Upload folder using huggingface_hub

README.md

@@ -0,0 +1,169 @@
+---
+base_model: Qwen/Qwen2-7B
+#base_model: /workspace/data/models/Qwen2-7B
+library_name: peft
+tags:
+- generated_from_trainer
+model-index:
+- name: workspace/data/outputs/Qwen2-7B-TestFinetune-LORA
+  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: `0.4.1`
+```yaml
+base_model: /workspace/data/models/Qwen2-7B
+model_type: Qwen2ForCausalLM
+tokenizer_type: Qwen2Tokenizer
+
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: NobodyExistsOnTheInternet/ToxicQAFinal
+    type: sharegpt
+#  - path: /workspace/data/SystemChat_filtered_sharegpt.jsonl
+#    type: sharegpt
+#    conversation: chatml
+#  - path: /workspace/data/Opus_Instruct-v2-6.5K-Filtered-v2.json
+#    type:
+#      field_system: system
+#      field_instruction: prompt
+#      field_output: response
+#      format: "[INST] {instruction} [/INST]"
+#      no_input_format: "[INST] {instruction} [/INST]"
+#  - path: Undi95/orthogonal-activation-steering-TOXIC
+#    type:
+#      field_instruction: goal
+#      field_output: target
+#      format: "[INST] {instruction} [/INST]"
+#      no_input_format: "[INST] {instruction} [/INST]"
+#    split: test
+#  - path: cognitivecomputations/WizardLM_alpaca_evol_instruct_70k_unfiltered
+#    type: alpaca
+#    split: train
+
+dataset_prepared_path: /workspace/data/last_run_prepared
+val_set_size: 0.15
+output_dir: /workspace/data/outputs/Qwen2-7B-TestFinetune-LORA
+
+chat_template: chatml
+
+sequence_len: 8192
+sample_packing: true
+pad_to_sequence_len: true
+
+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: 8
+micro_batch_size: 1
+num_epochs: 4
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 3e-5
+
+train_on_inputs: false
+group_by_length: true
+bf16: true
+fp16: false
+tf32: false
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 2
+eval_table_size:
+saves_per_epoch: 2
+debug:
+deepspeed:
+weight_decay: 0.05
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: "<|endoftext|>"
+  eos_token: "<|im_end|>"
+```
+
+</details><br>
+
+# workspace/data/outputs/Qwen2-7B-TestFinetune-LORA
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0055
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1751        | 0.0169 | 1    | 1.1860          |
+| 1.1007        | 0.5063 | 30   | 1.0912          |
+| 1.0418        | 1.0127 | 60   | 1.0428          |
+| 1.0105        | 1.5042 | 90   | 1.0232          |
+| 1.0082        | 2.0105 | 120  | 1.0127          |
+| 0.9946        | 2.5042 | 150  | 1.0074          |
+| 0.9826        | 3.0105 | 180  | 1.0057          |
+| 0.9898        | 3.5021 | 210  | 1.0055          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.42.3
+- Pytorch 2.1.2+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/data/models/Qwen2-7B",
+  "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": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "o_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:a8d74db78cede6a8d0f55f6e138c4d042f5e04e56667fad86df0f8b21da9e901
+size 161622314

added_tokens.json

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

checkpoint-150/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /workspace/data/models/Qwen2-7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-150/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/data/models/Qwen2-7B",
+  "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": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85c16b2611b53132f65205d8cc2cfea6dd4535a080257570c53d1bca38a406b
+size 161533584

checkpoint-150/added_tokens.json

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

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af7fd609322fa7c6d8c35bdebd39fe0c9275a5845980d682fb787cde90bee591
+size 323292010

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a99d4192b32fbb6795950b98e8cadf12766e63518543fb1e2091e7f45f3c5e77
+size 14244

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3019b93b7cc8175e4ec5a34d768cfc964cc70a5a29c48f62e0f050568322c02f
+size 1064

checkpoint-150/special_tokens_map.json

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

checkpoint-150/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "use_fast": true
+}

