Upload folder using huggingface_hub

README.md

@@ -0,0 +1,110 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: qlora-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+# qlora-out
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5477
+
+## 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: 0.0004
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8333        | 0.06  | 20   | 0.6411          |
+| 0.6715        | 0.12  | 40   | 0.5899          |
+| 0.5905        | 0.18  | 60   | 0.5573          |
+| 0.5845        | 0.24  | 80   | 0.5342          |
+| 0.5524        | 0.3   | 100  | 0.5260          |
+| 0.5516        | 0.36  | 120  | 0.5273          |
+| 0.5465        | 0.42  | 140  | 0.5132          |
+| 0.439         | 0.48  | 160  | 0.5085          |
+| 0.6857        | 0.54  | 180  | 0.4982          |
+| 0.7326        | 0.6   | 200  | 0.5096          |
+| 0.8225        | 0.66  | 220  | 0.5080          |
+| 0.6148        | 0.72  | 240  | 0.4883          |
+| 0.4524        | 0.78  | 260  | 0.4970          |
+| 0.6084        | 0.84  | 280  | 0.5425          |
+| 0.6737        | 0.9   | 300  | 0.5059          |
+| 0.459         | 0.96  | 320  | 0.4968          |
+| 0.6138        | 1.02  | 340  | 0.5111          |
+| 0.4023        | 1.08  | 360  | 0.5499          |
+| 0.4406        | 1.14  | 380  | 0.5657          |
+| 0.4054        | 1.2   | 400  | 0.5387          |
+| 0.4707        | 1.26  | 420  | 0.5698          |
+| 0.577         | 1.32  | 440  | 0.5181          |
+| 0.279         | 1.38  | 460  | 0.5243          |
+| 0.5576        | 1.44  | 480  | 0.5172          |
+| 0.382         | 1.5   | 500  | 0.5178          |
+| 0.4541        | 1.56  | 520  | 0.5166          |
+| 0.339         | 1.62  | 540  | 0.5087          |
+| 0.4609        | 1.68  | 560  | 0.5257          |
+| 0.4768        | 1.74  | 580  | 0.4990          |
+| 0.5313        | 1.8   | 600  | 0.4952          |
+| 0.347         | 1.86  | 620  | 0.4823          |
+| 0.4216        | 1.92  | 640  | 0.4832          |
+| 0.3905        | 1.98  | 660  | 0.4748          |
+| 0.1525        | 2.04  | 680  | 0.6280          |
+| 0.3269        | 2.1   | 700  | 0.5995          |
+| 0.1502        | 2.16  | 720  | 0.5412          |
+| 0.1845        | 2.22  | 740  | 0.5421          |
+| 0.2009        | 2.28  | 760  | 0.5564          |
+| 0.1896        | 2.34  | 780  | 0.5275          |
+| 0.1433        | 2.4   | 800  | 0.5569          |
+| 0.1758        | 2.46  | 820  | 0.5463          |
+| 0.1336        | 2.51  | 840  | 0.5564          |
+| 0.2063        | 2.57  | 860  | 0.5505          |
+| 0.1724        | 2.63  | 880  | 0.5392          |
+| 0.2444        | 2.69  | 900  | 0.5468          |
+| 0.2315        | 2.75  | 920  | 0.5484          |
+| 0.194         | 2.81  | 940  | 0.5492          |
+| 0.2251        | 2.87  | 960  | 0.5483          |
+| 0.1779        | 2.93  | 980  | 0.5484          |
+| 0.3551        | 2.99  | 1000 | 0.5477          |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": [
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff2bfe4f9d531e48450f2ce5c4094f8c5b316ad5d876d44a906725d9e26257d5
+size 335705741

checkpoint-1002/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-1002/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": [
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1002/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff2bfe4f9d531e48450f2ce5c4094f8c5b316ad5d876d44a906725d9e26257d5
+size 335705741

checkpoint-1002/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c64b3ddcc1aff2379be3efba7d7de71942f330c8e8d61036f6a1d9b15fbd4127
+size 168624735

checkpoint-1002/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e937012c99c33c40ca0ccd5d60cc1d4fbbcab22232e4e7d12052e3657205af89
+size 14575

checkpoint-1002/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9918e5a7f1925ff5913d17bc9cb764150357ed8088ad5535a840dab9a4d9bca6
+size 627

checkpoint-1002/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27098634af21778b649dbcd66e907b3281d3f7c9df308b74b9b43e87b72e667c
+size 4475

checkpoint-334/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-334/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": [
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-334/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1cf78d90ac6a6ea4a2e27ed5dc9fc3e3cfe9763a8e68fedab8536f46dc04ff
+size 335705741

checkpoint-334/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42849373dfcef74cb8d4db73a063300b273cd16103c54d61fd763ad74c8c5560
+size 168624735

checkpoint-334/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc82e48e2fe7cf523bb484488c3ac61e735969077c2760d4b43e8a465319345a
+size 14575

checkpoint-334/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51af7900d77cd5a39cb09610802d30e0086a6341b6efebecd39a3c9b7b17be41
+size 627

