Upload folder using huggingface_hub

README.md

@@ -0,0 +1,119 @@
+---
+license: mit
+---
+
+
+## TIGERScore
+
+[Project Page](https://tiger-ai-lab.github.io/TIGERScore/) | [Paper](https://arxiv.org/abs/2310.00752) | [Code](https://github.com/TIGER-AI-Lab/TIGERScore) | [🤗Demo](https://huggingface.co/spaces/TIGER-Lab/TIGERScore) | 
+[🤗TIGERScore-7B](https://huggingface.co/TIGER-Lab/TIGERScore-7B-V1.2) | [🤗TIGERScore-13B](https://huggingface.co/TIGER-Lab/TIGERScore-13B-V1.2)
+
+## Introduction
+
+We present TIGERScore, a **T**rained metric that follows **I**nstruction **G**uidance to perform **E**xplainable, and **R**eference-free evaluation over a wide spectrum of text generation tasks. TIGERScore is guided by natural language instruction to provide error analysis to pinpoint the mistakes in the generated text. Our metric is based on LLaMA-2, trained on our meticulously curated instruction-tuning dataset MetricInstruct which covers 6 text generation tasks and 23 text generation datasets. As a reference-free metric, its correlation can even surpass the best existing reference-based metrics. To further qualitatively assess the rationale generated by our metric, we conduct human evaluation on the generated explanations and found that the explanations are 70.8% accurate. Through these experimental results, we believe TIGERScore demonstrates the possibility of building universal explainable metrics to evaluate any text generation task.
+
+## Training Data
+
+The models are trained on the 🤗 [MetricInstruct Dataset](https://huggingface.co/datasets/TIGER-Lab/MetricInstruct), which covers 6 text generation tasks and 22 text generation datasets. Check out the dataset card for more details.
+
+## Training Procedure
+
+The models are fine-tuned with the MetricInstruct dataset using the original Llama-2 model as base models. The training procedure varies for different models based on their sizes. Check out our paper for more details.
+
+## Evaluation
+
+TIGERScore significantly surpasses traditional metrics, i.e. BLUE, ROUGE, BARTScore, and BLEURT, and emerging LLM-based metrics as reference-free metrics. Though our dataset was originally sourced from ChatGPT, our distilled model actually outperforms ChatGPT itself, which proves the effectiveness of our filtering strategy. On the unseen task of story generation, TIGERScore also demonstrates reasonable generalization capability.
+
+| Tasks→                                    | Summarization  | Translation    | Data2Text      | Long-form QA    | MathQA         | Instruction Following   | Story-Gen      | Average        |
+|-------------------------------------------|----------------|----------------|----------------|-----------------|----------------|----------------|----------------|----------------|
+| GPT-3.5-turbo (few-shot)                  | **38.50**      | 40.53          | 40.20          | 29.33           | **66.46**      | 23.20          | 4.77           | 34.71          |
+| GPT-4 (zero-shot)                         | 36.46          | **43.87**      | **44.04**      | **48.95**       | 51.71          | **58.53**      | **32.48**      | **45.15**      |
+| BLEU                                      | 11.98          | 19.73          | 33.29          | 11.38           | 21.12          | **46.61**      | -1.17          | 20.42          |
+| ROUGE-2f                                  | 14.53          | 17.83          | 35.49          | 16.83           | 22.12          | 44.56          | 2.34           | 21.96          |
+| InstructScore                             | 26.33          | 47.30          | 43.93          | 21.62           | -4.15          | 16.19          | 16.13          | 23.91          |
+| GPTScore-ref                              | 14.73          | 24.95          | 39.42          | 31.60           | 18.20          | 33.14          | 18.24          | 25.75          |
+| BARTScore-cnn(hypo-ref)                   | 13.64          | 28.53          | 36.12          | 29.57           | **23.35**      | 32.49          | 26.64          | 27.19          |
+| BARTScore-para (hypo-ref)                 | 17.18          | 33.72          | 40.79          | 28.94           | 17.27          | 34.47          | 17.43          | 27.11          |
