Upload 41 files

README.md

@@ -0,0 +1,167 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: mid-nids
+  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)
+# mid-nids
+
+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: 0.0342
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 4
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0682        | 0.03  | 20   | 0.0982          |
+| 0.0895        | 0.06  | 40   | 0.0792          |
+| 0.015         | 0.09  | 60   | 0.0405          |
+| 0.0376        | 0.11  | 80   | 0.0357          |
+| 0.0196        | 0.14  | 100  | 0.0342          |
+| 0.0219        | 0.17  | 120  | 0.0334          |
+| 0.0188        | 0.2   | 140  | 0.0317          |
+| 0.0147        | 0.23  | 160  | 0.0365          |
+| 0.0224        | 0.26  | 180  | 0.0388          |
+| 0.0116        | 0.28  | 200  | 0.0504          |
+| 0.0158        | 0.31  | 220  | 0.0692          |
+| 0.0193        | 0.34  | 240  | 0.0407          |
+| 0.0181        | 0.37  | 260  | 0.0443          |
+| 0.0124        | 0.4   | 280  | 0.0482          |
+| 0.0094        | 0.43  | 300  | 0.0549          |
+| 0.0081        | 0.46  | 320  | 0.0341          |
+| 0.0188        | 0.48  | 340  | 0.0401          |
+| 0.021         | 0.51  | 360  | 0.0508          |
+| 0.0125        | 0.54  | 380  | 0.0409          |
+| 0.0071        | 0.57  | 400  | 0.0424          |
+| 0.0165        | 0.6   | 420  | 0.0566          |
+| 0.0075        | 0.63  | 440  | 0.0537          |
+| 0.0096        | 0.65  | 460  | 0.0338          |
+| 0.012         | 0.68  | 480  | 0.0489          |
+| 0.0041        | 0.71  | 500  | 0.0442          |
+| 0.0012        | 0.74  | 520  | 0.0439          |
+| 0.0096        | 0.77  | 540  | 0.0381          |
+| 0.005         | 0.8   | 560  | 0.0449          |
+| 0.0239        | 0.83  | 580  | 0.0452          |
+| 0.0166        | 0.85  | 600  | 0.0383          |
+| 0.0081        | 0.88  | 620  | 0.0249          |
+| 0.0166        | 0.91  | 640  | 0.0442          |
+| 0.0106        | 0.94  | 660  | 0.0327          |
+| 0.0161        | 0.97  | 680  | 0.0386          |
+| 0.0038        | 1.0   | 700  | 0.0377          |
+| 0.0029        | 1.02  | 720  | 0.0367          |
+| 0.0164        | 1.05  | 740  | 0.0276          |
+| 0.0128        | 1.08  | 760  | 0.0259          |
+| 0.0108        | 1.11  | 780  | 0.0294          |
+| 0.026         | 1.14  | 800  | 0.0285          |
+| 0.0104        | 1.17  | 820  | 0.0297          |
+| 0.0102        | 1.19  | 840  | 0.0271          |
+| 0.0111        | 1.22  | 860  | 0.0293          |
+| 0.0088        | 1.25  | 880  | 0.0305          |
+| 0.0116        | 1.28  | 900  | 0.0250          |
+| 0.0066        | 1.31  | 920  | 0.0442          |
+| 0.0061        | 1.34  | 940  | 0.0309          |
+| 0.0173        | 1.37  | 960  | 0.0231          |
+| 0.0032        | 1.39  | 980  | 0.0230          |
+| 0.0119        | 1.42  | 1000 | 0.0401          |
+| 0.0083        | 1.45  | 1020 | 0.0274          |
+| 0.0047        | 1.48  | 1040 | 0.0359          |
+| 0.0221        | 1.51  | 1060 | 0.0301          |
+| 0.0038        | 1.54  | 1080 | 0.0280          |
+| 0.0052        | 1.56  | 1100 | 0.0235          |
+| 0.0084        | 1.59  | 1120 | 0.0323          |
+| 0.012         | 1.62  | 1140 | 0.0320          |
+| 0.0019        | 1.65  | 1160 | 0.0256          |
+| 0.0175        | 1.68  | 1180 | 0.0300          |
+| 0.0078        | 1.71  | 1200 | 0.0362          |
+| 0.0088        | 1.74  | 1220 | 0.0310          |
+| 0.0065        | 1.76  | 1240 | 0.0301          |
+| 0.0059        | 1.79  | 1260 | 0.0348          |
+| 0.0066        | 1.82  | 1280 | 0.0341          |
+| 0.0015        | 1.85  | 1300 | 0.0280          |
+| 0.0091        | 1.88  | 1320 | 0.0266          |
+| 0.0053        | 1.91  | 1340 | 0.0350          |
+| 0.0077        | 1.93  | 1360 | 0.0333          |
+| 0.0081        | 1.96  | 1380 | 0.0320          |
+| 0.0129        | 1.99  | 1400 | 0.0391          |
+| 0.0082        | 2.02  | 1420 | 0.0388          |
+| 0.008         | 2.05  | 1440 | 0.0212          |
+| 0.0025        | 2.08  | 1460 | 0.0362          |
+| 0.0006        | 2.11  | 1480 | 0.0289          |
+| 0.0034        | 2.13  | 1500 | 0.0347          |
+| 0.0115        | 2.16  | 1520 | 0.0313          |
+| 0.0061        | 2.19  | 1540 | 0.0297          |
+| 0.0065        | 2.22  | 1560 | 0.0335          |
+| 0.0144        | 2.25  | 1580 | 0.0379          |
+| 0.0075        | 2.28  | 1600 | 0.0300          |
+| 0.0093        | 2.3   | 1620 | 0.0322          |
+| 0.0091        | 2.33  | 1640 | 0.0313          |
+| 0.0051        | 2.36  | 1660 | 0.0278          |
+| 0.0046        | 2.39  | 1680 | 0.0294          |
+| 0.0004        | 2.42  | 1700 | 0.0283          |
+| 0.0054        | 2.45  | 1720 | 0.0296          |
+| 0.0034        | 2.48  | 1740 | 0.0337          |
+| 0.0065        | 2.5   | 1760 | 0.0341          |
+| 0.0034        | 2.53  | 1780 | 0.0345          |
+| 0.0114        | 2.56  | 1800 | 0.0371          |
+| 0.0044        | 2.59  | 1820 | 0.0377          |
+| 0.0086        | 2.62  | 1840 | 0.0344          |
+| 0.0065        | 2.65  | 1860 | 0.0332          |
+| 0.0051        | 2.67  | 1880 | 0.0344          |
+| 0.008         | 2.7   | 1900 | 0.0355          |
+| 0.0035        | 2.73  | 1920 | 0.0351          |
+| 0.0065        | 2.76  | 1940 | 0.0352          |
+| 0.0097        | 2.79  | 1960 | 0.0347          |
+| 0.0034        | 2.82  | 1980 | 0.0347          |
+| 0.0054        | 2.84  | 2000 | 0.0348          |
+| 0.0045        | 2.87  | 2020 | 0.0344          |
+| 0.0032        | 2.9   | 2040 | 0.0343          |
+| 0.0072        | 2.93  | 2060 | 0.0342          |
+| 0.0074        | 2.96  | 2080 | 0.0344          |
+| 0.0111        | 2.99  | 2100 | 0.0342          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu117
+- 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": [
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0ae85e5ae693f1d3caedf19e7bc8bf0a88cacb6e12f3a18c57c205e44d9e20
+size 319977229

checkpoint-1406/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: True
+- load_in_4bit: False
+- 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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.7.0.dev0

checkpoint-1406/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": [
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1406/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05099d9c30a39fff51fb853b86eb10cffb2721398dbfce005395f1151f60dd49
+size 319977229

checkpoint-1406/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d2a4ae9032069d56ba507908d535003ab01b499498f5d16d847f03c156e772
+size 160736095

checkpoint-1406/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6bb1fdbde844889354bbb27d1d1a5675bdcbd5078d10eb563ee7898fd4971df
+size 17655

checkpoint-1406/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329b9fd81ba172a415c020ca29f9a1dede713ba98ea6ac90b9017b5ebe54c4c8
+size 17655

checkpoint-1406/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387a69e82135d50bd7039ecf3bf58d4d374eaa89f6f3c7c9d10e5f7c32043100
+size 17655

checkpoint-1406/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792356ca922c0cec662b13eafaf604e762b721920d72aba037aae47c2d413d43
+size 17655

checkpoint-1406/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4cfbb0692c3156463e2efb538441a09b4307943dba5d25113ec0576f73c832
+size 627

checkpoint-1406/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f130e25197a3f46f0428131d8b9093939760918998e06b5589ad2fbdf87ef81f
+size 4475

checkpoint-2109/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: True
+- load_in_4bit: False
+- 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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.7.0.dev0