checkpoint-150/trainer_state.json

@@ -0,0 +1,1131 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5042194092827,
+  "eval_steps": 30,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016877637130801686,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 3e-06,
+      "loss": 1.1751,
+      "step": 1
+    },
+    {
+      "epoch": 0.016877637130801686,
+      "eval_loss": 1.185997486114502,
+      "eval_runtime": 72.8223,
+      "eval_samples_per_second": 14.144,
+      "eval_steps_per_second": 14.144,
+      "step": 1
+    },
+    {
+      "epoch": 0.03375527426160337,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 6e-06,
+      "loss": 1.1683,
+      "step": 2
+    },
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 9e-06,
+      "loss": 1.1737,
+      "step": 3
+    },
+    {
+      "epoch": 0.06751054852320675,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 1.2e-05,
+      "loss": 1.1889,
+      "step": 4
+    },
+    {
+      "epoch": 0.08438818565400844,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 1.5e-05,
+      "loss": 1.1619,
+      "step": 5
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 1.8e-05,
+      "loss": 1.1815,
+      "step": 6
+    },
+    {
+      "epoch": 0.11814345991561181,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 2.1e-05,
+      "loss": 1.1726,
+      "step": 7
+    },
+    {
+      "epoch": 0.1350210970464135,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 2.4e-05,
+      "loss": 1.1701,
+      "step": 8
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.1818,
+      "step": 9
+    },
+    {
+      "epoch": 0.16877637130801687,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 3e-05,
+      "loss": 1.1896,
+      "step": 10
+    },
+    {
+      "epoch": 0.18565400843881857,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 2.999855077059572e-05,
+      "loss": 1.1873,
+      "step": 11
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 0.08984375,
+      "learning_rate": 2.9994203362418313e-05,
+      "loss": 1.1838,
+      "step": 12
+    },
+    {
+      "epoch": 0.21940928270042195,
+      "grad_norm": 0.0859375,
+      "learning_rate": 2.998695861552002e-05,
+      "loss": 1.1569,
+      "step": 13
+    },
+    {
+      "epoch": 0.23628691983122363,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 2.9976817929807542e-05,
+      "loss": 1.1595,
+      "step": 14
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 0.078125,
+      "learning_rate": 2.996378326477153e-05,
+      "loss": 1.1348,
+      "step": 15
+    },
+    {
+      "epoch": 0.270042194092827,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 2.9947857139107964e-05,
+      "loss": 1.1434,
+      "step": 16
+    },
+    {
+      "epoch": 0.2869198312236287,
+      "grad_norm": 0.140625,
+      "learning_rate": 2.992904263023146e-05,
+      "loss": 1.8213,
+      "step": 17
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 2.990734337368062e-05,
+      "loss": 1.1289,
+      "step": 18
+    },
+    {
+      "epoch": 0.3206751054852321,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 2.9882763562415518e-05,
+      "loss": 1.1106,
+      "step": 19
+    },
+    {
+      "epoch": 0.33755274261603374,
+      "grad_norm": 0.06640625,
+      "learning_rate": 2.9855307946007532e-05,
+      "loss": 1.1381,
+      "step": 20
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 0.064453125,
+      "learning_rate": 2.982498182972154e-05,
+      "loss": 1.1192,
+      "step": 21
+    },
+    {
+      "epoch": 0.37130801687763715,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 2.9791791073490795e-05,
+      "loss": 1.1105,
+      "step": 22
+    },
+    {
+      "epoch": 0.3881856540084388,
+      "grad_norm": 0.061767578125,
+      "learning_rate": 2.9755742090784617e-05,
+      "loss": 1.1207,
+      "step": 23
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 2.9716841847369106e-05,
+      "loss": 1.1083,
+      "step": 24
+    },
+    {
+      "epoch": 0.4219409282700422,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 2.967509785996114e-05,
+      "loss": 1.1007,
+      "step": 25
+    },
+    {
+      "epoch": 0.4388185654008439,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 2.963051819477592e-05,
+      "loss": 1.0842,
+      "step": 26
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 0.0625,
+      "learning_rate": 2.958311146596833e-05,
+      "loss": 1.0961,
+      "step": 27
+    },
+    {
+      "epoch": 0.47257383966244726,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 2.953288683396841e-05,
+      "loss": 1.109,
+      "step": 28
+    },
+    {
+      "epoch": 0.48945147679324896,
+      "grad_norm": 0.061767578125,
+      "learning_rate": 2.9479854003711298e-05,
+      "loss": 1.0789,
+      "step": 29
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 2.9424023222761938e-05,
+      "loss": 1.1007,
+      "step": 30
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "eval_loss": 1.091182827949524,
+      "eval_runtime": 74.0135,
+      "eval_samples_per_second": 13.916,
+      "eval_steps_per_second": 13.916,
+      "step": 30
+    },
+    {
+      "epoch": 0.5232067510548524,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 2.9365405279334904e-05,
+      "loss": 1.0756,
+      "step": 31
+    },
+    {
+      "epoch": 0.540084388185654,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 2.930401150020983e-05,
+      "loss": 1.0939,
+      "step": 32
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 0.05712890625,
+      "learning_rate": 2.9239853748542717e-05,
+      "loss": 1.0901,
+      "step": 33
+    },
+    {
+      "epoch": 0.5738396624472574,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.9172944421573587e-05,
+      "loss": 1.0873,
+      "step": 34
+    },
+    {
+      "epoch": 0.5907172995780591,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.9103296448230986e-05,
+      "loss": 1.0584,
+      "step": 35
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 2.9030923286633703e-05,
+      "loss": 1.0692,
+      "step": 36
+    },
+    {
+      "epoch": 0.6244725738396625,
+      "grad_norm": 0.16015625,
+      "learning_rate": 2.8955838921490252e-05,
+      "loss": 1.782,
+      "step": 37
+    },
+    {
+      "epoch": 0.6413502109704642,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.8878057861396606e-05,
+      "loss": 1.0667,
+      "step": 38
+    },
+    {
+      "epoch": 0.6582278481012658,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.8797595136032675e-05,
+      "loss": 1.0656,
+      "step": 39
+    },
+    {
+      "epoch": 0.6751054852320675,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.8714466293258142e-05,
+      "loss": 1.0736,
+      "step": 40
+    },
+    {
+      "epoch": 0.6919831223628692,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 2.8628687396108107e-05,
+      "loss": 1.0638,
+      "step": 41
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.8540275019689237e-05,
+      "loss": 1.0746,
+      "step": 42
+    },
+    {
+      "epoch": 0.7257383966244726,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 2.8449246247976947e-05,
+      "loss": 1.0608,
+      "step": 43
+    },
+    {
+      "epoch": 0.7426160337552743,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.835561867051426e-05,
+      "loss": 1.0619,
+      "step": 44
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.051025390625,
+      "learning_rate": 2.825941037901294e-05,
+      "loss": 1.048,
+      "step": 45
+    },
+    {
+      "epoch": 0.7763713080168776,
+      "grad_norm": 0.05078125,
+      "learning_rate": 2.816063996385765e-05,
+      "loss": 1.0761,
+      "step": 46
+    },
+    {
+      "epoch": 0.7932489451476793,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 2.805932651051372e-05,
+      "loss": 1.0443,
+      "step": 47
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 0.051025390625,
+      "learning_rate": 2.7955489595839228e-05,
+      "loss": 1.0527,
+      "step": 48
+    },
+    {
+      "epoch": 0.8270042194092827,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.784914928430218e-05,
+      "loss": 1.0498,
+      "step": 49
+    },
+    {
+      "epoch": 0.8438818565400844,
+      "grad_norm": 0.049560546875,
+      "learning_rate": 2.7740326124103416e-05,
+      "loss": 1.0537,
+      "step": 50
+    },
+    {
+      "epoch": 0.8607594936708861,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 2.762904114320609e-05,
+      "loss": 1.0326,
+      "step": 51
+    },
+    {
+      "epoch": 0.8776371308016878,
+      "grad_norm": 0.04931640625,
+      "learning_rate": 2.751531584527241e-05,
+      "loss": 1.043,
+      "step": 52
+    },
+    {
+      "epoch": 0.8945147679324894,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.7399172205508476e-05,
+      "loss": 1.0463,
+      "step": 53
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.0517578125,
+      "learning_rate": 2.7280632666418013e-05,
+      "loss": 1.0476,
+      "step": 54
+    },
+    {
+      "epoch": 0.9282700421940928,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 2.715972013346576e-05,
+      "loss": 1.0467,
+      "step": 55
+    },
+    {
+      "epoch": 0.9451476793248945,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 2.703645797065147e-05,
+      "loss": 1.0467,
+      "step": 56
+    },
+    {
+      "epoch": 0.9620253164556962,
+      "grad_norm": 0.05078125,
+      "learning_rate": 2.6910869995995247e-05,
+      "loss": 1.05,
+      "step": 57
+    },
+    {
+      "epoch": 0.9789029535864979,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 2.678298047693518e-05,
+      "loss": 1.0453,
+      "step": 58
+    },
+    {
+      "epoch": 0.9957805907172996,
+      "grad_norm": 0.050048828125,
+      "learning_rate": 2.6652814125638142e-05,
+      "loss": 1.0348,
+      "step": 59
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "grad_norm": 0.052490234375,
+      "learning_rate": 2.652039609422463e-05,
+      "loss": 1.0418,
+      "step": 60
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "eval_loss": 1.0428293943405151,
+      "eval_runtime": 74.0734,
+      "eval_samples_per_second": 13.905,
+      "eval_steps_per_second": 13.905,
+      "step": 60
+    },
+    {
+      "epoch": 1.0147679324894514,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 2.638575196990862e-05,
+      "loss": 1.0194,
+      "step": 61
+    },
+    {
+      "epoch": 1.0316455696202531,
+      "grad_norm": 0.049560546875,
+      "learning_rate": 2.624890777005332e-05,
+      "loss": 1.0365,
+      "step": 62
+    },
+    {
+      "epoch": 1.0485232067510548,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.6109889937143828e-05,
+      "loss": 1.0426,
+      "step": 63
+    },
+    {
+      "epoch": 1.0654008438818565,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.5968725333677628e-05,
+      "loss": 1.043,
+      "step": 64
+    },
+    {
+      "epoch": 1.0822784810126582,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 2.582544123697395e-05,
+      "loss": 1.0243,
+      "step": 65
+    },
+    {
+      "epoch": 1.09915611814346,
+      "grad_norm": 0.0517578125,
+      "learning_rate": 2.568006533390295e-05,
+      "loss": 1.0258,
+      "step": 66
+    },
+    {
+      "epoch": 1.1160337552742616,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 2.5532625715535733e-05,
+      "loss": 1.0248,
+      "step": 67
+    },
+    {
+      "epoch": 1.1329113924050633,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 2.5383150871716342e-05,
+      "loss": 1.0083,
+      "step": 68
+    },
+    {
+      "epoch": 1.149789029535865,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.5231669685556636e-05,
+      "loss": 1.0207,
+      "step": 69
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 2.507821142785516e-05,
+      "loss": 1.0435,
+      "step": 70
+    },
+    {
+      "epoch": 1.1835443037974684,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.4922805751441174e-05,
+      "loss": 1.0354,
+      "step": 71
+    },
+    {
+      "epoch": 1.20042194092827,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 2.4765482685444786e-05,
+      "loss": 1.0266,
+      "step": 72
+    },
+    {
+      "epoch": 1.2172995780590719,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.460627262949443e-05,
+      "loss": 1.0411,
+      "step": 73
+    },
+    {
+      "epoch": 1.2341772151898733,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.4445206347842714e-05,
+      "loss": 1.0224,
+      "step": 74
+    },
+    {
+      "epoch": 1.251054852320675,
+      "grad_norm": 0.052978515625,
+      "learning_rate": 2.428231496342181e-05,
+      "loss": 1.0253,
+      "step": 75
+    },
+    {
+      "epoch": 1.2679324894514767,
+      "grad_norm": 0.05322265625,
+      "learning_rate": 2.4117629951829602e-05,
+      "loss": 1.0298,
+      "step": 76
+    },
+    {
+      "epoch": 1.2848101265822784,
+      "grad_norm": 0.052490234375,
+      "learning_rate": 2.395118313524758e-05,
+      "loss": 1.0239,
+      "step": 77
+    },
+    {
+      "epoch": 1.3016877637130801,
