Upload folder using huggingface_hub

README.md

@@ -0,0 +1,163 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: qlora-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# qlora-out
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6420
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9758        | 0.03  | 20   | 0.6870          |
+| 0.7228        | 0.06  | 40   | 0.6791          |
+| 0.6804        | 0.09  | 60   | 0.6613          |
+| 0.8117        | 0.11  | 80   | 0.6360          |
+| 0.6458        | 0.14  | 100  | 0.6335          |
+| 0.7509        | 0.17  | 120  | 0.6245          |
+| 0.6174        | 0.2   | 140  | 0.6313          |
+| 0.7549        | 0.23  | 160  | 0.6180          |
+| 0.6015        | 0.26  | 180  | 0.6167          |
+| 0.716         | 0.29  | 200  | 0.6165          |
+| 0.6304        | 0.31  | 220  | 0.6014          |
+| 0.5781        | 0.34  | 240  | 0.6107          |
+| 0.8           | 0.37  | 260  | 0.5949          |
+| 0.6845        | 0.4   | 280  | 0.5953          |
+| 0.5857        | 0.43  | 300  | 0.5940          |
+| 0.6369        | 0.46  | 320  | 0.5889          |
+| 0.4767        | 0.49  | 340  | 0.5946          |
+| 0.4848        | 0.52  | 360  | 0.5991          |
+| 0.9067        | 0.54  | 380  | 0.5943          |
+| 0.5943        | 0.57  | 400  | 0.5854          |
+| 0.6999        | 0.6   | 420  | 0.5941          |
+| 0.5173        | 0.63  | 440  | 0.5887          |
+| 0.4201        | 0.66  | 460  | 0.5952          |
+| 0.667         | 0.69  | 480  | 0.5802          |
+| 0.8568        | 0.72  | 500  | 0.5922          |
+| 0.515         | 0.74  | 520  | 0.5800          |
+| 0.504         | 0.77  | 540  | 0.5894          |
+| 0.6361        | 0.8   | 560  | 0.5983          |
+| 0.4896        | 0.83  | 580  | 0.5770          |
+| 0.6044        | 0.86  | 600  | 0.5717          |
+| 0.4925        | 0.89  | 620  | 0.5715          |
+| 0.4704        | 0.92  | 640  | 0.5707          |
+| 0.5342        | 0.94  | 660  | 0.5748          |
+| 0.755         | 0.97  | 680  | 0.5673          |
+| 0.6547        | 1.0   | 700  | 0.5721          |
+| 0.6014        | 1.03  | 720  | 0.5892          |
+| 0.4692        | 1.06  | 740  | 0.5981          |
+| 0.407         | 1.09  | 760  | 0.5995          |
+| 0.5351        | 1.12  | 780  | 0.5948          |
+| 0.3004        | 1.14  | 800  | 0.5758          |
+| 0.554         | 1.17  | 820  | 0.5862          |
+| 0.6394        | 1.2   | 840  | 0.5850          |
+| 0.7135        | 1.23  | 860  | 0.5900          |
+| 0.6323        | 1.26  | 880  | 0.5931          |
+| 0.3257        | 1.29  | 900  | 0.5902          |
+| 0.5183        | 1.32  | 920  | 0.5763          |
+| 0.5383        | 1.34  | 940  | 0.5842          |
+| 0.453         | 1.37  | 960  | 0.5878          |
+| 0.5305        | 1.4   | 980  | 0.5975          |
+| 0.4316        | 1.43  | 1000 | 0.5829          |
+| 0.5992        | 1.46  | 1020 | 0.5801          |
+| 0.5043        | 1.49  | 1040 | 0.5731          |
+| 0.4566        | 1.52  | 1060 | 0.5777          |
+| 0.4879        | 1.55  | 1080 | 0.5785          |
+| 0.7149        | 1.57  | 1100 | 0.5727          |
+| 0.4555        | 1.6   | 1120 | 0.5824          |
+| 0.5248        | 1.63  | 1140 | 0.5821          |
+| 0.4981        | 1.66  | 1160 | 0.5711          |
+| 0.5595        | 1.69  | 1180 | 0.5931          |
+| 0.577         | 1.72  | 1200 | 0.5898          |
+| 0.3202        | 1.75  | 1220 | 0.5775          |
+| 0.7182        | 1.77  | 1240 | 0.5800          |
+| 0.5608        | 1.8   | 1260 | 0.5668          |
+| 0.5677        | 1.83  | 1280 | 0.5797          |
+| 0.5046        | 1.86  | 1300 | 0.5725          |
+| 0.5165        | 1.89  | 1320 | 0.5709          |
+| 0.6432        | 1.92  | 1340 | 0.5817          |
+| 0.4973        | 1.95  | 1360 | 0.5695          |
+| 0.2903        | 1.97  | 1380 | 0.5762          |
+| 0.3099        | 2.0   | 1400 | 0.5832          |
+| 0.4383        | 2.03  | 1420 | 0.6773          |
+| 0.287         | 2.06  | 1440 | 0.6324          |
+| 0.3395        | 2.09  | 1460 | 0.6600          |
+| 0.2677        | 2.12  | 1480 | 0.6409          |
+| 0.4145        | 2.15  | 1500 | 0.6259          |
+| 0.2435        | 2.17  | 1520 | 0.6528          |
+| 0.2539        | 2.2   | 1540 | 0.6379          |
+| 0.3619        | 2.23  | 1560 | 0.6402          |
+| 0.3289        | 2.26  | 1580 | 0.6355          |
+| 0.4993        | 2.29  | 1600 | 0.6515          |
+| 0.2705        | 2.32  | 1620 | 0.6357          |
+| 0.4863        | 2.35  | 1640 | 0.6385          |
+| 0.356         | 2.37  | 1660 | 0.6364          |
+| 0.3433        | 2.4   | 1680 | 0.6390          |
+| 0.3215        | 2.43  | 1700 | 0.6325          |
+| 0.4795        | 2.46  | 1720 | 0.6336          |
+| 0.3457        | 2.49  | 1740 | 0.6342          |
+| 0.6864        | 2.52  | 1760 | 0.6435          |
+| 0.3965        | 2.55  | 1780 | 0.6447          |
+| 0.3424        | 2.58  | 1800 | 0.6344          |
+| 0.7203        | 2.6   | 1820 | 0.6385          |
+| 0.6209        | 2.63  | 1840 | 0.6475          |
+| 0.3693        | 2.66  | 1860 | 0.6439          |
+| 0.4004        | 2.69  | 1880 | 0.6410          |
+| 0.3499        | 2.72  | 1900 | 0.6392          |
+| 0.4691        | 2.75  | 1920 | 0.6396          |
+| 0.2775        | 2.78  | 1940 | 0.6387          |
+| 0.26          | 2.8   | 1960 | 0.6423          |
+| 0.2917        | 2.83  | 1980 | 0.6432          |
+| 0.4461        | 2.86  | 2000 | 0.6414          |
+| 0.4149        | 2.89  | 2020 | 0.6433          |
+| 0.2863        | 2.92  | 2040 | 0.6428          |
+| 0.1832        | 2.95  | 2060 | 0.6424          |
+| 0.5409        | 2.98  | 2080 | 0.6420          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e9457448b5e801fdc2e9c8428f40a98db53e104fdae6c0391ff361036ed4d1
+size 319977229

checkpoint-1398/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# 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: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-1398/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1398/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff3292cedf441038efba84acacdfa37bab942efd7107d194b5f92c00b3339da0
+size 319977229

checkpoint-1398/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383eeab158877fdde71dbb12aeb67ab77ca64d235db0055bb08fe6c72075c503
+size 639908613

checkpoint-1398/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a6bb6962a339d917c288ead1960493402e9b02073b73feedd269e908fcb2df
+size 14575

checkpoint-1398/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b52a0bfc5d50187cdcd52d78d862c8ad66c418b4de30913ccd1cc5a2d78096be
+size 627

checkpoint-1398/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec169c134980720877e79f395fe6bb950547a52de90d95eec3dd885a9b35107b
+size 4475

checkpoint-2097/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# 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: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-2097/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2097/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e9457448b5e801fdc2e9c8428f40a98db53e104fdae6c0391ff361036ed4d1
+size 319977229

checkpoint-2097/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edaf418483afa5222f0e82204acccc0ec4a85ecb265a4cfac79c5ce566f082d4
+size 639908613

