Upload folder using huggingface_hub

README.md

@@ -0,0 +1,238 @@
+---
+library_name: peft
+base_model: deepseek-ai/deepseek-coder-1.3b-base
+---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.7.0.dev0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.7.0.dev0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb42107555e3e0ab171c8ba76aef09ec22f15e1f5f4f2e066290788a665aabd7
+size 239983242

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6a1f3fe00404dd888f569535094ab24d798eea6c5c3efc2c5e1bea032cc064
+size 239906848

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ab8041d4cb371361e63a0575603f9b6906e3fa8cb2bd51cd41c394ed549c442
+size 479931770

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7423341963e3ea64c39b9661a17db5b776015320f508475dd08bf627ae4b2449
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec307cf9db5bf0d472c30966049b0e36d515f7926bb815cce7815434f7703c0b
+size 1064

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<｜end▁of▁sentence｜>"
+}

tokenizer_config.json

@@ -0,0 +1,190 @@
+{
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,1861 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9993906154783668,
+  "eval_steps": 500,
+  "global_step": 615,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 1.2236,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.4631,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 1.405,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.7103,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 1.6165,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.7487,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5e-06,
+      "loss": 1.7254,
+      "step": 14
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.6604,
+      "step": 16
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.4285714285714295e-06,
+      "loss": 1.622,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 1.8001,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.857142857142858e-06,
+      "loss": 1.5987,
+      "step": 22
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.7409,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.285714285714288e-06,
+      "loss": 1.9162,
+      "step": 26
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 1.8572,
+      "step": 28
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 1.9669,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 1.9432,
+      "step": 32
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2142857142857142e-05,
+      "loss": 1.9297,
+      "step": 34
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2857142857142859e-05,
+      "loss": 2.0854,
+      "step": 36
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.3571428571428574e-05,
+      "loss": 2.092,
+      "step": 38
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 2.1925,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.3367,
+      "step": 42
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 2.4136,
+      "step": 44
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.642857142857143e-05,
+      "loss": 2.5252,
+      "step": 46
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 2.5727,
+      "step": 48
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 3.1009,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8571428571428575e-05,
+      "loss": 1.4247,
+      "step": 52
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 1.3148,
+      "step": 54
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 1.6329,
+      "step": 56
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.999993832507735e-05,
+      "loss": 1.4144,
+      "step": 58
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999753301070156e-05,
+      "loss": 1.6329,
+      "step": 60
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999444930260684e-05,
+      "loss": 1.5957,
+      "step": 62
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9999013216452688e-05,
+      "loss": 1.4545,
+      "step": 64
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999845816497135e-05,
+      "loss": 1.7986,
+      "step": 66
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9997779782663217e-05,
+      "loss": 1.7363,
+      "step": 68
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.999697807789613e-05,
+      "loss": 1.7775,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.99960530605591e-05,
+      "loss": 1.6756,
+      "step": 72
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9995004742062206e-05,
+      "loss": 1.5798,
+      "step": 74
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.999383313533644e-05,
+      "loss": 1.8129,
+      "step": 76
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9992538254833548e-05,
+      "loss": 1.7426,
+      "step": 78
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9991120116525866e-05,
+      "loss": 1.7854,
+      "step": 80
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9989578737906107e-05,
+      "loss": 1.9305,
+      "step": 82
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9987914137987153e-05,
+      "loss": 1.9058,
+      "step": 84
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9986126337301814e-05,
+      "loss": 1.8474,
+      "step": 86
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9984215357902586e-05,
+      "loss": 1.8505,
+      "step": 88
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9982181223361373e-05,
+      "loss": 1.8879,
+      "step": 90
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9980023958769195e-05,
+      "loss": 2.229,
+      "step": 92
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9977743590735866e-05,
+      "loss": 2.0788,
+      "step": 94
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9975340147389707e-05,
+      "loss": 2.3521,
+      "step": 96
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.997281365837714e-05,
+      "loss": 2.2187,
+      "step": 98
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9970164154862375e-05,
+      "loss": 2.2225,
+      "step": 100