+      "grad_norm": 0.0537109375,
+      "learning_rate": 2.3783006676291866e-05,
+      "loss": 1.0212,
+      "step": 78
+    },
+    {
+      "epoch": 1.3185654008438819,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.361313307179837e-05,
+      "loss": 1.0371,
+      "step": 79
+    },
+    {
+      "epoch": 1.3354430379746836,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.3441595146543458e-05,
+      "loss": 1.0314,
+      "step": 80
+    },
+    {
+      "epoch": 1.3523206751054853,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.3268426046901153e-05,
+      "loss": 1.0195,
+      "step": 81
+    },
+    {
+      "epoch": 1.369198312236287,
+      "grad_norm": 0.052978515625,
+      "learning_rate": 2.3093659234438266e-05,
+      "loss": 1.0219,
+      "step": 82
+    },
+    {
+      "epoch": 1.3860759493670887,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.291732847944861e-05,
+      "loss": 1.0293,
+      "step": 83
+    },
+    {
+      "epoch": 1.4029535864978904,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.2739467854427512e-05,
+      "loss": 0.9992,
+      "step": 84
+    },
+    {
+      "epoch": 1.4198312236286919,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.2560111727488e-05,
+      "loss": 1.0254,
+      "step": 85
+    },
+    {
+      "epoch": 1.4367088607594938,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.237929475571979e-05,
+      "loss": 1.0148,
+      "step": 86
+    },
+    {
+      "epoch": 1.4535864978902953,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 2.219705187849254e-05,
+      "loss": 1.0228,
+      "step": 87
+    },
+    {
+      "epoch": 1.4704641350210972,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 2.2013418310704422e-05,
+      "loss": 1.021,
+      "step": 88
+    },
+    {
+      "epoch": 1.4873417721518987,
+      "grad_norm": 0.0537109375,
+      "learning_rate": 2.1828429535977585e-05,
+      "loss": 1.0352,
+      "step": 89
+    },
+    {
+      "epoch": 1.5042194092827004,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.1642121299801594e-05,
+      "loss": 1.0105,
+      "step": 90
+    },
+    {
+      "epoch": 1.5042194092827004,
+      "eval_loss": 1.0232045650482178,
+      "eval_runtime": 74.0589,
+      "eval_samples_per_second": 13.908,
+      "eval_steps_per_second": 13.908,
+      "step": 90
+    },
+    {
+      "epoch": 1.521097046413502,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.1454529602626336e-05,
+      "loss": 1.0051,
+      "step": 91
+    },
+    {
+      "epoch": 1.5379746835443038,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.126569069290562e-05,
+      "loss": 1.023,
+      "step": 92
+    },
+    {
+      "epoch": 1.5548523206751055,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.107564106009286e-05,
+      "loss": 1.012,
+      "step": 93
+    },
+    {
+      "epoch": 1.5717299578059072,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.0884417427590217e-05,
+      "loss": 1.0136,
+      "step": 94
+    },
+    {
+      "epoch": 1.5886075949367089,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.0692056745652483e-05,
+      "loss": 1.0194,
+      "step": 95
+    },
+    {
+      "epoch": 1.6054852320675106,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 2.0498596184247196e-05,
+      "loss": 1.0089,
+      "step": 96
+    },
+    {
+      "epoch": 1.6223628691983123,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.030407312587224e-05,
+      "loss": 1.0226,
+      "step": 97
+    },
+    {
+      "epoch": 1.6392405063291138,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 2.010852515833242e-05,
+      "loss": 1.0219,
+      "step": 98
+    },
+    {
+      "epoch": 1.6561181434599157,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 1.9911990067476336e-05,
+      "loss": 1.0035,
+      "step": 99
+    },
+    {
+      "epoch": 1.6729957805907172,
+      "grad_norm": 0.055908203125,
+      "learning_rate": 1.9714505829895004e-05,
+      "loss": 1.0052,
+      "step": 100
+    },
+    {
+      "epoch": 1.689873417721519,
+      "grad_norm": 0.05712890625,
+      "learning_rate": 1.951611060558363e-05,
+      "loss": 1.0175,
+      "step": 101
+    },
+    {
+      "epoch": 1.7067510548523206,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 1.9316842730567902e-05,
+      "loss": 1.0099,
+      "step": 102
+    },
+    {
+      "epoch": 1.7236286919831225,
+      "grad_norm": 0.05615234375,
+      "learning_rate": 1.9116740709496334e-05,
+      "loss": 0.998,
+      "step": 103
+    },
+    {
+      "epoch": 1.740506329113924,
+      "grad_norm": 0.05615234375,
+      "learning_rate": 1.8915843208199967e-05,
+      "loss": 0.996,
+      "step": 104
+    },
+    {
+      "epoch": 1.7573839662447257,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 1.8714189046220946e-05,
+      "loss": 1.009,
+      "step": 105
+    },
+    {
+      "epoch": 1.7742616033755274,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 1.851181718931141e-05,
+      "loss": 1.0127,
+      "step": 106
+    },
+    {
+      "epoch": 1.7911392405063291,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 1.830876674190411e-05,
+      "loss": 1.0107,
+      "step": 107
+    },
+    {
+      "epoch": 1.8080168776371308,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 1.8105076939556238e-05,
+      "loss": 1.0264,
+      "step": 108
+    },
+    {
+      "epoch": 1.8248945147679325,
+      "grad_norm": 0.056884765625,
+      "learning_rate": 1.790078714136792e-05,
+      "loss": 1.0068,
+      "step": 109
+    },
+    {
+      "epoch": 1.8417721518987342,
+      "grad_norm": 0.056640625,
+      "learning_rate": 1.769593682237682e-05,
+      "loss": 1.0094,
+      "step": 110
+    },
+    {
+      "epoch": 1.8586497890295357,
+      "grad_norm": 0.057861328125,
+      "learning_rate": 1.7490565565930382e-05,
+      "loss": 1.0135,
+      "step": 111
+    },
+    {
+      "epoch": 1.8755274261603376,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.7284713056037074e-05,
+      "loss": 0.993,
+      "step": 112
+    },
+    {
+      "epoch": 1.8924050632911391,
+      "grad_norm": 0.056884765625,
+      "learning_rate": 1.7078419069698283e-05,
+      "loss": 1.015,
+      "step": 113
+    },
+    {
+      "epoch": 1.909282700421941,
+      "grad_norm": 0.055908203125,
+      "learning_rate": 1.687172346922213e-05,
+      "loss": 1.0043,
+      "step": 114
+    },
+    {
+      "epoch": 1.9261603375527425,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.6664666194520873e-05,
+      "loss": 0.9959,
+      "step": 115
+    },
+    {
+      "epoch": 1.9430379746835444,
+      "grad_norm": 0.0625,
+      "learning_rate": 1.645728725539329e-05,
+      "loss": 1.0177,
+      "step": 116
+    },
+    {
+      "epoch": 1.959915611814346,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 1.6249626723793572e-05,
+      "loss": 1.033,
+      "step": 117
+    },
+    {
+      "epoch": 1.9767932489451476,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 1.6041724726088187e-05,
+      "loss": 1.0155,
+      "step": 118
+    },
+    {
+      "epoch": 1.9936708860759493,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 1.5833621435302247e-05,
+      "loss": 1.0167,
+      "step": 119
+    },
+    {
+      "epoch": 2.010548523206751,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.5625357063356825e-05,
+      "loss": 1.0082,
+      "step": 120
+    },
+    {
+      "epoch": 2.010548523206751,
+      "eval_loss": 1.0127062797546387,
+      "eval_runtime": 74.0711,
+      "eval_samples_per_second": 13.906,
+      "eval_steps_per_second": 13.906,
+      "step": 120
+    },
+    {
+      "epoch": 2.0147679324894514,
+      "grad_norm": 0.1865234375,
+      "learning_rate": 1.541697185329881e-05,
+      "loss": 1.6592,
+      "step": 121
+    },
+    {
+      "epoch": 2.0316455696202533,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.5208506071524727e-05,
+      "loss": 1.0041,
+      "step": 122
+    },
+    {
+      "epoch": 2.048523206751055,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 1.5e-05,
+      "loss": 1.0116,
+      "step": 123
+    },
+    {
+      "epoch": 2.0654008438818567,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.4791493928475275e-05,
+      "loss": 1.0026,
+      "step": 124
+    },
+    {
+      "epoch": 2.0822784810126582,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 1.4583028146701191e-05,
+      "loss": 1.0122,
+      "step": 125
+    },
+    {
+      "epoch": 2.0991561181434597,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 1.437464293664318e-05,
+      "loss": 1.0024,
+      "step": 126
+    },
+    {
+      "epoch": 2.1160337552742616,
+      "grad_norm": 0.060546875,
+      "learning_rate": 1.4166378564697757e-05,
+      "loss": 1.0092,
+      "step": 127
+    },
+    {
+      "epoch": 2.132911392405063,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 1.3958275273911812e-05,
+      "loss": 1.0048,
+      "step": 128
+    },
+    {
+      "epoch": 2.149789029535865,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 1.375037327620643e-05,
+      "loss": 0.9921,
+      "step": 129
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 1.3542712744606712e-05,
+      "loss": 1.0117,
+      "step": 130
+    },
+    {
+      "epoch": 2.1835443037974684,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.3335333805479126e-05,
+      "loss": 0.9965,
+      "step": 131
+    },
+    {
+      "epoch": 2.20042194092827,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 1.3128276530777874e-05,
+      "loss": 1.0108,
+      "step": 132
+    },
+    {
+      "epoch": 2.217299578059072,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 1.292158093030172e-05,
+      "loss": 1.0029,
+      "step": 133
+    },
+    {
+      "epoch": 2.2341772151898733,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 1.2715286943962925e-05,
+      "loss": 0.9958,
+      "step": 134
+    },
+    {
+      "epoch": 2.2510548523206753,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 1.2509434434069625e-05,
+      "loss": 1.0054,
+      "step": 135
+    },
+    {
+      "epoch": 2.2679324894514767,
+      "grad_norm": 0.0576171875,
+      "learning_rate": 1.2304063177623182e-05,
+      "loss": 0.9837,
+      "step": 136
+    },
+    {
+      "epoch": 2.2848101265822787,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 1.2099212858632083e-05,
+      "loss": 1.0014,
+      "step": 137
+    },
+    {
+      "epoch": 2.30168776371308,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.1894923060443763e-05,
+      "loss": 0.9816,
+      "step": 138
+    },
+    {
+      "epoch": 2.318565400843882,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.169123325809589e-05,
+      "loss": 1.0021,
+      "step": 139
+    },
+    {
+      "epoch": 2.3354430379746836,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.1488182810688593e-05,
+      "loss": 1.0005,
+      "step": 140
+    },
+    {
+      "epoch": 2.352320675105485,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 1.1285810953779057e-05,
+      "loss": 1.0167,
+      "step": 141
+    },
+    {
+      "epoch": 2.369198312236287,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 1.1084156791800036e-05,
+      "loss": 1.0146,
+      "step": 142
+    },
+    {
+      "epoch": 2.3860759493670884,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.0883259290503665e-05,
+      "loss": 1.0024,
+      "step": 143
+    },
+    {
+      "epoch": 2.4029535864978904,
+      "grad_norm": 0.0576171875,
+      "learning_rate": 1.0683157269432097e-05,
+      "loss": 0.9959,
+      "step": 144
+    },
+    {
+      "epoch": 2.419831223628692,
+      "grad_norm": 0.060546875,
+      "learning_rate": 1.0483889394416373e-05,
+      "loss": 1.0059,
+      "step": 145
+    },
+    {
+      "epoch": 2.4367088607594938,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 1.0285494170104996e-05,
+      "loss": 0.983,
+      "step": 146
+    },
+    {
+      "epoch": 2.4535864978902953,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 1.0088009932523664e-05,
+      "loss": 1.0116,
+      "step": 147
+    },
+    {
+      "epoch": 2.470464135021097,
+      "grad_norm": 0.061279296875,
+      "learning_rate": 9.891474841667585e-06,
+      "loss": 1.0136,
+      "step": 148
+    },
+    {
+      "epoch": 2.4873417721518987,
+      "grad_norm": 0.057861328125,
+      "learning_rate": 9.695926874127765e-06,
+      "loss": 0.9937,
+      "step": 149
+    },
+    {
+      "epoch": 2.5042194092827,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 9.501403815752813e-06,
+      "loss": 0.9946,
+      "step": 150
+    },
+    {
+      "epoch": 2.5042194092827,
+      "eval_loss": 1.0074498653411865,
+      "eval_runtime": 74.0482,
+      "eval_samples_per_second": 13.91,
+      "eval_steps_per_second": 13.91,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 236,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.218043458650112e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47fe3d8f86dd99270fe973ee57cf8bc56524ac1c04eb16ea3572e34a069a173f
+size 6072

