Upload folder using huggingface_hub

llama2_7b_nf4_adapter/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

llama2_7b_nf4_adapter/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

llama2_7b_nf4_adapter/adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj,",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_nf4_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab6627df4954f17c448066d84ab30078460054ba11e760f67914af34568dbd1
+size 8397056

llama2_7b_nf4_adapter/all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.8390089311812183,
+    "train_runtime": 5852.5175,
+    "train_samples_per_second": 8.844,
+    "train_steps_per_second": 0.069
+}

llama2_7b_nf4_adapter/bnb_config.json

@@ -0,0 +1,6 @@
+{
+    "load_in_4bit": true,
+    "bnb_4bit_quant_type" : "nf4",
+    "bnb_4bit_use_double_quant" : false,
+    "bnb_4bit_compute_dtype" : "bfloat16"
+}

llama2_7b_nf4_adapter/checkpoint-350/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

llama2_7b_nf4_adapter/checkpoint-350/adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj,",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_nf4_adapter/checkpoint-350/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e160fea8712de475401080c4e3339ba361d08ddcd41d120fe4a80ed82de299d2
+size 8397056

llama2_7b_nf4_adapter/checkpoint-350/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1afa3f09b1bb3aeaec85038a47a133b4c0c5b5fffb2a17467ace531a760bcb19
+size 16831290

llama2_7b_nf4_adapter/checkpoint-350/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe0cf24ad3a1caf290143988dca3ea1f517a4391bcfa4a82de127fa8ebe5264
+size 14244

llama2_7b_nf4_adapter/checkpoint-350/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb8667a83950be0c98f02598cd77edba87c3860dfb23232169d020ae72feaa8
+size 1064

llama2_7b_nf4_adapter/checkpoint-350/trainer_state.json

@@ -0,0 +1,2121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.865533230293663,
+  "eval_steps": 500,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.7194,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.5944,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6244,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6388,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.4784,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.4072,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.3096,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.266,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1784,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.0751,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0596,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.004,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 0.9479,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 0.9473,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9147,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9056,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.8848,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.8982,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9278,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9191,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8514,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8358,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8404,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9196,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8522,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8501,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8363,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8594,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8857,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8596,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8931,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8385,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8512,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.846,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8606,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8779,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8537,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8517,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8258,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8664,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8347,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8508,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8779,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8202,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8302,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8339,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8518,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8445,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.887,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8198,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8141,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8372,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8319,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8405,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8324,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8396,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8472,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8338,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8421,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8881,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8112,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8495,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8486,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.7843,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.841,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8398,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8436,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.834,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8375,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8396,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8245,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.82,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.7925,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8348,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8134,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8477,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.826,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.8436,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.84,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.8416,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8166,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8366,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8597,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8247,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8125,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8287,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.832,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8082,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8562,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.837,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8457,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.7864,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8111,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8356,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8156,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.843,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8349,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8443,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8051,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8192,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8336,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.845,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.827,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.7963,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.7696,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8263,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.7804,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8163,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8346,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.828,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8252,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8365,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8129,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8458,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8475,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8142,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8152,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8122,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8071,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.878,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8578,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.7773,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.7965,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8366,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8205,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.7888,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8595,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.821,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8261,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8285,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8449,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.7975,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.7891,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8208,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8465,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8015,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8525,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.7932,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8023,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8352,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8121,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8434,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8156,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8254,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.7854,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.802,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8204,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.7987,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8176,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8679,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.799,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8012,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.7898,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.824,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8477,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8505,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8363,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8065,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.838,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.7906,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8393,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8206,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8448,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8449,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.822,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.7787,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.812,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8494,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8505,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8343,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8238,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8454,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8437,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.7944,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.83,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8394,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8426,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8295,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8121,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8391,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.7788,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8173,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.7804,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.812,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.7989,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8408,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8496,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8191,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8571,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.815,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8047,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8127,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.7772,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.829,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8182,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8145,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8294,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8044,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.816,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.788,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8063,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8532,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8241,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.861,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8099,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8192,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8102,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8231,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.7988,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.838,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8132,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8339,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8266,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8144,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8139,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.7863,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8063,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8283,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8453,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8282,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8608,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8043,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8095,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8169,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8049,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8243,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8215,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8411,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8136,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.807,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.7606,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8247,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8286,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8277,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8224,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8157,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8284,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.7926,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8017,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8248,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.7779,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.7972,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8653,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8111,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.831,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.77,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8038,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.7753,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8059,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8224,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8524,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.7774,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.7878,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.7764,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8188,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8137,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.815,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.7844,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8242,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8046,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8069,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8134,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8016,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.7842,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8066,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8028,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8118,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8321,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.7843,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8025,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.7579,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.7955,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8085,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.7992,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.818,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.7916,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8237,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.793,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8212,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.7994,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.789,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.7982,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.7997,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8273,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8089,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8359,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8362,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8242,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8131,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.7697,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8059,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8258,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8057,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8145,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8476,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8004,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.7657,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.7745,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8294,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8412,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8061,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8107,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8066,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8207,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.7907,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7953,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7889,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8413,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8182,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.7869,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.7813,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8131,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8071,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8316,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.7976,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8128,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8219,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8285,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8109,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8323,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8103,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8112,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8043,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8018,
+      "step": 350
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 3.9310521413861376e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_nf4_adapter/checkpoint-350/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5926f4cc28daa5ba612d1695e20d14df0585c893f74e44c74c43c7bab82e94b4
+size 5048

