Upload folder using huggingface_hub

llama2_7b_r256_alpha256/.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_r256_alpha256/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_r256_alpha256/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": 256.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj,",
+    "gate_proj,",
+    "o_proj,",
+    "q_proj,",
+    "down_proj,",
+    "up_proj,"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_r256_alpha256/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c850af3bc322e35f3eaaaa0b6e4b108273a1f81e9559caed5d81a652726feeb9
+size 268444256

llama2_7b_r256_alpha256/all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9242179525075572,
+    "train_runtime": 18375.2967,
+    "train_samples_per_second": 2.817,
+    "train_steps_per_second": 0.022
+}

llama2_7b_r256_alpha256/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_r256_alpha256/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_r256_alpha256/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": 256.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj,",
+    "gate_proj,",
+    "o_proj,",
+    "q_proj,",
+    "down_proj,",
+    "up_proj,"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_r256_alpha256/checkpoint-350/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e541f3d649b00edc3ac8f5eb82ef6823ed6c239d933c0b7ebf568f4faf6e873
+size 268444256

llama2_7b_r256_alpha256/checkpoint-350/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81549136f0cb91e734efbcec6d571f89d6c4ecc54493655c89f7accc3e96325
+size 536925434

llama2_7b_r256_alpha256/checkpoint-350/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fad764dc4fdad5d5711c95cabb670515d289d8f504219305df3572500a90d7f
+size 14244

llama2_7b_r256_alpha256/checkpoint-350/scheduler.pt

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

llama2_7b_r256_alpha256/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": 1.8161,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.6317,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6129,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.5679,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.362,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.2853,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.201,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.2034,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1587,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1093,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.1136,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0783,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0285,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.045,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.034,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.013,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9754,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9695,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9904,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.001,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9761,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.0067,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.0043,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9413,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9184,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.0034,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9402,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9435,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9769,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9486,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9792,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9295,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9626,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9384,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9353,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9399,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9133,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9591,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9347,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9327,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9582,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9291,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.93,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9611,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.916,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9142,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9333,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9769,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9139,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9276,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9222,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9304,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9167,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9308,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.978,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.937,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8707,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9293,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9321,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9288,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9112,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9097,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8756,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9191,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9132,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9052,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9086,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9355,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9233,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8995,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9479,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.909,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9087,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9127,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.921,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9023,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9258,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9326,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8949,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9229,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9099,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9327,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9257,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.932,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9054,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.93,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9393,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9152,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.89,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.861,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9126,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9188,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9043,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9303,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9245,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.932,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8959,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9077,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8965,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9647,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9436,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8752,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.888,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9453,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9148,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9161,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9205,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8875,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8822,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9075,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9376,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8904,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9457,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8855,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9068,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8868,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9234,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.938,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9106,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8678,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8879,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9149,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8919,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9104,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9576,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8911,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8829,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9111,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9391,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9041,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8824,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9171,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9041,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9357,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9128,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8631,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8982,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9262,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9452,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9434,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9068,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9092,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9346,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9375,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8884,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9127,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9361,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9182,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9007,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9294,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8693,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9096,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8738,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9004,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8822,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9085,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9348,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9393,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.906,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9388,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8881,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8999,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8647,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.918,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8958,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9586,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9017,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9139,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8994,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8979,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8756,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8903,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9368,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9054,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9501,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8966,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9153,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8943,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9236,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9223,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8959,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9025,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8764,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8937,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.916,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9291,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9104,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9552,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9015,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9051,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8966,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9157,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.927,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9027,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9147,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9153,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9025,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9036,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9177,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8934,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8631,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8852,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9475,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8961,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.863,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8938,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8648,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8957,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9136,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9399,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8741,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8775,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.873,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9046,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9017,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.874,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9144,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9263,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8943,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8921,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9045,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.893,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8765,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8958,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8968,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9237,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8795,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8946,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8475,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8839,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.895,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8795,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9038,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8835,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9179,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8919,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8766,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9094,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8834,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8922,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9125,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8945,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.919,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9205,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.91,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8947,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8668,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.901,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8964,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9365,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8955,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8586,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8609,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9143,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9334,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8891,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9026,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.887,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8714,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8856,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8823,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9338,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8812,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9086,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8788,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9138,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8709,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8954,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8991,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9067,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.915,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.903,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9172,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8973,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 350
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 3.969718715252736e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_r256_alpha256/checkpoint-350/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ab87159feca6e6629014ac02992be64579de9dfc26c78eb8bd3fc791f84f21
+size 5112

