Upload folder using huggingface_hub

README.md

@@ -0,0 +1,159 @@
+---
+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/1e-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_cn.json
+  - 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/CN/toxi/3e-5/
+output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/toxi/1e-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: 0.00001
+
+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/1e-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: 0.0540
+
+## 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: 1e-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          |
+| 0.0881        | 0.25  | 142  | 0.0819          |
+| 0.1131        | 0.5   | 284  | 0.0763          |
+| 0.0538        | 0.75  | 426  | 0.0732          |
+| 0.0425        | 1.0   | 568  | 0.0656          |
+| 0.0866        | 1.26  | 710  | 0.0582          |
+| 0.0705        | 1.51  | 852  | 0.0593          |
+| 0.0848        | 1.76  | 994  | 0.0562          |
+| 0.0631        | 2.01  | 1136 | 0.0552          |
+| 0.0299        | 2.26  | 1278 | 0.0551          |
+| 0.0494        | 2.51  | 1420 | 0.0545          |
+| 0.0417        | 2.76  | 1562 | 0.0540          |
+
+
+### 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": [
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_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 sha256:9c4f1dfe64a64e487f2cc8ec6cec5df1f706187bbf9e0421a6c3c72e2647407d
+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": [
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_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 sha256:2169609e4e111e205423af6669bcf745f2d4ffb7fe04d98fe4c9b494d80ed181
+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:a0e0675f0ab9875f1d79a804457d8974c62eea898d5703d28d64c9ab05744fbf
+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:e62998afaa8578d5258681d029fbfb3a81f919238169575bd2ab994d0eec64b3
+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 sha256:2667f02973c48c9daa1abbdc506826bb40abce66f6990081fb40359affcf7486
+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": [
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_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 sha256:3e0f3e305fe591b78c617c06319c2ef07c876302a05b6af2df8f349ca4803106
+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 sha256:4aa4589166256b5978ed67bf82a78d6c49a8b02bade043cc00530243a007c003
+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:cd718d8885c7b195217779b1c1603102771881de6f058bded44d4708de1787e5
+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 sha256:2667f02973c48c9daa1abbdc506826bb40abce66f6990081fb40359affcf7486
+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": [
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_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 sha256:0edcdb94705d8a049cc8f634d50e739abdd88ba64f53a8f51aecaa8ade2ac167
+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:c91cc2cdf808e6b860d36ebc8569a9885b2335b464d222847b9b2de70589d44e
+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:b7d15de12a469c7a06ad3c6f3a9cd00dc4668104e471506fe0f4503bf26a8ad1
+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": 5.349672317504883,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 3.4697,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 3.547457695007324,
+      "eval_runtime": 14.4843,
+      "eval_samples_per_second": 32.863,
+      "eval_steps_per_second": 8.216,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 5.466770648956299,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 3.4361,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.768375873565674,
+      "learning_rate": 3e-06,
+      "loss": 3.5871,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.6878485679626465,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 3.4894,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.205628871917725,
+      "learning_rate": 5e-06,
+      "loss": 3.501,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.880322456359863,
+      "learning_rate": 6e-06,
+      "loss": 3.5771,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.782011032104492,
+      "learning_rate": 7e-06,
+      "loss": 3.5119,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.285853385925293,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.4089,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.527816295623779,
+      "learning_rate": 9e-06,
+      "loss": 3.4341,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.505781650543213,
+      "learning_rate": 1e-05,
+      "loss": 3.4175,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.26746940612793,
+      "learning_rate": 9.999991309598975e-06,
+      "loss": 3.3163,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.086071968078613,
+      "learning_rate": 9.999965238426104e-06,
+      "loss": 3.274,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 5.271662712097168,
+      "learning_rate": 9.999921786572015e-06,
+      "loss": 3.2964,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.7532830238342285,
+      "learning_rate": 9.999860954187756e-06,
+      "loss": 3.1292,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.79344367980957,
+      "learning_rate": 9.99978274148479e-06,
+      "loss": 3.0481,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.707954406738281,
+      "learning_rate": 9.999687148734996e-06,
+      "loss": 2.9757,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.709782600402832,
+      "learning_rate": 9.999574176270667e-06,
+      "loss": 2.8673,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.751430988311768,
+      "learning_rate": 9.999443824484519e-06,
+      "loss": 2.8341,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.603825092315674,
+      "learning_rate": 9.999296093829672e-06,
+      "loss": 2.6421,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.514200210571289,
+      "learning_rate": 9.999130984819662e-06,
+      "loss": 2.5699,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.427622318267822,
+      "learning_rate": 9.998948498028435e-06,
+      "loss": 2.434,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.507719993591309,
+      "learning_rate": 9.998748634090344e-06,
+      "loss": 2.3301,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.355949878692627,
+      "learning_rate": 9.998531393700149e-06,
+      "loss": 2.0848,
+      "step": 23
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.219519138336182,
+      "learning_rate": 9.99829677761301e-06,
+      "loss": 1.9115,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.065847873687744,
+      "learning_rate": 9.998044786644492e-06,
+      "loss": 1.7682,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.7316126823425293,
+      "learning_rate": 9.997775421670558e-06,
+      "loss": 1.6426,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.5228142738342285,
+      "learning_rate": 9.997488683627558e-06,
+      "loss": 1.5855,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.2372498512268066,
+      "learning_rate": 9.997184573512245e-06,
+      "loss": 1.4059,
+      "step": 28
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.072031259536743,
+      "learning_rate": 9.996863092381753e-06,
+      "loss": 1.2633,
+      "step": 29
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.941805124282837,
+      "learning_rate": 9.9965242413536e-06,
+      "loss": 1.1709,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.8302178382873535,
+      "learning_rate": 9.99616802160569e-06,
+      "loss": 1.0615,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.7408287525177,
+      "learning_rate": 9.995794434376297e-06,
+      "loss": 1.0031,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.6635422706604004,
+      "learning_rate": 9.995403480964072e-06,
+      "loss": 0.9273,
+      "step": 33
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.538907766342163,
+      "learning_rate": 9.994995162728029e-06,
+      "loss": 0.8141,
+      "step": 34
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.457651138305664,
+      "learning_rate": 9.994569481087552e-06,
+      "loss": 0.7208,
+      "step": 35
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.383510112762451,
+      "learning_rate": 9.994126437522376e-06,
+      "loss": 0.6763,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.170029401779175,
+      "learning_rate": 9.99366603357259e-06,
+      "loss": 0.6163,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.0166823863983154,
+      "learning_rate": 9.993188270838636e-06,
+      "loss": 0.5146,
+      "step": 38
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.9549278020858765,
+      "learning_rate": 9.992693150981293e-06,
+      "loss": 0.4851,
+      "step": 39
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.7454789876937866,
+      "learning_rate": 9.992180675721671e-06,
+      "loss": 0.4015,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.5932520627975464,
+      "learning_rate": 9.991650846841226e-06,
+      "loss": 0.3704,
+      "step": 41
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.4394928216934204,
+      "learning_rate": 9.991103666181721e-06,
+      "loss": 0.3194,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.2608178853988647,
+      "learning_rate": 9.990539135645246e-06,
+      "loss": 0.2621,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0825426578521729,
+      "learning_rate": 9.989957257194199e-06,
+      "loss": 0.2489,
+      "step": 44
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.0383331775665283,
+      "learning_rate": 9.989358032851283e-06,
+      "loss": 0.249,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.7754441499710083,
+      "learning_rate": 9.9887414646995e-06,
+      "loss": 0.162,
+      "step": 46
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.7348763942718506,
+      "learning_rate": 9.988107554882138e-06,
+      "loss": 0.1713,
+      "step": 47
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5076927542686462,
+      "learning_rate": 9.987456305602769e-06,
+      "loss": 0.1438,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.5017581582069397,
+      "learning_rate": 9.986787719125241e-06,
+      "loss": 0.1386,
+      "step": 49
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.42143169045448303,
+      "learning_rate": 9.986101797773667e-06,
+      "loss": 0.138,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.2827802896499634,
+      "learning_rate": 9.985398543932421e-06,
+      "loss": 0.1165,
+      "step": 51
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.33519247174263,
+      "learning_rate": 9.984677960046123e-06,
+      "loss": 0.119,
+      "step": 52
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.2341219186782837,
+      "learning_rate": 9.983940048619641e-06,
+      "loss": 0.0748,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.20707747340202332,
+      "learning_rate": 9.983184812218071e-06,
+      "loss": 0.0949,
+      "step": 54
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.3519020974636078,
+      "learning_rate": 9.98241225346674e-06,
+      "loss": 0.0964,
+      "step": 55
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.2268177717924118,
+      "learning_rate": 9.981622375051183e-06,
+      "loss": 0.0771,
+      "step": 56
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.16427360475063324,
+      "learning_rate": 9.980815179717144e-06,
+      "loss": 0.08,
+      "step": 57
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.3412397503852844,
+      "learning_rate": 9.979990670270565e-06,
+      "loss": 0.085,
+      "step": 58
