Upload folder using huggingface_hub

llama2_7b_r16_alpha16/.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_r16_alpha16/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_r16_alpha16/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj,",
+    "v_proj,",
+    "k_proj",
+    "gate_proj,",
+    "q_proj,",
+    "down_proj,",
+    "up_proj,"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_r16_alpha16/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8240979c21e4bf8cd48f61cbcd395e2a7e9e618fe1abc9515b9fdc19718c5f3
+size 16785792

llama2_7b_r16_alpha16/all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9688728674508558,
+    "train_runtime": 27658.059,
+    "train_samples_per_second": 1.871,
+    "train_steps_per_second": 0.015
+}

llama2_7b_r16_alpha16/bnb_config.json

@@ -0,0 +1,12 @@
+{
+  "bnb_4bit_compute_dtype": "bfloat16",
+  "bnb_4bit_quant_type": "fp4",
+  "bnb_4bit_use_double_quant": false,
+  "llm_int8_enable_fp32_cpu_offload": false,
+  "llm_int8_has_fp16_weight": false,
+  "llm_int8_skip_modules": null,
+  "llm_int8_threshold": 6.0,
+  "load_in_4bit": true,
+  "load_in_8bit": false,
+  "quant_method": "bitsandbytes"
+}

llama2_7b_r16_alpha16/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_r16_alpha16/checkpoint-350/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj,",
+    "v_proj,",
+    "k_proj",
+    "gate_proj,",
+    "q_proj,",
+    "down_proj,",
+    "up_proj,"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_r16_alpha16/checkpoint-350/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591361e7623f3d2d1811fef271054cf22a26dd64912e4874c6d0e7cf59b6253c
+size 16785792

llama2_7b_r16_alpha16/checkpoint-350/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb3f246fcdd27b071913101bc6e44fcf5284923c7acc3bf2612a9eb739f09f8
+size 33608762

llama2_7b_r16_alpha16/checkpoint-350/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb51010fb74fdd1d16f39ac27627e738237e2898de444269e7f141f1f4f9f89f
+size 14244

llama2_7b_r16_alpha16/checkpoint-350/scheduler.pt

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

llama2_7b_r16_alpha16/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": 1.8146,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.7128,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7934,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.8663,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7405,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7479,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.7056,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.7681,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.767,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.6407,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.6092,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.5077,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.4746,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.4743,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.4388,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.3198,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.2482,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.3124,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.3294,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.3068,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.2152,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.2475,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.2338,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.1761,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.1325,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.109,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.179,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.1049,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.1057,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.0743,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.0916,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.1079,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.0831,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.1066,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0571,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0616,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0372,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0247,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0285,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0031,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0416,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0013,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 1.0033,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9867,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9778,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 1.0149,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9756,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9752,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9662,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9988,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9385,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.955,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9509,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9478,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9628,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9629,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 1.0102,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9445,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9574,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9524,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9556,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9435,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9527,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9615,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9425,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9624,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 1.0114,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9294,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9667,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9618,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8984,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9577,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9536,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9596,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9491,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9574,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9554,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9381,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.941,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9558,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9472,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9395,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9549,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9612,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9505,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9498,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9245,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9742,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9365,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9345,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9397,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9501,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.928,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9696,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9519,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9555,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9206,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9483,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9389,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9579,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9526,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.958,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9212,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9269,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.956,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9657,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9381,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9142,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.8811,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9375,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8994,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9411,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9318,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.957,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9323,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9252,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9562,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9229,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9489,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9549,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9232,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9296,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9185,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9892,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9659,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9093,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9408,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9339,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9115,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9675,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9347,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.941,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9431,