Upload folder using huggingface_hub

llama2_7b_SGD_Cosine/.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_SGD_Cosine/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_SGD_Cosine/adapter_config.json

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

llama2_7b_SGD_Cosine/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17458a74f0d532555a12f9e10058c8be0307127760686b5213ed5c10b2d19403
+size 8397056

llama2_7b_SGD_Cosine/all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9254943004043976,
+    "train_runtime": 17197.3779,
+    "train_samples_per_second": 3.01,
+    "train_steps_per_second": 0.023
+}

llama2_7b_SGD_Cosine/bnb_config.json

@@ -0,0 +1,6 @@
+{
+    "load_in_4bit": true,
+    "bnb_4bit_quant_type" : "fp4",
+    "bnb_4bit_use_double_quant" : false,
+    "bnb_4bit_compute_dtype" : "bfloat16"
+}

llama2_7b_SGD_Cosine/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_SGD_Cosine/checkpoint-350/adapter_config.json

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

llama2_7b_SGD_Cosine/checkpoint-350/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d96c47a634db7ffa52602553058586111a5ec653c0b12aa5f06686d5a39ab69
+size 8397056

llama2_7b_SGD_Cosine/checkpoint-350/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e314e5acf23c8cd94c2fb64de12837643f8c570de625e18d06471d68d185cb
+size 16831290

llama2_7b_SGD_Cosine/checkpoint-350/rng_state.pth

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

llama2_7b_SGD_Cosine/checkpoint-350/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d08bdbdf4c933a839603446dac2e909850c1088508182ad82dd43da0e10670a
+size 1064