llama2_7b_nf4_adapter/checkpoint-375/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

llama2_7b_nf4_adapter/checkpoint-375/adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj,",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_nf4_adapter/checkpoint-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e8062ca054073ac8f89563309b9c9a79fd57967bd3ccec3dcb6b6444e80c49
+size 8397056

llama2_7b_nf4_adapter/checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fd5e97c59084f3dde50ee4eb3a13a0be37bf67a55652fb0de42acf2df2ad90
+size 16831290

llama2_7b_nf4_adapter/checkpoint-375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddd9ff13c3dea6565a0137274d71da460e0429b39d8bd3d10936a3957b362c5
+size 14244

llama2_7b_nf4_adapter/checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14cea28c471a1fa6c9ff7b3f2af69adfdf6d7188fce36d402b7c4283553cbae4
+size 1064

llama2_7b_nf4_adapter/checkpoint-375/trainer_state.json

@@ -0,0 +1,2271 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9273570324574961,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.7194,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.5944,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6244,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6388,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.4784,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.4072,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.3096,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.266,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1784,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.0751,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0596,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.004,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 0.9479,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 0.9473,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9147,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9056,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.8848,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.8982,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9278,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9191,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8514,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8358,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8404,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9196,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8522,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8501,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8363,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8594,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8857,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8596,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8931,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8385,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8512,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.846,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8606,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8779,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8537,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8517,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8258,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8664,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8347,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8508,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8779,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8202,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8302,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8339,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8518,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8445,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.887,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8198,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8141,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8372,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8319,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8405,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8324,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8396,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8472,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8338,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8421,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8881,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8112,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8495,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8486,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.7843,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.841,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8398,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8436,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.834,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8375,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8396,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8245,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.82,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.7925,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8348,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8134,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8477,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.826,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.8436,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.84,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.8416,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8166,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8366,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8597,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8247,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8125,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8287,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.832,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8082,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8562,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.837,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8457,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.7864,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8111,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8356,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8156,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.843,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8349,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8443,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8051,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8192,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8336,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.845,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.827,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.7963,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.7696,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8263,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.7804,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8163,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8346,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.828,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8252,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8365,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8129,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8458,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8475,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8142,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8152,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8122,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8071,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.878,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8578,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.7773,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.7965,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8366,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8205,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.7888,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8595,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.821,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8261,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8285,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8449,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.7975,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.7891,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8208,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8465,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8015,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8525,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.7932,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8023,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8352,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8121,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8434,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8156,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8254,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.7854,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.802,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8204,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.7987,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8176,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8679,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.799,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8012,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.7898,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.824,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8477,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8505,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8363,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8065,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.838,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.7906,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8393,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8206,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8448,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8449,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.822,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.7787,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.812,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8494,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8505,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8343,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8238,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8454,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8437,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.7944,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.83,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8394,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8426,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8295,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8121,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8391,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.7788,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8173,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.7804,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.812,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.7989,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8408,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8496,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8191,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8571,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.815,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8047,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8127,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.7772,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.829,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8182,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8145,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8294,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8044,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.816,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.788,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8063,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8532,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8241,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.861,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8099,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8192,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8102,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8231,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.7988,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.838,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8132,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8339,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8266,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8144,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8139,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.7863,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8063,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8283,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8453,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8282,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8608,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8043,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8095,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8169,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8049,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8243,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8215,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8411,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8136,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.807,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.7606,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8247,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8286,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8277,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8224,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8157,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8284,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.7926,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8017,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8248,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.7779,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.7972,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8653,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8111,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.831,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.77,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8038,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.7753,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8059,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8224,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8524,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.7774,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.7878,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.7764,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8188,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8137,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.815,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.7844,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8242,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8046,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8069,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8134,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8016,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.7842,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8066,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8028,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8118,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8321,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.7843,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8025,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.7579,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.7955,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8085,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.7992,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.818,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.7916,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8237,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.793,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8212,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.7994,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.789,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.7982,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.7997,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8273,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8089,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8359,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8362,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8242,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8131,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.7697,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8059,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8258,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8057,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8145,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8476,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8004,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.7657,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.7745,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8294,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8412,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8061,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8107,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8066,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8207,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.7907,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7953,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7889,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8413,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8182,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.7869,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.7813,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8131,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8071,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8316,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.7976,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8128,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8219,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8285,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8109,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8323,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8103,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8112,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8043,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8018,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8015,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.7845,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8079,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8144,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8235,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8158,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8549,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.7984,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.789,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.7867,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8552,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.801,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.7742,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.7987,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.808,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8054,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8257,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8442,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8152,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.81,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.7818,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.796,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8045,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 375
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.214459938342994e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_nf4_adapter/checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5926f4cc28daa5ba612d1695e20d14df0585c893f74e44c74c43c7bab82e94b4
+size 5048