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.955,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9084,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9311,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9614,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9109,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9683,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9062,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9106,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9469,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9259,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9642,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9216,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.927,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8858,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.934,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9101,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9306,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9782,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9105,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9044,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9323,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9618,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9525,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9502,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9243,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9448,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9416,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9387,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9226,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9329,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9547,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9515,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.92,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9357,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.882,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9177,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9455,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9667,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9641,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9359,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9517,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9543,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9318,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.946,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.951,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9352,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9236,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.948,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8868,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9284,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8917,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9202,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9048,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9258,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9596,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9235,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9581,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.9181,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8831,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.937,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9103,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9816,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9307,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.9206,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.918,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8884,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.9095,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9505,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9259,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9678,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9132,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9296,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9286,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9103,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9214,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9413,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9211,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8922,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9088,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9422,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.975,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.907,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.923,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9297,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9491,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9221,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8605,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.928,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9319,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9185,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9187,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9353,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8942,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8801,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9044,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9646,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9156,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9405,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8802,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.9094,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8809,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.9083,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9282,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9579,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8925,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9295,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9242,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9169,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8876,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9315,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9429,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9089,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9069,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.92,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9081,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8913,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9158,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9156,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9404,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8985,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.91,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8605,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8989,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.9105,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8932,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9199,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8941,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9279,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9311,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9065,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8938,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9004,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9063,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9314,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9092,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9339,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9335,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9138,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8845,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9171,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9293,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9179,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9524,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8732,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8759,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9305,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9481,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9024,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9224,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.913,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9028,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8984,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9518,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8977,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9246,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9282,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9223,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9125,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9234,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8995,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9163,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9181,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9337,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9207,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9107,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 350
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 3.932299450220544e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_r16_alpha16/checkpoint-350/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252716072e0a3f494e120fae24b2024dc12c506ed8cc5125efbbc631cc03c647
+size 5112