+| BERTScore                                 | 23.67          | 42.41          | 43.75          | 25.60           | 11.53          | 45.77          | 2.88           | 27.95          |
+| BLEURT                                    | 17.30          | 48.41          | **48.76**      | 33.26           | 3.53           | 36.46          | 27.52          | 30.75          |
+| UniEval(summ)                             | **47.52**      | 21.90          | 38.38          | **41.83**       | 19.78          | 16.02          | **44.46**      | 32.84          |
+| COMET-22                                  | 33.75          | **56.35**      | 33.92          | 35.28           | -5.53          | 46.13          | 39.20          | **34.16**      |
+| BARTScore-para (src-hypo)                 | **38.68**      | 9.60           | 32.26          | 26.86           | -2.70          | 5.92           | 20.55          | 18.74          |
+| BARTScore-cnn (src-hypo)                  | 35.50          | 12.83          | 34.33          | 40.96           | 1.50           | 25.43          | 33.48          | 26.29          |
+| Llama-2-13b-chat-0-shot                   | 28.53          | 14.38          | 29.24          | 19.91           | 1.08           | 21.37          | 26.78          | 20.18          |
+| COMETKiwi                                 | 16.27          | **48.48**      | 27.90          | 18.05           | -11.48         | 34.86          | 18.47          | 21.79          |
+| GPTScore-src                              | 37.41          | 8.90           | 28.82          | 39.48           | 14.25          | 26.46          | 23.91          | 25.61          |
+| TIGERScore-7B (ours)                      | 35.11          | 41.50          | 42.39          | **47.11**       | 21.23          | 43.57          | 39.26          | 38.60          |
+| TIGERScore-13B (ours)                     | 36.81          | 44.99          | **45.88**      | 46.22           | **23.32**      | **47.03**      | **46.36**      | **41.52**      |
+| Δ (ours - best reference-free)            | -2             | -3             | +12            | +5              | +9             | +14            | +13            | +16            |
+
+
+## Formatting
+
+
+To format the data fields into a single prompt for finetuning or testing, We provide the following code for users to refer:
+```python
+FINETUNE_INST = "You are evaluating errors in a model-generated output for a given instruction."
+FINETUNE_INPUT = """\
+Instruction: ${generation_instruction}
+${input_context}
+
+
+Model-generated Output:
+${hypothesis_output}
+
+
+For each error you give in the response, please also elaborate the following information:
+- error location (the words that are wrong in the output)
+- error aspect it belongs to.
+- explanation why it's an error, and the correction suggestions.
+- severity of the error ("Major" or "Minor").
+- reduction of score (between 0.5 and 5 given the severity of the error)
+
+Your evaluation output:
+"""
+inst_part = Template(FINETUNE_INST)
+inst_part = inst_part.substitute(task=task)
+input_part = Template(FINETUNE_INPUT)
+input_part = input_part.substitute(
+    generation_instruction=instruction,
+    input_context=input_context,
+    hypothesis_output=hypo_output
+)
+prompt = (inst_part + "\n" + input_part).strip("\n ") + "\n"
+encodings = tigerscore_tokenizer(prompt, return_tensors="pt")
+input_ids = encodings["input_ids"].to(tigerscore_model.device)
+attention_mask = encodings["attention_mask"].to(tigerscore_model.device)
+```
+
+Example of formatted prompt:
+```txt
+You are evaluating errors in a model-generated output for a given instruction.
+Instruction: Translate the following text from German to English.
+Der künftige EM-Cheforganisator Philipp Lahm soll laut Grindel im DFB-Präsidium mitarbeiten.
+
+
+Model-generated Output:
+According to Grindel, the future head of the European Championships, Philipp Lahm, is to participate in the DFB Presidency.
+
+
+For each error you give in the response, please also elaborate the following information:
+- error location (the words that are wrong in the output)
+- error aspect it belongs to.
+- explanation why it's an error, and the correction suggestions.
+- severity of the error ("Major" or "Minor").