checkpoint-2097/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784df19cfd6f9f1fc0863a8e3e5da380453ebd75c36a36d882f33e3850487076
+size 14575

checkpoint-2097/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a935b762d146e0ba040bdbd51d74ba747682110fd097d5a9a6e5a07a69f2430
+size 627

checkpoint-2097/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec169c134980720877e79f395fe6bb950547a52de90d95eec3dd885a9b35107b
+size 4475

checkpoint-699/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# 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: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-699/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-699/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3b34fb3fe30141e24e9b02d3e4f4285d4609efee60c513dccd3cddd9dbe6f2
+size 319977229

checkpoint-699/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10bf9160c46e9d64e61b5e0143580f8df74fe8c7cd99de74b59f2e3b6d2d5a44
+size 639908613

checkpoint-699/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276c8e7cdcca392e11c241b87343dfe60d9640f48681eb9dbd91c73fd2ad7991
+size 14575

checkpoint-699/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76c99afa3e26a9381596d1682e0d530348cdb6e7c2002297a885960e9c8d103
+size 627

checkpoint-699/trainer_state.json

@@ -0,0 +1,4485 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 20,
+  "global_step": 699,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2e-05,
+      "loss": 3.8527,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4e-05,
+      "loss": 2.357,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6e-05,
+      "loss": 1.6448,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 3.7495,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001,
+      "loss": 3.6283,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00012,
+      "loss": 2.8617,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014,
+      "loss": 2.1554,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016,
+      "loss": 1.5715,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00018,
+      "loss": 1.162,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 0.9593,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999988670134103,
+      "loss": 0.8023,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999954680562074,
+      "loss": 0.9134,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999898031360943,
+      "loss": 0.8533,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999818722659068,
+      "loss": 0.792,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999716754636165,
+      "loss": 0.9903,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999592127523287,
+      "loss": 0.7565,
+      "step": 16
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001999944484160284,
+      "loss": 0.8171,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019999274897208565,
+      "loss": 0.9344,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019999082294725555,
+      "loss": 0.8733,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019998867034590241,
+      "loss": 0.9758,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.6869800090789795,
+      "eval_runtime": 29.3692,
+      "eval_samples_per_second": 55.466,
+      "eval_steps_per_second": 27.75,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019998629117290396,
+      "loss": 0.8391,
+      "step": 21
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001999836854336514,
+      "loss": 1.032,
+      "step": 22
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019998085313404916,
+      "loss": 0.9099,
+      "step": 23
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019997779428051522,
+      "loss": 0.8684,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019997450887998086,
+      "loss": 0.9439,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001999709969398907,
+      "loss": 1.0515,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001999672584682027,
+      "loss": 1.1631,
+      "step": 27
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019996329347338814,
+      "loss": 0.7389,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019995910196443157,
+      "loss": 0.6839,
+      "step": 29
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019995468395083088,
+      "loss": 1.0289,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019995003944259715,
+      "loss": 0.9143,
+      "step": 31
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019994516845025468,
+      "loss": 0.95,
+      "step": 32
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001999400709848411,
+      "loss": 0.9214,
+      "step": 33
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.000199934747057907,
+      "loss": 0.9471,
+      "step": 34
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019992919668151635,
+      "loss": 0.7858,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019992341986824612,
+      "loss": 0.6643,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019991741663118642,
+      "loss": 0.7344,
+      "step": 37
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019991118698394042,
+      "loss": 0.7909,
+      "step": 38
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019990473094062434,
+      "loss": 0.7732,
+      "step": 39
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019989804851586743,
+      "loss": 0.7228,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.6790834069252014,
+      "eval_runtime": 29.3451,
+      "eval_samples_per_second": 55.512,
+      "eval_steps_per_second": 27.773,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019989113972481183,
+      "loss": 0.8713,
+      "step": 41
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001998840045831127,
+      "loss": 0.6862,
+      "step": 42
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019987664310693805,
+      "loss": 0.7524,
+      "step": 43
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019986905531296884,
+      "loss": 0.7405,
+      "step": 44
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001998612412183988,
+      "loss": 0.7113,
+      "step": 45
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019985320084093443,
+      "loss": 0.7264,
+      "step": 46
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019984493419879503,
+      "loss": 0.717,
+      "step": 47
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019983644131071256,
+      "loss": 0.9136,
+      "step": 48
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019982772219593172,
+      "loss": 0.662,
+      "step": 49
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019981877687420975,
+      "loss": 0.6811,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019980960536581654,
+      "loss": 0.7089,
+      "step": 51
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001998002076915345,
+      "loss": 0.774,
+      "step": 52
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019979058387265843,
+      "loss": 0.9975,
+      "step": 53
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001997807339309957,
+      "loss": 0.8504,
+      "step": 54
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019977065788886602,
+      "loss": 0.7098,
+      "step": 55
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001997603557691014,
+      "loss": 0.6549,
+      "step": 56
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019974982759504625,
+      "loss": 0.6731,
+      "step": 57
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000199739073390557,
+      "loss": 0.8107,
+      "step": 58
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019972809318000246,
+      "loss": 0.7196,
+      "step": 59
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019971688698826353,
+      "loss": 0.6804,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.6613275408744812,
+      "eval_runtime": 29.3333,
+      "eval_samples_per_second": 55.534,
+      "eval_steps_per_second": 27.784,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019970545484073306,
+      "loss": 0.7939,
+      "step": 61
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019969379676331602,
+      "loss": 0.7578,
+      "step": 62
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019968191278242934,
+      "loss": 0.792,
+      "step": 63
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019966980292500174,
+      "loss": 0.9361,
+      "step": 64
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019965746721847387,
+      "loss": 0.7841,
+      "step": 65
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019964490569079812,
+      "loss": 0.7706,
+      "step": 66
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019963211837043852,
+      "loss": 0.8221,
+      "step": 67
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019961910528637088,
+      "loss": 0.6315,
+      "step": 68
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0001996058664680824,
+      "loss": 0.6358,
+      "step": 69
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019959240194557197,
+      "loss": 0.7126,
+      "step": 70
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019957871174934978,
+      "loss": 0.5788,
+      "step": 71
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019956479591043752,
+      "loss": 0.7683,
+      "step": 72
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000199550654460368,
+      "loss": 0.7092,
+      "step": 73
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019953628743118546,
+      "loss": 0.7995,
+      "step": 74
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019952169485544516,
+      "loss": 0.6204,
+      "step": 75
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019950687676621352,
+      "loss": 0.6226,
+      "step": 76
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001994918331970679,
+      "loss": 0.5133,
+      "step": 77
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001994765641820966,
+      "loss": 0.9482,
+      "step": 78
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019946106975589884,
+      "loss": 0.7825,
+      "step": 79
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019944534995358458,
+      "loss": 0.8117,
+      "step": 80
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 0.6359772682189941,
+      "eval_runtime": 29.2458,
+      "eval_samples_per_second": 55.7,
+      "eval_steps_per_second": 27.867,
+      "step": 80
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019942940481077446,
+      "loss": 0.844,
+      "step": 81
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019941323436359972,
+      "loss": 0.766,
+      "step": 82
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019939683864870217,
+      "loss": 0.7071,
+      "step": 83
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001993802177032341,
+      "loss": 0.7645,
+      "step": 84
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001993633715648581,
+      "loss": 0.9787,
+      "step": 85
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019934630027174707,
+      "loss": 0.6916,
+      "step": 86
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019932900386258407,
+      "loss": 0.6979,
+      "step": 87
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001993114823765623,
+      "loss": 0.688,
+      "step": 88
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019929373585338508,
+      "loss": 0.8155,
+      "step": 89
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019927576433326544,
+      "loss": 0.6204,
+      "step": 90
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001992575678569264,
+      "loss": 0.8641,
+      "step": 91
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001992391464656007,
+      "loss": 0.758,
+      "step": 92
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001992205002010307,
+      "loss": 0.6035,
+      "step": 93
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019920162910546833,
+      "loss": 0.857,
+      "step": 94
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019918253322167502,
+      "loss": 0.6189,
+      "step": 95
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019916321259292152,
+      "loss": 0.8429,
+      "step": 96
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019914366726298782,
+      "loss": 0.9827,
+      "step": 97
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019912389727616314,
+      "loss": 0.9278,
+      "step": 98
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019910390267724576,