llama2_7b_r16_alpha16/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_r16_alpha16/checkpoint-375/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj,",
+    "v_proj,",
+    "k_proj",
+    "gate_proj,",
+    "q_proj,",
+    "down_proj,",
+    "up_proj,"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_r16_alpha16/checkpoint-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f41fbcfe6ede1e9811a171113a27b22462be9f08c12e728a028535395e0366
+size 16785792

llama2_7b_r16_alpha16/checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f3bbfae7c2f8c4611040c7029557d2269ff37c12ad373d61f21ad02900070b
+size 33608762

llama2_7b_r16_alpha16/checkpoint-375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb285dff5f857d12597dee3e082b3988cdffb9cdeb22829e31cbbbce637d605
+size 14244

llama2_7b_r16_alpha16/checkpoint-375/scheduler.pt

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

llama2_7b_r16_alpha16/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": 1.8146,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.7128,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7934,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.8663,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7405,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7479,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.7056,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.7681,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.767,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.6407,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.6092,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.5077,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.4746,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.4743,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.4388,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.3198,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.2482,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.3124,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.3294,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.3068,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.2152,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.2475,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.2338,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.1761,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.1325,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.109,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.179,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.1049,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.1057,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.0743,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.0916,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.1079,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.0831,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.1066,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0571,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0616,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0372,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0247,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0285,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0031,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0416,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0013,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 1.0033,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9867,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9778,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 1.0149,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9756,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9752,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9662,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9988,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9385,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.955,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9509,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9478,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9628,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9629,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 1.0102,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9445,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9574,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9524,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9556,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9435,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9527,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9615,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9425,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9624,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 1.0114,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9294,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9667,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9618,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8984,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9577,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9536,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9596,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9491,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9574,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9554,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9381,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.941,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9558,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9472,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9395,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9549,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9612,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9505,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9498,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9245,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9742,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9365,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9345,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9397,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9501,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.928,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9696,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9519,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9555,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9206,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9483,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9389,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9579,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9526,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.958,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9212,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9269,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.956,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9657,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9381,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9142,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.8811,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9375,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8994,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9411,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9318,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.957,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9323,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9252,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9562,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9229,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9489,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9549,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9232,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9296,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9185,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9892,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9659,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9093,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9408,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9339,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9115,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9675,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9347,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.941,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9431,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.955,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9084,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9311,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9614,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9109,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9683,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9062,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9106,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9469,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9259,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9642,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9216,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.927,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8858,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.934,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9101,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9306,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9782,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9105,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9044,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9323,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9618,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9525,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9502,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9243,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9448,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9416,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9387,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9226,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9329,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9547,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9515,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.92,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9357,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.882,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9177,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9455,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9667,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9641,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9359,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9517,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9543,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9318,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.946,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.951,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9352,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9236,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.948,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8868,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9284,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8917,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9202,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9048,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9258,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9596,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9235,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9581,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.9181,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8831,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.937,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9103,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9816,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9307,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.9206,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.918,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8884,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.9095,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9505,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9259,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9678,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9132,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9296,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9286,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9103,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9214,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9413,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9211,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8922,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9088,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9422,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.975,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.907,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.923,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9297,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9491,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9221,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8605,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.928,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9319,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9185,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9187,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9353,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8942,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8801,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9044,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9646,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9156,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9405,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8802,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.9094,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8809,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.9083,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9282,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9579,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8925,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9295,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9242,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9169,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8876,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9315,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9429,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9089,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9069,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.92,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9081,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8913,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9158,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9156,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9404,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8985,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.91,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8605,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8989,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.9105,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8932,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9199,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8941,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9279,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9311,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9065,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8938,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9004,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9063,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9314,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9092,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9339,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9335,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9138,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8845,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9171,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9293,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9179,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9524,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8732,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8759,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9305,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9481,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9024,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9224,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.913,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9028,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8984,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9518,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8977,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9246,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9282,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9223,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9125,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9234,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8995,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9163,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9181,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9337,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9207,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9107,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.908,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8957,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.9082,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9194,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9175,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9607,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8893,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9603,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9067,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8835,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9089,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9314,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.9115,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8805,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8968,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.9084,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 375
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.215797171461325e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_r16_alpha16/checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252716072e0a3f494e120fae24b2024dc12c506ed8cc5125efbbc631cc03c647
+size 5112

llama2_7b_r16_alpha16/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_r16_alpha16/checkpoint-400/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj,",
+    "v_proj,",
+    "k_proj",
+    "gate_proj,",
+    "q_proj,",
+    "down_proj,",
+    "up_proj,"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_r16_alpha16/checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ec27c159a808cea7d20e8b2d07e8058b81e9f5321497c0a8406bb5c574675d
+size 16785792

llama2_7b_r16_alpha16/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89cadfe949869873afe28c5c32c6bdf78b66db021e3857c8857af10d632f5b2d
+size 33608762

llama2_7b_r16_alpha16/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e190938d4a2bf1b2984cff6f7344325da248688b9146ea1ce90340c7a96409cf
+size 14244