llama2_7b_r256_alpha256/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_r256_alpha256/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": 256.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj,",
+    "gate_proj,",
+    "o_proj,",
+    "q_proj,",
+    "down_proj,",
+    "up_proj,"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_r256_alpha256/checkpoint-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d536e12986f421646004f1864e9ad5326eca52f65d6da10dc23381f00afda953
+size 268444256

llama2_7b_r256_alpha256/checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0f9b477e49ce99b0085e1ca64795d0c6e89393dbc6a15ba0e508279b5d6310
+size 536925434

llama2_7b_r256_alpha256/checkpoint-375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0adbd8cb675c06ea37e7b8cd0f727aff6d64b6b54dcaa30377206597e8a085
+size 14244

llama2_7b_r256_alpha256/checkpoint-375/scheduler.pt

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

llama2_7b_r256_alpha256/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": 1.8161,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.6317,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6129,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.5679,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.362,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.2853,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.201,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.2034,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1587,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1093,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.1136,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0783,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0285,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.045,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.034,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.013,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9754,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9695,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9904,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.001,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9761,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.0067,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.0043,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9413,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9184,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.0034,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9402,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9435,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9769,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9486,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9792,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9295,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9626,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9384,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9353,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9399,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9133,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9591,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9347,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9327,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9582,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9291,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.93,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9611,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.916,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9142,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9333,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9769,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9139,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9276,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9222,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9304,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9167,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9308,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.978,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.937,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8707,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9293,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9321,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9288,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9112,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9097,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8756,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9191,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9132,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9052,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9086,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9355,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9233,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8995,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9479,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.909,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9087,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9127,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.921,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9023,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9258,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9326,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8949,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9229,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9099,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9327,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9257,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.932,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9054,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.93,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9393,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9152,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.89,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.861,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9126,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9188,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9043,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9303,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9245,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.932,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8959,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9077,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8965,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9647,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9436,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8752,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.888,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9453,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9148,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9161,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9205,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8875,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8822,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9075,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9376,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8904,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9457,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8855,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9068,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8868,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9234,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.938,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9106,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8678,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8879,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9149,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8919,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9104,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9576,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8911,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8829,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9111,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9391,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9041,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8824,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9171,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9041,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9357,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9128,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8631,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8982,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9262,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9452,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9434,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9068,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9092,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9346,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9375,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8884,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9127,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9361,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9182,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9007,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9294,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8693,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9096,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8738,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9004,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8822,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9085,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9348,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9393,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.906,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9388,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8881,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8999,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8647,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.918,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8958,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9586,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9017,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9139,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8994,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8979,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8756,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8903,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9368,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9054,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9501,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8966,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9153,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8943,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9236,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9223,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8959,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9025,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8764,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8937,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.916,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9291,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9104,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9552,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9015,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9051,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8966,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9157,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.927,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9027,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9147,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9153,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9025,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9036,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9177,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8934,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8631,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8852,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9475,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8961,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.863,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8938,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8648,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8957,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9136,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9399,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8741,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8775,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.873,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9046,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9017,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.874,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9144,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9263,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8943,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8921,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9045,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.893,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8765,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8958,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8968,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9237,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8795,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8946,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8475,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8839,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.895,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8795,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9038,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8835,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9179,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8919,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8766,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9094,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8834,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8922,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9125,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8945,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.919,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9205,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.91,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8947,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8668,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.901,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8964,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9365,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8955,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8586,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8609,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9143,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9334,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8891,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9026,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.887,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8714,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8856,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8823,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9338,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8812,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9086,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8788,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9138,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8709,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8954,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8991,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9067,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.915,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.903,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9172,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8973,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8911,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8751,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8941,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9126,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9006,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9449,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.886,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8725,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9445,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8902,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.866,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8889,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9055,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8942,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8893,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9144,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9304,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8981,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8662,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8823,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8928,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8789,
+      "step": 375
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.255914165011251e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_r256_alpha256/checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ab87159feca6e6629014ac02992be64579de9dfc26c78eb8bd3fc791f84f21
+size 5112

