Upload folder using huggingface_hub

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-1.8B-Chat
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-1.8B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 26,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 13,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff26fa9fc3b29b5f5d8971c459fc247e451702ba679f6d0f7127805cdce715cc
+size 10236368

added_tokens.json

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

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba42a7fe8a57e10690e631749654b4e3ade05ca46b016eeef19b7e8453411a02
+size 20528122

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4309f0ddf54f51237572ca56fecbe23d0d8e14e821dcf5af2ed8a199915128e
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad89ed24dc09d6874f2a51d56e2610358696056858d3efd22159964a77f1309
+size 1064

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2181 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.96,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.5e-06,
+      "loss": 1.3998,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5e-06,
+      "loss": 1.3688,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.5e-06,
+      "loss": 1.4511,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1e-05,
+      "loss": 1.5508,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.25e-05,
+      "loss": 1.4908,
+      "step": 25
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.5e-05,
+      "loss": 1.4012,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.75e-05,
+      "loss": 1.4774,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2e-05,
+      "loss": 1.5198,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.25e-05,
+      "loss": 1.1156,
+      "step": 45
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.5e-05,
+      "loss": 1.2655,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 1.2638,
+      "step": 55
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3e-05,
+      "loss": 1.4318,
+      "step": 60
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 1.2045,
+      "step": 65
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.5e-05,
+      "loss": 1.2026,
+      "step": 70
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.2322,
+      "step": 75
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4e-05,
+      "loss": 0.9502,
+      "step": 80
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.25e-05,
+      "loss": 0.9484,
+      "step": 85
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.5e-05,
+      "loss": 0.9976,
+      "step": 90
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.75e-05,
+      "loss": 0.9654,
+      "step": 95
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5e-05,
+      "loss": 0.9907,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9999021073200754e-05,
+      "loss": 0.8228,
+      "step": 105
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.999608436946682e-05,
+      "loss": 0.9102,
+      "step": 110
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9991190118783634e-05,
+      "loss": 0.8813,
+      "step": 115
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.998433870444026e-05,
+      "loss": 1.0755,
+      "step": 120
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9975530662999344e-05,
+      "loss": 1.0611,
+      "step": 125
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.99647666842551e-05,
+      "loss": 0.8125,
+      "step": 130
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.995204761117933e-05,
+      "loss": 0.9662,
+      "step": 135
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9937374439855336e-05,
+      "loss": 1.1076,
+      "step": 140
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9920748319399966e-05,
+      "loss": 0.7678,
+      "step": 145
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.990217055187362e-05,
+      "loss": 0.9845,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9881642592178265e-05,
+      "loss": 0.8852,
+      "step": 155
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.985916604794348e-05,
+      "loss": 1.1478,
+      "step": 160
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.983474267940059e-05,
+      "loss": 0.8057,
+      "step": 165
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.980837439924478e-05,
+      "loss": 0.9576,
+      "step": 170
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.978006327248537e-05,
+      "loss": 0.9848,
+      "step": 175
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.974981151628398e-05,
+      "loss": 0.866,
+      "step": 180
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.9717621499781034e-05,
+      "loss": 0.8123,
+      "step": 185
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.9683495743910094e-05,
+      "loss": 0.8428,
+      "step": 190
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.9647436921200514e-05,
+      "loss": 0.8741,
+      "step": 195
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.960944785556814e-05,
+      "loss": 1.0406,
+      "step": 200
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.9569531522094126e-05,
+      "loss": 0.951,
+      "step": 205
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.952769104679195e-05,
+      "loss": 0.8859,
+      "step": 210
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.9483929706362616e-05,
+      "loss": 0.9462,
+      "step": 215
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.943825092793806e-05,
+      "loss": 0.7735,
+      "step": 220
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.9390658288812675e-05,
+      "loss": 1.0622,
+      "step": 225
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.9341155516163275e-05,
+      "loss": 0.8898,
+      "step": 230
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.928974648675711e-05,
+      "loss": 1.0837,
+      "step": 235
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.923643522664833e-05,
+      "loss": 1.0851,
+      "step": 240
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.91812259108626e-05,
