End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,161 @@
+---
+library_name: peft
+base_model: peft-internal-testing/tiny-dummy-qwen2
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 284f2d0e-bfda-4337-926c-cea681a504a8
+  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+adapter: lora
+base_model: peft-internal-testing/tiny-dummy-qwen2
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - cb723d44360708a8_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/cb723d44360708a8_train_data.json
+  type:
+    field_instruction: title
+    field_output: content
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_table_size: null
+evals_per_epoch: 4
+flash_attention: false
+fp16: true
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: true
+group_by_length: false
+hub_model_id: null
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+load_in_4bit: false
+load_in_8bit: false
+local_rank: 0
+logging_steps: 3
+lora_alpha: 128
+lora_dropout: 0.1
+lora_fan_in_fan_out: true
+lora_model_dir: null
+lora_r: 64
+lora_target_linear: true
+lr_scheduler: cosine
+max_steps: 500
+micro_batch_size: 8
+mlflow_experiment_name: /tmp/cb723d44360708a8_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 3
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: false
+sample_packing: false
+saves_per_epoch: 4
+sequence_len: 1024
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: sn56-miner
+wandb_mode: disabled
+wandb_name: null
+wandb_project: god
+wandb_run: wb6u
+wandb_runid: null
+warmup_steps: 10
+weight_decay: 0.01
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 284f2d0e-bfda-4337-926c-cea681a504a8
+
+This model is a fine-tuned version of [peft-internal-testing/tiny-dummy-qwen2](https://huggingface.co/peft-internal-testing/tiny-dummy-qwen2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 11.9207
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 441
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0068 | 1    | 11.9315         |
+| 11.9261       | 0.2517 | 37   | 11.9249         |
+| 11.9229       | 0.5034 | 74   | 11.9225         |
+| 11.9227       | 0.7551 | 111  | 11.9223         |
+| 11.9227       | 1.0068 | 148  | 11.9219         |
+| 11.9226       | 1.2585 | 185  | 11.9214         |
+| 11.9217       | 1.5102 | 222  | 11.9211         |
+| 11.9217       | 1.7619 | 259  | 11.9209         |
+| 11.9215       | 2.0136 | 296  | 11.9208         |
+| 11.9214       | 2.2653 | 333  | 11.9207         |
+| 11.9211       | 2.5170 | 370  | 11.9207         |
+| 11.9211       | 2.7687 | 407  | 11.9207         |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f684d884f32dff3e2f3b26576cbd9fbfc93df14a585cae65b64dd6e2249345
+size 100226

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85d034a32597d1b00c1577c94520a1eedbf1b3b031a431832226ddcef425bc4
+size 93608

added_tokens.json

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: peft-internal-testing/tiny-dummy-qwen2
+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 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85d034a32597d1b00c1577c94520a1eedbf1b3b031a431832226ddcef425bc4
+size 93608

last-checkpoint/added_tokens.json

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

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e4cc7bd3625ffd6d4a1921c6492defea3dcacb643d18fdecd1652217ba134c
+size 197158

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3acd41253109b861c5c48977cff6b2a1d8e9e5bcad10432ac1e3be0575ee7f
+size 14960

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf7a09346e979e993ba58256f5fda0e7cfb2721276d013ddfa9e6716b6197f3
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c523ab57d8c44012691e0fa8da2e68b2546e13077a80a608be1d54527997c79
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027ba72f371decbec68b311970696ea39d299ff1cf16a9eb9f8b566a331f0ad8
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c76042fb6618d1d31186487d78be5a9adc9f6fd4e9f0432d42ae90c7689878
+size 1064

last-checkpoint/special_tokens_map.json

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

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1158 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 37,
