Upload folder using huggingface_hub

README.md

@@ -0,0 +1,162 @@
+---
+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/1e-4/
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+# base_model: Qwen/Qwen-7B
+base_model: Qwen/Qwen1.5-7B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+trust_remote_code: true
+
+load_in_8bit: true
+load_in_4bit: false
+strict: false
+
+datasets:
+  # - path: mhenrichsen/alpaca_2k_test
+  - path: /home/yujia/home/CN_Hateful/train_toxiCN_cn.json
+  # - path: /home/yujia/home/CN_Hateful/train_toxiCN.json
+  # - path: /home/yujia/home/CN_Hateful/train.json
+  # - path: /home/yujia/home/CN_Hateful/train_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/1e-4/
+# output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/toxi/1e-5/
+# output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/cold/3e-4/
+# output_dir: /home/yujia/home/CN_Hateful/trained_models/qwen/CN/cold/3e-4/
+
+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: 0.0001
+
+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/1e-4/
+
+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: 0.0997
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- 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          |
+| 0.0781        | 0.25  | 142  | 0.0848          |
+| 0.0151        | 0.5   | 284  | 0.0799          |
+| 0.118         | 0.75  | 426  | 0.0783          |
+| 0.1088        | 1.0   | 568  | 0.0927          |
+| 0.0725        | 1.26  | 710  | 0.0729          |
+| 0.0495        | 1.51  | 852  | 0.0755          |
+| 0.0627        | 1.76  | 994  | 0.0778          |
+| 0.0161        | 2.01  | 1136 | 0.0706          |
+| 0.0024        | 2.26  | 1278 | 0.0935          |
+| 0.005         | 2.51  | 1420 | 0.0936          |
+| 0.0028        | 2.76  | 1562 | 0.0997          |
+
+
+### 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",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_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 sha256:4307a7228c91758826616e9c40f6e83e63eb0703cc14ab9d0a8143419e9e7c08
+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",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_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:eeaaff455f38fc30e246f1cfb0a922d42faeab193ec958fbb51318aedc4ccabf
+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:d3c975f9a8e18e3a103d521cc89105b8f25bdffda67fcc27ade6783a29c5bdec
+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:dfa93553d337da32cd72950bc0532cb0783db958f6e9f48b2af1166ef9e1b9c2
+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 sha256:4dbf4a4958574f4f247050e1bfe19a04f1b69ecafa7464449959a7e1da1e5cf5
+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",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_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 sha256:33cdc70ed920507ea584a4454f8c9d7849bde2fc3efebba38ff9be504a950fbc
+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 sha256:43debd74ddd5abf1718133c535fce4b7d1006ead4d63cfc0ed4d55220e96f9ca
+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:d126722e4a85722e098404cc2792bf4798ba7bb9e99dadca28b19b907d584007
+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 sha256:4dbf4a4958574f4f247050e1bfe19a04f1b69ecafa7464449959a7e1da1e5cf5
+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",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_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 sha256:0606d15ffbc2964eba9c0dbf46f255c8dd652d95a8732628847e33a12d694923
+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:d56c8f44e5bbd3a5bc5cab6456acc1d6916f975114d593ebb94d834633cb45b0
+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:aea4b777480a073ce1cd6a8633b3662ef0fcb7e8c60eb61f15fac746a35ff7f8
+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": 4.680586814880371,
+      "learning_rate": 1e-05,
+      "loss": 3.3182,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 3.3362529277801514,
+      "eval_runtime": 14.4477,
+      "eval_samples_per_second": 33.016,
+      "eval_steps_per_second": 8.306,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 4.609802722930908,
+      "learning_rate": 2e-05,
+      "loss": 3.2788,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.793943405151367,
+      "learning_rate": 3e-05,
+      "loss": 3.3432,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.687256336212158,
+      "learning_rate": 4e-05,
+      "loss": 3.2521,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.676945209503174,
+      "learning_rate": 5e-05,
+      "loss": 3.1085,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.490086078643799,
+      "learning_rate": 6e-05,
+      "loss": 2.8093,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.042544364929199,
+      "learning_rate": 7e-05,
+      "loss": 2.3501,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 3.4973549842834473,
+      "learning_rate": 8e-05,
+      "loss": 1.6118,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.9255049228668213,
+      "learning_rate": 9e-05,
+      "loss": 0.9938,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.9458708763122559,
+      "learning_rate": 0.0001,
+      "loss": 0.4821,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.3317277431488037,
+      "learning_rate": 9.999991309598974e-05,
+      "loss": 0.3336,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.7918155193328857,
+      "learning_rate": 9.999965238426104e-05,
+      "loss": 0.1707,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.779201090335846,
+      "learning_rate": 9.999921786572015e-05,
+      "loss": 0.1089,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.8333582878112793,
+      "learning_rate": 9.999860954187756e-05,
+      "loss": 0.1829,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.7508969902992249,
+      "learning_rate": 9.999782741484788e-05,
+      "loss": 0.1284,
+      "step": 15
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.6024438142776489,
+      "learning_rate": 9.999687148734995e-05,
+      "loss": 0.1321,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.2141278237104416,
+      "learning_rate": 9.999574176270667e-05,
+      "loss": 0.1294,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.8326414227485657,
+      "learning_rate": 9.999443824484519e-05,
+      "loss": 0.1414,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.25254812836647034,
+      "learning_rate": 9.999296093829672e-05,
+      "loss": 0.1389,
+      "step": 19
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.24321849644184113,
+      "learning_rate": 9.999130984819662e-05,
+      "loss": 0.1354,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.27592459321022034,
+      "learning_rate": 9.998948498028435e-05,
+      "loss": 0.1032,
+      "step": 21
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.5619893670082092,
+      "learning_rate": 9.998748634090344e-05,
+      "loss": 0.1264,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.7668437361717224,
+      "learning_rate": 9.998531393700148e-05,
+      "loss": 0.1223,
+      "step": 23
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.38381776213645935,
+      "learning_rate": 9.99829677761301e-05,
+      "loss": 0.0988,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.8528074026107788,
+      "learning_rate": 9.998044786644491e-05,
+      "loss": 0.1421,
+      "step": 25
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.61940336227417,
+      "learning_rate": 9.997775421670556e-05,
+      "loss": 0.2738,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5642948150634766,
+      "learning_rate": 9.997488683627559e-05,
+      "loss": 0.1113,
+      "step": 27
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.31713128089904785,
+      "learning_rate": 9.997184573512245e-05,
+      "loss": 0.0593,
+      "step": 28
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.540770411491394,
+      "learning_rate": 9.996863092381752e-05,
+      "loss": 0.2008,
+      "step": 29
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.5343081951141357,
+      "learning_rate": 9.9965242413536e-05,
+      "loss": 0.1141,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.3453178107738495,
+      "learning_rate": 9.99616802160569e-05,
+      "loss": 0.1137,
+      "step": 31
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.24307988584041595,
+      "learning_rate": 9.995794434376297e-05,
+      "loss": 0.0971,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.1228247806429863,
+      "learning_rate": 9.995403480964072e-05,
+      "loss": 0.1246,
+      "step": 33
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.28919702768325806,
+      "learning_rate": 9.994995162728029e-05,
+      "loss": 0.1485,
+      "step": 34
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.16266010701656342,
+      "learning_rate": 9.994569481087552e-05,
+      "loss": 0.1196,
+      "step": 35
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.13942277431488037,
+      "learning_rate": 9.994126437522375e-05,
+      "loss": 0.1266,
+      "step": 36
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.22137008607387543,
+      "learning_rate": 9.99366603357259e-05,
+      "loss": 0.1226,
+      "step": 37
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.4418635070323944,
+      "learning_rate": 9.993188270838635e-05,
+      "loss": 0.1577,
+      "step": 38
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.1568412482738495,
+      "learning_rate": 9.992693150981292e-05,
+      "loss": 0.1205,
+      "step": 39
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.33117881417274475,
+      "learning_rate": 9.992180675721672e-05,
+      "loss": 0.1179,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.18135391175746918,
+      "learning_rate": 9.991650846841226e-05,
+      "loss": 0.098,
+      "step": 41
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.23688584566116333,
+      "learning_rate": 9.99110366618172e-05,
+      "loss": 0.0839,
+      "step": 42
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.40056225657463074,
+      "learning_rate": 9.990539135645245e-05,
+      "loss": 0.1648,
+      "step": 43
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.16901437938213348,
+      "learning_rate": 9.9899572571942e-05,
+      "loss": 0.052,
+      "step": 44
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6529514193534851,
+      "learning_rate": 9.989358032851284e-05,
+      "loss": 0.1448,
+      "step": 45
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.25050362944602966,
+      "learning_rate": 9.9887414646995e-05,
+      "loss": 0.083,
+      "step": 46
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.38230955600738525,
+      "learning_rate": 9.988107554882138e-05,
+      "loss": 0.0912,
+      "step": 47
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.24738825857639313,
+      "learning_rate": 9.987456305602769e-05,
+      "loss": 0.1337,
+      "step": 48
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.22692906856536865,
+      "learning_rate": 9.986787719125241e-05,
+      "loss": 0.0924,
+      "step": 49
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.6348592638969421,
+      "learning_rate": 9.986101797773667e-05,
+      "loss": 0.1401,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.27844250202178955,
+      "learning_rate": 9.985398543932421e-05,
+      "loss": 0.1028,
+      "step": 51
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4353552460670471,
+      "learning_rate": 9.984677960046123e-05,
+      "loss": 0.1245,
+      "step": 52
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3049747943878174,
+      "learning_rate": 9.98394004861964e-05,
+      "loss": 0.0936,
+      "step": 53
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.34531188011169434,