+      "loss": 0.8921,
+      "step": 245
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.9124122863070255e-05,
+      "loss": 1.1334,
+      "step": 250
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.9065130555247574e-05,
+      "loss": 1.0134,
+      "step": 255
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.900425360732667e-05,
+      "loss": 0.8632,
+      "step": 260
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.894149678683358e-05,
+      "loss": 0.8454,
+      "step": 265
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.887686500851499e-05,
+      "loss": 1.0354,
+      "step": 270
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.881036333395329e-05,
+      "loss": 0.8201,
+      "step": 275
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.874199697117019e-05,
+      "loss": 1.0308,
+      "step": 280
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.8671771274218864e-05,
+      "loss": 0.8313,
+      "step": 285
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.859969174276465e-05,
+      "loss": 0.9553,
+      "step": 290
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.852576402165436e-05,
+      "loss": 0.6957,
+      "step": 295
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.8449993900474187e-05,
+      "loss": 0.8249,
+      "step": 300
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.83723873130963e-05,
+      "loss": 0.8603,
+      "step": 305
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.8292950337214147e-05,
+      "loss": 1.0159,
+      "step": 310
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.82116891938665e-05,
+      "loss": 0.8829,
+      "step": 315
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.812861024695023e-05,
+      "loss": 0.8929,
+      "step": 320
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.804372000272196e-05,
+      "loss": 0.8426,
+      "step": 325
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.795702510928848e-05,
+      "loss": 0.9862,
+      "step": 330
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.786853235608616e-05,
+      "loss": 0.7721,
+      "step": 335
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.77782486733492e-05,
+      "loss": 0.8675,
+      "step": 340
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.768618113156694e-05,
+      "loss": 0.9827,
+      "step": 345
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.75923369409301e-05,
+      "loss": 0.985,
+      "step": 350
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.7496723450766125e-05,
+      "loss": 0.8595,
+      "step": 355
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.739934814896364e-05,
+      "loss": 0.7193,
+      "step": 360
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.730021866138607e-05,
+      "loss": 0.8829,
+      "step": 365
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.719934275127434e-05,
+      "loss": 1.029,
+      "step": 370
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.7096728318639025e-05,
+      "loss": 0.9495,
+      "step": 375
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.6992383399641564e-05,
+      "loss": 1.0201,
+      "step": 380
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.688631616596496e-05,
+      "loss": 1.0748,
+      "step": 385
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.6778534924173816e-05,
+      "loss": 0.8893,
+      "step": 390
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.6669048115063816e-05,
+      "loss": 0.9947,
+      "step": 395
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.6557864313000695e-05,
+      "loss": 0.8135,
+      "step": 400
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.644499222524873e-05,
+      "loss": 0.6328,
+      "step": 405
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.633044069128884e-05,
+      "loss": 0.8124,
+      "step": 410
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.621421868212635e-05,
+      "loss": 0.7317,
+      "step": 415
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.609633529958841e-05,
+      "loss": 0.9451,
+      "step": 420
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.597679977561122e-05,
+      "loss": 0.7934,
+      "step": 425
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.5855621471516997e-05,
+      "loss": 0.8032,
+      "step": 430
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.57328098772809e-05,
+      "loss": 0.8991,
+      "step": 435
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.560837461078779e-05,
+      "loss": 0.9042,
+      "step": 440
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.548232541707904e-05,
+      "loss": 0.6863,
+      "step": 445
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.535467216758936e-05,
+      "loss": 0.8636,
+      "step": 450
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 1.0166,
+      "step": 455
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.5094593614324334e-05,
+      "loss": 0.8609,
+      "step": 460
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.4962188678378254e-05,
+      "loss": 0.9181,
+      "step": 465
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.482822042071466e-05,
+      "loss": 0.8425,
+      "step": 470
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.469269933294296e-05,
+      "loss": 1.0779,
+      "step": 475
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.455563602828113e-05,
+      "loss": 0.7981,
+      "step": 480
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.441704124072455e-05,
+      "loss": 0.8449,
+      "step": 485
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.427692582420536e-05,
+      "loss": 0.9613,
+      "step": 490
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.413530075174245e-05,
+      "loss": 1.0064,
+      "step": 495
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.3992177114582124e-05,
+      "loss": 0.8283,
+      "step": 500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.384756612132952e-05,
+      "loss": 0.7479,
+      "step": 505