checkpoint-180/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /workspace/data/models/Qwen2-7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-180/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/data/models/Qwen2-7B",
+  "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": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-180/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a933cf7ed41256d49bccda4b1153f6affe2986053033092840b95fa48d9df31e
+size 161533584

checkpoint-180/added_tokens.json

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

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1dc869bec2cf0aa1ad33c3eeb39c8a620aba198b8c5ebb4e7bb24833ead283
+size 323292010

checkpoint-180/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3781185f0ef813c9c8a67f316a3f390d519f89baede75c3072348102493359e
+size 14244

checkpoint-180/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9a133418374b5458f322f3eadfaa2df68068d4d299ddea0c4f82fc6655354b
+size 1064

checkpoint-180/special_tokens_map.json

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

checkpoint-180/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "use_fast": true
+}

checkpoint-180/trainer_state.json

@@ -0,0 +1,1349 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.010548523206751,
+  "eval_steps": 30,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016877637130801686,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 3e-06,
+      "loss": 1.1751,
+      "step": 1
+    },
+    {
+      "epoch": 0.016877637130801686,
+      "eval_loss": 1.185997486114502,
+      "eval_runtime": 72.8223,
+      "eval_samples_per_second": 14.144,
+      "eval_steps_per_second": 14.144,
+      "step": 1
+    },
+    {
+      "epoch": 0.03375527426160337,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 6e-06,
+      "loss": 1.1683,
+      "step": 2
+    },
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 9e-06,
+      "loss": 1.1737,
+      "step": 3
+    },
+    {
+      "epoch": 0.06751054852320675,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 1.2e-05,
+      "loss": 1.1889,
+      "step": 4
+    },
+    {
+      "epoch": 0.08438818565400844,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 1.5e-05,
+      "loss": 1.1619,
+      "step": 5
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 1.8e-05,
+      "loss": 1.1815,
+      "step": 6
+    },
+    {
+      "epoch": 0.11814345991561181,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 2.1e-05,
+      "loss": 1.1726,
+      "step": 7
+    },
+    {
+      "epoch": 0.1350210970464135,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 2.4e-05,
+      "loss": 1.1701,
+      "step": 8
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.1818,
+      "step": 9
+    },
+    {
+      "epoch": 0.16877637130801687,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 3e-05,
+      "loss": 1.1896,
+      "step": 10
+    },
+    {
+      "epoch": 0.18565400843881857,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 2.999855077059572e-05,
+      "loss": 1.1873,
+      "step": 11
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 0.08984375,
+      "learning_rate": 2.9994203362418313e-05,
+      "loss": 1.1838,
+      "step": 12
+    },
+    {
+      "epoch": 0.21940928270042195,
+      "grad_norm": 0.0859375,
+      "learning_rate": 2.998695861552002e-05,
+      "loss": 1.1569,
+      "step": 13
+    },
+    {
+      "epoch": 0.23628691983122363,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 2.9976817929807542e-05,
+      "loss": 1.1595,
+      "step": 14
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 0.078125,
+      "learning_rate": 2.996378326477153e-05,
+      "loss": 1.1348,
+      "step": 15
+    },
+    {
+      "epoch": 0.270042194092827,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 2.9947857139107964e-05,
+      "loss": 1.1434,
+      "step": 16
+    },
+    {
+      "epoch": 0.2869198312236287,
+      "grad_norm": 0.140625,
+      "learning_rate": 2.992904263023146e-05,
+      "loss": 1.8213,
+      "step": 17
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 2.990734337368062e-05,
+      "loss": 1.1289,
+      "step": 18
+    },
+    {
+      "epoch": 0.3206751054852321,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 2.9882763562415518e-05,
+      "loss": 1.1106,
+      "step": 19
+    },
+    {
+      "epoch": 0.33755274261603374,
+      "grad_norm": 0.06640625,
+      "learning_rate": 2.9855307946007532e-05,
+      "loss": 1.1381,
+      "step": 20
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 0.064453125,
+      "learning_rate": 2.982498182972154e-05,
+      "loss": 1.1192,
+      "step": 21
+    },
+    {
+      "epoch": 0.37130801687763715,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 2.9791791073490795e-05,
+      "loss": 1.1105,
+      "step": 22
+    },
+    {
+      "epoch": 0.3881856540084388,
+      "grad_norm": 0.061767578125,
+      "learning_rate": 2.9755742090784617e-05,
+      "loss": 1.1207,
+      "step": 23
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 2.9716841847369106e-05,
+      "loss": 1.1083,
+      "step": 24
+    },
+    {
+      "epoch": 0.4219409282700422,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 2.967509785996114e-05,
+      "loss": 1.1007,
+      "step": 25
+    },
+    {
+      "epoch": 0.4388185654008439,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 2.963051819477592e-05,
+      "loss": 1.0842,
+      "step": 26
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 0.0625,
+      "learning_rate": 2.958311146596833e-05,
+      "loss": 1.0961,
+      "step": 27
+    },
+    {
+      "epoch": 0.47257383966244726,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 2.953288683396841e-05,
+      "loss": 1.109,
+      "step": 28
+    },
+    {
+      "epoch": 0.48945147679324896,
+      "grad_norm": 0.061767578125,
+      "learning_rate": 2.9479854003711298e-05,
+      "loss": 1.0789,
+      "step": 29
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 2.9424023222761938e-05,
+      "loss": 1.1007,
+      "step": 30
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "eval_loss": 1.091182827949524,
+      "eval_runtime": 74.0135,
+      "eval_samples_per_second": 13.916,
+      "eval_steps_per_second": 13.916,
+      "step": 30
+    },
+    {
+      "epoch": 0.5232067510548524,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 2.9365405279334904e-05,
+      "loss": 1.0756,
+      "step": 31
+    },
+    {
+      "epoch": 0.540084388185654,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 2.930401150020983e-05,
+      "loss": 1.0939,
+      "step": 32
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 0.05712890625,
+      "learning_rate": 2.9239853748542717e-05,
+      "loss": 1.0901,
+      "step": 33
+    },
+    {
+      "epoch": 0.5738396624472574,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.9172944421573587e-05,
+      "loss": 1.0873,
+      "step": 34
+    },
+    {
+      "epoch": 0.5907172995780591,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.9103296448230986e-05,
+      "loss": 1.0584,
+      "step": 35
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 2.9030923286633703e-05,
+      "loss": 1.0692,
+      "step": 36
+    },
+    {
+      "epoch": 0.6244725738396625,
+      "grad_norm": 0.16015625,
+      "learning_rate": 2.8955838921490252e-05,
+      "loss": 1.782,
+      "step": 37
+    },
+    {
+      "epoch": 0.6413502109704642,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.8878057861396606e-05,
+      "loss": 1.0667,
+      "step": 38
+    },
+    {
+      "epoch": 0.6582278481012658,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.8797595136032675e-05,
+      "loss": 1.0656,
+      "step": 39
+    },
+    {
+      "epoch": 0.6751054852320675,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.8714466293258142e-05,
+      "loss": 1.0736,
+      "step": 40
+    },
+    {
+      "epoch": 0.6919831223628692,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 2.8628687396108107e-05,
+      "loss": 1.0638,
+      "step": 41
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.8540275019689237e-05,
+      "loss": 1.0746,
+      "step": 42
+    },
+    {
+      "epoch": 0.7257383966244726,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 2.8449246247976947e-05,
+      "loss": 1.0608,
+      "step": 43
+    },
+    {
+      "epoch": 0.7426160337552743,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.835561867051426e-05,
+      "loss": 1.0619,
+      "step": 44
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.051025390625,
+      "learning_rate": 2.825941037901294e-05,
+      "loss": 1.048,
+      "step": 45
+    },
+    {
+      "epoch": 0.7763713080168776,
+      "grad_norm": 0.05078125,
+      "learning_rate": 2.816063996385765e-05,
+      "loss": 1.0761,
+      "step": 46
+    },
+    {
+      "epoch": 0.7932489451476793,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 2.805932651051372e-05,
+      "loss": 1.0443,
+      "step": 47
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 0.051025390625,
+      "learning_rate": 2.7955489595839228e-05,
+      "loss": 1.0527,
+      "step": 48
+    },
+    {
+      "epoch": 0.8270042194092827,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.784914928430218e-05,
+      "loss": 1.0498,
+      "step": 49
+    },
+    {
+      "epoch": 0.8438818565400844,
+      "grad_norm": 0.049560546875,
+      "learning_rate": 2.7740326124103416e-05,
+      "loss": 1.0537,
+      "step": 50
+    },
+    {
+      "epoch": 0.8607594936708861,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 2.762904114320609e-05,
+      "loss": 1.0326,
+      "step": 51
+    },
+    {
+      "epoch": 0.8776371308016878,
+      "grad_norm": 0.04931640625,
+      "learning_rate": 2.751531584527241e-05,
+      "loss": 1.043,
+      "step": 52
+    },
+    {
+      "epoch": 0.8945147679324894,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.7399172205508476e-05,
+      "loss": 1.0463,
+      "step": 53
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.0517578125,
+      "learning_rate": 2.7280632666418013e-05,
+      "loss": 1.0476,
+      "step": 54
+    },
+    {
+      "epoch": 0.9282700421940928,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 2.715972013346576e-05,
+      "loss": 1.0467,
+      "step": 55
+    },
+    {
+      "epoch": 0.9451476793248945,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 2.703645797065147e-05,
+      "loss": 1.0467,
+      "step": 56
+    },
+    {
+      "epoch": 0.9620253164556962,
+      "grad_norm": 0.05078125,
+      "learning_rate": 2.6910869995995247e-05,
+      "loss": 1.05,
+      "step": 57
+    },
+    {
+      "epoch": 0.9789029535864979,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 2.678298047693518e-05,
+      "loss": 1.0453,
+      "step": 58
+    },
+    {
+      "epoch": 0.9957805907172996,
+      "grad_norm": 0.050048828125,
+      "learning_rate": 2.6652814125638142e-05,
+      "loss": 1.0348,
+      "step": 59
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "grad_norm": 0.052490234375,
+      "learning_rate": 2.652039609422463e-05,
+      "loss": 1.0418,
+      "step": 60
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "eval_loss": 1.0428293943405151,
+      "eval_runtime": 74.0734,
+      "eval_samples_per_second": 13.905,
+      "eval_steps_per_second": 13.905,
+      "step": 60
+    },
+    {
+      "epoch": 1.0147679324894514,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 2.638575196990862e-05,
+      "loss": 1.0194,
+      "step": 61
+    },
+    {
+      "epoch": 1.0316455696202531,
+      "grad_norm": 0.049560546875,
+      "learning_rate": 2.624890777005332e-05,
+      "loss": 1.0365,
+      "step": 62
+    },
+    {
+      "epoch": 1.0485232067510548,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.6109889937143828e-05,
+      "loss": 1.0426,
+      "step": 63
+    },
+    {
+      "epoch": 1.0654008438818565,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.5968725333677628e-05,
+      "loss": 1.043,
+      "step": 64
+    },
+    {
+      "epoch": 1.0822784810126582,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 2.582544123697395e-05,
+      "loss": 1.0243,
+      "step": 65
+    },
+    {
+      "epoch": 1.09915611814346,
+      "grad_norm": 0.0517578125,
+      "learning_rate": 2.568006533390295e-05,
+      "loss": 1.0258,
+      "step": 66
+    },
+    {
+      "epoch": 1.1160337552742616,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 2.5532625715535733e-05,
+      "loss": 1.0248,
+      "step": 67
+    },
+    {
+      "epoch": 1.1329113924050633,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 2.5383150871716342e-05,
+      "loss": 1.0083,
+      "step": 68
+    },
+    {
+      "epoch": 1.149789029535865,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.5231669685556636e-05,
+      "loss": 1.0207,
+      "step": 69
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 2.507821142785516e-05,
+      "loss": 1.0435,
+      "step": 70
+    },
+    {
+      "epoch": 1.1835443037974684,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.4922805751441174e-05,
+      "loss": 1.0354,
+      "step": 71
+    },
+    {
+      "epoch": 1.20042194092827,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 2.4765482685444786e-05,
+      "loss": 1.0266,
+      "step": 72
+    },
+    {
+      "epoch": 1.2172995780590719,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.460627262949443e-05,
+      "loss": 1.0411,
+      "step": 73
+    },
+    {
+      "epoch": 1.2341772151898733,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.4445206347842714e-05,
+      "loss": 1.0224,
+      "step": 74
+    },
+    {
+      "epoch": 1.251054852320675,
+      "grad_norm": 0.052978515625,
+      "learning_rate": 2.428231496342181e-05,
+      "loss": 1.0253,
+      "step": 75
+    },
+    {
+      "epoch": 1.2679324894514767,
+      "grad_norm": 0.05322265625,
+      "learning_rate": 2.4117629951829602e-05,
+      "loss": 1.0298,
+      "step": 76
+    },
+    {
+      "epoch": 1.2848101265822784,
+      "grad_norm": 0.052490234375,
+      "learning_rate": 2.395118313524758e-05,
+      "loss": 1.0239,
+      "step": 77
+    },
+    {
+      "epoch": 1.3016877637130801,
+      "grad_norm": 0.0537109375,
+      "learning_rate": 2.3783006676291866e-05,
+      "loss": 1.0212,
+      "step": 78
+    },
+    {
+      "epoch": 1.3185654008438819,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.361313307179837e-05,
+      "loss": 1.0371,
+      "step": 79
+    },
+    {
+      "epoch": 1.3354430379746836,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.3441595146543458e-05,
+      "loss": 1.0314,
+      "step": 80
+    },
+    {
+      "epoch": 1.3523206751054853,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.3268426046901153e-05,
+      "loss": 1.0195,
+      "step": 81
+    },
+    {
+      "epoch": 1.369198312236287,
+      "grad_norm": 0.052978515625,
+      "learning_rate": 2.3093659234438266e-05,
+      "loss": 1.0219,
+      "step": 82
+    },
+    {
+      "epoch": 1.3860759493670887,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.291732847944861e-05,
+      "loss": 1.0293,
+      "step": 83
+    },
+    {
+      "epoch": 1.4029535864978904,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.2739467854427512e-05,
+      "loss": 0.9992,
+      "step": 84
+    },
+    {
+      "epoch": 1.4198312236286919,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.2560111727488e-05,
+      "loss": 1.0254,
+      "step": 85
+    },
+    {
+      "epoch": 1.4367088607594938,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.237929475571979e-05,
+      "loss": 1.0148,
+      "step": 86
+    },
+    {
+      "epoch": 1.4535864978902953,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 2.219705187849254e-05,
+      "loss": 1.0228,
+      "step": 87
+    },
+    {
+      "epoch": 1.4704641350210972,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 2.2013418310704422e-05,
+      "loss": 1.021,
+      "step": 88
+    },
+    {
+      "epoch": 1.4873417721518987,
+      "grad_norm": 0.0537109375,
+      "learning_rate": 2.1828429535977585e-05,
+      "loss": 1.0352,
+      "step": 89
+    },
+    {
+      "epoch": 1.5042194092827004,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.1642121299801594e-05,
+      "loss": 1.0105,