+      "loss": 0.6625,
+      "step": 99
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001990836835115429,
+      "loss": 0.6458,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.6334865093231201,
+      "eval_runtime": 29.3599,
+      "eval_samples_per_second": 55.484,
+      "eval_steps_per_second": 27.759,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001990632398248706,
+      "loss": 0.6327,
+      "step": 101
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019904257166355376,
+      "loss": 0.719,
+      "step": 102
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019902167907442583,
+      "loss": 0.6946,
+      "step": 103
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019900056210482892,
+      "loss": 0.6667,
+      "step": 104
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019897922080261345,
+      "loss": 0.6793,
+      "step": 105
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001989576552161383,
+      "loss": 0.7095,
+      "step": 106
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019893586539427048,
+      "loss": 0.6903,
+      "step": 107
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001989138513863851,
+      "loss": 0.9088,
+      "step": 108
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001988916132423654,
+      "loss": 0.7673,
+      "step": 109
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019886915101260234,
+      "loss": 0.671,
+      "step": 110
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019884646474799475,
+      "loss": 0.6958,
+      "step": 111
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019882355449994915,
+      "loss": 0.6109,
+      "step": 112
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019880042032037947,
+      "loss": 0.7404,
+      "step": 113
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001987770622617072,
+      "loss": 0.7017,
+      "step": 114
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019875348037686106,
+      "loss": 0.8272,
+      "step": 115
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019872967471927692,
+      "loss": 0.8391,
+      "step": 116
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019870564534289783,
+      "loss": 0.6695,
+      "step": 117
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001986813923021737,
+      "loss": 0.7992,
+      "step": 118
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019865691565206122,
+      "loss": 0.7508,
+      "step": 119
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019863221544802386,
+      "loss": 0.7509,
+      "step": 120
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.6245399713516235,
+      "eval_runtime": 29.3529,
+      "eval_samples_per_second": 55.497,
+      "eval_steps_per_second": 27.766,
+      "step": 120
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019860729174603163,
+      "loss": 0.6813,
+      "step": 121
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019858214460256095,
+      "loss": 0.6432,
+      "step": 122
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019855677407459458,
+      "loss": 0.672,
+      "step": 123
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019853118021962148,
+      "loss": 0.7951,
+      "step": 124
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019850536309563656,
+      "loss": 0.7095,
+      "step": 125
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019847932276114083,
+      "loss": 0.6037,
+      "step": 126
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019845305927514094,
+      "loss": 0.5812,
+      "step": 127
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019842657269714923,
+      "loss": 0.6124,
+      "step": 128
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001983998630871836,
+      "loss": 0.6501,
+      "step": 129
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0001983729305057673,
+      "loss": 0.9065,
+      "step": 130
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019834577501392885,
+      "loss": 0.8046,
+      "step": 131
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019831839667320183,
+      "loss": 0.904,
+      "step": 132
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019829079554562487,
+      "loss": 0.5364,
+      "step": 133
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0001982629716937414,
+      "loss": 0.4704,
+      "step": 134
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019823492518059946,
+      "loss": 0.6457,
+      "step": 135
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019820665606975175,
+      "loss": 0.752,
+      "step": 136
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019817816442525526,
+      "loss": 0.7523,
+      "step": 137
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019814945031167134,
+      "loss": 0.675,
+      "step": 138
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001981205137940654,
+      "loss": 0.7782,
+      "step": 139
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019809135493800679,
+      "loss": 0.6174,
+      "step": 140
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.6312826871871948,
+      "eval_runtime": 29.36,
+      "eval_samples_per_second": 55.484,
+      "eval_steps_per_second": 27.759,
+      "step": 140
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019806197380956874,
+      "loss": 0.5355,
+      "step": 141
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019803237047532802,
+      "loss": 0.5741,
+      "step": 142
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019800254500236503,
+      "loss": 0.7357,
+      "step": 143
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019797249745826353,
+      "loss": 0.6641,
+      "step": 144
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001979422279111104,
+      "loss": 0.5884,
+      "step": 145
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019791173642949564,
+      "loss": 0.4902,
+      "step": 146
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019788102308251212,
+      "loss": 0.6585,
+      "step": 147
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019785008793975548,
+      "loss": 0.6445,
+      "step": 148
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019781893107132393,
+      "loss": 0.8865,
+      "step": 149
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019778755254781807,
+      "loss": 0.6996,
+      "step": 150
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019775595244034077,
+      "loss": 0.5696,
+      "step": 151
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019772413082049713,
+      "loss": 0.6353,
+      "step": 152
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019769208776039397,
+      "loss": 0.6547,
+      "step": 153
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019765982333264006,
+      "loss": 1.059,
+      "step": 154
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001976273376103457,
+      "loss": 0.6234,
+      "step": 155
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001975946306671227,
+      "loss": 0.5276,
+      "step": 156
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019756170257708412,
+      "loss": 0.6942,
+      "step": 157
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001975285534148441,
+      "loss": 0.7216,
+      "step": 158
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019749518325551778,
+      "loss": 0.6563,
+      "step": 159
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019746159217472097,
+      "loss": 0.7549,
+      "step": 160
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 0.6180239319801331,
+      "eval_runtime": 29.3051,
+      "eval_samples_per_second": 55.588,
+      "eval_steps_per_second": 27.811,
+      "step": 160
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019742778024857028,
+      "loss": 0.6399,
+      "step": 161
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019739374755368253,
+      "loss": 0.6149,
+      "step": 162
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019735949416717493,
+      "loss": 0.5183,
+      "step": 163
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019732502016666476,
+      "loss": 0.5566,
+      "step": 164
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019729032563026914,
+      "loss": 0.7261,
+      "step": 165
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019725541063660498,
+      "loss": 0.7432,
+      "step": 166
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0001972202752647887,
+      "loss": 0.6235,
+      "step": 167
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019718491959443615,
+      "loss": 0.8306,
+      "step": 168
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019714934370566227,
+      "loss": 0.7739,
+      "step": 169
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019711354767908113,
+      "loss": 0.5514,
+      "step": 170
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0001970775315958055,
+      "loss": 0.6287,
+      "step": 171
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019704129553744696,
+      "loss": 0.5172,
+      "step": 172
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019700483958611534,
+      "loss": 0.5628,
+      "step": 173
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001969681638244189,
+      "loss": 0.5371,
+      "step": 174
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019693126833546392,
+      "loss": 0.5714,
+      "step": 175
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001968941532028546,
+      "loss": 0.7978,
+      "step": 176
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019685681851069285,
+      "loss": 0.7627,
+      "step": 177
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019681926434357802,
+      "loss": 0.5672,
+      "step": 178
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019678149078660692,
+      "loss": 0.639,
+      "step": 179
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019674349792537336,
+      "loss": 0.6015,
+      "step": 180
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.616681694984436,
+      "eval_runtime": 29.315,
+      "eval_samples_per_second": 55.569,
+      "eval_steps_per_second": 27.801,
+      "step": 180
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001967052858459682,
+      "loss": 0.564,
+      "step": 181
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001966668546349789,
+      "loss": 0.6838,
+      "step": 182
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019662820437948967,
+      "loss": 0.6492,
+      "step": 183
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019658933516708085,
+      "loss": 0.7017,
+      "step": 184
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019655024708582904,
+      "loss": 0.7092,
+      "step": 185
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019651094022430686,
+      "loss": 0.4604,
+      "step": 186
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0001964714146715826,
+      "loss": 0.6142,
+      "step": 187
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019643167051722,
+      "loss": 0.6881,
+      "step": 188
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019639170785127835,
+      "loss": 0.5784,
+      "step": 189
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0001963515267643119,
+      "loss": 0.8617,
+      "step": 190
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019631112734737,
+      "loss": 0.7697,
+      "step": 191
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019627050969199655,
+      "loss": 0.5587,
+      "step": 192
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019622967389023015,
+      "loss": 0.5915,
+      "step": 193
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001961886200346036,
+      "loss": 0.9243,
+      "step": 194
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019614734821814383,
+      "loss": 0.7143,
+      "step": 195
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019610585853437165,
+      "loss": 0.9429,
+      "step": 196
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019606415107730165,
+      "loss": 0.5176,
+      "step": 197
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001960222259414417,
+      "loss": 0.5437,
+      "step": 198
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019598008322179312,
+      "loss": 0.6687,
+      "step": 199
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019593772301385016,