llama2_7b_r16_alpha16/checkpoint-400/scheduler.pt

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

llama2_7b_r16_alpha16/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": 1.8146,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.7128,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7934,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.8663,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7405,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7479,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.7056,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.7681,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.767,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.6407,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.6092,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.5077,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.4746,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.4743,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.4388,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.3198,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.2482,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.3124,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.3294,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.3068,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.2152,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.2475,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.2338,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.1761,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.1325,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.109,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.179,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.1049,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.1057,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.0743,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.0916,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.1079,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.0831,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.1066,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0571,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0616,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0372,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0247,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0285,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0031,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0416,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0013,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 1.0033,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9867,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9778,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 1.0149,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9756,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9752,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9662,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9988,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9385,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.955,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9509,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9478,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9628,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9629,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 1.0102,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9445,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9574,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9524,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9556,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9435,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9527,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9615,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9425,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9624,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 1.0114,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9294,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9667,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9618,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8984,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9577,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9536,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9596,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9491,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9574,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9554,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9381,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.941,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9558,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9472,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9395,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9549,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9612,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9505,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9498,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9245,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9742,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9365,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9345,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9397,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9501,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.928,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9696,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9519,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9555,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9206,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9483,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9389,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9579,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9526,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.958,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9212,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9269,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.956,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9657,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9381,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9142,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.8811,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9375,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8994,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9411,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9318,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.957,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9323,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9252,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9562,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9229,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9489,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9549,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9232,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9296,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9185,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9892,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9659,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9093,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9408,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9339,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9115,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9675,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9347,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.941,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9431,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.955,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9084,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9311,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9614,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9109,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9683,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9062,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9106,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9469,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9259,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9642,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9216,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.927,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8858,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.934,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9101,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9306,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9782,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9105,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9044,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9323,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9618,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9525,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9502,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9243,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9448,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9416,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9387,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9226,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9329,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9547,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9515,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.92,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9357,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.882,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9177,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9455,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9667,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9641,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9359,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9517,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9543,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9318,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.946,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.951,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9352,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9236,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.948,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8868,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9284,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8917,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9202,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9048,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9258,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9596,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9235,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9581,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.9181,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8831,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.937,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9103,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9816,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9307,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.9206,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.918,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8884,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.9095,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9505,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9259,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9678,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9132,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9296,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9286,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9103,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9214,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9413,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9211,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8922,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9088,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9422,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.975,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.907,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.923,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9297,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9491,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9221,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8605,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.928,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9319,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9185,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9187,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9353,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8942,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8801,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9044,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9646,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9156,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9405,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8802,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.9094,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8809,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.9083,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9282,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9579,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8925,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9295,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9242,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9169,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8876,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9315,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9429,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9089,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9069,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.92,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9081,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8913,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9158,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9156,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9404,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8985,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.91,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8605,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8989,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.9105,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8932,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9199,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8941,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9279,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9311,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9065,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8938,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9004,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9063,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9314,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9092,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9339,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9335,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9138,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8845,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9171,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9293,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9179,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9524,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8732,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8759,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9305,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9481,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9024,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9224,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.913,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9028,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8984,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9518,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8977,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9246,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9282,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9223,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9125,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9234,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8995,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9163,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9181,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9337,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9207,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9107,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.908,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8957,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.9082,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9194,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9175,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9607,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8893,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9603,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9067,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8835,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9089,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9314,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.9115,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8805,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8968,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.9084,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 375
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.9044,
+      "step": 376
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.9403,
+      "step": 377
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8831,
+      "step": 378
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.9051,
+      "step": 379
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.9224,
+      "step": 380
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.9263,
+      "step": 381
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.924,
+      "step": 382
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.927,
+      "step": 383
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.9126,
+      "step": 384
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.9103,
+      "step": 385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.9239,
+      "step": 386
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8892,
+      "step": 387
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8765,
+      "step": 388
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8902,
+      "step": 389
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.9553,
+      "step": 390
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.908,
+      "step": 391
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.9295,
+      "step": 392
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.901,
+      "step": 393
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.9235,
+      "step": 394
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.8801,
+      "step": 395
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 396
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.9155,
+      "step": 397
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.9205,
+      "step": 398
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.9172,
+      "step": 399
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.8874,
+      "step": 400
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.496649748611072e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_r16_alpha16/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252716072e0a3f494e120fae24b2024dc12c506ed8cc5125efbbc631cc03c647
+size 5112

llama2_7b_r16_alpha16/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9688728674508558,
+    "train_runtime": 27658.059,
+    "train_samples_per_second": 1.871,
+    "train_steps_per_second": 0.015
+}