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.13405166566371918,
+      "learning_rate": 9.979148849577574e-06,
+      "loss": 0.0852,
+      "step": 59
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.23308596014976501,
+      "learning_rate": 9.978289720564471e-06,
+      "loss": 0.0895,
+      "step": 60
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.20687691867351532,
+      "learning_rate": 9.97741328621773e-06,
+      "loss": 0.0875,
+      "step": 61
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.14851821959018707,
+      "learning_rate": 9.976519549583974e-06,
+      "loss": 0.0898,
+      "step": 62
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.31722521781921387,
+      "learning_rate": 9.975608513769977e-06,
+      "loss": 0.0902,
+      "step": 63
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.13900260627269745,
+      "learning_rate": 9.974680181942645e-06,
+      "loss": 0.0987,
+      "step": 64
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.21426311135292053,
+      "learning_rate": 9.97373455732901e-06,
+      "loss": 0.0765,
+      "step": 65
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.18942435085773468,
+      "learning_rate": 9.972771643216213e-06,
+      "loss": 0.092,
+      "step": 66
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.15527579188346863,
+      "learning_rate": 9.971791442951498e-06,
+      "loss": 0.0667,
+      "step": 67
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.2748473286628723,
+      "learning_rate": 9.970793959942197e-06,
+      "loss": 0.0905,
+      "step": 68
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.2710763216018677,
+      "learning_rate": 9.969779197655726e-06,
+      "loss": 0.0767,
+      "step": 69
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.19998699426651,
+      "learning_rate": 9.968747159619556e-06,
+      "loss": 0.0836,
+      "step": 70
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.5467928051948547,
+      "learning_rate": 9.96769784942122e-06,
+      "loss": 0.1069,
+      "step": 71
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.1530974954366684,
+      "learning_rate": 9.966631270708288e-06,
+      "loss": 0.0867,
+      "step": 72
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.2446594089269638,
+      "learning_rate": 9.965547427188358e-06,
+      "loss": 0.0771,
+      "step": 73
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.14469081163406372,
+      "learning_rate": 9.964446322629044e-06,
+      "loss": 0.0892,
+      "step": 74
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.2065022885799408,
+      "learning_rate": 9.963327960857962e-06,
+      "loss": 0.0729,
+      "step": 75
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.27265021204948425,
+      "learning_rate": 9.962192345762717e-06,
+      "loss": 0.0684,
+      "step": 76
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3528543710708618,
+      "learning_rate": 9.961039481290888e-06,
+      "loss": 0.0656,
+      "step": 77
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.14887100458145142,
+      "learning_rate": 9.959869371450022e-06,
+      "loss": 0.0794,
+      "step": 78
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.24467024207115173,
+      "learning_rate": 9.958682020307602e-06,
+      "loss": 0.0749,
+      "step": 79
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.4109407961368561,
+      "learning_rate": 9.957477431991053e-06,
+      "loss": 0.1062,
+      "step": 80
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.20120254158973694,
+      "learning_rate": 9.95625561068772e-06,
+      "loss": 0.101,
+      "step": 81
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.30039364099502563,
+      "learning_rate": 9.955016560644847e-06,
+      "loss": 0.1015,
+      "step": 82
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.3657380938529968,
+      "learning_rate": 9.953760286169571e-06,
+      "loss": 0.1124,
+      "step": 83
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.3613692820072174,
+      "learning_rate": 9.952486791628905e-06,
+      "loss": 0.0836,
+      "step": 84
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.3250538110733032,
+      "learning_rate": 9.95119608144972e-06,
+      "loss": 0.0753,
+      "step": 85
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.21736566722393036,
+      "learning_rate": 9.94988816011873e-06,
+      "loss": 0.075,
+      "step": 86
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.8842391967773438,
+      "learning_rate": 9.948563032182482e-06,
+      "loss": 0.1067,
+      "step": 87
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.2460835725069046,
+      "learning_rate": 9.947220702247329e-06,
+      "loss": 0.0832,
+      "step": 88
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5178576707839966,
+      "learning_rate": 9.94586117497943e-06,
+      "loss": 0.1007,
+      "step": 89
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.19302992522716522,
+      "learning_rate": 9.944484455104716e-06,
+      "loss": 0.0705,
+      "step": 90
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5060548186302185,
+      "learning_rate": 9.943090547408888e-06,
+      "loss": 0.1216,
+      "step": 91
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.3466648757457733,
+      "learning_rate": 9.941679456737395e-06,
+      "loss": 0.0938,
+      "step": 92
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.22704587876796722,
+      "learning_rate": 9.940251187995412e-06,
+      "loss": 0.0803,
+      "step": 93
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.25966060161590576,
+      "learning_rate": 9.938805746147827e-06,
+      "loss": 0.0966,
+      "step": 94
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.20877382159233093,
+      "learning_rate": 9.937343136219234e-06,
+      "loss": 0.0667,
+      "step": 95
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.1972026228904724,
+      "learning_rate": 9.935863363293896e-06,
+      "loss": 0.0642,
+      "step": 96
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.21666616201400757,
+      "learning_rate": 9.934366432515741e-06,
+      "loss": 0.0943,
+      "step": 97
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.3361506760120392,
+      "learning_rate": 9.932852349088342e-06,
+      "loss": 0.0797,
+      "step": 98
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.3094469904899597,
+      "learning_rate": 9.931321118274897e-06,
+      "loss": 0.0762,
+      "step": 99
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.33961156010627747,
+      "learning_rate": 9.929772745398207e-06,
+      "loss": 0.0744,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.3448229730129242,
+      "learning_rate": 9.928207235840664e-06,
+      "loss": 0.0562,
+      "step": 101
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.2657065689563751,
+      "learning_rate": 9.926624595044235e-06,
+      "loss": 0.0922,
+      "step": 102
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.2084828019142151,
+      "learning_rate": 9.925024828510429e-06,
+      "loss": 0.0616,
+      "step": 103
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.342433899641037,
+      "learning_rate": 9.92340794180029e-06,
+      "loss": 0.0827,
+      "step": 104
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.21574071049690247,
+      "learning_rate": 9.921773940534382e-06,
+      "loss": 0.0593,
+      "step": 105
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.15846671164035797,
+      "learning_rate": 9.920122830392748e-06,
+      "loss": 0.0732,
+      "step": 106
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.2687283456325531,
+      "learning_rate": 9.91845461711492e-06,
+      "loss": 0.0699,
+      "step": 107
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.18184144794940948,
+      "learning_rate": 9.916769306499866e-06,
+      "loss": 0.0632,
+      "step": 108
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.21744874119758606,
+      "learning_rate": 9.915066904406e-06,
+      "loss": 0.0805,
+      "step": 109
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.3575034737586975,
+      "learning_rate": 9.913347416751148e-06,
+      "loss": 0.0819,
+      "step": 110
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.23368307948112488,
+      "learning_rate": 9.91161084951252e-06,
+      "loss": 0.0576,
+      "step": 111
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.4599943161010742,
+      "learning_rate": 9.909857208726705e-06,
+      "loss": 0.0867,
+      "step": 112
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.26656806468963623,
+      "learning_rate": 9.908086500489638e-06,
+      "loss": 0.0586,
+      "step": 113
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.5311251282691956,
+      "learning_rate": 9.906298730956585e-06,
+      "loss": 0.102,
+      "step": 114
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.3186182677745819,
+      "learning_rate": 9.904493906342124e-06,
+      "loss": 0.0743,
+      "step": 115
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.20787174999713898,
+      "learning_rate": 9.902672032920106e-06,
+      "loss": 0.0536,
+      "step": 116
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.18734194338321686,
+      "learning_rate": 9.900833117023665e-06,
+      "loss": 0.06,
+      "step": 117
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.46386289596557617,
+      "learning_rate": 9.898977165045161e-06,
+      "loss": 0.0861,
+      "step": 118
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.2560313940048218,
+      "learning_rate": 9.897104183436184e-06,
+      "loss": 0.0574,
+      "step": 119
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.22062335908412933,
+      "learning_rate": 9.895214178707516e-06,
+      "loss": 0.0631,
+      "step": 120
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.2438971847295761,
+      "learning_rate": 9.89330715742912e-06,
+      "loss": 0.0906,
+      "step": 121
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.17582635581493378,
+      "learning_rate": 9.891383126230105e-06,
+      "loss": 0.0507,
+      "step": 122
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2775309979915619,
+      "learning_rate": 9.889442091798712e-06,
+      "loss": 0.0741,
+      "step": 123
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.18693320453166962,
+      "learning_rate": 9.887484060882292e-06,
+      "loss": 0.0624,
+      "step": 124
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.5480987429618835,
+      "learning_rate": 9.885509040287267e-06,
+      "loss": 0.1104,
+      "step": 125
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.25776028633117676,
+      "learning_rate": 9.883517036879133e-06,
+      "loss": 0.0876,
+      "step": 126
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.6148080825805664,
+      "learning_rate": 9.881508057582411e-06,
+      "loss": 0.0678,
+      "step": 127
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.8079890608787537,
+      "learning_rate": 9.879482109380634e-06,
+      "loss": 0.0801,
+      "step": 128
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.22970955073833466,
+      "learning_rate": 9.877439199316324e-06,
+      "loss": 0.0662,
+      "step": 129
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.4607698917388916,
+      "learning_rate": 9.875379334490962e-06,
+      "loss": 0.0863,
+      "step": 130
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.4692334532737732,
+      "learning_rate": 9.873302522064972e-06,
+      "loss": 0.0968,
+      "step": 131
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.8688197135925293,