checkpoint-2109/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": [
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-2109/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0ae85e5ae693f1d3caedf19e7bc8bf0a88cacb6e12f3a18c57c205e44d9e20
+size 319977229

checkpoint-2109/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c17bc205dae87cc849562081ac3cf5ffe991d131ee665b097ce292a756bc5c
+size 160736095

checkpoint-2109/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d073a1dc64070b7ab3e6f0b3ed16937bb52420f0f27e4540c746ec2fb338a141
+size 17655

checkpoint-2109/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e5a3baca4b10907079198dcab43f9e007a1662540e40125c81f0b267ab0fcd
+size 17655

checkpoint-2109/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79cae11deaee0f8c12f55aa4a85fbfe74293242362487bfe5c9ee4f530b839b
+size 17655

checkpoint-2109/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b028b8cf231033635774a069f1817a4fdd89b4ca6e3f975beff5be9b7284301f
+size 17655

checkpoint-2109/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5cbc89a7ad3b176f3e4280e5d7af393a38483dccfc4ed5392d2ffc95ea80596
+size 627

checkpoint-2109/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f130e25197a3f46f0428131d8b9093939760918998e06b5589ad2fbdf87ef81f
+size 4475

checkpoint-703/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: True
+- load_in_4bit: False
+- 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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
+- PEFT 0.7.0.dev0

checkpoint-703/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": [
+    "down_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-703/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd296b190634d7ee3d22bc12a549ad7a41cf711d206bf10427fbbd9ffe8eaa9
+size 319977229

checkpoint-703/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0c4b64927aace0017b60ec20ed2a22f68860e113a76da0de3724b02952a55ed
+size 160736095

checkpoint-703/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:345bbf15aacbe08f2f1dfb6b26a436b94ed679269cb367dde8c8a42ae5bf45f3
+size 17655

checkpoint-703/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2bc682b1de5dbfb1597197e083b20aff56186d3a169940aaa8ecbb08260a79
+size 17655

checkpoint-703/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6ab98ea00f614bad9166313e822626a8383231e46c3f3976a432613f2da385
+size 17655

checkpoint-703/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:718ffd8973acd4841f384fc506cafbe064bb741a55110272379940724339a1de
+size 17655

checkpoint-703/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab06f7e8dfbe551c13ec2568e8dbb7992d97e08889a8a4806742e6b7aded904
+size 627