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.370147909707077e-05,
+      "loss": 0.9646,
+      "step": 510
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.3553927482486125e-05,
+      "loss": 0.7828,
+      "step": 515
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.340492283295397e-05,
+      "loss": 1.1004,
+      "step": 520
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.325447681764586e-05,
+      "loss": 0.94,
+      "step": 525
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.3102601218612704e-05,
+      "loss": 0.8336,
+      "step": 530
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.2949307929862034e-05,
+      "loss": 0.8661,
+      "step": 535
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.279460895642652e-05,
+      "loss": 0.776,
+      "step": 540
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.263851641342383e-05,
+      "loss": 0.7592,
+      "step": 545
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.2481042525107854e-05,
+      "loss": 0.8982,
+      "step": 550
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.2322199623911354e-05,
+      "loss": 1.0055,
+      "step": 555
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.216200014948014e-05,
+      "loss": 1.029,
+      "step": 560
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.200045664769892e-05,
+      "loss": 0.7536,
+      "step": 565
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.1837581769708755e-05,
+      "loss": 0.9696,
+      "step": 570
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.167338827091627e-05,
+      "loss": 0.809,
+      "step": 575
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.150788900999477e-05,
+      "loss": 0.6986,
+      "step": 580
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.13410969478772e-05,
+      "loss": 0.9191,
+      "step": 585
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.1173025146741115e-05,
+      "loss": 0.7988,
+      "step": 590
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.100368676898574e-05,
+      "loss": 1.2793,
+      "step": 595
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.083309507620118e-05,
+      "loss": 0.9876,
+      "step": 600
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.066126342812979e-05,
+      "loss": 0.9145,
+      "step": 605
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.048820528162002e-05,
+      "loss": 0.7188,
+      "step": 610
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.031393418957246e-05,
+      "loss": 1.0917,
+      "step": 615
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.0138463799878475e-05,
+      "loss": 0.7947,
+      "step": 620
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.996180785435144e-05,
+      "loss": 1.035,
+      "step": 625
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.9783980187650496e-05,
+      "loss": 0.9993,
+      "step": 630
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.960499472619713e-05,
+      "loss": 0.8827,
+      "step": 635
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.942486548708454e-05,
+      "loss": 1.008,
+      "step": 640
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.924360657697987e-05,
+      "loss": 0.9294,
+      "step": 645
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.906123219101952e-05,
+      "loss": 0.9193,
+      "step": 650
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.887775661169738e-05,
+      "loss": 0.9623,
+      "step": 655
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.8693194207746385e-05,
+      "loss": 0.9708,
+      "step": 660
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.8507559433013216e-05,
+      "loss": 0.8962,
+      "step": 665
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.832086682532633e-05,
+      "loss": 0.9749,
+      "step": 670
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.813313100535747e-05,
+      "loss": 0.8436,
+      "step": 675
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.7944366675476686e-05,
+      "loss": 1.119,
+      "step": 680
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.775458861860086e-05,
+      "loss": 0.766,
+      "step": 685
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.756381169703607e-05,
+      "loss": 0.8493,
+      "step": 690
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.737205085131359e-05,
+      "loss": 0.943,
+      "step": 695
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.7179321099019916e-05,
+      "loss": 0.8762,
+      "step": 700
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.69856375336206e-05,
+      "loss": 0.8062,
+      "step": 705
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.6791015323278264e-05,
+      "loss": 1.0253,
+      "step": 710
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.65954697096647e-05,
+      "loss": 0.7868,
+      "step": 715
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.639901600676725e-05,
+      "loss": 1.0347,
+      "step": 720
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.6201669599689465e-05,
+      "loss": 0.9483,
+      "step": 725
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.600344594344628e-05,
+      "loss": 1.087,
+      "step": 730
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.580436056175365e-05,
+      "loss": 1.0731,
+      "step": 735
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.560442904581281e-05,
+      "loss": 0.7429,
+      "step": 740
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.5403667053089265e-05,
+      "loss": 0.9416,
+      "step": 745
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.520209030608662e-05,
+      "loss": 0.9878,
+      "step": 750
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.4999714591115266e-05,
+      "loss": 0.9712,
+      "step": 755
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.479655575705606e-05,
+      "loss": 1.045,
+      "step": 760
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.459262971411918e-05,
+      "loss": 0.9611,
+      "step": 765
