Upload folder using huggingface_hub

README.md

@@ -0,0 +1,156 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: Qwen/Qwen1.5-7B
+model-index:
+- name: home/yujia/home/CN_Hateful/trained_models/qwen/CN/toxi/3e-5/
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+# base_model: Qwen/Qwen-7B
+base_model: Qwen/Qwen1.5-7B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+trust_remote_code: true
+
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+
+datasets:
+  # - path: mhenrichsen/alpaca_2k_test
+  - path: /home/yujia/home/CN_Hateful/train_toxiCN_cn.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/
+
+sequence_len: 256  # supports up to 8192
+sample_packing: false
+pad_to_sequence_len:
+
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_project:
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 4
+micro_batch_size: 2
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.00003
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention:
+
+warmup_steps: 10
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 20
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# home/yujia/home/CN_Hateful/trained_models/qwen/CN/toxi/3e-5/
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0712
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.3182        | 0.0   | 1    | 3.3363          |
+| 0.0815        | 0.25  | 142  | 0.0904          |
+| 0.022         | 0.5   | 284  | 0.0816          |
+| 0.1295        | 0.75  | 426  | 0.0785          |
+| 0.0869        | 1.0   | 568  | 0.0801          |
+| 0.087         | 1.26  | 710  | 0.0744          |
+| 0.0724        | 1.51  | 852  | 0.0710          |
+| 0.0663        | 1.76  | 994  | 0.0759          |
+| 0.0447        | 2.01  | 1136 | 0.0711          |
+| 0.0402        | 2.26  | 1278 | 0.0715          |
+| 0.0623        | 2.51  | 1420 | 0.0712          |
+| 0.0285        | 2.76  | 1562 | 0.0712          |
+
+
+### 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": [
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_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 sha256:7404ae856a1f0a1713c3e857cbc7bd907b4a738417d8972763cf4b0441581065
+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": [
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_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 sha256:13d85681b7760ec2d81a1a87a5320870309a1c5f380c9e5cb10f2230d5856e8a
+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:b0887a81024a89e9984a93fe71e0a267dc58b5bb92a5a5ab6c8d97a0d99ec66d
+size 160736532

checkpoint-1130/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4901585e9d75e84023ab72e4541020015ec7f9e3a44dd30228bed49938a1bc
+size 14512

checkpoint-1130/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52b8bbcff4bb55ccbed97b61cc7bef4a35d002ff92406d2e23baa476f0a8d21
+size 14512

checkpoint-1130/scheduler.pt

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

checkpoint-1130/special_tokens_map.json

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

checkpoint-1130/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1130/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79597bc285f43a30d268224af285fdf02eba4cbe9e0332db42b2b4ac018fc35e
+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": [
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_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 sha256:5313b81f8f002957f9d4e597cb9e3028b14f3046dbe2396dd5e4fea1dfca2821
+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 sha256:749992b86a5b417ecbb451918ffbfff89f147d062e842a722b07d51eb44357a9
+size 160736532

checkpoint-1695/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55ad0de153a9394c92810ea3c27399952a305bd25451ed430aaf933a9a5e55c
+size 14512

checkpoint-1695/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49270efca7489b54d9139d7c93770e62001cb2f4e09707c29e75b02ffb96afb7
+size 14512

checkpoint-1695/scheduler.pt

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

checkpoint-1695/special_tokens_map.json

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

checkpoint-1695/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1695/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79597bc285f43a30d268224af285fdf02eba4cbe9e0332db42b2b4ac018fc35e
+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": [
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_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:e7ae236bdddb4ca164b86e651297e29f0540918e164caecf16a7289abc460053
+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:ad9910e7149b9d3102b54d72a7c652298e5da299fede09a415d2a9998ec927ae
+size 160736532

checkpoint-565/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a681c33ffd6b61feaf98d05f702d37f2e4cea5ae28ff9fe027ab78959f6d28
+size 14512

checkpoint-565/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:264fc0be051e80523f0b0faf9f50191b6a6d8a450a601ac7a6354029ee14de9c
+size 14512

checkpoint-565/scheduler.pt

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

checkpoint-565/special_tokens_map.json

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

checkpoint-565/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-565/trainer_state.json