checkpoint-703/trainer_state.json

@@ -0,0 +1,4517 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 20,
+  "global_step": 703,
+  "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": 5.8403,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4e-05,
+      "loss": 5.8714,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6e-05,
+      "loss": 5.7358,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8e-05,
+      "loss": 5.368,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001,
+      "loss": 4.4602,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00012,
+      "loss": 3.3684,
+      "step": 6
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00014,
+      "loss": 2.4129,
+      "step": 7
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016,
+      "loss": 1.4315,
+      "step": 8
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00018,
+      "loss": 0.529,
+      "step": 9
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002,
+      "loss": 0.2216,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001999998879930964,
+      "loss": 0.2577,
+      "step": 11
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999955197263648,
+      "loss": 0.1995,
+      "step": 12
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999899193937299,
+      "loss": 0.0976,
+      "step": 13
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999820789456046,
+      "loss": 0.2842,
+      "step": 14
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999719983995528,
+      "loss": 0.121,
+      "step": 15
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999596777781563,
+      "loss": 0.0472,
+      "step": 16
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019999451171090149,
+      "loss": 0.0736,
+      "step": 17
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019999283164247466,
+      "loss": 0.1005,
+      "step": 18
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019999092757629872,
+      "loss": 0.087,
+      "step": 19
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019998879951663902,
+      "loss": 0.0682,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.09823722392320633,
+      "eval_runtime": 23.24,
+      "eval_samples_per_second": 43.029,
+      "eval_steps_per_second": 10.757,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019998644746826275,
+      "loss": 0.1509,
+      "step": 21
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001999838714364388,
+      "loss": 0.0885,
+      "step": 22
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019998107142693786,
+      "loss": 0.0734,
+      "step": 23
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019997804744603225,
+      "loss": 0.0817,
+      "step": 24
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019997479950049622,
+      "loss": 0.0609,
+      "step": 25
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019997132759760558,
+      "loss": 0.0923,
+      "step": 26
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019996763174513787,
+      "loss": 0.1019,
+      "step": 27
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019996371195137226,
+      "loss": 0.0931,
+      "step": 28
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001999595682250897,
+      "loss": 0.073,
+      "step": 29
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019995520057557262,
+      "loss": 0.0877,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019995060901260527,
+      "loss": 0.0846,
+      "step": 31
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001999457935464733,
+      "loss": 0.0853,
+      "step": 32
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001999407541879641,
+      "loss": 0.0783,
+      "step": 33
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019993549094836642,
+      "loss": 0.0503,
+      "step": 34
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019993000383947073,
+      "loss": 0.1231,
+      "step": 35
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001999242928735689,
+      "loss": 0.0707,
+      "step": 36
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019991835806345423,
+      "loss": 0.0699,
+      "step": 37
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019991219942242156,
+      "loss": 0.0747,
+      "step": 38
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001999058169642671,
+      "loss": 0.0722,
+      "step": 39
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019989921070328844,
+      "loss": 0.0895,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.07923433184623718,
+      "eval_runtime": 23.2627,
+      "eval_samples_per_second": 42.987,
+      "eval_steps_per_second": 10.747,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019989238065428445,
+      "loss": 0.0726,
+      "step": 41
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019988532683255547,
+      "loss": 0.0697,
+      "step": 42
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.000199878049253903,
+      "loss": 0.0525,
+      "step": 43
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001998705479346298,
+      "loss": 0.101,
+      "step": 44
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001998628228915399,
+      "loss": 0.0805,
+      "step": 45
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019985487414193845,
+      "loss": 0.055,
+      "step": 46
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019984670170363172,
+      "loss": 0.0556,
+      "step": 47
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001998383055949271,
+      "loss": 0.0735,
+      "step": 48
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001998296858346331,
+      "loss": 0.0539,
+      "step": 49
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019982084244205909,
+      "loss": 0.0525,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019981177543701556,
+      "loss": 0.0426,
+      "step": 51
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019980248483981376,
+      "loss": 0.0343,
+      "step": 52
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000199792970671266,
+      "loss": 0.0268,
+      "step": 53
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019978323295268533,
+      "loss": 0.0287,
+      "step": 54
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001997732717058855,
+      "loss": 0.024,
+      "step": 55
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001997630869531812,
+      "loss": 0.0164,
+      "step": 56
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019975267871738756,
+      "loss": 0.0272,
+      "step": 57
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019974204702182056,
+      "loss": 0.0233,
+      "step": 58
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0001997311918902966,
+      "loss": 0.0211,
+      "step": 59
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001997201133471327,
+      "loss": 0.015,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.040460266172885895,
+      "eval_runtime": 23.2455,
+      "eval_samples_per_second": 43.019,
+      "eval_steps_per_second": 10.755,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019970881141714636,
+      "loss": 0.0275,
+      "step": 61
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001996972861256554,
+      "loss": 0.0264,
+      "step": 62
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019968553749847808,
+      "loss": 0.0314,
+      "step": 63
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000199673565561933,
+      "loss": 0.033,
+      "step": 64
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001996613703428389,
+      "loss": 0.0379,
+      "step": 65
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019964895186851475,
+      "loss": 0.0156,
+      "step": 66
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019963631016677968,
+      "loss": 0.0147,
+      "step": 67
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019962344526595283,
+      "loss": 0.0255,
+      "step": 68
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019961035719485336,
+      "loss": 0.0269,
+      "step": 69
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019959704598280034,
+      "loss": 0.0273,
+      "step": 70
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019958351165961274,
+      "loss": 0.0342,
+      "step": 71
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0001995697542556093,
+      "loss": 0.0194,
+      "step": 72
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019955577380160853,
+      "loss": 0.0256,
+      "step": 73
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019954157032892855,
+      "loss": 0.0126,
+      "step": 74
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001995271438693871,
+      "loss": 0.0141,
+      "step": 75
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019951249445530146,
+      "loss": 0.0283,
+      "step": 76
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019949762211948833,
+      "loss": 0.0486,
+      "step": 77
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019948252689526381,
+      "loss": 0.0211,
+      "step": 78
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019946720881644324,
+      "loss": 0.0336,
+      "step": 79
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019945166791734132,
+      "loss": 0.0376,
+      "step": 80
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 0.035690754652023315,
+      "eval_runtime": 23.2365,
+      "eval_samples_per_second": 43.036,
+      "eval_steps_per_second": 10.759,
+      "step": 80
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001994359042327717,
+      "loss": 0.0414,
+      "step": 81
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019941991779804727,
+      "loss": 0.0199,
+      "step": 82
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019940370864897987,
+      "loss": 0.0214,
+      "step": 83
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001993872768218802,
+      "loss": 0.0112,
+      "step": 84
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001993706223535578,
+      "loss": 0.0512,
+      "step": 85
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019935374528132105,
+      "loss": 0.0236,
+      "step": 86
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019933664564297687,
+      "loss": 0.0254,
+      "step": 87
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001993193234768308,
+      "loss": 0.0257,
+      "step": 88
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019930177882168692,
+      "loss": 0.0311,
+      "step": 89
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019928401171684766,
+      "loss": 0.0294,
+      "step": 90
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001992660222021138,
+      "loss": 0.0207,
+      "step": 91
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001992478103177843,
+      "loss": 0.0151,
+      "step": 92
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019922937610465638,
+      "loss": 0.0315,
+      "step": 93
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019921071960402512,
+      "loss": 0.0228,
+      "step": 94
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001991918408576837,
+      "loss": 0.0126,
+      "step": 95
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019917273990792316,
+      "loss": 0.0126,
+      "step": 96
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019915341679753218,
+      "loss": 0.0282,
+      "step": 97
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019913387156979728,
+      "loss": 0.0155,
+      "step": 98
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019911410426850243,
+      "loss": 0.0218,
+      "step": 99
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001990941149379291,
+      "loss": 0.0196,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.03417763113975525,
+      "eval_runtime": 23.1746,
+      "eval_samples_per_second": 43.151,
+      "eval_steps_per_second": 10.788,
+      "step": 100
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019907390362285617,
+      "loss": 0.0175,
+      "step": 101
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019905347036855978,
+      "loss": 0.0185,
+      "step": 102
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019903281522081322,
+      "loss": 0.0159,
+      "step": 103
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001990119382258869,
+      "loss": 0.0164,
+      "step": 104
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019899083943054815,
+      "loss": 0.0224,
+      "step": 105
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001989695188820612,
+      "loss": 0.0211,
+      "step": 106
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019894797662818703,
+      "loss": 0.0525,
+      "step": 107
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001989262127171832,
+      "loss": 0.0146,
+      "step": 108
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019890422719780396,
+      "loss": 0.0181,
+      "step": 109
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001988820201192999,
+      "loss": 0.0141,
+      "step": 110
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019885959153141783,
+      "loss": 0.0185,
+      "step": 111
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019883694148440105,
+      "loss": 0.0297,
+      "step": 112
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019881407002898867,
+      "loss": 0.0169,
+      "step": 113
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019879097721641595,
+      "loss": 0.0241,
+      "step": 114
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019876766309841396,
+      "loss": 0.0136,
+      "step": 115
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001987441277272096,
+      "loss": 0.0223,
+      "step": 116
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001987203711555253,
+      "loss": 0.0186,
+      "step": 117
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019869639343657907,
+      "loss": 0.0145,
+      "step": 118
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019867219462408432,
+      "loss": 0.0164,
+      "step": 119
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001986477747722497,
+      "loss": 0.0219,
+      "step": 120
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.0333634614944458,
+      "eval_runtime": 23.4378,
+      "eval_samples_per_second": 42.666,
+      "eval_steps_per_second": 10.667,
+      "step": 120
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001986231339357791,
+      "loss": 0.0233,
+      "step": 121
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019859827216987136,