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9967391669526995e-05,
+      "loss": 1.2585,
+      "step": 102
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996449623656956e-05,
+      "loss": 1.4347,
+      "step": 104
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9961477891705203e-05,
+      "loss": 1.552,
+      "step": 106
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9958336672165147e-05,
+      "loss": 1.571,
+      "step": 108
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9955072616696294e-05,
+      "loss": 1.5051,
+      "step": 110
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9951685765560717e-05,
+      "loss": 1.6931,
+      "step": 112
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.994817616053517e-05,
+      "loss": 1.5936,
+      "step": 114
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.994454384491058e-05,
+      "loss": 1.5303,
+      "step": 116
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9940788863491503e-05,
+      "loss": 1.5092,
+      "step": 118
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9936911262595574e-05,
+      "loss": 1.678,
+      "step": 120
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.993291109005294e-05,
+      "loss": 1.4946,
+      "step": 122
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9928788395205673e-05,
+      "loss": 1.7905,
+      "step": 124
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9924543228907147e-05,
+      "loss": 1.788,
+      "step": 126
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.992017564352142e-05,
+      "loss": 1.6872,
+      "step": 128
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9915685692922592e-05,
+      "loss": 1.7038,
+      "step": 130
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9911073432494138e-05,
+      "loss": 1.7661,
+      "step": 132
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9906338919128214e-05,
+      "loss": 1.7958,
+      "step": 134
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.990148221122497e-05,
+      "loss": 1.8836,
+      "step": 136
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9896503368691826e-05,
+      "loss": 1.9028,
+      "step": 138
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.989140245294272e-05,
+      "loss": 2.077,
+      "step": 140
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.988617952689738e-05,
+      "loss": 1.9555,
+      "step": 142
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.988083465498051e-05,
+      "loss": 2.2974,
+      "step": 144
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9875367903121022e-05,
+      "loss": 2.1295,
+      "step": 146
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9869779338751217e-05,
+      "loss": 2.2783,
+      "step": 148
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9864069030805955e-05,
+      "loss": 2.0852,
+      "step": 150
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9858237049721793e-05,
+      "loss": 1.5204,
+      "step": 152
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9852283467436124e-05,
+      "loss": 1.4498,
+      "step": 154
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.98462083573863e-05,
+      "loss": 1.4835,
+      "step": 156
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9840011794508702e-05,
+      "loss": 1.5079,
+      "step": 158
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.983369385523784e-05,
+      "loss": 1.5743,
+      "step": 160
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.98272546175054e-05,
+      "loss": 1.5409,
+      "step": 162
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.982069416073928e-05,
+      "loss": 1.5208,
+      "step": 164
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9814012565862607e-05,
+      "loss": 1.7327,
+      "step": 166
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9807209915292754e-05,
+      "loss": 1.7466,
+      "step": 168
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9800286292940313e-05,
+      "loss": 1.6901,
+      "step": 170
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9793241784208054e-05,
+      "loss": 1.7233,
+      "step": 172
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.978607647598989e-05,
+      "loss": 1.6692,
+      "step": 174
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9778790456669777e-05,
+      "loss": 1.7248,
+      "step": 176
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9771383816120658e-05,
+      "loss": 1.8977,
+      "step": 178
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.976385664570333e-05,
+      "loss": 1.8373,
+      "step": 180
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9756209038265317e-05,
+      "loss": 1.8188,
+      "step": 182
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9748441088139746e-05,
+      "loss": 1.8918,
+      "step": 184
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9740552891144157e-05,
+      "loss": 1.9215,
+      "step": 186
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.973254454457934e-05,
+      "loss": 1.9047,
+      "step": 188
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9724416147228127e-05,
+      "loss": 2.0088,
+      "step": 190
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.971616779935417e-05,
+      "loss": 2.1103,
+      "step": 192
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9707799602700712e-05,
+      "loss": 2.1014,
+      "step": 194
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9699311660489333e-05,
+      "loss": 1.8813,
+      "step": 196
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.969070407741867e-05,
+      "loss": 2.2869,
+      "step": 198
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.968197695966312e-05,
+      "loss": 2.2136,
+      "step": 200
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9673130414871556e-05,
+      "loss": 1.473,
+      "step": 202
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9664164552165957e-05,
+      "loss": 1.4018,