llama2_7b_SGD_Cosine/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": 2.9999999999999997e-06,
+      "loss": 1.8153,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 1.7198,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-06,
+      "loss": 1.8135,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 1.91,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 1.8073,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 1.848,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.1e-05,
+      "loss": 1.8294,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 1.9358,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 1.98,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.8625,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 1.8559,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 1.7621,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.9e-05,
+      "loss": 1.7816,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.2e-05,
+      "loss": 1.8272,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 1.8546,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 1.6863,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.1e-05,
+      "loss": 1.6002,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 1.7753,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 1.8031,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.7884,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.299999999999999e-05,
+      "loss": 1.6288,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.599999999999999e-05,
+      "loss": 1.672,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 6.9e-05,
+      "loss": 1.6625,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 1.6373,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.5e-05,
+      "loss": 1.5654,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.8e-05,
+      "loss": 1.5128,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.1e-05,
+      "loss": 1.5769,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.4e-05,
+      "loss": 1.4986,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 1.514,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.4492,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.3e-05,
+      "loss": 1.437,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.599999999999999e-05,
+      "loss": 1.4183,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.9e-05,
+      "loss": 1.3496,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000102,
+      "loss": 1.3538,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010499999999999999,
+      "loss": 1.2837,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010799999999999998,
+      "loss": 1.2471,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 1.2154,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.1819,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000117,
+      "loss": 1.16,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.1309,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00012299999999999998,
+      "loss": 1.1511,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 1.0796,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000129,
+      "loss": 1.0747,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013199999999999998,
+      "loss": 1.0301,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000135,
+      "loss": 1.0205,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000138,
+      "loss": 1.05,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014099999999999998,
+      "loss": 1.0128,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 1.0066,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000147,
+      "loss": 0.9924,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00015,
+      "loss": 1.0251,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00015299999999999998,
+      "loss": 0.9605,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000156,
+      "loss": 0.9755,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000159,
+      "loss": 0.9642,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000162,
+      "loss": 0.9631,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000165,
+      "loss": 0.9736,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000168,
+      "loss": 0.9673,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017099999999999998,
+      "loss": 1.0058,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017399999999999997,
+      "loss": 0.9245,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 0.8959,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.8951,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00018299999999999998,
+      "loss": 0.9796,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000186,
+      "loss": 0.9347,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00018899999999999999,
+      "loss": 0.8796,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019199999999999998,
+      "loss": 0.8916,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000195,
+      "loss": 0.8951,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000198,
+      "loss": 0.8821,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000201,
+      "loss": 0.8916,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000204,
+      "loss": 0.94,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 0.8569,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.8929,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021299999999999997,
+      "loss": 0.8895,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021599999999999996,
+      "loss": 0.8258,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021899999999999998,
+      "loss": 0.885,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00022199999999999998,
+      "loss": 0.8788,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000225,
+      "loss": 0.8865,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.8757,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00023099999999999998,
+      "loss": 0.8821,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000234,
+      "loss": 0.8786,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000237,
+      "loss": 0.8665,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.8617,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000243,
+      "loss": 0.8288,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00024599999999999996,
+      "loss": 0.8719,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000249,
+      "loss": 0.872,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00025199999999999995,
+      "loss": 0.8618,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00025499999999999996,
+      "loss": 0.8502,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000258,
+      "loss": 0.8855,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000261,
+      "loss": 0.8593,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00026399999999999997,
+      "loss": 0.878,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000267,
+      "loss": 0.8736,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00027,
+      "loss": 0.8757,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00027299999999999997,
+      "loss": 0.848,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000276,
+      "loss": 0.87,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000279,
+      "loss": 0.8922,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00028199999999999997,
+      "loss": 0.8581,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000285,
+      "loss": 0.8453,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00028799999999999995,
+      "loss": 0.8585,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00029099999999999997,
+      "loss": 0.8634,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000294,
+      "loss": 0.8409,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 0.8882,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8696,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029999199041570257,