llama2_7b_r256_alpha256/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_r256_alpha256/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": 256.0,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj,",
+    "gate_proj,",
+    "o_proj,",
+    "q_proj,",
+    "down_proj,",
+    "up_proj,"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama2_7b_r256_alpha256/checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5ac4ce13d494d2c58304b4963f73992f79c52655aac67756bf4bbaedff7ed6
+size 268444256

llama2_7b_r256_alpha256/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f371ad2882792ca97a4f82c70da7c88b50fa353c6379f105eaf3ab344b1b75
+size 536925434

llama2_7b_r256_alpha256/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a8e2639340d8644780a15f83dd523fe71a787435d9e2f2e948fbb1aba1f410
+size 14244

llama2_7b_r256_alpha256/checkpoint-400/scheduler.pt

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

llama2_7b_r256_alpha256/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": 1.8161,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.6317,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6129,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.5679,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.362,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.2853,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.201,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.2034,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1587,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1093,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.1136,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0783,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0285,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.045,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.034,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.013,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9754,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9695,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9904,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.001,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9761,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.0067,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.0043,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9413,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9184,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.0034,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9402,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9435,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9769,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9486,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9792,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9295,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9626,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9384,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9353,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9399,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9133,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9591,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9347,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9327,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9582,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9291,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.93,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9611,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.916,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9142,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9333,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9769,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9139,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9276,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9222,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9304,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9167,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9308,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.978,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.937,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8707,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9293,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9321,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9288,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9112,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9097,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8756,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9191,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9132,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9052,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9086,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9355,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9233,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8995,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9479,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.909,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9087,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9127,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.921,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9023,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9258,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9326,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8949,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9229,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9099,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9327,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9257,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.932,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9054,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.93,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9393,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9152,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.89,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.861,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9126,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9188,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9043,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9303,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9245,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.932,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8959,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9077,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8965,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9647,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9436,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8752,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.888,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9453,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9148,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9161,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9205,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8875,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8822,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9075,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9376,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8904,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9457,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8855,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9068,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8868,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9234,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.938,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9106,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8678,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8879,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9149,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8919,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9104,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9576,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8911,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8829,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9111,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9391,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9041,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8824,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9171,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9041,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9357,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9128,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8631,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8982,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9262,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9452,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9434,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9068,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9092,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9346,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9375,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8884,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9127,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9361,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9182,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9007,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9294,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8693,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9096,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8738,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9004,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8822,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9085,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9348,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9393,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.906,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9388,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8881,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8999,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8647,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.918,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8958,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9586,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9017,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9139,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8994,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8979,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8756,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8903,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9368,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9054,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9501,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8966,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9153,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8943,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9236,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9223,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8959,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9025,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8764,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8937,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.916,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9291,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9104,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9552,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9015,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9051,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8966,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9157,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.927,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9027,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9147,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9153,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9025,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9036,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9177,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8934,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8631,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8852,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9475,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8961,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.863,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8938,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8648,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8957,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9136,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9399,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8741,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8775,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.873,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9046,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9017,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.874,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9144,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9263,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8943,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8921,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9045,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.893,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8765,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8958,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8968,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9237,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8795,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8946,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8475,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8839,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.895,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8795,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9038,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8835,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9179,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8919,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8766,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9094,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8834,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8922,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9125,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8945,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.919,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9205,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.91,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8947,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8668,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.901,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8964,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9365,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8955,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8586,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8609,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9143,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9334,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8891,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9026,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.887,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8714,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8856,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8823,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9338,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8812,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9086,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8788,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9138,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8709,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8954,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8991,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9067,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.915,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.903,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9172,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8973,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8911,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8751,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8941,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9126,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9006,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9449,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.886,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8725,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9445,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8902,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.866,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8889,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9055,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8942,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8893,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9144,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9304,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8981,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8662,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8823,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8928,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8789,
+      "step": 375
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8892,
+      "step": 376
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.9237,
+      "step": 377
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8653,
+      "step": 378
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.8914,
+      "step": 379
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.906,
+      "step": 380
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.9069,
+      "step": 381
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.9076,
+      "step": 382
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.9061,
+      "step": 383
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.8983,
+      "step": 384
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.8933,
+      "step": 385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.909,
+      "step": 386
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.874,
+      "step": 387
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8617,
+      "step": 388
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8736,
+      "step": 389
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.939,
+      "step": 390
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.8937,
+      "step": 391
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.9151,
+      "step": 392
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.8863,
+      "step": 393
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.9079,
+      "step": 394
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.8665,
+      "step": 395
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.9081,
+      "step": 396
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.8966,
+      "step": 397
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.9048,
+      "step": 398
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.9024,
+      "step": 399
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.8764,
+      "step": 400
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.539439299821568e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_r256_alpha256/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ab87159feca6e6629014ac02992be64579de9dfc26c78eb8bd3fc791f84f21
+size 5112