@@ -0,0 +1,4008 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9995577178239717,
+  "eval_steps": 142,
+  "global_step": 565,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 4.582726955413818,
+      "learning_rate": 3e-06,
+      "loss": 3.3182,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 3.3362529277801514,
+      "eval_runtime": 14.4066,
+      "eval_samples_per_second": 33.11,
+      "eval_steps_per_second": 8.329,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 4.511408805847168,
+      "learning_rate": 6e-06,
+      "loss": 3.2788,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.698073387145996,
+      "learning_rate": 9e-06,
+      "loss": 3.3753,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.63289213180542,
+      "learning_rate": 1.2e-05,
+      "loss": 3.3188,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.522731781005859,
+      "learning_rate": 1.5e-05,
+      "loss": 3.3082,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.691629409790039,
+      "learning_rate": 1.8e-05,
+      "loss": 3.2839,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.7225470542907715,
+      "learning_rate": 2.1e-05,
+      "loss": 3.2686,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.691238880157471,
+      "learning_rate": 2.4e-05,
+      "loss": 3.0782,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.64508581161499,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 2.9714,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.355061054229736,
+      "learning_rate": 3e-05,
+      "loss": 2.6886,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.206029891967773,
+      "learning_rate": 2.9999973928796923e-05,
+      "loss": 2.4829,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.8142871856689453,
+      "learning_rate": 2.999989571527831e-05,
+      "loss": 2.0556,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.5461277961730957,
+      "learning_rate": 2.9999765359716046e-05,
+      "loss": 1.6669,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.3414511680603027,
+      "learning_rate": 2.999958286256327e-05,
+      "loss": 1.3396,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 3.0794336795806885,
+      "learning_rate": 2.9999348224454367e-05,
+      "loss": 1.0494,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.524055242538452,
+      "learning_rate": 2.9999061446204985e-05,
+      "loss": 0.7706,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.8878108263015747,
+      "learning_rate": 2.9998722528812e-05,
+      "loss": 0.5666,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.5863118171691895,
+      "learning_rate": 2.9998331473453557e-05,
+      "loss": 0.4017,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.3763269186019897,
+      "learning_rate": 2.9997888281489015e-05,
+      "loss": 0.3645,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.0631593465805054,
+      "learning_rate": 2.9997392954458985e-05,
+      "loss": 0.2886,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9699187278747559,
+      "learning_rate": 2.9996845494085306e-05,
+      "loss": 0.1911,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8020363450050354,
+      "learning_rate": 2.999624590227103e-05,
+      "loss": 0.1762,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8209808468818665,
+      "learning_rate": 2.9995594181100443e-05,
+      "loss": 0.1449,
+      "step": 23
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.39430710673332214,
+      "learning_rate": 2.9994890332839027e-05,
+      "loss": 0.1201,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9686388969421387,
+      "learning_rate": 2.9994134359933476e-05,
+      "loss": 0.1421,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.3096848726272583,
+      "learning_rate": 2.999332626501167e-05,
+      "loss": 0.1178,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.7969554662704468,
+      "learning_rate": 2.9992466050882673e-05,
+      "loss": 0.1127,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.6500488519668579,
+      "learning_rate": 2.9991553720536733e-05,
+      "loss": 0.0909,
+      "step": 28
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.3015730381011963,
+      "learning_rate": 2.9990589277145254e-05,
+      "loss": 0.2658,
+      "step": 29
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9849212169647217,
+      "learning_rate": 2.9989572724060797e-05,
+      "loss": 0.0956,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.366385579109192,
+      "learning_rate": 2.998850406481707e-05,
+      "loss": 0.1276,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.42471978068351746,
+      "learning_rate": 2.9987383303128887e-05,
+      "loss": 0.0885,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.2538015842437744,
+      "learning_rate": 2.9986210442892215e-05,
+      "loss": 0.1246,
+      "step": 33
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.9688710570335388,
+      "learning_rate": 2.9984985488184086e-05,
+      "loss": 0.147,
+      "step": 34
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4737780690193176,
+      "learning_rate": 2.9983708443262656e-05,
+      "loss": 0.1141,
+      "step": 35
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.33743003010749817,
+      "learning_rate": 2.9982379312567126e-05,
+      "loss": 0.119,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.49797967076301575,
+      "learning_rate": 2.998099810071777e-05,
+      "loss": 0.1319,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.8518417477607727,
+      "learning_rate": 2.9979564812515906e-05,
+      "loss": 0.1609,
+      "step": 38
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.2824989855289459,
+      "learning_rate": 2.9978079452943875e-05,
+      "loss": 0.1126,
+      "step": 39
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.2989768981933594,
+      "learning_rate": 2.9976542027165016e-05,
+      "loss": 0.1164,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.49210599064826965,
+      "learning_rate": 2.9974952540523676e-05,
+      "loss": 0.1175,
+      "step": 41
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.35604602098464966,
+      "learning_rate": 2.997331099854516e-05,
+      "loss": 0.0876,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6768718957901001,
+      "learning_rate": 2.9971617406935735e-05,
+      "loss": 0.1649,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4443073868751526,
+      "learning_rate": 2.9969871771582596e-05,
+      "loss": 0.0655,
+      "step": 44
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.8104651570320129,
+      "learning_rate": 2.996807409855385e-05,
+      "loss": 0.1336,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4232860803604126,
+      "learning_rate": 2.99662243940985e-05,
+      "loss": 0.0993,
+      "step": 46
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5418788194656372,
+      "learning_rate": 2.9964322664646412e-05,
+      "loss": 0.1131,
+      "step": 47
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.39015039801597595,
+      "learning_rate": 2.9962368916808308e-05,
+      "loss": 0.13,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.40271061658859253,
+      "learning_rate": 2.9960363157375724e-05,
+      "loss": 0.1088,
+      "step": 49
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.23656688630580902,
+      "learning_rate": 2.9958305393321e-05,
+      "loss": 0.1209,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4160294234752655,
+      "learning_rate": 2.995619563179726e-05,
+      "loss": 0.1214,
+      "step": 51
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.25202676653862,
+      "learning_rate": 2.9954033880138368e-05,
+      "loss": 0.115,
+      "step": 52
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.5302817821502686,
+      "learning_rate": 2.995182014585892e-05,
+      "loss": 0.124,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.063620924949646,
+      "learning_rate": 2.9949554436654215e-05,
+      "loss": 0.1347,
+      "step": 54
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.3588281273841858,
+      "learning_rate": 2.994723676040022e-05,
+      "loss": 0.0931,
+      "step": 55
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.6446585059165955,
+      "learning_rate": 2.9944867125153548e-05,
+      "loss": 0.1108,
+      "step": 56
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.31614363193511963,
+      "learning_rate": 2.9942445539151432e-05,
+      "loss": 0.0712,
+      "step": 57
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.2502954304218292,
+      "learning_rate": 2.9939972010811693e-05,
+      "loss": 0.0914,
+      "step": 58
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.33516696095466614,
+      "learning_rate": 2.993744654873272e-05,
+      "loss": 0.0923,
+      "step": 59
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2990712821483612,
+      "learning_rate": 2.993486916169341e-05,
+      "loss": 0.0899,
+      "step": 60
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.40888020396232605,
+      "learning_rate": 2.9932239858653183e-05,
+      "loss": 0.0789,
+      "step": 61
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.756536602973938,
+      "learning_rate": 2.992955864875192e-05,
+      "loss": 0.1707,
+      "step": 62
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.3337976932525635,
+      "learning_rate": 2.9926825541309928e-05,
+      "loss": 0.0676,
+      "step": 63
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.6163253784179688,
+      "learning_rate": 2.9924040545827936e-05,
+      "loss": 0.0961,
+      "step": 64
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.45453113317489624,
+      "learning_rate": 2.9921203671987025e-05,
+      "loss": 0.0724,
+      "step": 65
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.64926677942276,
+      "learning_rate": 2.9918314929648637e-05,
+      "loss": 0.1015,
+      "step": 66
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.37845009565353394,
+      "learning_rate": 2.991537432885449e-05,
+      "loss": 0.0964,
+      "step": 67
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.3352985382080078,
+      "learning_rate": 2.991238187982659e-05,
+      "loss": 0.0862,
+      "step": 68
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.485416442155838,
+      "learning_rate": 2.9909337592967176e-05,
+      "loss": 0.1095,
+      "step": 69
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.9582281708717346,
+      "learning_rate": 2.9906241478858666e-05,
+      "loss": 0.1314,
+      "step": 70
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.3674233555793762,
+      "learning_rate": 2.990309354826366e-05,
+      "loss": 0.109,
+      "step": 71
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.408796101808548,
+      "learning_rate": 2.9899893812124862e-05,
+      "loss": 0.126,
+      "step": 72
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.5258140563964844,
+      "learning_rate": 2.989664228156507e-05,
+      "loss": 0.0596,
+      "step": 73
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.3256467580795288,
+      "learning_rate": 2.9893338967887128e-05,
+      "loss": 0.0736,
+      "step": 74
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.22679170966148376,
+      "learning_rate": 2.988998388257388e-05,
+      "loss": 0.0982,
+      "step": 75
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.2959941625595093,
+      "learning_rate": 2.988657703728815e-05,
+      "loss": 0.0515,
+      "step": 76
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.26353922486305237,
+      "learning_rate": 2.9883118443872662e-05,
+      "loss": 0.0732,
+      "step": 77
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.23671653866767883,
+      "learning_rate": 2.9879608114350064e-05,
+      "loss": 0.0865,
+      "step": 78
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.415596067905426,
+      "learning_rate": 2.9876046060922803e-05,
+      "loss": 0.0871,
+      "step": 79
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.5430477261543274,
+      "learning_rate": 2.987243229597316e-05,
+      "loss": 0.1385,
+      "step": 80
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.6044889092445374,
+      "learning_rate": 2.9868766832063156e-05,
+      "loss": 0.1279,
+      "step": 81
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.452231764793396,
+      "learning_rate": 2.986504968193454e-05,
+      "loss": 0.0767,
+      "step": 82
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.3864612579345703,
+      "learning_rate": 2.9861280858508712e-05,
+      "loss": 0.0728,
+      "step": 83
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.3158702850341797,
+      "learning_rate": 2.9857460374886717e-05,
+      "loss": 0.087,
+      "step": 84
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.448408842086792,
+      "learning_rate": 2.985358824434916e-05,
+      "loss": 0.078,
+      "step": 85