+  "global_step": 441,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006802721088435374,
+      "eval_loss": 11.931451797485352,
+      "eval_runtime": 2.6548,
+      "eval_samples_per_second": 372.912,
+      "eval_steps_per_second": 11.677,
+      "step": 1
+    },
+    {
+      "epoch": 0.02040816326530612,
+      "grad_norm": 0.01636049710214138,
+      "learning_rate": 3e-05,
+      "loss": 11.9317,
+      "step": 3
+    },
+    {
+      "epoch": 0.04081632653061224,
+      "grad_norm": 0.018158216029405594,
+      "learning_rate": 6e-05,
+      "loss": 11.9316,
+      "step": 6
+    },
+    {
+      "epoch": 0.061224489795918366,
+      "grad_norm": 0.017022155225276947,
+      "learning_rate": 9e-05,
+      "loss": 11.9314,
+      "step": 9
+    },
+    {
+      "epoch": 0.08163265306122448,
+      "grad_norm": 0.020832879468798637,
+      "learning_rate": 9.999468702816552e-05,
+      "loss": 11.9312,
+      "step": 12
+    },
+    {
+      "epoch": 0.10204081632653061,
+      "grad_norm": 0.03084990754723549,
+      "learning_rate": 9.996679701338662e-05,
+      "loss": 11.9309,
+      "step": 15
+    },
+    {
+      "epoch": 0.12244897959183673,
+      "grad_norm": 0.034195929765701294,
+      "learning_rate": 9.991501503086435e-05,
+      "loss": 11.9308,
+      "step": 18
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.0448000393807888,
+      "learning_rate": 9.983936584050992e-05,
+      "loss": 11.9304,
+      "step": 21
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.05750146135687828,
+      "learning_rate": 9.973988561450411e-05,
+      "loss": 11.9299,
+      "step": 24
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": 0.06743118911981583,
+      "learning_rate": 9.961662192000138e-05,
+      "loss": 11.9293,
+      "step": 27
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 0.07145452499389648,
+      "learning_rate": 9.946963369638525e-05,
+      "loss": 11.928,
+      "step": 30
+    },
+    {
+      "epoch": 0.22448979591836735,
+      "grad_norm": 0.07963183522224426,
+      "learning_rate": 9.929899122708609e-05,
+      "loss": 11.9275,
+      "step": 33
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 0.06796199083328247,
+      "learning_rate": 9.91047761059745e-05,
+      "loss": 11.9261,
+      "step": 36
+    },
+    {
+      "epoch": 0.25170068027210885,
+      "eval_loss": 11.9249267578125,
+      "eval_runtime": 2.8686,
+      "eval_samples_per_second": 345.112,
+      "eval_steps_per_second": 10.807,
+      "step": 37
+    },
+    {
+      "epoch": 0.2653061224489796,
+      "grad_norm": 0.04962217062711716,
+      "learning_rate": 9.88870811983468e-05,
+      "loss": 11.925,
+      "step": 39
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.042071931064128876,
+      "learning_rate": 9.86460105965207e-05,
+      "loss": 11.9244,
+      "step": 42
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 0.03425384312868118,
+      "learning_rate": 9.838167957006295e-05,
+      "loss": 11.9248,
+      "step": 45
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.035133086144924164,
+      "learning_rate": 9.809421451067233e-05,
+      "loss": 11.9241,
+      "step": 48
+    },
+    {
+      "epoch": 0.3469387755102041,
+      "grad_norm": 0.02793348953127861,
+      "learning_rate": 9.778375287174465e-05,
+      "loss": 11.9238,
+      "step": 51
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 0.02287479303777218,
+      "learning_rate": 9.745044310264839e-05,
+      "loss": 11.9234,
+      "step": 54
+    },
+    {
+      "epoch": 0.3877551020408163,
+      "grad_norm": 0.016594573855400085,
+      "learning_rate": 9.70944445777427e-05,
+      "loss": 11.9232,
+      "step": 57
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.013930396176874638,
+      "learning_rate": 9.671592752017138e-05,
+      "loss": 11.9233,
+      "step": 60
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.015639444813132286,
+      "learning_rate": 9.631507292046955e-05,
+      "loss": 11.9231,
+      "step": 63
+    },
+    {
+      "epoch": 0.4489795918367347,
+      "grad_norm": 0.013282309286296368,
+      "learning_rate": 9.589207245002178e-05,