+      "loss": 0.716,
+      "step": 200
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 0.6165403127670288,
+      "eval_runtime": 29.3359,
+      "eval_samples_per_second": 55.529,
+      "eval_steps_per_second": 27.782,
+      "step": 200
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001958951454135999,
+      "loss": 0.6579,
+      "step": 201
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.000195852350517522,
+      "loss": 0.6,
+      "step": 202
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019580933842258867,
+      "loss": 0.6689,
+      "step": 203
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019576610922626402,
+      "loss": 0.679,
+      "step": 204
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019572266302650434,
+      "loss": 0.8533,
+      "step": 205
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019567899992175753,
+      "loss": 0.5989,
+      "step": 206
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.000195635120010963,
+      "loss": 0.5986,
+      "step": 207
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019559102339355148,
+      "loss": 0.7082,
+      "step": 208
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019554671016944474,
+      "loss": 0.6403,
+      "step": 209
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019550218043905526,
+      "loss": 0.5886,
+      "step": 210
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019545743430328632,
+      "loss": 0.5391,
+      "step": 211
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001954124718635314,
+      "loss": 0.6303,
+      "step": 212
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001953672932216742,
+      "loss": 0.7248,
+      "step": 213
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019532189848008833,
+      "loss": 0.6166,
+      "step": 214
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019527628774163705,
+      "loss": 0.5582,
+      "step": 215
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019523046110967305,
+      "loss": 0.6682,
+      "step": 216
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019518441868803828,
+      "loss": 0.6317,
+      "step": 217
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001951381605810636,
+      "loss": 0.7702,
+      "step": 218
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019509168689356866,
+      "loss": 0.584,
+      "step": 219
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001950449977308616,
+      "loss": 0.6304,
+      "step": 220
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.6014450192451477,
+      "eval_runtime": 29.301,
+      "eval_samples_per_second": 55.595,
+      "eval_steps_per_second": 27.815,
+      "step": 220
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019499809319873873,
+      "loss": 0.5839,
+      "step": 221
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019495097340348458,
+      "loss": 0.589,
+      "step": 222
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019490363845187125,
+      "loss": 0.8189,
+      "step": 223
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019485608845115854,
+      "loss": 0.5217,
+      "step": 224
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019480832350909344,
+      "loss": 0.6624,
+      "step": 225
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019476034373391005,
+      "loss": 0.9488,
+      "step": 226
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001947121492343292,
+      "loss": 0.7354,
+      "step": 227
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001946637401195584,
+      "loss": 0.6767,
+      "step": 228
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019461511649929137,
+      "loss": 0.6337,
+      "step": 229
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019456627848370793,
+      "loss": 0.436,
+      "step": 230
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001945172261834737,
+      "loss": 0.4473,
+      "step": 231
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019446795970973993,
+      "loss": 0.5208,
+      "step": 232
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019441847917414307,
+      "loss": 0.5907,
+      "step": 233
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001943687846888047,
+      "loss": 0.6171,
+      "step": 234
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019431887636633125,
+      "loss": 0.7125,
+      "step": 235
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019426875431981355,
+      "loss": 0.46,
+      "step": 236
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019421841866282686,
+      "loss": 0.71,
+      "step": 237
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019416786950943044,
+      "loss": 0.6707,
+      "step": 238
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019411710697416726,
+      "loss": 0.4639,
+      "step": 239
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019406613117206397,
+      "loss": 0.5781,
+      "step": 240
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.6106613874435425,
+      "eval_runtime": 29.3327,
+      "eval_samples_per_second": 55.535,
+      "eval_steps_per_second": 27.785,
+      "step": 240
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019401494221863024,
+      "loss": 0.5778,
+      "step": 241
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019396354022985896,
+      "loss": 0.6418,
+      "step": 242
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001939119253222256,
+      "loss": 0.4679,
+      "step": 243
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019386009761268821,
+      "loss": 0.6215,
+      "step": 244
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019380805721868694,
+      "loss": 0.5621,
+      "step": 245
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019375580425814396,
+      "loss": 0.5727,
+      "step": 246
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019370333884946307,
+      "loss": 0.7134,
+      "step": 247
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001936506611115295,
+      "loss": 0.6081,
+      "step": 248
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019359777116370955,
+      "loss": 0.9212,
+      "step": 249
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001935446691258504,
+      "loss": 0.5593,
+      "step": 250
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019349135511827995,
+      "loss": 0.6382,
+      "step": 251
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001934378292618062,
+      "loss": 0.6483,
+      "step": 252
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019338409167771734,
+      "loss": 0.5854,
+      "step": 253
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019333014248778133,
+      "loss": 0.6317,
+      "step": 254
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019327598181424557,
+      "loss": 0.556,
+      "step": 255
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001932216097798367,
+      "loss": 0.7319,
+      "step": 256
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001931670265077602,
+      "loss": 0.6195,
+      "step": 257
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019311223212170045,
+      "loss": 0.5316,
+      "step": 258
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019305722674581996,
+      "loss": 0.753,
+      "step": 259
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019300201050475948,
+      "loss": 0.8,
+      "step": 260
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 0.594850480556488,
+      "eval_runtime": 29.3304,
+      "eval_samples_per_second": 55.54,
+      "eval_steps_per_second": 27.787,
+      "step": 260
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001929465835236375,
+      "loss": 0.5674,
+      "step": 261
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019289094592805011,
+      "loss": 0.5302,
+      "step": 262
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019283509784407058,
+      "loss": 0.621,
+      "step": 263
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019277903939824914,
+      "loss": 0.6329,
+      "step": 264
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019272277071761282,
+      "loss": 0.5637,
+      "step": 265
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019266629192966485,
+      "loss": 0.5367,
+      "step": 266
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019260960316238467,
+      "loss": 0.6705,
+      "step": 267
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019255270454422756,
+      "loss": 0.7982,
+      "step": 268
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019249559620412418,
+      "loss": 0.5728,
+      "step": 269
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019243827827148055,
+      "loss": 0.5841,
+      "step": 270
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019238075087617759,
+      "loss": 0.7056,
+      "step": 271
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019232301414857074,
+      "loss": 0.6554,
+      "step": 272
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019226506821948998,
+      "loss": 0.6277,
+      "step": 273
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019220691322023917,
+      "loss": 0.5815,
+      "step": 274
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019214854928259603,
+      "loss": 0.722,
+      "step": 275
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019208997653881164,
+      "loss": 0.6855,
+      "step": 276
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019203119512161023,
+      "loss": 0.532,
+      "step": 277
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019197220516418902,
+      "loss": 0.5008,
+      "step": 278
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019191300680021755,
+      "loss": 0.5297,
+      "step": 279
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001918536001638378,
+      "loss": 0.6845,
+      "step": 280
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.595288097858429,
+      "eval_runtime": 29.2376,
+      "eval_samples_per_second": 55.716,
+      "eval_steps_per_second": 27.875,
+      "step": 280
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019179398538966358,
+      "loss": 0.6998,
+      "step": 281
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019173416261278044,
+      "loss": 0.8184,
+      "step": 282
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001916741319687451,
+      "loss": 0.4835,
+      "step": 283
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001916138935935854,
+      "loss": 0.7273,
+      "step": 284
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00019155344762379994,
+      "loss": 0.854,
+      "step": 285
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001914927941963576,
+      "loss": 0.6895,
+      "step": 286
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001914319334486975,
+      "loss": 0.6412,
+      "step": 287
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001913708655187284,
+      "loss": 0.5484,
+      "step": 288
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00019130959054482858,
+      "loss": 0.5316,
+      "step": 289
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00019124810866584554,
+      "loss": 0.5696,
+      "step": 290
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019118642002109552,
+      "loss": 0.6214,
+      "step": 291
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019112452475036337,
+      "loss": 0.5533,
+      "step": 292
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019106242299390212,
+      "loss": 0.4784,
+      "step": 293
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019100011489243263,
+      "loss": 0.856,
+      "step": 294
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019093760058714346,
+      "loss": 0.6587,
+      "step": 295
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019087488021969027,
+      "loss": 0.6849,
+      "step": 296
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001908119539321958,
+      "loss": 0.5236,
+      "step": 297
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019074882186724928,
+      "loss": 0.584,
+      "step": 298
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001906854841679063,
+      "loss": 0.5225,
+      "step": 299
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001906219409776884,
+      "loss": 0.5857,
+      "step": 300
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.5940439701080322,