+      "loss": 0.0269,
+      "step": 122
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019857318953022028,
+      "loss": 0.0201,
+      "step": 123
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019854788607301445,
+      "loss": 0.0241,
+      "step": 124
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019852236185493707,
+      "loss": 0.0147,
+      "step": 125
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019849661693316595,
+      "loss": 0.0257,
+      "step": 126
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019847065136537325,
+      "loss": 0.0144,
+      "step": 127
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019844446520972544,
+      "loss": 0.0214,
+      "step": 128
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019841805852488308,
+      "loss": 0.0156,
+      "step": 129
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019839143137000088,
+      "loss": 0.0228,
+      "step": 130
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019836458380472724,
+      "loss": 0.0257,
+      "step": 131
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019833751588920452,
+      "loss": 0.022,
+      "step": 132
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019831022768406845,
+      "loss": 0.0202,
+      "step": 133
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019828271925044852,
+      "loss": 0.0118,
+      "step": 134
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019825499064996733,
+      "loss": 0.0279,
+      "step": 135
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019822704194474082,
+      "loss": 0.0207,
+      "step": 136
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019819887319737795,
+      "loss": 0.0272,
+      "step": 137
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019817048447098054,
+      "loss": 0.0112,
+      "step": 138
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001981418758291433,
+      "loss": 0.0255,
+      "step": 139
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019811304733595355,
+      "loss": 0.0188,
+      "step": 140
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.031686607748270035,
+      "eval_runtime": 23.3537,
+      "eval_samples_per_second": 42.82,
+      "eval_steps_per_second": 10.705,
+      "step": 140
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019808399905599111,
+      "loss": 0.0224,
+      "step": 141
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019805473105432805,
+      "loss": 0.0155,
+      "step": 142
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019802524339652885,
+      "loss": 0.0163,
+      "step": 143
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019799553614864985,
+      "loss": 0.0272,
+      "step": 144
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019796560937723946,
+      "loss": 0.0145,
+      "step": 145
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001979354631493377,
+      "loss": 0.0232,
+      "step": 146
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019790509753247633,
+      "loss": 0.0182,
+      "step": 147
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019787451259467852,
+      "loss": 0.0241,
+      "step": 148
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019784370840445875,
+      "loss": 0.0237,
+      "step": 149
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019781268503082263,
+      "loss": 0.0197,
+      "step": 150
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00019778144254326683,
+      "loss": 0.009,
+      "step": 151
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019774998101177886,
+      "loss": 0.0216,
+      "step": 152
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019771830050683686,
+      "loss": 0.0155,
+      "step": 153
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019768640109940955,
+      "loss": 0.0226,
+      "step": 154
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000197654282860956,
+      "loss": 0.0207,
+      "step": 155
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019762194586342546,
+      "loss": 0.0229,
+      "step": 156
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019758939017925736,
+      "loss": 0.021,
+      "step": 157
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019755661588138085,
+      "loss": 0.0213,
+      "step": 158
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019752362304321493,
+      "loss": 0.0099,
+      "step": 159
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019749041173866807,
+      "loss": 0.0147,
+      "step": 160
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 0.036477215588092804,
+      "eval_runtime": 23.6345,
+      "eval_samples_per_second": 42.311,
+      "eval_steps_per_second": 10.578,
+      "step": 160
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019745698204213822,
+      "loss": 0.0183,
+      "step": 161
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019742333402851246,
+      "loss": 0.0124,
+      "step": 162
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019738946777316706,
+      "loss": 0.0066,
+      "step": 163
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019735538335196706,
+      "loss": 0.0175,
+      "step": 164
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00019732108084126625,
+      "loss": 0.0215,
+      "step": 165
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019728656031790706,
+      "loss": 0.026,
+      "step": 166
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019725182185922018,
+      "loss": 0.0094,
+      "step": 167
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019721686554302457,
+      "loss": 0.0301,
+      "step": 168
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019718169144762718,
+      "loss": 0.0131,
+      "step": 169
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019714629965182282,
+      "loss": 0.0206,
+      "step": 170
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019711069023489408,
+      "loss": 0.0147,
+      "step": 171
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019707486327661094,
+      "loss": 0.0219,
+      "step": 172
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001970388188572307,
+      "loss": 0.0253,
+      "step": 173
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019700255705749786,
+      "loss": 0.0188,
+      "step": 174
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019696607795864382,
+      "loss": 0.0149,
+      "step": 175
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001969293816423869,
+      "loss": 0.0211,
+      "step": 176
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001968924681909318,
+      "loss": 0.015,
+      "step": 177
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019685533768696982,
+      "loss": 0.0201,
+      "step": 178
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019681799021367837,
+      "loss": 0.0253,
+      "step": 179
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019678042585472098,
+      "loss": 0.0224,
+      "step": 180
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.0387922078371048,
+      "eval_runtime": 23.0013,
+      "eval_samples_per_second": 43.476,
+      "eval_steps_per_second": 10.869,
+      "step": 180
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019674264469424698,
+      "loss": 0.0069,
+      "step": 181
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019670464681689144,
+      "loss": 0.0082,
+      "step": 182
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019666643230777475,
+      "loss": 0.0199,
+      "step": 183
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019662800125250276,
+      "loss": 0.0101,
+      "step": 184
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019658935373716632,
+      "loss": 0.0157,
+      "step": 185
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00019655048984834118,
+      "loss": 0.0268,
+      "step": 186
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0001965114096730879,
+      "loss": 0.0135,
+      "step": 187
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019647211329895136,
+      "loss": 0.0144,
+      "step": 188
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019643260081396094,
+      "loss": 0.0116,
+      "step": 189
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019639287230663004,
+      "loss": 0.0191,
+      "step": 190
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019635292786595598,
+      "loss": 0.0216,
+      "step": 191
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019631276758141987,
+      "loss": 0.0114,
+      "step": 192
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019627239154298623,
+      "loss": 0.0367,
+      "step": 193
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019623179984110296,
+      "loss": 0.0071,
+      "step": 194
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019619099256670114,
+      "loss": 0.0171,
+      "step": 195
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019614996981119468,
+      "loss": 0.0124,
+      "step": 196
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001961087316664802,
+      "loss": 0.024,
+      "step": 197
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019606727822493687,
+      "loss": 0.0121,
+      "step": 198
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019602560957942606,
+      "loss": 0.0079,
+      "step": 199
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019598372582329133,
+      "loss": 0.0116,
+      "step": 200
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.05043657124042511,
+      "eval_runtime": 23.2026,
+      "eval_samples_per_second": 43.099,
+      "eval_steps_per_second": 10.775,
+      "step": 200
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019594162705035808,
+      "loss": 0.0163,
+      "step": 201
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019589931335493334,
+      "loss": 0.0158,
+      "step": 202
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001958567848318057,
+      "loss": 0.0055,
+      "step": 203
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019581404157624483,
+      "loss": 0.011,
+      "step": 204
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019577108368400162,
+      "loss": 0.0075,
+      "step": 205
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001957279112513076,
+      "loss": 0.0219,
+      "step": 206
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019568452437487504,
+      "loss": 0.0054,
+      "step": 207
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019564092315189647,
+      "loss": 0.0111,
+      "step": 208
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019559710768004472,
+      "loss": 0.0115,
+      "step": 209
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019555307805747246,
+      "loss": 0.0114,
+      "step": 210
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001955088343828121,
+      "loss": 0.0055,
+      "step": 211
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019546437675517563,
+      "loss": 0.0084,
+      "step": 212
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019541970527415424,
+      "loss": 0.0189,
+      "step": 213
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00019537482003981825,
+      "loss": 0.0172,
+      "step": 214
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019532972115271675,
+      "loss": 0.0054,
+      "step": 215
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019528440871387746,
+      "loss": 0.0149,
+      "step": 216
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019523888282480656,
+      "loss": 0.0264,
+      "step": 217
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019519314358748825,
+      "loss": 0.0094,
+      "step": 218
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019514719110438482,
+      "loss": 0.0221,
+      "step": 219
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001951010254784361,
+      "loss": 0.0158,
+      "step": 220
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.06923255324363708,
+      "eval_runtime": 23.5744,
+      "eval_samples_per_second": 42.419,
+      "eval_steps_per_second": 10.605,
+      "step": 220
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019505464681305953,
+      "loss": 0.0207,
+      "step": 221
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001950080552121497,
+      "loss": 0.0301,
+      "step": 222
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019496125078007816,
+      "loss": 0.021,
+      "step": 223
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001949142336216934,
+      "loss": 0.0166,
+      "step": 224
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019486700384232033,
+      "loss": 0.0037,
+      "step": 225
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019481956154776016,
+      "loss": 0.0083,
+      "step": 226
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019477190684429014,
+      "loss": 0.0085,
+      "step": 227
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00019472403983866344,
+      "loss": 0.0103,
+      "step": 228
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019467596063810872,
+      "loss": 0.0169,
+      "step": 229
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001946276693503301,
+      "loss": 0.008,
+      "step": 230
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019457916608350666,
+      "loss": 0.0243,
+      "step": 231
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019453045094629246,
+      "loss": 0.0211,
+      "step": 232
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019448152404781608,
+      "loss": 0.0148,
+      "step": 233
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019443238549768057,
+      "loss": 0.0178,
+      "step": 234
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019438303540596309,
+      "loss": 0.0132,
+      "step": 235
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019433347388321458,
+      "loss": 0.0207,
+      "step": 236
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019428370104045977,
+      "loss": 0.0058,
+      "step": 237
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019423371698919665,
+      "loss": 0.0182,
+      "step": 238
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001941835218413964,
+      "loss": 0.0164,
+      "step": 239
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019413311570950316,
+      "loss": 0.0193,
+      "step": 240
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.04074312746524811,
+      "eval_runtime": 23.6367,
+      "eval_samples_per_second": 42.307,