+      "loss": 11.9229,
+      "step": 66
+    },
+    {
+      "epoch": 0.46938775510204084,
+      "grad_norm": 0.011825870722532272,
+      "learning_rate": 9.544712836941308e-05,
+      "loss": 11.9232,
+      "step": 69
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.014082890003919601,
+      "learning_rate": 9.498045343171664e-05,
+      "loss": 11.9229,
+      "step": 72
+    },
+    {
+      "epoch": 0.5034013605442177,
+      "eval_loss": 11.922492027282715,
+      "eval_runtime": 2.7156,
+      "eval_samples_per_second": 364.561,
+      "eval_steps_per_second": 11.416,
+      "step": 74
+    },
+    {
+      "epoch": 0.5102040816326531,
+      "grad_norm": 0.012438306584954262,
+      "learning_rate": 9.449227078076443e-05,
+      "loss": 11.9226,
+      "step": 75
+    },
+    {
+      "epoch": 0.5306122448979592,
+      "grad_norm": 0.008214130997657776,
+      "learning_rate": 9.398281384444956e-05,
+      "loss": 11.9228,
+      "step": 78
+    },
+    {
+      "epoch": 0.5510204081632653,
+      "grad_norm": 0.008153177797794342,
+      "learning_rate": 9.345232622311092e-05,
+      "loss": 11.9228,
+      "step": 81
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.00989192258566618,
+      "learning_rate": 9.290106157305423e-05,
+      "loss": 11.9225,
+      "step": 84
+    },
+    {
+      "epoch": 0.5918367346938775,
+      "grad_norm": 0.008665865287184715,
+      "learning_rate": 9.23292834852644e-05,
+      "loss": 11.9233,
+      "step": 87
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 0.0082166139036417,
+      "learning_rate": 9.173726535936768e-05,
+      "loss": 11.9228,
+      "step": 90
+    },
+    {
+      "epoch": 0.6326530612244898,
+      "grad_norm": 0.0089117381721735,
+      "learning_rate": 9.112529027290382e-05,
+      "loss": 11.9229,
+      "step": 93
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 0.009443915449082851,
+      "learning_rate": 9.049365084597059e-05,
+      "loss": 11.9229,
+      "step": 96
+    },
+    {
+      "epoch": 0.673469387755102,
+      "grad_norm": 0.007972587831318378,
+      "learning_rate": 8.984264910130535e-05,
+      "loss": 11.9226,
+      "step": 99
+    },
+    {
+      "epoch": 0.6938775510204082,
+      "grad_norm": 0.008118909783661366,
+      "learning_rate": 8.917259631987098e-05,
+      "loss": 11.923,
+      "step": 102
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.009298138320446014,
+      "learning_rate": 8.848381289201459e-05,
+      "loss": 11.9228,
+      "step": 105
+    },
+    {
+      "epoch": 0.7346938775510204,
+      "grad_norm": 0.008324788883328438,
+      "learning_rate": 8.77766281642708e-05,
+      "loss": 11.9224,
+      "step": 108
+    },
+    {
+      "epoch": 0.7551020408163265,
+      "grad_norm": 0.008361688815057278,
+      "learning_rate": 8.705138028188228e-05,
+      "loss": 11.9227,
+      "step": 111
+    },
+    {
+      "epoch": 0.7551020408163265,
+      "eval_loss": 11.922290802001953,
+      "eval_runtime": 2.7455,
+      "eval_samples_per_second": 360.59,
+      "eval_steps_per_second": 11.291,
+      "step": 111
+    },
+    {
+      "epoch": 0.7755102040816326,
+      "grad_norm": 0.012222371064126492,
+      "learning_rate": 8.630841602711344e-05,
+      "loss": 11.9227,
+      "step": 114
+    },
+    {
+      "epoch": 0.7959183673469388,
+      "grad_norm": 0.009516862221062183,
+      "learning_rate": 8.554809065343397e-05,
+      "loss": 11.9227,
+      "step": 117
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.01142488420009613,
+      "learning_rate": 8.477076771565203e-05,
+      "loss": 11.9224,
+      "step": 120
+    },
+    {
+      "epoch": 0.8367346938775511,
+      "grad_norm": 0.01184010412544012,
+      "learning_rate": 8.3976818896078e-05,
+      "loss": 11.9227,
+      "step": 123
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.010025064460933208,
+      "learning_rate": 8.316662382680202e-05,
+      "loss": 11.9226,
+      "step": 126
+    },
+    {
+      "epoch": 0.8775510204081632,
+      "grad_norm": 0.007526579778641462,
+      "learning_rate": 8.234056990817024e-05,
+      "loss": 11.9226,
+      "step": 129
+    },