+      "eval_runtime": 29.3378,
+      "eval_samples_per_second": 55.526,
+      "eval_steps_per_second": 27.78,
+      "step": 300
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019055819244058272,
+      "loss": 0.9588,
+      "step": 301
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019049423870104174,
+      "loss": 0.5345,
+      "step": 302
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019043007990398293,
+      "loss": 0.827,
+      "step": 303
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001903657161947884,
+      "loss": 0.53,
+      "step": 304
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001903011477193046,
+      "loss": 0.469,
+      "step": 305
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019023637462384194,
+      "loss": 0.6566,
+      "step": 306
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019017139705517454,
+      "loss": 0.5136,
+      "step": 307
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019010621516053977,
+      "loss": 0.6217,
+      "step": 308
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019004082908763813,
+      "loss": 0.5953,
+      "step": 309
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00018997523898463267,
+      "loss": 0.6747,
+      "step": 310
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00018990944500014883,
+      "loss": 0.5683,
+      "step": 311
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018984344728327395,
+      "loss": 0.8048,
+      "step": 312
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018977724598355717,
+      "loss": 0.5998,
+      "step": 313
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018971084125100882,
+      "loss": 0.6533,
+      "step": 314
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018964423323610026,
+      "loss": 0.5986,
+      "step": 315
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018957742208976344,
+      "loss": 0.5504,
+      "step": 316
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0001895104079633906,
+      "loss": 0.6991,
+      "step": 317
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018944319100883404,
+      "loss": 0.566,
+      "step": 318
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001893757713784055,
+      "loss": 0.5838,
+      "step": 319
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00018930814922487607,
+      "loss": 0.6369,
+      "step": 320
+    },
+    {
+      "epoch": 0.46,
+      "eval_loss": 0.5889019966125488,
+      "eval_runtime": 29.353,
+      "eval_samples_per_second": 55.497,
+      "eval_steps_per_second": 27.765,
+      "step": 320
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00018924032470147575,
+      "loss": 0.6911,
+      "step": 321
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001891722979618931,
+      "loss": 0.839,
+      "step": 322
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001891040691602749,
+      "loss": 0.664,
+      "step": 323
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001890356384512257,
+      "loss": 0.7154,
+      "step": 324
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00018896700598980775,
+      "loss": 0.6249,
+      "step": 325
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001888981719315403,
+      "loss": 0.6035,
+      "step": 326
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018882913643239953,
+      "loss": 0.542,
+      "step": 327
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018875989964881797,
+      "loss": 0.7356,
+      "step": 328
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001886904617376844,
+      "loss": 0.5376,
+      "step": 329
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001886208228563432,
+      "loss": 0.5325,
+      "step": 330
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001885509831625942,
+      "loss": 0.4952,
+      "step": 331
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001884809428146923,
+      "loss": 0.5887,
+      "step": 332
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018841070197134706,
+      "loss": 0.5159,
+      "step": 333
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018834026079172237,
+      "loss": 0.6428,
+      "step": 334
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018826961943543594,
+      "loss": 0.624,
+      "step": 335
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018819877806255933,
+      "loss": 0.7188,
+      "step": 336
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018812773683361708,
+      "loss": 0.4654,
+      "step": 337
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018805649590958678,
+      "loss": 0.7584,
+      "step": 338
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018798505545189844,
+      "loss": 0.5568,
+      "step": 339
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00018791341562243418,
+      "loss": 0.4767,
+      "step": 340
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 0.5945929288864136,
+      "eval_runtime": 29.3121,
+      "eval_samples_per_second": 55.574,
+      "eval_steps_per_second": 27.804,
+      "step": 340
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.000187841576583528,
+      "loss": 0.6751,
+      "step": 341
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00018776953849796514,
+      "loss": 0.4626,
+      "step": 342
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00018769730152898208,
+      "loss": 0.7323,
+      "step": 343
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00018762486584026578,
+      "loss": 0.4619,
+      "step": 344
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0001875522315959536,
+      "loss": 0.6054,
+      "step": 345
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00018747939896063276,
+      "loss": 0.6465,
+      "step": 346
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00018740636809934009,
+      "loss": 0.8281,
+      "step": 347
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00018733313917756154,
+      "loss": 0.6565,
+      "step": 348
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001872597123612319,
+      "loss": 0.6819,
+      "step": 349
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001871860878167344,
+      "loss": 0.7214,
+      "step": 350
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001871122657109002,
+      "loss": 0.6414,
+      "step": 351
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00018703824621100825,
+      "loss": 0.3563,
+      "step": 352
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018696402948478475,
+      "loss": 0.6458,
+      "step": 353
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018688961570040283,
+      "loss": 0.4847,
+      "step": 354
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018681500502648214,
+      "loss": 0.6457,
+      "step": 355
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018674019763208842,
+      "loss": 0.7152,
+      "step": 356
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018666519368673324,
+      "loss": 0.8583,
+      "step": 357
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018658999336037356,
+      "loss": 0.7007,
+      "step": 358
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018651459682341126,
+      "loss": 0.5519,
+      "step": 359
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00018643900424669286,
+      "loss": 0.4848,
+      "step": 360
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 0.5990561842918396,
+      "eval_runtime": 29.3397,
+      "eval_samples_per_second": 55.522,
+      "eval_steps_per_second": 27.778,
+      "step": 360
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00018636321580150917,
+      "loss": 0.5851,
+      "step": 361
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001862872316595947,
+      "loss": 0.5745,
+      "step": 362
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00018621105199312753,
+      "loss": 0.5597,
+      "step": 363
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00018613467697472876,
+      "loss": 0.6364,
+      "step": 364
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001860581067774621,
+      "loss": 0.5668,
+      "step": 365
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00018598134157483354,
+      "loss": 0.7182,
+      "step": 366
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000185904381540791,
+      "loss": 0.5478,
+      "step": 367
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00018582722684972383,
+      "loss": 0.485,
+      "step": 368
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00018574987767646254,
+      "loss": 0.7902,
+      "step": 369
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00018567233419627824,
+      "loss": 0.6895,
+      "step": 370
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00018559459658488238,
+      "loss": 0.6304,
+      "step": 371
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00018551666501842636,
+      "loss": 0.4389,
+      "step": 372
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0001854385396735009,
+      "loss": 0.7157,
+      "step": 373
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018536022072713606,
+      "loss": 0.552,
+      "step": 374
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018528170835680036,
+      "loss": 0.5701,
+      "step": 375
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018520300274040084,
+      "loss": 0.7629,
+      "step": 376
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018512410405628225,
+      "loss": 0.4954,
+      "step": 377
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018504501248322686,
+      "loss": 1.0569,
+      "step": 378
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018496572820045413,
+      "loss": 0.5473,
+      "step": 379
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018488625138762008,
+      "loss": 0.9067,
+      "step": 380
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.5943491458892822,
+      "eval_runtime": 29.3323,
+      "eval_samples_per_second": 55.536,
+      "eval_steps_per_second": 27.785,
+      "step": 380
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018480658222481703,
+      "loss": 0.4678,
+      "step": 381
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0001847267208925732,
+      "loss": 0.7051,
+      "step": 382
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018464666757185216,
+      "loss": 0.3741,
+      "step": 383
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018456642244405266,
+      "loss": 0.6583,
+      "step": 384
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.000184485985691008,
+      "loss": 0.4571,
+      "step": 385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018440535749498563,
+      "loss": 0.4962,
+      "step": 386
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018432453803868696,
+      "loss": 0.6971,
+      "step": 387
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018424352750524668,
+      "loss": 0.7043,
+      "step": 388
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0001841623260782325,
+      "loss": 0.5788,
+      "step": 389
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018408093394164468,
+      "loss": 0.6969,
+      "step": 390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018399935127991554,
+      "loss": 0.6253,
+      "step": 391
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018391757827790933,
+      "loss": 0.6763,
+      "step": 392
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018383561512092138,
+      "loss": 0.6583,
+      "step": 393
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018375346199467807,
+      "loss": 0.5904,
+      "step": 394
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018367111908533615,
+      "loss": 0.8813,
+      "step": 395
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0001835885865794824,
+      "loss": 0.7437,
+      "step": 396
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018350586466413336,
+      "loss": 0.6893,
+      "step": 397
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018342295352673463,
+      "loss": 0.5746,
+      "step": 398
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018333985335516057,
+      "loss": 0.7338,
+      "step": 399
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.000183256564337714,
+      "loss": 0.5943,
+      "step": 400
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.5853814482688904,
+      "eval_runtime": 29.3481,