+      "step": 90
+    },
+    {
+      "epoch": 1.5042194092827004,
+      "eval_loss": 1.0232045650482178,
+      "eval_runtime": 74.0589,
+      "eval_samples_per_second": 13.908,
+      "eval_steps_per_second": 13.908,
+      "step": 90
+    },
+    {
+      "epoch": 1.521097046413502,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.1454529602626336e-05,
+      "loss": 1.0051,
+      "step": 91
+    },
+    {
+      "epoch": 1.5379746835443038,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.126569069290562e-05,
+      "loss": 1.023,
+      "step": 92
+    },
+    {
+      "epoch": 1.5548523206751055,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.107564106009286e-05,
+      "loss": 1.012,
+      "step": 93
+    },
+    {
+      "epoch": 1.5717299578059072,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.0884417427590217e-05,
+      "loss": 1.0136,
+      "step": 94
+    },
+    {
+      "epoch": 1.5886075949367089,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.0692056745652483e-05,
+      "loss": 1.0194,
+      "step": 95
+    },
+    {
+      "epoch": 1.6054852320675106,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 2.0498596184247196e-05,
+      "loss": 1.0089,
+      "step": 96
+    },
+    {
+      "epoch": 1.6223628691983123,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.030407312587224e-05,
+      "loss": 1.0226,
+      "step": 97
+    },
+    {
+      "epoch": 1.6392405063291138,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 2.010852515833242e-05,
+      "loss": 1.0219,
+      "step": 98
+    },
+    {
+      "epoch": 1.6561181434599157,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 1.9911990067476336e-05,
+      "loss": 1.0035,
+      "step": 99
+    },
+    {
+      "epoch": 1.6729957805907172,
+      "grad_norm": 0.055908203125,
+      "learning_rate": 1.9714505829895004e-05,
+      "loss": 1.0052,
+      "step": 100
+    },
+    {
+      "epoch": 1.689873417721519,
+      "grad_norm": 0.05712890625,
+      "learning_rate": 1.951611060558363e-05,
+      "loss": 1.0175,
+      "step": 101
+    },
+    {
+      "epoch": 1.7067510548523206,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 1.9316842730567902e-05,
+      "loss": 1.0099,
+      "step": 102
+    },
+    {
+      "epoch": 1.7236286919831225,
+      "grad_norm": 0.05615234375,
+      "learning_rate": 1.9116740709496334e-05,
+      "loss": 0.998,
+      "step": 103
+    },
+    {
+      "epoch": 1.740506329113924,
+      "grad_norm": 0.05615234375,
+      "learning_rate": 1.8915843208199967e-05,
+      "loss": 0.996,
+      "step": 104
+    },
+    {
+      "epoch": 1.7573839662447257,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 1.8714189046220946e-05,
+      "loss": 1.009,
+      "step": 105
+    },
+    {
+      "epoch": 1.7742616033755274,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 1.851181718931141e-05,
+      "loss": 1.0127,
+      "step": 106
+    },
+    {
+      "epoch": 1.7911392405063291,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 1.830876674190411e-05,
+      "loss": 1.0107,
+      "step": 107
+    },
+    {
+      "epoch": 1.8080168776371308,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 1.8105076939556238e-05,
+      "loss": 1.0264,
+      "step": 108
+    },
+    {
+      "epoch": 1.8248945147679325,
+      "grad_norm": 0.056884765625,
+      "learning_rate": 1.790078714136792e-05,
+      "loss": 1.0068,
+      "step": 109
+    },
+    {
+      "epoch": 1.8417721518987342,
+      "grad_norm": 0.056640625,
+      "learning_rate": 1.769593682237682e-05,
+      "loss": 1.0094,
+      "step": 110
+    },
+    {
+      "epoch": 1.8586497890295357,
+      "grad_norm": 0.057861328125,
+      "learning_rate": 1.7490565565930382e-05,
+      "loss": 1.0135,
+      "step": 111
+    },
+    {
+      "epoch": 1.8755274261603376,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.7284713056037074e-05,
+      "loss": 0.993,
+      "step": 112
+    },
+    {
+      "epoch": 1.8924050632911391,
+      "grad_norm": 0.056884765625,
+      "learning_rate": 1.7078419069698283e-05,
+      "loss": 1.015,
+      "step": 113
+    },
+    {
+      "epoch": 1.909282700421941,
+      "grad_norm": 0.055908203125,
+      "learning_rate": 1.687172346922213e-05,
+      "loss": 1.0043,
+      "step": 114
+    },
+    {
+      "epoch": 1.9261603375527425,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.6664666194520873e-05,
+      "loss": 0.9959,
+      "step": 115
+    },
+    {
+      "epoch": 1.9430379746835444,
+      "grad_norm": 0.0625,
+      "learning_rate": 1.645728725539329e-05,
+      "loss": 1.0177,
+      "step": 116
+    },
+    {
+      "epoch": 1.959915611814346,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 1.6249626723793572e-05,
+      "loss": 1.033,
+      "step": 117
+    },
+    {
+      "epoch": 1.9767932489451476,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 1.6041724726088187e-05,
+      "loss": 1.0155,
+      "step": 118
+    },
+    {
+      "epoch": 1.9936708860759493,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 1.5833621435302247e-05,
+      "loss": 1.0167,
+      "step": 119
+    },
+    {
+      "epoch": 2.010548523206751,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.5625357063356825e-05,
+      "loss": 1.0082,
+      "step": 120
+    },
+    {
+      "epoch": 2.010548523206751,
+      "eval_loss": 1.0127062797546387,
+      "eval_runtime": 74.0711,
+      "eval_samples_per_second": 13.906,
+      "eval_steps_per_second": 13.906,
+      "step": 120
+    },
+    {
+      "epoch": 2.0147679324894514,
+      "grad_norm": 0.1865234375,
+      "learning_rate": 1.541697185329881e-05,
+      "loss": 1.6592,
+      "step": 121
+    },
+    {
+      "epoch": 2.0316455696202533,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.5208506071524727e-05,
+      "loss": 1.0041,
+      "step": 122
+    },
+    {
+      "epoch": 2.048523206751055,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 1.5e-05,
+      "loss": 1.0116,
+      "step": 123
+    },
+    {
+      "epoch": 2.0654008438818567,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.4791493928475275e-05,
+      "loss": 1.0026,
+      "step": 124
+    },
+    {
+      "epoch": 2.0822784810126582,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 1.4583028146701191e-05,
+      "loss": 1.0122,
+      "step": 125
+    },
+    {
+      "epoch": 2.0991561181434597,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 1.437464293664318e-05,
+      "loss": 1.0024,
+      "step": 126
+    },
+    {
+      "epoch": 2.1160337552742616,
+      "grad_norm": 0.060546875,
+      "learning_rate": 1.4166378564697757e-05,
+      "loss": 1.0092,
+      "step": 127
+    },
+    {
+      "epoch": 2.132911392405063,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 1.3958275273911812e-05,
+      "loss": 1.0048,
+      "step": 128
+    },
+    {
+      "epoch": 2.149789029535865,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 1.375037327620643e-05,
+      "loss": 0.9921,
+      "step": 129
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 1.3542712744606712e-05,
+      "loss": 1.0117,
+      "step": 130
+    },
+    {
+      "epoch": 2.1835443037974684,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.3335333805479126e-05,
+      "loss": 0.9965,
+      "step": 131
+    },
+    {
+      "epoch": 2.20042194092827,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 1.3128276530777874e-05,
+      "loss": 1.0108,
+      "step": 132
+    },
+    {
+      "epoch": 2.217299578059072,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 1.292158093030172e-05,
+      "loss": 1.0029,
+      "step": 133
+    },
+    {
+      "epoch": 2.2341772151898733,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 1.2715286943962925e-05,
+      "loss": 0.9958,
+      "step": 134
+    },
+    {
+      "epoch": 2.2510548523206753,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 1.2509434434069625e-05,
+      "loss": 1.0054,
+      "step": 135
+    },
+    {
+      "epoch": 2.2679324894514767,
+      "grad_norm": 0.0576171875,
+      "learning_rate": 1.2304063177623182e-05,
+      "loss": 0.9837,
+      "step": 136
+    },
+    {
+      "epoch": 2.2848101265822787,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 1.2099212858632083e-05,
+      "loss": 1.0014,
+      "step": 137
+    },
+    {
+      "epoch": 2.30168776371308,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.1894923060443763e-05,
+      "loss": 0.9816,
+      "step": 138
+    },
+    {
+      "epoch": 2.318565400843882,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.169123325809589e-05,
+      "loss": 1.0021,
+      "step": 139
+    },
+    {
+      "epoch": 2.3354430379746836,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.1488182810688593e-05,
+      "loss": 1.0005,
+      "step": 140
+    },
+    {
+      "epoch": 2.352320675105485,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 1.1285810953779057e-05,
+      "loss": 1.0167,
+      "step": 141
+    },
+    {
+      "epoch": 2.369198312236287,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 1.1084156791800036e-05,
+      "loss": 1.0146,
+      "step": 142
+    },
+    {
+      "epoch": 2.3860759493670884,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.0883259290503665e-05,
+      "loss": 1.0024,
+      "step": 143
+    },
+    {
+      "epoch": 2.4029535864978904,
+      "grad_norm": 0.0576171875,
+      "learning_rate": 1.0683157269432097e-05,
+      "loss": 0.9959,
+      "step": 144
+    },
+    {
+      "epoch": 2.419831223628692,
+      "grad_norm": 0.060546875,
+      "learning_rate": 1.0483889394416373e-05,
+      "loss": 1.0059,
+      "step": 145
+    },
+    {
+      "epoch": 2.4367088607594938,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 1.0285494170104996e-05,
+      "loss": 0.983,
+      "step": 146
+    },
+    {
+      "epoch": 2.4535864978902953,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 1.0088009932523664e-05,
+      "loss": 1.0116,
+      "step": 147
+    },
+    {
+      "epoch": 2.470464135021097,
+      "grad_norm": 0.061279296875,
+      "learning_rate": 9.891474841667585e-06,
+      "loss": 1.0136,
+      "step": 148
+    },
+    {
+      "epoch": 2.4873417721518987,
+      "grad_norm": 0.057861328125,
+      "learning_rate": 9.695926874127765e-06,
+      "loss": 0.9937,
+      "step": 149
+    },
+    {
+      "epoch": 2.5042194092827,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 9.501403815752813e-06,
+      "loss": 0.9946,
+      "step": 150
+    },
+    {
+      "epoch": 2.5042194092827,
+      "eval_loss": 1.0074498653411865,
+      "eval_runtime": 74.0482,
+      "eval_samples_per_second": 13.91,
+      "eval_steps_per_second": 13.91,
+      "step": 150
+    },
+    {
+      "epoch": 2.521097046413502,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 9.307943254347521e-06,
+      "loss": 1.0043,
+      "step": 151
+    },
+    {
+      "epoch": 2.537974683544304,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 9.115582572409789e-06,
+      "loss": 1.0125,
+      "step": 152
+    },
+    {
+      "epoch": 2.5548523206751055,
+      "grad_norm": 0.05859375,
+      "learning_rate": 8.92435893990714e-06,
+      "loss": 0.9753,
+      "step": 153
+    },
+    {
+      "epoch": 2.571729957805907,
+      "grad_norm": 0.060546875,
+      "learning_rate": 8.734309307094382e-06,
+      "loss": 0.9959,
+      "step": 154
+    },
+    {
+      "epoch": 2.588607594936709,
+      "grad_norm": 0.061279296875,
+      "learning_rate": 8.545470397373665e-06,
+      "loss": 1.0158,
+      "step": 155
+    },
+    {
+      "epoch": 2.605485232067511,
+      "grad_norm": 0.062255859375,
+      "learning_rate": 8.357878700198407e-06,
+      "loss": 1.0001,
+      "step": 156
+    },
+    {
+      "epoch": 2.6223628691983123,
+      "grad_norm": 0.060546875,
+      "learning_rate": 8.171570464022419e-06,
+      "loss": 0.9963,
+      "step": 157
+    },
+    {
+      "epoch": 2.6392405063291138,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 7.986581689295577e-06,
+      "loss": 0.968,
+      "step": 158
+    },
+    {
+      "epoch": 2.6561181434599157,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 7.802948121507462e-06,
+      "loss": 0.9872,
+      "step": 159
+    },
+    {
+      "epoch": 2.672995780590717,
+      "grad_norm": 0.0625,
+      "learning_rate": 7.620705244280208e-06,
+      "loss": 1.0181,
+      "step": 160
+    },
+    {
+      "epoch": 2.689873417721519,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 7.439888272512004e-06,
+      "loss": 1.0057,
+      "step": 161
+    },
+    {
+      "epoch": 2.7067510548523206,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 7.260532145572487e-06,
+      "loss": 0.9985,
+      "step": 162
+    },
+    {
+      "epoch": 2.7236286919831225,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 7.082671520551391e-06,
+      "loss": 0.9973,
+      "step": 163
+    },
+    {
+      "epoch": 2.740506329113924,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 6.906340765561734e-06,
+      "loss": 0.991,
+      "step": 164
+    },
+    {
+      "epoch": 2.757383966244726,
+      "grad_norm": 0.060546875,
+      "learning_rate": 6.731573953098851e-06,
+      "loss": 0.9979,
+      "step": 165
+    },
+    {
+      "epoch": 2.7742616033755274,
+      "grad_norm": 0.060546875,
+      "learning_rate": 6.558404853456545e-06,
+      "loss": 1.0096,
+      "step": 166
+    },
+    {
+      "epoch": 2.791139240506329,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 6.38686692820163e-06,
+      "loss": 0.9981,
+      "step": 167
+    },
+    {
+      "epoch": 2.808016877637131,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 6.2169933237081386e-06,
+      "loss": 1.0169,
+      "step": 168
+    },
+    {
+      "epoch": 2.8248945147679327,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 6.048816864752422e-06,
+      "loss": 0.9934,
+      "step": 169
+    },
+    {
+      "epoch": 2.8417721518987342,
+      "grad_norm": 0.05859375,
+      "learning_rate": 5.882370048170403e-06,
+      "loss": 0.9913,
+      "step": 170
+    },
+    {
+      "epoch": 2.8586497890295357,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 5.71768503657819e-06,
+      "loss": 1.0107,
+      "step": 171
+    },
+    {
+      "epoch": 2.8755274261603376,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 5.55479365215729e-06,
+      "loss": 1.0098,
+      "step": 172
+    },
+    {
+      "epoch": 2.892405063291139,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 5.393727370505569e-06,
+      "loss": 1.0123,
+      "step": 173
+    },
+    {
+      "epoch": 2.909282700421941,
+      "grad_norm": 0.060546875,
+      "learning_rate": 5.234517314555213e-06,
+      "loss": 0.9837,
+      "step": 174
+    },
+    {
+      "epoch": 2.9261603375527425,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 5.077194248558827e-06,
+      "loss": 0.9865,
+      "step": 175
+    },
+    {
+      "epoch": 2.9430379746835444,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 4.921788572144841e-06,
+      "loss": 0.995,
+      "step": 176
+    },
+    {
+      "epoch": 2.959915611814346,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 4.768330314443367e-06,
+      "loss": 1.0009,
+      "step": 177
+    },
+    {
+      "epoch": 2.976793248945148,
+      "grad_norm": 0.060546875,
+      "learning_rate": 4.616849128283658e-06,
+      "loss": 1.0016,
+      "step": 178
+    },
+    {
+      "epoch": 2.9936708860759493,
+      "grad_norm": 0.0625,
+      "learning_rate": 4.4673742844642716e-06,
+      "loss": 0.9979,
+      "step": 179
+    },
+    {
+      "epoch": 3.010548523206751,
+      "grad_norm": 0.062255859375,
+      "learning_rate": 4.319934666097055e-06,
+      "loss": 0.9826,
+      "step": 180
+    },
+    {
+      "epoch": 3.010548523206751,
+      "eval_loss": 1.0056920051574707,
+      "eval_runtime": 74.0404,
+      "eval_samples_per_second": 13.911,
+      "eval_steps_per_second": 13.911,
+      "step": 180
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 236,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.0616521503801344e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-180/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47fe3d8f86dd99270fe973ee57cf8bc56524ac1c04eb16ea3572e34a069a173f
+size 6072