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.43879524325981e-05,
+      "loss": 1.0409,
+      "step": 770
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.418253994161892e-05,
+      "loss": 0.9732,
+      "step": 775
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.3976408327885015e-05,
+      "loss": 0.7373,
+      "step": 780
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.3769573734417256e-05,
+      "loss": 0.9754,
+      "step": 785
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.356205235928978e-05,
+      "loss": 0.7527,
+      "step": 790
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.33538604543614e-05,
+      "loss": 0.9828,
+      "step": 795
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.3145014324002944e-05,
+      "loss": 0.8507,
+      "step": 800
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.293553032382032e-05,
+      "loss": 0.9479,
+      "step": 805
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.7149,
+      "step": 810
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.251471438489262e-05,
+      "loss": 0.829,
+      "step": 815
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.230341540198754e-05,
+      "loss": 0.8014,
+      "step": 820
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.209154445835742e-05,
+      "loss": 0.8209,
+      "step": 825
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.187911814649383e-05,
+      "loss": 0.8609,
+      "step": 830
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.166615310238153e-05,
+      "loss": 0.8066,
+      "step": 835
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.145266600419565e-05,
+      "loss": 0.9395,
+      "step": 840
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.1238673570995524e-05,
+      "loss": 0.7853,
+      "step": 845
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.102419256141536e-05,
+      "loss": 0.9172,
+      "step": 850
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.0809239772351824e-05,
+      "loss": 1.2131,
+      "step": 855
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.059383203764857e-05,
+      "loss": 0.9192,
+      "step": 860
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.0377986226777945e-05,
+      "loss": 0.9534,
+      "step": 865
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.016171924351985e-05,
+      "loss": 0.7594,
+      "step": 870
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.9945048024637935e-05,
+      "loss": 0.8499,
+      "step": 875
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.9727989538553232e-05,
+      "loss": 0.9014,
+      "step": 880
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.9510560784015257e-05,
+      "loss": 0.7373,
+      "step": 885
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.9292778788770797e-05,
+      "loss": 1.1039,
+      "step": 890
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.907466060823037e-05,
+      "loss": 0.7907,
+      "step": 895
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.885622332413256e-05,
+      "loss": 0.942,
+      "step": 900
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.863748404320628e-05,
+      "loss": 0.6486,
+      "step": 905
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.8418459895831068e-05,
+      "loss": 1.0279,
+      "step": 910
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.819916803469551e-05,
+      "loss": 0.9169,
+      "step": 915
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.7979625633454004e-05,
+      "loss": 0.9556,
+      "step": 920
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.775984988538175e-05,
+      "loss": 0.8916,
+      "step": 925
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.7539858002028314e-05,
+      "loss": 0.7564,
+      "step": 930
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.7319667211869725e-05,
+      "loss": 0.8854,
+      "step": 935
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.709929475895921e-05,
+      "loss": 1.0735,
+      "step": 940
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.6878757901576773e-05,
+      "loss": 1.0539,
+      "step": 945
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.6658073910877603e-05,
+      "loss": 0.7653,
+      "step": 950
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.6437260069539503e-05,
+      "loss": 0.9273,
+      "step": 955
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.6216333670409453e-05,
+      "loss": 0.7204,
+      "step": 960
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.5995312015149253e-05,
+      "loss": 1.182,
+      "step": 965
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.5774212412880634e-05,
+      "loss": 0.699,
+      "step": 970
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.555305217882967e-05,
+      "loss": 1.0156,
+      "step": 975
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.5331848632970772e-05,
+      "loss": 1.144,
+      "step": 980
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.5110619098670263e-05,
+      "loss": 0.7747,
+      "step": 985
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.488938090132974e-05,
+      "loss": 0.9474,
+      "step": 990
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.4668151367029234e-05,
+      "loss": 0.9307,
+      "step": 995
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.444694782117033e-05,
+      "loss": 1.002,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.422578758711937e-05,
+      "loss": 0.8443,
+      "step": 1005
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.4004687984850753e-05,
+      "loss": 1.1606,
+      "step": 1010
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3783666329590553e-05,
+      "loss": 0.875,
+      "step": 1015
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.35627399304605e-05,
+      "loss": 0.873,
+      "step": 1020
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.334192608912241e-05,
+      "loss": 0.9557,
+      "step": 1025
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.3121242098423233e-05,