+      "learning_rate": 9.871208769257686e-06,
+      "loss": 0.0963,
+      "step": 132
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2747116982936859,
+      "learning_rate": 9.869098083347323e-06,
+      "loss": 0.0801,
+      "step": 133
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.5444130897521973,
+      "learning_rate": 9.866970471670968e-06,
+      "loss": 0.0965,
+      "step": 134
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.303763210773468,
+      "learning_rate": 9.864825941624538e-06,
+      "loss": 0.0727,
+      "step": 135
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.16060137748718262,
+      "learning_rate": 9.862664500662763e-06,
+      "loss": 0.0468,
+      "step": 136
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.22011107206344604,
+      "learning_rate": 9.860486156299164e-06,
+      "loss": 0.0832,
+      "step": 137
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.38508448004722595,
+      "learning_rate": 9.85829091610601e-06,
+      "loss": 0.0947,
+      "step": 138
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2385941594839096,
+      "learning_rate": 9.856078787714309e-06,
+      "loss": 0.0676,
+      "step": 139
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.15575379133224487,
+      "learning_rate": 9.853849778813777e-06,
+      "loss": 0.0833,
+      "step": 140
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.23725704848766327,
+      "learning_rate": 9.851603897152804e-06,
+      "loss": 0.0807,
+      "step": 141
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.20930880308151245,
+      "learning_rate": 9.849341150538434e-06,
+      "loss": 0.0881,
+      "step": 142
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.08187390118837357,
+      "eval_runtime": 14.7383,
+      "eval_samples_per_second": 32.297,
+      "eval_steps_per_second": 8.074,
+      "step": 142
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2966826260089874,
+      "learning_rate": 9.84706154683634e-06,
+      "loss": 0.0567,
+      "step": 143
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.3383941948413849,
+      "learning_rate": 9.844765093970787e-06,
+      "loss": 0.0597,
+      "step": 144
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.20434536039829254,
+      "learning_rate": 9.842451799924616e-06,
+      "loss": 0.0873,
+      "step": 145
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.27841946482658386,
+      "learning_rate": 9.840121672739208e-06,
+      "loss": 0.0746,
+      "step": 146
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.18767426908016205,
+      "learning_rate": 9.837774720514456e-06,
+      "loss": 0.0928,
+      "step": 147
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.4455524981021881,
+      "learning_rate": 9.835410951408748e-06,
+      "loss": 0.0692,
+      "step": 148
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.24763479828834534,
+      "learning_rate": 9.83303037363892e-06,
+      "loss": 0.0643,
+      "step": 149
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.4498063325881958,
+      "learning_rate": 9.830632995480243e-06,
+      "loss": 0.0736,
+      "step": 150
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2298639714717865,
+      "learning_rate": 9.828218825266389e-06,
+      "loss": 0.0678,
+      "step": 151
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.46498408913612366,
+      "learning_rate": 9.8257878713894e-06,
+      "loss": 0.0775,
+      "step": 152
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.3503478169441223,
+      "learning_rate": 9.823340142299662e-06,
+      "loss": 0.0749,
+      "step": 153
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.3784450590610504,
+      "learning_rate": 9.820875646505874e-06,
+      "loss": 0.0806,
+      "step": 154
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2675660252571106,
+      "learning_rate": 9.818394392575018e-06,
+      "loss": 0.1054,
+      "step": 155
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.18610945343971252,
+      "learning_rate": 9.815896389132333e-06,
+      "loss": 0.0793,
+      "step": 156
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.25484928488731384,
+      "learning_rate": 9.813381644861276e-06,
+      "loss": 0.1004,
+      "step": 157
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.2842435836791992,
+      "learning_rate": 9.810850168503506e-06,
+      "loss": 0.0413,
+      "step": 158
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.2782611548900604,
+      "learning_rate": 9.808301968858838e-06,
+      "loss": 0.1083,
+      "step": 159
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.1917373687028885,
+      "learning_rate": 9.805737054785223e-06,
+      "loss": 0.0727,
+      "step": 160
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.2308584451675415,
+      "learning_rate": 9.803155435198713e-06,
+      "loss": 0.0629,
+      "step": 161
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.20095452666282654,
+      "learning_rate": 9.800557119073433e-06,
+      "loss": 0.0857,
+      "step": 162
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.28956976532936096,
+      "learning_rate": 9.797942115441546e-06,
+      "loss": 0.053,
+      "step": 163
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.24081195890903473,
+      "learning_rate": 9.795310433393227e-06,
+      "loss": 0.0611,
+      "step": 164
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.4568108022212982,
+      "learning_rate": 9.792662082076618e-06,
+      "loss": 0.1011,
+      "step": 165
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.16725283861160278,
+      "learning_rate": 9.789997070697821e-06,
+      "loss": 0.0525,
+      "step": 166
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.27492183446884155,
+      "learning_rate": 9.787315408520839e-06,
+      "loss": 0.0581,
+      "step": 167
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.21994265913963318,
+      "learning_rate": 9.78461710486756e-06,
+      "loss": 0.068,
+      "step": 168
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2217988818883896,
+      "learning_rate": 9.78190216911772e-06,
+      "loss": 0.0663,
+      "step": 169
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.43498608469963074,
+      "learning_rate": 9.779170610708872e-06,
+      "loss": 0.1003,
+      "step": 170
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.5494738817214966,
+      "learning_rate": 9.776422439136351e-06,
+      "loss": 0.0901,
+      "step": 171
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.30544596910476685,
+      "learning_rate": 9.773657663953244e-06,
+      "loss": 0.1049,
+      "step": 172
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.5173572301864624,
+      "learning_rate": 9.77087629477035e-06,
+      "loss": 0.084,
+      "step": 173
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1275845617055893,
+      "learning_rate": 9.768078341256156e-06,
+      "loss": 0.0668,
+      "step": 174
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.28769540786743164,
+      "learning_rate": 9.765263813136796e-06,
+      "loss": 0.0743,
+      "step": 175
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.7122567296028137,
+      "learning_rate": 9.762432720196024e-06,
+      "loss": 0.129,
+      "step": 176
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.28987741470336914,
+      "learning_rate": 9.759585072275171e-06,
+      "loss": 0.077,
+      "step": 177
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.24338261783123016,
+      "learning_rate": 9.756720879273117e-06,
+      "loss": 0.0763,
+      "step": 178
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3709527254104614,
+      "learning_rate": 9.753840151146259e-06,
+      "loss": 0.0639,
+      "step": 179
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.1488633006811142,
+      "learning_rate": 9.750942897908468e-06,
+      "loss": 0.0825,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.13455910980701447,
+      "learning_rate": 9.748029129631062e-06,
+      "loss": 0.0594,
+      "step": 181
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2483726590871811,
+      "learning_rate": 9.745098856442769e-06,
+      "loss": 0.0621,
+      "step": 182
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.34576350450515747,
+      "learning_rate": 9.742152088529683e-06,
+      "loss": 0.083,
+      "step": 183
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.28745996952056885,
+      "learning_rate": 9.739188836135247e-06,
+      "loss": 0.0517,
+      "step": 184
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.18788190186023712,
+      "learning_rate": 9.736209109560201e-06,
+      "loss": 0.0831,
+      "step": 185
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1737545132637024,
+      "learning_rate": 9.733212919162551e-06,
+      "loss": 0.0597,
+      "step": 186
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.31250202655792236,
+      "learning_rate": 9.730200275357535e-06,
+      "loss": 0.0591,
+      "step": 187
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.20151746273040771,
+      "learning_rate": 9.727171188617588e-06,
+      "loss": 0.0687,
+      "step": 188
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.19415058195590973,
+      "learning_rate": 9.7241256694723e-06,
+      "loss": 0.0463,
+      "step": 189
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1791050285100937,
+      "learning_rate": 9.721063728508384e-06,
+      "loss": 0.0727,
+      "step": 190
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.5859791040420532,
+      "learning_rate": 9.71798537636964e-06,
+      "loss": 0.0996,
+      "step": 191
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.4107828438282013,
+      "learning_rate": 9.714890623756912e-06,
+      "loss": 0.0675,
+      "step": 192
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.339235782623291,
+      "learning_rate": 9.711779481428057e-06,
+      "loss": 0.0916,
+      "step": 193
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.3153787851333618,
+      "learning_rate": 9.708651960197904e-06,
+      "loss": 0.0838,
+      "step": 194
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.38205188512802124,
+      "learning_rate": 9.705508070938219e-06,
+      "loss": 0.0773,
+      "step": 195
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.48745977878570557,
+      "learning_rate": 9.702347824577667e-06,
+      "loss": 0.0571,
+      "step": 196
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.3050192594528198,
+      "learning_rate": 9.699171232101769e-06,
+      "loss": 0.0473,
+      "step": 197
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.22496673464775085,
+      "learning_rate": 9.695978304552871e-06,
+      "loss": 0.0589,
+      "step": 198
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.3087387979030609,
+      "learning_rate": 9.6927690530301e-06,
+      "loss": 0.0814,
+      "step": 199
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.1646536886692047,
+      "learning_rate": 9.689543488689332e-06,
+      "loss": 0.0694,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.3601110279560089,
+      "learning_rate": 9.686301622743144e-06,
+      "loss": 0.0919,
+      "step": 201
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.20077168941497803,
+      "learning_rate": 9.683043466460783e-06,
+      "loss": 0.0754,
+      "step": 202
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.2863204777240753,
+      "learning_rate": 9.67976903116812e-06,
+      "loss": 0.0814,
+      "step": 203
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.30959010124206543,