+      "learning_rate": 9.983184812218072e-05,
+      "loss": 0.0775,
+      "step": 54
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.252056360244751,
+      "learning_rate": 9.98241225346674e-05,
+      "loss": 0.1082,
+      "step": 55
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.14545601606369019,
+      "learning_rate": 9.981622375051183e-05,
+      "loss": 0.0857,
+      "step": 56
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.313376784324646,
+      "learning_rate": 9.980815179717145e-05,
+      "loss": 0.0798,
+      "step": 57
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.3164367079734802,
+      "learning_rate": 9.979990670270564e-05,
+      "loss": 0.1103,
+      "step": 58
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.30412447452545166,
+      "learning_rate": 9.979148849577572e-05,
+      "loss": 0.0889,
+      "step": 59
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2582318186759949,
+      "learning_rate": 9.978289720564471e-05,
+      "loss": 0.0844,
+      "step": 60
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2912735939025879,
+      "learning_rate": 9.977413286217728e-05,
+      "loss": 0.077,
+      "step": 61
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.3888057768344879,
+      "learning_rate": 9.976519549583974e-05,
+      "loss": 0.1386,
+      "step": 62
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.42121654748916626,
+      "learning_rate": 9.975608513769976e-05,
+      "loss": 0.0823,
+      "step": 63
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.4052259624004364,
+      "learning_rate": 9.974680181942645e-05,
+      "loss": 0.0846,
+      "step": 64
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2273682802915573,
+      "learning_rate": 9.973734557329009e-05,
+      "loss": 0.0589,
+      "step": 65
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.5051669478416443,
+      "learning_rate": 9.972771643216212e-05,
+      "loss": 0.1111,
+      "step": 66
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.2672370970249176,
+      "learning_rate": 9.971791442951497e-05,
+      "loss": 0.0819,
+      "step": 67
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.28557881712913513,
+      "learning_rate": 9.970793959942198e-05,
+      "loss": 0.0912,
+      "step": 68
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.34148702025413513,
+      "learning_rate": 9.969779197655726e-05,
+      "loss": 0.1036,
+      "step": 69
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.3550778925418854,
+      "learning_rate": 9.968747159619556e-05,
+      "loss": 0.0833,
+      "step": 70
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.3434258699417114,
+      "learning_rate": 9.967697849421221e-05,
+      "loss": 0.1186,
+      "step": 71
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.23545867204666138,
+      "learning_rate": 9.966631270708287e-05,
+      "loss": 0.1185,
+      "step": 72
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.28094542026519775,
+      "learning_rate": 9.965547427188357e-05,
+      "loss": 0.052,
+      "step": 73
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.13517600297927856,
+      "learning_rate": 9.964446322629043e-05,
+      "loss": 0.0695,
+      "step": 74
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.16696467995643616,
+      "learning_rate": 9.963327960857962e-05,
+      "loss": 0.1003,
+      "step": 75
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.18569788336753845,
+      "learning_rate": 9.962192345762717e-05,
+      "loss": 0.0495,
+      "step": 76
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.19817449152469635,
+      "learning_rate": 9.961039481290888e-05,
+      "loss": 0.067,
+      "step": 77
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.14672966301441193,
+      "learning_rate": 9.959869371450021e-05,
+      "loss": 0.0737,
+      "step": 78
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.302121639251709,
+      "learning_rate": 9.958682020307601e-05,
+      "loss": 0.0779,
+      "step": 79
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.35970303416252136,
+      "learning_rate": 9.957477431991054e-05,
+      "loss": 0.134,
+      "step": 80
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.308292955160141,
+      "learning_rate": 9.956255610687719e-05,
+      "loss": 0.1006,
+      "step": 81
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.27124735713005066,
+      "learning_rate": 9.955016560644847e-05,
+      "loss": 0.0572,
+      "step": 82
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.1820615977048874,
+      "learning_rate": 9.953760286169571e-05,
+      "loss": 0.0595,
+      "step": 83
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.36385104060173035,
+      "learning_rate": 9.952486791628905e-05,
+      "loss": 0.0874,
+      "step": 84
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.848340630531311,
+      "learning_rate": 9.95119608144972e-05,
+      "loss": 0.1178,
+      "step": 85
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.7947489023208618,
+      "learning_rate": 9.94988816011873e-05,
+      "loss": 0.1115,
+      "step": 86
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.33932074904441833,
+      "learning_rate": 9.94856303218248e-05,
+      "loss": 0.0546,
+      "step": 87
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.26873940229415894,
+      "learning_rate": 9.947220702247329e-05,
+      "loss": 0.0873,
+      "step": 88
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.3373044431209564,
+      "learning_rate": 9.945861174979429e-05,
+      "loss": 0.1051,
+      "step": 89
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.24391719698905945,
+      "learning_rate": 9.944484455104717e-05,
+      "loss": 0.0986,
+      "step": 90
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.4301680326461792,
+      "learning_rate": 9.943090547408888e-05,
+      "loss": 0.1524,
+      "step": 91
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.4246341288089752,
+      "learning_rate": 9.941679456737394e-05,
+      "loss": 0.1619,
+      "step": 92
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.2680893838405609,
+      "learning_rate": 9.940251187995411e-05,
+      "loss": 0.1187,
+      "step": 93
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.18920297920703888,
+      "learning_rate": 9.938805746147827e-05,
+      "loss": 0.105,
+      "step": 94
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.22168701887130737,
+      "learning_rate": 9.937343136219233e-05,
+      "loss": 0.0856,
+      "step": 95
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.2235199213027954,
+      "learning_rate": 9.935863363293896e-05,
+      "loss": 0.1026,
+      "step": 96
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.16578496992588043,
+      "learning_rate": 9.93436643251574e-05,
+      "loss": 0.0777,
+      "step": 97
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.15994016826152802,
+      "learning_rate": 9.932852349088342e-05,
+      "loss": 0.0957,
+      "step": 98
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.18692170083522797,
+      "learning_rate": 9.931321118274897e-05,
+      "loss": 0.0913,
+      "step": 99
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.15477485954761505,
+      "learning_rate": 9.929772745398206e-05,
+      "loss": 0.0911,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.28473320603370667,
+      "learning_rate": 9.928207235840664e-05,
+      "loss": 0.1283,
+      "step": 101
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.38557159900665283,
+      "learning_rate": 9.926624595044234e-05,
+      "loss": 0.1125,
+      "step": 102
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.13523289561271667,
+      "learning_rate": 9.925024828510427e-05,
+      "loss": 0.0555,
+      "step": 103
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.15305563807487488,
+      "learning_rate": 9.923407941800291e-05,
+      "loss": 0.1003,
+      "step": 104
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.21130621433258057,
+      "learning_rate": 9.921773940534382e-05,
+      "loss": 0.0945,
+      "step": 105
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.2301904559135437,
+      "learning_rate": 9.920122830392748e-05,
+      "loss": 0.1019,
+      "step": 106
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.16425654292106628,
+      "learning_rate": 9.918454617114918e-05,
+      "loss": 0.0781,
+      "step": 107
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.2672991454601288,
+      "learning_rate": 9.916769306499866e-05,
+      "loss": 0.085,
+      "step": 108
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.3746218681335449,
+      "learning_rate": 9.915066904406e-05,
+      "loss": 0.1698,
+      "step": 109
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.1691233068704605,
+      "learning_rate": 9.913347416751148e-05,
+      "loss": 0.046,
+      "step": 110
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.3089153468608856,
+      "learning_rate": 9.91161084951252e-05,
+      "loss": 0.131,
+      "step": 111
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1581045240163803,
+      "learning_rate": 9.909857208726705e-05,
+      "loss": 0.0654,
+      "step": 112
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2545772194862366,
+      "learning_rate": 9.908086500489637e-05,
+      "loss": 0.1021,
+      "step": 113
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2257249355316162,
+      "learning_rate": 9.906298730956586e-05,
+      "loss": 0.0636,
+      "step": 114
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.17862719297409058,
+      "learning_rate": 9.904493906342123e-05,
+      "loss": 0.0942,
+      "step": 115
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.23423053324222565,
+      "learning_rate": 9.902672032920106e-05,
+      "loss": 0.0676,
+      "step": 116
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.26653358340263367,
+      "learning_rate": 9.900833117023664e-05,
+      "loss": 0.0918,
+      "step": 117
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.4517073631286621,
+      "learning_rate": 9.89897716504516e-05,
+      "loss": 0.1102,
+      "step": 118
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.20187437534332275,
+      "learning_rate": 9.897104183436183e-05,
+      "loss": 0.0713,
+      "step": 119
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.5759711861610413,
+      "learning_rate": 9.895214178707516e-05,
+      "loss": 0.0837,
+      "step": 120
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.43704915046691895,
+      "learning_rate": 9.89330715742912e-05,
+      "loss": 0.0868,
+      "step": 121
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.30784374475479126,
+      "learning_rate": 9.891383126230104e-05,
+      "loss": 0.1171,
+      "step": 122
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.23538921773433685,
+      "learning_rate": 9.889442091798712e-05,
+      "loss": 0.055,
+      "step": 123
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.27727362513542175,
+      "learning_rate": 9.887484060882291e-05,
+      "loss": 0.041,
+      "step": 124
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.21666617691516876,
+      "learning_rate": 9.885509040287268e-05,
+      "loss": 0.0624,
+      "step": 125
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.2829636335372925,
+      "learning_rate": 9.883517036879132e-05,
+      "loss": 0.0946,
+      "step": 126
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.34035512804985046,
+      "learning_rate": 9.88150805758241e-05,
+      "loss": 0.0635,
+      "step": 127
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.44064444303512573,
+      "learning_rate": 9.879482109380634e-05,