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.4518391788005829,
+      "learning_rate": 2.984966448035619e-05,
+      "loss": 0.1013,
+      "step": 86
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.9920629858970642,
+      "learning_rate": 2.9845689096547442e-05,
+      "loss": 0.1145,
+      "step": 87
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5967357754707336,
+      "learning_rate": 2.9841662106741986e-05,
+      "loss": 0.1132,
+      "step": 88
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5016050338745117,
+      "learning_rate": 2.983758352493829e-05,
+      "loss": 0.094,
+      "step": 89
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.300605833530426,
+      "learning_rate": 2.983345336531415e-05,
+      "loss": 0.0762,
+      "step": 90
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.44358232617378235,
+      "learning_rate": 2.9829271642226665e-05,
+      "loss": 0.0969,
+      "step": 91
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.9166831374168396,
+      "learning_rate": 2.9825038370212183e-05,
+      "loss": 0.1532,
+      "step": 92
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.6240636706352234,
+      "learning_rate": 2.982075356398623e-05,
+      "loss": 0.1351,
+      "step": 93
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.34054040908813477,
+      "learning_rate": 2.9816417238443482e-05,
+      "loss": 0.0803,
+      "step": 94
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.3595755100250244,
+      "learning_rate": 2.9812029408657698e-05,
+      "loss": 0.0522,
+      "step": 95
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.4143121540546417,
+      "learning_rate": 2.9807590089881687e-05,
+      "loss": 0.0816,
+      "step": 96
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.2190728336572647,
+      "learning_rate": 2.980309929754722e-05,
+      "loss": 0.0606,
+      "step": 97
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.23459163308143616,
+      "learning_rate": 2.9798557047265023e-05,
+      "loss": 0.0841,
+      "step": 98
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.24551355838775635,
+      "learning_rate": 2.979396335482469e-05,
+      "loss": 0.0545,
+      "step": 99
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.471500426530838,
+      "learning_rate": 2.9789318236194618e-05,
+      "loss": 0.0948,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.5168260335922241,
+      "learning_rate": 2.9784621707521993e-05,
+      "loss": 0.1471,
+      "step": 101
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.7932892441749573,
+      "learning_rate": 2.97798737851327e-05,
+      "loss": 0.1101,
+      "step": 102
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.32231828570365906,
+      "learning_rate": 2.977507448553128e-05,
+      "loss": 0.0525,
+      "step": 103
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.30824771523475647,
+      "learning_rate": 2.9770223825400872e-05,
+      "loss": 0.0965,
+      "step": 104
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.5549985766410828,
+      "learning_rate": 2.9765321821603143e-05,
+      "loss": 0.1105,
+      "step": 105
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.6406698822975159,
+      "learning_rate": 2.9760368491178244e-05,
+      "loss": 0.1111,
+      "step": 106
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.3495526909828186,
+      "learning_rate": 2.9755363851344753e-05,
+      "loss": 0.0792,
+      "step": 107
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.3962193429470062,
+      "learning_rate": 2.9750307919499595e-05,
+      "loss": 0.0894,
+      "step": 108
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.5372034907341003,
+      "learning_rate": 2.9745200713218002e-05,
+      "loss": 0.1735,
+      "step": 109
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.22693391144275665,
+      "learning_rate": 2.9740042250253443e-05,
+      "loss": 0.0603,
+      "step": 110
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.4251677393913269,
+      "learning_rate": 2.973483254853756e-05,
+      "loss": 0.1124,
+      "step": 111
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.22285960614681244,
+      "learning_rate": 2.9729571626180116e-05,
+      "loss": 0.0677,
+      "step": 112
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.18614518642425537,
+      "learning_rate": 2.972425950146891e-05,
+      "loss": 0.0854,
+      "step": 113
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.3953099250793457,
+      "learning_rate": 2.9718896192869758e-05,
+      "loss": 0.0832,
+      "step": 114
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2483922243118286,
+      "learning_rate": 2.9713481719026368e-05,
+      "loss": 0.0992,
+      "step": 115
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.3185414969921112,
+      "learning_rate": 2.970801609876032e-05,
+      "loss": 0.0707,
+      "step": 116
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.40958282351493835,
+      "learning_rate": 2.9702499351070992e-05,
+      "loss": 0.1019,
+      "step": 117
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.5805838704109192,
+      "learning_rate": 2.969693149513548e-05,
+      "loss": 0.116,
+      "step": 118
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.21251153945922852,
+      "learning_rate": 2.969131255030855e-05,
+      "loss": 0.0843,
+      "step": 119
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.4262985587120056,
+      "learning_rate": 2.9685642536122545e-05,
+      "loss": 0.0706,
+      "step": 120
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.4474552869796753,
+      "learning_rate": 2.9679921472287358e-05,
+      "loss": 0.0859,
+      "step": 121
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.3137888014316559,
+      "learning_rate": 2.967414937869031e-05,
+      "loss": 0.1316,
+      "step": 122
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2894512712955475,
+      "learning_rate": 2.9668326275396133e-05,
+      "loss": 0.0715,
+      "step": 123
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2738913595676422,
+      "learning_rate": 2.966245218264687e-05,
+      "loss": 0.0524,
+      "step": 124
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.6975142955780029,
+      "learning_rate": 2.96565271208618e-05,
+      "loss": 0.1225,
+      "step": 125
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.5777083039283752,
+      "learning_rate": 2.9650551110637397e-05,
+      "loss": 0.1309,
+      "step": 126
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.8783730864524841,
+      "learning_rate": 2.964452417274723e-05,
+      "loss": 0.0995,
+      "step": 127
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.28593194484710693,
+      "learning_rate": 2.96384463281419e-05,
+      "loss": 0.0771,
+      "step": 128
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.35265710949897766,
+      "learning_rate": 2.9632317597948968e-05,
+      "loss": 0.0696,
+      "step": 129
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.4801347851753235,
+      "learning_rate": 2.9626138003472884e-05,
+      "loss": 0.0954,
+      "step": 130
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.7368841171264648,
+      "learning_rate": 2.9619907566194915e-05,
+      "loss": 0.1493,
+      "step": 131
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.3211562931537628,
+      "learning_rate": 2.9613626307773055e-05,
+      "loss": 0.0721,
+      "step": 132
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2380824089050293,
+      "learning_rate": 2.9607294250041965e-05,
+      "loss": 0.0574,
+      "step": 133
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4969393312931061,
+      "learning_rate": 2.96009114150129e-05,
+      "loss": 0.0463,
+      "step": 134
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.4968222379684448,
+      "learning_rate": 2.959447782487361e-05,
+      "loss": 0.1302,
+      "step": 135
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.5577062368392944,
+      "learning_rate": 2.9587993501988292e-05,
+      "loss": 0.1239,
+      "step": 136
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.5446056127548218,
+      "learning_rate": 2.958145846889749e-05,
+      "loss": 0.1169,
+      "step": 137
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.3976798355579376,
+      "learning_rate": 2.957487274831803e-05,
+      "loss": 0.1012,
+      "step": 138
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.6089766621589661,
+      "learning_rate": 2.9568236363142927e-05,
+      "loss": 0.0859,
+      "step": 139
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.3312886655330658,
+      "learning_rate": 2.9561549336441333e-05,
+      "loss": 0.0996,
+      "step": 140
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.3692180812358856,
+      "learning_rate": 2.955481169145841e-05,
+      "loss": 0.0958,
+      "step": 141
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.23727117478847504,
+      "learning_rate": 2.95480234516153e-05,
+      "loss": 0.0815,
+      "step": 142
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.09037704020738602,
+      "eval_runtime": 14.7372,
+      "eval_samples_per_second": 32.367,
+      "eval_steps_per_second": 8.143,
+      "step": 142
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.44341254234313965,
+      "learning_rate": 2.9541184640509015e-05,
+      "loss": 0.108,
+      "step": 143
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.27407336235046387,
+      "learning_rate": 2.953429528191236e-05,
+      "loss": 0.1192,
+      "step": 144
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.39919063448905945,
+      "learning_rate": 2.9527355399773847e-05,
+      "loss": 0.0832,
+      "step": 145
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.3581640422344208,
+      "learning_rate": 2.9520365018217622e-05,
+      "loss": 0.0625,
+      "step": 146
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.29779088497161865,
+      "learning_rate": 2.951332416154337e-05,
+      "loss": 0.111,
+      "step": 147
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.21348236501216888,
+      "learning_rate": 2.9506232854226242e-05,
+      "loss": 0.092,
+      "step": 148
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.3025546073913574,
+      "learning_rate": 2.9499091120916757e-05,
+      "loss": 0.1217,
+      "step": 149
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.24288436770439148,
+      "learning_rate": 2.9491898986440726e-05,
+      "loss": 0.0752,
+      "step": 150
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.22768545150756836,
+      "learning_rate": 2.9484656475799164e-05,
+      "loss": 0.0964,
+      "step": 151
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.7110497355461121,
+      "learning_rate": 2.9477363614168197e-05,
+      "loss": 0.1099,
+      "step": 152
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.7041640281677246,
+      "learning_rate": 2.9470020426898983e-05,
+      "loss": 0.1599,
+      "step": 153
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.4882669746875763,
+      "learning_rate": 2.946262693951762e-05,
+      "loss": 0.1059,
+      "step": 154
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.2939213812351227,
+      "learning_rate": 2.9455183177725055e-05,
+      "loss": 0.0776,
+      "step": 155
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.25689342617988586,
+      "learning_rate": 2.9447689167397e-05,
+      "loss": 0.098,
+      "step": 156
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.22836799919605255,
+      "learning_rate": 2.944014493458383e-05,
+      "loss": 0.0838,
+      "step": 157
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.525640606880188,
+      "learning_rate": 2.9432550505510516e-05,
+      "loss": 0.0958,
+      "step": 158
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.6011547446250916,
+      "learning_rate": 2.942490590657651e-05,
+      "loss": 0.1154,
+      "step": 159
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.3123567998409271,
+      "learning_rate": 2.9417211164355668e-05,
+      "loss": 0.1097,
+      "step": 160
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.39742252230644226,
+      "learning_rate": 2.9409466305596135e-05,
+      "loss": 0.0671,
+      "step": 161
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.2927655279636383,
+      "learning_rate": 2.9401671357220297e-05,
+      "loss": 0.0752,
+      "step": 162
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.6094531416893005,
+      "learning_rate": 2.9393826346324634e-05,
+      "loss": 0.1437,
+      "step": 163
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.23876389861106873,
+      "learning_rate": 2.9385931300179675e-05,
+      "loss": 0.1064,
+      "step": 164
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.26306307315826416,
+      "learning_rate": 2.9377986246229853e-05,
+      "loss": 0.065,