+      "learning_rate": 9.676478328247623e-06,
+      "loss": 0.1012,
+      "step": 204
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.2969251871109009,
+      "learning_rate": 9.673171369138297e-06,
+      "loss": 0.0983,
+      "step": 205
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.19835108518600464,
+      "learning_rate": 9.669848165335668e-06,
+      "loss": 0.0814,
+      "step": 206
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.30629757046699524,
+      "learning_rate": 9.666508728391719e-06,
+      "loss": 0.0985,
+      "step": 207
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.17222163081169128,
+      "learning_rate": 9.663153069914874e-06,
+      "loss": 0.0789,
+      "step": 208
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.4108015298843384,
+      "learning_rate": 9.65978120156994e-06,
+      "loss": 0.0797,
+      "step": 209
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.2489665299654007,
+      "learning_rate": 9.656393135078067e-06,
+      "loss": 0.0927,
+      "step": 210
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.27541467547416687,
+      "learning_rate": 9.652988882216725e-06,
+      "loss": 0.0496,
+      "step": 211
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.17665977776050568,
+      "learning_rate": 9.649568454819637e-06,
+      "loss": 0.0666,
+      "step": 212
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.20858129858970642,
+      "learning_rate": 9.646131864776762e-06,
+      "loss": 0.0708,
+      "step": 213
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.18341350555419922,
+      "learning_rate": 9.642679124034234e-06,
+      "loss": 0.0805,
+      "step": 214
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.26587384939193726,
+      "learning_rate": 9.639210244594335e-06,
+      "loss": 0.0744,
+      "step": 215
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.20824970304965973,
+      "learning_rate": 9.635725238515447e-06,
+      "loss": 0.0821,
+      "step": 216
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.20785243809223175,
+      "learning_rate": 9.63222411791201e-06,
+      "loss": 0.0435,
+      "step": 217
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.45304587483406067,
+      "learning_rate": 9.628706894954481e-06,
+      "loss": 0.0791,
+      "step": 218
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.34389665722846985,
+      "learning_rate": 9.62517358186929e-06,
+      "loss": 0.0829,
+      "step": 219
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.24149852991104126,
+      "learning_rate": 9.621624190938802e-06,
+      "loss": 0.0555,
+      "step": 220
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.24253778159618378,
+      "learning_rate": 9.61805873450127e-06,
+      "loss": 0.0948,
+      "step": 221
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.24377629160881042,
+      "learning_rate": 9.614477224950788e-06,
+      "loss": 0.0758,
+      "step": 222
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.1714078187942505,
+      "learning_rate": 9.610879674737263e-06,
+      "loss": 0.0773,
+      "step": 223
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.15262386202812195,
+      "learning_rate": 9.607266096366353e-06,
+      "loss": 0.0523,
+      "step": 224
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.34207943081855774,
+      "learning_rate": 9.603636502399436e-06,
+      "loss": 0.0981,
+      "step": 225
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2515898048877716,
+      "learning_rate": 9.599990905453567e-06,
+      "loss": 0.0576,
+      "step": 226
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.509267270565033,
+      "learning_rate": 9.59632931820142e-06,
+      "loss": 0.0819,
+      "step": 227
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.21576029062271118,
+      "learning_rate": 9.592651753371264e-06,
+      "loss": 0.0758,
+      "step": 228
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.44684383273124695,
+      "learning_rate": 9.588958223746903e-06,
+      "loss": 0.0543,
+      "step": 229
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.4631918668746948,
+      "learning_rate": 9.585248742167638e-06,
+      "loss": 0.0795,
+      "step": 230
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.3433883488178253,
+      "learning_rate": 9.581523321528224e-06,
+      "loss": 0.0505,
+      "step": 231
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.23749905824661255,
+      "learning_rate": 9.577781974778817e-06,
+      "loss": 0.0463,
+      "step": 232
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.26895391941070557,
+      "learning_rate": 9.574024714924941e-06,
+      "loss": 0.0501,
+      "step": 233
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.45005208253860474,
+      "learning_rate": 9.570251555027432e-06,
+      "loss": 0.1112,
+      "step": 234
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.21089734137058258,
+      "learning_rate": 9.566462508202403e-06,
+      "loss": 0.0912,
+      "step": 235
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.22349245846271515,
+      "learning_rate": 9.562657587621186e-06,
+      "loss": 0.0671,
+      "step": 236
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.20209869742393494,
+      "learning_rate": 9.558836806510292e-06,
+      "loss": 0.0507,
+      "step": 237
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.29422205686569214,
+      "learning_rate": 9.555000178151375e-06,
+      "loss": 0.0744,
+      "step": 238
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2201872318983078,
+      "learning_rate": 9.551147715881167e-06,
+      "loss": 0.0784,
+      "step": 239
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2708396017551422,
+      "learning_rate": 9.547279433091446e-06,
+      "loss": 0.0574,
+      "step": 240
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.1722852736711502,
+      "learning_rate": 9.543395343228984e-06,
+      "loss": 0.0788,
+      "step": 241
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.5377947688102722,
+      "learning_rate": 9.5394954597955e-06,
+      "loss": 0.0908,
+      "step": 242
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.2269710898399353,
+      "learning_rate": 9.535579796347612e-06,
+      "loss": 0.078,
+      "step": 243
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.2239355891942978,
+      "learning_rate": 9.531648366496799e-06,
+      "loss": 0.0501,
+      "step": 244
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.20963357388973236,
+      "learning_rate": 9.527701183909336e-06,
+      "loss": 0.0611,
+      "step": 245
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.2847237288951874,
+      "learning_rate": 9.52373826230627e-06,
+      "loss": 0.0761,
+      "step": 246
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.20428815484046936,
+      "learning_rate": 9.519759615463346e-06,
+      "loss": 0.0684,
+      "step": 247
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.18516795337200165,
+      "learning_rate": 9.51576525721098e-06,
+      "loss": 0.0667,
+      "step": 248
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.4787046015262604,
+      "learning_rate": 9.511755201434206e-06,
+      "loss": 0.1339,
+      "step": 249
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.5016088485717773,
+      "learning_rate": 9.507729462072615e-06,
+      "loss": 0.0723,
+      "step": 250
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.24285417795181274,
+      "learning_rate": 9.503688053120327e-06,
+      "loss": 0.0553,
+      "step": 251
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.44292014837265015,
+      "learning_rate": 9.499630988625926e-06,
+      "loss": 0.071,
+      "step": 252
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.7392637133598328,
+      "learning_rate": 9.495558282692421e-06,
+      "loss": 0.1074,
+      "step": 253
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.24650004506111145,
+      "learning_rate": 9.491469949477189e-06,
+      "loss": 0.0505,
+      "step": 254
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.22753530740737915,
+      "learning_rate": 9.48736600319193e-06,
+      "loss": 0.065,
+      "step": 255
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.3731183111667633,
+      "learning_rate": 9.483246458102626e-06,
+      "loss": 0.0809,
+      "step": 256
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.16581465303897858,
+      "learning_rate": 9.479111328529473e-06,
+      "loss": 0.0575,
+      "step": 257
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.2750982344150543,
+      "learning_rate": 9.474960628846844e-06,
+      "loss": 0.0967,
+      "step": 258
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.3518216609954834,
+      "learning_rate": 9.470794373483236e-06,
+      "loss": 0.09,
+      "step": 259
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.3871642053127289,
+      "learning_rate": 9.466612576921223e-06,
+      "loss": 0.0741,
+      "step": 260
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.23743928968906403,
+      "learning_rate": 9.462415253697402e-06,
+      "loss": 0.0764,
+      "step": 261
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.4438982903957367,
+      "learning_rate": 9.458202418402339e-06,
+      "loss": 0.089,
+      "step": 262
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.1571800857782364,
+      "learning_rate": 9.453974085680527e-06,
+      "loss": 0.0481,
+      "step": 263
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.243282288312912,
+      "learning_rate": 9.449730270230326e-06,
+      "loss": 0.0843,
+      "step": 264
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.21889477968215942,
+      "learning_rate": 9.445470986803922e-06,
+      "loss": 0.0456,
+      "step": 265
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.14643190801143646,
+      "learning_rate": 9.441196250207267e-06,
+      "loss": 0.0555,
+      "step": 266
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.6666358709335327,
+      "learning_rate": 9.436906075300032e-06,
+      "loss": 0.0775,
+      "step": 267
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.16846437752246857,
+      "learning_rate": 9.432600476995552e-06,
+      "loss": 0.0354,
+      "step": 268
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.23625656962394714,
+      "learning_rate": 9.428279470260776e-06,
+      "loss": 0.0837,
+      "step": 269
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.25802698731422424,
+      "learning_rate": 9.423943070116219e-06,
+      "loss": 0.0685,
+      "step": 270
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.1842992752790451,
+      "learning_rate": 9.419591291635901e-06,
+      "loss": 0.0418,
+      "step": 271
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3693784773349762,
+      "learning_rate": 9.415224149947307e-06,
+      "loss": 0.0619,
+      "step": 272
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.36359575390815735,
+      "learning_rate": 9.410841660231315e-06,
+      "loss": 0.0675,
+      "step": 273
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.25318172574043274,
+      "learning_rate": 9.406443837722168e-06,
+      "loss": 0.0521,
+      "step": 274
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.32068488001823425,
+      "learning_rate": 9.402030697707398e-06,
+      "loss": 0.0744,
+      "step": 275
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.2709636390209198,
+      "learning_rate": 9.397602255527792e-06,
+      "loss": 0.0446,
+      "step": 276
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.4686291813850403,