checkpoint-334/trainer_state.json

@@ -0,0 +1,2151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 20,
+  "global_step": 334,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 2.8327,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 3.0988,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.6419,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 2.381,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.657,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.408,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 3.2158,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 2.2635,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.2e-05,
+      "loss": 1.9091,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.9039,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.4666666666666668e-05,
+      "loss": 1.789,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.3775,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 1.7759,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 1.2334,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2e-05,
+      "loss": 0.7635,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.1333333333333335e-05,
+      "loss": 0.8482,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.2666666666666668e-05,
+      "loss": 0.7464,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.4e-05,
+      "loss": 0.7694,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.5333333333333337e-05,
+      "loss": 0.6606,
+      "step": 19
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.8333,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.6411340832710266,
+      "eval_runtime": 39.0251,
+      "eval_samples_per_second": 41.742,
+      "eval_steps_per_second": 20.884,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.8225,
+      "step": 21
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.9333333333333336e-05,
+      "loss": 0.7741,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.066666666666667e-05,
+      "loss": 0.8105,
+      "step": 23
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6497,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6973,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.466666666666667e-05,
+      "loss": 0.8275,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9258,
+      "step": 27
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.6865,
+      "step": 28
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.866666666666667e-05,
+      "loss": 0.68,
+      "step": 29
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4e-05,
+      "loss": 0.7747,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.133333333333333e-05,
+      "loss": 0.725,
+      "step": 31
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.266666666666667e-05,
+      "loss": 0.6831,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.754,
+      "step": 33
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.5333333333333335e-05,
+      "loss": 0.7415,
+      "step": 34
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.7404,
+      "step": 35
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7474,
+      "step": 36
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.933333333333334e-05,
+      "loss": 0.7268,
+      "step": 37
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 5.0666666666666674e-05,
+      "loss": 0.7249,
+      "step": 38
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.5853,
+      "step": 39
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.6715,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.5898512005805969,
+      "eval_runtime": 39.0712,
+      "eval_samples_per_second": 41.693,
+      "eval_steps_per_second": 20.859,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.466666666666666e-05,
+      "loss": 0.6705,
+      "step": 41
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.6564,
+      "step": 42
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5.7333333333333336e-05,
+      "loss": 0.7193,
+      "step": 43
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5.866666666666667e-05,
+      "loss": 0.7587,
+      "step": 44
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 6e-05,
+      "loss": 0.7327,
+      "step": 45
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.133333333333334e-05,
+      "loss": 0.7989,
+      "step": 46
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.266666666666667e-05,
+      "loss": 0.586,
+      "step": 47
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6681,
+      "step": 48
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.533333333333334e-05,
+      "loss": 0.7467,
+      "step": 49
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.5078,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.7192,
+      "step": 51
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 6.933333333333334e-05,
+      "loss": 0.8233,
+      "step": 52
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.066666666666667e-05,
+      "loss": 0.7273,
+      "step": 53
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.2e-05,
+      "loss": 0.6151,
+      "step": 54
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.7629,
+      "step": 55
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.466666666666667e-05,
+      "loss": 0.6741,
+      "step": 56
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.6e-05,
+      "loss": 0.5387,
+      "step": 57
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.733333333333333e-05,
+      "loss": 0.7459,
+      "step": 58
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 7.866666666666666e-05,
+      "loss": 0.5558,
+      "step": 59
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8e-05,
+      "loss": 0.5905,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 0.557337760925293,
+      "eval_runtime": 39.0718,
+      "eval_samples_per_second": 41.692,
+      "eval_steps_per_second": 20.859,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8.133333333333334e-05,
+      "loss": 0.6305,
+      "step": 61
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.266666666666667e-05,
+      "loss": 0.7207,
+      "step": 62
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.4e-05,
+      "loss": 0.6926,
+      "step": 63
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.533333333333334e-05,
+      "loss": 0.4858,
+      "step": 64
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 0.634,
+      "step": 65
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.6184,
+      "step": 66
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 8.933333333333334e-05,
+      "loss": 0.5475,
+      "step": 67
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.066666666666667e-05,
+      "loss": 0.5431,
+      "step": 68
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.659,
+      "step": 69
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.8016,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.466666666666667e-05,
+      "loss": 0.6429,
+      "step": 71
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.6e-05,
+      "loss": 0.5628,
+      "step": 72
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.733333333333335e-05,
+      "loss": 0.6041,
+      "step": 73
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.866666666666668e-05,
+      "loss": 0.4893,
+      "step": 74
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001,
+      "loss": 0.7429,
+      "step": 75
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00010133333333333335,
+      "loss": 0.5158,
+      "step": 76
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00010266666666666666,
+      "loss": 0.7377,
+      "step": 77
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.5242,
+      "step": 78
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00010533333333333332,
+      "loss": 0.549,
+      "step": 79
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.5845,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.5341688990592957,
+      "eval_runtime": 39.1341,
+      "eval_samples_per_second": 41.626,
+      "eval_steps_per_second": 20.826,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.5873,
+      "step": 81
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00010933333333333333,
+      "loss": 0.5998,
+      "step": 82
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011066666666666667,
+      "loss": 0.8269,
+      "step": 83
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.6924,
+      "step": 84
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 0.5342,
+      "step": 85
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011466666666666667,
+      "loss": 0.5858,
+      "step": 86
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.000116,
+      "loss": 0.5207,
+      "step": 87
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011733333333333334,
+      "loss": 0.6034,
+      "step": 88
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011866666666666669,
+      "loss": 0.707,
+      "step": 89
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00012,
+      "loss": 0.6256,
+      "step": 90
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00012133333333333335,
+      "loss": 0.8011,
+      "step": 91
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00012266666666666668,
+      "loss": 0.7638,
+      "step": 92
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.000124,
+      "loss": 0.5857,
+      "step": 93
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00012533333333333334,
+      "loss": 0.5948,
+      "step": 94
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 0.6051,
+      "step": 95
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.6847,
+      "step": 96
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00012933333333333332,
+      "loss": 0.4701,
+      "step": 97
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00013066666666666668,
+      "loss": 0.6454,
+      "step": 98
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.000132,
+      "loss": 0.5723,
+      "step": 99
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.5524,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.5259758234024048,
+      "eval_runtime": 39.0597,
+      "eval_samples_per_second": 41.705,
+      "eval_steps_per_second": 20.865,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00013466666666666667,
+      "loss": 0.6256,
+      "step": 101
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.5798,
+      "step": 102
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013733333333333333,
+      "loss": 0.6021,
+      "step": 103
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013866666666666669,
+      "loss": 0.652,
+      "step": 104
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00014,
+      "loss": 0.5602,
+      "step": 105
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00014133333333333334,
+      "loss": 0.6358,
+      "step": 106
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00014266666666666667,
+      "loss": 0.6063,
+      "step": 107
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000144,
+      "loss": 0.6901,
+      "step": 108
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00014533333333333333,
+      "loss": 0.5586,
+      "step": 109
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.6054,
+      "step": 110
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000148,
+      "loss": 0.4814,
+      "step": 111
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00014933333333333335,
+      "loss": 0.347,
+      "step": 112
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015066666666666668,
+      "loss": 0.4877,
+      "step": 113
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000152,
+      "loss": 0.7594,
+      "step": 114
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015333333333333334,
+      "loss": 0.5597,
+      "step": 115
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015466666666666667,
+      "loss": 0.4975,
+      "step": 116
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6336,
+      "step": 117
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015733333333333333,
+      "loss": 0.6042,
+      "step": 118
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00015866666666666668,
+      "loss": 0.4253,
+      "step": 119
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00016,
+      "loss": 0.5516,
+      "step": 120
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.5273345708847046,
+      "eval_runtime": 39.0262,
+      "eval_samples_per_second": 41.741,
+      "eval_steps_per_second": 20.883,
+      "step": 120
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00016133333333333334,
+      "loss": 0.3813,
+      "step": 121
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00016266666666666667,
+      "loss": 0.5743,
+      "step": 122
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.000164,
+      "loss": 0.5525,
+      "step": 123
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00016533333333333333,
+      "loss": 0.6549,
+      "step": 124
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6705,
+      "step": 125
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.000168,
+      "loss": 0.6486,
+      "step": 126
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00016933333333333335,
+      "loss": 0.5122,
+      "step": 127
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00017066666666666668,
+      "loss": 0.6339,
+      "step": 128
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.000172,
+      "loss": 0.5281,
+      "step": 129
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.6219,
+      "step": 130
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00017466666666666667,
+      "loss": 0.548,
+      "step": 131
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6827,
+      "step": 132
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00017733333333333335,
+      "loss": 0.6162,
+      "step": 133
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00017866666666666668,
+      "loss": 0.4973,
+      "step": 134
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00018,
+      "loss": 0.7511,
+      "step": 135
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018133333333333334,
+      "loss": 0.4998,
+      "step": 136
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018266666666666667,
+      "loss": 0.4568,
+      "step": 137
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.4537,
+      "step": 138
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00018533333333333333,
+      "loss": 0.5601,
+      "step": 139
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.5465,
+      "step": 140
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 0.5131502151489258,
+      "eval_runtime": 39.125,
+      "eval_samples_per_second": 41.636,
+      "eval_steps_per_second": 20.831,
+      "step": 140
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.000188,
+      "loss": 0.5256,
+      "step": 141
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00018933333333333335,
+      "loss": 0.6077,
+      "step": 142
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019066666666666668,
+      "loss": 0.6348,
+      "step": 143
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.000192,
+      "loss": 0.5437,
+      "step": 144
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.602,
+      "step": 145
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001946666666666667,
+      "loss": 0.4774,
+      "step": 146
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000196,
+      "loss": 0.6249,
+      "step": 147
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019733333333333335,
+      "loss": 0.6498,
+      "step": 148
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00019866666666666668,
+      "loss": 0.5419,
+      "step": 149
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002,
+      "loss": 0.5724,
+      "step": 150
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00020133333333333334,
+      "loss": 0.6224,
+      "step": 151
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002026666666666667,
+      "loss": 0.4996,
+      "step": 152
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.5016,
+      "step": 153
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00020533333333333333,
+      "loss": 0.4315,
+      "step": 154
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00020666666666666668,
+      "loss": 0.5096,
+      "step": 155
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.5167,
+      "step": 156
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00020933333333333334,
+      "loss": 0.6057,
+      "step": 157
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00021066666666666665,
+      "loss": 0.763,
+      "step": 158
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.4568,
+      "step": 159
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.439,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.5084798336029053,
+      "eval_runtime": 39.1227,
+      "eval_samples_per_second": 41.638,
+      "eval_steps_per_second": 20.832,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00021466666666666666,
+      "loss": 0.3806,
+      "step": 161
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.4544,
+      "step": 162
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00021733333333333335,
+      "loss": 0.5606,
+      "step": 163
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00021866666666666665,
+      "loss": 0.5595,
+      "step": 164
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.5773,
+      "step": 165
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022133333333333334,
+      "loss": 0.511,
+      "step": 166
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022266666666666667,
+      "loss": 0.6515,
+      "step": 167
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.4612,
+      "step": 168
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022533333333333335,
+      "loss": 0.4674,
+      "step": 169
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.6907,
+      "step": 170
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6061,
+      "step": 171
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022933333333333334,
+      "loss": 0.594,
+      "step": 172
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00023066666666666667,
+      "loss": 0.5703,
+      "step": 173
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.000232,
+      "loss": 0.6094,
+      "step": 174
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00023333333333333336,
+      "loss": 0.5031,
+      "step": 175
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002346666666666667,
+      "loss": 0.4689,
+      "step": 176
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000236,
+      "loss": 0.6271,