+      "step": 204
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.9655079482140115e-05,
+      "loss": 1.3433,
+      "step": 206
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.964587531685822e-05,
+      "loss": 1.4818,
+      "step": 208
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9636552169853514e-05,
+      "loss": 1.5572,
+      "step": 210
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9627110156126862e-05,
+      "loss": 1.5843,
+      "step": 212
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9617549392145365e-05,
+      "loss": 1.6586,
+      "step": 214
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.96078699958409e-05,
+      "loss": 1.4021,
+      "step": 216
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9598072086608663e-05,
+      "loss": 1.4863,
+      "step": 218
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.958815578530572e-05,
+      "loss": 1.6731,
+      "step": 220
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9578121214249485e-05,
+      "loss": 1.6004,
+      "step": 222
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.956796849721625e-05,
+      "loss": 1.5723,
+      "step": 224
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9557697759439613e-05,
+      "loss": 1.7214,
+      "step": 226
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.954730912760897e-05,
+      "loss": 1.7316,
+      "step": 228
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9536802729867926e-05,
+      "loss": 1.7336,
+      "step": 230
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9526178695812747e-05,
+      "loss": 1.7207,
+      "step": 232
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.9515437156490724e-05,
+      "loss": 2.0022,
+      "step": 234
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.950457824439857e-05,
+      "loss": 1.7205,
+      "step": 236
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9493602093480807e-05,
+      "loss": 1.9002,
+      "step": 238
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9482508839128087e-05,
+      "loss": 2.0414,
+      "step": 240
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9471298618175523e-05,
+      "loss": 2.1061,
+      "step": 242
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9459971568901026e-05,
+      "loss": 2.2256,
+      "step": 244
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.944852783102357e-05,
+      "loss": 2.0902,
+      "step": 246
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9436967545701485e-05,
+      "loss": 2.1776,
+      "step": 248
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9425290855530705e-05,
+      "loss": 2.1136,
+      "step": 250
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9413497904543033e-05,
+      "loss": 1.2511,
+      "step": 252
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9401588838204334e-05,
+      "loss": 1.3177,
+      "step": 254
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9389563803412753e-05,
+      "loss": 1.4358,
+      "step": 256
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9377422948496912e-05,
+      "loss": 1.672,
+      "step": 258
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9365166423214065e-05,
+      "loss": 1.6008,
+      "step": 260
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9352794378748267e-05,
+      "loss": 1.5744,
+      "step": 262
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.934030696770849e-05,
+      "loss": 1.4593,
+      "step": 264
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.932770434412676e-05,
+      "loss": 1.7566,
+      "step": 266
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.931498666345624e-05,
+      "loss": 1.6279,
+      "step": 268
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9302154082569328e-05,
+      "loss": 1.5859,
+      "step": 270
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.928920675975571e-05,
+      "loss": 1.5577,
+      "step": 272
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9276144854720412e-05,
+      "loss": 1.5837,
+      "step": 274
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9262968528581828e-05,
+      "loss": 1.6993,
+      "step": 276
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9249677943869742e-05,
+      "loss": 1.6503,
+      "step": 278
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9236273264523304e-05,
+      "loss": 1.8387,
+      "step": 280
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9222754655889035e-05,
+      "loss": 1.7513,
+      "step": 282
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9209122284718757e-05,
+      "loss": 1.842,
+      "step": 284
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.919537631916756e-05,
+      "loss": 1.9954,
+      "step": 286
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9181516928791715e-05,
+      "loss": 2.0364,
+      "step": 288
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.916754428454659e-05,
+      "loss": 2.0113,
+      "step": 290
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9153458558784536e-05,
+      "loss": 2.0972,
+      "step": 292
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9139259925252756e-05,
+      "loss": 2.1826,
+      "step": 294
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.912494855909118e-05,
+      "loss": 2.2134,
+      "step": 296
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.911052463683029e-05,
+      "loss": 2.1347,
+      "step": 298
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9095988336388945e-05,
+      "loss": 2.1557,
+      "step": 300
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.908133983707218e-05,
+      "loss": 1.6206,
+      "step": 302
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.906657931956901e-05,
+      "loss": 1.466,
+      "step": 304
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9051706965950192e-05,
+      "loss": 1.4884,
+      "step": 306
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9036722959665975e-05,