+      "loss": 0.8779,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029996796251818966,
+      "loss": 0.8137,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029992791887350736,
+      "loss": 0.8419,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002998718637580951,
+      "loss": 0.8666,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002997998031583285,
+      "loss": 0.8451,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002997117447698802,
+      "loss": 0.875,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00029960769799689793,
+      "loss": 0.8658,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029948767395100045,
+      "loss": 0.8738,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002993516854500905,
+      "loss": 0.8324,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029919974701698635,
+      "loss": 0.8494,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029903187487787046,
+      "loss": 0.8624,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002988480869605567,
+      "loss": 0.8772,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002986484028925761,
+      "loss": 0.8527,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002984328439990804,
+      "loss": 0.8234,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002982014333005645,
+      "loss": 0.7951,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029795419551040833,
+      "loss": 0.8506,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029769115703223763,
+      "loss": 0.8084,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002974123459571039,
+      "loss": 0.8541,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029711779206048454,
+      "loss": 0.8425,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029680752679910315,
+      "loss": 0.8619,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029648158330756986,
+      "loss": 0.8502,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002961399963948431,
+      "loss": 0.8482,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002957828025405117,
+      "loss": 0.8647,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002954100398908995,
+      "loss": 0.8427,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00029502174825499146,
+      "loss": 0.8723,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000294617969100182,
+      "loss": 0.8716,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00029419874554784695,
+      "loss": 0.8385,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002937641223687379,
+      "loss": 0.841,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029331414597820145,
+      "loss": 0.838,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029284886443122214,
+      "loss": 0.8321,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029236832741729016,
+      "loss": 0.9036,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029187258625509513,
+      "loss": 0.8804,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002913616938870455,
+      "loss": 0.7992,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002908357048736144,
+      "loss": 0.8204,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029029467538751303,
+      "loss": 0.8584,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00028973866320769183,
+      "loss": 0.8478,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00028916772771316973,
+      "loss": 0.8135,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000288581929876693,
+      "loss": 0.8852,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0002879813322582237,
+      "loss": 0.8446,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028736599899825856,
+      "loss": 0.8527,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0002867359958109792,
+      "loss": 0.85,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028609138997723397,
+      "loss": 0.871,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028543225033735313,
+      "loss": 0.8208,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002847586472837968,
+      "loss": 0.8125,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00028407065275363753,
+      "loss": 0.8421,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002833683402208777,
+      "loss": 0.8677,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002826517846886033,
+      "loss": 0.8242,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00028192106268097334,
+      "loss": 0.8747,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002811762522350481,
+      "loss": 0.815,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.000280417432892455,
+      "loss": 0.8432,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002796446856908939,
+      "loss": 0.8256,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002788580931554828,
+      "loss": 0.856,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002780577392899446,
+      "loss": 0.8366,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00027724370956763603,
+      "loss": 0.8666,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002764160909224196,
+      "loss": 0.84,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00027557497173937923,
+      "loss": 0.8468,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0002747204418453818,
+      "loss": 0.8057,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00027385259249948333,
+      "loss": 0.8228,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.000272971516383184,
+      "loss": 0.8424,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00027207730759052924,
+      "loss": 0.8181,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002711700616180619,
+      "loss": 0.8378,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002702498753546232,
+      "loss": 0.8903,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00026931684707100586,
+      "loss": 0.8211,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026837107640945905,
+      "loss": 0.8213,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026741266437304716,
+      "loss": 0.811,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0002664417133148636,
+      "loss": 0.8481,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026545832692709964,
+      "loss": 0.8715,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00026446261022997097,
+      "loss": 0.8717,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00026345466956050176,
+      "loss": 0.8589,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0002624346125611689,
+      "loss": 0.8298,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.000261402548168406,
+      "loss": 0.859,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002603585866009697,
+      "loss": 0.8108,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002593028393481692,
+      "loss": 0.8591,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002582354191579593,
+      "loss": 0.8521,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00025715644002489996,
+      "loss": 0.8394,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025606601717798207,
+      "loss": 0.8457,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025496426706832193,
+      "loss": 0.8656,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002538513073567244,
+      "loss": 0.8678,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025272725690111806,
+      "loss": 0.8367,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00025159223574386114,
+      "loss": 0.8449,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00025044636509892227,
+      "loss": 0.8003,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00024928976733893494,
+      "loss": 0.8312,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002481225659821294,
+      "loss": 0.8567,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024694488567914106,
+      "loss": 0.872,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002457568521996988,