+    {
+      "epoch": 0.8979591836734694,
+      "grad_norm": 0.010171515867114067,
+      "learning_rate": 8.14990521235468e-05,
+      "loss": 11.9228,
+      "step": 132
+    },
+    {
+      "epoch": 0.9183673469387755,
+      "grad_norm": 0.010467471554875374,
+      "learning_rate": 8.064247285044972e-05,
+      "loss": 11.9226,
+      "step": 135
+    },
+    {
+      "epoch": 0.9387755102040817,
+      "grad_norm": 0.008835887536406517,
+      "learning_rate": 7.977124166815133e-05,
+      "loss": 11.9228,
+      "step": 138
+    },
+    {
+      "epoch": 0.9591836734693877,
+      "grad_norm": 0.010331097058951855,
+      "learning_rate": 7.88857751618352e-05,
+      "loss": 11.9224,
+      "step": 141
+    },
+    {
+      "epoch": 0.9795918367346939,
+      "grad_norm": 0.012341076508164406,
+      "learning_rate": 7.798649672340295e-05,
+      "loss": 11.9229,
+      "step": 144
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.014008646830916405,
+      "learning_rate": 7.707383634902659e-05,
+      "loss": 11.9227,
+      "step": 147
+    },
+    {
+      "epoch": 1.0068027210884354,
+      "eval_loss": 11.921862602233887,
+      "eval_runtime": 2.7724,
+      "eval_samples_per_second": 357.086,
+      "eval_steps_per_second": 11.181,
+      "step": 148
+    },
+    {
+      "epoch": 1.0204081632653061,
+      "grad_norm": 0.011518532410264015,
+      "learning_rate": 7.614823043354287e-05,
+      "loss": 11.9224,
+      "step": 150
+    },
+    {
+      "epoch": 1.0408163265306123,
+      "grad_norm": 0.010834796354174614,
+      "learning_rate": 7.521012156178808e-05,
+      "loss": 11.9222,
+      "step": 153
+    },
+    {
+      "epoch": 1.0612244897959184,
+      "grad_norm": 0.010119671002030373,
+      "learning_rate": 7.425995829697305e-05,
+      "loss": 11.9226,
+      "step": 156
+    },
+    {
+      "epoch": 1.0816326530612246,
+      "grad_norm": 0.008356979116797447,
+      "learning_rate": 7.32981949661996e-05,
+      "loss": 11.9221,
+      "step": 159
+    },
+    {
+      "epoch": 1.1020408163265305,
+      "grad_norm": 0.011819167993962765,
+      "learning_rate": 7.232529144322087e-05,
+      "loss": 11.9226,
+      "step": 162
+    },
+    {
+      "epoch": 1.1224489795918366,
+      "grad_norm": 0.0105531495064497,
+      "learning_rate": 7.134171292854956e-05,
+      "loss": 11.9227,
+      "step": 165
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.01237469632178545,
+      "learning_rate": 7.034792972701911e-05,
+      "loss": 11.9224,
+      "step": 168
+    },
+    {
+      "epoch": 1.163265306122449,
+      "grad_norm": 0.013601982034742832,
+      "learning_rate": 6.934441702290412e-05,
+      "loss": 11.9221,
+      "step": 171
+    },
+    {
+      "epoch": 1.183673469387755,
+      "grad_norm": 0.008788252249360085,
+      "learning_rate": 6.833165465270785e-05,
+      "loss": 11.922,
+      "step": 174
+    },
+    {
+      "epoch": 1.2040816326530612,
+      "grad_norm": 0.010858463123440742,
+      "learning_rate": 6.7310126875725e-05,
+      "loss": 11.9218,
+      "step": 177
+    },
+    {
+      "epoch": 1.2244897959183674,
+      "grad_norm": 0.00929215457290411,
+      "learning_rate": 6.628032214248983e-05,
+      "loss": 11.9219,
+      "step": 180
+    },
+    {
+      "epoch": 1.2448979591836735,
+      "grad_norm": 0.01050562970340252,
+      "learning_rate": 6.524273286122018e-05,
+      "loss": 11.9226,
+      "step": 183
+    },
+    {
+      "epoch": 1.2585034013605443,
+      "eval_loss": 11.921433448791504,
+      "eval_runtime": 2.6878,
+      "eval_samples_per_second": 368.332,
+      "eval_steps_per_second": 11.534,
+      "step": 185
+    },
+    {
+      "epoch": 1.2653061224489797,
+      "grad_norm": 0.00961016584187746,
+      "learning_rate": 6.419785516236907e-05,
+      "loss": 11.9219,
+      "step": 186
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.009320979937911034,
+      "learning_rate": 6.314618866139657e-05,
+      "loss": 11.922,
+      "step": 189
+    },
+    {
+      "epoch": 1.306122448979592,
+      "grad_norm": 0.009897406212985516,
+      "learning_rate": 6.208823621987516e-05,
+      "loss": 11.922,