+      "loss": 0.0931,
+      "step": 128
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.5164741277694702,
+      "learning_rate": 9.877439199316323e-05,
+      "loss": 0.0891,
+      "step": 129
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.5549228191375732,
+      "learning_rate": 9.875379334490962e-05,
+      "loss": 0.1144,
+      "step": 130
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.41133901476860046,
+      "learning_rate": 9.873302522064972e-05,
+      "loss": 0.1022,
+      "step": 131
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.5204330682754517,
+      "learning_rate": 9.871208769257685e-05,
+      "loss": 0.0867,
+      "step": 132
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.3383274972438812,
+      "learning_rate": 9.869098083347323e-05,
+      "loss": 0.0558,
+      "step": 133
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.7084139585494995,
+      "learning_rate": 9.866970471670967e-05,
+      "loss": 0.1208,
+      "step": 134
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.2974587380886078,
+      "learning_rate": 9.864825941624537e-05,
+      "loss": 0.1199,
+      "step": 135
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.1811504065990448,
+      "learning_rate": 9.862664500662764e-05,
+      "loss": 0.1025,
+      "step": 136
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.23748300969600677,
+      "learning_rate": 9.860486156299164e-05,
+      "loss": 0.0864,
+      "step": 137
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.21784676611423492,
+      "learning_rate": 9.85829091610601e-05,
+      "loss": 0.095,
+      "step": 138
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.26979225873947144,
+      "learning_rate": 9.856078787714309e-05,
+      "loss": 0.0864,
+      "step": 139
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.1479984074831009,
+      "learning_rate": 9.853849778813777e-05,
+      "loss": 0.0904,
+      "step": 140
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.17924343049526215,
+      "learning_rate": 9.851603897152803e-05,
+      "loss": 0.0752,
+      "step": 141
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.16448016464710236,
+      "learning_rate": 9.849341150538434e-05,
+      "loss": 0.0781,
+      "step": 142
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.0848281979560852,
+      "eval_runtime": 14.6961,
+      "eval_samples_per_second": 32.458,
+      "eval_steps_per_second": 8.165,
+      "step": 142
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.14405055344104767,
+      "learning_rate": 9.847061546836339e-05,
+      "loss": 0.1007,
+      "step": 143
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.20907168090343475,
+      "learning_rate": 9.844765093970787e-05,
+      "loss": 0.1126,
+      "step": 144
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.1777975857257843,
+      "learning_rate": 9.842451799924616e-05,
+      "loss": 0.0928,
+      "step": 145
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.1817995309829712,
+      "learning_rate": 9.840121672739208e-05,
+      "loss": 0.046,
+      "step": 146
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.2099136859178543,
+      "learning_rate": 9.837774720514457e-05,
+      "loss": 0.1032,
+      "step": 147
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.19467169046401978,
+      "learning_rate": 9.835410951408748e-05,
+      "loss": 0.0913,
+      "step": 148
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.24700500071048737,
+      "learning_rate": 9.833030373638919e-05,
+      "loss": 0.1101,
+      "step": 149
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.22854459285736084,
+      "learning_rate": 9.830632995480242e-05,
+      "loss": 0.0729,
+      "step": 150
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.206742063164711,
+      "learning_rate": 9.828218825266388e-05,
+      "loss": 0.0861,
+      "step": 151
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.40378740429878235,
+      "learning_rate": 9.8257878713894e-05,
+      "loss": 0.0948,
+      "step": 152
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.5055291652679443,
+      "learning_rate": 9.823340142299662e-05,
+      "loss": 0.193,
+      "step": 153
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.3036790192127228,
+      "learning_rate": 9.820875646505874e-05,
+      "loss": 0.0859,
+      "step": 154
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.1878231018781662,
+      "learning_rate": 9.818394392575019e-05,
+      "loss": 0.0702,
+      "step": 155
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.17990007996559143,
+      "learning_rate": 9.815896389132333e-05,
+      "loss": 0.0967,
+      "step": 156
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.22680750489234924,
+      "learning_rate": 9.813381644861277e-05,
+      "loss": 0.0959,
+      "step": 157
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.299663782119751,
+      "learning_rate": 9.810850168503506e-05,
+      "loss": 0.0801,
+      "step": 158
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.3132835924625397,
+      "learning_rate": 9.808301968858837e-05,
+      "loss": 0.1151,
+      "step": 159
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.16891297698020935,
+      "learning_rate": 9.805737054785222e-05,
+      "loss": 0.0799,
+      "step": 160
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.23542983829975128,
+      "learning_rate": 9.803155435198712e-05,
+      "loss": 0.0645,
+      "step": 161
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1784803569316864,
+      "learning_rate": 9.800557119073433e-05,
+      "loss": 0.0475,
+      "step": 162
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.37001606822013855,
+      "learning_rate": 9.797942115441545e-05,
+      "loss": 0.1331,
+      "step": 163
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.18926851451396942,
+      "learning_rate": 9.795310433393226e-05,
+      "loss": 0.0744,
+      "step": 164
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.15572589635849,
+      "learning_rate": 9.792662082076618e-05,
+      "loss": 0.0551,
+      "step": 165
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.2562514841556549,
+      "learning_rate": 9.789997070697821e-05,
+      "loss": 0.106,
+      "step": 166
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.4756919741630554,
+      "learning_rate": 9.787315408520838e-05,
+      "loss": 0.1229,
+      "step": 167
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2322833091020584,
+      "learning_rate": 9.78461710486756e-05,
+      "loss": 0.1212,
+      "step": 168
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.28180065751075745,
+      "learning_rate": 9.78190216911772e-05,
+      "loss": 0.0855,
+      "step": 169
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2058788239955902,
+      "learning_rate": 9.779170610708872e-05,
+      "loss": 0.0445,
+      "step": 170
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.16885802149772644,
+      "learning_rate": 9.776422439136352e-05,
+      "loss": 0.0619,
+      "step": 171
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2562006413936615,
+      "learning_rate": 9.773657663953243e-05,
+      "loss": 0.1111,
+      "step": 172
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.2394249439239502,
+      "learning_rate": 9.770876294770349e-05,
+      "loss": 0.0562,
+      "step": 173
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.214800164103508,
+      "learning_rate": 9.768078341256155e-05,
+      "loss": 0.0428,
+      "step": 174
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.30056923627853394,
+      "learning_rate": 9.765263813136796e-05,
+      "loss": 0.1173,
+      "step": 175
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.3174525499343872,
+      "learning_rate": 9.762432720196024e-05,
+      "loss": 0.0871,
+      "step": 176
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.31560906767845154,
+      "learning_rate": 9.75958507227517e-05,
+      "loss": 0.1133,
+      "step": 177
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.21752357482910156,
+      "learning_rate": 9.756720879273117e-05,
+      "loss": 0.0421,
+      "step": 178
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3215218484401703,
+      "learning_rate": 9.753840151146259e-05,
+      "loss": 0.0596,
+      "step": 179
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.3161137104034424,
+      "learning_rate": 9.750942897908468e-05,
+      "loss": 0.122,
+      "step": 180
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4206744134426117,
+      "learning_rate": 9.748029129631062e-05,
+      "loss": 0.0966,
+      "step": 181
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.28242579102516174,
+      "learning_rate": 9.745098856442768e-05,
+      "loss": 0.0853,
+      "step": 182
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.24647079408168793,
+      "learning_rate": 9.742152088529684e-05,
+      "loss": 0.1077,
+      "step": 183
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.29940977692604065,
+      "learning_rate": 9.739188836135247e-05,
+      "loss": 0.0837,
+      "step": 184
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.21811984479427338,
+      "learning_rate": 9.7362091095602e-05,
+      "loss": 0.1,
+      "step": 185
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.24434742331504822,
+      "learning_rate": 9.733212919162549e-05,
+      "loss": 0.0839,
+      "step": 186
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.1656690537929535,
+      "learning_rate": 9.730200275357535e-05,
+      "loss": 0.0894,
+      "step": 187
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.16984042525291443,
+      "learning_rate": 9.727171188617587e-05,
+      "loss": 0.0732,
+      "step": 188
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.19889003038406372,
+      "learning_rate": 9.7241256694723e-05,
+      "loss": 0.0832,
+      "step": 189
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1639273464679718,
+      "learning_rate": 9.721063728508383e-05,
+      "loss": 0.0912,
+      "step": 190
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.26211172342300415,
+      "learning_rate": 9.717985376369639e-05,
+      "loss": 0.0986,
+      "step": 191
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.12403538823127747,
+      "learning_rate": 9.714890623756912e-05,
+      "loss": 0.0844,
+      "step": 192
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1882586032152176,
+      "learning_rate": 9.711779481428057e-05,
+      "loss": 0.1163,
+      "step": 193
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1780715435743332,
+      "learning_rate": 9.708651960197904e-05,
+      "loss": 0.1038,
+      "step": 194
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1291002333164215,
+      "learning_rate": 9.705508070938218e-05,
+      "loss": 0.0746,
+      "step": 195
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.2384466975927353,
+      "learning_rate": 9.702347824577666e-05,
+      "loss": 0.0909,
+      "step": 196
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.25463247299194336,
+      "learning_rate": 9.699171232101768e-05,
+      "loss": 0.0977,
+      "step": 197
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.19303986430168152,
+      "learning_rate": 9.69597830455287e-05,
+      "loss": 0.1137,
+      "step": 198
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.21899022161960602,
+      "learning_rate": 9.692769053030099e-05,
+      "loss": 0.0671,
+      "step": 199
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.16923530399799347,
+      "learning_rate": 9.689543488689332e-05,
+      "loss": 0.0776,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.260955810546875,