+      "eval_steps_per_second": 10.577,
+      "step": 240
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019408249870643353,
+      "loss": 0.0135,
+      "step": 241
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001940316709455766,
+      "loss": 0.0185,
+      "step": 242
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019398063254079362,
+      "loss": 0.0125,
+      "step": 243
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019392938360641765,
+      "loss": 0.0099,
+      "step": 244
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019387792425725332,
+      "loss": 0.0124,
+      "step": 245
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019382625460857676,
+      "loss": 0.0116,
+      "step": 246
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019377437477613506,
+      "loss": 0.0067,
+      "step": 247
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019372228487614623,
+      "loss": 0.0135,
+      "step": 248
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019366998502529884,
+      "loss": 0.0096,
+      "step": 249
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019361747534075177,
+      "loss": 0.0258,
+      "step": 250
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019356475594013397,
+      "loss": 0.0061,
+      "step": 251
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019351182694154418,
+      "loss": 0.0065,
+      "step": 252
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019345868846355063,
+      "loss": 0.0167,
+      "step": 253
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019340534062519088,
+      "loss": 0.009,
+      "step": 254
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00019335178354597146,
+      "loss": 0.0079,
+      "step": 255
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001932980173458676,
+      "loss": 0.028,
+      "step": 256
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019324404214532303,
+      "loss": 0.0204,
+      "step": 257
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019318985806524966,
+      "loss": 0.0174,
+      "step": 258
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019313546522702727,
+      "loss": 0.017,
+      "step": 259
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019308086375250335,
+      "loss": 0.0181,
+      "step": 260
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 0.044319622218608856,
+      "eval_runtime": 23.1398,
+      "eval_samples_per_second": 43.216,
+      "eval_steps_per_second": 10.804,
+      "step": 260
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019302605376399277,
+      "loss": 0.0072,
+      "step": 261
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019297103538427744,
+      "loss": 0.0227,
+      "step": 262
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00019291580873660613,
+      "loss": 0.0113,
+      "step": 263
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019286037394469413,
+      "loss": 0.0084,
+      "step": 264
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0001928047311327231,
+      "loss": 0.0131,
+      "step": 265
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019274888042534056,
+      "loss": 0.0124,
+      "step": 266
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019269282194765984,
+      "loss": 0.011,
+      "step": 267
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019263655582525964,
+      "loss": 0.0062,
+      "step": 268
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019258008218418383,
+      "loss": 0.012,
+      "step": 269
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019252340115094124,
+      "loss": 0.011,
+      "step": 270
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019246651285250514,
+      "loss": 0.0039,
+      "step": 271
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019240941741631323,
+      "loss": 0.0261,
+      "step": 272
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019235211497026708,
+      "loss": 0.0098,
+      "step": 273
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019229460564273217,
+      "loss": 0.023,
+      "step": 274
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019223688956253727,
+      "loss": 0.0198,
+      "step": 275
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019217896685897444,
+      "loss": 0.0037,
+      "step": 276
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019212083766179846,
+      "loss": 0.0067,
+      "step": 277
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019206250210122684,
+      "loss": 0.0131,
+      "step": 278
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019200396030793918,
+      "loss": 0.0087,
+      "step": 279
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019194521241307726,
+      "loss": 0.0124,
+      "step": 280
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.048221979290246964,
+      "eval_runtime": 23.4398,
+      "eval_samples_per_second": 42.663,
+      "eval_steps_per_second": 10.666,
+      "step": 280
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019188625854824447,
+      "loss": 0.009,
+      "step": 281
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019182709884550558,
+      "loss": 0.0134,
+      "step": 282
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019176773343738653,
+      "loss": 0.012,
+      "step": 283
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.000191708162456874,
+      "loss": 0.0084,
+      "step": 284
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001916483860374152,
+      "loss": 0.008,
+      "step": 285
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00019158840431291761,
+      "loss": 0.0069,
+      "step": 286
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001915282174177485,
+      "loss": 0.0065,
+      "step": 287
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001914678254867349,
+      "loss": 0.0161,
+      "step": 288
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00019140722865516305,
+      "loss": 0.0156,
+      "step": 289
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001913464270587782,
+      "loss": 0.0127,
+      "step": 290
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00019128542083378435,
+      "loss": 0.003,
+      "step": 291
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019122421011684386,
+      "loss": 0.0114,
+      "step": 292
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019116279504507717,
+      "loss": 0.0057,
+      "step": 293
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019110117575606253,
+      "loss": 0.0053,
+      "step": 294
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019103935238783563,
+      "loss": 0.0077,
+      "step": 295
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019097732507888942,
+      "loss": 0.0173,
+      "step": 296
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019091509396817357,
+      "loss": 0.0117,
+      "step": 297
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001908526591950944,
+      "loss": 0.0152,
+      "step": 298
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001907900208995144,
+      "loss": 0.0162,
+      "step": 299
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019072717922175201,
+      "loss": 0.0094,
+      "step": 300
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.054927486926317215,
+      "eval_runtime": 23.3503,
+      "eval_samples_per_second": 42.826,
+      "eval_steps_per_second": 10.707,
+      "step": 300
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019066413430258127,
+      "loss": 0.0107,
+      "step": 301
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019060088628323145,
+      "loss": 0.0178,
+      "step": 302
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019053743530538693,
+      "loss": 0.0031,
+      "step": 303
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019047378151118663,
+      "loss": 0.0072,
+      "step": 304
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019040992504322382,
+      "loss": 0.0185,
+      "step": 305
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001903458660445458,
+      "loss": 0.0125,
+      "step": 306
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019028160465865362,
+      "loss": 0.0047,
+      "step": 307
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001902171410295016,
+      "loss": 0.0325,
+      "step": 308
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001901524753014972,
+      "loss": 0.011,
+      "step": 309
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019008760761950058,
+      "loss": 0.003,
+      "step": 310
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019002253812882427,
+      "loss": 0.0067,
+      "step": 311
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00018995726697523297,
+      "loss": 0.0092,
+      "step": 312
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018989179430494303,
+      "loss": 0.0224,
+      "step": 313
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0001898261202646223,
+      "loss": 0.0255,
+      "step": 314
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0001897602450013897,
+      "loss": 0.0097,
+      "step": 315
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018969416866281485,
+      "loss": 0.0074,
+      "step": 316
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.000189627891396918,
+      "loss": 0.0121,
+      "step": 317
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018956141335216926,
+      "loss": 0.0123,
+      "step": 318
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00018949473467748867,
+      "loss": 0.0042,
+      "step": 319
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00018942785552224564,
+      "loss": 0.0081,
+      "step": 320
+    },
+    {
+      "epoch": 0.46,
+      "eval_loss": 0.03408419340848923,
+      "eval_runtime": 23.1715,
+      "eval_samples_per_second": 43.156,
+      "eval_steps_per_second": 10.789,
+      "step": 320
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001893607760362588,
+      "loss": 0.0142,
+      "step": 321
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00018929349636979536,
+      "loss": 0.0097,
+      "step": 322
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001892260166735711,
+      "loss": 0.0164,
+      "step": 323
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00018915833709874988,
+      "loss": 0.0148,
+      "step": 324
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00018909045779694325,
+      "loss": 0.0212,
+      "step": 325
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00018902237892021024,
+      "loss": 0.0203,
+      "step": 326
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018895410062105694,
+      "loss": 0.0116,
+      "step": 327
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018888562305243616,
+      "loss": 0.0169,
+      "step": 328
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018881694636774712,
+      "loss": 0.0192,
+      "step": 329
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018874807072083503,
+      "loss": 0.0079,
+      "step": 330
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018867899626599094,
+      "loss": 0.0138,
+      "step": 331
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00018860972315795107,
+      "loss": 0.0148,
+      "step": 332
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0001885402515518968,
+      "loss": 0.0146,
+      "step": 333
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0001884705816034541,
+      "loss": 0.0094,
+      "step": 334
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018840071346869328,
+      "loss": 0.023,
+      "step": 335
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0001883306473041286,
+      "loss": 0.0092,
+      "step": 336
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018826038326671797,
+      "loss": 0.0192,
+      "step": 337
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0001881899215138625,
+      "loss": 0.0116,
+      "step": 338
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00018811926220340628,
+      "loss": 0.0245,
+      "step": 339
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0001880484054936359,
+      "loss": 0.0188,
+      "step": 340
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.0401308573782444,
+      "eval_runtime": 23.3351,
+      "eval_samples_per_second": 42.854,
+      "eval_steps_per_second": 10.713,
+      "step": 340
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00018797735154328014,
+      "loss": 0.0094,
+      "step": 341
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00018790610051150973,
+      "loss": 0.0048,
+      "step": 342
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0001878346525579368,
+      "loss": 0.0168,
+      "step": 343
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0001877630078426146,
+      "loss": 0.0134,
+      "step": 344
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0001876911665260372,
+      "loss": 0.0209,
+      "step": 345
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00018761912876913908,
+      "loss": 0.0158,
+      "step": 346
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00018754689473329475,
+      "loss": 0.0085,
+      "step": 347
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00018747446458031842,
+      "loss": 0.0014,
+      "step": 348
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00018740183847246362,
+      "loss": 0.0198,
+      "step": 349
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00018732901657242287,
+      "loss": 0.0301,
+      "step": 350
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001872559990433273,
+      "loss": 0.0069,
+      "step": 351
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001871827860487463,
+      "loss": 0.0082,
+      "step": 352
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00018710937775268696,
+      "loss": 0.0092,
+      "step": 353
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0001870357743195941,
+      "loss": 0.0065,
+      "step": 354
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00018696197591434955,
+      "loss": 0.015,
+      "step": 355
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018688798270227188,
+      "loss": 0.013,
+      "step": 356
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018681379484911616,
+      "loss": 0.0238,
+      "step": 357
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018673941252107343,
+      "loss": 0.0123,
+      "step": 358
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018666483588477032,