+      "learning_rate": 9.393158526577322e-06,
+      "loss": 0.0683,
+      "step": 277
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.32740774750709534,
+      "learning_rate": 9.388699526303106e-06,
+      "loss": 0.061,
+      "step": 278
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.5102832913398743,
+      "learning_rate": 9.38422527020534e-06,
+      "loss": 0.0904,
+      "step": 279
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3581833243370056,
+      "learning_rate": 9.37973577383726e-06,
+      "loss": 0.0691,
+      "step": 280
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.22778642177581787,
+      "learning_rate": 9.375231052805074e-06,
+      "loss": 0.0507,
+      "step": 281
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3017262816429138,
+      "learning_rate": 9.370711122767912e-06,
+      "loss": 0.0909,
+      "step": 282
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.24568532407283783,
+      "learning_rate": 9.36617599943778e-06,
+      "loss": 0.0622,
+      "step": 283
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3963547348976135,
+      "learning_rate": 9.361625698579493e-06,
+      "loss": 0.1131,
+      "step": 284
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.07626692205667496,
+      "eval_runtime": 14.7121,
+      "eval_samples_per_second": 32.354,
+      "eval_steps_per_second": 8.089,
+      "step": 284
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.6276136636734009,
+      "learning_rate": 9.357060236010626e-06,
+      "loss": 0.1067,
+      "step": 285
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.30459901690483093,
+      "learning_rate": 9.35247962760146e-06,
+      "loss": 0.0863,
+      "step": 286
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.5768241286277771,
+      "learning_rate": 9.347883889274922e-06,
+      "loss": 0.0966,
+      "step": 287
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.14496010541915894,
+      "learning_rate": 9.34327303700654e-06,
+      "loss": 0.0242,
+      "step": 288
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.25412389636039734,
+      "learning_rate": 9.338647086824373e-06,
+      "loss": 0.071,
+      "step": 289
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.23926912248134613,
+      "learning_rate": 9.334006054808966e-06,
+      "loss": 0.0378,
+      "step": 290
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.7999410629272461,
+      "learning_rate": 9.329349957093293e-06,
+      "loss": 0.0912,
+      "step": 291
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.18663926422595978,
+      "learning_rate": 9.324678809862696e-06,
+      "loss": 0.0658,
+      "step": 292
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.27844029664993286,
+      "learning_rate": 9.319992629354828e-06,
+      "loss": 0.0657,
+      "step": 293
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.295076847076416,
+      "learning_rate": 9.31529143185961e-06,
+      "loss": 0.0497,
+      "step": 294
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.25130167603492737,
+      "learning_rate": 9.310575233719155e-06,
+      "loss": 0.0771,
+      "step": 295
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.3607313632965088,
+      "learning_rate": 9.305844051327725e-06,
+      "loss": 0.0852,
+      "step": 296
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.2247592657804489,
+      "learning_rate": 9.301097901131671e-06,
+      "loss": 0.0793,
+      "step": 297
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.34789037704467773,
+      "learning_rate": 9.296336799629368e-06,
+      "loss": 0.0602,
+      "step": 298
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.27349668741226196,
+      "learning_rate": 9.291560763371173e-06,
+      "loss": 0.0546,
+      "step": 299
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.15801368653774261,
+      "learning_rate": 9.28676980895935e-06,
+      "loss": 0.0545,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.22296564280986786,
+      "learning_rate": 9.28196395304803e-06,
+      "loss": 0.0512,
+      "step": 301
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.18935079872608185,
+      "learning_rate": 9.277143212343134e-06,
+      "loss": 0.0382,
+      "step": 302
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.41481491923332214,
+      "learning_rate": 9.272307603602334e-06,
+      "loss": 0.0924,
+      "step": 303
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.4681742489337921,
+      "learning_rate": 9.26745714363498e-06,
+      "loss": 0.0644,
+      "step": 304
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.2106870412826538,
+      "learning_rate": 9.262591849302049e-06,
+      "loss": 0.0562,
+      "step": 305
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.45636868476867676,
+      "learning_rate": 9.257711737516083e-06,
+      "loss": 0.0751,
+      "step": 306
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.21162806451320648,
+      "learning_rate": 9.252816825241135e-06,
+      "loss": 0.0356,
+      "step": 307
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.31407129764556885,
+      "learning_rate": 9.247907129492707e-06,
+      "loss": 0.0713,
+      "step": 308
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.15091249346733093,
+      "learning_rate": 9.242982667337686e-06,
+      "loss": 0.066,
+      "step": 309
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.22152362763881683,
+      "learning_rate": 9.238043455894294e-06,
+      "loss": 0.0732,
+      "step": 310
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.21332816779613495,
+      "learning_rate": 9.233089512332021e-06,
+      "loss": 0.0744,
+      "step": 311
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.3001808524131775,
+      "learning_rate": 9.228120853871571e-06,
+      "loss": 0.0337,
+      "step": 312
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.45393407344818115,
+      "learning_rate": 9.223137497784798e-06,
+      "loss": 0.0704,
+      "step": 313
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.36986440420150757,
+      "learning_rate": 9.218139461394644e-06,
+      "loss": 0.0751,
+      "step": 314
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.25236037373542786,
+      "learning_rate": 9.213126762075088e-06,
+      "loss": 0.0782,
+      "step": 315
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.19866494834423065,
+      "learning_rate": 9.208099417251077e-06,
+      "loss": 0.0404,
+      "step": 316
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.18358244001865387,
+      "learning_rate": 9.203057444398469e-06,
+      "loss": 0.0362,
+      "step": 317
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.38209205865859985,
+      "learning_rate": 9.198000861043967e-06,
+      "loss": 0.0531,
+      "step": 318
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2181481420993805,
+      "learning_rate": 9.19292968476507e-06,
+      "loss": 0.0607,
+      "step": 319
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.19979895651340485,
+      "learning_rate": 9.187843933189994e-06,
+      "loss": 0.0654,
+      "step": 320
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.46315455436706543,
+      "learning_rate": 9.182743623997634e-06,
+      "loss": 0.0654,
+      "step": 321
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.31687167286872864,
+      "learning_rate": 9.17762877491748e-06,
+      "loss": 0.0628,
+      "step": 322
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.3118394613265991,
+      "learning_rate": 9.172499403729567e-06,
+      "loss": 0.0808,
+      "step": 323
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.8999722599983215,
+      "learning_rate": 9.167355528264415e-06,
+      "loss": 0.1028,
+      "step": 324
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.41446566581726074,
+      "learning_rate": 9.162197166402957e-06,
+      "loss": 0.0896,
+      "step": 325
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.23004719614982605,
+      "learning_rate": 9.157024336076488e-06,
+      "loss": 0.067,
+      "step": 326
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.42118194699287415,
+      "learning_rate": 9.151837055266595e-06,
+      "loss": 0.0391,
+      "step": 327
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.21042917668819427,
+      "learning_rate": 9.1466353420051e-06,
+      "loss": 0.0677,
+      "step": 328
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.22170236706733704,
+      "learning_rate": 9.14141921437399e-06,
+      "loss": 0.0551,
+      "step": 329
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.24892501533031464,
+      "learning_rate": 9.136188690505363e-06,
+      "loss": 0.0527,
+      "step": 330
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.319352924823761,
+      "learning_rate": 9.130943788581359e-06,
+      "loss": 0.0843,
+      "step": 331
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.36097249388694763,
+      "learning_rate": 9.1256845268341e-06,
+      "loss": 0.108,
+      "step": 332
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.39498621225357056,
+      "learning_rate": 9.120410923545619e-06,
+      "loss": 0.053,
+      "step": 333
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.5976508855819702,
+      "learning_rate": 9.115122997047812e-06,
+      "loss": 0.093,
+      "step": 334
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.3573974072933197,
+      "learning_rate": 9.109820765722357e-06,
+      "loss": 0.0988,
+      "step": 335
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.3447941839694977,
+      "learning_rate": 9.10450424800066e-06,
+      "loss": 0.1083,
+      "step": 336
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.36789995431900024,
+      "learning_rate": 9.099173462363794e-06,
+      "loss": 0.048,
+      "step": 337
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.23102298378944397,
+      "learning_rate": 9.093828427342419e-06,
+      "loss": 0.0615,
+      "step": 338
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2154015451669693,
+      "learning_rate": 9.088469161516735e-06,
+      "loss": 0.0775,
+      "step": 339
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2312682718038559,
+      "learning_rate": 9.083095683516414e-06,
+      "loss": 0.0708,
+      "step": 340
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.1561180055141449,
+      "learning_rate": 9.077708012020525e-06,
+      "loss": 0.0628,
+      "step": 341
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2561321556568146,
+      "learning_rate": 9.072306165757476e-06,
+      "loss": 0.0913,
+      "step": 342
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.4026300013065338,
+      "learning_rate": 9.066890163504956e-06,
+      "loss": 0.0757,
+      "step": 343
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2731042802333832,
+      "learning_rate": 9.061460024089853e-06,
+      "loss": 0.1009,
+      "step": 344
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.32153868675231934,
+      "learning_rate": 9.056015766388205e-06,
+      "loss": 0.0841,
+      "step": 345
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2845655381679535,
+      "learning_rate": 9.050557409325126e-06,
+      "loss": 0.0573,
+      "step": 346
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2339751124382019,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.083,
+      "step": 347
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.1685064285993576,
+      "learning_rate": 9.039598473060114e-06,
+      "loss": 0.0598,
+      "step": 348
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2221630960702896,