+- reduction of score (between 0.5 and 5 given the severity of the error)
+
+Your evaluation output:
+```
+
+## Citation
+
+```
+@article{jiang2023TIGERScore,
+  title={TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks},
+  author={Dongfu Jiang, Yishan Li, Ge Zhang, Wenhao Huang, Bill Yuchen Lin, Wenhu Chen},
+  journal={arXiv preprint arXiv:2310.00752},
+  year={2023}
+}
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/ML-A100/models/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.1",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.35.1"
+}

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476847616
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd993665c352add26016540703df4ac241865d95c410d2ca1846ef919d95f774
+size 6878499292

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,2011 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 664,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8347554024716023e-06,
+      "loss": 0.8007,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.6695108049432045e-06,
+      "loss": 0.6499,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7.327736414105801e-06,
+      "loss": 0.553,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.504266207414806e-06,
+      "loss": 0.5237,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.41685361360415e-06,
+      "loss": 0.5046,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0162491816577402e-05,
+      "loss": 0.4709,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.0792919934429639e-05,
+      "loss": 0.4447,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1339021609886409e-05,
+      "loss": 0.4447,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1820717425739998e-05,
+      "loss": 0.4335,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.225160901607575e-05,
+      "loss": 0.4261,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.2641397872884761e-05,
+      "loss": 0.4484,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.2997247219049005e-05,
+      "loss": 0.4257,
+      "step": 24
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3324596884992558e-05,
+      "loss": 0.4204,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.362767533690124e-05,
+      "loss": 0.4223,
+      "step": 28
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3909834625238347e-05,
+      "loss": 0.421,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.4173777012358013e-05,
+      "loss": 0.4087,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.4421712774107928e-05,
+      "loss": 0.3996,
+      "step": 34
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.4655472828211601e-05,
+      "loss": 0.4163,
+      "step": 36
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.4876590870513565e-05,
+      "loss": 0.3931,
+      "step": 38
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.5086364418547353e-05,
+      "loss": 0.3902,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.5285900946063837e-05,
+      "loss": 0.3775,
+      "step": 42
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.547615327535636e-05,
+      "loss": 0.384,
+      "step": 44
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.5657947095819226e-05,
+      "loss": 0.3891,
+      "step": 46
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.583200262152061e-05,
+      "loss": 0.3965,
+      "step": 48
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.5998951824736692e-05,
+      "loss": 0.385,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.615935228746416e-05,
+      "loss": 0.3821,
+      "step": 52
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.6313698437374197e-05,
+      "loss": 0.3772,
+      "step": 54
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.6462430739372846e-05,
+      "loss": 0.3771,
+      "step": 56
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.6605943273513858e-05,
+      "loss": 0.3998,
+      "step": 58
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.674459002770995e-05,
+      "loss": 0.3811,
+      "step": 60
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.6878690158245678e-05,
+      "loss": 0.3877,
+      "step": 62
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.700853241482961e-05,
+      "loss": 0.3871,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.713437888451896e-05,
+      "loss": 0.3932,
+      "step": 66
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.725646817657953e-05,
+      "loss": 0.3849,
+      "step": 68
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.7375018145562187e-05,
+      "loss": 0.3922,
+      "step": 70
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7490228230683203e-05,
+      "loss": 0.3654,
+      "step": 72
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.760228147461214e-05,
+      "loss": 0.3612,
+      "step": 74
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7711346272985167e-05,
+      "loss": 0.3807,
+      "step": 76
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7817577896626754e-05,
+      "loss": 0.357,
+      "step": 78
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.792111982101895e-05,
+      "loss": 0.3771,
+      "step": 80
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.802210489158528e-05,
+      "loss": 0.3793,
+      "step": 82
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.812065634853544e-05,
+      "loss": 0.3694,
+      "step": 84
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8216888731104615e-05,
+      "loss": 0.3754,
+      "step": 86
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8310908677827968e-05,
+      "loss": 0.3613,
+      "step": 88
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8402815636872544e-05,
+      "loss": 0.3479,
+      "step": 90
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.849270249829083e-05,
+      "loss": 0.3606,
+      "step": 92