+      "loss": 0.0067,
+      "step": 359
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018659006510726887,
+      "loss": 0.021,
+      "step": 360
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.050777580589056015,
+      "eval_runtime": 23.3931,
+      "eval_samples_per_second": 42.748,
+      "eval_steps_per_second": 10.687,
+      "step": 360
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018651510035606585,
+      "loss": 0.0186,
+      "step": 361
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018643994179909276,
+      "loss": 0.0159,
+      "step": 362
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00018636458960471505,
+      "loss": 0.0146,
+      "step": 363
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00018628904394173205,
+      "loss": 0.0193,
+      "step": 364
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001862133049793765,
+      "loss": 0.0156,
+      "step": 365
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001861373728873142,
+      "loss": 0.0079,
+      "step": 366
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00018606124783564337,
+      "loss": 0.0092,
+      "step": 367
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001859849299948948,
+      "loss": 0.0141,
+      "step": 368
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00018590841953603087,
+      "loss": 0.0108,
+      "step": 369
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00018583171663044565,
+      "loss": 0.0352,
+      "step": 370
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00018575482144996417,
+      "loss": 0.013,
+      "step": 371
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0001856777341668423,
+      "loss": 0.0087,
+      "step": 372
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00018560045495376616,
+      "loss": 0.0135,
+      "step": 373
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0001855229839838519,
+      "loss": 0.0073,
+      "step": 374
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00018544532143064516,
+      "loss": 0.0135,
+      "step": 375
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0001853674674681208,
+      "loss": 0.0109,
+      "step": 376
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018528942227068247,
+      "loss": 0.0123,
+      "step": 377
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0001852111860131621,
+      "loss": 0.0101,
+      "step": 378
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018513275887081977,
+      "loss": 0.0153,
+      "step": 379
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018505414101934316,
+      "loss": 0.0125,
+      "step": 380
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.040892839431762695,
+      "eval_runtime": 23.0536,
+      "eval_samples_per_second": 43.377,
+      "eval_steps_per_second": 10.844,
+      "step": 380
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018497533263484698,
+      "loss": 0.007,
+      "step": 381
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018489633389387299,
+      "loss": 0.0122,
+      "step": 382
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00018481714497338927,
+      "loss": 0.0091,
+      "step": 383
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018473776605078992,
+      "loss": 0.0086,
+      "step": 384
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0001846581973038947,
+      "loss": 0.0134,
+      "step": 385
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018457843891094851,
+      "loss": 0.0088,
+      "step": 386
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0001844984910506213,
+      "loss": 0.005,
+      "step": 387
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018441835390200722,
+      "loss": 0.0081,
+      "step": 388
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018433802764462455,
+      "loss": 0.0123,
+      "step": 389
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00018425751245841526,
+      "loss": 0.0101,
+      "step": 390
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018417680852374438,
+      "loss": 0.0148,
+      "step": 391
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018409591602139996,
+      "loss": 0.0067,
+      "step": 392
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018401483513259237,
+      "loss": 0.0145,
+      "step": 393
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018393356603895396,
+      "loss": 0.0181,
+      "step": 394
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018385210892253871,
+      "loss": 0.0094,
+      "step": 395
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018377046396582185,
+      "loss": 0.0212,
+      "step": 396
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018368863135169932,
+      "loss": 0.0062,
+      "step": 397
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0001836066112634875,
+      "loss": 0.0176,
+      "step": 398
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0001835244038849227,
+      "loss": 0.0144,
+      "step": 399
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0001834420094001608,
+      "loss": 0.0071,
+      "step": 400
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.04236825183033943,
+      "eval_runtime": 23.1651,
+      "eval_samples_per_second": 43.168,
+      "eval_steps_per_second": 10.792,
+      "step": 400
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018335942799377678,
+      "loss": 0.0126,
+      "step": 401
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018327665985076448,
+      "loss": 0.0192,
+      "step": 402
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0001831937051565359,
+      "loss": 0.0266,
+      "step": 403
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018311056409692106,
+      "loss": 0.0056,
+      "step": 404
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018302723685816735,
+      "loss": 0.0069,
+      "step": 405
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018294372362693935,
+      "loss": 0.0046,
+      "step": 406
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0001828600245903182,
+      "loss": 0.01,
+      "step": 407
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018277613993580128,
+      "loss": 0.0124,
+      "step": 408
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018269206985130186,
+      "loss": 0.0037,
+      "step": 409
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00018260781452514847,
+      "loss": 0.024,
+      "step": 410
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0001825233741460847,
+      "loss": 0.0127,
+      "step": 411
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018243874890326865,
+      "loss": 0.0159,
+      "step": 412
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018235393898627256,
+      "loss": 0.0328,
+      "step": 413
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018226894458508235,
+      "loss": 0.0187,
+      "step": 414
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018218376589009723,
+      "loss": 0.0102,
+      "step": 415
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018209840309212923,
+      "loss": 0.0117,
+      "step": 416
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001820128563824028,
+      "loss": 0.0108,
+      "step": 417
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00018192712595255434,
+      "loss": 0.0105,
+      "step": 418
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018184121199463191,
+      "loss": 0.0052,
+      "step": 419
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018175511470109462,
+      "loss": 0.0165,
+      "step": 420
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.056613512337207794,
+      "eval_runtime": 23.1787,
+      "eval_samples_per_second": 43.143,
+      "eval_steps_per_second": 10.786,
+      "step": 420
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018166883426481227,
+      "loss": 0.0064,
+      "step": 421
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018158237087906496,
+      "loss": 0.0081,
+      "step": 422
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018149572473754268,
+      "loss": 0.0086,
+      "step": 423
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018140889603434466,
+      "loss": 0.0086,
+      "step": 424
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0001813218849639792,
+      "loss": 0.012,
+      "step": 425
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018123469172136317,
+      "loss": 0.0061,
+      "step": 426
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001811473165018214,
+      "loss": 0.012,
+      "step": 427
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001810597595010865,
+      "loss": 0.0072,
+      "step": 428
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018097202091529822,
+      "loss": 0.0067,
+      "step": 429
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018088410094100309,
+      "loss": 0.0134,
+      "step": 430
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018079599977515397,
+      "loss": 0.0009,
+      "step": 431
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00018070771761510973,
+      "loss": 0.0177,
+      "step": 432
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018061925465863448,
+      "loss": 0.0124,
+      "step": 433
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018053061110389758,
+      "loss": 0.0053,
+      "step": 434
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018044178714947276,
+      "loss": 0.0058,
+      "step": 435
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001803527829943379,
+      "loss": 0.0168,
+      "step": 436
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001802635988378747,
+      "loss": 0.0121,
+      "step": 437
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001801742348798679,
+      "loss": 0.0132,
+      "step": 438
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018008469132050516,
+      "loss": 0.003,
+      "step": 439
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017999496836037637,
+      "loss": 0.0075,
+      "step": 440
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.053666725754737854,
+      "eval_runtime": 23.2275,
+      "eval_samples_per_second": 43.052,
+      "eval_steps_per_second": 10.763,
+      "step": 440
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017990506620047339,
+      "loss": 0.01,
+      "step": 441
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017981498504218943,
+      "loss": 0.036,
+      "step": 442
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017972472508731878,
+      "loss": 0.0158,
+      "step": 443
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017963428653805614,
+      "loss": 0.0085,
+      "step": 444
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017954366959699637,
+      "loss": 0.0137,
+      "step": 445
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00017945287446713393,
+      "loss": 0.0236,
+      "step": 446
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00017936190135186246,
+      "loss": 0.0163,
+      "step": 447
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001792707504549743,
+      "loss": 0.0066,
+      "step": 448
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00017917942198066,
+      "loss": 0.0067,
+      "step": 449
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00017908791613350803,
+      "loss": 0.0085,
+      "step": 450
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00017899623311850405,
+      "loss": 0.0193,
+      "step": 451
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001789043731410307,
+      "loss": 0.0127,
+      "step": 452
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00017881233640686705,
+      "loss": 0.0104,
+      "step": 453
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.000178720123122188,
+      "loss": 0.0138,
+      "step": 454
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017862773349356414,
+      "loss": 0.0056,
+      "step": 455
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017853516772796093,
+      "loss": 0.0126,
+      "step": 456
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017844242603273848,
+      "loss": 0.0055,
+      "step": 457
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017834950861565102,
+      "loss": 0.0143,
+      "step": 458
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017825641568484634,
+      "loss": 0.0047,
+      "step": 459
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00017816314744886552,
+      "loss": 0.0096,
+      "step": 460
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 0.03381817042827606,
+      "eval_runtime": 23.3676,
+      "eval_samples_per_second": 42.794,
+      "eval_steps_per_second": 10.699,
+      "step": 460
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017806970411664224,
+      "loss": 0.0041,
+      "step": 461
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001779760858975025,
+      "loss": 0.0116,
+      "step": 462
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017788229300116402,
+      "loss": 0.0107,
+      "step": 463
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001777883256377358,
+      "loss": 0.0034,
+      "step": 464
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017769418401771778,
+      "loss": 0.0104,
+      "step": 465
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017759986835200016,
+      "loss": 0.012,
+      "step": 466
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00017750537885186302,
+      "loss": 0.0083,
+      "step": 467
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017741071572897592,
+      "loss": 0.0076,
+      "step": 468
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001773158791953973,
+      "loss": 0.0176,
+      "step": 469
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017722086946357415,
+      "loss": 0.0024,
+      "step": 470
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017712568674634134,
+      "loss": 0.0112,
+      "step": 471
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001770303312569213,
+      "loss": 0.0172,
+      "step": 472
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017693480320892348,
+      "loss": 0.0071,
+      "step": 473
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001768391028163439,
+      "loss": 0.0055,
+      "step": 474
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017674323029356472,
+      "loss": 0.0022,
+      "step": 475
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017664718585535353,
+      "loss": 0.0087,