llama2_7b_nf4_adapter/checkpoint-400/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: meta-llama/Llama-2-7b-hf
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

llama2_7b_nf4_adapter/checkpoint-400/adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj,",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_nf4_adapter/checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:147ed4449ee477aa679b1e1cabf2b376259efc2e29910a8d727ab3be36d1f935
+size 8397056

llama2_7b_nf4_adapter/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f04fa6490910c19354643ec870abd3f59858d517f9e050e0741a1a005212a818
+size 16831290

llama2_7b_nf4_adapter/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98be3d82fe49b6295cbeedc17583d68b8fad84637b79fad00b4dd90873db94be
+size 14244

llama2_7b_nf4_adapter/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b97723dff35b080a119aa0ed1d20263fbea0a5b26831bf27653458b28c680d1
+size 1064

llama2_7b_nf4_adapter/checkpoint-400/trainer_state.json

@@ -0,0 +1,2421 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9891808346213292,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.7194,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.5944,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6244,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6388,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.4784,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.4072,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.3096,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.266,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1784,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.0751,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0596,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.004,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 0.9479,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 0.9473,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9147,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9056,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.8848,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.8982,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9278,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9191,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8514,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8358,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8404,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9196,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8522,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8501,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8363,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8594,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8857,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8596,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8931,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8385,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8512,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.846,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8606,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8779,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8537,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8517,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8258,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8664,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8347,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8508,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8779,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8202,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8302,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8339,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8518,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8445,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.887,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8198,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8141,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8372,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8319,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8405,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8324,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8396,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8472,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8338,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8421,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8881,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8112,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8495,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8486,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.7843,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.841,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8398,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8436,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.834,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8375,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8396,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8245,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.82,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.7925,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8348,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8134,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8477,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.826,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.8436,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.84,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.8416,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8166,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8366,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8597,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8247,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8125,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8287,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.832,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8082,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8562,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.837,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8457,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.7864,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8111,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8356,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8156,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.843,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8349,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8443,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8051,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8192,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8336,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.845,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.827,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.7963,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.7696,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8263,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.7804,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8163,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8346,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.828,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8252,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8365,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8129,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8458,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8475,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8142,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8152,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8122,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8071,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.878,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8578,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.7773,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.7965,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8366,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8205,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.7888,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8595,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.821,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8261,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8285,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8449,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.7975,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.7891,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8208,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8465,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8015,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8525,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.7932,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8023,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8352,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8121,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8434,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8156,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8254,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.7854,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.802,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8204,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.7987,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8176,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8679,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.799,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8012,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.7898,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.824,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8477,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8505,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8363,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8065,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.838,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.7906,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8393,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8206,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8448,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8449,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.822,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.7787,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.812,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8494,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8505,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8343,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8238,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8454,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8437,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.7944,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.83,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8394,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8426,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8295,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8121,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8391,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.7788,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8173,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.7804,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.812,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.7989,