+      "loss": 0.8735,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024455859241919326,
+      "loss": 0.8571,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002433502343051274,
+      "loss": 0.8395,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024213190690345018,
+      "loss": 0.8439,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00024090374032477533,
+      "loss": 0.8661,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002396658657304861,
+      "loss": 0.8679,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00023841841531872798,
+      "loss": 0.8151,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00023716152231029072,
+      "loss": 0.8517,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.000235895320934381,
+      "loss": 0.8591,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00023461994641428766,
+      "loss": 0.8638,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002333355349529403,
+      "loss": 0.8512,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00023204222371836405,
+      "loss": 0.835,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00023074015082903015,
+      "loss": 0.8611,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002294294553391063,
+      "loss": 0.7981,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022811027722360598,
+      "loss": 0.84,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022678275736344014,
+      "loss": 0.8008,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022544703753037178,
+      "loss": 0.8333,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022410326037187558,
+      "loss": 0.8197,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022275156939590392,
+      "loss": 0.8408,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022139210895556104,
+      "loss": 0.8608,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022002502423368678,
+      "loss": 0.8705,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002186504612273522,
+      "loss": 0.8388,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002172685667322676,
+      "loss": 0.8779,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00021587948832710554,
+      "loss": 0.8314,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002144833743577405,
+      "loss": 0.8249,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002130803739214061,
+      "loss": 0.8312,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00021167063685077262,
+      "loss": 0.8003,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002102543136979454,
+      "loss": 0.8513,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020883155571838692,
+      "loss": 0.835,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020740251485476345,
+      "loss": 0.8981,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020596734372071852,
+      "loss": 0.8353,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020452619558457446,
+      "loss": 0.8457,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00020307922435296443,
+      "loss": 0.8225,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002016265845543958,
+      "loss": 0.8342,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00020016843132274746,
+      "loss": 0.807,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00019870492038070252,
+      "loss": 0.8271,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019723620802311774,
+      "loss": 0.8731,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019576245110033231,
+      "loss": 0.8436,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019428380700141698,
+      "loss": 0.8816,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019280043363736579,
+      "loss": 0.8281,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0001913124894242322,
+      "loss": 0.8413,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018982013326621083,
+      "loss": 0.8318,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018832352453866777,
+      "loss": 0.8394,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018682282307111987,
+      "loss": 0.819,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018531818913016584,
+      "loss": 0.8598,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018380978340237092,
+      "loss": 0.8346,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018229776697710617,
+      "loss": 0.8523,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018078230132934512,
+      "loss": 0.8461,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017926354830241924,
+      "loss": 0.8368,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017774167009073377,
+      "loss": 0.8336,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017621682922244633,
+      "loss": 0.8049,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017468918854211007,
+      "loss": 0.8245,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001731589111932823,
+      "loss": 0.8474,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000171626160601102,
+      "loss": 0.8643,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001700911004548369,
+      "loss": 0.8448,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00016855389469040217,
+      "loss": 0.8822,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016701470747285317,
+      "loss": 0.8225,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016547370317885354,
+      "loss": 0.8269,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0001639310463791205,
+      "loss": 0.8365,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016238690182084986,
+      "loss": 0.8265,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016084143441012156,
+      "loss": 0.8439,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001592948091942892,
+      "loss": 0.8438,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001577471913443532,
+      "loss": 0.8595,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00015619874613732196,
+      "loss": 0.8313,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001546496389385611,
+      "loss": 0.8258,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015310003518413315,
+      "loss": 0.7778,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015155010036313008,
+      "loss": 0.8442,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015,
+      "loss": 0.8477,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014844989963686992,
+      "loss": 0.8447,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014689996481586688,
+      "loss": 0.8424,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014535036106143892,
+      "loss": 0.8357,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000143801253862678,
+      "loss": 0.8467,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001422528086556468,
+      "loss": 0.8105,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001407051908057108,
+      "loss": 0.8215,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001391585655898784,
+      "loss": 0.8452,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00013761309817915014,
+      "loss": 0.7967,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013606895362087949,
+      "loss": 0.8172,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013452629682114646,
+      "loss": 0.8837,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013298529252714684,
+      "loss": 0.8293,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013144610530959784,
+      "loss": 0.8493,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001299088995451631,
+      "loss": 0.7906,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012837383939889798,
+      "loss": 0.8201,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012684108880671772,
+      "loss": 0.7947,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012531081145788987,
+      "loss": 0.8238,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012378317077755362,
+      "loss": 0.8417,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012225832990926623,