+      "step": 192
+    },
+    {
+      "epoch": 1.3265306122448979,
+      "grad_norm": 0.00750324223190546,
+      "learning_rate": 6.1024503705043e-05,
+      "loss": 11.9219,
+      "step": 195
+    },
+    {
+      "epoch": 1.346938775510204,
+      "grad_norm": 0.01272102352231741,
+      "learning_rate": 5.995549974792016e-05,
+      "loss": 11.9221,
+      "step": 198
+    },
+    {
+      "epoch": 1.3673469387755102,
+      "grad_norm": 0.013028099201619625,
+      "learning_rate": 5.888173550010301e-05,
+      "loss": 11.9213,
+      "step": 201
+    },
+    {
+      "epoch": 1.3877551020408163,
+      "grad_norm": 0.008812615647912025,
+      "learning_rate": 5.780372438935374e-05,
+      "loss": 11.9219,
+      "step": 204
+    },
+    {
+      "epoch": 1.4081632653061225,
+      "grad_norm": 0.00870923325419426,
+      "learning_rate": 5.672198187410122e-05,
+      "loss": 11.922,
+      "step": 207
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.007657302543520927,
+      "learning_rate": 5.563702519697108e-05,
+      "loss": 11.9218,
+      "step": 210
+    },
+    {
+      "epoch": 1.4489795918367347,
+      "grad_norm": 0.009517359547317028,
+      "learning_rate": 5.454937313746255e-05,
+      "loss": 11.9218,
+      "step": 213
+    },
+    {
+      "epoch": 1.469387755102041,
+      "grad_norm": 0.010530628263950348,
+      "learning_rate": 5.345954576389047e-05,
+      "loss": 11.9215,
+      "step": 216
+    },
+    {
+      "epoch": 1.489795918367347,
+      "grad_norm": 0.007918890565633774,
+      "learning_rate": 5.236806418471113e-05,
+      "loss": 11.9217,
+      "step": 219
+    },
+    {
+      "epoch": 1.510204081632653,
+      "grad_norm": 0.009183686226606369,
+      "learning_rate": 5.1275450299350534e-05,
+      "loss": 11.9217,
+      "step": 222
+    },
+    {
+      "epoch": 1.510204081632653,
+      "eval_loss": 11.921103477478027,
+      "eval_runtime": 2.7526,
+      "eval_samples_per_second": 359.663,
+      "eval_steps_per_second": 11.262,
+      "step": 222
+    },
+    {
+      "epoch": 1.5306122448979593,
+      "grad_norm": 0.013725336641073227,
+      "learning_rate": 5.018222654865472e-05,
+      "loss": 11.9218,
+      "step": 225
+    },
+    {
+      "epoch": 1.5510204081632653,
+      "grad_norm": 0.01041232980787754,
+      "learning_rate": 4.908891566508103e-05,
+      "loss": 11.922,
+      "step": 228
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.013697491958737373,
+      "learning_rate": 4.7996040422749965e-05,
+      "loss": 11.9217,
+      "step": 231
+    },
+    {
+      "epoch": 1.5918367346938775,
+      "grad_norm": 0.013910558074712753,
+      "learning_rate": 4.690412338747721e-05,
+      "loss": 11.9217,
+      "step": 234
+    },
+    {
+      "epoch": 1.6122448979591837,
+      "grad_norm": 0.009510298259556293,
+      "learning_rate": 4.5813686666905096e-05,
+      "loss": 11.9216,
+      "step": 237
+    },
+    {
+      "epoch": 1.6326530612244898,
+      "grad_norm": 0.010002524591982365,
+      "learning_rate": 4.472525166085336e-05,
+      "loss": 11.9219,
+      "step": 240
+    },
+    {
+      "epoch": 1.6530612244897958,
+      "grad_norm": 0.01105476450175047,
+      "learning_rate": 4.363933881200811e-05,
+      "loss": 11.9217,
+      "step": 243
+    },
+    {
+      "epoch": 1.6734693877551021,
+      "grad_norm": 0.008844634518027306,
+      "learning_rate": 4.25564673570687e-05,
+      "loss": 11.9216,
+      "step": 246
+    },
+    {
+      "epoch": 1.693877551020408,
+      "grad_norm": 0.012191870249807835,
+      "learning_rate": 4.147715507847101e-05,
+      "loss": 11.9218,
+      "step": 249
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.01220732368528843,
+      "learning_rate": 4.040191805680627e-05,
+      "loss": 11.9215,
+      "step": 252
+    },
+    {
+      "epoch": 1.7346938775510203,
+      "grad_norm": 0.00849160086363554,
+      "learning_rate": 3.933127042405362e-05,
+      "loss": 11.9218,
+      "step": 255
+    },
+    {
+      "epoch": 1.7551020408163265,
+      "grad_norm": 0.009470686316490173,
+      "learning_rate": 3.826572411774426e-05,
+      "loss": 11.9217,