+      "step": 165
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.3406679332256317,
+      "learning_rate": 2.9369991212093462e-05,
+      "loss": 0.0939,
+      "step": 166
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.5959851741790771,
+      "learning_rate": 2.9361946225562516e-05,
+      "loss": 0.1163,
+      "step": 167
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.3201580047607422,
+      "learning_rate": 2.9353851314602676e-05,
+      "loss": 0.115,
+      "step": 168
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.4657009243965149,
+      "learning_rate": 2.9345706507353158e-05,
+      "loss": 0.0877,
+      "step": 169
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.313793420791626,
+      "learning_rate": 2.9337511832126616e-05,
+      "loss": 0.0574,
+      "step": 170
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2866755723953247,
+      "learning_rate": 2.9329267317409053e-05,
+      "loss": 0.0968,
+      "step": 171
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2852758765220642,
+      "learning_rate": 2.9320972991859728e-05,
+      "loss": 0.1091,
+      "step": 172
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.3556657135486603,
+      "learning_rate": 2.9312628884311048e-05,
+      "loss": 0.0716,
+      "step": 173
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.3235069215297699,
+      "learning_rate": 2.9304235023768465e-05,
+      "loss": 0.0532,
+      "step": 174
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.3486980199813843,
+      "learning_rate": 2.9295791439410387e-05,
+      "loss": 0.1146,
+      "step": 175
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.319968044757843,
+      "learning_rate": 2.9287298160588073e-05,
+      "loss": 0.1007,
+      "step": 176
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.48733624815940857,
+      "learning_rate": 2.927875521682551e-05,
+      "loss": 0.1164,
+      "step": 177
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.2947496473789215,
+      "learning_rate": 2.9270162637819352e-05,
+      "loss": 0.0434,
+      "step": 178
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.35532888770103455,
+      "learning_rate": 2.9261520453438775e-05,
+      "loss": 0.0498,
+      "step": 179
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5203955173492432,
+      "learning_rate": 2.9252828693725404e-05,
+      "loss": 0.1061,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4153119921684265,
+      "learning_rate": 2.9244087388893187e-05,
+      "loss": 0.0953,
+      "step": 181
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.41368868947029114,
+      "learning_rate": 2.9235296569328303e-05,
+      "loss": 0.1015,
+      "step": 182
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4907214343547821,
+      "learning_rate": 2.922645626558905e-05,
+      "loss": 0.1213,
+      "step": 183
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.2939632833003998,
+      "learning_rate": 2.921756650840574e-05,
+      "loss": 0.0757,
+      "step": 184
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.36250534653663635,
+      "learning_rate": 2.92086273286806e-05,
+      "loss": 0.0983,
+      "step": 185
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.34401020407676697,
+      "learning_rate": 2.9199638757487648e-05,
+      "loss": 0.115,
+      "step": 186
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.24301297962665558,
+      "learning_rate": 2.9190600826072603e-05,
+      "loss": 0.0871,
+      "step": 187
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.3000582754611969,
+      "learning_rate": 2.918151356585276e-05,
+      "loss": 0.0675,
+      "step": 188
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.23538866639137268,
+      "learning_rate": 2.9172377008416898e-05,
+      "loss": 0.0645,
+      "step": 189
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.3890560567378998,
+      "learning_rate": 2.916319118552515e-05,
+      "loss": 0.1009,
+      "step": 190
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.4634495973587036,
+      "learning_rate": 2.9153956129108918e-05,
+      "loss": 0.098,
+      "step": 191
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.20195429027080536,
+      "learning_rate": 2.9144671871270734e-05,
+      "loss": 0.0894,
+      "step": 192
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.42528125643730164,
+      "learning_rate": 2.913533844428417e-05,
+      "loss": 0.1398,
+      "step": 193
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.36887580156326294,
+      "learning_rate": 2.912595588059371e-05,
+      "loss": 0.1066,
+      "step": 194
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.17726579308509827,
+      "learning_rate": 2.9116524212814653e-05,
+      "loss": 0.0611,
+      "step": 195
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.19946645200252533,
+      "learning_rate": 2.9107043473733e-05,
+      "loss": 0.0947,
+      "step": 196
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.3372867703437805,
+      "learning_rate": 2.9097513696305304e-05,
+      "loss": 0.0952,
+      "step": 197
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.3198525011539459,
+      "learning_rate": 2.908793491365861e-05,
+      "loss": 0.1155,
+      "step": 198
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.3473115861415863,
+      "learning_rate": 2.90783071590903e-05,
+      "loss": 0.0752,
+      "step": 199
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.20476488769054413,
+      "learning_rate": 2.9068630466067997e-05,
+      "loss": 0.0708,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.3317318558692932,
+      "learning_rate": 2.905890486822943e-05,
+      "loss": 0.111,
+      "step": 201
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.247785285115242,
+      "learning_rate": 2.9049130399382345e-05,
+      "loss": 0.0855,
+      "step": 202
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.18749944865703583,
+      "learning_rate": 2.903930709350436e-05,
+      "loss": 0.0864,
+      "step": 203
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.43616777658462524,
+      "learning_rate": 2.9029434984742866e-05,
+      "loss": 0.1307,
+      "step": 204
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.23449763655662537,
+      "learning_rate": 2.9019514107414888e-05,
+      "loss": 0.086,
+      "step": 205
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.3940359055995941,
+      "learning_rate": 2.9009544496006998e-05,
+      "loss": 0.0711,
+      "step": 206
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.8495943546295166,
+      "learning_rate": 2.8999526185175155e-05,
+      "loss": 0.1159,
+      "step": 207
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.6435235142707825,
+      "learning_rate": 2.898945920974462e-05,
+      "loss": 0.0951,
+      "step": 208
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.24877464771270752,
+      "learning_rate": 2.8979343604709818e-05,
+      "loss": 0.0472,
+      "step": 209
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.3478896915912628,
+      "learning_rate": 2.8969179405234202e-05,
+      "loss": 0.1026,
+      "step": 210
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.4590359032154083,
+      "learning_rate": 2.8958966646650172e-05,
+      "loss": 0.1551,
+      "step": 211
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.33144280314445496,
+      "learning_rate": 2.894870536445891e-05,
+      "loss": 0.069,
+      "step": 212
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.0096515417099,
+      "learning_rate": 2.893839559433028e-05,
+      "loss": 0.1919,
+      "step": 213
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.4398234188556671,
+      "learning_rate": 2.8928037372102698e-05,
+      "loss": 0.1481,
+      "step": 214
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.2270442694425583,
+      "learning_rate": 2.8917630733783004e-05,
+      "loss": 0.0811,
+      "step": 215
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.30207884311676025,
+      "learning_rate": 2.8907175715546337e-05,
+      "loss": 0.091,
+      "step": 216
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.21270009875297546,
+      "learning_rate": 2.889667235373603e-05,
+      "loss": 0.092,
+      "step": 217
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.2912154197692871,
+      "learning_rate": 2.888612068486344e-05,
+      "loss": 0.0834,
+      "step": 218
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.23577392101287842,
+      "learning_rate": 2.887552074560787e-05,
+      "loss": 0.1215,
+      "step": 219
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.16501927375793457,
+      "learning_rate": 2.8864872572816407e-05,
+      "loss": 0.0665,
+      "step": 220
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.1898716688156128,
+      "learning_rate": 2.885417620350381e-05,
+      "loss": 0.0595,
+      "step": 221
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.25912415981292725,
+      "learning_rate": 2.8843431674852366e-05,
+      "loss": 0.0455,
+      "step": 222
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.33551594614982605,
+      "learning_rate": 2.883263902421179e-05,
+      "loss": 0.0836,
+      "step": 223
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2037317305803299,
+      "learning_rate": 2.8821798289099054e-05,
+      "loss": 0.0974,
+      "step": 224
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.29482024908065796,
+      "learning_rate": 2.881090950719831e-05,
+      "loss": 0.1051,
+      "step": 225
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.20771493017673492,
+      "learning_rate": 2.87999727163607e-05,
+      "loss": 0.0761,
+      "step": 226
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2051924616098404,
+      "learning_rate": 2.878898795460426e-05,
+      "loss": 0.0553,
+      "step": 227
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2791610062122345,
+      "learning_rate": 2.8777955260113794e-05,
+      "loss": 0.0651,
+      "step": 228
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.35246115922927856,
+      "learning_rate": 2.8766874671240708e-05,
+      "loss": 0.1042,
+      "step": 229
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.29613715410232544,
+      "learning_rate": 2.8755746226502914e-05,
+      "loss": 0.0679,
+      "step": 230
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.5915008783340454,
+      "learning_rate": 2.874456996458467e-05,
+      "loss": 0.1112,
+      "step": 231
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.5234435200691223,
+      "learning_rate": 2.8733345924336448e-05,
+      "loss": 0.1,
+      "step": 232
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.582992434501648,
+      "learning_rate": 2.872207414477482e-05,
+      "loss": 0.1505,
+      "step": 233
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.463219553232193,
+      "learning_rate": 2.8710754665082295e-05,
+      "loss": 0.1148,
+      "step": 234
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.3954102694988251,
+      "learning_rate": 2.8699387524607206e-05,
+      "loss": 0.1252,
+      "step": 235
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.2828240692615509,
+      "learning_rate": 2.868797276286355e-05,
+      "loss": 0.0916,
+      "step": 236
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.6134512424468994,
+      "learning_rate": 2.8676510419530875e-05,
+      "loss": 0.0953,
+      "step": 237
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.4864056408405304,
+      "learning_rate": 2.866500053445412e-05,
+      "loss": 0.0887,
+      "step": 238
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.34841328859329224,
+      "learning_rate": 2.86534431476435e-05,
+      "loss": 0.0919,
+      "step": 239
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.22810260951519012,
+      "learning_rate": 2.8641838299274336e-05,
+      "loss": 0.0515,
+      "step": 240
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.7178006768226624,
+      "learning_rate": 2.863018602968695e-05,
+      "loss": 0.2241,
+      "step": 241
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.3194310665130615,
+      "learning_rate": 2.8618486379386496e-05,
+      "loss": 0.111,
+      "step": 242
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.15743738412857056,
+      "learning_rate": 2.8606739389042838e-05,
+      "loss": 0.0634,
+      "step": 243
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.24189315736293793,
+      "learning_rate": 2.8594945099490395e-05,
+      "loss": 0.0644,
+      "step": 244
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.21816010773181915,
+      "learning_rate": 2.8583103551728008e-05,
+      "loss": 0.0852,
+      "step": 245
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.282953679561615,
+      "learning_rate": 2.857121478691881e-05,
+      "loss": 0.0842,
+      "step": 246