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8408,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8496,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8191,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8571,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.815,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8047,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8127,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.7772,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.829,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8182,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8145,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8294,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8044,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.816,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.788,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8063,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8532,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8241,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.861,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8099,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8192,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8102,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8231,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.7988,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.838,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8132,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8339,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8266,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8144,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8139,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.7863,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8063,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8283,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8453,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8282,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8608,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8043,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8095,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8169,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8049,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8243,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8215,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8411,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8136,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.807,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.7606,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8247,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8286,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8277,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8224,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8157,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8284,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.7926,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8017,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8248,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.7779,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.7972,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8653,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8111,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.831,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.77,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8038,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.7753,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8059,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8224,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8524,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.7774,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.7878,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.7764,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8188,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8137,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.815,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.7844,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8242,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8046,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8069,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8134,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8016,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.7842,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8066,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8028,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8118,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8321,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.7843,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8025,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.7579,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.7955,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8085,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.7992,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.818,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.7916,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8237,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.793,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8212,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.7994,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.789,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.7982,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.7997,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8273,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8089,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8359,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8362,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8242,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8131,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.7697,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8059,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8258,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8057,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8145,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8476,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8004,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.7657,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.7745,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8294,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8412,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8061,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8107,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8066,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8207,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.7907,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7953,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7889,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8413,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8182,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.7869,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.7813,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8131,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8071,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8316,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.7976,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8128,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8219,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8285,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8109,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8323,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8103,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8112,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8043,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8018,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8015,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.7845,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8079,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8144,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8235,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8158,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8549,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.7984,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.789,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.7867,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8552,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.801,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.7742,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.7987,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.808,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8054,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8257,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8442,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8152,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.81,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.7818,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.796,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8045,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 375
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8019,
+      "step": 376
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8451,
+      "step": 377
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.7786,
+      "step": 378
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.8,
+      "step": 379
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.8199,
+      "step": 380
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 381
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.8214,
+      "step": 382
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.8171,
+      "step": 383
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.8143,
+      "step": 384
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.806,
+      "step": 385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.8186,
+      "step": 386
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.7835,
+      "step": 387
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.7702,
+      "step": 388
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.7869,
+      "step": 389
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8483,
+      "step": 390
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.8024,
+      "step": 391
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.8305,
+      "step": 392
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.7952,
+      "step": 393
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.8193,
+      "step": 394
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.7855,
+      "step": 395
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.8163,
+      "step": 396
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.8198,
+      "step": 397
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.813,
+      "step": 398
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 399
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.7892,
+      "step": 400
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.495223430237389e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_nf4_adapter/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5926f4cc28daa5ba612d1695e20d14df0585c893f74e44c74c43c7bab82e94b4
+size 5048

llama2_7b_nf4_adapter/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.8390089311812183,
+    "train_runtime": 5852.5175,
+    "train_samples_per_second": 8.844,
+    "train_steps_per_second": 0.069
+}