+      "step": 258
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "eval_loss": 11.920886039733887,
+      "eval_runtime": 2.9807,
+      "eval_samples_per_second": 332.134,
+      "eval_steps_per_second": 10.4,
+      "step": 259
+    },
+    {
+      "epoch": 1.7755102040816326,
+      "grad_norm": 0.008847080171108246,
+      "learning_rate": 3.7205788636175075e-05,
+      "loss": 11.9214,
+      "step": 261
+    },
+    {
+      "epoch": 1.7959183673469388,
+      "grad_norm": 0.014345753937959671,
+      "learning_rate": 3.6151970794788524e-05,
+      "loss": 11.9214,
+      "step": 264
+    },
+    {
+      "epoch": 1.816326530612245,
+      "grad_norm": 0.012002954259514809,
+      "learning_rate": 3.510477448383529e-05,
+      "loss": 11.9217,
+      "step": 267
+    },
+    {
+      "epoch": 1.836734693877551,
+      "grad_norm": 0.008899074047803879,
+      "learning_rate": 3.406470042743575e-05,
+      "loss": 11.9212,
+      "step": 270
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.010487317107617855,
+      "learning_rate": 3.3032245944155285e-05,
+      "loss": 11.9216,
+      "step": 273
+    },
+    {
+      "epoch": 1.8775510204081631,
+      "grad_norm": 0.014448858797550201,
+      "learning_rate": 3.20079047092079e-05,
+      "loss": 11.9215,
+      "step": 276
+    },
+    {
+      "epoch": 1.8979591836734695,
+      "grad_norm": 0.015154534950852394,
+      "learning_rate": 3.0992166518402193e-05,
+      "loss": 11.9215,
+      "step": 279
+    },
+    {
+      "epoch": 1.9183673469387754,
+      "grad_norm": 0.011302746832370758,
+      "learning_rate": 2.9985517053941924e-05,
+      "loss": 11.9212,
+      "step": 282
+    },
+    {
+      "epoch": 1.9387755102040818,
+      "grad_norm": 0.008427857421338558,
+      "learning_rate": 2.8988437652193878e-05,
+      "loss": 11.9213,
+      "step": 285
+    },
+    {
+      "epoch": 1.9591836734693877,
+      "grad_norm": 0.009195243939757347,
+      "learning_rate": 2.8001405073533515e-05,
+      "loss": 11.9216,
+      "step": 288
+    },
+    {
+      "epoch": 1.9795918367346939,
+      "grad_norm": 0.009580681100487709,
+      "learning_rate": 2.7024891274378693e-05,
+      "loss": 11.9215,
+      "step": 291
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.012584543786942959,
+      "learning_rate": 2.6059363181520518e-05,
+      "loss": 11.9215,
+      "step": 294
+    },
+    {
+      "epoch": 2.0136054421768708,
+      "eval_loss": 11.920774459838867,
+      "eval_runtime": 2.705,
+      "eval_samples_per_second": 365.99,
+      "eval_steps_per_second": 11.46,
+      "step": 296
+    },
+    {
+      "epoch": 2.020408163265306,
+      "grad_norm": 0.011345138773322105,
+      "learning_rate": 2.5105282468859027e-05,
+      "loss": 11.9217,
+      "step": 297
+    },
+    {
+      "epoch": 2.0408163265306123,
+      "grad_norm": 0.010026050731539726,
+      "learning_rate": 2.4163105336650642e-05,
+      "loss": 11.9212,
+      "step": 300
+    },
+    {
+      "epoch": 2.061224489795918,
+      "grad_norm": 0.012251692824065685,
+      "learning_rate": 2.3233282293372976e-05,
+      "loss": 11.9216,
+      "step": 303
+    },
+    {
+      "epoch": 2.0816326530612246,
+      "grad_norm": 0.009570994414389133,
+      "learning_rate": 2.2316257940310947e-05,
+      "loss": 11.9215,
+      "step": 306
+    },
+    {
+      "epoch": 2.1020408163265305,
+      "grad_norm": 0.011543840169906616,
+      "learning_rate": 2.141247075896774e-05,
+      "loss": 11.9216,
+      "step": 309
+    },
+    {
+      "epoch": 2.122448979591837,
+      "grad_norm": 0.008260723203420639,
+      "learning_rate": 2.0522352901401787e-05,
+      "loss": 11.9213,
+      "step": 312
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.01163262128829956,
+      "learning_rate": 1.964632998359036e-05,
+      "loss": 11.9213,
+      "step": 315
+    },
+    {
+      "epoch": 2.163265306122449,
+      "grad_norm": 0.008361991494894028,
+      "learning_rate": 1.8784820881918275e-05,
+      "loss": 11.9215,
+      "step": 318
+    },
+    {
+      "epoch": 2.183673469387755,
+      "grad_norm": 0.009338167496025562,