+      "learning_rate": 9.686301622743144e-05,
+      "loss": 0.092,
+      "step": 201
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.1771455854177475,
+      "learning_rate": 9.683043466460782e-05,
+      "loss": 0.06,
+      "step": 202
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.18851810693740845,
+      "learning_rate": 9.67976903116812e-05,
+      "loss": 0.0965,
+      "step": 203
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.589522659778595,
+      "learning_rate": 9.676478328247622e-05,
+      "loss": 0.1673,
+      "step": 204
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.21747058629989624,
+      "learning_rate": 9.673171369138296e-05,
+      "loss": 0.0997,
+      "step": 205
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.4168107807636261,
+      "learning_rate": 9.669848165335666e-05,
+      "loss": 0.0795,
+      "step": 206
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.6520416140556335,
+      "learning_rate": 9.666508728391719e-05,
+      "loss": 0.1177,
+      "step": 207
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.3752453029155731,
+      "learning_rate": 9.663153069914875e-05,
+      "loss": 0.0871,
+      "step": 208
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.26546868681907654,
+      "learning_rate": 9.65978120156994e-05,
+      "loss": 0.0647,
+      "step": 209
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.20044176280498505,
+      "learning_rate": 9.656393135078068e-05,
+      "loss": 0.1072,
+      "step": 210
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.25033503770828247,
+      "learning_rate": 9.652988882216724e-05,
+      "loss": 0.1326,
+      "step": 211
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.24569682776927948,
+      "learning_rate": 9.649568454819637e-05,
+      "loss": 0.0931,
+      "step": 212
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.5623157620429993,
+      "learning_rate": 9.64613186477676e-05,
+      "loss": 0.2157,
+      "step": 213
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.15052182972431183,
+      "learning_rate": 9.642679124034233e-05,
+      "loss": 0.1236,
+      "step": 214
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.14209671318531036,
+      "learning_rate": 9.639210244594334e-05,
+      "loss": 0.0971,
+      "step": 215
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.1627768725156784,
+      "learning_rate": 9.635725238515445e-05,
+      "loss": 0.1161,
+      "step": 216
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.10190293937921524,
+      "learning_rate": 9.63222411791201e-05,
+      "loss": 0.0999,
+      "step": 217
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.11575043201446533,
+      "learning_rate": 9.62870689495448e-05,
+      "loss": 0.0986,
+      "step": 218
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.09842410683631897,
+      "learning_rate": 9.62517358186929e-05,
+      "loss": 0.1176,
+      "step": 219
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.14816004037857056,
+      "learning_rate": 9.621624190938803e-05,
+      "loss": 0.0833,
+      "step": 220
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.11311839520931244,
+      "learning_rate": 9.618058734501269e-05,
+      "loss": 0.0815,
+      "step": 221
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.17481163144111633,
+      "learning_rate": 9.614477224950789e-05,
+      "loss": 0.0678,
+      "step": 222
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.2277013659477234,
+      "learning_rate": 9.610879674737264e-05,
+      "loss": 0.0941,
+      "step": 223
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.14689870178699493,
+      "learning_rate": 9.607266096366352e-05,
+      "loss": 0.0991,
+      "step": 224
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.24558769166469574,
+      "learning_rate": 9.603636502399436e-05,
+      "loss": 0.0878,
+      "step": 225
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.1541660875082016,
+      "learning_rate": 9.599990905453567e-05,
+      "loss": 0.0784,
+      "step": 226
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.12188339233398438,
+      "learning_rate": 9.59632931820142e-05,
+      "loss": 0.0464,
+      "step": 227
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.32710394263267517,
+      "learning_rate": 9.592651753371265e-05,
+      "loss": 0.0541,
+      "step": 228
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.3118465840816498,
+      "learning_rate": 9.588958223746903e-05,
+      "loss": 0.0845,
+      "step": 229
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.26805219054222107,
+      "learning_rate": 9.585248742167639e-05,
+      "loss": 0.0485,
+      "step": 230
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.7972936630249023,
+      "learning_rate": 9.581523321528223e-05,
+      "loss": 0.1013,
+      "step": 231
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.6285438537597656,
+      "learning_rate": 9.577781974778817e-05,
+      "loss": 0.0767,
+      "step": 232
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.6384493708610535,
+      "learning_rate": 9.57402471492494e-05,
+      "loss": 0.1855,
+      "step": 233
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.5759001970291138,
+      "learning_rate": 9.570251555027432e-05,
+      "loss": 0.1585,
+      "step": 234
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.42002353072166443,
+      "learning_rate": 9.566462508202402e-05,
+      "loss": 0.1479,
+      "step": 235
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.18405884504318237,
+      "learning_rate": 9.562657587621184e-05,
+      "loss": 0.09,
+      "step": 236
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.20893922448158264,
+      "learning_rate": 9.558836806510291e-05,
+      "loss": 0.0685,
+      "step": 237
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.31388092041015625,
+      "learning_rate": 9.555000178151374e-05,
+      "loss": 0.0983,
+      "step": 238
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.20344533026218414,
+      "learning_rate": 9.551147715881166e-05,
+      "loss": 0.0944,
+      "step": 239
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.1582648903131485,
+      "learning_rate": 9.547279433091446e-05,
+      "loss": 0.0662,
+      "step": 240
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.16737405955791473,
+      "learning_rate": 9.543395343228983e-05,
+      "loss": 0.1565,
+      "step": 241
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.21974924206733704,
+      "learning_rate": 9.539495459795499e-05,
+      "loss": 0.1243,
+      "step": 242
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.1147058829665184,
+      "learning_rate": 9.535579796347612e-05,
+      "loss": 0.0727,
+      "step": 243
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.13460345566272736,
+      "learning_rate": 9.531648366496799e-05,
+      "loss": 0.0691,
+      "step": 244
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.1404263824224472,
+      "learning_rate": 9.527701183909336e-05,
+      "loss": 0.0975,
+      "step": 245
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.17380090057849884,
+      "learning_rate": 9.523738262306269e-05,
+      "loss": 0.0873,
+      "step": 246
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.13862797617912292,
+      "learning_rate": 9.519759615463346e-05,
+      "loss": 0.0738,
+      "step": 247
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.17551685869693756,
+      "learning_rate": 9.51576525721098e-05,
+      "loss": 0.0676,
+      "step": 248
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.20715269446372986,
+      "learning_rate": 9.511755201434205e-05,
+      "loss": 0.0737,
+      "step": 249
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.14763356745243073,
+      "learning_rate": 9.507729462072614e-05,
+      "loss": 0.07,
+      "step": 250
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.317452073097229,
+      "learning_rate": 9.503688053120327e-05,
+      "loss": 0.1252,
+      "step": 251
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.21908459067344666,
+      "learning_rate": 9.499630988625925e-05,
+      "loss": 0.0877,
+      "step": 252
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.3233601450920105,
+      "learning_rate": 9.49555828269242e-05,
+      "loss": 0.0891,
+      "step": 253
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.4098372161388397,
+      "learning_rate": 9.491469949477187e-05,
+      "loss": 0.0805,
+      "step": 254
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.40573808550834656,
+      "learning_rate": 9.487366003191931e-05,
+      "loss": 0.1284,
+      "step": 255
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.3391616940498352,
+      "learning_rate": 9.483246458102625e-05,
+      "loss": 0.0901,
+      "step": 256
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.1822938323020935,
+      "learning_rate": 9.479111328529473e-05,
+      "loss": 0.0398,
+      "step": 257
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.4700302183628082,
+      "learning_rate": 9.474960628846843e-05,
+      "loss": 0.1509,
+      "step": 258
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.20210890471935272,
+      "learning_rate": 9.470794373483236e-05,
+      "loss": 0.0765,
+      "step": 259
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.28329914808273315,
+      "learning_rate": 9.466612576921223e-05,
+      "loss": 0.0666,
+      "step": 260
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.41083166003227234,
+      "learning_rate": 9.462415253697401e-05,
+      "loss": 0.1248,
+      "step": 261
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.17644570767879486,
+      "learning_rate": 9.458202418402338e-05,
+      "loss": 0.0532,
+      "step": 262
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.2667219936847687,
+      "learning_rate": 9.453974085680526e-05,
+      "loss": 0.0937,
+      "step": 263
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.20900332927703857,
+      "learning_rate": 9.449730270230326e-05,
+      "loss": 0.0853,
+      "step": 264
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.26425743103027344,
+      "learning_rate": 9.445470986803922e-05,
+      "loss": 0.12,
+      "step": 265
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.1956167221069336,
+      "learning_rate": 9.441196250207267e-05,
+      "loss": 0.0965,
+      "step": 266
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.21896903216838837,
+      "learning_rate": 9.436906075300032e-05,
+      "loss": 0.0867,
+      "step": 267
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.2082919031381607,
+      "learning_rate": 9.432600476995551e-05,
+      "loss": 0.0847,
+      "step": 268
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.1674569696187973,
+      "learning_rate": 9.428279470260776e-05,
+      "loss": 0.0846,
+      "step": 269
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.23109744489192963,
+      "learning_rate": 9.423943070116218e-05,
+      "loss": 0.136,
+      "step": 270
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.21344415843486786,
+      "learning_rate": 9.4195912916359e-05,
+      "loss": 0.1091,
+      "step": 271
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.16391590237617493,
+      "learning_rate": 9.415224149947306e-05,
+      "loss": 0.0901,
+      "step": 272
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.2023243010044098,
+      "learning_rate": 9.410841660231315e-05,
+      "loss": 0.0635,
+      "step": 273
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.1723608821630478,
+      "learning_rate": 9.406443837722168e-05,
+      "loss": 0.1001,