+      "eval_samples_per_second": 55.506,
+      "eval_steps_per_second": 27.77,
+      "step": 400
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0001831730866631256,
+      "loss": 0.631,
+      "step": 401
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018308942052055354,
+      "loss": 0.5297,
+      "step": 402
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018300556609958304,
+      "loss": 0.6393,
+      "step": 403
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018292152359022595,
+      "loss": 0.4876,
+      "step": 404
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018283729318292036,
+      "loss": 0.5634,
+      "step": 405
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018275287506853017,
+      "loss": 0.4768,
+      "step": 406
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018266826943834445,
+      "loss": 0.9219,
+      "step": 407
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0001825834764840774,
+      "loss": 0.5326,
+      "step": 408
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018249849639786749,
+      "loss": 0.717,
+      "step": 409
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018241332937227734,
+      "loss": 0.7521,
+      "step": 410
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001823279756002932,
+      "loss": 0.8977,
+      "step": 411
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001822424352753244,
+      "loss": 0.7813,
+      "step": 412
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000182156708591203,
+      "loss": 0.8893,
+      "step": 413
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018207079574218338,
+      "loss": 0.6064,
+      "step": 414
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018198469692294174,
+      "loss": 0.8171,
+      "step": 415
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018189841232857571,
+      "loss": 0.6169,
+      "step": 416
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018181194215460388,
+      "loss": 0.5828,
+      "step": 417
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018172528659696533,
+      "loss": 0.5173,
+      "step": 418
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0001816384458520192,
+      "loss": 0.5217,
+      "step": 419
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018155142011654435,
+      "loss": 0.6999,
+      "step": 420
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.5941495299339294,
+      "eval_runtime": 29.3194,
+      "eval_samples_per_second": 55.561,
+      "eval_steps_per_second": 27.797,
+      "step": 420
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0001814642095877387,
+      "loss": 0.5381,
+      "step": 421
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018137681446321903,
+      "loss": 0.7032,
+      "step": 422
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018128923494102028,
+      "loss": 0.5898,
+      "step": 423
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018120147121959536,
+      "loss": 0.4766,
+      "step": 424
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001811135234978145,
+      "loss": 0.5916,
+      "step": 425
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018102539197496482,
+      "loss": 0.5091,
+      "step": 426
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018093707685075004,
+      "loss": 0.7035,
+      "step": 427
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018084857832528987,
+      "loss": 0.7507,
+      "step": 428
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018075989659911956,
+      "loss": 0.4905,
+      "step": 429
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018067103187318956,
+      "loss": 0.5706,
+      "step": 430
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018058198434886492,
+      "loss": 0.784,
+      "step": 431
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018049275422792497,
+      "loss": 0.5877,
+      "step": 432
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018040334171256277,
+      "loss": 0.6392,
+      "step": 433
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018031374700538467,
+      "loss": 0.5623,
+      "step": 434
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018022397030940986,
+      "loss": 0.6878,
+      "step": 435
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018013401182806994,
+      "loss": 0.5297,
+      "step": 436
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00018004387176520843,
+      "loss": 0.4828,
+      "step": 437
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017995355032508027,
+      "loss": 0.5836,
+      "step": 438
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017986304771235143,
+      "loss": 0.5292,
+      "step": 439
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0001797723641320984,
+      "loss": 0.5173,
+      "step": 440
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.5887213349342346,
+      "eval_runtime": 29.3237,
+      "eval_samples_per_second": 55.552,
+      "eval_steps_per_second": 27.793,
+      "step": 440
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017968149978980774,
+      "loss": 0.6018,
+      "step": 441
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017959045489137566,
+      "loss": 0.5353,
+      "step": 442
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017949922964310738,
+      "loss": 0.7697,
+      "step": 443
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00017940782425171693,
+      "loss": 0.4775,
+      "step": 444
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001793162389243264,
+      "loss": 0.6834,
+      "step": 445
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00017922447386846578,
+      "loss": 0.8259,
+      "step": 446
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00017913252929207217,
+      "loss": 0.7376,
+      "step": 447
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001790404054034895,
+      "loss": 0.7481,
+      "step": 448
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001789481024114681,
+      "loss": 0.8861,
+      "step": 449
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00017885562052516398,
+      "loss": 0.4938,
+      "step": 450
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017876295995413867,
+      "loss": 0.5681,
+      "step": 451
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017867012090835854,
+      "loss": 0.4892,
+      "step": 452
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017857710359819436,
+      "loss": 0.6888,
+      "step": 453
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017848390823442086,
+      "loss": 0.5947,
+      "step": 454
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0001783905350282163,
+      "loss": 0.7089,
+      "step": 455
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017829698419116177,
+      "loss": 0.5473,
+      "step": 456
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017820325593524098,
+      "loss": 0.6345,
+      "step": 457
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017810935047283966,
+      "loss": 0.6343,
+      "step": 458
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017801526801674506,
+      "loss": 0.5587,
+      "step": 459
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017792100878014552,
+      "loss": 0.4201,
+      "step": 460
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 0.5952056646347046,
+      "eval_runtime": 29.408,
+      "eval_samples_per_second": 55.393,
+      "eval_steps_per_second": 27.714,
+      "step": 460
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017782657297662992,
+      "loss": 0.6726,
+      "step": 461
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017773196082018728,
+      "loss": 0.5181,
+      "step": 462
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001776371725252062,
+      "loss": 0.4734,
+      "step": 463
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001775422083064744,
+      "loss": 0.5406,
+      "step": 464
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017744706837917828,
+      "loss": 0.4941,
+      "step": 465
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017735175295890233,
+      "loss": 0.5945,
+      "step": 466
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017725626226162874,
+      "loss": 0.5451,
+      "step": 467
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001771605965037369,
+      "loss": 0.6012,
+      "step": 468
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017706475590200285,
+      "loss": 0.6645,
+      "step": 469
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001769687406735988,
+      "loss": 0.8397,
+      "step": 470
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017687255103609266,
+      "loss": 0.4745,
+      "step": 471
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017677618720744764,
+      "loss": 0.9309,
+      "step": 472
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001766796494060215,
+      "loss": 0.5752,
+      "step": 473
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017658293785056638,
+      "loss": 0.846,
+      "step": 474
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017648605276022808,
+      "loss": 0.4726,
+      "step": 475
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017638899435454554,
+      "loss": 0.5713,
+      "step": 476
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001762917628534506,
+      "loss": 0.5512,
+      "step": 477
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017619435847726712,
+      "loss": 0.538,
+      "step": 478
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017609678144671093,
+      "loss": 0.5254,
+      "step": 479
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017599903198288886,
+      "loss": 0.667,
+      "step": 480
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 0.5801939964294434,
+      "eval_runtime": 29.3619,
+      "eval_samples_per_second": 55.48,
+      "eval_steps_per_second": 27.757,
+      "step": 480
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017590111030729862,
+      "loss": 0.8356,
+      "step": 481
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017580301664182812,
+      "loss": 0.6087,
+      "step": 482
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017570475120875495,
+      "loss": 0.5965,
+      "step": 483
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017560631423074591,
+      "loss": 0.5231,
+      "step": 484
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017550770593085662,
+      "loss": 0.595,
+      "step": 485
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0001754089265325308,
+      "loss": 0.5015,
+      "step": 486
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00017530997625959992,
+      "loss": 0.4863,
+      "step": 487
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00017521085533628265,
+      "loss": 0.7477,
+      "step": 488
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00017511156398718439,
+      "loss": 0.5633,
+      "step": 489
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0001750121024372966,
+      "loss": 0.6316,
+      "step": 490
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0001749124709119965,
+      "loss": 0.4627,
+      "step": 491
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0001748126696370465,
+      "loss": 0.662,
+      "step": 492
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017471269883859356,
+      "loss": 0.6426,
+      "step": 493
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017461255874316885,
+      "loss": 0.6185,
+      "step": 494
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017451224957768717,
+      "loss": 0.6106,
+      "step": 495
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017441177156944635,
+      "loss": 0.7092,
+      "step": 496
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0001743111249461269,
+      "loss": 0.816,
+      "step": 497
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017421030993579133,
+      "loss": 0.8185,
+      "step": 498
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017410932676688377,
+      "loss": 0.4779,
+      "step": 499
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00017400817566822938,
+      "loss": 0.8568,
+      "step": 500
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.5921781063079834,
+      "eval_runtime": 29.3482,
+      "eval_samples_per_second": 55.506,