+      "learning_rate": 1.7938237532889357e-05,
+      "loss": 11.9213,
+      "step": 321
+    },
+    {
+      "epoch": 2.204081632653061,
+      "grad_norm": 0.012479112483561039,
+      "learning_rate": 1.7106984736156077e-05,
+      "loss": 11.9212,
+      "step": 324
+    },
+    {
+      "epoch": 2.2244897959183674,
+      "grad_norm": 0.010746627114713192,
+      "learning_rate": 1.6291459960961887e-05,
+      "loss": 11.9212,
+      "step": 327
+    },
+    {
+      "epoch": 2.2448979591836733,
+      "grad_norm": 0.008642462082207203,
+      "learning_rate": 1.54920531560885e-05,
+      "loss": 11.9218,
+      "step": 330
+    },
+    {
+      "epoch": 2.2653061224489797,
+      "grad_norm": 0.009854198433458805,
+      "learning_rate": 1.4709146563399301e-05,
+      "loss": 11.9214,
+      "step": 333
+    },
+    {
+      "epoch": 2.2653061224489797,
+      "eval_loss": 11.920734405517578,
+      "eval_runtime": 2.8232,
+      "eval_samples_per_second": 350.662,
+      "eval_steps_per_second": 10.98,
+      "step": 333
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.01021676603704691,
+      "learning_rate": 1.394311453506763e-05,
+      "loss": 11.9214,
+      "step": 336
+    },
+    {
+      "epoch": 2.306122448979592,
+      "grad_norm": 0.011460648849606514,
+      "learning_rate": 1.319432335457786e-05,
+      "loss": 11.9212,
+      "step": 339
+    },
+    {
+      "epoch": 2.326530612244898,
+      "grad_norm": 0.010614064522087574,
+      "learning_rate": 1.246313106158431e-05,
+      "loss": 11.9213,
+      "step": 342
+    },
+    {
+      "epoch": 2.3469387755102042,
+      "grad_norm": 0.012491398490965366,
+      "learning_rate": 1.1749887280712164e-05,
+      "loss": 11.9209,
+      "step": 345
+    },
+    {
+      "epoch": 2.36734693877551,
+      "grad_norm": 0.011822333559393883,
+      "learning_rate": 1.1054933054382106e-05,
+      "loss": 11.9218,
+      "step": 348
+    },
+    {
+      "epoch": 2.387755102040816,
+      "grad_norm": 0.009794401936233044,
+      "learning_rate": 1.0378600679738442e-05,
+      "loss": 11.9217,
+      "step": 351
+    },
+    {
+      "epoch": 2.4081632653061225,
+      "grad_norm": 0.007897097617387772,
+      "learning_rate": 9.721213549759011e-06,
+      "loss": 11.9214,
+      "step": 354
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.010740007273852825,
+      "learning_rate": 9.08308599862256e-06,
+      "loss": 11.9216,
+      "step": 357
+    },
+    {
+      "epoch": 2.4489795918367347,
+      "grad_norm": 0.009365779347717762,
+      "learning_rate": 8.464523151407722e-06,
+      "loss": 11.9217,
+      "step": 360
+    },
+    {
+      "epoch": 2.4693877551020407,
+      "grad_norm": 0.008345544338226318,
+      "learning_rate": 7.865820778195366e-06,
+      "loss": 11.9213,
+      "step": 363
+    },
+    {
+      "epoch": 2.489795918367347,
+      "grad_norm": 0.00913438480347395,
+      "learning_rate": 7.287265152644079e-06,
+      "loss": 11.9213,
+      "step": 366
+    },
+    {
+      "epoch": 2.510204081632653,
+      "grad_norm": 0.010115435346961021,
+      "learning_rate": 6.7291329151064455e-06,
+      "loss": 11.9211,
+      "step": 369
+    },
+    {
+      "epoch": 2.5170068027210886,
+      "eval_loss": 11.920697212219238,
+      "eval_runtime": 2.9612,
+      "eval_samples_per_second": 334.32,
+      "eval_steps_per_second": 10.469,
+      "step": 370
+    },
+    {
+      "epoch": 2.5306122448979593,
+      "grad_norm": 0.011003920808434486,
+      "learning_rate": 6.191690940351569e-06,
+      "loss": 11.9213,
+      "step": 372
+    },
+    {
+      "epoch": 2.5510204081632653,
+      "grad_norm": 0.010234669782221317,
+      "learning_rate": 5.67519620995704e-06,
+      "loss": 11.9212,
+      "step": 375
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.008843546733260155,
+      "learning_rate": 5.179895689431502e-06,
+      "loss": 11.921,
+      "step": 378
+    },
+    {
+      "epoch": 2.5918367346938775,
+      "grad_norm": 0.010195941664278507,
+      "learning_rate": 4.706026210126302e-06,
+      "loss": 11.9212,
+      "step": 381
+    },
+    {
+      "epoch": 2.612244897959184,