+      "loss": 0.7154,
+      "step": 1030
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.2900705241040792e-05,
+      "loss": 0.8942,
+      "step": 1035
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.268033278813028e-05,
+      "loss": 0.9301,
+      "step": 1040
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.2460141997971692e-05,
+      "loss": 1.0188,
+      "step": 1045
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.224015011461826e-05,
+      "loss": 0.8915,
+      "step": 1050
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.2020374366546006e-05,
+      "loss": 0.7145,
+      "step": 1055
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.1800831965304498e-05,
+      "loss": 0.8901,
+      "step": 1060
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.158154010416894e-05,
+      "loss": 0.798,
+      "step": 1065
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.1362515956793715e-05,
+      "loss": 0.8913,
+      "step": 1070
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.114377667586744e-05,
+      "loss": 0.881,
+      "step": 1075
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.0925339391769632e-05,
+      "loss": 0.8176,
+      "step": 1080
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.0707221211229205e-05,
+      "loss": 0.9179,
+      "step": 1085
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.0489439215984742e-05,
+      "loss": 0.8757,
+      "step": 1090
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.027201046144677e-05,
+      "loss": 0.8905,
+      "step": 1095
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.0054951975362067e-05,
+      "loss": 0.9235,
+      "step": 1100
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9838280756480156e-05,
+      "loss": 0.9577,
+      "step": 1105
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.962201377322206e-05,
+      "loss": 0.9302,
+      "step": 1110
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9406167962351435e-05,
+      "loss": 0.8898,
+      "step": 1115
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.9190760227648182e-05,
+      "loss": 1.1963,
+      "step": 1120
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8975807438584642e-05,
+      "loss": 0.9905,
+      "step": 1125
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8761326429004482e-05,
+      "loss": 0.9767,
+      "step": 1130
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8547333995804352e-05,
+      "loss": 0.9304,
+      "step": 1135
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8333846897618473e-05,
+      "loss": 0.8,
+      "step": 1140
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.812088185350618e-05,
+      "loss": 0.7821,
+      "step": 1145
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7908455541642584e-05,
+      "loss": 1.0053,
+      "step": 1150
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.7696584598012463e-05,
+      "loss": 1.0378,
+      "step": 1155
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.7485285615107387e-05,
+      "loss": 0.7936,
+      "step": 1160
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.7954,
+      "step": 1165
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.706446967617968e-05,
+      "loss": 0.9855,
+      "step": 1170
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6854985675997066e-05,
+      "loss": 1.0846,
+      "step": 1175
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.664613954563861e-05,
+      "loss": 0.8494,
+      "step": 1180
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.643794764071024e-05,
+      "loss": 0.837,
+      "step": 1185
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.623042626558275e-05,
+      "loss": 0.8491,
+      "step": 1190
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.602359167211499e-05,
+      "loss": 1.0021,
+      "step": 1195
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5817460058381088e-05,
+      "loss": 0.8144,
+      "step": 1200
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5612047567401904e-05,
+      "loss": 0.8625,
+      "step": 1205
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.540737028588082e-05,
+      "loss": 1.0831,
+      "step": 1210
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.520344424294394e-05,
+      "loss": 0.668,
+      "step": 1215
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.5000285408884735e-05,
+      "loss": 0.7774,
+      "step": 1220
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.4797909693913376e-05,
+      "loss": 1.0238,
+      "step": 1225
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.4596332946910738e-05,
+      "loss": 1.1004,
+      "step": 1230
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.4395570954187199e-05,
+      "loss": 0.8647,
+      "step": 1235
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.4195639438246355e-05,
+      "loss": 0.794,
+      "step": 1240
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3996554056553723e-05,
+      "loss": 0.8817,
+      "step": 1245
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.3798330400310539e-05,
+      "loss": 0.7758,
+      "step": 1250
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.3600983993232758e-05,
+      "loss": 1.1403,
+      "step": 1255
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.3404530290335304e-05,
+      "loss": 0.8733,
+      "step": 1260
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.3208984676721741e-05,
+      "loss": 0.8425,
+      "step": 1265
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.3014362466379407e-05,
+      "loss": 0.8829,
+      "step": 1270
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.2820678900980093e-05,
+      "loss": 0.8972,
+      "step": 1275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.262794914868642e-05,
+      "loss": 0.6963,
+      "step": 1280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.2436188302963944e-05,
+      "loss": 0.7988,
+      "step": 1285
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.224541138139915e-05,