checkpoint-210/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /workspace/data/models/Qwen2-7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-210/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/data/models/Qwen2-7B",
+  "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": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-210/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211e075290261b180bf07444a698f876b0bf0d4f25a0f5d9a63c1a0817dd684a
+size 161533584

checkpoint-210/added_tokens.json

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

checkpoint-210/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e88a09d37b5d510640296d54ddd41c6450aa4ba2b6e23c8afe6658afd53b8e
+size 323292010

checkpoint-210/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3acd095418f1f164bc481993af24e659f064b41527543ccbde827f79f691f6a2
+size 14244

checkpoint-210/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3572e42c81044982b589162cb8d8c0f32fd7261e0a56bbd08c208bc4f8dd4f36
+size 1064

checkpoint-210/special_tokens_map.json

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

checkpoint-210/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "use_fast": true
+}

checkpoint-210/trainer_state.json

@@ -0,0 +1,1567 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.50210970464135,
+  "eval_steps": 30,
+  "global_step": 210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016877637130801686,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 3e-06,
+      "loss": 1.1751,
+      "step": 1
+    },
+    {
+      "epoch": 0.016877637130801686,
+      "eval_loss": 1.185997486114502,
+      "eval_runtime": 72.8223,
+      "eval_samples_per_second": 14.144,
+      "eval_steps_per_second": 14.144,
+      "step": 1
+    },
+    {
+      "epoch": 0.03375527426160337,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 6e-06,
+      "loss": 1.1683,
+      "step": 2
+    },
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 9e-06,
+      "loss": 1.1737,
+      "step": 3
+    },
+    {
+      "epoch": 0.06751054852320675,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 1.2e-05,
+      "loss": 1.1889,
+      "step": 4
+    },
+    {
+      "epoch": 0.08438818565400844,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 1.5e-05,
+      "loss": 1.1619,
+      "step": 5
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 1.8e-05,
+      "loss": 1.1815,
+      "step": 6
+    },
+    {
+      "epoch": 0.11814345991561181,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 2.1e-05,
+      "loss": 1.1726,
+      "step": 7
+    },
+    {
+      "epoch": 0.1350210970464135,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 2.4e-05,
+      "loss": 1.1701,
+      "step": 8
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.1818,
+      "step": 9
+    },
+    {
+      "epoch": 0.16877637130801687,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 3e-05,
+      "loss": 1.1896,
+      "step": 10
+    },
+    {
+      "epoch": 0.18565400843881857,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 2.999855077059572e-05,
+      "loss": 1.1873,
+      "step": 11
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 0.08984375,
+      "learning_rate": 2.9994203362418313e-05,
+      "loss": 1.1838,
+      "step": 12
+    },
+    {
+      "epoch": 0.21940928270042195,
+      "grad_norm": 0.0859375,
+      "learning_rate": 2.998695861552002e-05,
+      "loss": 1.1569,
+      "step": 13
+    },
+    {
+      "epoch": 0.23628691983122363,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 2.9976817929807542e-05,
+      "loss": 1.1595,
+      "step": 14
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 0.078125,
+      "learning_rate": 2.996378326477153e-05,
+      "loss": 1.1348,
+      "step": 15
+    },
+    {
+      "epoch": 0.270042194092827,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 2.9947857139107964e-05,
+      "loss": 1.1434,
+      "step": 16
+    },
+    {
+      "epoch": 0.2869198312236287,
+      "grad_norm": 0.140625,
+      "learning_rate": 2.992904263023146e-05,
+      "loss": 1.8213,
+      "step": 17
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 2.990734337368062e-05,
+      "loss": 1.1289,
+      "step": 18
+    },
+    {
+      "epoch": 0.3206751054852321,
+      "grad_norm": 0.0654296875,
+      "learning_rate": 2.9882763562415518e-05,
+      "loss": 1.1106,
+      "step": 19
+    },
+    {
+      "epoch": 0.33755274261603374,
+      "grad_norm": 0.06640625,
+      "learning_rate": 2.9855307946007532e-05,
+      "loss": 1.1381,
+      "step": 20
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 0.064453125,
+      "learning_rate": 2.982498182972154e-05,
+      "loss": 1.1192,
+      "step": 21
+    },
+    {
+      "epoch": 0.37130801687763715,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 2.9791791073490795e-05,
+      "loss": 1.1105,
+      "step": 22
+    },
+    {
+      "epoch": 0.3881856540084388,
+      "grad_norm": 0.061767578125,
+      "learning_rate": 2.9755742090784617e-05,
+      "loss": 1.1207,
+      "step": 23
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 2.9716841847369106e-05,
+      "loss": 1.1083,
+      "step": 24
+    },
+    {
+      "epoch": 0.4219409282700422,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 2.967509785996114e-05,
+      "loss": 1.1007,
+      "step": 25
+    },
+    {
+      "epoch": 0.4388185654008439,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 2.963051819477592e-05,
+      "loss": 1.0842,
+      "step": 26
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 0.0625,
+      "learning_rate": 2.958311146596833e-05,
+      "loss": 1.0961,
+      "step": 27
+    },
+    {
+      "epoch": 0.47257383966244726,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 2.953288683396841e-05,
+      "loss": 1.109,
+      "step": 28
+    },
+    {
+      "epoch": 0.48945147679324896,
+      "grad_norm": 0.061767578125,
+      "learning_rate": 2.9479854003711298e-05,
+      "loss": 1.0789,
+      "step": 29
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 2.9424023222761938e-05,
+      "loss": 1.1007,
+      "step": 30
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "eval_loss": 1.091182827949524,
+      "eval_runtime": 74.0135,
+      "eval_samples_per_second": 13.916,
+      "eval_steps_per_second": 13.916,
+      "step": 30
+    },
+    {
+      "epoch": 0.5232067510548524,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 2.9365405279334904e-05,
+      "loss": 1.0756,
+      "step": 31
+    },
+    {
+      "epoch": 0.540084388185654,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 2.930401150020983e-05,
+      "loss": 1.0939,
+      "step": 32
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 0.05712890625,
+      "learning_rate": 2.9239853748542717e-05,
+      "loss": 1.0901,
+      "step": 33
+    },
+    {
+      "epoch": 0.5738396624472574,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.9172944421573587e-05,
+      "loss": 1.0873,
+      "step": 34
+    },
+    {
+      "epoch": 0.5907172995780591,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.9103296448230986e-05,
+      "loss": 1.0584,
+      "step": 35
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 2.9030923286633703e-05,
+      "loss": 1.0692,
+      "step": 36
+    },
+    {
+      "epoch": 0.6244725738396625,
+      "grad_norm": 0.16015625,
+      "learning_rate": 2.8955838921490252e-05,
+      "loss": 1.782,
+      "step": 37
+    },
+    {
+      "epoch": 0.6413502109704642,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.8878057861396606e-05,
+      "loss": 1.0667,
+      "step": 38
+    },
+    {
+      "epoch": 0.6582278481012658,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.8797595136032675e-05,
+      "loss": 1.0656,
+      "step": 39
+    },
+    {
+      "epoch": 0.6751054852320675,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.8714466293258142e-05,
+      "loss": 1.0736,
+      "step": 40
+    },
+    {
+      "epoch": 0.6919831223628692,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 2.8628687396108107e-05,
+      "loss": 1.0638,
+      "step": 41
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.8540275019689237e-05,
+      "loss": 1.0746,
+      "step": 42
+    },
+    {
+      "epoch": 0.7257383966244726,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 2.8449246247976947e-05,
+      "loss": 1.0608,
+      "step": 43
+    },
+    {
+      "epoch": 0.7426160337552743,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.835561867051426e-05,
+      "loss": 1.0619,
+      "step": 44
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.051025390625,
+      "learning_rate": 2.825941037901294e-05,
+      "loss": 1.048,
+      "step": 45
+    },
+    {
+      "epoch": 0.7763713080168776,
+      "grad_norm": 0.05078125,
+      "learning_rate": 2.816063996385765e-05,
+      "loss": 1.0761,
+      "step": 46
+    },
+    {
+      "epoch": 0.7932489451476793,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 2.805932651051372e-05,
+      "loss": 1.0443,
+      "step": 47
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 0.051025390625,
+      "learning_rate": 2.7955489595839228e-05,
+      "loss": 1.0527,
+      "step": 48
+    },
+    {
+      "epoch": 0.8270042194092827,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.784914928430218e-05,
+      "loss": 1.0498,
+      "step": 49
+    },
+    {
+      "epoch": 0.8438818565400844,
+      "grad_norm": 0.049560546875,
+      "learning_rate": 2.7740326124103416e-05,
+      "loss": 1.0537,
+      "step": 50
+    },
+    {
+      "epoch": 0.8607594936708861,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 2.762904114320609e-05,
+      "loss": 1.0326,
+      "step": 51
+    },
+    {
+      "epoch": 0.8776371308016878,
+      "grad_norm": 0.04931640625,
+      "learning_rate": 2.751531584527241e-05,
+      "loss": 1.043,
+      "step": 52
+    },
+    {
+      "epoch": 0.8945147679324894,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.7399172205508476e-05,
+      "loss": 1.0463,
+      "step": 53
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.0517578125,
+      "learning_rate": 2.7280632666418013e-05,
+      "loss": 1.0476,
+      "step": 54
+    },
+    {
+      "epoch": 0.9282700421940928,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 2.715972013346576e-05,
+      "loss": 1.0467,
+      "step": 55
+    },
+    {
+      "epoch": 0.9451476793248945,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 2.703645797065147e-05,
+      "loss": 1.0467,
+      "step": 56
+    },
+    {
+      "epoch": 0.9620253164556962,
+      "grad_norm": 0.05078125,
+      "learning_rate": 2.6910869995995247e-05,
+      "loss": 1.05,
+      "step": 57
+    },
+    {
+      "epoch": 0.9789029535864979,
+      "grad_norm": 0.053955078125,
+      "learning_rate": 2.678298047693518e-05,
+      "loss": 1.0453,
+      "step": 58
+    },
+    {
+      "epoch": 0.9957805907172996,
+      "grad_norm": 0.050048828125,
+      "learning_rate": 2.6652814125638142e-05,
+      "loss": 1.0348,
+      "step": 59
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "grad_norm": 0.052490234375,
+      "learning_rate": 2.652039609422463e-05,
+      "loss": 1.0418,
+      "step": 60
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "eval_loss": 1.0428293943405151,
+      "eval_runtime": 74.0734,
+      "eval_samples_per_second": 13.905,
+      "eval_steps_per_second": 13.905,
+      "step": 60
+    },
+    {
+      "epoch": 1.0147679324894514,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 2.638575196990862e-05,
+      "loss": 1.0194,
+      "step": 61
+    },
+    {
+      "epoch": 1.0316455696202531,
+      "grad_norm": 0.049560546875,
+      "learning_rate": 2.624890777005332e-05,
+      "loss": 1.0365,
+      "step": 62
+    },
+    {
+      "epoch": 1.0485232067510548,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.6109889937143828e-05,
+      "loss": 1.0426,
+      "step": 63
+    },
+    {
+      "epoch": 1.0654008438818565,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.5968725333677628e-05,
+      "loss": 1.043,
+      "step": 64
+    },
+    {
+      "epoch": 1.0822784810126582,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 2.582544123697395e-05,
+      "loss": 1.0243,
+      "step": 65
+    },
+    {
+      "epoch": 1.09915611814346,
+      "grad_norm": 0.0517578125,
+      "learning_rate": 2.568006533390295e-05,
+      "loss": 1.0258,
+      "step": 66
+    },
+    {
+      "epoch": 1.1160337552742616,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 2.5532625715535733e-05,
+      "loss": 1.0248,
+      "step": 67
+    },
+    {
+      "epoch": 1.1329113924050633,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 2.5383150871716342e-05,
+      "loss": 1.0083,
+      "step": 68
+    },
+    {
+      "epoch": 1.149789029535865,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.5231669685556636e-05,
+      "loss": 1.0207,
+      "step": 69