llama2_7b_nf4_adapter/trainer_state.json

@@ -0,0 +1,2454 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9990726429675425,
+  "eval_steps": 500,
+  "global_step": 404,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.7194,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.5944,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6244,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6388,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.4784,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.4072,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.3096,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.266,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1784,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.0751,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0596,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.004,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 0.9479,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 0.9473,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9147,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9056,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.8848,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.8982,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9278,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9191,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8514,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8358,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.8404,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9196,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8522,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8501,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.8363,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8594,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8857,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8596,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.8931,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8385,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.8512,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.846,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8606,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8779,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.8537,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8517,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8258,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.8664,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8347,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8508,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.8779,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8202,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8302,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.8339,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8518,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8445,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.887,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.8198,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8141,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8372,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8319,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.8405,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8324,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8396,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8472,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.8338,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8421,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8881,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8112,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.8495,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8486,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.7843,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.841,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8398,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8436,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.834,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8375,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.8396,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8245,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.82,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.7925,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8348,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8134,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.8477,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.826,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.8436,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.84,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.8416,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8166,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8366,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8597,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8247,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8125,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8287,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.832,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8082,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.8562,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.837,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8457,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.7864,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8111,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8356,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8156,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.843,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.8349,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8443,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8051,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8192,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.8336,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.845,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.827,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.7963,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.7696,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8263,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.7804,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8163,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8346,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.828,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8252,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.8365,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8129,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8458,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8475,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8142,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8152,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8122,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8071,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.878,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8578,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.7773,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.7965,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8366,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8205,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.7888,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8595,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.821,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8261,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8285,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8449,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.7975,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.7891,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8208,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8465,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8015,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8525,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.7932,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8023,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8352,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8121,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8434,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8156,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8254,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.7854,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.802,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8204,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.7987,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8176,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8679,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.799,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8012,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.7898,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.824,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8477,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8505,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8363,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.8065,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.838,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.7906,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8393,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8206,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8448,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8449,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.822,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.7787,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.812,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8494,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8505,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8343,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.8238,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8454,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8437,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.7944,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.83,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8394,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8426,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8295,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.8121,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8391,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.7788,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8173,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.7804,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.812,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.7989,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8408,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8496,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8191,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.8571,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.815,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8047,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8127,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.7772,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.829,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8182,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8145,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8294,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8044,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.816,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.788,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8063,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8532,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8241,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.861,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8099,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8192,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8102,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8231,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.7988,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.838,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8132,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8339,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.8266,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8144,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8139,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.7863,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8063,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8283,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8453,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8282,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.8608,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8043,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8095,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8169,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8049,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8243,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8215,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8411,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.8136,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.807,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.7606,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8247,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8286,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8277,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8224,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8157,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.8284,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.7926,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8017,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8248,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.7779,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.7972,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8653,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8111,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.831,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.77,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8038,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.7753,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8059,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8224,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8524,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.7774,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.7878,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.7764,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8188,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8137,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.815,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.7844,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8242,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8371,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8046,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8069,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8134,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8016,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.7842,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8066,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8028,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8118,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8321,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.7843,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8025,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.7579,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.7955,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8085,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.7992,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.818,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.7916,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8237,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.793,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8212,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.7994,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.789,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8274,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.7982,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.7997,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8273,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8089,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8359,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8362,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8242,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8131,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.7697,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8059,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8258,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8057,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8145,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8476,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8004,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.7657,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.7745,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8246,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8294,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8412,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8061,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8107,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8066,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8207,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.7907,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7953,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7889,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8413,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8182,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.7869,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8262,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.7813,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8131,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8071,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8316,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.7976,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8128,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8219,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8285,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8109,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8323,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8103,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8112,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8043,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8018,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8015,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.7845,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8079,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8144,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8235,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8158,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.8549,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.7984,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.789,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.7867,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8552,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.801,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.7742,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.7987,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.808,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8054,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8257,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8442,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8152,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.81,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.7818,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.796,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8045,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.7957,
+      "step": 375
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8019,
+      "step": 376
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8451,
+      "step": 377
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.7786,
+      "step": 378
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.8,
+      "step": 379
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.8199,
+      "step": 380
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.8189,
+      "step": 381
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.8214,
+      "step": 382
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.8171,
+      "step": 383
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.8143,
+      "step": 384
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.806,
+      "step": 385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.8186,
+      "step": 386
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.7835,
+      "step": 387
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.7702,
+      "step": 388
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.7869,
+      "step": 389
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8483,
+      "step": 390
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.8024,
+      "step": 391
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.8305,
+      "step": 392
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.7952,
+      "step": 393
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.8193,
+      "step": 394
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.7855,
+      "step": 395
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.8163,
+      "step": 396
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.8198,
+      "step": 397
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.813,
+      "step": 398
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 399
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.7892,
+      "step": 400
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.8018,
+      "step": 401
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.7949,
+      "step": 402
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003,
+      "loss": 0.8175,
+      "step": 403
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003,
+      "loss": 0.801,
+      "step": 404
+    },
+    {
+      "epoch": 1.0,
+      "step": 404,
+      "total_flos": 4.5406536857338675e+17,
+      "train_loss": 0.8390089311812183,
+      "train_runtime": 5852.5175,
+      "train_samples_per_second": 8.844,
+      "train_steps_per_second": 0.069
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.5406536857338675e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_nf4_adapter/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5926f4cc28daa5ba612d1695e20d14df0585c893f74e44c74c43c7bab82e94b4
+size 5048