+      "loss": 1.1047,
+      "step": 1290
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.2055633324523324e-05,
+      "loss": 0.9825,
+      "step": 1295
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.1866868994642535e-05,
+      "loss": 0.7205,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1679133174673684e-05,
+      "loss": 0.6994,
+      "step": 1305
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1492440566986795e-05,
+      "loss": 0.7823,
+      "step": 1310
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1306805792253614e-05,
+      "loss": 0.9258,
+      "step": 1315
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.1122243388302621e-05,
+      "loss": 0.7392,
+      "step": 1320
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0938767808980486e-05,
+      "loss": 0.693,
+      "step": 1325
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0756393423020128e-05,
+      "loss": 0.9524,
+      "step": 1330
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0575134512915463e-05,
+      "loss": 0.9227,
+      "step": 1335
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.0395005273802872e-05,
+      "loss": 0.9156,
+      "step": 1340
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.0216019812349508e-05,
+      "loss": 0.7696,
+      "step": 1345
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.0038192145648567e-05,
+      "loss": 0.8188,
+      "step": 1350
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.861536200121534e-06,
+      "loss": 1.1761,
+      "step": 1355
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.686065810427547e-06,
+      "loss": 1.0429,
+      "step": 1360
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.511794718379977e-06,
+      "loss": 0.9353,
+      "step": 1365
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.338736571870204e-06,
+      "loss": 1.0411,
+      "step": 1370
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 9.166904923798821e-06,
+      "loss": 0.8242,
+      "step": 1375
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.996313231014256e-06,
+      "loss": 0.977,
+      "step": 1380
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.826974853258884e-06,
+      "loss": 0.8923,
+      "step": 1385
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.658903052122798e-06,
+      "loss": 0.859,
+      "step": 1390
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.492110990005228e-06,
+      "loss": 0.9146,
+      "step": 1395
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.32661172908373e-06,
+      "loss": 0.848,
+      "step": 1400
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.162418230291249e-06,
+      "loss": 1.0004,
+      "step": 1405
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.99954335230108e-06,
+      "loss": 0.9763,
+      "step": 1410
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.837999850519868e-06,
+      "loss": 0.8771,
+      "step": 1415
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.677800376088656e-06,
+      "loss": 0.766,
+      "step": 1420
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.518957474892149e-06,
+      "loss": 0.8326,
+      "step": 1425
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.3614835865761765e-06,
+      "loss": 1.0521,
+      "step": 1430
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.20539104357349e-06,
+      "loss": 0.7602,
+      "step": 1435
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.0506920701379735e-06,
+      "loss": 1.0047,
+      "step": 1440
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.897398781387299e-06,
+      "loss": 0.9478,
+      "step": 1445
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.745523182354147e-06,
+      "loss": 0.8251,
+      "step": 1450
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.59507716704604e-06,
+      "loss": 0.9253,
+      "step": 1455
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.446072517513879e-06,
+      "loss": 0.7583,
+      "step": 1460
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.298520902929234e-06,
+      "loss": 1.1714,
+      "step": 1465
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.152433878670486e-06,
+      "loss": 0.8578,
+      "step": 1470
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.007822885417882e-06,
+      "loss": 0.9193,
+      "step": 1475
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.864699248257563e-06,
+      "loss": 0.8938,
+      "step": 1480
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.7230741757946485e-06,
+      "loss": 0.9434,
+      "step": 1485
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.582958759275456e-06,
+      "loss": 0.8449,
+      "step": 1490
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.444363971718874e-06,
+      "loss": 0.9795,
+      "step": 1495
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.307300667057049e-06,
+      "loss": 0.8855,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.171779579285352e-06,
+      "loss": 0.8158,
+      "step": 1505
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 5.0378113216217495e-06,
+      "loss": 0.8632,
+      "step": 1510
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.9054063856756674e-06,
+      "loss": 1.0902,
+      "step": 1515
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.7169,
+      "step": 1520
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.645327832410648e-06,
+      "loss": 0.8929,
+      "step": 1525
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.5176745829209614e-06,
+      "loss": 1.1013,
+      "step": 1530
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.391625389212214e-06,
+      "loss": 1.049,
+      "step": 1535
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.2671901227191055e-06,
+      "loss": 0.9125,
+      "step": 1540
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.144378528483009e-06,
+      "loss": 0.919,
+      "step": 1545
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.023200224388787e-06,
+      "loss": 0.9128,
+      "step": 1550