+      "step": 177
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00023733333333333337,
+      "loss": 0.4404,
+      "step": 178
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00023866666666666668,
+      "loss": 0.4846,
+      "step": 179
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00024,
+      "loss": 0.6857,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.49820253252983093,
+      "eval_runtime": 39.0562,
+      "eval_samples_per_second": 41.709,
+      "eval_steps_per_second": 20.867,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00024133333333333336,
+      "loss": 0.6329,
+      "step": 181
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002426666666666667,
+      "loss": 0.4513,
+      "step": 182
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.000244,
+      "loss": 0.5719,
+      "step": 183
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00024533333333333335,
+      "loss": 0.5743,
+      "step": 184
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002466666666666667,
+      "loss": 0.4558,
+      "step": 185
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.000248,
+      "loss": 0.8386,
+      "step": 186
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00024933333333333334,
+      "loss": 0.5067,
+      "step": 187
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00025066666666666667,
+      "loss": 0.4633,
+      "step": 188
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.000252,
+      "loss": 0.8261,
+      "step": 189
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.4692,
+      "step": 190
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002546666666666667,
+      "loss": 0.4346,
+      "step": 191
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.4951,
+      "step": 192
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002573333333333333,
+      "loss": 0.5326,
+      "step": 193
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00025866666666666665,
+      "loss": 0.7204,
+      "step": 194
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5423,
+      "step": 195
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00026133333333333336,
+      "loss": 0.5059,
+      "step": 196
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00026266666666666664,
+      "loss": 0.7371,
+      "step": 197
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000264,
+      "loss": 0.4905,
+      "step": 198
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026533333333333335,
+      "loss": 0.5729,
+      "step": 199
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.7326,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.5096016526222229,
+      "eval_runtime": 38.9974,
+      "eval_samples_per_second": 41.772,
+      "eval_steps_per_second": 20.899,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.000268,
+      "loss": 0.7271,
+      "step": 201
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026933333333333334,
+      "loss": 0.5519,
+      "step": 202
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00027066666666666667,
+      "loss": 0.6148,
+      "step": 203
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.5656,
+      "step": 204
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00027333333333333333,
+      "loss": 0.4745,
+      "step": 205
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00027466666666666666,
+      "loss": 0.3901,
+      "step": 206
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.000276,
+      "loss": 0.5684,
+      "step": 207
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00027733333333333337,
+      "loss": 0.6405,
+      "step": 208
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002786666666666667,
+      "loss": 0.6566,
+      "step": 209
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028,
+      "loss": 0.6318,
+      "step": 210
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028133333333333336,
+      "loss": 0.5454,
+      "step": 211
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002826666666666667,
+      "loss": 0.7309,
+      "step": 212
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.000284,
+      "loss": 0.4298,
+      "step": 213
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028533333333333335,
+      "loss": 0.6239,
+      "step": 214
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002866666666666667,
+      "loss": 0.6409,
+      "step": 215
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.000288,
+      "loss": 0.5176,
+      "step": 216
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002893333333333334,
+      "loss": 0.5586,
+      "step": 217
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00029066666666666667,
+      "loss": 0.5455,
+      "step": 218
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000292,
+      "loss": 0.5462,
+      "step": 219
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8225,
+      "step": 220
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 0.5079875588417053,
+      "eval_runtime": 39.0413,
+      "eval_samples_per_second": 41.725,
+      "eval_steps_per_second": 20.875,
+      "step": 220
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002946666666666667,
+      "loss": 0.5573,
+      "step": 221
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000296,
+      "loss": 0.53,
+      "step": 222
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002973333333333333,
+      "loss": 0.4626,
+      "step": 223
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002986666666666667,
+      "loss": 0.4893,
+      "step": 224
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.4595,
+      "step": 225
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00030133333333333336,
+      "loss": 0.6778,
+      "step": 226
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003026666666666667,
+      "loss": 0.6783,
+      "step": 227
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.000304,
+      "loss": 0.6577,
+      "step": 228
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00030533333333333335,
+      "loss": 0.5897,
+      "step": 229
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.6532,
+      "step": 230
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000308,
+      "loss": 0.6298,
+      "step": 231
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00030933333333333334,
+      "loss": 0.4022,
+      "step": 232
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00031066666666666666,
+      "loss": 0.5869,
+      "step": 233
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.6087,
+      "step": 234
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003133333333333333,
+      "loss": 0.5389,
+      "step": 235
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00031466666666666665,
+      "loss": 0.4441,
+      "step": 236
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.4996,
+      "step": 237
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00031733333333333337,
+      "loss": 0.7413,
+      "step": 238
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00031866666666666664,
+      "loss": 0.5144,
+      "step": 239
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00032,
+      "loss": 0.6148,
+      "step": 240
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.4882766604423523,
+      "eval_runtime": 39.1262,
+      "eval_samples_per_second": 41.635,
+      "eval_steps_per_second": 20.83,
+      "step": 240
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00032133333333333336,
+      "loss": 0.4032,
+      "step": 241
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003226666666666667,
+      "loss": 0.5266,
+      "step": 242
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.000324,
+      "loss": 0.6,
+      "step": 243
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00032533333333333334,
+      "loss": 0.55,
+      "step": 244
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003266666666666667,
+      "loss": 0.5816,
+      "step": 245
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000328,
+      "loss": 0.4583,
+      "step": 246
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00032933333333333333,
+      "loss": 0.4872,
+      "step": 247
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00033066666666666666,
+      "loss": 0.5112,
+      "step": 248
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000332,
+      "loss": 0.4714,
+      "step": 249
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8368,
+      "step": 250
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003346666666666667,
+      "loss": 0.4689,
+      "step": 251
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000336,
+      "loss": 0.6403,
+      "step": 252
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00033733333333333337,
+      "loss": 0.6252,
+      "step": 253
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003386666666666667,
+      "loss": 0.6707,
+      "step": 254
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00034,
+      "loss": 0.6497,
+      "step": 255
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00034133333333333335,
+      "loss": 0.3741,
+      "step": 256
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003426666666666667,
+      "loss": 0.3442,
+      "step": 257
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000344,
+      "loss": 0.459,
+      "step": 258
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00034533333333333334,
+      "loss": 0.7909,
+      "step": 259
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.4524,
+      "step": 260
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 0.4969780147075653,
+      "eval_runtime": 39.097,
+      "eval_samples_per_second": 41.666,
+      "eval_steps_per_second": 20.846,
+      "step": 260
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.000348,
+      "loss": 0.514,
+      "step": 261
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00034933333333333333,
+      "loss": 0.5195,
+      "step": 262
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003506666666666667,
+      "loss": 0.5651,
+      "step": 263
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.5681,
+      "step": 264
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003533333333333333,
+      "loss": 0.4571,
+      "step": 265
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003546666666666667,
+      "loss": 0.4669,
+      "step": 266
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6006,
+      "step": 267
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035733333333333336,
+      "loss": 0.61,
+      "step": 268
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035866666666666664,
+      "loss": 0.685,
+      "step": 269
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00036,
+      "loss": 0.5961,
+      "step": 270
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00036133333333333335,
+      "loss": 0.5775,
+      "step": 271
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003626666666666667,
+      "loss": 0.5196,
+      "step": 272
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000364,
+      "loss": 0.5586,
+      "step": 273
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00036533333333333334,
+      "loss": 0.5283,
+      "step": 274
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.5068,
+      "step": 275
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.5045,
+      "step": 276
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00036933333333333333,
+      "loss": 0.5001,
+      "step": 277
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00037066666666666666,
+      "loss": 0.5021,
+      "step": 278
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.4542,
+      "step": 279
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.6084,
+      "step": 280
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.5424579381942749,
+      "eval_runtime": 39.1219,
+      "eval_samples_per_second": 41.639,
+      "eval_steps_per_second": 20.832,
+      "step": 280
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003746666666666667,
+      "loss": 0.5885,
+      "step": 281
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000376,
+      "loss": 0.7034,
+      "step": 282
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00037733333333333336,
+      "loss": 0.601,
+      "step": 283
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003786666666666667,
+      "loss": 0.646,
+      "step": 284
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00038,
+      "loss": 0.5125,
+      "step": 285
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00038133333333333335,
+      "loss": 0.5087,
+      "step": 286
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003826666666666667,
+      "loss": 0.6016,
+      "step": 287
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.000384,
+      "loss": 0.5239,
+      "step": 288
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003853333333333334,
+      "loss": 0.406,
+      "step": 289
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.5812,
+      "step": 290
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.000388,
+      "loss": 0.621,
+      "step": 291
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003893333333333334,
+      "loss": 0.6048,
+      "step": 292
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003906666666666667,
+      "loss": 0.4498,
+      "step": 293
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.000392,
+      "loss": 0.6144,
+      "step": 294
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003933333333333333,
+      "loss": 0.7374,
+      "step": 295
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003946666666666667,
+      "loss": 0.5784,
+      "step": 296
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.5084,
+      "step": 297
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00039733333333333336,
+      "loss": 0.5633,
+      "step": 298
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003986666666666667,
+      "loss": 0.5172,
+      "step": 299
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0004,
+      "loss": 0.6737,
+      "step": 300
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.5059300065040588,
+      "eval_runtime": 39.1035,
+      "eval_samples_per_second": 41.659,
+      "eval_steps_per_second": 20.842,
+      "step": 300
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003999979972589652,
+      "loss": 0.6431,
+      "step": 301
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00039999198907597047,
+      "loss": 0.6727,
+      "step": 302
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00039998197557134424,
+      "loss": 0.4213,
+      "step": 303
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00039996795694563096,
+      "loss": 0.4473,
+      "step": 304
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003999499334795875,
+      "loss": 0.5899,
+      "step": 305
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003999279055341771,
+      "loss": 0.414,
+      "step": 306
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003999018735505626,
+      "loss": 0.4664,
+      "step": 307
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003998718380500971,
+      "loss": 0.6036,
+      "step": 308
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00039983779963431395,
+      "loss": 0.5764,
+      "step": 309
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00039979975898491447,
+      "loss": 0.4595,
+      "step": 310
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003997577168637543,
+      "loss": 0.591,
+      "step": 311
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00039971167411282835,
+      "loss": 0.4327,
+      "step": 312
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003996616316542537,
+      "loss": 0.4061,
+      "step": 313
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00039960759049025105,
+      "loss": 0.5463,
+      "step": 314
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00039954955170312504,
+      "loss": 0.7175,
+      "step": 315
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00039948751645524236,
+      "loss": 0.6533,
+      "step": 316
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003994214859890082,
+      "loss": 0.5988,
+      "step": 317
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00039935146162684205,
+      "loss": 0.5692,
+      "step": 318
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003992774447711503,
+      "loss": 0.5004,
+      "step": 319
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.000399199436904299,
+      "loss": 0.459,
+      "step": 320
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.49676987528800964,
+      "eval_runtime": 39.1916,
+      "eval_samples_per_second": 41.565,
+      "eval_steps_per_second": 20.795,
+      "step": 320
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003991174395885838,
+      "loss": 0.532,
+      "step": 321
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003990314544661984,
+      "loss": 0.4235,
+      "step": 322
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00039894148325920223,
+      "loss": 0.502,
+      "step": 323
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003988475277694856,
+      "loss": 0.5263,
+      "step": 324
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00039874958987873364,
+      "loss": 0.5009,
+      "step": 325
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00039864767154838864,
+      "loss": 0.6524,
+      "step": 326
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003985417748196108,
+      "loss": 0.731,
+      "step": 327
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00039843190181323746,
+      "loss": 0.4875,
+      "step": 328
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00039831805472974037,
+      "loss": 0.3963,
+      "step": 329
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00039820023584918174,
+      "loss": 0.7317,
+      "step": 330
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003980784475311686,
+      "loss": 0.5558,
+      "step": 331
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00039795269221480574,
+      "loss": 0.5645,
+      "step": 332
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00039782297241864635,
+      "loss": 0.6321,
+      "step": 333
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.000397689290740642,
+      "loss": 0.431,
+      "step": 334
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1002,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 9.448895634934333e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-334/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27098634af21778b649dbcd66e907b3281d3f7c9df308b74b9b43e87b72e667c
+size 4475