+      "loss": 1.485,
+      "step": 308
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9021627485543844e-05,
+      "loss": 1.6297,
+      "step": 310
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9006420729786246e-05,
+      "loss": 1.6544,
+      "step": 312
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.899110287996827e-05,
+      "loss": 1.552,
+      "step": 314
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.897567412503536e-05,
+      "loss": 1.7586,
+      "step": 316
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8960134655300966e-05,
+      "loss": 1.6673,
+      "step": 318
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.894448466244421e-05,
+      "loss": 1.6194,
+      "step": 320
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8928724339507515e-05,
+      "loss": 1.4731,
+      "step": 322
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8912853880894215e-05,
+      "loss": 1.6042,
+      "step": 324
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8896873482366173e-05,
+      "loss": 1.7247,
+      "step": 326
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8880783341041357e-05,
+      "loss": 1.7958,
+      "step": 328
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8864583655391417e-05,
+      "loss": 1.6097,
+      "step": 330
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8848274625239216e-05,
+      "loss": 1.7074,
+      "step": 332
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8831856451756394e-05,
+      "loss": 1.928,
+      "step": 334
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.881532933746087e-05,
+      "loss": 1.7286,
+      "step": 336
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.879869348621433e-05,
+      "loss": 1.7516,
+      "step": 338
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8781949103219758e-05,
+      "loss": 1.95,
+      "step": 340
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.876509639501885e-05,
+      "loss": 1.893,
+      "step": 342
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8748135569489504e-05,
+      "loss": 2.0016,
+      "step": 344
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8731066835843237e-05,
+      "loss": 2.1922,
+      "step": 346
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8713890404622618e-05,
+      "loss": 2.1049,
+      "step": 348
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.869660648769866e-05,
+      "loss": 2.3154,
+      "step": 350
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.867921529826821e-05,
+      "loss": 1.2,
+      "step": 352
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8661717050851323e-05,
+      "loss": 1.3897,
+      "step": 354
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8644111961288605e-05,
+      "loss": 1.4177,
+      "step": 356
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8626400246738568e-05,
+      "loss": 1.3511,
+      "step": 358
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8608582125674933e-05,
+      "loss": 1.6614,
+      "step": 360
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8590657817883952e-05,
+      "loss": 1.5387,
+      "step": 362
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8572627544461682e-05,
+      "loss": 1.6492,
+      "step": 364
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.8554491527811266e-05,
+      "loss": 1.5073,
+      "step": 366
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8536249991640192e-05,
+      "loss": 1.7497,
+      "step": 368
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8517903160957523e-05,
+      "loss": 1.4961,
+      "step": 370
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8499451262071134e-05,
+      "loss": 1.7061,
+      "step": 372
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.848089452258491e-05,
+      "loss": 1.6356,
+      "step": 374
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.846223317139595e-05,
+      "loss": 1.6088,
+      "step": 376
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.844346743869173e-05,
+      "loss": 1.6825,
+      "step": 378
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8424597555947268e-05,
+      "loss": 1.6737,
+      "step": 380
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.840562375592228e-05,
+      "loss": 1.8381,
+      "step": 382
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8386546272658296e-05,
+      "loss": 1.8862,
+      "step": 384
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8367365341475777e-05,
+      "loss": 1.8186,
+      "step": 386
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.834808119897121e-05,
+      "loss": 1.8536,
+      "step": 388
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8328694083014196e-05,
+      "loss": 2.0862,
+      "step": 390
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.830920423274451e-05,
+      "loss": 2.2656,
+      "step": 392
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8289611888569158e-05,
+      "loss": 2.085,
+      "step": 394
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8269917292159393e-05,
+      "loss": 2.2241,
+      "step": 396
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8250120686447767e-05,
+      "loss": 2.0626,
+      "step": 398
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.82302223156251e-05,
+      "loss": 2.3965,
+      "step": 400
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8210222425137485e-05,
+      "loss": 1.4121,
+      "step": 402
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8190121261683268e-05,
+      "loss": 1.4354,
+      "step": 404
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.816991907320999e-05,
+      "loss": 1.493,
+      "step": 406
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8149616108911327e-05,
+      "loss": 1.5228,
+      "step": 408
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8129212619224034e-05,
+      "loss": 1.4622,
+      "step": 410
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8108708855824838e-05,