llama2_7b_r256_alpha256/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9242179525075572,
+    "train_runtime": 18375.2967,
+    "train_samples_per_second": 2.817,
+    "train_steps_per_second": 0.022
+}

llama2_7b_r256_alpha256/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": 1.8161,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0003,
+      "loss": 1.6317,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.6129,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.5679,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.362,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0003,
+      "loss": 1.2853,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.201,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.2034,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1587,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003,
+      "loss": 1.1093,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.1136,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0783,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.0285,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0003,
+      "loss": 1.045,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.034,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 1.013,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9754,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0003,
+      "loss": 0.9695,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9904,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.001,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.9761,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.0067,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 1.0043,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9413,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9184,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 1.0034,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9402,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.9435,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.95,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9769,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9486,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0003,
+      "loss": 0.9792,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9295,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9626,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9384,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0003,
+      "loss": 0.9353,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9399,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9133,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9591,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0003,
+      "loss": 0.9347,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9327,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0003,
+      "loss": 0.9582,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9267,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9291,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.93,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003,
+      "loss": 0.9611,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9034,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9165,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.916,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0003,
+      "loss": 0.9142,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9333,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9769,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003,
+      "loss": 0.9139,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9276,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9222,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0003,
+      "loss": 0.9264,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9304,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0003,
+      "loss": 0.9167,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9308,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.978,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.937,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.8707,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0003,
+      "loss": 0.9293,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9321,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9288,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0003,
+      "loss": 0.9244,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9112,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9097,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.8756,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9191,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9132,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9052,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0003,
+      "loss": 0.9292,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9086,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9355,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.9233,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.8995,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9479,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.909,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0003,
+      "loss": 0.9087,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9127,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.921,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.9023,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0003,
+      "loss": 0.945,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9258,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.9326,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8949,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9229,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9099,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9327,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0003,
+      "loss": 0.9257,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.932,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.9054,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003,
+      "loss": 0.93,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9393,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.9152,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.89,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0003,
+      "loss": 0.861,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9126,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.8745,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9188,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0003,
+      "loss": 0.9108,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9271,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9043,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0003,
+      "loss": 0.9303,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.9245,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.932,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0003,
+      "loss": 0.8959,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9077,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.8965,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0003,
+      "loss": 0.9647,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9436,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.8752,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.888,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9453,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.9148,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9161,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.9205,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.931,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0003,
+      "loss": 0.8875,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8822,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9075,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.9376,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0003,
+      "loss": 0.8904,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9457,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8855,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.9068,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0003,
+      "loss": 0.8868,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9234,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.938,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9106,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8678,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.8879,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0003,
+      "loss": 0.9149,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8919,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9104,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.9576,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003,
+      "loss": 0.8911,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8898,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.8829,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9111,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003,
+      "loss": 0.9391,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9298,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.9041,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003,
+      "loss": 0.926,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.8824,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9217,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9171,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003,
+      "loss": 0.9041,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9357,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9343,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9128,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8631,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.8982,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003,
+      "loss": 0.9262,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9452,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9434,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9192,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9068,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003,
+      "loss": 0.9092,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9346,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9375,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.8884,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003,
+      "loss": 0.9127,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9275,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9361,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9182,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003,
+      "loss": 0.9007,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9294,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8693,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.9096,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003,
+      "loss": 0.8738,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9004,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.8822,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9085,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003,
+      "loss": 0.9348,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9393,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.906,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9388,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003,
+      "loss": 0.9018,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8881,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8999,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.8647,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003,
+      "loss": 0.918,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.8958,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9586,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9017,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003,
+      "loss": 0.9139,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8994,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8979,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8756,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003,