checkpoint-668/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-668/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": [
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-668/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2059c79e085b404019c4c4e414b8e41c5fcda471db918494f35071c97ab05736
+size 335705741

checkpoint-668/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa31f33dfdf6babf1d7d90df2c474bcf618c1d0d88805ea361fc08fac4d745a7
+size 168624735

checkpoint-668/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1220fee9fd322e2f312fe8568004edae1ea6601aca9184fdbfe03c0a94424d
+size 14575

checkpoint-668/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3206f15c7d9ecd7446f3de714be42999153b81a96f79b5bbedecb40eef013d8c
+size 627

checkpoint-668/trainer_state.json

@@ -0,0 +1,4291 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 20,
+  "global_step": 668,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 2.8327,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 3.0988,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.6419,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 2.381,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.657,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.408,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 3.2158,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 2.2635,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.2e-05,
+      "loss": 1.9091,
+      "step": 9
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.9039,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.4666666666666668e-05,
+      "loss": 1.789,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.3775,
+      "step": 12
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 1.7759,
+      "step": 13
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 1.2334,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2e-05,
+      "loss": 0.7635,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.1333333333333335e-05,
+      "loss": 0.8482,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.2666666666666668e-05,
+      "loss": 0.7464,
+      "step": 17
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.4e-05,
+      "loss": 0.7694,
+      "step": 18
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.5333333333333337e-05,
+      "loss": 0.6606,
+      "step": 19
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.8333,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.6411340832710266,
+      "eval_runtime": 39.0251,
+      "eval_samples_per_second": 41.742,
+      "eval_steps_per_second": 20.884,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.8225,
+      "step": 21
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.9333333333333336e-05,
+      "loss": 0.7741,
+      "step": 22
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.066666666666667e-05,
+      "loss": 0.8105,
+      "step": 23
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.6497,
+      "step": 24
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6973,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.466666666666667e-05,
+      "loss": 0.8275,
+      "step": 26
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.6e-05,
+      "loss": 0.9258,
+      "step": 27
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.6865,
+      "step": 28
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.866666666666667e-05,
+      "loss": 0.68,
+      "step": 29
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4e-05,
+      "loss": 0.7747,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.133333333333333e-05,
+      "loss": 0.725,
+      "step": 31
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.266666666666667e-05,
+      "loss": 0.6831,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.754,
+      "step": 33
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.5333333333333335e-05,
+      "loss": 0.7415,
+      "step": 34
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.7404,
+      "step": 35
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8e-05,
+      "loss": 0.7474,
+      "step": 36
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.933333333333334e-05,
+      "loss": 0.7268,
+      "step": 37
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 5.0666666666666674e-05,
+      "loss": 0.7249,
+      "step": 38
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.5853,
+      "step": 39
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.6715,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.5898512005805969,
+      "eval_runtime": 39.0712,
+      "eval_samples_per_second": 41.693,
+      "eval_steps_per_second": 20.859,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 5.466666666666666e-05,
+      "loss": 0.6705,
+      "step": 41
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.6564,
+      "step": 42
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5.7333333333333336e-05,
+      "loss": 0.7193,
+      "step": 43
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 5.866666666666667e-05,
+      "loss": 0.7587,
+      "step": 44
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 6e-05,
+      "loss": 0.7327,
+      "step": 45
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.133333333333334e-05,
+      "loss": 0.7989,
+      "step": 46
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.266666666666667e-05,
+      "loss": 0.586,
+      "step": 47
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.6681,
+      "step": 48
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.533333333333334e-05,
+      "loss": 0.7467,
+      "step": 49
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.5078,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.7192,
+      "step": 51
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 6.933333333333334e-05,
+      "loss": 0.8233,
+      "step": 52
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.066666666666667e-05,
+      "loss": 0.7273,
+      "step": 53
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.2e-05,
+      "loss": 0.6151,
+      "step": 54
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.7629,
+      "step": 55
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.466666666666667e-05,
+      "loss": 0.6741,
+      "step": 56
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.6e-05,
+      "loss": 0.5387,
+      "step": 57
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 7.733333333333333e-05,
+      "loss": 0.7459,
+      "step": 58
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 7.866666666666666e-05,
+      "loss": 0.5558,
+      "step": 59
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8e-05,
+      "loss": 0.5905,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 0.557337760925293,
+      "eval_runtime": 39.0718,
+      "eval_samples_per_second": 41.692,
+      "eval_steps_per_second": 20.859,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 8.133333333333334e-05,
+      "loss": 0.6305,
+      "step": 61
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.266666666666667e-05,
+      "loss": 0.7207,
+      "step": 62
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.4e-05,
+      "loss": 0.6926,
+      "step": 63
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.533333333333334e-05,
+      "loss": 0.4858,
+      "step": 64
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 0.634,
+      "step": 65
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.6184,
+      "step": 66
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 8.933333333333334e-05,
+      "loss": 0.5475,
+      "step": 67
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.066666666666667e-05,
+      "loss": 0.5431,
+      "step": 68
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.659,
+      "step": 69
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.8016,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.466666666666667e-05,
+      "loss": 0.6429,
+      "step": 71
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.6e-05,
+      "loss": 0.5628,
+      "step": 72
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.733333333333335e-05,
+      "loss": 0.6041,
+      "step": 73
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.866666666666668e-05,
+      "loss": 0.4893,
+      "step": 74
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001,
+      "loss": 0.7429,
+      "step": 75
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00010133333333333335,
+      "loss": 0.5158,
+      "step": 76
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00010266666666666666,
+      "loss": 0.7377,
+      "step": 77
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.5242,
+      "step": 78
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00010533333333333332,
+      "loss": 0.549,
+      "step": 79
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.5845,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.5341688990592957,
+      "eval_runtime": 39.1341,
+      "eval_samples_per_second": 41.626,
+      "eval_steps_per_second": 20.826,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.5873,
+      "step": 81
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00010933333333333333,
+      "loss": 0.5998,
+      "step": 82
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011066666666666667,
+      "loss": 0.8269,
+      "step": 83
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.6924,
+      "step": 84
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 0.5342,
+      "step": 85
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011466666666666667,
+      "loss": 0.5858,
+      "step": 86
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.000116,
+      "loss": 0.5207,
+      "step": 87
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011733333333333334,
+      "loss": 0.6034,
+      "step": 88
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011866666666666669,
+      "loss": 0.707,
+      "step": 89
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00012,
+      "loss": 0.6256,
+      "step": 90
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00012133333333333335,
+      "loss": 0.8011,
+      "step": 91
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00012266666666666668,
+      "loss": 0.7638,
+      "step": 92
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.000124,
+      "loss": 0.5857,
+      "step": 93
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00012533333333333334,
+      "loss": 0.5948,
+      "step": 94
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 0.6051,
+      "step": 95
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.6847,
+      "step": 96
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00012933333333333332,
+      "loss": 0.4701,
+      "step": 97
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00013066666666666668,
+      "loss": 0.6454,
+      "step": 98
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.000132,
+      "loss": 0.5723,
+      "step": 99
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.5524,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.5259758234024048,
+      "eval_runtime": 39.0597,
+      "eval_samples_per_second": 41.705,
+      "eval_steps_per_second": 20.865,
+      "step": 100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00013466666666666667,
+      "loss": 0.6256,
+      "step": 101
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.5798,
+      "step": 102
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013733333333333333,
+      "loss": 0.6021,
+      "step": 103
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00013866666666666669,
+      "loss": 0.652,
+      "step": 104
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00014,
+      "loss": 0.5602,
+      "step": 105
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00014133333333333334,
+      "loss": 0.6358,
+      "step": 106
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00014266666666666667,
+      "loss": 0.6063,
+      "step": 107
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.000144,
+      "loss": 0.6901,
+      "step": 108
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00014533333333333333,
+      "loss": 0.5586,
+      "step": 109
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.6054,
+      "step": 110
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000148,
+      "loss": 0.4814,
+      "step": 111
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00014933333333333335,
+      "loss": 0.347,
+      "step": 112
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015066666666666668,
+      "loss": 0.4877,
+      "step": 113
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000152,
+      "loss": 0.7594,
+      "step": 114
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015333333333333334,
+      "loss": 0.5597,
+      "step": 115
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015466666666666667,
+      "loss": 0.4975,
+      "step": 116
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.6336,
+      "step": 117
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015733333333333333,
+      "loss": 0.6042,
+      "step": 118
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00015866666666666668,
+      "loss": 0.4253,
+      "step": 119
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00016,
+      "loss": 0.5516,
+      "step": 120
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.5273345708847046,
+      "eval_runtime": 39.0262,
+      "eval_samples_per_second": 41.741,
+      "eval_steps_per_second": 20.883,
+      "step": 120
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00016133333333333334,
+      "loss": 0.3813,
+      "step": 121
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00016266666666666667,
+      "loss": 0.5743,
+      "step": 122
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.000164,
+      "loss": 0.5525,
+      "step": 123
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00016533333333333333,
+      "loss": 0.6549,
+      "step": 124
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.6705,
+      "step": 125
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.000168,
+      "loss": 0.6486,
+      "step": 126
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00016933333333333335,
+      "loss": 0.5122,
+      "step": 127
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00017066666666666668,
+      "loss": 0.6339,
+      "step": 128
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.000172,
+      "loss": 0.5281,
+      "step": 129
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.6219,
+      "step": 130
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00017466666666666667,
+      "loss": 0.548,
+      "step": 131
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.6827,
+      "step": 132
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00017733333333333335,
+      "loss": 0.6162,
+      "step": 133
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00017866666666666668,
+      "loss": 0.4973,
+      "step": 134
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00018,
+      "loss": 0.7511,
+      "step": 135
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018133333333333334,
+      "loss": 0.4998,
+      "step": 136
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018266666666666667,
+      "loss": 0.4568,
+      "step": 137
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.4537,
+      "step": 138
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00018533333333333333,
+      "loss": 0.5601,
+      "step": 139
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.5465,
+      "step": 140
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 0.5131502151489258,
+      "eval_runtime": 39.125,
+      "eval_samples_per_second": 41.636,
+      "eval_steps_per_second": 20.831,
+      "step": 140
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.000188,
+      "loss": 0.5256,
+      "step": 141
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00018933333333333335,
+      "loss": 0.6077,
+      "step": 142
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019066666666666668,
+      "loss": 0.6348,
+      "step": 143
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.000192,
+      "loss": 0.5437,
+      "step": 144
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 0.602,
+      "step": 145