+      "step": 274
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.1470147669315338,
+      "learning_rate": 9.402030697707398e-05,
+      "loss": 0.0721,
+      "step": 275
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.15082985162734985,
+      "learning_rate": 9.397602255527791e-05,
+      "loss": 0.0698,
+      "step": 276
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.16322006285190582,
+      "learning_rate": 9.393158526577323e-05,
+      "loss": 0.0809,
+      "step": 277
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.10098633915185928,
+      "learning_rate": 9.388699526303105e-05,
+      "loss": 0.0386,
+      "step": 278
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.19049708545207977,
+      "learning_rate": 9.38422527020534e-05,
+      "loss": 0.0559,
+      "step": 279
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.22742775082588196,
+      "learning_rate": 9.37973577383726e-05,
+      "loss": 0.0802,
+      "step": 280
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.2055177539587021,
+      "learning_rate": 9.375231052805072e-05,
+      "loss": 0.1048,
+      "step": 281
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.1366245150566101,
+      "learning_rate": 9.370711122767913e-05,
+      "loss": 0.0204,
+      "step": 282
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3235447406768799,
+      "learning_rate": 9.36617599943778e-05,
+      "loss": 0.0974,
+      "step": 283
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.09579204767942429,
+      "learning_rate": 9.361625698579493e-05,
+      "loss": 0.0151,
+      "step": 284
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.07987037301063538,
+      "eval_runtime": 14.6437,
+      "eval_samples_per_second": 32.574,
+      "eval_steps_per_second": 8.195,
+      "step": 284
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.22850771248340607,
+      "learning_rate": 9.357060236010625e-05,
+      "loss": 0.0458,
+      "step": 285
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.4980478882789612,
+      "learning_rate": 9.352479627601457e-05,
+      "loss": 0.1306,
+      "step": 286
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.18770304322242737,
+      "learning_rate": 9.347883889274923e-05,
+      "loss": 0.0218,
+      "step": 287
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.6386083364486694,
+      "learning_rate": 9.34327303700654e-05,
+      "loss": 0.0912,
+      "step": 288
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.4997164309024811,
+      "learning_rate": 9.338647086824372e-05,
+      "loss": 0.1083,
+      "step": 289
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.31682559847831726,
+      "learning_rate": 9.334006054808966e-05,
+      "loss": 0.0947,
+      "step": 290
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.28325051069259644,
+      "learning_rate": 9.329349957093292e-05,
+      "loss": 0.0794,
+      "step": 291
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5778185725212097,
+      "learning_rate": 9.324678809862695e-05,
+      "loss": 0.1223,
+      "step": 292
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2953624725341797,
+      "learning_rate": 9.319992629354828e-05,
+      "loss": 0.0747,
+      "step": 293
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.28283196687698364,
+      "learning_rate": 9.31529143185961e-05,
+      "loss": 0.1099,
+      "step": 294
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.36138102412223816,
+      "learning_rate": 9.310575233719154e-05,
+      "loss": 0.1303,
+      "step": 295
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.16202205419540405,
+      "learning_rate": 9.305844051327725e-05,
+      "loss": 0.0805,
+      "step": 296
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.11523901671171188,
+      "learning_rate": 9.30109790113167e-05,
+      "loss": 0.0775,
+      "step": 297
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.10756238549947739,
+      "learning_rate": 9.296336799629369e-05,
+      "loss": 0.0795,
+      "step": 298
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.18142195045948029,
+      "learning_rate": 9.291560763371173e-05,
+      "loss": 0.0833,
+      "step": 299
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.14596430957317352,
+      "learning_rate": 9.28676980895935e-05,
+      "loss": 0.0904,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.10054739564657211,
+      "learning_rate": 9.28196395304803e-05,
+      "loss": 0.0898,
+      "step": 301
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.24579764902591705,
+      "learning_rate": 9.277143212343134e-05,
+      "loss": 0.145,
+      "step": 302
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.13506978750228882,
+      "learning_rate": 9.272307603602334e-05,
+      "loss": 0.0847,
+      "step": 303
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.17480792105197906,
+      "learning_rate": 9.267457143634979e-05,
+      "loss": 0.125,
+      "step": 304
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.31458401679992676,
+      "learning_rate": 9.262591849302048e-05,
+      "loss": 0.1047,
+      "step": 305
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.17494355142116547,
+      "learning_rate": 9.257711737516082e-05,
+      "loss": 0.0576,
+      "step": 306
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.2996468245983124,
+      "learning_rate": 9.252816825241134e-05,
+      "loss": 0.1012,
+      "step": 307
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.19122976064682007,
+      "learning_rate": 9.247907129492707e-05,
+      "loss": 0.0878,
+      "step": 308
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.16079925000667572,
+      "learning_rate": 9.242982667337685e-05,
+      "loss": 0.0778,
+      "step": 309
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.2628028392791748,
+      "learning_rate": 9.238043455894293e-05,
+      "loss": 0.0987,
+      "step": 310
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.318097859621048,
+      "learning_rate": 9.23308951233202e-05,
+      "loss": 0.1108,
+      "step": 311
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.2207389920949936,
+      "learning_rate": 9.228120853871571e-05,
+      "loss": 0.0826,
+      "step": 312
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.34375905990600586,
+      "learning_rate": 9.223137497784797e-05,
+      "loss": 0.1174,
+      "step": 313
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.16714760661125183,
+      "learning_rate": 9.218139461394644e-05,
+      "loss": 0.0883,
+      "step": 314
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.24213539063930511,
+      "learning_rate": 9.213126762075088e-05,
+      "loss": 0.0686,
+      "step": 315
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.2654499113559723,
+      "learning_rate": 9.208099417251077e-05,
+      "loss": 0.1185,
+      "step": 316
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.1353083997964859,
+      "learning_rate": 9.203057444398469e-05,
+      "loss": 0.0806,
+      "step": 317
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.30304938554763794,
+      "learning_rate": 9.198000861043967e-05,
+      "loss": 0.0817,
+      "step": 318
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.14495517313480377,
+      "learning_rate": 9.192929684765067e-05,
+      "loss": 0.0436,
+      "step": 319
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.2180556207895279,
+      "learning_rate": 9.187843933189995e-05,
+      "loss": 0.1255,
+      "step": 320
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.3051697611808777,
+      "learning_rate": 9.182743623997634e-05,
+      "loss": 0.1241,
+      "step": 321
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.42936787009239197,
+      "learning_rate": 9.17762877491748e-05,
+      "loss": 0.1847,
+      "step": 322
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.20895107090473175,
+      "learning_rate": 9.172499403729566e-05,
+      "loss": 0.0939,
+      "step": 323
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.15273532271385193,
+      "learning_rate": 9.167355528264414e-05,
+      "loss": 0.1012,
+      "step": 324
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.15428248047828674,
+      "learning_rate": 9.162197166402956e-05,
+      "loss": 0.061,
+      "step": 325
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.13089029490947723,
+      "learning_rate": 9.157024336076487e-05,
+      "loss": 0.089,
+      "step": 326
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.12000248581171036,
+      "learning_rate": 9.151837055266594e-05,
+      "loss": 0.0813,
+      "step": 327
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.12965545058250427,
+      "learning_rate": 9.146635342005099e-05,
+      "loss": 0.113,
+      "step": 328
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.12225235253572464,
+      "learning_rate": 9.14141921437399e-05,
+      "loss": 0.0968,
+      "step": 329
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.11869696527719498,
+      "learning_rate": 9.136188690505363e-05,
+      "loss": 0.0752,
+      "step": 330
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.22600843012332916,
+      "learning_rate": 9.130943788581359e-05,
+      "loss": 0.1049,
+      "step": 331
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.13381795585155487,
+      "learning_rate": 9.125684526834099e-05,
+      "loss": 0.0917,
+      "step": 332
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.12936879694461823,
+      "learning_rate": 9.120410923545619e-05,
+      "loss": 0.0782,
+      "step": 333
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.14804388582706451,
+      "learning_rate": 9.115122997047811e-05,
+      "loss": 0.0959,
+      "step": 334
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.18504676222801208,
+      "learning_rate": 9.109820765722357e-05,
+      "loss": 0.1126,
+      "step": 335
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.1957363486289978,
+      "learning_rate": 9.10450424800066e-05,
+      "loss": 0.101,
+      "step": 336
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.15677915513515472,
+      "learning_rate": 9.099173462363792e-05,
+      "loss": 0.0775,
+      "step": 337
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.124906025826931,
+      "learning_rate": 9.093828427342418e-05,
+      "loss": 0.07,
+      "step": 338
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.12451624125242233,
+      "learning_rate": 9.088469161516735e-05,
+      "loss": 0.0588,
+      "step": 339
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.509678304195404,
+      "learning_rate": 9.083095683516414e-05,
+      "loss": 0.1563,
+      "step": 340
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2245551496744156,
+      "learning_rate": 9.077708012020524e-05,
+      "loss": 0.1029,
+      "step": 341
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2735763192176819,
+      "learning_rate": 9.072306165757476e-05,
+      "loss": 0.0958,
+      "step": 342
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.2062731385231018,
+      "learning_rate": 9.066890163504955e-05,
+      "loss": 0.0638,
+      "step": 343
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.1664024293422699,
+      "learning_rate": 9.061460024089853e-05,
+      "loss": 0.0555,
+      "step": 344
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.15788845717906952,
+      "learning_rate": 9.056015766388205e-05,
+      "loss": 0.0509,
+      "step": 345
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.185616135597229,
+      "learning_rate": 9.050557409325125e-05,
+      "loss": 0.1196,
+      "step": 346