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 2.507821142785516e-05,
+      "loss": 1.0435,
+      "step": 70
+    },
+    {
+      "epoch": 1.1835443037974684,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.4922805751441174e-05,
+      "loss": 1.0354,
+      "step": 71
+    },
+    {
+      "epoch": 1.20042194092827,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 2.4765482685444786e-05,
+      "loss": 1.0266,
+      "step": 72
+    },
+    {
+      "epoch": 1.2172995780590719,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.460627262949443e-05,
+      "loss": 1.0411,
+      "step": 73
+    },
+    {
+      "epoch": 1.2341772151898733,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.4445206347842714e-05,
+      "loss": 1.0224,
+      "step": 74
+    },
+    {
+      "epoch": 1.251054852320675,
+      "grad_norm": 0.052978515625,
+      "learning_rate": 2.428231496342181e-05,
+      "loss": 1.0253,
+      "step": 75
+    },
+    {
+      "epoch": 1.2679324894514767,
+      "grad_norm": 0.05322265625,
+      "learning_rate": 2.4117629951829602e-05,
+      "loss": 1.0298,
+      "step": 76
+    },
+    {
+      "epoch": 1.2848101265822784,
+      "grad_norm": 0.052490234375,
+      "learning_rate": 2.395118313524758e-05,
+      "loss": 1.0239,
+      "step": 77
+    },
+    {
+      "epoch": 1.3016877637130801,
+      "grad_norm": 0.0537109375,
+      "learning_rate": 2.3783006676291866e-05,
+      "loss": 1.0212,
+      "step": 78
+    },
+    {
+      "epoch": 1.3185654008438819,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.361313307179837e-05,
+      "loss": 1.0371,
+      "step": 79
+    },
+    {
+      "epoch": 1.3354430379746836,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 2.3441595146543458e-05,
+      "loss": 1.0314,
+      "step": 80
+    },
+    {
+      "epoch": 1.3523206751054853,
+      "grad_norm": 0.052001953125,
+      "learning_rate": 2.3268426046901153e-05,
+      "loss": 1.0195,
+      "step": 81
+    },
+    {
+      "epoch": 1.369198312236287,
+      "grad_norm": 0.052978515625,
+      "learning_rate": 2.3093659234438266e-05,
+      "loss": 1.0219,
+      "step": 82
+    },
+    {
+      "epoch": 1.3860759493670887,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.291732847944861e-05,
+      "loss": 1.0293,
+      "step": 83
+    },
+    {
+      "epoch": 1.4029535864978904,
+      "grad_norm": 0.052734375,
+      "learning_rate": 2.2739467854427512e-05,
+      "loss": 0.9992,
+      "step": 84
+    },
+    {
+      "epoch": 1.4198312236286919,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 2.2560111727488e-05,
+      "loss": 1.0254,
+      "step": 85
+    },
+    {
+      "epoch": 1.4367088607594938,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.237929475571979e-05,
+      "loss": 1.0148,
+      "step": 86
+    },
+    {
+      "epoch": 1.4535864978902953,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 2.219705187849254e-05,
+      "loss": 1.0228,
+      "step": 87
+    },
+    {
+      "epoch": 1.4704641350210972,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 2.2013418310704422e-05,
+      "loss": 1.021,
+      "step": 88
+    },
+    {
+      "epoch": 1.4873417721518987,
+      "grad_norm": 0.0537109375,
+      "learning_rate": 2.1828429535977585e-05,
+      "loss": 1.0352,
+      "step": 89
+    },
+    {
+      "epoch": 1.5042194092827004,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.1642121299801594e-05,
+      "loss": 1.0105,
+      "step": 90
+    },
+    {
+      "epoch": 1.5042194092827004,
+      "eval_loss": 1.0232045650482178,
+      "eval_runtime": 74.0589,
+      "eval_samples_per_second": 13.908,
+      "eval_steps_per_second": 13.908,
+      "step": 90
+    },
+    {
+      "epoch": 1.521097046413502,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.1454529602626336e-05,
+      "loss": 1.0051,
+      "step": 91
+    },
+    {
+      "epoch": 1.5379746835443038,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.126569069290562e-05,
+      "loss": 1.023,
+      "step": 92
+    },
+    {
+      "epoch": 1.5548523206751055,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.107564106009286e-05,
+      "loss": 1.012,
+      "step": 93
+    },
+    {
+      "epoch": 1.5717299578059072,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.0884417427590217e-05,
+      "loss": 1.0136,
+      "step": 94
+    },
+    {
+      "epoch": 1.5886075949367089,
+      "grad_norm": 0.0546875,
+      "learning_rate": 2.0692056745652483e-05,
+      "loss": 1.0194,
+      "step": 95
+    },
+    {
+      "epoch": 1.6054852320675106,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 2.0498596184247196e-05,
+      "loss": 1.0089,
+      "step": 96
+    },
+    {
+      "epoch": 1.6223628691983123,
+      "grad_norm": 0.054931640625,
+      "learning_rate": 2.030407312587224e-05,
+      "loss": 1.0226,
+      "step": 97
+    },
+    {
+      "epoch": 1.6392405063291138,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 2.010852515833242e-05,
+      "loss": 1.0219,
+      "step": 98
+    },
+    {
+      "epoch": 1.6561181434599157,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 1.9911990067476336e-05,
+      "loss": 1.0035,
+      "step": 99
+    },
+    {
+      "epoch": 1.6729957805907172,
+      "grad_norm": 0.055908203125,
+      "learning_rate": 1.9714505829895004e-05,
+      "loss": 1.0052,
+      "step": 100
+    },
+    {
+      "epoch": 1.689873417721519,
+      "grad_norm": 0.05712890625,
+      "learning_rate": 1.951611060558363e-05,
+      "loss": 1.0175,
+      "step": 101
+    },
+    {
+      "epoch": 1.7067510548523206,
+      "grad_norm": 0.056396484375,
+      "learning_rate": 1.9316842730567902e-05,
+      "loss": 1.0099,
+      "step": 102
+    },
+    {
+      "epoch": 1.7236286919831225,
+      "grad_norm": 0.05615234375,
+      "learning_rate": 1.9116740709496334e-05,
+      "loss": 0.998,
+      "step": 103
+    },
+    {
+      "epoch": 1.740506329113924,
+      "grad_norm": 0.05615234375,
+      "learning_rate": 1.8915843208199967e-05,
+      "loss": 0.996,
+      "step": 104
+    },
+    {
+      "epoch": 1.7573839662447257,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 1.8714189046220946e-05,
+      "loss": 1.009,
+      "step": 105
+    },
+    {
+      "epoch": 1.7742616033755274,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 1.851181718931141e-05,
+      "loss": 1.0127,
+      "step": 106
+    },
+    {
+      "epoch": 1.7911392405063291,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 1.830876674190411e-05,
+      "loss": 1.0107,
+      "step": 107
+    },
+    {
+      "epoch": 1.8080168776371308,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 1.8105076939556238e-05,
+      "loss": 1.0264,
+      "step": 108
+    },
+    {
+      "epoch": 1.8248945147679325,
+      "grad_norm": 0.056884765625,
+      "learning_rate": 1.790078714136792e-05,
+      "loss": 1.0068,
+      "step": 109
+    },
+    {
+      "epoch": 1.8417721518987342,
+      "grad_norm": 0.056640625,
+      "learning_rate": 1.769593682237682e-05,
+      "loss": 1.0094,
+      "step": 110
+    },
+    {
+      "epoch": 1.8586497890295357,
+      "grad_norm": 0.057861328125,
+      "learning_rate": 1.7490565565930382e-05,
+      "loss": 1.0135,
+      "step": 111
+    },
+    {
+      "epoch": 1.8755274261603376,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.7284713056037074e-05,
+      "loss": 0.993,
+      "step": 112
+    },
+    {
+      "epoch": 1.8924050632911391,
+      "grad_norm": 0.056884765625,
+      "learning_rate": 1.7078419069698283e-05,
+      "loss": 1.015,
+      "step": 113
+    },
+    {
+      "epoch": 1.909282700421941,
+      "grad_norm": 0.055908203125,
+      "learning_rate": 1.687172346922213e-05,
+      "loss": 1.0043,
+      "step": 114
+    },
+    {
+      "epoch": 1.9261603375527425,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.6664666194520873e-05,
+      "loss": 0.9959,
+      "step": 115
+    },
+    {
+      "epoch": 1.9430379746835444,
+      "grad_norm": 0.0625,
+      "learning_rate": 1.645728725539329e-05,
+      "loss": 1.0177,
+      "step": 116
+    },
+    {
+      "epoch": 1.959915611814346,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 1.6249626723793572e-05,
+      "loss": 1.033,
+      "step": 117
+    },
+    {
+      "epoch": 1.9767932489451476,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 1.6041724726088187e-05,
+      "loss": 1.0155,
+      "step": 118
+    },
+    {
+      "epoch": 1.9936708860759493,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 1.5833621435302247e-05,
+      "loss": 1.0167,
+      "step": 119
+    },
+    {
+      "epoch": 2.010548523206751,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.5625357063356825e-05,
+      "loss": 1.0082,
+      "step": 120
+    },
+    {
+      "epoch": 2.010548523206751,
+      "eval_loss": 1.0127062797546387,
+      "eval_runtime": 74.0711,
+      "eval_samples_per_second": 13.906,
+      "eval_steps_per_second": 13.906,
+      "step": 120
+    },
+    {
+      "epoch": 2.0147679324894514,
+      "grad_norm": 0.1865234375,
+      "learning_rate": 1.541697185329881e-05,
+      "loss": 1.6592,
+      "step": 121
+    },
+    {
+      "epoch": 2.0316455696202533,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.5208506071524727e-05,
+      "loss": 1.0041,
+      "step": 122
+    },
+    {
+      "epoch": 2.048523206751055,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 1.5e-05,
+      "loss": 1.0116,
+      "step": 123
+    },
+    {
+      "epoch": 2.0654008438818567,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.4791493928475275e-05,
+      "loss": 1.0026,
+      "step": 124
+    },
+    {
+      "epoch": 2.0822784810126582,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 1.4583028146701191e-05,
+      "loss": 1.0122,
+      "step": 125
+    },
+    {
+      "epoch": 2.0991561181434597,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 1.437464293664318e-05,
+      "loss": 1.0024,
+      "step": 126
+    },
+    {
+      "epoch": 2.1160337552742616,
+      "grad_norm": 0.060546875,
+      "learning_rate": 1.4166378564697757e-05,
+      "loss": 1.0092,
+      "step": 127
+    },
+    {
+      "epoch": 2.132911392405063,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 1.3958275273911812e-05,
+      "loss": 1.0048,
+      "step": 128
+    },
+    {
+      "epoch": 2.149789029535865,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 1.375037327620643e-05,
+      "loss": 0.9921,
+      "step": 129
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 1.3542712744606712e-05,
+      "loss": 1.0117,
+      "step": 130
+    },
+    {
+      "epoch": 2.1835443037974684,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.3335333805479126e-05,
+      "loss": 0.9965,
+      "step": 131
+    },
+    {
+      "epoch": 2.20042194092827,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 1.3128276530777874e-05,
+      "loss": 1.0108,
+      "step": 132
+    },
+    {
+      "epoch": 2.217299578059072,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 1.292158093030172e-05,
+      "loss": 1.0029,
+      "step": 133
+    },
+    {
+      "epoch": 2.2341772151898733,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 1.2715286943962925e-05,
+      "loss": 0.9958,
+      "step": 134
+    },
+    {
+      "epoch": 2.2510548523206753,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 1.2509434434069625e-05,
+      "loss": 1.0054,
+      "step": 135
+    },
+    {
+      "epoch": 2.2679324894514767,
+      "grad_norm": 0.0576171875,
+      "learning_rate": 1.2304063177623182e-05,
+      "loss": 0.9837,
+      "step": 136
+    },
+    {
+      "epoch": 2.2848101265822787,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 1.2099212858632083e-05,
+      "loss": 1.0014,
+      "step": 137
+    },
+    {
+      "epoch": 2.30168776371308,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.1894923060443763e-05,
+      "loss": 0.9816,
+      "step": 138
+    },
+    {
+      "epoch": 2.318565400843882,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.169123325809589e-05,
+      "loss": 1.0021,
+      "step": 139
+    },
+    {
+      "epoch": 2.3354430379746836,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.1488182810688593e-05,
+      "loss": 1.0005,
+      "step": 140
+    },
+    {
+      "epoch": 2.352320675105485,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 1.1285810953779057e-05,
+      "loss": 1.0167,
+      "step": 141
+    },
+    {
+      "epoch": 2.369198312236287,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 1.1084156791800036e-05,
+      "loss": 1.0146,
+      "step": 142
+    },
+    {
+      "epoch": 2.3860759493670884,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.0883259290503665e-05,
+      "loss": 1.0024,
+      "step": 143
+    },
+    {
+      "epoch": 2.4029535864978904,
+      "grad_norm": 0.0576171875,
+      "learning_rate": 1.0683157269432097e-05,
+      "loss": 0.9959,
+      "step": 144