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001946666666666667,
+      "loss": 0.4774,
+      "step": 146
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000196,
+      "loss": 0.6249,
+      "step": 147
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019733333333333335,
+      "loss": 0.6498,
+      "step": 148
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00019866666666666668,
+      "loss": 0.5419,
+      "step": 149
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002,
+      "loss": 0.5724,
+      "step": 150
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00020133333333333334,
+      "loss": 0.6224,
+      "step": 151
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002026666666666667,
+      "loss": 0.4996,
+      "step": 152
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00020400000000000003,
+      "loss": 0.5016,
+      "step": 153
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00020533333333333333,
+      "loss": 0.4315,
+      "step": 154
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00020666666666666668,
+      "loss": 0.5096,
+      "step": 155
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00020800000000000001,
+      "loss": 0.5167,
+      "step": 156
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00020933333333333334,
+      "loss": 0.6057,
+      "step": 157
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00021066666666666665,
+      "loss": 0.763,
+      "step": 158
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00021200000000000003,
+      "loss": 0.4568,
+      "step": 159
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00021333333333333333,
+      "loss": 0.439,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.5084798336029053,
+      "eval_runtime": 39.1227,
+      "eval_samples_per_second": 41.638,
+      "eval_steps_per_second": 20.832,
+      "step": 160
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00021466666666666666,
+      "loss": 0.3806,
+      "step": 161
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00021600000000000002,
+      "loss": 0.4544,
+      "step": 162
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00021733333333333335,
+      "loss": 0.5606,
+      "step": 163
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00021866666666666665,
+      "loss": 0.5595,
+      "step": 164
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022000000000000003,
+      "loss": 0.5773,
+      "step": 165
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022133333333333334,
+      "loss": 0.511,
+      "step": 166
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022266666666666667,
+      "loss": 0.6515,
+      "step": 167
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022400000000000002,
+      "loss": 0.4612,
+      "step": 168
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022533333333333335,
+      "loss": 0.4674,
+      "step": 169
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022666666666666668,
+      "loss": 0.6907,
+      "step": 170
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.6061,
+      "step": 171
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022933333333333334,
+      "loss": 0.594,
+      "step": 172
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00023066666666666667,
+      "loss": 0.5703,
+      "step": 173
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.000232,
+      "loss": 0.6094,
+      "step": 174
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00023333333333333336,
+      "loss": 0.5031,
+      "step": 175
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0002346666666666667,
+      "loss": 0.4689,
+      "step": 176
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000236,
+      "loss": 0.6271,
+      "step": 177
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00023733333333333337,
+      "loss": 0.4404,
+      "step": 178
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00023866666666666668,
+      "loss": 0.4846,
+      "step": 179
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00024,
+      "loss": 0.6857,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.49820253252983093,
+      "eval_runtime": 39.0562,
+      "eval_samples_per_second": 41.709,
+      "eval_steps_per_second": 20.867,
+      "step": 180
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00024133333333333336,
+      "loss": 0.6329,
+      "step": 181
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002426666666666667,
+      "loss": 0.4513,
+      "step": 182
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.000244,
+      "loss": 0.5719,
+      "step": 183
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00024533333333333335,
+      "loss": 0.5743,
+      "step": 184
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002466666666666667,
+      "loss": 0.4558,
+      "step": 185
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.000248,
+      "loss": 0.8386,
+      "step": 186
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00024933333333333334,
+      "loss": 0.5067,
+      "step": 187
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00025066666666666667,
+      "loss": 0.4633,
+      "step": 188
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.000252,
+      "loss": 0.8261,
+      "step": 189
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00025333333333333333,
+      "loss": 0.4692,
+      "step": 190
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002546666666666667,
+      "loss": 0.4346,
+      "step": 191
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00025600000000000004,
+      "loss": 0.4951,
+      "step": 192
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002573333333333333,
+      "loss": 0.5326,
+      "step": 193
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00025866666666666665,
+      "loss": 0.7204,
+      "step": 194
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00026000000000000003,
+      "loss": 0.5423,
+      "step": 195
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00026133333333333336,
+      "loss": 0.5059,
+      "step": 196
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00026266666666666664,
+      "loss": 0.7371,
+      "step": 197
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000264,
+      "loss": 0.4905,
+      "step": 198
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026533333333333335,
+      "loss": 0.5729,
+      "step": 199
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002666666666666667,
+      "loss": 0.7326,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.5096016526222229,
+      "eval_runtime": 38.9974,
+      "eval_samples_per_second": 41.772,
+      "eval_steps_per_second": 20.899,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.000268,
+      "loss": 0.7271,
+      "step": 201
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026933333333333334,
+      "loss": 0.5519,
+      "step": 202
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00027066666666666667,
+      "loss": 0.6148,
+      "step": 203
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00027200000000000005,
+      "loss": 0.5656,
+      "step": 204
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00027333333333333333,
+      "loss": 0.4745,
+      "step": 205
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00027466666666666666,
+      "loss": 0.3901,
+      "step": 206
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.000276,
+      "loss": 0.5684,
+      "step": 207
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00027733333333333337,
+      "loss": 0.6405,
+      "step": 208
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002786666666666667,
+      "loss": 0.6566,
+      "step": 209
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028,
+      "loss": 0.6318,
+      "step": 210
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00028133333333333336,
+      "loss": 0.5454,
+      "step": 211
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002826666666666667,
+      "loss": 0.7309,
+      "step": 212
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.000284,
+      "loss": 0.4298,
+      "step": 213
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00028533333333333335,
+      "loss": 0.6239,
+      "step": 214
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002866666666666667,
+      "loss": 0.6409,
+      "step": 215
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.000288,
+      "loss": 0.5176,
+      "step": 216
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002893333333333334,
+      "loss": 0.5586,
+      "step": 217
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00029066666666666667,
+      "loss": 0.5455,
+      "step": 218
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000292,
+      "loss": 0.5462,
+      "step": 219
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002933333333333333,
+      "loss": 0.8225,
+      "step": 220
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 0.5079875588417053,
+      "eval_runtime": 39.0413,
+      "eval_samples_per_second": 41.725,
+      "eval_steps_per_second": 20.875,
+      "step": 220
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002946666666666667,
+      "loss": 0.5573,
+      "step": 221
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000296,
+      "loss": 0.53,
+      "step": 222
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002973333333333333,
+      "loss": 0.4626,
+      "step": 223
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002986666666666667,
+      "loss": 0.4893,
+      "step": 224
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.4595,
+      "step": 225
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00030133333333333336,
+      "loss": 0.6778,
+      "step": 226
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003026666666666667,
+      "loss": 0.6783,
+      "step": 227
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.000304,
+      "loss": 0.6577,
+      "step": 228
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00030533333333333335,
+      "loss": 0.5897,
+      "step": 229
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003066666666666667,
+      "loss": 0.6532,
+      "step": 230
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.000308,
+      "loss": 0.6298,
+      "step": 231
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00030933333333333334,
+      "loss": 0.4022,
+      "step": 232
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00031066666666666666,
+      "loss": 0.5869,
+      "step": 233
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00031200000000000005,
+      "loss": 0.6087,
+      "step": 234
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003133333333333333,
+      "loss": 0.5389,
+      "step": 235
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00031466666666666665,
+      "loss": 0.4441,
+      "step": 236
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00031600000000000004,
+      "loss": 0.4996,
+      "step": 237
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00031733333333333337,
+      "loss": 0.7413,
+      "step": 238
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00031866666666666664,
+      "loss": 0.5144,
+      "step": 239
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00032,
+      "loss": 0.6148,
+      "step": 240
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.4882766604423523,
+      "eval_runtime": 39.1262,
+      "eval_samples_per_second": 41.635,
+      "eval_steps_per_second": 20.83,
+      "step": 240
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00032133333333333336,
+      "loss": 0.4032,
+      "step": 241
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003226666666666667,
+      "loss": 0.5266,
+      "step": 242
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.000324,
+      "loss": 0.6,
+      "step": 243
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00032533333333333334,
+      "loss": 0.55,
+      "step": 244
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003266666666666667,
+      "loss": 0.5816,
+      "step": 245
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000328,
+      "loss": 0.4583,
+      "step": 246
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00032933333333333333,
+      "loss": 0.4872,
+      "step": 247
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00033066666666666666,
+      "loss": 0.5112,
+      "step": 248
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000332,
+      "loss": 0.4714,
+      "step": 249
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003333333333333334,
+      "loss": 0.8368,
+      "step": 250
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003346666666666667,
+      "loss": 0.4689,
+      "step": 251
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000336,
+      "loss": 0.6403,
+      "step": 252
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00033733333333333337,
+      "loss": 0.6252,
+      "step": 253
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003386666666666667,
+      "loss": 0.6707,
+      "step": 254
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00034,
+      "loss": 0.6497,
+      "step": 255
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00034133333333333335,
+      "loss": 0.3741,
+      "step": 256
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003426666666666667,
+      "loss": 0.3442,
+      "step": 257
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000344,
+      "loss": 0.459,
+      "step": 258
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00034533333333333334,
+      "loss": 0.7909,
+      "step": 259
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00034666666666666667,
+      "loss": 0.4524,
+      "step": 260
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 0.4969780147075653,
+      "eval_runtime": 39.097,
+      "eval_samples_per_second": 41.666,
+      "eval_steps_per_second": 20.846,
+      "step": 260
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.000348,
+      "loss": 0.514,
+      "step": 261
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00034933333333333333,
+      "loss": 0.5195,
+      "step": 262
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003506666666666667,
+      "loss": 0.5651,
+      "step": 263
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00035200000000000005,
+      "loss": 0.5681,
+      "step": 264
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003533333333333333,
+      "loss": 0.4571,
+      "step": 265
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003546666666666667,
+      "loss": 0.4669,
+      "step": 266
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035600000000000003,
+      "loss": 0.6006,
+      "step": 267
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00035733333333333336,
+      "loss": 0.61,
+      "step": 268
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00035866666666666664,
+      "loss": 0.685,
+      "step": 269
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00036,
+      "loss": 0.5961,
+      "step": 270
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00036133333333333335,
+      "loss": 0.5775,
+      "step": 271
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003626666666666667,
+      "loss": 0.5196,
+      "step": 272
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.000364,
+      "loss": 0.5586,
+      "step": 273
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00036533333333333334,
+      "loss": 0.5283,
+      "step": 274
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00036666666666666667,
+      "loss": 0.5068,
+      "step": 275
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00036800000000000005,
+      "loss": 0.5045,
+      "step": 276
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00036933333333333333,
+      "loss": 0.5001,
+      "step": 277
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00037066666666666666,
+      "loss": 0.5021,
+      "step": 278
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00037200000000000004,
+      "loss": 0.4542,
+      "step": 279
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003733333333333334,
+      "loss": 0.6084,
+      "step": 280
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.5424579381942749,
+      "eval_runtime": 39.1219,