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.24650661647319794,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0723,
+      "step": 347
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.23959776759147644,
+      "learning_rate": 9.039598473060113e-05,
+      "loss": 0.1139,
+      "step": 348
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.24370582401752472,
+      "learning_rate": 9.034097931953201e-05,
+      "loss": 0.0559,
+      "step": 349
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.11590461432933807,
+      "learning_rate": 9.028583367674765e-05,
+      "loss": 0.0285,
+      "step": 350
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.21419131755828857,
+      "learning_rate": 9.023054799394316e-05,
+      "loss": 0.0686,
+      "step": 351
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2115790992975235,
+      "learning_rate": 9.017512246330042e-05,
+      "loss": 0.071,
+      "step": 352
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.2025454044342041,
+      "learning_rate": 9.011955727748748e-05,
+      "loss": 0.0993,
+      "step": 353
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.22743502259254456,
+      "learning_rate": 9.006385262965786e-05,
+      "loss": 0.0705,
+      "step": 354
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.16963045299053192,
+      "learning_rate": 9.00080087134498e-05,
+      "loss": 0.0569,
+      "step": 355
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.12319042533636093,
+      "learning_rate": 8.995202572298576e-05,
+      "loss": 0.0427,
+      "step": 356
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.15424852073192596,
+      "learning_rate": 8.989590385287155e-05,
+      "loss": 0.0564,
+      "step": 357
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.306594580411911,
+      "learning_rate": 8.983964329819583e-05,
+      "loss": 0.095,
+      "step": 358
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.13876177370548248,
+      "learning_rate": 8.978324425452931e-05,
+      "loss": 0.0641,
+      "step": 359
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.19561870396137238,
+      "learning_rate": 8.972670691792409e-05,
+      "loss": 0.0635,
+      "step": 360
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.3458711504936218,
+      "learning_rate": 8.967003148491304e-05,
+      "loss": 0.1328,
+      "step": 361
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.1129189059138298,
+      "learning_rate": 8.961321815250905e-05,
+      "loss": 0.0205,
+      "step": 362
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.3680332601070404,
+      "learning_rate": 8.955626711820438e-05,
+      "loss": 0.1302,
+      "step": 363
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2695287764072418,
+      "learning_rate": 8.949917857996996e-05,
+      "loss": 0.0511,
+      "step": 364
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.17332953214645386,
+      "learning_rate": 8.94419527362547e-05,
+      "loss": 0.0494,
+      "step": 365
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.11610284447669983,
+      "learning_rate": 8.938458978598483e-05,
+      "loss": 0.0381,
+      "step": 366
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.23595061898231506,
+      "learning_rate": 8.932708992856315e-05,
+      "loss": 0.0802,
+      "step": 367
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.26876452565193176,
+      "learning_rate": 8.926945336386838e-05,
+      "loss": 0.0461,
+      "step": 368
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.19504375755786896,
+      "learning_rate": 8.921168029225448e-05,
+      "loss": 0.0317,
+      "step": 369
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.4416268467903137,
+      "learning_rate": 8.915377091454992e-05,
+      "loss": 0.0952,
+      "step": 370
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.32519325613975525,
+      "learning_rate": 8.909572543205698e-05,
+      "loss": 0.1027,
+      "step": 371
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.3939536511898041,
+      "learning_rate": 8.903754404655106e-05,
+      "loss": 0.1718,
+      "step": 372
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.20514678955078125,
+      "learning_rate": 8.897922696027999e-05,
+      "loss": 0.06,
+      "step": 373
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.3049127459526062,
+      "learning_rate": 8.892077437596332e-05,
+      "loss": 0.1014,
+      "step": 374
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.19251297414302826,
+      "learning_rate": 8.88621864967916e-05,
+      "loss": 0.048,
+      "step": 375
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.21226820349693298,
+      "learning_rate": 8.880346352642575e-05,
+      "loss": 0.0652,
+      "step": 376
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.42633509635925293,
+      "learning_rate": 8.874460566899616e-05,
+      "loss": 0.1083,
+      "step": 377
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.24073313176631927,
+      "learning_rate": 8.868561312910221e-05,
+      "loss": 0.0851,
+      "step": 378
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.3047339618206024,
+      "learning_rate": 8.862648611181145e-05,
+      "loss": 0.086,
+      "step": 379
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.2227114737033844,
+      "learning_rate": 8.856722482265886e-05,
+      "loss": 0.1196,
+      "step": 380
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.1860799938440323,
+      "learning_rate": 8.850782946764619e-05,
+      "loss": 0.0779,
+      "step": 381
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.2109043002128601,
+      "learning_rate": 8.844830025324122e-05,
+      "loss": 0.076,
+      "step": 382
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.1998620331287384,
+      "learning_rate": 8.838863738637706e-05,
+      "loss": 0.1027,
+      "step": 383
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.12607474625110626,
+      "learning_rate": 8.832884107445139e-05,
+      "loss": 0.0436,
+      "step": 384
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.2890150845050812,
+      "learning_rate": 8.826891152532579e-05,
+      "loss": 0.0966,
+      "step": 385
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.4496447443962097,
+      "learning_rate": 8.820884894732497e-05,
+      "loss": 0.1575,
+      "step": 386
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.19411596655845642,
+      "learning_rate": 8.814865354923613e-05,
+      "loss": 0.1201,
+      "step": 387
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.19513021409511566,
+      "learning_rate": 8.808832554030808e-05,
+      "loss": 0.0747,
+      "step": 388
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.14038780331611633,
+      "learning_rate": 8.802786513025068e-05,
+      "loss": 0.0608,
+      "step": 389
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.14907363057136536,
+      "learning_rate": 8.796727252923402e-05,
+      "loss": 0.0843,
+      "step": 390
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.18512780964374542,
+      "learning_rate": 8.790654794788769e-05,
+      "loss": 0.0988,
+      "step": 391
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.17880797386169434,
+      "learning_rate": 8.784569159730007e-05,
+      "loss": 0.079,
+      "step": 392
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.16263402998447418,
+      "learning_rate": 8.778470368901762e-05,
+      "loss": 0.0704,
+      "step": 393
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.27071598172187805,
+      "learning_rate": 8.772358443504405e-05,
+      "loss": 0.0983,
+      "step": 394
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.23446398973464966,
+      "learning_rate": 8.766233404783974e-05,
+      "loss": 0.0577,
+      "step": 395
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.2932927906513214,
+      "learning_rate": 8.760095274032083e-05,
+      "loss": 0.0946,
+      "step": 396
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.29224956035614014,
+      "learning_rate": 8.75394407258586e-05,
+      "loss": 0.078,
+      "step": 397
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.15467233955860138,
+      "learning_rate": 8.747779821827868e-05,
+      "loss": 0.0779,
+      "step": 398
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.1883499026298523,
+      "learning_rate": 8.741602543186032e-05,
+      "loss": 0.0721,
+      "step": 399
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.25179481506347656,
+      "learning_rate": 8.735412258133562e-05,
+      "loss": 0.0875,
+      "step": 400
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.23851999640464783,
+      "learning_rate": 8.729208988188881e-05,
+      "loss": 0.0959,
+      "step": 401
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.2662704885005951,
+      "learning_rate": 8.722992754915554e-05,
+      "loss": 0.1025,
+      "step": 402
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.17909982800483704,
+      "learning_rate": 8.716763579922204e-05,
+      "loss": 0.0504,
+      "step": 403
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.17002324759960175,
+      "learning_rate": 8.710521484862439e-05,
+      "loss": 0.0856,
+      "step": 404
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.2229025810956955,
+      "learning_rate": 8.704266491434788e-05,
+      "loss": 0.0591,
+      "step": 405
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.1444559544324875,
+      "learning_rate": 8.697998621382607e-05,
+      "loss": 0.0297,
+      "step": 406
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.2677093744277954,
+      "learning_rate": 8.69171789649402e-05,
+      "loss": 0.0543,
+      "step": 407
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5875506401062012,
+      "learning_rate": 8.685424338601834e-05,
+      "loss": 0.1199,
+      "step": 408
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.34576529264450073,
+      "learning_rate": 8.679117969583464e-05,
+      "loss": 0.1003,
+      "step": 409
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.2765222489833832,
+      "learning_rate": 8.672798811360863e-05,
+      "loss": 0.0358,
+      "step": 410
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.17154745757579803,
+      "learning_rate": 8.666466885900438e-05,
+      "loss": 0.0736,
+      "step": 411
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.1607416719198227,
+      "learning_rate": 8.660122215212977e-05,
+      "loss": 0.0678,
+      "step": 412
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.1216413602232933,
+      "learning_rate": 8.653764821353573e-05,
+      "loss": 0.0341,
+      "step": 413
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.3713608980178833,
+      "learning_rate": 8.647394726421547e-05,
+      "loss": 0.118,
+      "step": 414
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.48576387763023376,
+      "learning_rate": 8.641011952560371e-05,
+      "loss": 0.0931,
+      "step": 415
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.14704179763793945,
+      "learning_rate": 8.63461652195759e-05,
+      "loss": 0.0285,
+      "step": 416
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.3306657671928406,
+      "learning_rate": 8.628208456844747e-05,
+      "loss": 0.0737,
+      "step": 417
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.39767885208129883,
+      "learning_rate": 8.621787779497305e-05,
+      "loss": 0.097,
+      "step": 418
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.3198534846305847,
+      "learning_rate": 8.615354512234569e-05,
+      "loss": 0.0731,
+      "step": 419
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.19191338121891022,
+      "learning_rate": 8.608908677419606e-05,
+      "loss": 0.0697,
+      "step": 420