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.8580656158273317e-05,
+      "loss": 0.374,
+      "step": 94
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.866675802399221e-05,
+      "loss": 0.3794,
+      "step": 96
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.8751084466387678e-05,
+      "loss": 0.3545,
+      "step": 98
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.88337072272083e-05,
+      "loss": 0.3767,
+      "step": 100
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.8914693785742126e-05,
+      "loss": 0.3766,
+      "step": 102
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.899410768993576e-05,
+      "loss": 0.363,
+      "step": 104
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9072008855972226e-05,
+      "loss": 0.3742,
+      "step": 106
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.91484538398458e-05,
+      "loss": 0.3649,
+      "step": 108
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.922349608401731e-05,
+      "loss": 0.3768,
+      "step": 110
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9297186141844446e-05,
+      "loss": 0.3702,
+      "step": 112
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9369571882147768e-05,
+      "loss": 0.3567,
+      "step": 114
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.944069867598546e-05,
+      "loss": 0.3682,
+      "step": 116
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9510609567462104e-05,
+      "loss": 0.3748,
+      "step": 118
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9579345430181553e-05,
+      "loss": 0.3548,
+      "step": 120
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9646945110768043e-05,
+      "loss": 0.3495,
+      "step": 122
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9713445560717278e-05,
+      "loss": 0.3584,
+      "step": 124
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.977888195769804e-05,
+      "loss": 0.3729,
+      "step": 126
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9843287817301215e-05,
+      "loss": 0.3598,
+      "step": 128
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.99066950961251e-05,
+      "loss": 0.3806,
+      "step": 130
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9969134286990563e-05,
+      "loss": 0.3419,
+      "step": 132
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2e-05,
+      "loss": 0.3531,
+      "step": 134
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2e-05,
+      "loss": 0.3563,
+      "step": 136
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2e-05,
+      "loss": 0.3623,
+      "step": 138
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2e-05,
+      "loss": 0.3661,
+      "step": 140
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2e-05,
+      "loss": 0.3496,
+      "step": 142
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2e-05,
+      "loss": 0.3607,
+      "step": 144
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2e-05,
+      "loss": 0.3496,
+      "step": 146
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2e-05,
+      "loss": 0.3709,
+      "step": 148
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2e-05,
+      "loss": 0.3473,
+      "step": 150
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2e-05,
+      "loss": 0.3781,
+      "step": 152
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2e-05,
+      "loss": 0.3534,
+      "step": 154
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2e-05,
+      "loss": 0.3645,
+      "step": 156
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2e-05,
+      "loss": 0.3506,
+      "step": 158
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2e-05,
+      "loss": 0.3483,
+      "step": 160
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2e-05,
+      "loss": 0.3523,
+      "step": 162
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2e-05,
+      "loss": 0.3791,
+      "step": 164
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2e-05,
+      "loss": 0.3667,
+      "step": 166
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2e-05,
+      "loss": 0.3578,
+      "step": 168
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2e-05,
+      "loss": 0.3547,
+      "step": 170
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2e-05,
+      "loss": 0.3576,
+      "step": 172
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2e-05,
+      "loss": 0.3221,
+      "step": 174
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2e-05,
+      "loss": 0.3512,
+      "step": 176
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2e-05,
+      "loss": 0.3474,
+      "step": 178
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2e-05,
+      "loss": 0.3816,
+      "step": 180
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2e-05,
+      "loss": 0.3482,
+      "step": 182
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2e-05,
+      "loss": 0.3663,
+      "step": 184
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2e-05,
+      "loss": 0.3549,
+      "step": 186
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2e-05,
+      "loss": 0.3389,
+      "step": 188
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2e-05,
+      "loss": 0.3543,
+      "step": 190
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2e-05,
+      "loss": 0.3492,
+      "step": 192
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2e-05,
+      "loss": 0.3515,
+      "step": 194
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2e-05,
+      "loss": 0.3474,
+      "step": 196
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2e-05,
+      "loss": 0.349,
+      "step": 198
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2e-05,
+      "loss": 0.3488,
+      "step": 200
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2e-05,
+      "loss": 0.3352,
+      "step": 202
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 2e-05,