+      "eval_samples_per_second": 41.639,
+      "eval_steps_per_second": 20.832,
+      "step": 280
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003746666666666667,
+      "loss": 0.5885,
+      "step": 281
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000376,
+      "loss": 0.7034,
+      "step": 282
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00037733333333333336,
+      "loss": 0.601,
+      "step": 283
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003786666666666667,
+      "loss": 0.646,
+      "step": 284
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00038,
+      "loss": 0.5125,
+      "step": 285
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00038133333333333335,
+      "loss": 0.5087,
+      "step": 286
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003826666666666667,
+      "loss": 0.6016,
+      "step": 287
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.000384,
+      "loss": 0.5239,
+      "step": 288
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003853333333333334,
+      "loss": 0.406,
+      "step": 289
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00038666666666666667,
+      "loss": 0.5812,
+      "step": 290
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.000388,
+      "loss": 0.621,
+      "step": 291
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003893333333333334,
+      "loss": 0.6048,
+      "step": 292
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003906666666666667,
+      "loss": 0.4498,
+      "step": 293
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.000392,
+      "loss": 0.6144,
+      "step": 294
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003933333333333333,
+      "loss": 0.7374,
+      "step": 295
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003946666666666667,
+      "loss": 0.5784,
+      "step": 296
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00039600000000000003,
+      "loss": 0.5084,
+      "step": 297
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00039733333333333336,
+      "loss": 0.5633,
+      "step": 298
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003986666666666667,
+      "loss": 0.5172,
+      "step": 299
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0004,
+      "loss": 0.6737,
+      "step": 300
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.5059300065040588,
+      "eval_runtime": 39.1035,
+      "eval_samples_per_second": 41.659,
+      "eval_steps_per_second": 20.842,
+      "step": 300
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003999979972589652,
+      "loss": 0.6431,
+      "step": 301
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00039999198907597047,
+      "loss": 0.6727,
+      "step": 302
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00039998197557134424,
+      "loss": 0.4213,
+      "step": 303
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00039996795694563096,
+      "loss": 0.4473,
+      "step": 304
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003999499334795875,
+      "loss": 0.5899,
+      "step": 305
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003999279055341771,
+      "loss": 0.414,
+      "step": 306
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003999018735505626,
+      "loss": 0.4664,
+      "step": 307
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003998718380500971,
+      "loss": 0.6036,
+      "step": 308
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00039983779963431395,
+      "loss": 0.5764,
+      "step": 309
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00039979975898491447,
+      "loss": 0.4595,
+      "step": 310
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003997577168637543,
+      "loss": 0.591,
+      "step": 311
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00039971167411282835,
+      "loss": 0.4327,
+      "step": 312
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003996616316542537,
+      "loss": 0.4061,
+      "step": 313
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00039960759049025105,
+      "loss": 0.5463,
+      "step": 314
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00039954955170312504,
+      "loss": 0.7175,
+      "step": 315
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00039948751645524236,
+      "loss": 0.6533,
+      "step": 316
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003994214859890082,
+      "loss": 0.5988,
+      "step": 317
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00039935146162684205,
+      "loss": 0.5692,
+      "step": 318
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003992774447711503,
+      "loss": 0.5004,
+      "step": 319
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.000399199436904299,
+      "loss": 0.459,
+      "step": 320
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.49676987528800964,
+      "eval_runtime": 39.1916,
+      "eval_samples_per_second": 41.565,
+      "eval_steps_per_second": 20.795,
+      "step": 320
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003991174395885838,
+      "loss": 0.532,
+      "step": 321
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003990314544661984,
+      "loss": 0.4235,
+      "step": 322
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00039894148325920223,
+      "loss": 0.502,
+      "step": 323
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003988475277694856,
+      "loss": 0.5263,
+      "step": 324
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00039874958987873364,
+      "loss": 0.5009,
+      "step": 325
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00039864767154838864,
+      "loss": 0.6524,
+      "step": 326
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003985417748196108,
+      "loss": 0.731,
+      "step": 327
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00039843190181323746,
+      "loss": 0.4875,
+      "step": 328
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00039831805472974037,
+      "loss": 0.3963,
+      "step": 329
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00039820023584918174,
+      "loss": 0.7317,
+      "step": 330
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003980784475311686,
+      "loss": 0.5558,
+      "step": 331
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00039795269221480574,
+      "loss": 0.5645,
+      "step": 332
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00039782297241864635,
+      "loss": 0.6321,
+      "step": 333
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.000397689290740642,
+      "loss": 0.431,
+      "step": 334
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00039755164985809063,
+      "loss": 0.4686,
+      "step": 335
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00039741005252758255,
+      "loss": 0.6301,
+      "step": 336
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003972645015849457,
+      "loss": 0.4018,
+      "step": 337
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00039711499994518856,
+      "loss": 0.6649,
+      "step": 338
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00039696155060244166,
+      "loss": 0.4922,
+      "step": 339
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.000396804156629898,
+      "loss": 0.6138,
+      "step": 340
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.5111443996429443,
+      "eval_runtime": 39.2254,
+      "eval_samples_per_second": 41.529,
+      "eval_steps_per_second": 20.777,
+      "step": 340
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003966428211797514,
+      "loss": 0.4932,
+      "step": 341
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00039647754748313294,
+      "loss": 0.4322,
+      "step": 342
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0003963083388500469,
+      "loss": 0.577,
+      "step": 343
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.000396135198669304,
+      "loss": 0.5161,
+      "step": 344
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00039595813040845353,
+      "loss": 0.6532,
+      "step": 345
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003957771376137144,
+      "loss": 0.3927,
+      "step": 346
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00039559222390990353,
+      "loss": 0.5745,
+      "step": 347
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00039540339300036344,
+      "loss": 0.4108,
+      "step": 348
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0003952106486668884,
+      "loss": 0.549,
+      "step": 349
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00039501399476964805,
+      "loss": 0.3471,
+      "step": 350
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00039481343524711097,
+      "loss": 0.5154,
+      "step": 351
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00039460897411596477,
+      "loss": 0.4799,
+      "step": 352
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003944006154710366,
+      "loss": 0.4751,
+      "step": 353
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003941883634852104,
+      "loss": 0.429,
+      "step": 354
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0003939722224093439,
+      "loss": 0.4617,
+      "step": 355
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003937521965721831,
+      "loss": 0.3747,
+      "step": 356
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00039352829038027563,
+      "loss": 0.478,
+      "step": 357
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003933005083178828,
+      "loss": 0.3775,
+      "step": 358
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0003930688549468894,
+      "loss": 0.5047,
+      "step": 359
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003928333349067125,
+      "loss": 0.4023,
+      "step": 360
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.5498852729797363,
+      "eval_runtime": 39.0748,
+      "eval_samples_per_second": 41.689,
+      "eval_steps_per_second": 20.857,
+      "step": 360
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00039259395291420864,
+      "loss": 0.4544,
+      "step": 361
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0003923507137635792,
+      "loss": 0.5693,
+      "step": 362
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003921036223262745,
+      "loss": 0.3904,
+      "step": 363
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003918526835508961,
+      "loss": 0.3278,
+      "step": 364
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0003915979024630978,
+      "loss": 0.5908,
+      "step": 365
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003913392841654851,
+      "loss": 0.6124,
+      "step": 366
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003910768338375126,
+      "loss": 0.5616,
+      "step": 367
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00039081055673538095,
+      "loss": 0.509,
+      "step": 368
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0003905404581919307,
+      "loss": 0.5066,
+      "step": 369
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003902665436165364,
+      "loss": 0.6078,
+      "step": 370
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00038998881849499755,
+      "loss": 0.457,
+      "step": 371
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0003897072883894291,
+      "loss": 0.4299,
+      "step": 372
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003894219589381501,
+      "loss": 0.5378,
+      "step": 373
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0003891328358555705,
+      "loss": 0.3455,
+      "step": 374
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00038883992493207693,
+      "loss": 0.5129,
+      "step": 375
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00038854323203391664,
+      "loss": 0.5162,
+      "step": 376
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00038824276310308003,
+      "loss": 0.4989,
+      "step": 377
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0003879385241571817,
+      "loss": 0.4063,
+      "step": 378
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00038763052128933985,
+      "loss": 0.4347,
+      "step": 379
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0003873187606680543,
+      "loss": 0.4406,
+      "step": 380
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 0.5657373070716858,
+      "eval_runtime": 39.1369,
+      "eval_samples_per_second": 41.623,
+      "eval_steps_per_second": 20.824,
+      "step": 380
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.000387003248537083,
+      "loss": 0.6143,
+      "step": 381
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0003866839912153168,
+      "loss": 0.3564,
+      "step": 382
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00038636099509665306,
+      "loss": 0.3914,
+      "step": 383
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0003860342666498677,
+      "loss": 0.4229,
+      "step": 384
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0003857038124184853,
+      "loss": 0.52,
+      "step": 385
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00038536963902064834,
+      "loss": 0.4873,
+      "step": 386
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0003850317531489847,
+      "loss": 0.3773,
+      "step": 387
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00038469016157047334,
+      "loss": 0.3672,
+      "step": 388
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0003843448711263089,
+      "loss": 0.5072,
+      "step": 389
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00038399588873176487,
+      "loss": 0.5866,
+      "step": 390
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00038364322137605483,
+      "loss": 0.3751,
+      "step": 391
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00038328687612219263,
+      "loss": 0.5793,
+      "step": 392
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00038292686010685093,
+      "loss": 0.4443,
+      "step": 393
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0003825631805402182,
+      "loss": 0.3881,
+      "step": 394
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0003821958447058543,
+      "loss": 0.4709,
+      "step": 395
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0003818248599605448,
+      "loss": 0.4203,
+      "step": 396
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00038145023373415326,
+      "loss": 0.438,
+      "step": 397
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0003810719735294731,
+      "loss": 0.4127,
+      "step": 398
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00038069008692207646,
+      "loss": 0.3724,
+      "step": 399
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0003803045815601633,
+      "loss": 0.4054,
+      "step": 400
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.5386510491371155,
+      "eval_runtime": 39.0231,
+      "eval_samples_per_second": 41.744,
+      "eval_steps_per_second": 20.885,
+      "step": 400
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00037991546516440746,
+      "loss": 0.3894,
+      "step": 401
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0003795227455278028,
+      "loss": 0.4255,
+      "step": 402
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00037912643051550674,
+      "loss": 0.5649,
+      "step": 403
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0003787265280646825,
+      "loss": 0.4947,
+      "step": 404
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0003783230461843406,
+      "loss": 0.3681,
+      "step": 405
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00037791599295517825,
+      "loss": 0.5551,
+      "step": 406
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00037750537652941744,
+      "loss": 0.3648,
+      "step": 407
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.000377091205130642,
+      "loss": 0.4568,
+      "step": 408
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0003766734870536323,
+      "loss": 0.4425,
+      "step": 409
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0003762522306641998,
+      "loss": 0.4919,
+      "step": 410
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00037582744439901896,
+      "loss": 0.406,
+      "step": 411
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.0003753991367654587,