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.26490989327430725,
+      "learning_rate": 8.602450297459172e-05,
+      "loss": 0.1214,
+      "step": 421
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.3545917868614197,
+      "learning_rate": 8.595979394803634e-05,
+      "loss": 0.0933,
+      "step": 422
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.28239014744758606,
+      "learning_rate": 8.589495991946885e-05,
+      "loss": 0.0707,
+      "step": 423
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.48272502422332764,
+      "learning_rate": 8.583000111426276e-05,
+      "loss": 0.0831,
+      "step": 424
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.15938633680343628,
+      "learning_rate": 8.576491775822527e-05,
+      "loss": 0.0899,
+      "step": 425
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.2616162896156311,
+      "learning_rate": 8.569971007759657e-05,
+      "loss": 0.118,
+      "step": 426
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.0783080980181694,
+      "eval_runtime": 14.6414,
+      "eval_samples_per_second": 32.579,
+      "eval_steps_per_second": 8.196,
+      "step": 426
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.19521737098693848,
+      "learning_rate": 8.563437829904903e-05,
+      "loss": 0.0814,
+      "step": 427
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.194011390209198,
+      "learning_rate": 8.55689226496864e-05,
+      "loss": 0.0799,
+      "step": 428
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.2743787169456482,
+      "learning_rate": 8.550334335704298e-05,
+      "loss": 0.0869,
+      "step": 429
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.1369010955095291,
+      "learning_rate": 8.543764064908295e-05,
+      "loss": 0.0435,
+      "step": 430
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.24237819015979767,
+      "learning_rate": 8.537181475419944e-05,
+      "loss": 0.1148,
+      "step": 431
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.14511409401893616,
+      "learning_rate": 8.530586590121383e-05,
+      "loss": 0.0764,
+      "step": 432
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.15356196463108063,
+      "learning_rate": 8.523979431937492e-05,
+      "loss": 0.05,
+      "step": 433
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.21860916912555695,
+      "learning_rate": 8.51736002383581e-05,
+      "loss": 0.0971,
+      "step": 434
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.23724305629730225,
+      "learning_rate": 8.510728388826463e-05,
+      "loss": 0.1049,
+      "step": 435
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.25301918387413025,
+      "learning_rate": 8.50408454996208e-05,
+      "loss": 0.0848,
+      "step": 436
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.22409550845623016,
+      "learning_rate": 8.497428530337706e-05,
+      "loss": 0.101,
+      "step": 437
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.1324710100889206,
+      "learning_rate": 8.490760353090737e-05,
+      "loss": 0.0723,
+      "step": 438
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1362515389919281,
+      "learning_rate": 8.484080041400826e-05,
+      "loss": 0.0709,
+      "step": 439
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.16375669836997986,
+      "learning_rate": 8.477387618489807e-05,
+      "loss": 0.0405,
+      "step": 440
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.21752700209617615,
+      "learning_rate": 8.470683107621616e-05,
+      "loss": 0.0455,
+      "step": 441
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1989530771970749,
+      "learning_rate": 8.463966532102207e-05,
+      "loss": 0.0704,
+      "step": 442
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.192123144865036,
+      "learning_rate": 8.457237915279476e-05,
+      "loss": 0.063,
+      "step": 443
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.1221012994647026,
+      "learning_rate": 8.450497280543174e-05,
+      "loss": 0.0302,
+      "step": 444
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.5705539584159851,
+      "learning_rate": 8.443744651324827e-05,
+      "loss": 0.1531,
+      "step": 445
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.21490426361560822,
+      "learning_rate": 8.436980051097659e-05,
+      "loss": 0.0626,
+      "step": 446
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.2654309570789337,
+      "learning_rate": 8.430203503376505e-05,
+      "loss": 0.0838,
+      "step": 447
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.22457195818424225,
+      "learning_rate": 8.423415031717733e-05,
+      "loss": 0.0309,
+      "step": 448
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.10934180021286011,
+      "learning_rate": 8.416614659719157e-05,
+      "loss": 0.0132,
+      "step": 449
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.32622861862182617,
+      "learning_rate": 8.409802411019963e-05,
+      "loss": 0.107,
+      "step": 450
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.24298590421676636,
+      "learning_rate": 8.40297830930062e-05,
+      "loss": 0.1268,
+      "step": 451
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.29994437098503113,
+      "learning_rate": 8.396142378282798e-05,
+      "loss": 0.0747,
+      "step": 452
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.16668649017810822,
+      "learning_rate": 8.389294641729293e-05,
+      "loss": 0.0479,
+      "step": 453
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.26706060767173767,
+      "learning_rate": 8.382435123443934e-05,
+      "loss": 0.1116,
+      "step": 454
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.1750030219554901,
+      "learning_rate": 8.375563847271506e-05,
+      "loss": 0.0597,
+      "step": 455
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.2318125069141388,
+      "learning_rate": 8.36868083709767e-05,
+      "loss": 0.0909,
+      "step": 456
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.1834569126367569,
+      "learning_rate": 8.361786116848872e-05,
+      "loss": 0.0813,
+      "step": 457
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.27685895562171936,
+      "learning_rate": 8.354879710492264e-05,
+      "loss": 0.1301,
+      "step": 458
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.16120545566082,
+      "learning_rate": 8.347961642035624e-05,
+      "loss": 0.0717,
+      "step": 459
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.17625439167022705,
+      "learning_rate": 8.341031935527267e-05,
+      "loss": 0.0867,
+      "step": 460
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.2321135252714157,
+      "learning_rate": 8.334090615055966e-05,
+      "loss": 0.1122,
+      "step": 461
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.12720270454883575,
+      "learning_rate": 8.327137704750862e-05,
+      "loss": 0.0375,
+      "step": 462
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.2046743929386139,
+      "learning_rate": 8.320173228781389e-05,
+      "loss": 0.0808,
+      "step": 463
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.16513489186763763,
+      "learning_rate": 8.313197211357181e-05,
+      "loss": 0.0825,
+      "step": 464
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.12492749094963074,
+      "learning_rate": 8.306209676727994e-05,
+      "loss": 0.0876,
+      "step": 465
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.1343008577823639,
+      "learning_rate": 8.299210649183619e-05,
+      "loss": 0.0852,
+      "step": 466
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.13951613008975983,
+      "learning_rate": 8.2922001530538e-05,
+      "loss": 0.1003,
+      "step": 467
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.16553768515586853,
+      "learning_rate": 8.285178212708143e-05,
+      "loss": 0.0662,
+      "step": 468
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.15311822295188904,
+      "learning_rate": 8.278144852556042e-05,
+      "loss": 0.0785,
+      "step": 469
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.1948017179965973,
+      "learning_rate": 8.271100097046584e-05,
+      "loss": 0.0898,
+      "step": 470
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.11078551411628723,
+      "learning_rate": 8.264043970668469e-05,
+      "loss": 0.0386,
+      "step": 471
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.1605585515499115,
+      "learning_rate": 8.256976497949924e-05,
+      "loss": 0.0497,
+      "step": 472
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.1617887318134308,
+      "learning_rate": 8.249897703458619e-05,
+      "loss": 0.0624,
+      "step": 473
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.1274091750383377,
+      "learning_rate": 8.242807611801578e-05,
+      "loss": 0.0578,
+      "step": 474
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.15953154861927032,
+      "learning_rate": 8.235706247625098e-05,
+      "loss": 0.042,
+      "step": 475
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.27984094619750977,
+      "learning_rate": 8.228593635614659e-05,
+      "loss": 0.1037,
+      "step": 476
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.1895013153553009,
+      "learning_rate": 8.22146980049484e-05,
+      "loss": 0.0728,
+      "step": 477
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.1580246388912201,
+      "learning_rate": 8.214334767029239e-05,
+      "loss": 0.0398,
+      "step": 478
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.2391231805086136,
+      "learning_rate": 8.207188560020373e-05,
+      "loss": 0.0707,
+      "step": 479
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.25975751876831055,
+      "learning_rate": 8.200031204309603e-05,
+      "loss": 0.1369,
+      "step": 480
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.32591861486434937,
+      "learning_rate": 8.192862724777051e-05,
+      "loss": 0.0878,
+      "step": 481
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.32488566637039185,
+      "learning_rate": 8.185683146341496e-05,
+      "loss": 0.0692,
+      "step": 482
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.1918002963066101,
+      "learning_rate": 8.178492493960309e-05,
+      "loss": 0.0942,
+      "step": 483
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.43140751123428345,
+      "learning_rate": 8.171290792629347e-05,
+      "loss": 0.0979,
+      "step": 484
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.1771157830953598,
+      "learning_rate": 8.164078067382882e-05,
+      "loss": 0.0894,
+      "step": 485
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.25012728571891785,
+      "learning_rate": 8.1568543432935e-05,
+      "loss": 0.0734,
+      "step": 486
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.19328337907791138,
+      "learning_rate": 8.149619645472031e-05,
+      "loss": 0.0869,
+      "step": 487
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.18180640041828156,
+      "learning_rate": 8.142373999067439e-05,
+      "loss": 0.0897,
+      "step": 488
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.25753355026245117,
+      "learning_rate": 8.135117429266757e-05,
+      "loss": 0.0883,
+      "step": 489
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.23837833106517792,
+      "learning_rate": 8.127849961294984e-05,
+      "loss": 0.0549,
+      "step": 490
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.25032365322113037,
+      "learning_rate": 8.120571620415006e-05,
+      "loss": 0.0976,
+      "step": 491
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.30728307366371155,
+      "learning_rate": 8.113282431927502e-05,
+      "loss": 0.0709,
+      "step": 492
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.1391928791999817,