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.2257271707057953,
+      "learning_rate": 2.855927884639004e-05,
+      "loss": 0.0686,
+      "step": 247
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.2596382796764374,
+      "learning_rate": 2.854729577163294e-05,
+      "loss": 0.0595,
+      "step": 248
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.3601246178150177,
+      "learning_rate": 2.8535265604302614e-05,
+      "loss": 0.0781,
+      "step": 249
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.22987039387226105,
+      "learning_rate": 2.852318838621784e-05,
+      "loss": 0.0712,
+      "step": 250
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.2668680250644684,
+      "learning_rate": 2.851106415936098e-05,
+      "loss": 0.1015,
+      "step": 251
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.3502819836139679,
+      "learning_rate": 2.8498892965877776e-05,
+      "loss": 0.1164,
+      "step": 252
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.4412795603275299,
+      "learning_rate": 2.848667484807726e-05,
+      "loss": 0.0891,
+      "step": 253
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.506323516368866,
+      "learning_rate": 2.8474409848431562e-05,
+      "loss": 0.1134,
+      "step": 254
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.519180178642273,
+      "learning_rate": 2.8462098009575793e-05,
+      "loss": 0.1147,
+      "step": 255
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.4656154215335846,
+      "learning_rate": 2.8449739374307877e-05,
+      "loss": 0.0939,
+      "step": 256
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.23170435428619385,
+      "learning_rate": 2.8437333985588418e-05,
+      "loss": 0.0365,
+      "step": 257
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.4948550760746002,
+      "learning_rate": 2.8424881886540527e-05,
+      "loss": 0.127,
+      "step": 258
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.2533349096775055,
+      "learning_rate": 2.8412383120449707e-05,
+      "loss": 0.0582,
+      "step": 259
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.3986698091030121,
+      "learning_rate": 2.839983773076367e-05,
+      "loss": 0.0687,
+      "step": 260
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5078080296516418,
+      "learning_rate": 2.8387245761092203e-05,
+      "loss": 0.1166,
+      "step": 261
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.5207770466804504,
+      "learning_rate": 2.8374607255207012e-05,
+      "loss": 0.0615,
+      "step": 262
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.578711211681366,
+      "learning_rate": 2.8361922257041577e-05,
+      "loss": 0.1259,
+      "step": 263
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.3096364140510559,
+      "learning_rate": 2.8349190810690977e-05,
+      "loss": 0.0708,
+      "step": 264
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.4309447407722473,
+      "learning_rate": 2.8336412960411765e-05,
+      "loss": 0.1351,
+      "step": 265
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.4576749801635742,
+      "learning_rate": 2.8323588750621802e-05,
+      "loss": 0.0875,
+      "step": 266
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.5308840274810791,
+      "learning_rate": 2.8310718225900095e-05,
+      "loss": 0.0803,
+      "step": 267
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.32970359921455383,
+      "learning_rate": 2.8297801430986652e-05,
+      "loss": 0.0774,
+      "step": 268
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.2413233071565628,
+      "learning_rate": 2.8284838410782327e-05,
+      "loss": 0.056,
+      "step": 269
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.45652082562446594,
+      "learning_rate": 2.8271829210348657e-05,
+      "loss": 0.165,
+      "step": 270
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.36683741211891174,
+      "learning_rate": 2.82587738749077e-05,
+      "loss": 0.1019,
+      "step": 271
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.3328053057193756,
+      "learning_rate": 2.824567244984192e-05,
+      "loss": 0.1022,
+      "step": 272
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.40834105014801025,
+      "learning_rate": 2.8232524980693947e-05,
+      "loss": 0.0607,
+      "step": 273
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.2283175140619278,
+      "learning_rate": 2.8219331513166503e-05,
+      "loss": 0.0772,
+      "step": 274
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.3196583092212677,
+      "learning_rate": 2.8206092093122195e-05,
+      "loss": 0.0834,
+      "step": 275
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.27474430203437805,
+      "learning_rate": 2.8192806766583373e-05,
+      "loss": 0.0749,
+      "step": 276
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.3614490330219269,
+      "learning_rate": 2.8179475579731967e-05,
+      "loss": 0.0888,
+      "step": 277
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.20857541263103485,
+      "learning_rate": 2.8166098578909315e-05,
+      "loss": 0.035,
+      "step": 278
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.27701324224472046,
+      "learning_rate": 2.815267581061602e-05,
+      "loss": 0.062,
+      "step": 279
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.45753782987594604,
+      "learning_rate": 2.8139207321511778e-05,
+      "loss": 0.1062,
+      "step": 280
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3005506098270416,
+      "learning_rate": 2.8125693158415217e-05,
+      "loss": 0.1344,
+      "step": 281
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.2129545509815216,
+      "learning_rate": 2.8112133368303737e-05,
+      "loss": 0.0382,
+      "step": 282
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.37999290227890015,
+      "learning_rate": 2.809852799831334e-05,
+      "loss": 0.0812,
+      "step": 283
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.1718507707118988,
+      "learning_rate": 2.8084877095738477e-05,
+      "loss": 0.022,
+      "step": 284
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.08163367211818695,
+      "eval_runtime": 14.651,
+      "eval_samples_per_second": 32.558,
+      "eval_steps_per_second": 8.191,
+      "step": 284
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.27595949172973633,
+      "learning_rate": 2.8071180708031874e-05,
+      "loss": 0.0593,
+      "step": 285
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.48061394691467285,
+      "learning_rate": 2.8057438882804372e-05,
+      "loss": 0.1139,
+      "step": 286
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.32916727662086487,
+      "learning_rate": 2.8043651667824767e-05,
+      "loss": 0.0335,
+      "step": 287
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.6290953755378723,
+      "learning_rate": 2.8029819111019618e-05,
+      "loss": 0.099,
+      "step": 288
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.7197291851043701,
+      "learning_rate": 2.8015941260473117e-05,
+      "loss": 0.1165,
+      "step": 289
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.4702732264995575,
+      "learning_rate": 2.8002018164426896e-05,
+      "loss": 0.0948,
+      "step": 290
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.4018266201019287,
+      "learning_rate": 2.798804987127988e-05,
+      "loss": 0.0982,
+      "step": 291
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.7587385773658752,
+      "learning_rate": 2.7974036429588082e-05,
+      "loss": 0.0915,
+      "step": 292
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.36278435587882996,
+      "learning_rate": 2.7959977888064484e-05,
+      "loss": 0.0442,
+      "step": 293
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5261387228965759,
+      "learning_rate": 2.7945874295578827e-05,
+      "loss": 0.117,
+      "step": 294
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.8715558648109436,
+      "learning_rate": 2.7931725701157462e-05,
+      "loss": 0.1461,
+      "step": 295
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.3017662465572357,
+      "learning_rate": 2.7917532153983176e-05,
+      "loss": 0.0829,
+      "step": 296
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.23709601163864136,
+      "learning_rate": 2.790329370339501e-05,
+      "loss": 0.0693,
+      "step": 297
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.23073746263980865,
+      "learning_rate": 2.7889010398888104e-05,
+      "loss": 0.0657,
+      "step": 298
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.35000571608543396,
+      "learning_rate": 2.7874682290113514e-05,
+      "loss": 0.0774,
+      "step": 299
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.2956024408340454,
+      "learning_rate": 2.786030942687805e-05,
+      "loss": 0.0836,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.35490185022354126,
+      "learning_rate": 2.7845891859144088e-05,
+      "loss": 0.1066,
+      "step": 301
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.5659674406051636,
+      "learning_rate": 2.7831429637029402e-05,
+      "loss": 0.1574,
+      "step": 302
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.3070801794528961,
+      "learning_rate": 2.7816922810807e-05,
+      "loss": 0.0913,
+      "step": 303
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.3739650547504425,
+      "learning_rate": 2.7802371430904936e-05,
+      "loss": 0.1343,
+      "step": 304
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.6166901588439941,
+      "learning_rate": 2.7787775547906142e-05,
+      "loss": 0.0998,
+      "step": 305
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.3676758408546448,
+      "learning_rate": 2.7773135212548247e-05,
+      "loss": 0.0673,
+      "step": 306
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.4253583550453186,
+      "learning_rate": 2.7758450475723405e-05,
+      "loss": 0.1059,
+      "step": 307
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.31137579679489136,
+      "learning_rate": 2.774372138847812e-05,
+      "loss": 0.0884,
+      "step": 308
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.23509562015533447,
+      "learning_rate": 2.7728948002013054e-05,
+      "loss": 0.0792,
+      "step": 309
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.459160715341568,
+      "learning_rate": 2.771413036768288e-05,
+      "loss": 0.1156,
+      "step": 310
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.34745368361473083,
+      "learning_rate": 2.769926853699606e-05,
+      "loss": 0.0971,
+      "step": 311
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.30285558104515076,
+      "learning_rate": 2.7684362561614714e-05,
+      "loss": 0.0954,
+      "step": 312
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.30963224172592163,
+      "learning_rate": 2.766941249335439e-05,
+      "loss": 0.099,
+      "step": 313
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.34839507937431335,
+      "learning_rate": 2.765441838418393e-05,
+      "loss": 0.1011,
+      "step": 314
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.23209823668003082,
+      "learning_rate": 2.7639380286225264e-05,
+      "loss": 0.0662,
+      "step": 315
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.3385458290576935,
+      "learning_rate": 2.7624298251753232e-05,
+      "loss": 0.1058,
+      "step": 316
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2462904453277588,
+      "learning_rate": 2.7609172333195406e-05,
+      "loss": 0.1128,
+      "step": 317
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.3830464482307434,
+      "learning_rate": 2.75940025831319e-05,
+      "loss": 0.0927,
+      "step": 318
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.23960565030574799,
+      "learning_rate": 2.7578789054295202e-05,
+      "loss": 0.0484,
+      "step": 319
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.24503108859062195,
+      "learning_rate": 2.7563531799569984e-05,
+      "loss": 0.1001,
+      "step": 320
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.3050799071788788,
+      "learning_rate": 2.75482308719929e-05,
+      "loss": 0.1168,
+      "step": 321
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.4061020016670227,
+      "learning_rate": 2.753288632475244e-05,
+      "loss": 0.1424,
+      "step": 322
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.30394184589385986,
+      "learning_rate": 2.75174982111887e-05,
+      "loss": 0.0774,
+      "step": 323
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.22858074307441711,
+      "learning_rate": 2.7502066584793243e-05,
+      "loss": 0.0911,
+      "step": 324
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.31271883845329285,
+      "learning_rate": 2.7486591499208867e-05,
+      "loss": 0.0555,
+      "step": 325
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.22895589470863342,
+      "learning_rate": 2.7471073008229462e-05,