+      "loss": 0.3955,
+      "step": 412
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0003749673163414117,
+      "loss": 0.6121,
+      "step": 413
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0003745319917751229,
+      "loss": 0.5588,
+      "step": 414
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.0003740931717850159,
+      "loss": 0.4977,
+      "step": 415
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00037365086515951874,
+      "loss": 0.4462,
+      "step": 416
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00037320508075688776,
+      "loss": 0.4864,
+      "step": 417
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00037275582750503005,
+      "loss": 0.3771,
+      "step": 418
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00037230311440132494,
+      "loss": 0.4767,
+      "step": 419
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0003718469505124434,
+      "loss": 0.4707,
+      "step": 420
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.5697975158691406,
+      "eval_runtime": 39.0417,
+      "eval_samples_per_second": 41.725,
+      "eval_steps_per_second": 20.875,
+      "step": 420
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00037138734497416684,
+      "loss": 0.6288,
+      "step": 421
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00037092430699120407,
+      "loss": 0.4509,
+      "step": 422
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0003704578458370067,
+      "loss": 0.456,
+      "step": 423
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00036998797085358373,
+      "loss": 0.3633,
+      "step": 424
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0003695146914513142,
+      "loss": 0.5356,
+      "step": 425
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.000369038017108759,
+      "loss": 0.4065,
+      "step": 426
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0003685579573724707,
+      "loss": 0.4022,
+      "step": 427
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0003680745218568026,
+      "loss": 0.5808,
+      "step": 428
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0003675877202437163,
+      "loss": 0.5291,
+      "step": 429
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00036709756228258734,
+      "loss": 0.5039,
+      "step": 430
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.0003666040577900104,
+      "loss": 0.5416,
+      "step": 431
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00036610721664960235,
+      "loss": 0.4544,
+      "step": 432
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0003656070488118047,
+      "loss": 0.5335,
+      "step": 433
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.000365103564293684,
+      "loss": 0.3835,
+      "step": 434
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.0003645967731787313,
+      "loss": 0.5434,
+      "step": 435
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00036408668561666014,
+      "loss": 0.4031,
+      "step": 436
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00036357331182320344,
+      "loss": 0.426,
+      "step": 437
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00036305666207990886,
+      "loss": 0.6629,
+      "step": 438
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0003625367467339329,
+      "loss": 0.3697,
+      "step": 439
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0003620135761978333,
+      "loss": 0.577,
+      "step": 440
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.518071711063385,
+      "eval_runtime": 39.13,
+      "eval_samples_per_second": 41.631,
+      "eval_steps_per_second": 20.828,
+      "step": 440
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0003614871609493614,
+      "loss": 0.4543,
+      "step": 441
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00036095751153125113,
+      "loss": 0.5656,
+      "step": 442
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0003604246385510088,
+      "loss": 0.4478,
+      "step": 443
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0003598885526807003,
+      "loss": 0.3964,
+      "step": 444
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0003593492646567372,
+      "loss": 0.3682,
+      "step": 445
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00035880678527966224,
+      "loss": 0.4475,
+      "step": 446
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0003582611254139324,
+      "loss": 0.7257,
+      "step": 447
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00035771229598770174,
+      "loss": 0.5785,
+      "step": 448
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00035716030799260237,
+      "loss": 0.542,
+      "step": 449
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0003566051724835245,
+      "loss": 0.2928,
+      "step": 450
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0003560469005783945,
+      "loss": 0.5397,
+      "step": 451
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0003554855034579532,
+      "loss": 0.4156,
+      "step": 452
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0003549209923655309,
+      "loss": 0.5145,
+      "step": 453
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00035435337860682304,
+      "loss": 0.4941,
+      "step": 454
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0003537826735496631,
+      "loss": 0.4365,
+      "step": 455
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0003532088886237956,
+      "loss": 0.4155,
+      "step": 456
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0003526320353206467,
+      "loss": 0.5667,
+      "step": 457
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00035205212519309406,
+      "loss": 0.3406,
+      "step": 458
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00035146916985523603,
+      "loss": 0.5219,
+      "step": 459
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00035088318098215805,
+      "loss": 0.279,
+      "step": 460
+    },
+    {
+      "epoch": 1.38,
+      "eval_loss": 0.5242519378662109,
+      "eval_runtime": 39.0363,
+      "eval_samples_per_second": 41.73,
+      "eval_steps_per_second": 20.878,
+      "step": 460
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0003502941703097,
+      "loss": 0.3764,
+      "step": 461
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00034970214963422024,
+      "loss": 0.4389,
+      "step": 462
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0003491071308123598,
+      "loss": 0.4601,
+      "step": 463
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0003485091257608047,
+      "loss": 0.5373,
+      "step": 464
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00034790814645604745,
+      "loss": 0.4069,
+      "step": 465
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0003473042049341474,
+      "loss": 0.6186,
+      "step": 466
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0003466973132904892,
+      "loss": 0.6,
+      "step": 467
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00034608748367954067,
+      "loss": 0.4138,
+      "step": 468
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00034547472831460976,
+      "loss": 0.4754,
+      "step": 469
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00034485905946759967,
+      "loss": 0.5631,
+      "step": 470
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00034424048946876294,
+      "loss": 0.347,
+      "step": 471
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0003436190307064548,
+      "loss": 0.505,
+      "step": 472
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00034299469562688493,
+      "loss": 0.395,
+      "step": 473
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.0003423674967338681,
+      "loss": 0.4521,
+      "step": 474
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.000341737446588574,
+      "loss": 0.62,
+      "step": 475
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0003411045578092754,
+      "loss": 0.4563,
+      "step": 476
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00034046884307109554,
+      "loss": 0.426,
+      "step": 477
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0003398303151057543,
+      "loss": 0.3657,
+      "step": 478
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.0003391889867013134,
+      "loss": 0.4089,
+      "step": 479
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00033854487070191994,
+      "loss": 0.5576,
+      "step": 480
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 0.5171985626220703,
+      "eval_runtime": 39.1209,
+      "eval_samples_per_second": 41.64,
+      "eval_steps_per_second": 20.833,
+      "step": 480
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00033789798000754927,
+      "loss": 0.564,
+      "step": 481
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0003372483275737468,
+      "loss": 0.5006,
+      "step": 482
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0003365959264113683,
+      "loss": 0.4876,
+      "step": 483
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00033594078958631984,
+      "loss": 0.6769,
+      "step": 484
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00033528293021929526,
+      "loss": 0.5196,
+      "step": 485
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00033462236148551407,
+      "loss": 0.5664,
+      "step": 486
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00033395909661445737,
+      "loss": 0.2954,
+      "step": 487
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0003332931488896029,
+      "loss": 0.5158,
+      "step": 488
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00033262453164815904,
+      "loss": 0.3675,
+      "step": 489
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0003319532582807977,
+      "loss": 0.3627,
+      "step": 490
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00033127934223138594,
+      "loss": 0.5265,
+      "step": 491
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.000330602796996717,
+      "loss": 0.4126,
+      "step": 492
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0003299236361262401,
+      "loss": 0.4083,
+      "step": 493
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00032924187322178863,
+      "loss": 0.4159,
+      "step": 494
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00032855752193730787,
+      "loss": 0.376,
+      "step": 495
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00032787059597858204,
+      "loss": 0.3039,
+      "step": 496
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.000327181109102959,
+      "loss": 0.4458,
+      "step": 497
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00032648907511907547,
+      "loss": 0.4663,
+      "step": 498
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00032579450788658,
+      "loss": 0.4005,
+      "step": 499
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0003250974213158555,
+      "loss": 0.382,
+      "step": 500
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.5177609920501709,
+      "eval_runtime": 39.1238,
+      "eval_samples_per_second": 41.637,
+      "eval_steps_per_second": 20.831,
+      "step": 500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0003243978293677408,
+      "loss": 0.4902,
+      "step": 501
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.000323695746053251,
+      "loss": 0.63,
+      "step": 502
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00032299118543329666,
+      "loss": 0.4135,
+      "step": 503
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00032228416161840246,
+      "loss": 0.4497,
+      "step": 504
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0003215746887684244,
+      "loss": 0.3634,
+      "step": 505
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0003208627810922665,
+      "loss": 0.3359,
+      "step": 506
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0003201484528475958,
+      "loss": 0.5302,
+      "step": 507
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00031943171834055724,
+      "loss": 0.4115,
+      "step": 508
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00031871259192548695,
+      "loss": 0.5049,
+      "step": 509
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00031799108800462464,
+      "loss": 0.3291,
+      "step": 510
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.0003172672210278254,
+      "loss": 0.4867,
+      "step": 511
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00031654100549227026,
+      "loss": 0.5247,
+      "step": 512
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0003158124559421758,
+      "loss": 0.4055,
+      "step": 513
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00031508158696850276,
+      "loss": 0.4846,
+      "step": 514
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00031434841320866395,
+      "loss": 0.5182,
+      "step": 515
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00031361294934623114,
+      "loss": 0.5588,
+      "step": 516
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.000312875210110641,
+      "loss": 0.6245,
+      "step": 517
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0003121352102768998,
+      "loss": 0.332,
+      "step": 518
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0003113929646652879,
+      "loss": 0.4909,
+      "step": 519
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0003106484881410628,
+      "loss": 0.4541,
+      "step": 520
+    },
+    {
+      "epoch": 1.56,
+      "eval_loss": 0.516572892665863,
+      "eval_runtime": 39.1297,
+      "eval_samples_per_second": 41.631,
+      "eval_steps_per_second": 20.828,
+      "step": 520
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0003099017956141612,
+      "loss": 0.2962,
+      "step": 521
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0003091529020389009,
+      "loss": 0.4434,
+      "step": 522
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0003084018224136808,
+      "loss": 0.4728,
+      "step": 523
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0003076485717806808,
+      "loss": 0.3787,
+      "step": 524
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0003068931652255602,
+      "loss": 0.5694,
+      "step": 525
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00030613561787715636,
+      "loss": 0.4464,
+      "step": 526
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0003053759449071807,
+      "loss": 0.6158,
+      "step": 527
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0003046141615299155,
+      "loss": 0.8141,
+      "step": 528
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.0003038502830019092,
+      "loss": 0.6886,
+      "step": 529
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00030308432462167043,
+      "loss": 0.5019,
+      "step": 530
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00030231630172936205,
+      "loss": 0.4838,
+      "step": 531
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0003015462297064936,
+      "loss": 0.5484,
+      "step": 532
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00030077412397561343,
+      "loss": 0.5688,
+      "step": 533
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00030000000000000003,
+      "loss": 0.4014,
+      "step": 534
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002992238732833518,
+      "loss": 0.4936,
+      "step": 535
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00029844575936947696,
+      "loss": 0.3926,
+      "step": 536
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00029766567384198223,
+      "loss": 0.4229,
+      "step": 537
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00029688363232396056,
+      "loss": 0.3198,
+      "step": 538
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0002960996504776783,
+      "loss": 0.5628,
+      "step": 539
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.0002953137440042616,
+      "loss": 0.339,
+      "step": 540
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 0.5086627006530762,
+      "eval_runtime": 39.1178,
+      "eval_samples_per_second": 41.643,
+      "eval_steps_per_second": 20.834,
+      "step": 540
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00029452592864338194,
+      "loss": 0.5298,