+      "learning_rate": 8.10598242117086e-05,
+      "loss": 0.0378,
+      "step": 493
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.1786775141954422,
+      "learning_rate": 8.098671613521089e-05,
+      "loss": 0.0671,
+      "step": 494
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.21963584423065186,
+      "learning_rate": 8.091350034391732e-05,
+      "loss": 0.0936,
+      "step": 495
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.13954299688339233,
+      "learning_rate": 8.084017709233767e-05,
+      "loss": 0.052,
+      "step": 496
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.19656923413276672,
+      "learning_rate": 8.076674663535537e-05,
+      "loss": 0.0584,
+      "step": 497
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.14330637454986572,
+      "learning_rate": 8.069320922822643e-05,
+      "loss": 0.0786,
+      "step": 498
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.19019991159439087,
+      "learning_rate": 8.061956512657871e-05,
+      "loss": 0.0837,
+      "step": 499
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.2079285979270935,
+      "learning_rate": 8.05458145864109e-05,
+      "loss": 0.0459,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.3516862392425537,
+      "learning_rate": 8.047195786409172e-05,
+      "loss": 0.191,
+      "step": 501
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.192392036318779,
+      "learning_rate": 8.039799521635896e-05,
+      "loss": 0.1072,
+      "step": 502
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.1787678301334381,
+      "learning_rate": 8.032392690031867e-05,
+      "loss": 0.0649,
+      "step": 503
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.21046535670757294,
+      "learning_rate": 8.024975317344421e-05,
+      "loss": 0.1065,
+      "step": 504
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.1215684562921524,
+      "learning_rate": 8.017547429357532e-05,
+      "loss": 0.0433,
+      "step": 505
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.1342051476240158,
+      "learning_rate": 8.010109051891731e-05,
+      "loss": 0.0774,
+      "step": 506
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.10215850174427032,
+      "learning_rate": 8.002660210804011e-05,
+      "loss": 0.0338,
+      "step": 507
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.23539598286151886,
+      "learning_rate": 7.995200931987743e-05,
+      "loss": 0.0516,
+      "step": 508
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.15601155161857605,
+      "learning_rate": 7.987731241372572e-05,
+      "loss": 0.0559,
+      "step": 509
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.165851429104805,
+      "learning_rate": 7.98025116492434e-05,
+      "loss": 0.0372,
+      "step": 510
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.21045421063899994,
+      "learning_rate": 7.972760728644996e-05,
+      "loss": 0.086,
+      "step": 511
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.14814500510692596,
+      "learning_rate": 7.965259958572496e-05,
+      "loss": 0.0587,
+      "step": 512
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.15543898940086365,
+      "learning_rate": 7.95774888078072e-05,
+      "loss": 0.0682,
+      "step": 513
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.13527697324752808,
+      "learning_rate": 7.950227521379382e-05,
+      "loss": 0.0468,
+      "step": 514
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.35773295164108276,
+      "learning_rate": 7.94269590651393e-05,
+      "loss": 0.1273,
+      "step": 515
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.22433511912822723,
+      "learning_rate": 7.935154062365467e-05,
+      "loss": 0.0438,
+      "step": 516
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.1453983038663864,
+      "learning_rate": 7.927602015150655e-05,
+      "loss": 0.0367,
+      "step": 517
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.2343645691871643,
+      "learning_rate": 7.920039791121617e-05,
+      "loss": 0.128,
+      "step": 518
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.25178173184394836,
+      "learning_rate": 7.912467416565861e-05,
+      "loss": 0.1094,
+      "step": 519
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.3170076012611389,
+      "learning_rate": 7.904884917806174e-05,
+      "loss": 0.1323,
+      "step": 520
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.15917453169822693,
+      "learning_rate": 7.897292321200538e-05,
+      "loss": 0.036,
+      "step": 521
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.31578320264816284,
+      "learning_rate": 7.889689653142036e-05,
+      "loss": 0.0909,
+      "step": 522
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.16602741181850433,
+      "learning_rate": 7.882076940058764e-05,
+      "loss": 0.0371,
+      "step": 523
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.3235325813293457,
+      "learning_rate": 7.874454208413731e-05,
+      "loss": 0.1561,
+      "step": 524
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.1256486028432846,
+      "learning_rate": 7.866821484704776e-05,
+      "loss": 0.0364,
+      "step": 525
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.2234162986278534,
+      "learning_rate": 7.859178795464472e-05,
+      "loss": 0.0883,
+      "step": 526
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.1564294993877411,
+      "learning_rate": 7.851526167260034e-05,
+      "loss": 0.0679,
+      "step": 527
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.16309525072574615,
+      "learning_rate": 7.84386362669322e-05,
+      "loss": 0.0912,
+      "step": 528
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.21584004163742065,
+      "learning_rate": 7.836191200400255e-05,
+      "loss": 0.0695,
+      "step": 529
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.15948422253131866,
+      "learning_rate": 7.828508915051724e-05,
+      "loss": 0.0459,
+      "step": 530
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.24016940593719482,
+      "learning_rate": 7.82081679735248e-05,
+      "loss": 0.1127,
+      "step": 531
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.2894397974014282,
+      "learning_rate": 7.813114874041557e-05,
+      "loss": 0.0584,
+      "step": 532
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.20707662403583527,
+      "learning_rate": 7.805403171892079e-05,
+      "loss": 0.1045,
+      "step": 533
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.23427248001098633,
+      "learning_rate": 7.797681717711161e-05,
+      "loss": 0.1345,
+      "step": 534
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.13141866028308868,
+      "learning_rate": 7.789950538339812e-05,
+      "loss": 0.052,
+      "step": 535
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.21118536591529846,
+      "learning_rate": 7.782209660652855e-05,
+      "loss": 0.1272,
+      "step": 536
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.15485352277755737,
+      "learning_rate": 7.77445911155882e-05,
+      "loss": 0.0686,
+      "step": 537
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.11380946636199951,
+      "learning_rate": 7.766698917999861e-05,
+      "loss": 0.0735,
+      "step": 538
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.26798170804977417,
+      "learning_rate": 7.758929106951656e-05,
+      "loss": 0.0934,
+      "step": 539
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.23003587126731873,
+      "learning_rate": 7.751149705423312e-05,
+      "loss": 0.0816,
+      "step": 540
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.2122953236103058,
+      "learning_rate": 7.743360740457278e-05,
+      "loss": 0.0827,
+      "step": 541
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.22673499584197998,
+      "learning_rate": 7.735562239129247e-05,
+      "loss": 0.1232,
+      "step": 542
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.24960415065288544,
+      "learning_rate": 7.727754228548058e-05,
+      "loss": 0.1124,
+      "step": 543
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.10405872017145157,
+      "learning_rate": 7.719936735855611e-05,
+      "loss": 0.0687,
+      "step": 544
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.16980154812335968,
+      "learning_rate": 7.712109788226762e-05,
+      "loss": 0.0874,
+      "step": 545
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.1486412137746811,
+      "learning_rate": 7.704273412869238e-05,
+      "loss": 0.0815,
+      "step": 546
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.14432762563228607,
+      "learning_rate": 7.696427637023538e-05,
+      "loss": 0.0752,
+      "step": 547
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.2627028822898865,
+      "learning_rate": 7.688572487962835e-05,
+      "loss": 0.0982,
+      "step": 548
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.16832011938095093,
+      "learning_rate": 7.680707992992888e-05,
+      "loss": 0.0895,
+      "step": 549
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.14999301731586456,
+      "learning_rate": 7.672834179451942e-05,
+      "loss": 0.0544,
+      "step": 550
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.14237482845783234,
+      "learning_rate": 7.664951074710638e-05,
+      "loss": 0.0623,
+      "step": 551
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1694159060716629,
+      "learning_rate": 7.657058706171911e-05,
+      "loss": 0.0784,
+      "step": 552
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.1470886617898941,
+      "learning_rate": 7.649157101270902e-05,
+      "loss": 0.0635,
+      "step": 553
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.16492018103599548,
+      "learning_rate": 7.641246287474855e-05,
+      "loss": 0.0669,
+      "step": 554
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.195392444729805,
+      "learning_rate": 7.633326292283028e-05,
+      "loss": 0.0387,
+      "step": 555
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.17653177678585052,
+      "learning_rate": 7.625397143226596e-05,
+      "loss": 0.0592,
+      "step": 556
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.23455718159675598,
+      "learning_rate": 7.617458867868553e-05,
+      "loss": 0.0882,
+      "step": 557
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.3588998317718506,
+      "learning_rate": 7.609511493803616e-05,
+      "loss": 0.107,
+      "step": 558
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.2767946720123291,
+      "learning_rate": 7.601555048658134e-05,
+      "loss": 0.1609,
+      "step": 559
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.22181196510791779,
+      "learning_rate": 7.593589560089985e-05,
+      "loss": 0.0598,
+      "step": 560
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.30335313081741333,
+      "learning_rate": 7.585615055788484e-05,
+      "loss": 0.0825,
+      "step": 561
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.19477833807468414,
+      "learning_rate": 7.577631563474291e-05,
+      "loss": 0.0446,
+      "step": 562
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.11036123335361481,
+      "learning_rate": 7.569639110899303e-05,
+      "loss": 0.025,
+      "step": 563
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.19955220818519592,
+      "learning_rate": 7.561637725846568e-05,
+      "loss": 0.0484,
+      "step": 564
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.20293684303760529,
+      "learning_rate": 7.553627436130183e-05,
+      "loss": 0.0689,
+      "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 sha256:4dbf4a4958574f4f247050e1bfe19a04f1b69ecafa7464449959a7e1da1e5cf5
+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
+}