+      "learning_rate": 9.0340979319532e-06,
+      "loss": 0.0639,
+      "step": 349
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.24915754795074463,
+      "learning_rate": 9.028583367674767e-06,
+      "loss": 0.1017,
+      "step": 350
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.21576786041259766,
+      "learning_rate": 9.023054799394316e-06,
+      "loss": 0.0598,
+      "step": 351
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.46793073415756226,
+      "learning_rate": 9.017512246330043e-06,
+      "loss": 0.0845,
+      "step": 352
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.23132359981536865,
+      "learning_rate": 9.01195572774875e-06,
+      "loss": 0.0865,
+      "step": 353
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.1407833993434906,
+      "learning_rate": 9.006385262965786e-06,
+      "loss": 0.0771,
+      "step": 354
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.34604090452194214,
+      "learning_rate": 9.00080087134498e-06,
+      "loss": 0.1058,
+      "step": 355
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.31735068559646606,
+      "learning_rate": 8.995202572298575e-06,
+      "loss": 0.0833,
+      "step": 356
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.2618115246295929,
+      "learning_rate": 8.989590385287156e-06,
+      "loss": 0.0688,
+      "step": 357
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.22336295247077942,
+      "learning_rate": 8.983964329819584e-06,
+      "loss": 0.0963,
+      "step": 358
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.27905017137527466,
+      "learning_rate": 8.97832442545293e-06,
+      "loss": 0.068,
+      "step": 359
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.16449055075645447,
+      "learning_rate": 8.972670691792409e-06,
+      "loss": 0.0951,
+      "step": 360
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2156919538974762,
+      "learning_rate": 8.967003148491305e-06,
+      "loss": 0.0495,
+      "step": 361
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.17048591375350952,
+      "learning_rate": 8.961321815250905e-06,
+      "loss": 0.0739,
+      "step": 362
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.21207985281944275,
+      "learning_rate": 8.955626711820438e-06,
+      "loss": 0.0817,
+      "step": 363
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.17985820770263672,
+      "learning_rate": 8.949917857996996e-06,
+      "loss": 0.0798,
+      "step": 364
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.18554697930812836,
+      "learning_rate": 8.944195273625472e-06,
+      "loss": 0.0511,
+      "step": 365
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.41460761427879333,
+      "learning_rate": 8.938458978598483e-06,
+      "loss": 0.104,
+      "step": 366
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.1609378457069397,
+      "learning_rate": 8.932708992856315e-06,
+      "loss": 0.078,
+      "step": 367
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.5837603211402893,
+      "learning_rate": 8.926945336386838e-06,
+      "loss": 0.0916,
+      "step": 368
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.20917074382305145,
+      "learning_rate": 8.921168029225448e-06,
+      "loss": 0.0439,
+      "step": 369
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.16059182584285736,
+      "learning_rate": 8.915377091454992e-06,
+      "loss": 0.0622,
+      "step": 370
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.42982298135757446,
+      "learning_rate": 8.909572543205697e-06,
+      "loss": 0.0688,
+      "step": 371
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.204355388879776,
+      "learning_rate": 8.903754404655107e-06,
+      "loss": 0.0355,
+      "step": 372
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.1616220325231552,
+      "learning_rate": 8.897922696027998e-06,
+      "loss": 0.0751,
+      "step": 373
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.22931227087974548,
+      "learning_rate": 8.892077437596333e-06,
+      "loss": 0.064,
+      "step": 374
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.24884217977523804,
+      "learning_rate": 8.886218649679162e-06,
+      "loss": 0.092,
+      "step": 375
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.23468102514743805,
+      "learning_rate": 8.880346352642575e-06,
+      "loss": 0.074,
+      "step": 376
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.40000632405281067,
+      "learning_rate": 8.874460566899616e-06,
+      "loss": 0.0553,
+      "step": 377
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.24387776851654053,
+      "learning_rate": 8.868561312910222e-06,
+      "loss": 0.0469,
+      "step": 378
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.27059826254844666,
+      "learning_rate": 8.862648611181145e-06,
+      "loss": 0.0561,
+      "step": 379
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.2047024518251419,
+      "learning_rate": 8.856722482265886e-06,
+      "loss": 0.0425,
+      "step": 380
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.19120073318481445,
+      "learning_rate": 8.850782946764618e-06,
+      "loss": 0.0683,
+      "step": 381
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.25501665472984314,
+      "learning_rate": 8.844830025324123e-06,
+      "loss": 0.0625,
+      "step": 382
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5250377058982849,
+      "learning_rate": 8.838863738637707e-06,
+      "loss": 0.0729,
+      "step": 383
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.18302053213119507,
+      "learning_rate": 8.83288410744514e-06,
+      "loss": 0.0509,
+      "step": 384
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.3579452633857727,
+      "learning_rate": 8.826891152532579e-06,
+      "loss": 0.0815,
+      "step": 385
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.4426077902317047,
+      "learning_rate": 8.820884894732498e-06,
+      "loss": 0.0868,
+      "step": 386
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.18046371638774872,
+      "learning_rate": 8.814865354923614e-06,
+      "loss": 0.0545,
+      "step": 387
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.17153623700141907,
+      "learning_rate": 8.808832554030809e-06,
+      "loss": 0.0407,
+      "step": 388
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.29191163182258606,
+      "learning_rate": 8.802786513025069e-06,
+      "loss": 0.0551,
+      "step": 389
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.3224787414073944,
+      "learning_rate": 8.796727252923403e-06,
+      "loss": 0.0435,
+      "step": 390
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.5621923208236694,
+      "learning_rate": 8.79065479478877e-06,
+      "loss": 0.0522,
+      "step": 391
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.3209080398082733,
+      "learning_rate": 8.784569159730008e-06,
+      "loss": 0.0546,
+      "step": 392
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.6716540455818176,
+      "learning_rate": 8.778470368901761e-06,
+      "loss": 0.0754,
+      "step": 393
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.19775713980197906,
+      "learning_rate": 8.772358443504406e-06,
+      "loss": 0.013,
+      "step": 394
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.25971564650535583,
+      "learning_rate": 8.766233404783975e-06,
+      "loss": 0.0344,
+      "step": 395
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5102748870849609,
+      "learning_rate": 8.760095274032083e-06,
+      "loss": 0.0646,
+      "step": 396
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.30724096298217773,
+      "learning_rate": 8.75394407258586e-06,
+      "loss": 0.0444,
+      "step": 397
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.2920438051223755,
+      "learning_rate": 8.747779821827868e-06,
+      "loss": 0.0714,
+      "step": 398
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.5672811269760132,
+      "learning_rate": 8.741602543186032e-06,
+      "loss": 0.144,
+      "step": 399
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.29323235154151917,
+      "learning_rate": 8.735412258133562e-06,
+      "loss": 0.0467,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.7952798008918762,
+      "learning_rate": 8.729208988188882e-06,
+      "loss": 0.1006,
+      "step": 401
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.1980268657207489,
+      "learning_rate": 8.722992754915555e-06,
+      "loss": 0.0282,
+      "step": 402
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.3340957462787628,
+      "learning_rate": 8.716763579922203e-06,
+      "loss": 0.0587,
+      "step": 403
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.3219829499721527,
+      "learning_rate": 8.71052148486244e-06,
+      "loss": 0.0484,
+      "step": 404
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4473950266838074,
+      "learning_rate": 8.704266491434787e-06,
+      "loss": 0.0613,
+      "step": 405
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4419131875038147,
+      "learning_rate": 8.697998621382608e-06,
+      "loss": 0.0569,
+      "step": 406
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.3174911141395569,
+      "learning_rate": 8.69171789649402e-06,
+      "loss": 0.0381,
+      "step": 407
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.445470929145813,
+      "learning_rate": 8.685424338601833e-06,
+      "loss": 0.0818,
+      "step": 408
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.30242660641670227,
+      "learning_rate": 8.679117969583464e-06,
+      "loss": 0.0733,
+      "step": 409
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.30104532837867737,
+      "learning_rate": 8.672798811360863e-06,
+      "loss": 0.0635,
+      "step": 410
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.4942661225795746,
+      "learning_rate": 8.66646688590044e-06,
+      "loss": 0.0652,
+      "step": 411
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.48222100734710693,
+      "learning_rate": 8.660122215212976e-06,
+      "loss": 0.0519,
+      "step": 412
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.18950317800045013,
+      "learning_rate": 8.653764821353575e-06,
+      "loss": 0.0372,
+      "step": 413
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.0479586124420166,
+      "learning_rate": 8.647394726421547e-06,
+      "loss": 0.1133,
+      "step": 414
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9393060803413391,
+      "learning_rate": 8.641011952560372e-06,
+      "loss": 0.1114,
+      "step": 415
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.6437638998031616,
+      "learning_rate": 8.63461652195759e-06,
+      "loss": 0.0834,
+      "step": 416
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.5016691088676453,
+      "learning_rate": 8.628208456844749e-06,
+      "loss": 0.1051,
+      "step": 417
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.2746430039405823,
+      "learning_rate": 8.621787779497307e-06,
+      "loss": 0.0756,
+      "step": 418
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.1799677610397339,
+      "learning_rate": 8.615354512234569e-06,
+      "loss": 0.0748,
+      "step": 419
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.32306981086730957,
+      "learning_rate": 8.608908677419606e-06,
+      "loss": 0.09,
+      "step": 420
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.40375712513923645,
+      "learning_rate": 8.602450297459173e-06,
+      "loss": 0.1321,
+      "step": 421
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.1651470959186554,