+      "eval_steps_per_second": 27.77,
+      "step": 500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001739068568690338,
+      "loss": 0.6461,
+      "step": 501
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00017380537059888277,
+      "loss": 0.6208,
+      "step": 502
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00017370371708774141,
+      "loss": 0.5665,
+      "step": 503
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001736018965659539,
+      "loss": 0.5903,
+      "step": 504
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00017349990926424273,
+      "loss": 0.5639,
+      "step": 505
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001733977554137085,
+      "loss": 0.5138,
+      "step": 506
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017329543524582898,
+      "loss": 0.5628,
+      "step": 507
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.000173192948992459,
+      "loss": 0.3835,
+      "step": 508
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017309029688582963,
+      "loss": 0.6234,
+      "step": 509
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017298747915854782,
+      "loss": 0.86,
+      "step": 510
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017288449604359576,
+      "loss": 0.7151,
+      "step": 511
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017278134777433044,
+      "loss": 0.554,
+      "step": 512
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017267803458448307,
+      "loss": 0.583,
+      "step": 513
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017257455670815854,
+      "loss": 0.5642,
+      "step": 514
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017247091437983496,
+      "loss": 1.0091,
+      "step": 515
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017236710783436306,
+      "loss": 0.5834,
+      "step": 516
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017226313730696574,
+      "loss": 0.6862,
+      "step": 517
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017215900303323736,
+      "loss": 0.4787,
+      "step": 518
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017205470524914342,
+      "loss": 0.4951,
+      "step": 519
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017195024419101987,
+      "loss": 0.515,
+      "step": 520
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 0.5800089836120605,
+      "eval_runtime": 29.3282,
+      "eval_samples_per_second": 55.544,
+      "eval_steps_per_second": 27.789,
+      "step": 520
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00017184562009557271,
+      "loss": 0.6123,
+      "step": 521
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00017174083319987732,
+      "loss": 0.6898,
+      "step": 522
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000171635883741378,
+      "loss": 0.487,
+      "step": 523
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001715307719578874,
+      "loss": 0.6113,
+      "step": 524
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000171425498087586,
+      "loss": 0.4276,
+      "step": 525
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00017132006236902155,
+      "loss": 0.5996,
+      "step": 526
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00017121446504110859,
+      "loss": 0.564,
+      "step": 527
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017110870634312784,
+      "loss": 0.8961,
+      "step": 528
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017100278651472562,
+      "loss": 0.4929,
+      "step": 529
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0001708967057959135,
+      "loss": 0.5149,
+      "step": 530
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017079046442706748,
+      "loss": 0.4424,
+      "step": 531
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017068406264892768,
+      "loss": 1.0212,
+      "step": 532
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017057750070259765,
+      "loss": 0.4541,
+      "step": 533
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017047077882954392,
+      "loss": 0.7563,
+      "step": 534
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0001703638972715954,
+      "loss": 0.644,
+      "step": 535
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00017025685627094283,
+      "loss": 0.4545,
+      "step": 536
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00017014965607013824,
+      "loss": 0.61,
+      "step": 537
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0001700422969120944,
+      "loss": 0.6925,
+      "step": 538
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016993477904008432,
+      "loss": 0.4985,
+      "step": 539
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016982710269774058,
+      "loss": 0.504,
+      "step": 540
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.5893893241882324,
+      "eval_runtime": 29.3252,
+      "eval_samples_per_second": 55.55,
+      "eval_steps_per_second": 27.792,
+      "step": 540
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016971926812905488,
+      "loss": 0.3721,
+      "step": 541
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016961127557837751,
+      "loss": 0.5396,
+      "step": 542
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016950312529041663,
+      "loss": 0.4731,
+      "step": 543
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001693948175102379,
+      "loss": 0.5411,
+      "step": 544
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001692863524832639,
+      "loss": 0.6364,
+      "step": 545
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016917773045527343,
+      "loss": 0.5857,
+      "step": 546
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016906895167240112,
+      "loss": 0.7359,
+      "step": 547
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001689600163811367,
+      "loss": 0.5994,
+      "step": 548
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0001688509248283247,
+      "loss": 0.5892,
+      "step": 549
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016874167726116363,
+      "loss": 0.7209,
+      "step": 550
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016863227392720554,
+      "loss": 0.5054,
+      "step": 551
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016852271507435544,
+      "loss": 0.5956,
+      "step": 552
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016841300095087077,
+      "loss": 0.5568,
+      "step": 553
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016830313180536078,
+      "loss": 0.6406,
+      "step": 554
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016819310788678603,
+      "loss": 0.6066,
+      "step": 555
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016808292944445774,
+      "loss": 0.4708,
+      "step": 556
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0001679725967280373,
+      "loss": 0.6026,
+      "step": 557
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016786210998753575,
+      "loss": 0.8752,
+      "step": 558
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016775146947331298,
+      "loss": 0.7405,
+      "step": 559
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016764067543607753,
+      "loss": 0.6361,
+      "step": 560
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.5982840657234192,
+      "eval_runtime": 29.3385,
+      "eval_samples_per_second": 55.524,
+      "eval_steps_per_second": 27.779,
+      "step": 560
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016752972812688564,
+      "loss": 0.6528,
+      "step": 561
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016741862779714098,
+      "loss": 0.5128,
+      "step": 562
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00016730737469859388,
+      "loss": 0.723,
+      "step": 563
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00016719596908334092,
+      "loss": 0.5223,
+      "step": 564
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0001670844112038242,
+      "loss": 0.5353,
+      "step": 565
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0001669727013128309,
+      "loss": 0.7645,
+      "step": 566
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00016686083966349266,
+      "loss": 0.6167,
+      "step": 567
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00016674882650928493,
+      "loss": 0.3836,
+      "step": 568
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00016663666210402656,
+      "loss": 0.6045,
+      "step": 569
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016652434670187907,
+      "loss": 0.5973,
+      "step": 570
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0001664118805573461,
+      "loss": 0.5661,
+      "step": 571
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000166299263925273,
+      "loss": 0.4528,
+      "step": 572
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016618649706084596,
+      "loss": 0.6458,
+      "step": 573
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016607358021959173,
+      "loss": 0.412,
+      "step": 574
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0001659605136573768,
+      "loss": 0.5031,
+      "step": 575
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016584729763040697,
+      "loss": 0.4902,
+      "step": 576
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00016573393239522678,
+      "loss": 0.8064,
+      "step": 577
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00016562041820871874,
+      "loss": 0.5497,
+      "step": 578
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.000165506755328103,
+      "loss": 0.6602,
+      "step": 579
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00016539294401093658,
+      "loss": 0.4896,
+      "step": 580
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 0.5770359039306641,
+      "eval_runtime": 29.3487,
+      "eval_samples_per_second": 55.505,
+      "eval_steps_per_second": 27.77,
+      "step": 580
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00016527898451511287,
+      "loss": 0.3522,
+      "step": 581
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00016516487709886105,
+      "loss": 0.6396,
+      "step": 582
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0001650506220207454,
+      "loss": 0.8431,
+      "step": 583
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016493621953966495,
+      "loss": 0.5146,
+      "step": 584
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016482166991485265,
+      "loss": 0.5748,
+      "step": 585
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016470697340587476,
+      "loss": 0.5961,
+      "step": 586
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016459213027263063,
+      "loss": 0.5165,
+      "step": 587
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016447714077535167,
+      "loss": 0.8974,
+      "step": 588
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000164362005174601,
+      "loss": 0.839,
+      "step": 589
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016424672373127277,
+      "loss": 0.5579,
+      "step": 590
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00016413129670659167,
+      "loss": 0.832,
+      "step": 591
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00016401572436211222,
+      "loss": 0.7778,
+      "step": 592
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001639000069597183,
+      "loss": 0.4416,
+      "step": 593
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001637841447616224,
+      "loss": 0.4954,
+      "step": 594
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001636681380303652,
+      "loss": 0.487,
+      "step": 595
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00016355198702881478,
+      "loss": 0.6773,
+      "step": 596
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001634356920201662,
+      "loss": 0.5598,
+      "step": 597
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016331925326794087,
+      "loss": 0.4758,
+      "step": 598
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016320267103598585,
+      "loss": 0.5392,
+      "step": 599
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016308594558847337,
+      "loss": 0.6044,
+      "step": 600
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.5716915726661682,
+      "eval_runtime": 29.3528,
+      "eval_samples_per_second": 55.497,
+      "eval_steps_per_second": 27.766,
+      "step": 600