+      "loss": 0.3305,
+      "step": 204
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 2e-05,
+      "loss": 0.3491,
+      "step": 206
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2e-05,
+      "loss": 0.3646,
+      "step": 208
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2e-05,
+      "loss": 0.3487,
+      "step": 210
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2e-05,
+      "loss": 0.3524,
+      "step": 212
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2e-05,
+      "loss": 0.3748,
+      "step": 214
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 2e-05,
+      "loss": 0.3571,
+      "step": 216
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2e-05,
+      "loss": 0.3761,
+      "step": 218
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 2e-05,
+      "loss": 0.3586,
+      "step": 220
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2e-05,
+      "loss": 0.3596,
+      "step": 222
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 2e-05,
+      "loss": 0.3572,
+      "step": 224
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 2e-05,
+      "loss": 0.3458,
+      "step": 226
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2e-05,
+      "loss": 0.3365,
+      "step": 228
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2e-05,
+      "loss": 0.3512,
+      "step": 230
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2e-05,
+      "loss": 0.35,
+      "step": 232
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2e-05,
+      "loss": 0.3686,
+      "step": 234
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2e-05,
+      "loss": 0.3427,
+      "step": 236
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2e-05,
+      "loss": 0.3291,
+      "step": 238
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2e-05,
+      "loss": 0.3486,
+      "step": 240
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2e-05,
+      "loss": 0.3393,
+      "step": 242
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2e-05,
+      "loss": 0.3567,
+      "step": 244
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2e-05,
+      "loss": 0.3416,
+      "step": 246
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2e-05,
+      "loss": 0.3506,
+      "step": 248
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2e-05,
+      "loss": 0.3403,
+      "step": 250
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2e-05,
+      "loss": 0.3536,
+      "step": 252
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2e-05,
+      "loss": 0.3515,
+      "step": 254
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2e-05,
+      "loss": 0.3577,
+      "step": 256
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2e-05,
+      "loss": 0.3412,
+      "step": 258
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2e-05,
+      "loss": 0.3422,
+      "step": 260
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2e-05,
+      "loss": 0.3413,
+      "step": 262
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2e-05,
+      "loss": 0.3219,
+      "step": 264
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2e-05,
+      "loss": 0.3416,
+      "step": 266
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2e-05,
+      "loss": 0.3615,
+      "step": 268
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2e-05,
+      "loss": 0.3479,
+      "step": 270
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2e-05,
+      "loss": 0.3506,
+      "step": 272
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2e-05,
+      "loss": 0.3477,
+      "step": 274
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2e-05,
+      "loss": 0.3612,
+      "step": 276
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2e-05,
+      "loss": 0.3618,
+      "step": 278
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2e-05,
+      "loss": 0.3427,
+      "step": 280
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2e-05,
+      "loss": 0.3492,
+      "step": 282
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2e-05,
+      "loss": 0.3191,
+      "step": 284
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2e-05,
+      "loss": 0.3429,
+      "step": 286
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2e-05,
+      "loss": 0.3377,
+      "step": 288
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2e-05,
+      "loss": 0.3404,
+      "step": 290
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2e-05,
+      "loss": 0.3311,
+      "step": 292
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2e-05,
+      "loss": 0.3406,
+      "step": 294
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2e-05,
+      "loss": 0.3499,
+      "step": 296
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2e-05,
+      "loss": 0.3452,
+      "step": 298
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2e-05,
+      "loss": 0.3483,
+      "step": 300
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2e-05,
+      "loss": 0.3513,
+      "step": 302
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2e-05,
+      "loss": 0.3082,
+      "step": 304
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2e-05,
+      "loss": 0.3401,
+      "step": 306
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2e-05,
+      "loss": 0.3345,
+      "step": 308
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2e-05,
+      "loss": 0.3387,
+      "step": 310
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2e-05,
+      "loss": 0.3428,
+      "step": 312
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2e-05,
+      "loss": 0.3451,
+      "step": 314
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2e-05,
+      "loss": 0.3438,
+      "step": 316
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2e-05,
+      "loss": 0.3402,
+      "step": 318
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2e-05,
+      "loss": 0.3523,