+      "loss": 0.0741,
+      "step": 326
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.22698134183883667,
+      "learning_rate": 2.7455511165799783e-05,
+      "loss": 0.0829,
+      "step": 327
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.24353599548339844,
+      "learning_rate": 2.7439906026015297e-05,
+      "loss": 0.0965,
+      "step": 328
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.19678641855716705,
+      "learning_rate": 2.742425764312197e-05,
+      "loss": 0.0822,
+      "step": 329
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.21248051524162292,
+      "learning_rate": 2.7408566071516087e-05,
+      "loss": 0.0713,
+      "step": 330
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.47786301374435425,
+      "learning_rate": 2.7392831365744074e-05,
+      "loss": 0.0863,
+      "step": 331
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.2300809770822525,
+      "learning_rate": 2.7377053580502298e-05,
+      "loss": 0.0864,
+      "step": 332
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.34608194231987,
+      "learning_rate": 2.7361232770636856e-05,
+      "loss": 0.0869,
+      "step": 333
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.37124645709991455,
+      "learning_rate": 2.7345368991143433e-05,
+      "loss": 0.1013,
+      "step": 334
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.4118335545063019,
+      "learning_rate": 2.732946229716707e-05,
+      "loss": 0.1163,
+      "step": 335
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.5510608553886414,
+      "learning_rate": 2.7313512744001982e-05,
+      "loss": 0.1305,
+      "step": 336
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.21711857616901398,
+      "learning_rate": 2.7297520387091376e-05,
+      "loss": 0.0668,
+      "step": 337
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.24401220679283142,
+      "learning_rate": 2.7281485282027252e-05,
+      "loss": 0.0855,
+      "step": 338
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.33350592851638794,
+      "learning_rate": 2.7265407484550206e-05,
+      "loss": 0.0632,
+      "step": 339
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.7973533868789673,
+      "learning_rate": 2.724928705054924e-05,
+      "loss": 0.1894,
+      "step": 340
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.4574988782405853,
+      "learning_rate": 2.7233124036061575e-05,
+      "loss": 0.105,
+      "step": 341
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2864499092102051,
+      "learning_rate": 2.7216918497272426e-05,
+      "loss": 0.0826,
+      "step": 342
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2666662335395813,
+      "learning_rate": 2.7200670490514865e-05,
+      "loss": 0.0723,
+      "step": 343
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.27098262310028076,
+      "learning_rate": 2.7184380072269558e-05,
+      "loss": 0.0579,
+      "step": 344
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.22073043882846832,
+      "learning_rate": 2.7168047299164614e-05,
+      "loss": 0.0539,
+      "step": 345
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2872254550457001,
+      "learning_rate": 2.7151672227975377e-05,
+      "loss": 0.1239,
+      "step": 346
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.41940388083457947,
+      "learning_rate": 2.7135254915624213e-05,
+      "loss": 0.0755,
+      "step": 347
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2658102214336395,
+      "learning_rate": 2.711879541918034e-05,
+      "loss": 0.1158,
+      "step": 348
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.23337627947330475,
+      "learning_rate": 2.71022937958596e-05,
+      "loss": 0.0814,
+      "step": 349
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.26450300216674805,
+      "learning_rate": 2.7085750103024296e-05,
+      "loss": 0.0393,
+      "step": 350
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.34251630306243896,
+      "learning_rate": 2.7069164398182948e-05,
+      "loss": 0.0718,
+      "step": 351
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.3174653947353363,
+      "learning_rate": 2.7052536738990125e-05,
+      "loss": 0.0838,
+      "step": 352
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2430477887392044,
+      "learning_rate": 2.7035867183246247e-05,
+      "loss": 0.1018,
+      "step": 353
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.3248900771141052,
+      "learning_rate": 2.7019155788897357e-05,
+      "loss": 0.0764,
+      "step": 354
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.24875646829605103,
+      "learning_rate": 2.700240261403494e-05,
+      "loss": 0.0731,
+      "step": 355
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.209304079413414,
+      "learning_rate": 2.6985607716895727e-05,
+      "loss": 0.0482,
+      "step": 356
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.24239419400691986,
+      "learning_rate": 2.6968771155861464e-05,
+      "loss": 0.0515,
+      "step": 357
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.5304663777351379,
+      "learning_rate": 2.695189298945875e-05,
+      "loss": 0.0919,
+      "step": 358
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.21653291583061218,
+      "learning_rate": 2.6934973276358792e-05,
+      "loss": 0.0604,
+      "step": 359
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2541111409664154,
+      "learning_rate": 2.6918012075377226e-05,
+      "loss": 0.0823,
+      "step": 360
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.3744794428348541,
+      "learning_rate": 2.6901009445473912e-05,
+      "loss": 0.1051,
+      "step": 361
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.28307440876960754,
+      "learning_rate": 2.6883965445752714e-05,
+      "loss": 0.0425,
+      "step": 362
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.49167400598526,
+      "learning_rate": 2.6866880135461314e-05,
+      "loss": 0.1167,
+      "step": 363
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.3999198079109192,
+      "learning_rate": 2.684975357399099e-05,
+      "loss": 0.0547,
+      "step": 364
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.23400184512138367,
+      "learning_rate": 2.683258582087641e-05,
+      "loss": 0.0545,
+      "step": 365
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.1796039193868637,
+      "learning_rate": 2.681537693579545e-05,
+      "loss": 0.0346,
+      "step": 366
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.5400248169898987,
+      "learning_rate": 2.6798126978568942e-05,
+      "loss": 0.1084,
+      "step": 367
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.3125457167625427,
+      "learning_rate": 2.6780836009160514e-05,
+      "loss": 0.0445,
+      "step": 368
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.48360738158226013,
+      "learning_rate": 2.6763504087676346e-05,
+      "loss": 0.0612,
+      "step": 369
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.9248375296592712,
+      "learning_rate": 2.674613127436498e-05,
+      "loss": 0.1119,
+      "step": 370
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4848339855670929,
+      "learning_rate": 2.6728717629617093e-05,
+      "loss": 0.1119,
+      "step": 371
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.8126673102378845,
+      "learning_rate": 2.671126321396532e-05,
+      "loss": 0.1964,
+      "step": 372
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.3666157126426697,
+      "learning_rate": 2.6693768088083994e-05,
+      "loss": 0.0688,
+      "step": 373
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.33919093012809753,
+      "learning_rate": 2.6676232312788998e-05,
+      "loss": 0.087,
+      "step": 374
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.4218893349170685,
+      "learning_rate": 2.6658655949037482e-05,
+      "loss": 0.0704,
+      "step": 375
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.2786632776260376,
+      "learning_rate": 2.6641039057927724e-05,
+      "loss": 0.0724,
+      "step": 376
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.7727587819099426,
+      "learning_rate": 2.662338170069885e-05,
+      "loss": 0.1219,
+      "step": 377
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.47525373101234436,
+      "learning_rate": 2.6605683938730666e-05,
+      "loss": 0.0894,
+      "step": 378
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.6987584233283997,
+      "learning_rate": 2.6587945833543432e-05,
+      "loss": 0.0976,
+      "step": 379
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.28406238555908203,
+      "learning_rate": 2.6570167446797657e-05,
+      "loss": 0.1048,
+      "step": 380
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.2821677625179291,
+      "learning_rate": 2.6552348840293856e-05,
+      "loss": 0.0677,
+      "step": 381
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.37019118666648865,
+      "learning_rate": 2.6534490075972368e-05,
+      "loss": 0.0901,
+      "step": 382
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.3454105257987976,
+      "learning_rate": 2.6516591215913118e-05,
+      "loss": 0.0956,
+      "step": 383
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.2895926535129547,
+      "learning_rate": 2.6498652322335416e-05,
+      "loss": 0.0539,
+      "step": 384
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.4975215494632721,
+      "learning_rate": 2.6480673457597737e-05,
+      "loss": 0.0979,
+      "step": 385
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.6093487739562988,
+      "learning_rate": 2.646265468419749e-05,
+      "loss": 0.146,
+      "step": 386
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.3748679459095001,
+      "learning_rate": 2.6444596064770837e-05,
+      "loss": 0.131,
+      "step": 387
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.3992125391960144,
+      "learning_rate": 2.6426497662092424e-05,
+      "loss": 0.08,
+      "step": 388
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.18994563817977905,
+      "learning_rate": 2.6408359539075204e-05,
+      "loss": 0.064,
+      "step": 389
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.2519935965538025,
+      "learning_rate": 2.6390181758770208e-05,
+      "loss": 0.1035,
+      "step": 390
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.1836027204990387,
+      "learning_rate": 2.6371964384366305e-05,
+      "loss": 0.0876,
+      "step": 391
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.21602681279182434,
+      "learning_rate": 2.6353707479190022e-05,
+      "loss": 0.0764,
+      "step": 392
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.28096359968185425,
+      "learning_rate": 2.6335411106705283e-05,
+      "loss": 0.0598,
+      "step": 393
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.3226209878921509,
+      "learning_rate": 2.6317075330513212e-05,
+      "loss": 0.1071,
+      "step": 394
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.3776714503765106,
+      "learning_rate": 2.6298700214351922e-05,
+      "loss": 0.0576,
+      "step": 395
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5143963694572449,
+      "learning_rate": 2.628028582209625e-05,
+      "loss": 0.0927,
+      "step": 396
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.5534598231315613,
+      "learning_rate": 2.626183221775758e-05,
+      "loss": 0.0813,
+      "step": 397
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.3283978998661041,
+      "learning_rate": 2.6243339465483605e-05,
+      "loss": 0.091,
+      "step": 398
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.26208245754241943,
+      "learning_rate": 2.6224807629558094e-05,
+      "loss": 0.0825,
+      "step": 399
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.4244028925895691,
+      "learning_rate": 2.6206236774400684e-05,
+      "loss": 0.1077,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.39094752073287964,
+      "learning_rate": 2.6187626964566644e-05,
+      "loss": 0.1031,
+      "step": 401
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.4204391539096832,
+      "learning_rate": 2.6168978264746663e-05,
+      "loss": 0.1153,
+      "step": 402
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.3522421419620514,
+      "learning_rate": 2.615029073976661e-05,
+      "loss": 0.055,
+      "step": 403
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.28039833903312683,
+      "learning_rate": 2.6131564454587316e-05,
+      "loss": 0.1058,
+      "step": 404
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.3698963224887848,
+      "learning_rate": 2.611279947430436e-05,
+      "loss": 0.0639,
+      "step": 405
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.23384957015514374,
+      "learning_rate": 2.609399586414782e-05,
+      "loss": 0.0443,
+      "step": 406
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.24013498425483704,