+      "step": 541
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00029373622017294076,
+      "loss": 0.4892,
+      "step": 542
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0002929446344087537,
+      "loss": 0.3387,
+      "step": 543
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0002921511872042337,
+      "loss": 0.4144,
+      "step": 544
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00029135589445007356,
+      "loss": 0.3239,
+      "step": 545
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00029055877207392753,
+      "loss": 0.3875,
+      "step": 546
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00028975983604009246,
+      "loss": 0.3716,
+      "step": 547
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00028895910234918824,
+      "loss": 0.6995,
+      "step": 548
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00028815658703783715,
+      "loss": 0.524,
+      "step": 549
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00028735230617834255,
+      "loss": 0.5495,
+      "step": 550
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00028654627587836723,
+      "loss": 0.5321,
+      "step": 551
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00028573851228061084,
+      "loss": 0.6363,
+      "step": 552
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0002849290315624864,
+      "loss": 0.4375,
+      "step": 553
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00028411784993579635,
+      "loss": 0.4915,
+      "step": 554
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00028330498364640804,
+      "loss": 0.4506,
+      "step": 555
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0002824904489739281,
+      "loss": 0.3577,
+      "step": 556
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00028167426223137685,
+      "loss": 0.3603,
+      "step": 557
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.000280856439764861,
+      "loss": 0.4757,
+      "step": 558
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00028003699795324673,
+      "loss": 0.3465,
+      "step": 559
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.0002792159532078314,
+      "loss": 0.4609,
+      "step": 560
+    },
+    {
+      "epoch": 1.68,
+      "eval_loss": 0.5257359147071838,
+      "eval_runtime": 39.0772,
+      "eval_samples_per_second": 41.687,
+      "eval_steps_per_second": 20.856,
+      "step": 560
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00027839332197201506,
+      "loss": 0.5903,
+      "step": 561
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.000277569120720971,
+      "loss": 0.5743,
+      "step": 562
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002767433659613159,
+      "loss": 0.5751,
+      "step": 563
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002759160742307793,
+      "loss": 0.4579,
+      "step": 564
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.000275087262097872,
+      "loss": 0.3828,
+      "step": 565
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0002742569461615547,
+      "loss": 0.3544,
+      "step": 566
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00027342514305090553,
+      "loss": 0.4301,
+      "step": 567
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00027259186942478654,
+      "loss": 0.3553,
+      "step": 568
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0002717571419715107,
+      "loss": 0.4837,
+      "step": 569
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.0002709209774085071,
+      "loss": 0.4446,
+      "step": 570
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00027008339248198675,
+      "loss": 0.6023,
+      "step": 571
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00026924440396660656,
+      "loss": 0.4305,
+      "step": 572
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00026840402866513377,
+      "loss": 0.3237,
+      "step": 573
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.0002675622834081095,
+      "loss": 0.6138,
+      "step": 574
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.0002667191850535113,
+      "loss": 0.406,
+      "step": 575
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00026587475048641594,
+      "loss": 0.4759,
+      "step": 576
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.000265028996618661,
+      "loss": 0.595,
+      "step": 577
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002641819403885063,
+      "loss": 0.3512,
+      "step": 578
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00026333359876029453,
+      "loss": 0.4497,
+      "step": 579
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0002624839887241115,
+      "loss": 0.4768,
+      "step": 580
+    },
+    {
+      "epoch": 1.74,
+      "eval_loss": 0.4989789128303528,
+      "eval_runtime": 38.8281,
+      "eval_samples_per_second": 41.954,
+      "eval_steps_per_second": 20.99,
+      "step": 580
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00026163312729544615,
+      "loss": 0.3918,
+      "step": 581
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0002607810315148494,
+      "loss": 0.5133,
+      "step": 582
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00025992771844759316,
+      "loss": 0.5705,
+      "step": 583
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00025907320518332825,
+      "loss": 0.4736,
+      "step": 584
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00025821750883574257,
+      "loss": 0.3043,
+      "step": 585
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0002573606465422181,
+      "loss": 0.4725,
+      "step": 586
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0002565026354634874,
+      "loss": 0.522,
+      "step": 587
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.0002556434927832906,
+      "loss": 0.3749,
+      "step": 588
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00025478323570803053,
+      "loss": 0.482,
+      "step": 589
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0002539218814664288,
+      "loss": 0.6841,
+      "step": 590
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0002530594473091802,
+      "loss": 0.2958,
+      "step": 591
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00025219595050860746,
+      "loss": 0.5809,
+      "step": 592
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00025133140835831535,
+      "loss": 0.5042,
+      "step": 593
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00025046583817284434,
+      "loss": 0.6835,
+      "step": 594
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0002495992572873237,
+      "loss": 0.4265,
+      "step": 595
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0002487316830571244,
+      "loss": 0.427,
+      "step": 596
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0002478631328575116,
+      "loss": 0.2882,
+      "step": 597
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0002469936240832965,
+      "loss": 0.4629,
+      "step": 598
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00024612317414848806,
+      "loss": 0.6129,
+      "step": 599
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.0002452518004859445,
+      "loss": 0.5313,
+      "step": 600
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 0.4951966106891632,
+      "eval_runtime": 39.0975,
+      "eval_samples_per_second": 41.665,
+      "eval_steps_per_second": 20.845,
+      "step": 600
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00024437952054702354,
+      "loss": 0.5254,
+      "step": 601
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00024350635180123349,
+      "loss": 0.467,
+      "step": 602
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0002426323117358832,
+      "loss": 0.4913,
+      "step": 603
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00024175741785573176,
+      "loss": 0.4806,
+      "step": 604
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0002408816876826378,
+      "loss": 0.421,
+      "step": 605
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.0002400051387552089,
+      "loss": 0.5413,
+      "step": 606
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00023912778862845014,
+      "loss": 0.5817,
+      "step": 607
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00023824965487341247,
+      "loss": 0.4123,
+      "step": 608
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00023737075507684102,
+      "loss": 0.4143,
+      "step": 609
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00023649110684082256,
+      "loss": 0.5556,
+      "step": 610
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00023561072778243336,
+      "loss": 0.7397,
+      "step": 611
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00023472963553338613,
+      "loss": 0.2856,
+      "step": 612
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00023384784773967674,
+      "loss": 0.3371,
+      "step": 613
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00023296538206123133,
+      "loss": 0.5207,
+      "step": 614
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00023208225617155206,
+      "loss": 0.4478,
+      "step": 615
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00023119848775736358,
+      "loss": 0.4692,
+      "step": 616
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00023031409451825853,
+      "loss": 0.4573,
+      "step": 617
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00022942909416634325,
+      "loss": 0.4242,
+      "step": 618
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00022854350442588287,
+      "loss": 0.5599,
+      "step": 619
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00022765734303294664,
+      "loss": 0.347,
+      "step": 620
+    },
+    {
+      "epoch": 1.86,
+      "eval_loss": 0.4822976887226105,
+      "eval_runtime": 39.0799,
+      "eval_samples_per_second": 41.684,
+      "eval_steps_per_second": 20.855,
+      "step": 620
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00022677062773505236,
+      "loss": 0.4158,
+      "step": 621
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00022588337629081106,
+      "loss": 0.3382,
+      "step": 622
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002249956064695717,
+      "loss": 0.4924,
+      "step": 623
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002241073360510646,
+      "loss": 0.3995,
+      "step": 624
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00022321858282504605,
+      "loss": 0.4438,
+      "step": 625
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002223293645909416,
+      "loss": 0.3933,
+      "step": 626
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00022143969915748959,
+      "loss": 0.386,
+      "step": 627
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00022054960434238487,
+      "loss": 0.6419,
+      "step": 628
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00021965909797192143,
+      "loss": 0.3969,
+      "step": 629
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00021876819788063588,
+      "loss": 0.3944,
+      "step": 630
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00021787692191094986,
+      "loss": 0.4672,
+      "step": 631
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00021698528791281297,
+      "loss": 0.5495,
+      "step": 632
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00021609331374334523,
+      "loss": 0.49,
+      "step": 633
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00021520101726647922,
+      "loss": 0.4275,
+      "step": 634
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00021430841635260275,
+      "loss": 0.4274,
+      "step": 635
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.0002134155288782005,
+      "loss": 0.5855,
+      "step": 636
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0002125223727254964,
+      "loss": 0.5355,
+      "step": 637
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00021162896578209517,
+      "loss": 0.3813,
+      "step": 638
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0002107353259406243,
+      "loss": 0.4637,
+      "step": 639
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00020984147109837564,
+      "loss": 0.4216,
+      "step": 640
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.48321226239204407,
+      "eval_runtime": 38.9518,
+      "eval_samples_per_second": 41.821,
+      "eval_steps_per_second": 20.923,
+      "step": 640
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00020894741915694685,
+      "loss": 0.3868,
+      "step": 641
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00020805318802188304,
+      "loss": 0.4371,
+      "step": 642
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00020715879560231811,
+      "loss": 0.3519,
+      "step": 643
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00020626425981061606,
+      "loss": 0.4148,
+      "step": 644
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00020536959856201227,
+      "loss": 0.3349,
+      "step": 645
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00020447482977425466,
+      "loss": 0.3314,
+      "step": 646
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00020357997136724487,
+      "loss": 0.5866,
+      "step": 647
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.0002026850412626795,
+      "loss": 0.4521,
+      "step": 648
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00020179005738369096,
+      "loss": 0.4659,
+      "step": 649
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0002008950376544887,
+      "loss": 0.5333,
+      "step": 650
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0002,
+      "loss": 0.4153,
+      "step": 651
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00019910496234551133,
+      "loss": 0.4381,
+      "step": 652
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.0001982099426163091,
+      "loss": 0.3161,
+      "step": 653
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00019731495873732055,
+      "loss": 0.444,
+      "step": 654
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00019642002863275518,
+      "loss": 0.3875,
+      "step": 655
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00019552517022574541,
+      "loss": 0.3661,
+      "step": 656
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0001946304014379878,
+      "loss": 0.376,
+      "step": 657
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.000193735740189384,
+      "loss": 0.4913,
+      "step": 658
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0001928412043976819,
+      "loss": 0.5028,
+      "step": 659
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00019194681197811704,
+      "loss": 0.3905,
+      "step": 660
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 0.47484511137008667,
+      "eval_runtime": 39.0824,
+      "eval_samples_per_second": 41.681,
+      "eval_steps_per_second": 20.853,
+      "step": 660
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.0001910525808430532,
+      "loss": 0.4522,
+      "step": 661
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00019015852890162438,
+      "loss": 0.303,
+      "step": 662
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00018926467405937567,
+      "loss": 0.3451,
+      "step": 663
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00018837103421790485,
+      "loss": 0.4639,
+      "step": 664
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00018747762727450363,
+      "loss": 0.5916,
+      "step": 665
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0001865844711217995,
+      "loss": 0.5945,
+      "step": 666
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00018569158364739735,
+      "loss": 0.4625,
+      "step": 667
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00018479898273352082,
+      "loss": 0.3358,
+      "step": 668
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1002,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.8897791269868667e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-668/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27098634af21778b649dbcd66e907b3281d3f7c9df308b74b9b43e87b72e667c
+size 4475

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "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
+}