+      "step": 476
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017655096971686321,
+      "loss": 0.0158,
+      "step": 477
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017645458209363115,
+      "loss": 0.0121,
+      "step": 478
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017635802320157894,
+      "loss": 0.0146,
+      "step": 479
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017626129325701184,
+      "loss": 0.012,
+      "step": 480
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.048898741602897644,
+      "eval_runtime": 23.3056,
+      "eval_samples_per_second": 42.908,
+      "eval_steps_per_second": 10.727,
+      "step": 480
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00017616439247661826,
+      "loss": 0.0067,
+      "step": 481
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0001760673210774694,
+      "loss": 0.0096,
+      "step": 482
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017597007927701853,
+      "loss": 0.0056,
+      "step": 483
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017587266729310067,
+      "loss": 0.0078,
+      "step": 484
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0001757750853439322,
+      "loss": 0.0043,
+      "step": 485
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017567733364811015,
+      "loss": 0.0075,
+      "step": 486
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017557941242461178,
+      "loss": 0.0095,
+      "step": 487
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017548132189279417,
+      "loss": 0.0083,
+      "step": 488
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00017538306227239363,
+      "loss": 0.0029,
+      "step": 489
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00017528463378352528,
+      "loss": 0.0038,
+      "step": 490
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00017518603664668257,
+      "loss": 0.005,
+      "step": 491
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00017508727108273665,
+      "loss": 0.0191,
+      "step": 492
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00017498833731293605,
+      "loss": 0.0092,
+      "step": 493
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00017488923555890605,
+      "loss": 0.0255,
+      "step": 494
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0001747899660426483,
+      "loss": 0.0262,
+      "step": 495
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0001746905289865402,
+      "loss": 0.0106,
+      "step": 496
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017459092461333446,
+      "loss": 0.013,
+      "step": 497
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017449115314615866,
+      "loss": 0.0077,
+      "step": 498
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017439121480851465,
+      "loss": 0.0135,
+      "step": 499
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017429110982427815,
+      "loss": 0.0041,
+      "step": 500
+    },
+    {
+      "epoch": 0.71,
+      "eval_loss": 0.044191259890794754,
+      "eval_runtime": 23.2484,
+      "eval_samples_per_second": 43.014,
+      "eval_steps_per_second": 10.753,
+      "step": 500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017419083841769804,
+      "loss": 0.0108,
+      "step": 501
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017409040081339623,
+      "loss": 0.0149,
+      "step": 502
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00017398979723636676,
+      "loss": 0.0073,
+      "step": 503
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00017388902791197553,
+      "loss": 0.0121,
+      "step": 504
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001737880930659598,
+      "loss": 0.0131,
+      "step": 505
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00017368699292442748,
+      "loss": 0.0114,
+      "step": 506
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001735857277138569,
+      "loss": 0.0072,
+      "step": 507
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00017348429766109608,
+      "loss": 0.0047,
+      "step": 508
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001733827029933624,
+      "loss": 0.0033,
+      "step": 509
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017328094393824186,
+      "loss": 0.0025,
+      "step": 510
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017317902072368885,
+      "loss": 0.0051,
+      "step": 511
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017307693357802544,
+      "loss": 0.0161,
+      "step": 512
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017297468272994092,
+      "loss": 0.0056,
+      "step": 513
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001728722684084913,
+      "loss": 0.0166,
+      "step": 514
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017276969084309882,
+      "loss": 0.0122,
+      "step": 515
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017266695026355136,
+      "loss": 0.0028,
+      "step": 516
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017256404690000205,
+      "loss": 0.0058,
+      "step": 517
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017246098098296862,
+      "loss": 0.0174,
+      "step": 518
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017235775274333288,
+      "loss": 0.0172,
+      "step": 519
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017225436241234045,
+      "loss": 0.0012,
+      "step": 520
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 0.04391771927475929,
+      "eval_runtime": 23.2947,
+      "eval_samples_per_second": 42.928,
+      "eval_steps_per_second": 10.732,
+      "step": 520
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001721508102215999,
+      "loss": 0.0177,
+      "step": 521
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001720470964030824,
+      "loss": 0.0142,
+      "step": 522
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017194322118912128,
+      "loss": 0.0123,
+      "step": 523
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00017183918481241133,
+      "loss": 0.0049,
+      "step": 524
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001717349875060084,
+      "loss": 0.0118,
+      "step": 525
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00017163062950332884,
+      "loss": 0.016,
+      "step": 526
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00017152611103814902,
+      "loss": 0.0057,
+      "step": 527
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001714214323446047,
+      "loss": 0.0062,
+      "step": 528
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001713165936571906,
+      "loss": 0.0195,
+      "step": 529
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00017121159521075988,
+      "loss": 0.0088,
+      "step": 530
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017110643724052354,
+      "loss": 0.0048,
+      "step": 531
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017100111998204996,
+      "loss": 0.0074,
+      "step": 532
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017089564367126433,
+      "loss": 0.0102,
+      "step": 533
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017079000854444817,
+      "loss": 0.011,
+      "step": 534
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017068421483823872,
+      "loss": 0.017,
+      "step": 535
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017057826278962855,
+      "loss": 0.0103,
+      "step": 536
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0001704721526359648,
+      "loss": 0.0069,
+      "step": 537
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0001703658846149489,
+      "loss": 0.0199,
+      "step": 538
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00017025945896463593,
+      "loss": 0.0076,
+      "step": 539
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00017015287592343396,
+      "loss": 0.0096,
+      "step": 540
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.03808086737990379,
+      "eval_runtime": 23.0584,
+      "eval_samples_per_second": 43.368,
+      "eval_steps_per_second": 10.842,
+      "step": 540
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00017004613573010378,
+      "loss": 0.0056,
+      "step": 541
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016993923862375812,
+      "loss": 0.0045,
+      "step": 542
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0001698321848438613,
+      "loss": 0.0084,
+      "step": 543
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016972497463022852,
+      "loss": 0.014,
+      "step": 544
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001696176082230255,
+      "loss": 0.0159,
+      "step": 545
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001695100858627678,
+      "loss": 0.0061,
+      "step": 546
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016940240779032037,
+      "loss": 0.0215,
+      "step": 547
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016929457424689695,
+      "loss": 0.0134,
+      "step": 548
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016918658547405955,
+      "loss": 0.0142,
+      "step": 549
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016907844171371793,
+      "loss": 0.0017,
+      "step": 550
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016897014320812906,
+      "loss": 0.0116,
+      "step": 551
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016886169019989658,
+      "loss": 0.0058,
+      "step": 552
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016875308293197013,
+      "loss": 0.0119,
+      "step": 553
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016864432164764506,
+      "loss": 0.0126,
+      "step": 554
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0001685354065905616,
+      "loss": 0.0124,
+      "step": 555
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016842633800470455,
+      "loss": 0.0046,
+      "step": 556
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0001683171161344026,
+      "loss": 0.0081,
+      "step": 557
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0001682077412243278,
+      "loss": 0.0043,
+      "step": 558
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016809821351949507,
+      "loss": 0.004,
+      "step": 559
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016798853326526158,
+      "loss": 0.005,
+      "step": 560
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.04487919807434082,
+      "eval_runtime": 23.3744,
+      "eval_samples_per_second": 42.782,
+      "eval_steps_per_second": 10.695,
+      "step": 560
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016787870070732625,
+      "loss": 0.0051,
+      "step": 561
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016776871609172918,
+      "loss": 0.004,
+      "step": 562
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0001676585796648511,
+      "loss": 0.0174,
+      "step": 563
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0001675482916734128,
+      "loss": 0.0152,
+      "step": 564
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0001674378523644746,
+      "loss": 0.0178,
+      "step": 565
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0001673272619854358,
+      "loss": 0.0144,
+      "step": 566
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00016721652078403412,
+      "loss": 0.0103,
+      "step": 567
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00016710562900834519,
+      "loss": 0.0094,
+      "step": 568
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00016699458690678184,
+      "loss": 0.0191,
+      "step": 569
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0001668833947280937,
+      "loss": 0.0189,
+      "step": 570
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00016677205272136667,
+      "loss": 0.0102,
+      "step": 571
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00016666056113602218,
+      "loss": 0.012,
+      "step": 572
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016654892022181678,
+      "loss": 0.0064,
+      "step": 573
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016643713022884148,
+      "loss": 0.0066,
+      "step": 574
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0001663251914075214,
+      "loss": 0.0179,
+      "step": 575
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016621310400861486,
+      "loss": 0.004,
+      "step": 576
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016610086828321315,
+      "loss": 0.0062,
+      "step": 577
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00016598848448273984,
+      "loss": 0.0049,
+      "step": 578
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0001658759528589501,
+      "loss": 0.0213,
+      "step": 579
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0001657632736639303,
+      "loss": 0.0239,
+      "step": 580
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 0.04524041712284088,
+      "eval_runtime": 23.2755,
+      "eval_samples_per_second": 42.964,
+      "eval_steps_per_second": 10.741,
+      "step": 580
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0001656504471500974,
+      "loss": 0.0164,
+      "step": 581
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0001655374735701984,
+      "loss": 0.007,
+      "step": 582
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0001654243531773097,
+      "loss": 0.0106,
+      "step": 583
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0001653110862248366,
+      "loss": 0.0066,
+      "step": 584
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0001651976729665127,
+      "loss": 0.009,
+      "step": 585
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0001650841136563994,
+      "loss": 0.0033,
+      "step": 586
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00016497040854888517,
+      "loss": 0.0079,
+      "step": 587
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016485655789868518,
+      "loss": 0.004,
+      "step": 588
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016474256196084063,
+      "loss": 0.0111,
+      "step": 589
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016462842099071817,
+      "loss": 0.0094,
+      "step": 590
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016451413524400923,
+      "loss": 0.0143,
+      "step": 591
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016439970497672977,
+      "loss": 0.0051,
+      "step": 592
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016428513044521937,
+      "loss": 0.0116,
+      "step": 593