+      "learning_rate": 2.607515368948206e-05,
+      "loss": 0.0607,
+      "step": 407
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.6072742342948914,
+      "learning_rate": 2.60562730158055e-05,
+      "loss": 0.1062,
+      "step": 408
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5543622970581055,
+      "learning_rate": 2.6037353908750394e-05,
+      "loss": 0.108,
+      "step": 409
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.2501017153263092,
+      "learning_rate": 2.601839643408259e-05,
+      "loss": 0.0445,
+      "step": 410
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.3118091821670532,
+      "learning_rate": 2.5999400657701314e-05,
+      "loss": 0.0982,
+      "step": 411
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.424712210893631,
+      "learning_rate": 2.598036664563893e-05,
+      "loss": 0.0884,
+      "step": 412
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.18902163207530975,
+      "learning_rate": 2.596129446406072e-05,
+      "loss": 0.0453,
+      "step": 413
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.4779305160045624,
+      "learning_rate": 2.594218417926464e-05,
+      "loss": 0.1217,
+      "step": 414
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.3665257394313812,
+      "learning_rate": 2.592303585768111e-05,
+      "loss": 0.0791,
+      "step": 415
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.22645382583141327,
+      "learning_rate": 2.590384956587277e-05,
+      "loss": 0.0384,
+      "step": 416
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.3394840359687805,
+      "learning_rate": 2.5884625370534242e-05,
+      "loss": 0.0853,
+      "step": 417
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.5719820857048035,
+      "learning_rate": 2.5865363338491916e-05,
+      "loss": 0.1058,
+      "step": 418
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.5341434478759766,
+      "learning_rate": 2.5846063536703706e-05,
+      "loss": 0.0955,
+      "step": 419
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.27542081475257874,
+      "learning_rate": 2.582672603225882e-05,
+      "loss": 0.0547,
+      "step": 420
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.4750405550003052,
+      "learning_rate": 2.5807350892377517e-05,
+      "loss": 0.152,
+      "step": 421
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.292294979095459,
+      "learning_rate": 2.5787938184410902e-05,
+      "loss": 0.0877,
+      "step": 422
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.33273130655288696,
+      "learning_rate": 2.5768487975840655e-05,
+      "loss": 0.0721,
+      "step": 423
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.27887821197509766,
+      "learning_rate": 2.5749000334278825e-05,
+      "loss": 0.0603,
+      "step": 424
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.35635143518447876,
+      "learning_rate": 2.572947532746758e-05,
+      "loss": 0.1011,
+      "step": 425
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.5215089321136475,
+      "learning_rate": 2.570991302327897e-05,
+      "loss": 0.1295,
+      "step": 426
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.07854457199573517,
+      "eval_runtime": 14.6749,
+      "eval_samples_per_second": 32.505,
+      "eval_steps_per_second": 8.177,
+      "step": 426
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.3576556444168091,
+      "learning_rate": 2.569031348971471e-05,
+      "loss": 0.0801,
+      "step": 427
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.36309999227523804,
+      "learning_rate": 2.5670676794905915e-05,
+      "loss": 0.0694,
+      "step": 428
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.6117097735404968,
+      "learning_rate": 2.5651003007112892e-05,
+      "loss": 0.111,
+      "step": 429
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.217342346906662,
+      "learning_rate": 2.5631292194724883e-05,
+      "loss": 0.0346,
+      "step": 430
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.4748762249946594,
+      "learning_rate": 2.561154442625983e-05,
+      "loss": 0.1427,
+      "step": 431
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.295284241437912,
+      "learning_rate": 2.559175977036415e-05,
+      "loss": 0.083,
+      "step": 432
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.29578328132629395,
+      "learning_rate": 2.5571938295812476e-05,
+      "loss": 0.06,
+      "step": 433
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.22991441190242767,
+      "learning_rate": 2.555208007150743e-05,
+      "loss": 0.092,
+      "step": 434
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.23324204981327057,
+      "learning_rate": 2.553218516647939e-05,
+      "loss": 0.0972,
+      "step": 435
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.40380072593688965,
+      "learning_rate": 2.5512253649886237e-05,
+      "loss": 0.0752,
+      "step": 436
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.3805236518383026,
+      "learning_rate": 2.5492285591013118e-05,
+      "loss": 0.0998,
+      "step": 437
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.22794733941555023,
+      "learning_rate": 2.5472281059272213e-05,
+      "loss": 0.0747,
+      "step": 438
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.22835515439510345,
+      "learning_rate": 2.5452240124202477e-05,
+      "loss": 0.0797,
+      "step": 439
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.27887535095214844,
+      "learning_rate": 2.5432162855469422e-05,
+      "loss": 0.0499,
+      "step": 440
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.2706398069858551,
+      "learning_rate": 2.5412049322864847e-05,
+      "loss": 0.052,
+      "step": 441
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.22984421253204346,
+      "learning_rate": 2.539189959630662e-05,
+      "loss": 0.0735,
+      "step": 442
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.21597078442573547,
+      "learning_rate": 2.537171374583843e-05,
+      "loss": 0.0619,
+      "step": 443
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.1989249587059021,
+      "learning_rate": 2.535149184162952e-05,
+      "loss": 0.0438,
+      "step": 444
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.5477291345596313,
+      "learning_rate": 2.533123395397448e-05,
+      "loss": 0.1213,
+      "step": 445
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.2946613132953644,
+      "learning_rate": 2.5310940153292978e-05,
+      "loss": 0.0751,
+      "step": 446
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.3890973627567291,
+      "learning_rate": 2.5290610510129518e-05,
+      "loss": 0.0904,
+      "step": 447
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.4777461588382721,
+      "learning_rate": 2.5270245095153198e-05,
+      "loss": 0.0436,
+      "step": 448
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.3443584442138672,
+      "learning_rate": 2.524984397915747e-05,
+      "loss": 0.0327,
+      "step": 449
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.45741167664527893,
+      "learning_rate": 2.5229407233059887e-05,
+      "loss": 0.1213,
+      "step": 450
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3687816858291626,
+      "learning_rate": 2.5208934927901857e-05,
+      "loss": 0.1082,
+      "step": 451
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.46452489495277405,
+      "learning_rate": 2.5188427134848395e-05,
+      "loss": 0.0841,
+      "step": 452
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.23272164165973663,
+      "learning_rate": 2.5167883925187878e-05,
+      "loss": 0.0564,
+      "step": 453
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.48221856355667114,
+      "learning_rate": 2.51473053703318e-05,
+      "loss": 0.12,
+      "step": 454
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5240137577056885,
+      "learning_rate": 2.5126691541814518e-05,
+      "loss": 0.0835,
+      "step": 455
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.48311519622802734,
+      "learning_rate": 2.510604251129301e-05,
+      "loss": 0.1015,
+      "step": 456
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.29986709356307983,
+      "learning_rate": 2.5085358350546612e-05,
+      "loss": 0.0827,
+      "step": 457
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.4454290270805359,
+      "learning_rate": 2.506463913147679e-05,
+      "loss": 0.1309,
+      "step": 458
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.305890828371048,
+      "learning_rate": 2.5043884926106873e-05,
+      "loss": 0.0636,
+      "step": 459
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.25751793384552,
+      "learning_rate": 2.5023095806581802e-05,
+      "loss": 0.0857,
+      "step": 460
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.4034629166126251,
+      "learning_rate": 2.5002271845167896e-05,
+      "loss": 0.1383,
+      "step": 461
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.2389378845691681,
+      "learning_rate": 2.4981413114252588e-05,
+      "loss": 0.0411,
+      "step": 462
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.4818887412548065,
+      "learning_rate": 2.4960519686344168e-05,
+      "loss": 0.0837,
+      "step": 463
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.32815420627593994,
+      "learning_rate": 2.4939591634071544e-05,
+      "loss": 0.0903,
+      "step": 464
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1801011711359024,
+      "learning_rate": 2.491862903018398e-05,
+      "loss": 0.0827,
+      "step": 465
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.23406219482421875,
+      "learning_rate": 2.4897631947550857e-05,
+      "loss": 0.0887,
+      "step": 466
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.20487089455127716,
+      "learning_rate": 2.4876600459161397e-05,
+      "loss": 0.0944,
+      "step": 467
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.2795143127441406,
+      "learning_rate": 2.4855534638124427e-05,
+      "loss": 0.0721,
+      "step": 468
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.2514597475528717,
+      "learning_rate": 2.4834434557668126e-05,
+      "loss": 0.0798,
+      "step": 469
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.24707554280757904,
+      "learning_rate": 2.4813300291139754e-05,
+      "loss": 0.0875,
+      "step": 470
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.2397790551185608,
+      "learning_rate": 2.4792131912005407e-05,
+      "loss": 0.0497,
+      "step": 471
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.4203518331050873,
+      "learning_rate": 2.4770929493849773e-05,
+      "loss": 0.0789,
+      "step": 472
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.23552100360393524,
+      "learning_rate": 2.4749693110375856e-05,
+      "loss": 0.0682,
+      "step": 473
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.19143146276474,
+      "learning_rate": 2.4728422835404735e-05,
+      "loss": 0.0779,
+      "step": 474
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.2365415096282959,
+      "learning_rate": 2.4707118742875293e-05,
+      "loss": 0.0442,
+      "step": 475
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.36645641922950745,
+      "learning_rate": 2.4685780906843975e-05,
+      "loss": 0.1043,
+      "step": 476
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.20781370997428894,
+      "learning_rate": 2.4664409401484522e-05,
+      "loss": 0.0797,
+      "step": 477
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.27483153343200684,
+      "learning_rate": 2.4643004301087716e-05,
+      "loss": 0.0455,
+      "step": 478
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.2820053696632385,
+      "learning_rate": 2.462156568006112e-05,
+      "loss": 0.0615,
+      "step": 479
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.3784559369087219,
+      "learning_rate": 2.4600093612928812e-05,
+      "loss": 0.1338,
+      "step": 480
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.46063724160194397,
+      "learning_rate": 2.457858817433115e-05,
+      "loss": 0.0897,
+      "step": 481
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.320568323135376,
+      "learning_rate": 2.4557049439024488e-05,
+      "loss": 0.0747,
+      "step": 482
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.2996703088283539,
+      "learning_rate": 2.4535477481880923e-05,
+      "loss": 0.1219,
+      "step": 483
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.46839097142219543,
+      "learning_rate": 2.451387237788804e-05,
+      "loss": 0.1104,
+      "step": 484
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.3005930185317993,
+      "learning_rate": 2.4492234202148643e-05,
+      "loss": 0.0755,
+      "step": 485
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.2897649109363556,
+      "learning_rate": 2.44705630298805e-05,
+      "loss": 0.0798,
+      "step": 486