+      "loss": 0.8903,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9368,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9054,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.9501,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003,
+      "loss": 0.8966,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9123,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.9153,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0003,
+      "loss": 0.8943,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9195,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9013,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9236,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0003,
+      "loss": 0.9223,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8959,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.9025,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8764,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0003,
+      "loss": 0.8937,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.916,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9291,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9104,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0003,
+      "loss": 0.9552,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8864,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9015,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.9051,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0003,
+      "loss": 0.8966,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9157,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.927,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0003,
+      "loss": 0.9016,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9027,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.8417,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9147,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0003,
+      "loss": 0.9153,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9145,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9025,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9036,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0003,
+      "loss": 0.9177,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8934,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0003,
+      "loss": 0.8631,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8852,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9475,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.8961,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.863,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8938,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8648,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0003,
+      "loss": 0.8957,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9136,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.9399,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8741,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0003,
+      "loss": 0.8775,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.873,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9046,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0003,
+      "loss": 0.9017,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.874,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9144,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.9263,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8943,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0003,
+      "loss": 0.8921,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.9045,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.893,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8765,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0003,
+      "loss": 0.8958,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8968,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.9237,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0003,
+      "loss": 0.8795,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8946,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8475,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.8839,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0003,
+      "loss": 0.895,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8795,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9038,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.8781,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0003,
+      "loss": 0.9091,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8835,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.9179,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.911,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0003,
+      "loss": 0.8919,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8766,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.9094,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8834,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0003,
+      "loss": 0.8922,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9125,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.8945,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.919,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0003,
+      "loss": 0.9205,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.91,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8947,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.8668,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0003,
+      "loss": 0.901,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9118,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.8964,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9059,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0003,
+      "loss": 0.9365,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8955,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8586,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.8609,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0003,
+      "loss": 0.9143,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9209,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9334,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.8891,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0003,
+      "loss": 0.9026,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.9135,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.887,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0003,
+      "loss": 0.8714,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8856,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8823,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.9338,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003,
+      "loss": 0.8812,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9086,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8788,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.9138,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003,
+      "loss": 0.8709,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.905,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8954,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.9098,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.8991,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.9067,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.915,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003,
+      "loss": 0.903,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9172,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8973,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.9014,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003,
+      "loss": 0.8992,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8911,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8751,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0003,
+      "loss": 0.8941,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9053,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9126,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9006,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003,
+      "loss": 0.9449,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.886,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8843,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.8725,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003,
+      "loss": 0.9445,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8902,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.866,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.8889,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.0003,
+      "loss": 0.9055,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8942,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8893,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9144,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.9304,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003,
+      "loss": 0.8981,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8963,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8662,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8823,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003,
+      "loss": 0.8928,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8789,
+      "step": 375
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8892,
+      "step": 376
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.9237,
+      "step": 377
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0003,
+      "loss": 0.8653,
+      "step": 378
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.8914,
+      "step": 379
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.906,
+      "step": 380
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.9069,
+      "step": 381
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0003,
+      "loss": 0.9076,
+      "step": 382
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.9061,
+      "step": 383
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.8983,
+      "step": 384
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.8933,
+      "step": 385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003,
+      "loss": 0.909,
+      "step": 386
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.874,
+      "step": 387
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8617,
+      "step": 388
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.8736,
+      "step": 389
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0003,
+      "loss": 0.939,
+      "step": 390
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.8937,
+      "step": 391
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.9151,
+      "step": 392
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.8863,
+      "step": 393
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003,
+      "loss": 0.9079,
+      "step": 394
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.8665,
+      "step": 395
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.9081,
+      "step": 396
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.8966,
+      "step": 397
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003,
+      "loss": 0.9048,
+      "step": 398
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.9024,
+      "step": 399
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.8764,
+      "step": 400
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.8854,
+      "step": 401
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003,
+      "loss": 0.882,
+      "step": 402
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003,
+      "loss": 0.9126,
+      "step": 403
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0003,
+      "loss": 0.8861,
+      "step": 404
+    },
+    {
+      "epoch": 1.0,
+      "step": 404,
+      "total_flos": 4.585316415920947e+17,
+      "train_loss": 0.9242179525075572,
+      "train_runtime": 18375.2967,
+      "train_samples_per_second": 2.817,
+      "train_steps_per_second": 0.022
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.585316415920947e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_r256_alpha256/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ab87159feca6e6629014ac02992be64579de9dfc26c78eb8bd3fc791f84f21
+size 5112