+      "grad_norm": 0.008211387321352959,
+      "learning_rate": 4.2538143559929915e-06,
+      "loss": 11.9214,
+      "step": 384
+    },
+    {
+      "epoch": 2.63265306122449,
+      "grad_norm": 0.008034368976950645,
+      "learning_rate": 3.823476355240668e-06,
+      "loss": 11.9217,
+      "step": 387
+    },
+    {
+      "epoch": 2.6530612244897958,
+      "grad_norm": 0.010721351020038128,
+      "learning_rate": 3.41521797694494e-06,
+      "loss": 11.9214,
+      "step": 390
+    },
+    {
+      "epoch": 2.673469387755102,
+      "grad_norm": 0.012811296619474888,
+      "learning_rate": 3.029234432658051e-06,
+      "loss": 11.9213,
+      "step": 393
+    },
+    {
+      "epoch": 2.693877551020408,
+      "grad_norm": 0.008711621165275574,
+      "learning_rate": 2.6657102830671078e-06,
+      "loss": 11.9216,
+      "step": 396
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.0077378894202411175,
+      "learning_rate": 2.324819349745133e-06,
+      "loss": 11.9212,
+      "step": 399
+    },
+    {
+      "epoch": 2.7346938775510203,
+      "grad_norm": 0.008991695940494537,
+      "learning_rate": 2.0067246320370935e-06,
+      "loss": 11.9217,
+      "step": 402
+    },
+    {
+      "epoch": 2.7551020408163263,
+      "grad_norm": 0.012436670251190662,
+      "learning_rate": 1.7115782291206083e-06,
+      "loss": 11.9211,
+      "step": 405
+    },
+    {
+      "epoch": 2.7687074829931975,
+      "eval_loss": 11.92069149017334,
+      "eval_runtime": 2.6971,
+      "eval_samples_per_second": 367.061,
+      "eval_steps_per_second": 11.494,
+      "step": 407
+    },
+    {
+      "epoch": 2.7755102040816326,
+      "grad_norm": 0.009732716716825962,
+      "learning_rate": 1.4395212672787373e-06,
+      "loss": 11.9218,
+      "step": 408
+    },
+    {
+      "epoch": 2.795918367346939,
+      "grad_norm": 0.015267143957316875,
+      "learning_rate": 1.1906838324194258e-06,
+      "loss": 11.9214,
+      "step": 411
+    },
+    {
+      "epoch": 2.816326530612245,
+      "grad_norm": 0.00914175808429718,
+      "learning_rate": 9.65184907874045e-07,
+      "loss": 11.9214,
+      "step": 414
+    },
+    {
+      "epoch": 2.836734693877551,
+      "grad_norm": 0.007872041314840317,
+      "learning_rate": 7.631323175047167e-07,
+      "loss": 11.9209,
+      "step": 417
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.010440999642014503,
+      "learning_rate": 5.846226741475557e-07,
+      "loss": 11.9219,
+      "step": 420
+    },
+    {
+      "epoch": 2.877551020408163,
+      "grad_norm": 0.0071489280089735985,
+      "learning_rate": 4.2974133341662226e-07,
+      "loss": 11.9211,
+      "step": 423
+    },
+    {
+      "epoch": 2.8979591836734695,
+      "grad_norm": 0.011952205561101437,
+      "learning_rate": 2.985623528904913e-07,
+      "loss": 11.9216,
+      "step": 426
+    },
+    {
+      "epoch": 2.9183673469387754,
+      "grad_norm": 0.010003963485360146,
+      "learning_rate": 1.9114845670117342e-07,
+      "loss": 11.9211,
+      "step": 429
+    },
+    {
+      "epoch": 2.938775510204082,
+      "grad_norm": 0.012489134445786476,
+      "learning_rate": 1.0755100554208364e-07,
+      "loss": 11.9213,
+      "step": 432
+    },
+    {
+      "epoch": 2.9591836734693877,
+      "grad_norm": 0.007483236957341433,
+      "learning_rate": 4.780997210962479e-08,
+      "loss": 11.9215,
+      "step": 435
+    },
+    {
+      "epoch": 2.979591836734694,
+      "grad_norm": 0.008097127079963684,
+      "learning_rate": 1.1953921989915628e-08,
+      "loss": 11.9215,
+      "step": 438
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.009465374983847141,
+      "learning_rate": 0.0,
+      "loss": 11.9213,
+      "step": 441
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 441,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 37,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 16600521768960.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b5db478b32acb23e06e22cfb0e8772065e7601806c043041ff117dd456594b
+size 6712

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b5db478b32acb23e06e22cfb0e8772065e7601806c043041ff117dd456594b
+size 6712