+    },
+    {
+      "epoch": 2.419831223628692,
+      "grad_norm": 0.060546875,
+      "learning_rate": 1.0483889394416373e-05,
+      "loss": 1.0059,
+      "step": 145
+    },
+    {
+      "epoch": 2.4367088607594938,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 1.0285494170104996e-05,
+      "loss": 0.983,
+      "step": 146
+    },
+    {
+      "epoch": 2.4535864978902953,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 1.0088009932523664e-05,
+      "loss": 1.0116,
+      "step": 147
+    },
+    {
+      "epoch": 2.470464135021097,
+      "grad_norm": 0.061279296875,
+      "learning_rate": 9.891474841667585e-06,
+      "loss": 1.0136,
+      "step": 148
+    },
+    {
+      "epoch": 2.4873417721518987,
+      "grad_norm": 0.057861328125,
+      "learning_rate": 9.695926874127765e-06,
+      "loss": 0.9937,
+      "step": 149
+    },
+    {
+      "epoch": 2.5042194092827,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 9.501403815752813e-06,
+      "loss": 0.9946,
+      "step": 150
+    },
+    {
+      "epoch": 2.5042194092827,
+      "eval_loss": 1.0074498653411865,
+      "eval_runtime": 74.0482,
+      "eval_samples_per_second": 13.91,
+      "eval_steps_per_second": 13.91,
+      "step": 150
+    },
+    {
+      "epoch": 2.521097046413502,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 9.307943254347521e-06,
+      "loss": 1.0043,
+      "step": 151
+    },
+    {
+      "epoch": 2.537974683544304,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 9.115582572409789e-06,
+      "loss": 1.0125,
+      "step": 152
+    },
+    {
+      "epoch": 2.5548523206751055,
+      "grad_norm": 0.05859375,
+      "learning_rate": 8.92435893990714e-06,
+      "loss": 0.9753,
+      "step": 153
+    },
+    {
+      "epoch": 2.571729957805907,
+      "grad_norm": 0.060546875,
+      "learning_rate": 8.734309307094382e-06,
+      "loss": 0.9959,
+      "step": 154
+    },
+    {
+      "epoch": 2.588607594936709,
+      "grad_norm": 0.061279296875,
+      "learning_rate": 8.545470397373665e-06,
+      "loss": 1.0158,
+      "step": 155
+    },
+    {
+      "epoch": 2.605485232067511,
+      "grad_norm": 0.062255859375,
+      "learning_rate": 8.357878700198407e-06,
+      "loss": 1.0001,
+      "step": 156
+    },
+    {
+      "epoch": 2.6223628691983123,
+      "grad_norm": 0.060546875,
+      "learning_rate": 8.171570464022419e-06,
+      "loss": 0.9963,
+      "step": 157
+    },
+    {
+      "epoch": 2.6392405063291138,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 7.986581689295577e-06,
+      "loss": 0.968,
+      "step": 158
+    },
+    {
+      "epoch": 2.6561181434599157,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 7.802948121507462e-06,
+      "loss": 0.9872,
+      "step": 159
+    },
+    {
+      "epoch": 2.672995780590717,
+      "grad_norm": 0.0625,
+      "learning_rate": 7.620705244280208e-06,
+      "loss": 1.0181,
+      "step": 160
+    },
+    {
+      "epoch": 2.689873417721519,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 7.439888272512004e-06,
+      "loss": 1.0057,
+      "step": 161
+    },
+    {
+      "epoch": 2.7067510548523206,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 7.260532145572487e-06,
+      "loss": 0.9985,
+      "step": 162
+    },
+    {
+      "epoch": 2.7236286919831225,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 7.082671520551391e-06,
+      "loss": 0.9973,
+      "step": 163
+    },
+    {
+      "epoch": 2.740506329113924,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 6.906340765561734e-06,
+      "loss": 0.991,
+      "step": 164
+    },
+    {
+      "epoch": 2.757383966244726,
+      "grad_norm": 0.060546875,
+      "learning_rate": 6.731573953098851e-06,
+      "loss": 0.9979,
+      "step": 165
+    },
+    {
+      "epoch": 2.7742616033755274,
+      "grad_norm": 0.060546875,
+      "learning_rate": 6.558404853456545e-06,
+      "loss": 1.0096,
+      "step": 166
+    },
+    {
+      "epoch": 2.791139240506329,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 6.38686692820163e-06,
+      "loss": 0.9981,
+      "step": 167
+    },
+    {
+      "epoch": 2.808016877637131,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 6.2169933237081386e-06,
+      "loss": 1.0169,
+      "step": 168
+    },
+    {
+      "epoch": 2.8248945147679327,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 6.048816864752422e-06,
+      "loss": 0.9934,
+      "step": 169
+    },
+    {
+      "epoch": 2.8417721518987342,
+      "grad_norm": 0.05859375,
+      "learning_rate": 5.882370048170403e-06,
+      "loss": 0.9913,
+      "step": 170
+    },
+    {
+      "epoch": 2.8586497890295357,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 5.71768503657819e-06,
+      "loss": 1.0107,
+      "step": 171
+    },
+    {
+      "epoch": 2.8755274261603376,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 5.55479365215729e-06,
+      "loss": 1.0098,
+      "step": 172
+    },
+    {
+      "epoch": 2.892405063291139,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 5.393727370505569e-06,
+      "loss": 1.0123,
+      "step": 173
+    },
+    {
+      "epoch": 2.909282700421941,
+      "grad_norm": 0.060546875,
+      "learning_rate": 5.234517314555213e-06,
+      "loss": 0.9837,
+      "step": 174
+    },
+    {
+      "epoch": 2.9261603375527425,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 5.077194248558827e-06,
+      "loss": 0.9865,
+      "step": 175
+    },
+    {
+      "epoch": 2.9430379746835444,
+      "grad_norm": 0.058349609375,
+      "learning_rate": 4.921788572144841e-06,
+      "loss": 0.995,
+      "step": 176
+    },
+    {
+      "epoch": 2.959915611814346,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 4.768330314443367e-06,
+      "loss": 1.0009,
+      "step": 177
+    },
+    {
+      "epoch": 2.976793248945148,
+      "grad_norm": 0.060546875,
+      "learning_rate": 4.616849128283658e-06,
+      "loss": 1.0016,
+      "step": 178
+    },
+    {
+      "epoch": 2.9936708860759493,
+      "grad_norm": 0.0625,
+      "learning_rate": 4.4673742844642716e-06,
+      "loss": 0.9979,
+      "step": 179
+    },
+    {
+      "epoch": 3.010548523206751,
+      "grad_norm": 0.062255859375,
+      "learning_rate": 4.319934666097055e-06,
+      "loss": 0.9826,
+      "step": 180
+    },
+    {
+      "epoch": 3.010548523206751,
+      "eval_loss": 1.0056920051574707,
+      "eval_runtime": 74.0404,
+      "eval_samples_per_second": 13.911,
+      "eval_steps_per_second": 13.911,
+      "step": 180
+    },
+    {
+      "epoch": 3.0126582278481013,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 4.174558763026048e-06,
+      "loss": 1.0021,
+      "step": 181
+    },
+    {
+      "epoch": 3.029535864978903,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 4.031274666322372e-06,
+      "loss": 0.9997,
+      "step": 182
+    },
+    {
+      "epoch": 3.0464135021097047,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 3.8901100628561755e-06,
+      "loss": 1.0048,
+      "step": 183
+    },
+    {
+      "epoch": 3.0632911392405062,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 3.7510922299466818e-06,
+      "loss": 0.9874,
+      "step": 184
+    },
+    {
+      "epoch": 3.080168776371308,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 3.6142480300913805e-06,
+      "loss": 1.0054,
+      "step": 185
+    },
+    {
+      "epoch": 3.0970464135021096,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 3.4796039057753703e-06,
+      "loss": 0.9991,
+      "step": 186
+    },
+    {
+      "epoch": 3.1139240506329116,
+      "grad_norm": 0.05859375,
+      "learning_rate": 3.3471858743618615e-06,
+      "loss": 0.9941,
+      "step": 187
+    },
+    {
+      "epoch": 3.130801687763713,
+      "grad_norm": 0.061767578125,
+      "learning_rate": 3.217019523064825e-06,
+      "loss": 1.0032,
+      "step": 188
+    },
+    {
+      "epoch": 3.147679324894515,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 3.089130004004754e-06,
+      "loss": 0.9965,
+      "step": 189
+    },
+    {
+      "epoch": 3.1645569620253164,
+      "grad_norm": 0.05908203125,
+      "learning_rate": 2.96354202934853e-06,
+      "loss": 0.9954,
+      "step": 190
+    },
+    {
+      "epoch": 3.181434599156118,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 2.8402798665342412e-06,
+      "loss": 0.9938,
+      "step": 191
+    },
+    {
+      "epoch": 3.19831223628692,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 2.7193673335819893e-06,
+      "loss": 0.9967,
+      "step": 192
+    },
+    {
+      "epoch": 3.2151898734177213,
+      "grad_norm": 0.061279296875,
+      "learning_rate": 2.600827794491524e-06,
+      "loss": 1.0009,
+      "step": 193
+    },
+    {
+      "epoch": 3.2320675105485233,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 2.4846841547275916e-06,
+      "loss": 0.9902,
+      "step": 194
+    },
+    {
+      "epoch": 3.2489451476793247,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 2.3709588567939118e-06,
+      "loss": 0.9915,
+      "step": 195
+    },
+    {
+      "epoch": 3.2658227848101267,
+      "grad_norm": 0.061767578125,
+      "learning_rate": 2.259673875896585e-06,
+      "loss": 0.993,
+      "step": 196
+    },
+    {
+      "epoch": 3.282700421940928,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 2.150850715697823e-06,
+      "loss": 1.0027,
+      "step": 197
+    },
+    {
+      "epoch": 3.29957805907173,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 2.044510404160774e-06,
+      "loss": 0.9874,
+      "step": 198
+    },
+    {
+      "epoch": 3.3164556962025316,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 1.9406734894862848e-06,
+      "loss": 1.6607,
+      "step": 199
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 1.8393600361423534e-06,
+      "loss": 1.002,
+      "step": 200
+    },
+    {
+      "epoch": 3.350210970464135,
+      "grad_norm": 0.06103515625,
+      "learning_rate": 1.7405896209870665e-06,
+      "loss": 1.0005,
+      "step": 201
+    },
+    {
+      "epoch": 3.367088607594937,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 1.6443813294857452e-06,
+      "loss": 0.9842,
+      "step": 202
+    },
+    {
+      "epoch": 3.3839662447257384,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 1.550753752023053e-06,
+      "loss": 0.9877,
+      "step": 203
+    },
+    {
+      "epoch": 3.40084388185654,
+      "grad_norm": 0.060546875,
+      "learning_rate": 1.459724980310767e-06,
+      "loss": 0.991,
+      "step": 204
+    },
+    {
+      "epoch": 3.4177215189873418,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 1.3713126038918977e-06,
+      "loss": 0.9839,
+      "step": 205
+    },
+    {
+      "epoch": 3.4345991561181437,
+      "grad_norm": 0.060302734375,
+      "learning_rate": 1.2855337067418576e-06,
+      "loss": 0.9977,
+      "step": 206
+    },
+    {
+      "epoch": 3.451476793248945,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 1.2024048639673225e-06,
+      "loss": 0.9981,
+      "step": 207
+    },
+    {
+      "epoch": 3.4683544303797467,
+      "grad_norm": 0.059814453125,
+      "learning_rate": 1.1219421386033958e-06,
+      "loss": 1.0007,
+      "step": 208
+    },
+    {
+      "epoch": 3.4852320675105486,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 1.0441610785097471e-06,
+      "loss": 0.9977,
+      "step": 209
+    },
+    {
+      "epoch": 3.50210970464135,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 9.690767133662976e-07,
+      "loss": 0.9898,
+      "step": 210
+    },
+    {
+      "epoch": 3.50210970464135,
+      "eval_loss": 1.0054612159729004,
+      "eval_runtime": 74.055,
+      "eval_samples_per_second": 13.909,
+      "eval_steps_per_second": 13.909,
+      "step": 210
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 236,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.905260842110157e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-210/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47fe3d8f86dd99270fe973ee57cf8bc56524ac1c04eb16ea3572e34a069a173f
+size 6072

checkpoint-236/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /workspace/data/models/Qwen2-7B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-236/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/data/models/Qwen2-7B",
+  "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": [
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-236/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9d908415603516e2c6b008cd73797354cdb39ec4cbe0fe8b67f965c3e2e248
+size 161533584

checkpoint-236/added_tokens.json

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

checkpoint-236/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36bf5d761c2d90706ab47dab1d09eff6644e44da1c6c5e3291f1629c9bd09717
+size 323292010

checkpoint-236/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745ac19464ee4024c970aee16279b92c9cc18edf13e5d5f1fb84d36ccbb42966
+size 14244