llama2_7b_r16_alpha16/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": 1.8146,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.7128,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7934,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.8663,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7405,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.7479,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.7056,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.7681,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.767,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.6407,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.6092,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.5077,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.4746,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.4743,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.4388,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.3198,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.2482,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.3124,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.3294,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.3068,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.2152,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.2475,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.2338,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.1761,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.1325,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.109,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.179,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.1049,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.1057,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.0743,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.0916,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.1079,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.0831,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 1.1066,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0571,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0616,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0372,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 1.0247,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0285,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0031,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0416,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 1.0013,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 1.0033,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9867,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9778,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 1.0149,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9756,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9752,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9662,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9988,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9385,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.955,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9509,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9478,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9628,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9629,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 1.0102,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9445,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9574,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9524,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9556,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9435,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9527,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9615,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9425,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9624,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 1.0114,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9294,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9667,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9618,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8984,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9577,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9536,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9596,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9491,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9574,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9554,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9381,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.941,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9558,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9472,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9395,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9549,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9612,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9505,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9498,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9245,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9742,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9365,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9345,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9397,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9501,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.928,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9696,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9519,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9555,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9206,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9483,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9389,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9579,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9526,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.958,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9212,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9269,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.956,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9657,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9381,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9142,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.8811,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9375,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8994,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9411,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9318,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.957,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9323,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9252,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9562,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9229,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9489,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9549,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9232,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9296,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9185,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9892,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9659,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9093,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9408,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9339,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9115,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9675,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9347,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.941,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9431,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.955,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9084,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9311,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9614,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9109,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9683,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9062,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9106,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9469,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9259,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9642,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9216,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.927,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8858,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.934,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9101,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9306,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9782,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9105,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9044,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9323,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9618,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9525,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9502,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9243,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9448,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9416,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9387,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9226,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9329,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9547,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9515,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.92,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9357,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.882,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9177,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9455,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9667,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9641,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9359,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9517,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9543,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9318,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.946,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.951,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9352,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9236,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.948,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8868,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9284,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8917,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9202,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9048,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9258,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9596,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9235,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9581,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.9181,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8831,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.937,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9103,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9816,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9307,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.9206,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.918,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8884,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.9095,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9505,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9259,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9678,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9132,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9296,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9286,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9103,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9214,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9413,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9211,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8922,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9088,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9422,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.975,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.907,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.923,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9297,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9331,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9491,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9215,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9221,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8605,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.928,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9319,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9185,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9187,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9353,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8942,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8801,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9044,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9646,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9156,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9405,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8802,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.9094,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8809,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.9083,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9282,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9579,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8925,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9295,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9242,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9169,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8876,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9315,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9429,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9089,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9069,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.92,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9081,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8913,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9158,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9156,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9404,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8985,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.91,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8605,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8989,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.9105,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8932,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9199,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8941,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9279,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9311,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9065,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8938,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9004,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9063,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9314,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9092,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9339,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9335,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9138,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8845,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.9171,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9293,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9179,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9524,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8732,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8759,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9305,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.936,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9481,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9024,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9224,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.913,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9028,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8984,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9518,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8977,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9246,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9282,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9223,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9125,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9234,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8995,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9163,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9181,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9337,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9207,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9107,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.908,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8957,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.9082,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9194,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9175,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9607,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8893,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9603,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9067,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8835,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9089,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9314,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.9115,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8805,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8968,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.9084,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8929,
+      "step": 375
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.9044,
+      "step": 376
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.9403,
+      "step": 377
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8831,
+      "step": 378
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.9051,
+      "step": 379
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.9224,
+      "step": 380
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.9263,
+      "step": 381
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.924,
+      "step": 382
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.927,
+      "step": 383
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.9126,
+      "step": 384
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.9103,
+      "step": 385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.9239,
+      "step": 386
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8892,
+      "step": 387
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8765,
+      "step": 388
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8902,
+      "step": 389
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.9553,
+      "step": 390
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.908,
+      "step": 391
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.9295,
+      "step": 392
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.901,
+      "step": 393
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.9235,
+      "step": 394
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.8801,
+      "step": 395
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 396
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.9155,
+      "step": 397
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.9205,
+      "step": 398
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.9172,
+      "step": 399
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.8874,
+      "step": 400
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.9036,
+      "step": 401
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.895,
+      "step": 402
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003,
+      "loss": 0.9254,
+      "step": 403
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003,
+      "loss": 0.9003,
+      "step": 404
+    },
+    {
+      "epoch": 1.0,
+      "step": 404,
+      "total_flos": 4.542094418965709e+17,
+      "train_loss": 0.9688728674508558,
+      "train_runtime": 27658.059,
+      "train_samples_per_second": 1.871,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.542094418965709e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_r16_alpha16/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252716072e0a3f494e120fae24b2024dc12c506ed8cc5125efbbc631cc03c647
+size 5112