+      "loss": 1.6105,
+      "step": 412
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.808810507162735e-05,
+      "loss": 1.4222,
+      "step": 414
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8067401520778918e-05,
+      "loss": 1.5116,
+      "step": 416
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8046598458657528e-05,
+      "loss": 1.6267,
+      "step": 418
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8025696141868635e-05,
+      "loss": 1.6338,
+      "step": 420
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.800469482824198e-05,
+      "loss": 1.6313,
+      "step": 422
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.798359477682845e-05,
+      "loss": 1.6542,
+      "step": 424
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7962396247896855e-05,
+      "loss": 1.7611,
+      "step": 426
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7941099502930716e-05,
+      "loss": 1.6318,
+      "step": 428
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7919704804625055e-05,
+      "loss": 1.7348,
+      "step": 430
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.789821241688315e-05,
+      "loss": 1.7121,
+      "step": 432
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.787662260481326e-05,
+      "loss": 1.8076,
+      "step": 434
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.785493563472539e-05,
+      "loss": 1.9255,
+      "step": 436
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7833151774127978e-05,
+      "loss": 1.8057,
+      "step": 438
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.781127129172461e-05,
+      "loss": 1.8363,
+      "step": 440
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7789294457410693e-05,
+      "loss": 2.1584,
+      "step": 442
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7767221542270146e-05,
+      "loss": 2.0338,
+      "step": 444
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7745052818572033e-05,
+      "loss": 2.1332,
+      "step": 446
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.772278855976721e-05,
+      "loss": 2.0207,
+      "step": 448
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.770042904048498e-05,
+      "loss": 1.9562,
+      "step": 450
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7677974536529657e-05,
+      "loss": 1.4179,
+      "step": 452
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.76554253248772e-05,
+      "loss": 1.306,
+      "step": 454
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7632781683671787e-05,
+      "loss": 1.5095,
+      "step": 456
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7610043892222382e-05,
+      "loss": 1.4135,
+      "step": 458
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7587212230999298e-05,
+      "loss": 1.665,
+      "step": 460
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7564286981630713e-05,
+      "loss": 1.527,
+      "step": 462
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7541268426899222e-05,
+      "loss": 1.515,
+      "step": 464
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.751815685073835e-05,
+      "loss": 1.544,
+      "step": 466
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7494952538229034e-05,
+      "loss": 1.6127,
+      "step": 468
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7471655775596097e-05,
+      "loss": 1.5762,
+      "step": 470
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7448266850204754e-05,
+      "loss": 1.7019,
+      "step": 472
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7424786050557036e-05,
+      "loss": 1.6097,
+      "step": 474
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.740121366628824e-05,
+      "loss": 1.6101,
+      "step": 476
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7377549988163373e-05,
+      "loss": 1.6759,
+      "step": 478
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7353795308073526e-05,
+      "loss": 1.7808,
+      "step": 480
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.7329949919032315e-05,
+      "loss": 1.6366,
+      "step": 482
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7306014115172244e-05,
+      "loss": 1.8784,
+      "step": 484
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7281988191741085e-05,
+      "loss": 1.7896,
+      "step": 486
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7257872445098232e-05,
+      "loss": 1.9701,
+      "step": 488
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7233667172711045e-05,
+      "loss": 1.7598,
+      "step": 490
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.7209372673151186e-05,
+      "loss": 1.993,
+      "step": 492
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.718498924609093e-05,
+      "loss": 1.9188,
+      "step": 494
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7160517192299474e-05,
+      "loss": 2.099,
+      "step": 496
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7135956813639222e-05,
+      "loss": 2.0652,
+      "step": 498
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7111308413062063e-05,
+      "loss": 2.0021,
+      "step": 500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7086572294605642e-05,
+      "loss": 1.3524,
+      "step": 502
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.7061748763389593e-05,
+      "loss": 1.3037,
+      "step": 504
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.703683812561179e-05,
+      "loss": 1.6416,
+      "step": 506
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.701184068854457e-05,
+      "loss": 1.3975,
+      "step": 508
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.698675676053092e-05,
+      "loss": 1.3872,
+      "step": 510
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.696158665098072e-05,
+      "loss": 1.5235,
+      "step": 512
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6936330670366867e-05,
+      "loss": 1.6902,
+      "step": 514
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.69109891302215e-05,