+      "step": 320
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2e-05,
+      "loss": 0.3252,
+      "step": 322
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2e-05,
+      "loss": 0.3417,
+      "step": 324
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2e-05,
+      "loss": 0.3582,
+      "step": 326
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2e-05,
+      "loss": 0.3352,
+      "step": 328
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2e-05,
+      "loss": 0.3348,
+      "step": 330
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2e-05,
+      "loss": 0.3502,
+      "step": 332
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2e-05,
+      "loss": 0.3353,
+      "step": 334
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2e-05,
+      "loss": 0.3185,
+      "step": 336
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2e-05,
+      "loss": 0.3119,
+      "step": 338
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2e-05,
+      "loss": 0.3087,
+      "step": 340
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2e-05,
+      "loss": 0.3058,
+      "step": 342
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2e-05,
+      "loss": 0.2902,
+      "step": 344
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2e-05,
+      "loss": 0.2726,
+      "step": 346
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2e-05,
+      "loss": 0.2851,
+      "step": 348
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2e-05,
+      "loss": 0.2688,
+      "step": 350
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2e-05,
+      "loss": 0.2704,
+      "step": 352
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2e-05,
+      "loss": 0.2833,
+      "step": 354
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2e-05,
+      "loss": 0.2721,
+      "step": 356
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2e-05,
+      "loss": 0.2646,
+      "step": 358
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2e-05,
+      "loss": 0.2722,
+      "step": 360
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2e-05,
+      "loss": 0.2765,
+      "step": 362
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2e-05,
+      "loss": 0.2665,
+      "step": 364
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2e-05,
+      "loss": 0.2549,
+      "step": 366
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2e-05,
+      "loss": 0.2596,
+      "step": 368
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2e-05,
+      "loss": 0.2546,
+      "step": 370
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2e-05,
+      "loss": 0.2492,
+      "step": 372
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2e-05,
+      "loss": 0.242,
+      "step": 374
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2e-05,
+      "loss": 0.2478,
+      "step": 376
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2e-05,
+      "loss": 0.2518,
+      "step": 378
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2e-05,
+      "loss": 0.2561,
+      "step": 380
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2e-05,
+      "loss": 0.2409,
+      "step": 382
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2e-05,
+      "loss": 0.2472,
+      "step": 384
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2e-05,
+      "loss": 0.2388,
+      "step": 386
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2e-05,
+      "loss": 0.2368,
+      "step": 388
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2e-05,
+      "loss": 0.2529,
+      "step": 390
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2e-05,
+      "loss": 0.2338,
+      "step": 392
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2e-05,
+      "loss": 0.2383,
+      "step": 394
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2e-05,
+      "loss": 0.2487,
+      "step": 396
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2e-05,
+      "loss": 0.2543,
+      "step": 398
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2e-05,
+      "loss": 0.2434,
+      "step": 400
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2e-05,
+      "loss": 0.247,
+      "step": 402
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2e-05,
+      "loss": 0.2271,
+      "step": 404
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2e-05,
+      "loss": 0.2239,
+      "step": 406
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 2e-05,
+      "loss": 0.244,
+      "step": 408
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 2e-05,
+      "loss": 0.2262,
+      "step": 410
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 2e-05,
+      "loss": 0.2394,
+      "step": 412
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2e-05,
+      "loss": 0.2443,
+      "step": 414
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2e-05,
+      "loss": 0.2356,
+      "step": 416
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2e-05,
+      "loss": 0.2393,
+      "step": 418
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2e-05,
+      "loss": 0.2292,
+      "step": 420
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2e-05,
+      "loss": 0.2165,
+      "step": 422
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2e-05,
+      "loss": 0.2232,
+      "step": 424
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2e-05,
+      "loss": 0.2356,
+      "step": 426
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2e-05,
+      "loss": 0.241,
+      "step": 428
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2e-05,
+      "loss": 0.2268,
+      "step": 430
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2e-05,
+      "loss": 0.2375,
+      "step": 432
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2e-05,
+      "loss": 0.2361,
+      "step": 434
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2e-05,
+      "loss": 0.2265,
+      "step": 436