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016296907718990015,
+      "loss": 0.543,
+      "step": 601
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016285206610508685,
+      "loss": 0.677,
+      "step": 602
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016273491259917745,
+      "loss": 0.8737,
+      "step": 603
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0001626176169376387,
+      "loss": 0.6001,
+      "step": 604
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0001625001793862593,
+      "loss": 0.6186,
+      "step": 605
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0001623826002111497,
+      "loss": 0.6821,
+      "step": 606
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016226487967874116,
+      "loss": 0.4421,
+      "step": 607
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016214701805578518,
+      "loss": 0.5087,
+      "step": 608
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0001620290156093531,
+      "loss": 0.465,
+      "step": 609
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016191087260683523,
+      "loss": 0.5147,
+      "step": 610
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016179258931594051,
+      "loss": 0.6099,
+      "step": 611
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0001616741660046957,
+      "loss": 0.6062,
+      "step": 612
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016155560294144479,
+      "loss": 0.5735,
+      "step": 613
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016143690039484857,
+      "loss": 0.6008,
+      "step": 614
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016131805863388378,
+      "loss": 0.6302,
+      "step": 615
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016119907792784267,
+      "loss": 0.5624,
+      "step": 616
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016107995854633235,
+      "loss": 0.5803,
+      "step": 617
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016096070075927415,
+      "loss": 0.5977,
+      "step": 618
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00016084130483690295,
+      "loss": 0.4958,
+      "step": 619
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0001607217710497668,
+      "loss": 0.4925,
+      "step": 620
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 0.5715158581733704,
+      "eval_runtime": 29.3023,
+      "eval_samples_per_second": 55.593,
+      "eval_steps_per_second": 27.813,
+      "step": 620
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.000160602099668726,
+      "loss": 0.641,
+      "step": 621
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00016048229096495272,
+      "loss": 0.5944,
+      "step": 622
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00016036234520993024,
+      "loss": 0.655,
+      "step": 623
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0001602422626754524,
+      "loss": 0.3301,
+      "step": 624
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0001601220436336231,
+      "loss": 0.6563,
+      "step": 625
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00016000168835685535,
+      "loss": 0.6173,
+      "step": 626
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015988119711787105,
+      "loss": 0.7029,
+      "step": 627
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0001597605701897001,
+      "loss": 0.7588,
+      "step": 628
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015963980784567986,
+      "loss": 0.527,
+      "step": 629
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015951891035945464,
+      "loss": 0.6378,
+      "step": 630
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0001593978780049748,
+      "loss": 0.5056,
+      "step": 631
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015927671105649648,
+      "loss": 0.6517,
+      "step": 632
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015915540978858066,
+      "loss": 1.0716,
+      "step": 633
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015903397447609288,
+      "loss": 0.5948,
+      "step": 634
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0001589124053942022,
+      "loss": 0.4883,
+      "step": 635
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0001587907028183809,
+      "loss": 0.5172,
+      "step": 636
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015866886702440384,
+      "loss": 0.4618,
+      "step": 637
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015854689828834757,
+      "loss": 0.7591,
+      "step": 638
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015842479688659003,
+      "loss": 0.435,
+      "step": 639
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015830256309580968,
+      "loss": 0.4704,
+      "step": 640
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 0.5707182288169861,
+      "eval_runtime": 29.3397,
+      "eval_samples_per_second": 55.522,
+      "eval_steps_per_second": 27.778,
+      "step": 640
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015818019719298504,
+      "loss": 0.6049,
+      "step": 641
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015805769945539394,
+      "loss": 0.5501,
+      "step": 642
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015793507016061305,
+      "loss": 0.7212,
+      "step": 643
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015781230958651694,
+      "loss": 0.6531,
+      "step": 644
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015768941801127783,
+      "loss": 0.9526,
+      "step": 645
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015756639571336476,
+      "loss": 0.5878,
+      "step": 646
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015744324297154293,
+      "loss": 0.46,
+      "step": 647
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015731996006487317,
+      "loss": 0.4893,
+      "step": 648
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015719654727271122,
+      "loss": 0.5149,
+      "step": 649
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015707300487470717,
+      "loss": 0.6435,
+      "step": 650
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015694933315080477,
+      "loss": 0.5271,
+      "step": 651
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015682553238124082,
+      "loss": 0.4587,
+      "step": 652
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015670160284654458,
+      "loss": 0.4208,
+      "step": 653
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015657754482753704,
+      "loss": 0.5887,
+      "step": 654
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0001564533586053303,
+      "loss": 0.6264,
+      "step": 655
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015632904446132706,
+      "loss": 0.6527,
+      "step": 656
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015620460267721983,
+      "loss": 0.6423,
+      "step": 657
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015608003353499033,
+      "loss": 0.5313,
+      "step": 658
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0001559553373169089,
+      "loss": 0.58,
+      "step": 659
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015583051430553385,
+      "loss": 0.5342,
+      "step": 660
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.5747966766357422,
+      "eval_runtime": 29.3347,
+      "eval_samples_per_second": 55.531,
+      "eval_steps_per_second": 27.783,
+      "step": 660
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015570556478371075,
+      "loss": 0.6231,
+      "step": 661
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0001555804890345719,
+      "loss": 0.3901,
+      "step": 662
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015545528734153553,
+      "loss": 0.5303,
+      "step": 663
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0001553299599883054,
+      "loss": 0.5951,
+      "step": 664
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015520450725886988,
+      "loss": 0.4837,
+      "step": 665
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015507892943750147,
+      "loss": 0.6,
+      "step": 666
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0001549532268087562,
+      "loss": 0.5726,
+      "step": 667
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015482739965747282,
+      "loss": 0.5652,
+      "step": 668
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001547014482687723,
+      "loss": 0.8029,
+      "step": 669
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001545753729280571,
+      "loss": 0.6563,
+      "step": 670
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015444917392101054,
+      "loss": 0.5851,
+      "step": 671
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001543228515335962,
+      "loss": 0.4526,
+      "step": 672
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015419640605205727,
+      "loss": 0.6139,
+      "step": 673
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001540698377629157,
+      "loss": 0.5471,
+      "step": 674
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.000153943146952972,
+      "loss": 0.5244,
+      "step": 675
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015381633390930402,
+      "loss": 0.6256,
+      "step": 676
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0001536893989192668,
+      "loss": 0.4401,
+      "step": 677
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015356234227049154,
+      "loss": 0.5637,
+      "step": 678
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015343516425088524,
+      "loss": 0.5212,
+      "step": 679
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0001533078651486299,
+      "loss": 0.755,
+      "step": 680
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 0.5672922730445862,
+      "eval_runtime": 29.3376,
+      "eval_samples_per_second": 55.526,
+      "eval_steps_per_second": 27.78,
+      "step": 680
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0001531804452521818,
+      "loss": 0.6678,
+      "step": 681
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015305290485027114,
+      "loss": 0.413,
+      "step": 682
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015292524423190094,
+      "loss": 0.7693,
+      "step": 683
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015279746368634673,
+      "loss": 0.7246,
+      "step": 684
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015266956350315586,
+      "loss": 0.5489,
+      "step": 685
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0001525415439721467,
+      "loss": 0.6732,
+      "step": 686
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015241340538340808,
+      "loss": 0.4387,
+      "step": 687
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0001522851480272986,
+      "loss": 0.7792,
+      "step": 688
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015215677219444594,
+      "loss": 0.4398,
+      "step": 689
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0001520282781757464,
+      "loss": 0.5612,
+      "step": 690
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015189966626236385,
+      "loss": 0.7103,
+      "step": 691
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0001517709367457295,
+      "loss": 0.6044,
+      "step": 692
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.000151642089917541,
+      "loss": 0.6622,
+      "step": 693
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0001515131260697618,
+      "loss": 0.4819,
+      "step": 694
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015138404549462053,
+      "loss": 0.5547,
+      "step": 695
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00015125484848461026,
+      "loss": 0.6227,
+      "step": 696
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.000151125535332488,
+      "loss": 0.4646,
+      "step": 697
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00015099610633127387,
+      "loss": 0.5327,
+      "step": 698
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00015086656177425048,
+      "loss": 0.5109,
+      "step": 699
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2097,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 9.190285595765637e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-699/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec169c134980720877e79f395fe6bb950547a52de90d95eec3dd885a9b35107b
+size 4475

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}