+      "loss": 1.6784,
+      "step": 516
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6885562343132124e-05,
+      "loss": 1.7635,
+      "step": 518
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6860050622737764e-05,
+      "loss": 1.5534,
+      "step": 520
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6834454283725094e-05,
+      "loss": 1.6135,
+      "step": 522
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6808773641824562e-05,
+      "loss": 1.6691,
+      "step": 524
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.678300901380649e-05,
+      "loss": 1.6357,
+      "step": 526
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6757160717477157e-05,
+      "loss": 1.6624,
+      "step": 528
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6731229071674914e-05,
+      "loss": 1.6901,
+      "step": 530
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6705214396266196e-05,
+      "loss": 1.8505,
+      "step": 532
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.667911701214163e-05,
+      "loss": 1.9421,
+      "step": 534
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.665293724121204e-05,
+      "loss": 1.9344,
+      "step": 536
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6626675406404503e-05,
+      "loss": 1.9095,
+      "step": 538
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.660033183165834e-05,
+      "loss": 2.0502,
+      "step": 540
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6573906841921138e-05,
+      "loss": 2.2613,
+      "step": 542
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.654740076314474e-05,
+      "loss": 2.0965,
+      "step": 544
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.652081392228121e-05,
+      "loss": 2.1539,
+      "step": 546
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.649414664727883e-05,
+      "loss": 2.1094,
+      "step": 548
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.646739926707801e-05,
+      "loss": 2.0737,
+      "step": 550
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6440572111607287e-05,
+      "loss": 1.2207,
+      "step": 552
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6413665511779197e-05,
+      "loss": 1.45,
+      "step": 554
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6386679799486236e-05,
+      "loss": 1.4834,
+      "step": 556
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.635961530759675e-05,
+      "loss": 1.3523,
+      "step": 558
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6332472369950828e-05,
+      "loss": 1.3546,
+      "step": 560
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6305251321356183e-05,
+      "loss": 1.5468,
+      "step": 562
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6277952497584027e-05,
+      "loss": 1.5853,
+      "step": 564
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6250576235364938e-05,
+      "loss": 1.5904,
+      "step": 566
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6223122872384675e-05,
+      "loss": 1.6946,
+      "step": 568
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.619559274728005e-05,
+      "loss": 1.5193,
+      "step": 570
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6167986199634732e-05,
+      "loss": 1.6101,
+      "step": 572
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6140303569975064e-05,
+      "loss": 1.7246,
+      "step": 574
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6112545199765844e-05,
+      "loss": 1.7018,
+      "step": 576
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6084711431406144e-05,
+      "loss": 1.7813,
+      "step": 578
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.605680260822507e-05,
+      "loss": 1.7158,
+      "step": 580
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6028819074477517e-05,
+      "loss": 1.6571,
+      "step": 582
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.6000761175339944e-05,
+      "loss": 1.8461,
+      "step": 584
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5972629256906105e-05,
+      "loss": 1.7805,
+      "step": 586
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5944423666182776e-05,
+      "loss": 2.0146,
+      "step": 588
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5916144751085485e-05,
+      "loss": 1.9301,
+      "step": 590
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5887792860434207e-05,
+      "loss": 2.0717,
+      "step": 592
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5859368343949084e-05,
+      "loss": 2.1568,
+      "step": 594
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5830871552246076e-05,
+      "loss": 2.0925,
+      "step": 596
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5802302836832673e-05,
+      "loss": 2.119,
+      "step": 598
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.577366255010354e-05,
+      "loss": 2.1738,
+      "step": 600
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5744951045336166e-05,
+      "loss": 1.5105,
+      "step": 602
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5716168676686523e-05,
+      "loss": 1.486,
+      "step": 604
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.568731579918468e-05,
+      "loss": 1.6528,
+      "step": 606
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5658392768730434e-05,
+      "loss": 1.6643,
+      "step": 608
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.562939994208892e-05,
+      "loss": 1.7925,
+      "step": 610
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5600337676886205e-05,
+      "loss": 1.8235,
+      "step": 612
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5571206331604885e-05,
+      "loss": 2.0644,
+      "step": 614
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 1845,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.3933426003492864e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a10bdbf63af0e7a4cf3f2bd78152a316ce73bb83e19443f92f49b7dcd313dc
+size 4600