+      "learning_rate": 8.595979394803633e-06,
+      "loss": 0.0613,
+      "step": 422
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.17097824811935425,
+      "learning_rate": 8.589495991946885e-06,
+      "loss": 0.0701,
+      "step": 423
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.5410835146903992,
+      "learning_rate": 8.583000111426277e-06,
+      "loss": 0.0655,
+      "step": 424
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.2845303416252136,
+      "learning_rate": 8.576491775822527e-06,
+      "loss": 0.0859,
+      "step": 425
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.2452799528837204,
+      "learning_rate": 8.569971007759657e-06,
+      "loss": 0.0538,
+      "step": 426
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.07323230057954788,
+      "eval_runtime": 14.7111,
+      "eval_samples_per_second": 32.356,
+      "eval_steps_per_second": 8.089,
+      "step": 426
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.6456173062324524,
+      "learning_rate": 8.563437829904904e-06,
+      "loss": 0.1131,
+      "step": 427
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.3903690278530121,
+      "learning_rate": 8.556892264968639e-06,
+      "loss": 0.0997,
+      "step": 428
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.33470049500465393,
+      "learning_rate": 8.550334335704298e-06,
+      "loss": 0.0987,
+      "step": 429
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1498459130525589,
+      "learning_rate": 8.543764064908295e-06,
+      "loss": 0.0524,
+      "step": 430
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.21974940598011017,
+      "learning_rate": 8.537181475419944e-06,
+      "loss": 0.0789,
+      "step": 431
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.16694916784763336,
+      "learning_rate": 8.530586590121384e-06,
+      "loss": 0.0731,
+      "step": 432
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.12150876969099045,
+      "learning_rate": 8.523979431937493e-06,
+      "loss": 0.0694,
+      "step": 433
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.17073531448841095,
+      "learning_rate": 8.51736002383581e-06,
+      "loss": 0.0698,
+      "step": 434
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.2708394527435303,
+      "learning_rate": 8.510728388826464e-06,
+      "loss": 0.0739,
+      "step": 435
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.1602393388748169,
+      "learning_rate": 8.504084549962079e-06,
+      "loss": 0.0709,
+      "step": 436
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.2071549892425537,
+      "learning_rate": 8.497428530337707e-06,
+      "loss": 0.0757,
+      "step": 437
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.1717323213815689,
+      "learning_rate": 8.490760353090738e-06,
+      "loss": 0.0802,
+      "step": 438
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.2539728879928589,
+      "learning_rate": 8.484080041400827e-06,
+      "loss": 0.0852,
+      "step": 439
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.15313653647899628,
+      "learning_rate": 8.477387618489808e-06,
+      "loss": 0.0788,
+      "step": 440
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.20286281406879425,
+      "learning_rate": 8.470683107621616e-06,
+      "loss": 0.0423,
+      "step": 441
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.21172399818897247,
+      "learning_rate": 8.463966532102207e-06,
+      "loss": 0.0575,
+      "step": 442
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.23021037876605988,
+      "learning_rate": 8.457237915279477e-06,
+      "loss": 0.0774,
+      "step": 443
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.14592242240905762,
+      "learning_rate": 8.450497280543174e-06,
+      "loss": 0.0699,
+      "step": 444
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.2122061848640442,
+      "learning_rate": 8.443744651324828e-06,
+      "loss": 0.0801,
+      "step": 445
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.21682047843933105,
+      "learning_rate": 8.43698005109766e-06,
+      "loss": 0.0478,
+      "step": 446
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.19426396489143372,
+      "learning_rate": 8.430203503376506e-06,
+      "loss": 0.0508,
+      "step": 447
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.14614954590797424,
+      "learning_rate": 8.423415031717734e-06,
+      "loss": 0.0712,
+      "step": 448
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.1340399831533432,
+      "learning_rate": 8.416614659719158e-06,
+      "loss": 0.0723,
+      "step": 449
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.16521310806274414,
+      "learning_rate": 8.409802411019962e-06,
+      "loss": 0.0486,
+      "step": 450
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3560049533843994,
+      "learning_rate": 8.40297830930062e-06,
+      "loss": 0.0868,
+      "step": 451
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.1964522898197174,
+      "learning_rate": 8.396142378282799e-06,
+      "loss": 0.046,
+      "step": 452
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.175230011343956,
+      "learning_rate": 8.389294641729293e-06,
+      "loss": 0.0659,
+      "step": 453
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.22042769193649292,
+      "learning_rate": 8.382435123443934e-06,
+      "loss": 0.0746,
+      "step": 454
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.19862250983715057,
+      "learning_rate": 8.375563847271506e-06,
+      "loss": 0.055,
+      "step": 455
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.24993905425071716,
+      "learning_rate": 8.36868083709767e-06,
+      "loss": 0.0858,
+      "step": 456
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.14945238828659058,
+      "learning_rate": 8.361786116848871e-06,
+      "loss": 0.0573,
+      "step": 457
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.43160539865493774,
+      "learning_rate": 8.354879710492264e-06,
+      "loss": 0.094,
+      "step": 458
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.5086230635643005,
+      "learning_rate": 8.347961642035624e-06,
+      "loss": 0.0956,
+      "step": 459
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.1694391518831253,
+      "learning_rate": 8.341031935527267e-06,
+      "loss": 0.0539,
+      "step": 460
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.2055732011795044,
+      "learning_rate": 8.334090615055966e-06,
+      "loss": 0.0564,
+      "step": 461
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.14689050614833832,
+      "learning_rate": 8.327137704750863e-06,
+      "loss": 0.0554,
+      "step": 462
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.3445436656475067,
+      "learning_rate": 8.32017322878139e-06,
+      "loss": 0.1029,
+      "step": 463
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1985045075416565,
+      "learning_rate": 8.31319721135718e-06,
+      "loss": 0.0703,
+      "step": 464
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.24056944251060486,
+      "learning_rate": 8.306209676727994e-06,
+      "loss": 0.0909,
+      "step": 465
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.20218642055988312,
+      "learning_rate": 8.29921064918362e-06,
+      "loss": 0.0658,
+      "step": 466
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.2052248865365982,
+      "learning_rate": 8.2922001530538e-06,
+      "loss": 0.0522,
+      "step": 467
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.2361009120941162,
+      "learning_rate": 8.285178212708143e-06,
+      "loss": 0.0674,
+      "step": 468
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.30261772871017456,
+      "learning_rate": 8.278144852556042e-06,
+      "loss": 0.0672,
+      "step": 469
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.3114418685436249,
+      "learning_rate": 8.271100097046585e-06,
+      "loss": 0.0762,
+      "step": 470
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.4094521701335907,
+      "learning_rate": 8.26404397066847e-06,
+      "loss": 0.0725,
+      "step": 471
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.23902684450149536,
+      "learning_rate": 8.256976497949924e-06,
+      "loss": 0.0408,
+      "step": 472
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.2393728494644165,
+      "learning_rate": 8.249897703458619e-06,
+      "loss": 0.0608,
+      "step": 473
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.24134708940982819,
+      "learning_rate": 8.242807611801578e-06,
+      "loss": 0.0369,
+      "step": 474
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.14594919979572296,
+      "learning_rate": 8.235706247625098e-06,
+      "loss": 0.0261,
+      "step": 475
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.32239043712615967,
+      "learning_rate": 8.228593635614659e-06,
+      "loss": 0.1011,
+      "step": 476
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.2879891097545624,
+      "learning_rate": 8.22146980049484e-06,
+      "loss": 0.0742,
+      "step": 477
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.5778201818466187,
+      "learning_rate": 8.21433476702924e-06,
+      "loss": 0.1146,
+      "step": 478
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.214900940656662,
+      "learning_rate": 8.207188560020374e-06,
+      "loss": 0.037,
+      "step": 479
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.22797343134880066,
+      "learning_rate": 8.200031204309604e-06,
+      "loss": 0.0595,
+      "step": 480
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.19148996472358704,
+      "learning_rate": 8.192862724777052e-06,
+      "loss": 0.0339,
+      "step": 481
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.15512730181217194,
+      "learning_rate": 8.185683146341496e-06,
+      "loss": 0.051,
+      "step": 482
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.20564667880535126,
+      "learning_rate": 8.178492493960309e-06,
+      "loss": 0.0453,
+      "step": 483
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.3061021566390991,
+      "learning_rate": 8.171290792629348e-06,
+      "loss": 0.033,
+      "step": 484
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.23765882849693298,
+      "learning_rate": 8.16407806738288e-06,
+      "loss": 0.0614,
+      "step": 485
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.3384253978729248,
+      "learning_rate": 8.156854343293501e-06,
+      "loss": 0.0662,
+      "step": 486
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.1890600174665451,
+      "learning_rate": 8.149619645472031e-06,
+      "loss": 0.0495,
+      "step": 487
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.30018725991249084,
+      "learning_rate": 8.14237399906744e-06,
+      "loss": 0.0722,
+      "step": 488
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.31263217329978943,
+      "learning_rate": 8.135117429266756e-06,
+      "loss": 0.0693,
+      "step": 489
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.18034443259239197,
+      "learning_rate": 8.127849961294984e-06,
+      "loss": 0.0409,
+      "step": 490
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.23813746869564056,
+      "learning_rate": 8.120571620415007e-06,
+      "loss": 0.0433,
+      "step": 491
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.23636382818222046,
+      "learning_rate": 8.113282431927502e-06,
+      "loss": 0.0544,
+      "step": 492
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.5150755047798157,
+      "learning_rate": 8.10598242117086e-06,
+      "loss": 0.1072,
+      "step": 493