+      "loss": 0.8728,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012073645169758076,
+      "loss": 0.798,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00011921769867065485,
+      "loss": 0.8053,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011770223302289385,
+      "loss": 0.7943,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001161902165976291,
+      "loss": 0.8407,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011468181086983412,
+      "loss": 0.8326,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011317717692888012,
+      "loss": 0.8355,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0001116764754613322,
+      "loss": 0.8015,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00011017986673378918,
+      "loss": 0.8426,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010868751057576782,
+      "loss": 0.858,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010719956636263423,
+      "loss": 0.8268,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010571619299858303,
+      "loss": 0.8244,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010423754889966769,
+      "loss": 0.8328,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010276379197688222,
+      "loss": 0.8201,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010129507961929748,
+      "loss": 0.804,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.983156867725255e-05,
+      "loss": 0.8273,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.837341544560423e-05,
+      "loss": 0.8222,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.692077564703555e-05,
+      "loss": 0.828,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.547380441542549e-05,
+      "loss": 0.8507,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.403265627928147e-05,
+      "loss": 0.8044,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.259748514523653e-05,
+      "loss": 0.8202,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.116844428161309e-05,
+      "loss": 0.7773,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.97456863020546e-05,
+      "loss": 0.8119,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.83293631492274e-05,
+      "loss": 0.8274,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.691962607859386e-05,
+      "loss": 0.8167,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.55166256422595e-05,
+      "loss": 0.8389,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.412051167289446e-05,
+      "loss": 0.8091,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.27314332677324e-05,
+      "loss": 0.8418,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.134953877264778e-05,
+      "loss": 0.8105,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.997497576631323e-05,
+      "loss": 0.8409,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.860789104443896e-05,
+      "loss": 0.8429,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.724843060409606e-05,
+      "loss": 0.8175,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.589673962812442e-05,
+      "loss": 0.8115,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.455296246962823e-05,
+      "loss": 0.846,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.321724263655988e-05,
+      "loss": 0.8175,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.188972277639405e-05,
+      "loss": 0.8177,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.057054466089371e-05,
+      "loss": 0.8441,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.925984917096985e-05,
+      "loss": 0.8272,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.795777628163599e-05,
+      "loss": 0.8525,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.66644650470597e-05,
+      "loss": 0.8533,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.538005358571234e-05,
+      "loss": 0.8436,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.410467906561896e-05,
+      "loss": 0.832,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.283847768970926e-05,
+      "loss": 0.7897,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.158158468127196e-05,
+      "loss": 0.824,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.0334134269513865e-05,
+      "loss": 0.8435,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.9096259675224647e-05,
+      "loss": 0.8233,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.786809309654982e-05,
+      "loss": 0.8333,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.664976569487263e-05,
+      "loss": 0.8658,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.5441407580806745e-05,
+      "loss": 0.8229,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.4243147800301134e-05,
+      "loss": 0.7847,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.305511432085884e-05,
+      "loss": 0.7924,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.187743401787054e-05,
+      "loss": 0.8458,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.071023266106502e-05,
+      "loss": 0.8492,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.955363490107777e-05,
+      "loss": 0.8584,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.840776425613886e-05,
+      "loss": 0.8262,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.727274309888191e-05,
+      "loss": 0.8299,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.614869264327553e-05,
+      "loss": 0.8267,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.503573293167805e-05,
+      "loss": 0.8352,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.3933982822017876e-05,
+      "loss": 0.8181,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.284355997510003e-05,
+      "loss": 0.8091,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.17645808420407e-05,
+      "loss": 0.8123,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.0697160651830814e-05,
+      "loss": 0.8075,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.964141339903026e-05,
+      "loss": 0.8576,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.8597451831594014e-05,
+      "loss": 0.8134,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.756538743883111e-05,
+      "loss": 0.8384,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.654533043949823e-05,
+      "loss": 0.8061,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.5537389770029046e-05,
+      "loss": 0.8438,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.454167307290036e-05,
+      "loss": 0.8024,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.3558286685136384e-05,
+      "loss": 0.8332,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.258733562695283e-05,
+      "loss": 0.8247,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.162892359054098e-05,
+      "loss": 0.8482,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.0683152928994105e-05,
+      "loss": 0.8171,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.9750124645376755e-05,
+      "loss": 0.8296,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.8829938381938117e-05,
+      "loss": 0.8403,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.792269240947076e-05,
+      "loss": 0.8472,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.702848361681605e-05,
+      "loss": 0.8305,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.6147407500516643e-05,
+      "loss": 0.8491,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.5279558154618197e-05,
+      "loss": 0.8299,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.4425028260620715e-05,
+      "loss": 0.8329,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.35839090775804e-05,
+      "loss": 0.8234,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.2756290432363957e-05,
+      "loss": 0.8197,
+      "step": 350
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 3.9310521413861376e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_SGD_Cosine/checkpoint-350/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33222dfbebfe89abc6dfd2eda90df0b1c95c9ba8141e3518b9034d169c7a3c7
+size 5048