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2e-05,
+      "loss": 0.2294,
+      "step": 438
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2e-05,
+      "loss": 0.22,
+      "step": 440
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2e-05,
+      "loss": 0.2343,
+      "step": 442
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2e-05,
+      "loss": 0.2351,
+      "step": 444
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2e-05,
+      "loss": 0.2165,
+      "step": 446
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2e-05,
+      "loss": 0.2303,
+      "step": 448
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2e-05,
+      "loss": 0.2304,
+      "step": 450
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2e-05,
+      "loss": 0.2137,
+      "step": 452
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2e-05,
+      "loss": 0.2173,
+      "step": 454
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2e-05,
+      "loss": 0.2244,
+      "step": 456
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2e-05,
+      "loss": 0.2236,
+      "step": 458
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2e-05,
+      "loss": 0.2222,
+      "step": 460
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2e-05,
+      "loss": 0.2362,
+      "step": 462
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2e-05,
+      "loss": 0.2108,
+      "step": 464
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2e-05,
+      "loss": 0.2179,
+      "step": 466
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2e-05,
+      "loss": 0.2332,
+      "step": 468
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2e-05,
+      "loss": 0.2297,
+      "step": 470
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2e-05,
+      "loss": 0.2302,
+      "step": 472
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2e-05,
+      "loss": 0.222,
+      "step": 474
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2e-05,
+      "loss": 0.2193,
+      "step": 476
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2e-05,
+      "loss": 0.2145,
+      "step": 478
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2e-05,
+      "loss": 0.2294,
+      "step": 480
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2e-05,
+      "loss": 0.2059,
+      "step": 482
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 2e-05,
+      "loss": 0.2363,
+      "step": 484
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 2e-05,
+      "loss": 0.2179,
+      "step": 486
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2e-05,
+      "loss": 0.2182,
+      "step": 488
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2e-05,
+      "loss": 0.2129,
+      "step": 490
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2e-05,
+      "loss": 0.2073,
+      "step": 492
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2e-05,
+      "loss": 0.2153,
+      "step": 494
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2e-05,
+      "loss": 0.228,
+      "step": 496
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2e-05,
+      "loss": 0.228,
+      "step": 498
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2e-05,
+      "loss": 0.2124,
+      "step": 500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2e-05,
+      "loss": 0.2209,
+      "step": 502
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2e-05,
+      "loss": 0.2139,
+      "step": 504
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2e-05,
+      "loss": 0.2028,
+      "step": 506
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2e-05,
+      "loss": 0.2094,
+      "step": 508
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2e-05,
+      "loss": 0.2033,
+      "step": 510
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2e-05,
+      "loss": 0.2388,
+      "step": 512
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2e-05,
+      "loss": 0.2137,
+      "step": 514
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2e-05,
+      "loss": 0.228,
+      "step": 516
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2e-05,
+      "loss": 0.2143,
+      "step": 518
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2e-05,
+      "loss": 0.2016,
+      "step": 520
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2e-05,
+      "loss": 0.2113,
+      "step": 522
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2e-05,
+      "loss": 0.2071,
+      "step": 524
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2e-05,
+      "loss": 0.2201,
+      "step": 526
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2e-05,
+      "loss": 0.2159,
+      "step": 528
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2e-05,
+      "loss": 0.2143,
+      "step": 530
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2e-05,
+      "loss": 0.2124,
+      "step": 532
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2e-05,
+      "loss": 0.2006,
+      "step": 534
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2e-05,
+      "loss": 0.2016,
+      "step": 536
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2e-05,
+      "loss": 0.2144,
+      "step": 538
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2e-05,
+      "loss": 0.2182,
+      "step": 540
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2e-05,
+      "loss": 0.2139,
+      "step": 542
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2e-05,
+      "loss": 0.2147,
+      "step": 544
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2e-05,
+      "loss": 0.2333,
+      "step": 546
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2e-05,
+      "loss": 0.2154,
+      "step": 548
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 2e-05,
+      "loss": 0.2197,
+      "step": 550
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 2e-05,
+      "loss": 0.2231,
+      "step": 552
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2e-05,