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.903664700411588e-06,
+      "loss": 0.8124,
+      "step": 1555
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.785781317873652e-06,
+      "loss": 0.6316,
+      "step": 1560
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.6695593087111623e-06,
+      "loss": 0.8769,
+      "step": 1565
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.5550077747512732e-06,
+      "loss": 0.9873,
+      "step": 1570
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.4421356869993037e-06,
+      "loss": 0.8763,
+      "step": 1575
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.3309518849361814e-06,
+      "loss": 1.015,
+      "step": 1580
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.2214650758261854e-06,
+      "loss": 0.8868,
+      "step": 1585
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.1136838340350417e-06,
+      "loss": 0.8198,
+      "step": 1590
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.007616600358437e-06,
+      "loss": 0.9481,
+      "step": 1595
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.9032716813609723e-06,
+      "loss": 0.8791,
+      "step": 1600
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.800657248725658e-06,
+      "loss": 0.7747,
+      "step": 1605
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.699781338613938e-06,
+      "loss": 0.7336,
+      "step": 1610
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.600651851036362e-06,
+      "loss": 0.9263,
+      "step": 1615
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.503276549233882e-06,
+      "loss": 0.9969,
+      "step": 1620
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.4076630590699062e-06,
+      "loss": 0.788,
+      "step": 1625
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.3138188684330596e-06,
+      "loss": 1.0097,
+      "step": 1630
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.2217513266508007e-06,
+      "loss": 1.0821,
+      "step": 1635
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.131467643913848e-06,
+      "loss": 1.0141,
+      "step": 1640
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.042974890711524e-06,
+      "loss": 0.8745,
+      "step": 1645
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.956279997278043e-06,
+      "loss": 0.963,
+      "step": 1650
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.8713897530497653e-06,
+      "loss": 0.9889,
+      "step": 1655
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.7883108061335001e-06,
+      "loss": 0.7698,
+      "step": 1660
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.7070496627858563e-06,
+      "loss": 0.8428,
+      "step": 1665
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6276126869037038e-06,
+      "loss": 0.9162,
+      "step": 1670
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.5500060995258137e-06,
+      "loss": 1.1577,
+      "step": 1675
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.4742359783456367e-06,
+      "loss": 1.0998,
+      "step": 1680
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.400308257235347e-06,
+      "loss": 0.8622,
+      "step": 1685
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.3282287257811416e-06,
+      "loss": 0.943,
+      "step": 1690
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2580030288298183e-06,
+      "loss": 0.9814,
+      "step": 1695
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1896366660467173e-06,
+      "loss": 0.7347,
+      "step": 1700
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1231349914850143e-06,
+      "loss": 0.8488,
+      "step": 1705
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0585032131664257e-06,
+      "loss": 1.0964,
+      "step": 1710
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.957463926733385e-07,
+      "loss": 0.9621,
+      "step": 1715
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 9.348694447524259e-07,
+      "loss": 0.7326,
+      "step": 1720
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.758771369297536e-07,
+      "loss": 0.9444,
+      "step": 1725
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.18774089137403e-07,
+      "loss": 0.754,
+      "step": 1730
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.635647733516827e-07,
+      "loss": 0.8082,
+      "step": 1735
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.10253513242895e-07,
+      "loss": 0.8634,
+      "step": 1740
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.588444838367347e-07,
+      "loss": 0.6584,
+      "step": 1745
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.093417111873306e-07,
+      "loss": 0.9802,
+      "step": 1750
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.617490720619511e-07,
+      "loss": 0.9283,
+      "step": 1755
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.160702936373802e-07,
+      "loss": 0.6214,
+      "step": 1760
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.7230895320805044e-07,
+      "loss": 1.0153,
+      "step": 1765
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.3046847790587653e-07,
+      "loss": 0.8742,
+      "step": 1770
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.905521444318605e-07,
+      "loss": 1.1606,
+      "step": 1775
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.5256307879948933e-07,
+      "loss": 0.7276,
+      "step": 1780
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.1650425608991397e-07,
+      "loss": 1.0695,
+      "step": 1785
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.823785002189716e-07,
+      "loss": 0.9512,
+      "step": 1790
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.5018848371601844e-07,
+      "loss": 1.0723,
+      "step": 1795
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.1993672751463579e-07,
+      "loss": 0.8787,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "total_flos": 1.672777000943616e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4dffc4d3093bfbba2a0667994381e3048eee3cb52eb31653da5a3c5d3e2673
+size 4920