
+      "learning_rate": 2.369187696360161e-05,
+      "loss": 0.0533,
+      "step": 521
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.35978153347969055,
+      "learning_rate": 2.3669068959426107e-05,
+      "loss": 0.0871,
+      "step": 522
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.3314432203769684,
+      "learning_rate": 2.364623082017629e-05,
+      "loss": 0.0481,
+      "step": 523
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.19833628833293915,
+      "learning_rate": 2.3623362625241193e-05,
+      "loss": 0.0563,
+      "step": 524
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.17452682554721832,
+      "learning_rate": 2.3600464454114326e-05,
+      "loss": 0.0464,
+      "step": 525
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.24458369612693787,
+      "learning_rate": 2.3577536386393416e-05,
+      "loss": 0.0722,
+      "step": 526
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.309350848197937,
+      "learning_rate": 2.35545785017801e-05,
+      "loss": 0.0794,
+      "step": 527
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.42290210723876953,
+      "learning_rate": 2.3531590880079663e-05,
+      "loss": 0.0753,
+      "step": 528
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1993589699268341,
+      "learning_rate": 2.3508573601200767e-05,
+      "loss": 0.0589,
+      "step": 529
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1793728619813919,
+      "learning_rate": 2.348552674515517e-05,
+      "loss": 0.0587,
+      "step": 530
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1571635901927948,
+      "learning_rate": 2.3462450392057437e-05,
+      "loss": 0.0427,
+      "step": 531
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.2197573184967041,
+      "learning_rate": 2.343934462212467e-05,
+      "loss": 0.0569,
+      "step": 532
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1468045711517334,
+      "learning_rate": 2.341620951567624e-05,
+      "loss": 0.0501,
+      "step": 533
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.1460326462984085,
+      "learning_rate": 2.339304515313348e-05,
+      "loss": 0.0446,
+      "step": 534
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.20360475778579712,
+      "learning_rate": 2.3369851615019436e-05,
+      "loss": 0.056,
+      "step": 535
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.17234598100185394,
+      "learning_rate": 2.3346628981958565e-05,
+      "loss": 0.0493,
+      "step": 536
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.21084345877170563,
+      "learning_rate": 2.332337733467646e-05,
+      "loss": 0.0781,
+      "step": 537
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.15120622515678406,
+      "learning_rate": 2.3300096753999585e-05,
+      "loss": 0.0508,
+      "step": 538
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.19097232818603516,
+      "learning_rate": 2.3276787320854967e-05,
+      "loss": 0.0558,
+      "step": 539
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.14518237113952637,
+      "learning_rate": 2.3253449116269937e-05,
+      "loss": 0.0363,
+      "step": 540
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.38005223870277405,
+      "learning_rate": 2.3230082221371834e-05,
+      "loss": 0.1022,
+      "step": 541
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.15401460230350494,
+      "learning_rate": 2.3206686717387742e-05,
+      "loss": 0.0745,
+      "step": 542
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.15603908896446228,
+      "learning_rate": 2.3183262685644177e-05,
+      "loss": 0.035,
+      "step": 543
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.17525097727775574,
+      "learning_rate": 2.3159810207566832e-05,
+      "loss": 0.0584,
+      "step": 544
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.17069534957408905,
+      "learning_rate": 2.3136329364680288e-05,
+      "loss": 0.0569,
+      "step": 545
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.3221694231033325,
+      "learning_rate": 2.3112820238607716e-05,
+      "loss": 0.0878,
+      "step": 546
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2566680908203125,
+      "learning_rate": 2.3089282911070613e-05,
+      "loss": 0.0394,
+      "step": 547
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.17850065231323242,
+      "learning_rate": 2.3065717463888505e-05,
+      "loss": 0.0351,
+      "step": 548
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.25362351536750793,
+      "learning_rate": 2.3042123978978665e-05,
+      "loss": 0.0596,
+      "step": 549
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.20955722033977509,
+      "learning_rate": 2.3018502538355827e-05,
+      "loss": 0.0534,
+      "step": 550
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.19723302125930786,
+      "learning_rate": 2.2994853224131915e-05,
+      "loss": 0.0674,
+      "step": 551
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2044544219970703,
+      "learning_rate": 2.2971176118515734e-05,
+      "loss": 0.0505,
+      "step": 552
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2544882893562317,
+      "learning_rate": 2.2947471303812708e-05,
+      "loss": 0.0967,
+      "step": 553
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.16680030524730682,
+      "learning_rate": 2.2923738862424565e-05,
+      "loss": 0.0395,
+      "step": 554
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.27806153893470764,
+      "learning_rate": 2.2899978876849084e-05,
+      "loss": 0.0788,
+      "step": 555
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1830155849456787,
+      "learning_rate": 2.287619142967979e-05,
+      "loss": 0.0538,
+      "step": 556
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.33155858516693115,
+      "learning_rate": 2.285237660360566e-05,
+      "loss": 0.0417,
+      "step": 557
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2150736302137375,
+      "learning_rate": 2.2828534481410847e-05,
+      "loss": 0.0396,
+      "step": 558
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2404957413673401,
+      "learning_rate": 2.28046651459744e-05,
+      "loss": 0.0554,
+      "step": 559
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.22239123284816742,
+      "learning_rate": 2.278076868026995e-05,
+      "loss": 0.0592,
+      "step": 560
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.24049235880374908,
+      "learning_rate": 2.2756845167365452e-05,
+      "loss": 0.0462,
+      "step": 561
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.24881111085414886,
+      "learning_rate": 2.273289469042287e-05,
+      "loss": 0.0483,
+      "step": 562
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5261463522911072,
+      "learning_rate": 2.2708917332697908e-05,
+      "loss": 0.0748,
+      "step": 563
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3064204752445221,
+      "learning_rate": 2.26849131775397e-05,
+      "loss": 0.0532,
+      "step": 564
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6424417495727539,
+      "learning_rate": 2.2660882308390547e-05,
+      "loss": 0.1566,
+      "step": 565
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1695,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 565,
+  "total_flos": 5.277457624072192e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-565/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2222c6d9f6232f31ff9a258358b395f70d592023a50d4056572ccf3372d2fda1
+size 5752

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}