+      "loss": 0.2266,
+      "step": 554
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2e-05,
+      "loss": 0.2207,
+      "step": 556
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2e-05,
+      "loss": 0.2131,
+      "step": 558
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2e-05,
+      "loss": 0.2104,
+      "step": 560
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2e-05,
+      "loss": 0.2196,
+      "step": 562
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2e-05,
+      "loss": 0.2138,
+      "step": 564
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2e-05,
+      "loss": 0.2285,
+      "step": 566
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2e-05,
+      "loss": 0.206,
+      "step": 568
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2e-05,
+      "loss": 0.1989,
+      "step": 570
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2e-05,
+      "loss": 0.2141,
+      "step": 572
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2e-05,
+      "loss": 0.2101,
+      "step": 574
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2e-05,
+      "loss": 0.2141,
+      "step": 576
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2e-05,
+      "loss": 0.206,
+      "step": 578
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2e-05,
+      "loss": 0.2195,
+      "step": 580
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2e-05,
+      "loss": 0.2062,
+      "step": 582
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2e-05,
+      "loss": 0.2235,
+      "step": 584
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 2e-05,
+      "loss": 0.2276,
+      "step": 586
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 2e-05,
+      "loss": 0.2221,
+      "step": 588
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2e-05,
+      "loss": 0.2144,
+      "step": 590
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2e-05,
+      "loss": 0.1995,
+      "step": 592
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2e-05,
+      "loss": 0.2009,
+      "step": 594
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2e-05,
+      "loss": 0.1959,
+      "step": 596
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2e-05,
+      "loss": 0.2062,
+      "step": 598
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2e-05,
+      "loss": 0.2125,
+      "step": 600
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2e-05,
+      "loss": 0.2139,
+      "step": 602
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 2e-05,
+      "loss": 0.2176,
+      "step": 604
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 2e-05,
+      "loss": 0.2138,
+      "step": 606
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 2e-05,
+      "loss": 0.2189,
+      "step": 608
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2e-05,
+      "loss": 0.2224,
+      "step": 610
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2e-05,
+      "loss": 0.2079,
+      "step": 612
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2e-05,
+      "loss": 0.2109,
+      "step": 614
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2e-05,
+      "loss": 0.1944,
+      "step": 616
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 2e-05,
+      "loss": 0.2156,
+      "step": 618
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2e-05,
+      "loss": 0.2048,
+      "step": 620
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2e-05,
+      "loss": 0.2131,
+      "step": 622
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2e-05,
+      "loss": 0.1977,
+      "step": 624
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2e-05,
+      "loss": 0.215,
+      "step": 626
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 2e-05,
+      "loss": 0.2144,
+      "step": 628
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2e-05,
+      "loss": 0.208,
+      "step": 630
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2e-05,
+      "loss": 0.2149,
+      "step": 632
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2e-05,
+      "loss": 0.2142,
+      "step": 634
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2e-05,
+      "loss": 0.1788,
+      "step": 636
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2e-05,
+      "loss": 0.2131,
+      "step": 638
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 2e-05,
+      "loss": 0.2084,
+      "step": 640
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 2e-05,
+      "loss": 0.1999,
+      "step": 642
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2e-05,
+      "loss": 0.2124,
+      "step": 644
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2e-05,
+      "loss": 0.2114,
+      "step": 646
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 2e-05,
+      "loss": 0.2137,
+      "step": 648
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2e-05,
+      "loss": 0.2115,
+      "step": 650
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2e-05,
+      "loss": 0.2097,
+      "step": 652
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 2e-05,
+      "loss": 0.199,
+      "step": 654
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2e-05,
+      "loss": 0.2063,
+      "step": 656
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2e-05,
+      "loss": 0.2244,
+      "step": 658
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2e-05,
+      "loss": 0.2029,
+      "step": 660
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 2e-05,
+      "loss": 0.2079,
+      "step": 662
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2e-05,
+      "loss": 0.2054,
+      "step": 664
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1328,
+  "num_train_epochs": 4,
+  "save_steps": 64.0,
+  "total_flos": 95590771425280.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4f27065c9ee7f9cc195b716eae40fdbf8abfa63e6127edade2ecf855cf01c4
+size 6456