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.2890012860298157,
+      "learning_rate": 2.4448858936416093e-05,
+      "loss": 0.1019,
+      "step": 487
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.2596171200275421,
+      "learning_rate": 2.442712199720232e-05,
+      "loss": 0.0835,
+      "step": 488
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.4037571847438812,
+      "learning_rate": 2.4405352287800268e-05,
+      "loss": 0.0822,
+      "step": 489
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.337190181016922,
+      "learning_rate": 2.4383549883884954e-05,
+      "loss": 0.0356,
+      "step": 490
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.3917272686958313,
+      "learning_rate": 2.4361714861245017e-05,
+      "loss": 0.0966,
+      "step": 491
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.5287500023841858,
+      "learning_rate": 2.4339847295782508e-05,
+      "loss": 0.0706,
+      "step": 492
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.29515090584754944,
+      "learning_rate": 2.431794726351258e-05,
+      "loss": 0.054,
+      "step": 493
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.30174991488456726,
+      "learning_rate": 2.4296014840563266e-05,
+      "loss": 0.0768,
+      "step": 494
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.33137279748916626,
+      "learning_rate": 2.4274050103175195e-05,
+      "loss": 0.1008,
+      "step": 495
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.19129472970962524,
+      "learning_rate": 2.42520531277013e-05,
+      "loss": 0.0556,
+      "step": 496
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.3620724081993103,
+      "learning_rate": 2.423002399060661e-05,
+      "loss": 0.0604,
+      "step": 497
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.28499534726142883,
+      "learning_rate": 2.420796276846793e-05,
+      "loss": 0.067,
+      "step": 498
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.3519887328147888,
+      "learning_rate": 2.4185869537973613e-05,
+      "loss": 0.0973,
+      "step": 499
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.34655264019966125,
+      "learning_rate": 2.4163744375923272e-05,
+      "loss": 0.0425,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.5716597437858582,
+      "learning_rate": 2.4141587359227514e-05,
+      "loss": 0.1659,
+      "step": 501
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.32810407876968384,
+      "learning_rate": 2.4119398564907685e-05,
+      "loss": 0.116,
+      "step": 502
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.32078537344932556,
+      "learning_rate": 2.4097178070095602e-05,
+      "loss": 0.0646,
+      "step": 503
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.389475554227829,
+      "learning_rate": 2.4074925952033263e-05,
+      "loss": 0.1275,
+      "step": 504
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.15961997210979462,
+      "learning_rate": 2.4052642288072594e-05,
+      "loss": 0.0427,
+      "step": 505
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2679911255836487,
+      "learning_rate": 2.4030327155675192e-05,
+      "loss": 0.0868,
+      "step": 506
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2590488791465759,
+      "learning_rate": 2.4007980632412034e-05,
+      "loss": 0.0476,
+      "step": 507
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.4470207989215851,
+      "learning_rate": 2.398560279596323e-05,
+      "loss": 0.0644,
+      "step": 508
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.2822036147117615,
+      "learning_rate": 2.3963193724117715e-05,
+      "loss": 0.06,
+      "step": 509
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.3097975552082062,
+      "learning_rate": 2.394075349477302e-05,
+      "loss": 0.0481,
+      "step": 510
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.30676892399787903,
+      "learning_rate": 2.3918282185934986e-05,
+      "loss": 0.0794,
+      "step": 511
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.23650003969669342,
+      "learning_rate": 2.3895779875717486e-05,
+      "loss": 0.0653,
+      "step": 512
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.2657279968261719,
+      "learning_rate": 2.3873246642342163e-05,
+      "loss": 0.093,
+      "step": 513
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.24548004567623138,
+      "learning_rate": 2.3850682564138145e-05,
+      "loss": 0.0659,
+      "step": 514
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.5615881085395813,
+      "learning_rate": 2.3828087719541787e-05,
+      "loss": 0.1278,
+      "step": 515
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.27736374735832214,
+      "learning_rate": 2.3805462187096402e-05,
+      "loss": 0.0575,
+      "step": 516
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.24056284129619598,
+      "learning_rate": 2.3782806045451963e-05,
+      "loss": 0.0452,
+      "step": 517
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.4982932507991791,
+      "learning_rate": 2.376011937336485e-05,
+      "loss": 0.1689,
+      "step": 518
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.29784631729125977,
+      "learning_rate": 2.373740224969758e-05,
+      "loss": 0.0938,
+      "step": 519
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.43975648283958435,
+      "learning_rate": 2.371465475341852e-05,
+      "loss": 0.1245,
+      "step": 520
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.30927592515945435,
+      "learning_rate": 2.369187696360161e-05,
+      "loss": 0.0619,
+      "step": 521
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.36457571387290955,
+      "learning_rate": 2.3669068959426107e-05,
+      "loss": 0.0859,
+      "step": 522
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.25598183274269104,
+      "learning_rate": 2.364623082017629e-05,
+      "loss": 0.0461,
+      "step": 523
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.44431087374687195,
+      "learning_rate": 2.3623362625241193e-05,
+      "loss": 0.1439,
+      "step": 524
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.24602153897285461,
+      "learning_rate": 2.3600464454114326e-05,
+      "loss": 0.0408,
+      "step": 525
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.2084829956293106,
+      "learning_rate": 2.3577536386393416e-05,
+      "loss": 0.0856,
+      "step": 526
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.22140052914619446,
+      "learning_rate": 2.35545785017801e-05,
+      "loss": 0.0721,
+      "step": 527
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.24179723858833313,
+      "learning_rate": 2.3531590880079663e-05,
+      "loss": 0.0909,
+      "step": 528
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.3095971345901489,
+      "learning_rate": 2.3508573601200767e-05,
+      "loss": 0.0804,
+      "step": 529
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.2845352292060852,
+      "learning_rate": 2.348552674515517e-05,
+      "loss": 0.0462,
+      "step": 530
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.4917078912258148,
+      "learning_rate": 2.3462450392057437e-05,
+      "loss": 0.1184,
+      "step": 531
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.33279237151145935,
+      "learning_rate": 2.343934462212467e-05,
+      "loss": 0.0531,
+      "step": 532
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.33190539479255676,
+      "learning_rate": 2.341620951567624e-05,
+      "loss": 0.1114,
+      "step": 533
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.5710054039955139,
+      "learning_rate": 2.339304515313348e-05,
+      "loss": 0.1531,
+      "step": 534
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.20240336656570435,
+      "learning_rate": 2.3369851615019436e-05,
+      "loss": 0.0624,
+      "step": 535
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.4915199279785156,
+      "learning_rate": 2.3346628981958565e-05,
+      "loss": 0.1463,
+      "step": 536
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.29593560099601746,
+      "learning_rate": 2.332337733467646e-05,
+      "loss": 0.0789,
+      "step": 537
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.1819988489151001,
+      "learning_rate": 2.3300096753999585e-05,
+      "loss": 0.0724,
+      "step": 538
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.39005154371261597,
+      "learning_rate": 2.3276787320854967e-05,
+      "loss": 0.083,
+      "step": 539
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.4818272590637207,
+      "learning_rate": 2.3253449116269937e-05,
+      "loss": 0.0906,
+      "step": 540
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.3471298813819885,
+      "learning_rate": 2.3230082221371834e-05,
+      "loss": 0.0952,
+      "step": 541
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2572653591632843,
+      "learning_rate": 2.3206686717387742e-05,
+      "loss": 0.115,
+      "step": 542
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.407372385263443,
+      "learning_rate": 2.3183262685644177e-05,
+      "loss": 0.1084,
+      "step": 543
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.16921907663345337,
+      "learning_rate": 2.3159810207566832e-05,
+      "loss": 0.0694,
+      "step": 544
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2879027724266052,
+      "learning_rate": 2.3136329364680288e-05,
+      "loss": 0.0927,
+      "step": 545
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.23834727704524994,
+      "learning_rate": 2.3112820238607716e-05,
+      "loss": 0.0772,
+      "step": 546
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.29006141424179077,
+      "learning_rate": 2.3089282911070613e-05,
+      "loss": 0.0934,
+      "step": 547
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.4761680066585541,
+      "learning_rate": 2.3065717463888505e-05,
+      "loss": 0.1083,
+      "step": 548
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2773534953594208,
+      "learning_rate": 2.3042123978978665e-05,
+      "loss": 0.0802,
+      "step": 549
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.24215322732925415,
+      "learning_rate": 2.3018502538355827e-05,
+      "loss": 0.0661,
+      "step": 550
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.21285729110240936,
+      "learning_rate": 2.2994853224131915e-05,
+      "loss": 0.0709,
+      "step": 551
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1974431574344635,
+      "learning_rate": 2.2971176118515734e-05,
+      "loss": 0.0857,
+      "step": 552
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2114921659231186,
+      "learning_rate": 2.2947471303812708e-05,
+      "loss": 0.0715,
+      "step": 553
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.23644877970218658,
+      "learning_rate": 2.2923738862424565e-05,
+      "loss": 0.086,
+      "step": 554
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.2784081697463989,
+      "learning_rate": 2.2899978876849084e-05,
+      "loss": 0.0392,
+      "step": 555
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.20647476613521576,
+      "learning_rate": 2.287619142967979e-05,
+      "loss": 0.0479,
+      "step": 556
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.4792695641517639,
+      "learning_rate": 2.285237660360566e-05,
+      "loss": 0.1084,
+      "step": 557
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.32381659746170044,
+      "learning_rate": 2.2828534481410847e-05,
+      "loss": 0.0916,
+      "step": 558
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.5321642160415649,
+      "learning_rate": 2.28046651459744e-05,
+      "loss": 0.155,
+      "step": 559
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2742505669593811,
+      "learning_rate": 2.278076868026995e-05,
+      "loss": 0.0725,
+      "step": 560
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.40313002467155457,
+      "learning_rate": 2.2756845167365452e-05,
+      "loss": 0.0856,
+      "step": 561
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2948872745037079,
+      "learning_rate": 2.273289469042287e-05,
+      "loss": 0.0646,
+      "step": 562
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.23548893630504608,
+      "learning_rate": 2.2708917332697908e-05,
+      "loss": 0.0451,
+      "step": 563
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.25398510694503784,
+      "learning_rate": 2.26849131775397e-05,
+      "loss": 0.0647,
+      "step": 564
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.30981212854385376,
+      "learning_rate": 2.2660882308390547e-05,
+      "loss": 0.077,
+      "step": 565
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1695,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 565,
+  "total_flos": 5.169945694856806e+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 sha256:79597bc285f43a30d268224af285fdf02eba4cbe9e0332db42b2b4ac018fc35e
+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
+}