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00016417041190614076,
+      "loss": 0.0064,
+      "step": 594
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00016405554961647934,
+      "loss": 0.0068,
+      "step": 595
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00016394054383354247,
+      "loss": 0.0033,
+      "step": 596
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00016382539481495903,
+      "loss": 0.0017,
+      "step": 597
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00016371010281867866,
+      "loss": 0.0167,
+      "step": 598
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00016359466810297136,
+      "loss": 0.0029,
+      "step": 599
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00016347909092642694,
+      "loss": 0.0166,
+      "step": 600
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 0.038260262459516525,
+      "eval_runtime": 23.3542,
+      "eval_samples_per_second": 42.819,
+      "eval_steps_per_second": 10.705,
+      "step": 600
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00016336337154795408,
+      "loss": 0.0065,
+      "step": 601
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016324751022678028,
+      "loss": 0.0157,
+      "step": 602
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016313150722245082,
+      "loss": 0.0046,
+      "step": 603
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016301536279482846,
+      "loss": 0.0033,
+      "step": 604
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016289907720409277,
+      "loss": 0.006,
+      "step": 605
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016278265071073954,
+      "loss": 0.0199,
+      "step": 606
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00016266608357558016,
+      "loss": 0.0096,
+      "step": 607
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0001625493760597412,
+      "loss": 0.0048,
+      "step": 608
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016243252842466346,
+      "loss": 0.0157,
+      "step": 609
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016231554093210188,
+      "loss": 0.0149,
+      "step": 610
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016219841384412456,
+      "loss": 0.0103,
+      "step": 611
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016208114742311236,
+      "loss": 0.007,
+      "step": 612
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016196374193175824,
+      "loss": 0.0293,
+      "step": 613
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016184619763306675,
+      "loss": 0.0025,
+      "step": 614
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016172851479035328,
+      "loss": 0.0149,
+      "step": 615
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016161069366724375,
+      "loss": 0.0039,
+      "step": 616
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016149273452767363,
+      "loss": 0.0145,
+      "step": 617
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016137463763588777,
+      "loss": 0.0168,
+      "step": 618
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016125640325643942,
+      "loss": 0.0131,
+      "step": 619
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016113803165419003,
+      "loss": 0.0081,
+      "step": 620
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 0.024927595630288124,
+      "eval_runtime": 22.9947,
+      "eval_samples_per_second": 43.488,
+      "eval_steps_per_second": 10.872,
+      "step": 620
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016101952309430822,
+      "loss": 0.0065,
+      "step": 621
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00016090087784226959,
+      "loss": 0.0083,
+      "step": 622
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0001607820961638559,
+      "loss": 0.0173,
+      "step": 623
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00016066317832515446,
+      "loss": 0.0125,
+      "step": 624
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0001605441245925577,
+      "loss": 0.0053,
+      "step": 625
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00016042493523276238,
+      "loss": 0.0241,
+      "step": 626
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0001603056105127691,
+      "loss": 0.0089,
+      "step": 627
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0001601861506998818,
+      "loss": 0.003,
+      "step": 628
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00016006655606170687,
+      "loss": 0.0141,
+      "step": 629
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015994682686615286,
+      "loss": 0.0139,
+      "step": 630
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015982696338142963,
+      "loss": 0.0096,
+      "step": 631
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015970696587604803,
+      "loss": 0.0136,
+      "step": 632
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.000159586834618819,
+      "loss": 0.0055,
+      "step": 633
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0001594665698788531,
+      "loss": 0.0128,
+      "step": 634
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015934617192556,
+      "loss": 0.0066,
+      "step": 635
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015922564102864773,
+      "loss": 0.0086,
+      "step": 636
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015910497745812217,
+      "loss": 0.0068,
+      "step": 637
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015898418148428632,
+      "loss": 0.016,
+      "step": 638
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015886325337773988,
+      "loss": 0.0137,
+      "step": 639
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0001587421934093785,
+      "loss": 0.0166,
+      "step": 640
+    },
+    {
+      "epoch": 0.91,
+      "eval_loss": 0.04424288496375084,
+      "eval_runtime": 23.3621,
+      "eval_samples_per_second": 42.804,
+      "eval_steps_per_second": 10.701,
+      "step": 640
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015862100185039322,
+      "loss": 0.0116,
+      "step": 641
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015849967897226986,
+      "loss": 0.0092,
+      "step": 642
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015837822504678842,
+      "loss": 0.0061,
+      "step": 643
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015825664034602245,
+      "loss": 0.0141,
+      "step": 644
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0001581349251423385,
+      "loss": 0.0075,
+      "step": 645
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0001580130797083954,
+      "loss": 0.002,
+      "step": 646
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015789110431714377,
+      "loss": 0.0139,
+      "step": 647
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015776899924182532,
+      "loss": 0.0092,
+      "step": 648
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015764676475597228,
+      "loss": 0.0056,
+      "step": 649
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015752440113340677,
+      "loss": 0.016,
+      "step": 650
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0001574019086482402,
+      "loss": 0.0152,
+      "step": 651
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015727928757487266,
+      "loss": 0.0028,
+      "step": 652
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015715653818799226,
+      "loss": 0.0105,
+      "step": 653
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015703366076257456,
+      "loss": 0.0082,
+      "step": 654
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015691065557388206,
+      "loss": 0.0134,
+      "step": 655
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0001567875228974632,
+      "loss": 0.0052,
+      "step": 656
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015666426300915237,
+      "loss": 0.0089,
+      "step": 657
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015654087618506858,
+      "loss": 0.0094,
+      "step": 658
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015641736270161544,
+      "loss": 0.013,
+      "step": 659
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015629372283548017,
+      "loss": 0.0106,
+      "step": 660
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.03268582001328468,
+      "eval_runtime": 23.2536,
+      "eval_samples_per_second": 43.004,
+      "eval_steps_per_second": 10.751,
+      "step": 660
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015616995686363314,
+      "loss": 0.0145,
+      "step": 661
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015604606506332722,
+      "loss": 0.0081,
+      "step": 662
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015592204771209715,
+      "loss": 0.0115,
+      "step": 663
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015579790508775894,
+      "loss": 0.0128,
+      "step": 664
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015567363746840922,
+      "loss": 0.0006,
+      "step": 665
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015554924513242456,
+      "loss": 0.0071,
+      "step": 666
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015542472835846098,
+      "loss": 0.0076,
+      "step": 667
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015530008742545328,
+      "loss": 0.0083,
+      "step": 668
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015517532261261435,
+      "loss": 0.007,
+      "step": 669
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0001550504341994346,
+      "loss": 0.0052,
+      "step": 670
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015492542246568126,
+      "loss": 0.0162,
+      "step": 671
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015480028769139796,
+      "loss": 0.0155,
+      "step": 672
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015467503015690386,
+      "loss": 0.001,
+      "step": 673
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001545496501427931,
+      "loss": 0.0089,
+      "step": 674
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015442414792993416,
+      "loss": 0.0121,
+      "step": 675
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015429852379946946,
+      "loss": 0.012,
+      "step": 676
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001541727780328143,
+      "loss": 0.0076,
+      "step": 677
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015404691091165662,
+      "loss": 0.0006,
+      "step": 678
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0001539209227179561,
+      "loss": 0.0081,
+      "step": 679
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0001537948137339437,
+      "loss": 0.0161,
+      "step": 680
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 0.03857529163360596,
+      "eval_runtime": 23.3772,
+      "eval_samples_per_second": 42.777,
+      "eval_steps_per_second": 10.694,
+      "step": 680
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.000153668584242121,
+      "loss": 0.0015,
+      "step": 681
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015354223452525943,
+      "loss": 0.0105,
+      "step": 682
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015341576486639985,
+      "loss": 0.0162,
+      "step": 683
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015328917554885174,
+      "loss": 0.0062,
+      "step": 684
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015316246685619263,
+      "loss": 0.008,
+      "step": 685
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015303563907226753,
+      "loss": 0.0146,
+      "step": 686
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015290869248118813,
+      "loss": 0.0079,
+      "step": 687
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015278162736733237,
+      "loss": 0.0097,
+      "step": 688
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015265444401534362,
+      "loss": 0.006,
+      "step": 689
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015252714271013016,
+      "loss": 0.0074,
+      "step": 690
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015239972373686452,
+      "loss": 0.0015,
+      "step": 691
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015227218738098273,
+      "loss": 0.0067,
+      "step": 692
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0001521445339281839,
+      "loss": 0.0111,
+      "step": 693
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015201676366442932,
+      "loss": 0.016,
+      "step": 694
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0001518888768759421,
+      "loss": 0.01,
+      "step": 695
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015176087384920624,
+      "loss": 0.0103,
+      "step": 696
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015163275487096623,
+      "loss": 0.0143,
+      "step": 697
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015150452022822625,
+      "loss": 0.0079,
+      "step": 698
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015137617020824964,
+      "loss": 0.0082,
+      "step": 699
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00015124770509855812,
+      "loss": 0.0038,
+      "step": 700
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.037697676569223404,
+      "eval_runtime": 23.1666,
+      "eval_samples_per_second": 43.166,
+      "eval_steps_per_second": 10.791,
+      "step": 700
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001511191251869313,
+      "loss": 0.0111,
+      "step": 701
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00015099043076140595,
+      "loss": 0.0028,
+      "step": 702
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001508616221102753,
+      "loss": 0.0068,
+      "step": 703
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2109,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 9.242876643523953e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-703/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f130e25197a3f46f0428131d8b9093939760918998e06b5589ad2fbdf87ef81f
+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": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "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": false,
+    "load_in_8bit": true,
+    "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
+}

runs/Nov15_09-59-18_compute-3-6.hamming.cluster/events.out.tfevents.1700071160.compute-3-6.hamming.cluster.45622.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd05046c063d3f4c458b026c1685a2a32bce59e1ac86fd5e9f9c75256bcbeb7
+size 364456

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
+}