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.3001669645309448,
+      "learning_rate": 8.09867161352109e-06,
+      "loss": 0.0414,
+      "step": 494
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.228012353181839,
+      "learning_rate": 8.091350034391732e-06,
+      "loss": 0.0701,
+      "step": 495
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.3816164433956146,
+      "learning_rate": 8.084017709233767e-06,
+      "loss": 0.0723,
+      "step": 496
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.32659652829170227,
+      "learning_rate": 8.076674663535537e-06,
+      "loss": 0.0697,
+      "step": 497
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.48343512415885925,
+      "learning_rate": 8.069320922822644e-06,
+      "loss": 0.1034,
+      "step": 498
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.29286321997642517,
+      "learning_rate": 8.061956512657872e-06,
+      "loss": 0.075,
+      "step": 499
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.4552519917488098,
+      "learning_rate": 8.05458145864109e-06,
+      "loss": 0.0568,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.3469892740249634,
+      "learning_rate": 8.047195786409172e-06,
+      "loss": 0.0661,
+      "step": 501
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.1452968716621399,
+      "learning_rate": 8.039799521635896e-06,
+      "loss": 0.0226,
+      "step": 502
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.25091221928596497,
+      "learning_rate": 8.032392690031868e-06,
+      "loss": 0.0486,
+      "step": 503
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.1830379068851471,
+      "learning_rate": 8.024975317344421e-06,
+      "loss": 0.0448,
+      "step": 504
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.32811227440834045,
+      "learning_rate": 8.017547429357532e-06,
+      "loss": 0.055,
+      "step": 505
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.24694731831550598,
+      "learning_rate": 8.010109051891731e-06,
+      "loss": 0.0614,
+      "step": 506
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.3512776792049408,
+      "learning_rate": 8.002660210804011e-06,
+      "loss": 0.0699,
+      "step": 507
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2562338709831238,
+      "learning_rate": 7.995200931987744e-06,
+      "loss": 0.0726,
+      "step": 508
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.38721486926078796,
+      "learning_rate": 7.987731241372572e-06,
+      "loss": 0.0798,
+      "step": 509
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.24697037041187286,
+      "learning_rate": 7.980251164924342e-06,
+      "loss": 0.0657,
+      "step": 510
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.5245312452316284,
+      "learning_rate": 7.972760728644995e-06,
+      "loss": 0.0575,
+      "step": 511
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.29805997014045715,
+      "learning_rate": 7.965259958572495e-06,
+      "loss": 0.052,
+      "step": 512
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.21135053038597107,
+      "learning_rate": 7.957748880780722e-06,
+      "loss": 0.0378,
+      "step": 513
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.23149773478507996,
+      "learning_rate": 7.950227521379382e-06,
+      "loss": 0.0726,
+      "step": 514
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.19880171120166779,
+      "learning_rate": 7.94269590651393e-06,
+      "loss": 0.0714,
+      "step": 515
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.28021228313446045,
+      "learning_rate": 7.935154062365468e-06,
+      "loss": 0.0634,
+      "step": 516
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.21841171383857727,
+      "learning_rate": 7.927602015150655e-06,
+      "loss": 0.0625,
+      "step": 517
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1774914562702179,
+      "learning_rate": 7.920039791121617e-06,
+      "loss": 0.0321,
+      "step": 518
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.38757917284965515,
+      "learning_rate": 7.91246741656586e-06,
+      "loss": 0.1069,
+      "step": 519
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.19643576443195343,
+      "learning_rate": 7.904884917806174e-06,
+      "loss": 0.0409,
+      "step": 520
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.2885828912258148,
+      "learning_rate": 7.897292321200538e-06,
+      "loss": 0.0514,
+      "step": 521
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.4019085168838501,
+      "learning_rate": 7.889689653142037e-06,
+      "loss": 0.089,
+      "step": 522
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.350379079580307,
+      "learning_rate": 7.882076940058764e-06,
+      "loss": 0.0505,
+      "step": 523
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.3123965859413147,
+      "learning_rate": 7.87445420841373e-06,
+      "loss": 0.0555,
+      "step": 524
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.21883922815322876,
+      "learning_rate": 7.866821484704777e-06,
+      "loss": 0.0439,
+      "step": 525
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.2795931100845337,
+      "learning_rate": 7.859178795464473e-06,
+      "loss": 0.0757,
+      "step": 526
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.3848627507686615,
+      "learning_rate": 7.851526167260034e-06,
+      "loss": 0.0995,
+      "step": 527
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.5650475025177002,
+      "learning_rate": 7.843863626693221e-06,
+      "loss": 0.0956,
+      "step": 528
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.20236073434352875,
+      "learning_rate": 7.836191200400257e-06,
+      "loss": 0.0629,
+      "step": 529
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.19835765659809113,
+      "learning_rate": 7.828508915051724e-06,
+      "loss": 0.0661,
+      "step": 530
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.2083461880683899,
+      "learning_rate": 7.82081679735248e-06,
+      "loss": 0.051,
+      "step": 531
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.4042919874191284,
+      "learning_rate": 7.813114874041558e-06,
+      "loss": 0.0736,
+      "step": 532
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.20774157345294952,
+      "learning_rate": 7.80540317189208e-06,
+      "loss": 0.0578,
+      "step": 533
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.20473290979862213,
+      "learning_rate": 7.797681717711162e-06,
+      "loss": 0.0471,
+      "step": 534
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.2514810562133789,
+      "learning_rate": 7.789950538339813e-06,
+      "loss": 0.0665,
+      "step": 535
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.43802833557128906,
+      "learning_rate": 7.782209660652855e-06,
+      "loss": 0.087,
+      "step": 536
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.2503105103969574,
+      "learning_rate": 7.774459111558821e-06,
+      "loss": 0.0819,
+      "step": 537
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.16841083765029907,
+      "learning_rate": 7.766698917999862e-06,
+      "loss": 0.0505,
+      "step": 538
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.3313782513141632,
+      "learning_rate": 7.758929106951656e-06,
+      "loss": 0.0713,
+      "step": 539
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.16334685683250427,
+      "learning_rate": 7.751149705423313e-06,
+      "loss": 0.044,
+      "step": 540
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.4028722941875458,
+      "learning_rate": 7.743360740457278e-06,
+      "loss": 0.0847,
+      "step": 541
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.24219095706939697,
+      "learning_rate": 7.735562239129248e-06,
+      "loss": 0.0848,
+      "step": 542
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.19837279617786407,
+      "learning_rate": 7.72775422854806e-06,
+      "loss": 0.0331,
+      "step": 543
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.21855801343917847,
+      "learning_rate": 7.719936735855611e-06,
+      "loss": 0.0473,
+      "step": 544
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.1909436583518982,
+      "learning_rate": 7.712109788226763e-06,
+      "loss": 0.0694,
+      "step": 545
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.37223267555236816,
+      "learning_rate": 7.704273412869239e-06,
+      "loss": 0.077,
+      "step": 546
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.33873534202575684,
+      "learning_rate": 7.696427637023537e-06,
+      "loss": 0.0391,
+      "step": 547
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.22075894474983215,
+      "learning_rate": 7.688572487962836e-06,
+      "loss": 0.0363,
+      "step": 548
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.3139945864677429,
+      "learning_rate": 7.680707992992889e-06,
+      "loss": 0.0676,
+      "step": 549
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.24971792101860046,
+      "learning_rate": 7.672834179451943e-06,
+      "loss": 0.0561,
+      "step": 550
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2864936292171478,
+      "learning_rate": 7.664951074710638e-06,
+      "loss": 0.0885,
+      "step": 551
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.32206228375434875,
+      "learning_rate": 7.657058706171912e-06,
+      "loss": 0.065,
+      "step": 552
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.28918203711509705,
+      "learning_rate": 7.649157101270904e-06,
+      "loss": 0.108,
+      "step": 553
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2585963308811188,
+      "learning_rate": 7.641246287474856e-06,
+      "loss": 0.0536,
+      "step": 554
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.4212508797645569,
+      "learning_rate": 7.633326292283028e-06,
+      "loss": 0.0857,
+      "step": 555
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1916050761938095,
+      "learning_rate": 7.625397143226596e-06,
+      "loss": 0.0597,
+      "step": 556
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.678855299949646,
+      "learning_rate": 7.617458867868554e-06,
+      "loss": 0.0759,
+      "step": 557
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.3328985273838043,
+      "learning_rate": 7.609511493803616e-06,
+      "loss": 0.0545,
+      "step": 558
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2722048759460449,
+      "learning_rate": 7.601555048658133e-06,
+      "loss": 0.0633,
+      "step": 559
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2508256733417511,
+      "learning_rate": 7.593589560089984e-06,
+      "loss": 0.0571,
+      "step": 560
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.49203789234161377,
+      "learning_rate": 7.585615055788484e-06,
+      "loss": 0.0834,
+      "step": 561
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2127446085214615,
+      "learning_rate": 7.577631563474291e-06,
+      "loss": 0.0658,
+      "step": 562
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6191400289535522,
+      "learning_rate": 7.569639110899303e-06,
+      "loss": 0.0848,
+      "step": 563
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.22974306344985962,
+      "learning_rate": 7.561637725846568e-06,
+      "loss": 0.0493,
+      "step": 564
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6743472814559937,
+      "learning_rate": 7.553627436130183e-06,
+      "loss": 0.139,
+      "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 sha256:2667f02973c48c9daa1abbdc506826bb40abce66f6990081fb40359affcf7486
+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
+}