llama2_7b_SGD_Cosine/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_SGD_Cosine/checkpoint-375/adapter_config.json

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

llama2_7b_SGD_Cosine/checkpoint-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f93cd061a21b149a6d469d959bad5249a66258fe97323cacd1f3f03963c531
+size 8397056

llama2_7b_SGD_Cosine/checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a240e02cb24cd509e58533d199ea16a6bc937cfa0dc64f6ccc0845a66a474c
+size 16831290

llama2_7b_SGD_Cosine/checkpoint-375/rng_state.pth

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

llama2_7b_SGD_Cosine/checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50fc3bf1d9900c827f1861e9af9c3f345c30cc0cd813dbc6226d5bed3aa731d0
+size 1064

llama2_7b_SGD_Cosine/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": 2.9999999999999997e-06,
+      "loss": 1.8153,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 1.7198,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-06,
+      "loss": 1.8135,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 1.91,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 1.8073,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 1.848,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.1e-05,
+      "loss": 1.8294,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 1.9358,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 1.98,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.8625,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 1.8559,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 1.7621,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.9e-05,
+      "loss": 1.7816,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.2e-05,
+      "loss": 1.8272,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 1.8546,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 1.6863,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.1e-05,
+      "loss": 1.6002,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 1.7753,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 1.8031,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.7884,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.299999999999999e-05,
+      "loss": 1.6288,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.599999999999999e-05,
+      "loss": 1.672,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 6.9e-05,
+      "loss": 1.6625,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 1.6373,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.5e-05,
+      "loss": 1.5654,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.8e-05,
+      "loss": 1.5128,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.1e-05,
+      "loss": 1.5769,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.4e-05,
+      "loss": 1.4986,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 1.514,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.4492,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.3e-05,
+      "loss": 1.437,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.599999999999999e-05,
+      "loss": 1.4183,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.9e-05,
+      "loss": 1.3496,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000102,
+      "loss": 1.3538,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010499999999999999,
+      "loss": 1.2837,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010799999999999998,
+      "loss": 1.2471,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 1.2154,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.1819,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000117,
+      "loss": 1.16,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.1309,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00012299999999999998,
+      "loss": 1.1511,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 1.0796,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000129,
+      "loss": 1.0747,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013199999999999998,
+      "loss": 1.0301,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000135,
+      "loss": 1.0205,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000138,
+      "loss": 1.05,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014099999999999998,
+      "loss": 1.0128,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 1.0066,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000147,
+      "loss": 0.9924,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00015,
+      "loss": 1.0251,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00015299999999999998,
+      "loss": 0.9605,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000156,
+      "loss": 0.9755,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000159,
+      "loss": 0.9642,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000162,
+      "loss": 0.9631,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000165,
+      "loss": 0.9736,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000168,
+      "loss": 0.9673,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017099999999999998,
+      "loss": 1.0058,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017399999999999997,
+      "loss": 0.9245,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 0.8959,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.8951,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00018299999999999998,
+      "loss": 0.9796,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000186,
+      "loss": 0.9347,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00018899999999999999,
+      "loss": 0.8796,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019199999999999998,
+      "loss": 0.8916,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000195,
+      "loss": 0.8951,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000198,
+      "loss": 0.8821,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000201,
+      "loss": 0.8916,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000204,
+      "loss": 0.94,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 0.8569,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.8929,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021299999999999997,
+      "loss": 0.8895,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021599999999999996,
+      "loss": 0.8258,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021899999999999998,
+      "loss": 0.885,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00022199999999999998,
+      "loss": 0.8788,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000225,
+      "loss": 0.8865,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.8757,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00023099999999999998,
+      "loss": 0.8821,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000234,
+      "loss": 0.8786,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000237,
+      "loss": 0.8665,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.8617,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000243,
+      "loss": 0.8288,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00024599999999999996,
+      "loss": 0.8719,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000249,
+      "loss": 0.872,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00025199999999999995,
+      "loss": 0.8618,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00025499999999999996,
+      "loss": 0.8502,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000258,
+      "loss": 0.8855,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000261,
+      "loss": 0.8593,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00026399999999999997,
+      "loss": 0.878,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000267,
+      "loss": 0.8736,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00027,
+      "loss": 0.8757,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00027299999999999997,
+      "loss": 0.848,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000276,
+      "loss": 0.87,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000279,
+      "loss": 0.8922,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00028199999999999997,
+      "loss": 0.8581,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000285,
+      "loss": 0.8453,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00028799999999999995,
+      "loss": 0.8585,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00029099999999999997,
+      "loss": 0.8634,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000294,
+      "loss": 0.8409,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 0.8882,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8696,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029999199041570257,
+      "loss": 0.8779,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029996796251818966,
+      "loss": 0.8137,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029992791887350736,
+      "loss": 0.8419,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002998718637580951,
+      "loss": 0.8666,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002997998031583285,
+      "loss": 0.8451,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002997117447698802,
+      "loss": 0.875,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00029960769799689793,
+      "loss": 0.8658,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029948767395100045,
+      "loss": 0.8738,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002993516854500905,
+      "loss": 0.8324,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029919974701698635,
+      "loss": 0.8494,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029903187487787046,
+      "loss": 0.8624,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002988480869605567,
+      "loss": 0.8772,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002986484028925761,
+      "loss": 0.8527,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002984328439990804,
+      "loss": 0.8234,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002982014333005645,
+      "loss": 0.7951,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029795419551040833,
+      "loss": 0.8506,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029769115703223763,
+      "loss": 0.8084,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002974123459571039,
+      "loss": 0.8541,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029711779206048454,
+      "loss": 0.8425,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029680752679910315,
+      "loss": 0.8619,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029648158330756986,
+      "loss": 0.8502,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002961399963948431,
+      "loss": 0.8482,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002957828025405117,
+      "loss": 0.8647,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002954100398908995,
+      "loss": 0.8427,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00029502174825499146,
+      "loss": 0.8723,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000294617969100182,
+      "loss": 0.8716,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00029419874554784695,
+      "loss": 0.8385,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002937641223687379,
+      "loss": 0.841,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029331414597820145,
+      "loss": 0.838,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029284886443122214,
+      "loss": 0.8321,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029236832741729016,
+      "loss": 0.9036,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029187258625509513,
+      "loss": 0.8804,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002913616938870455,
+      "loss": 0.7992,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002908357048736144,
+      "loss": 0.8204,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029029467538751303,
+      "loss": 0.8584,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00028973866320769183,
+      "loss": 0.8478,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00028916772771316973,
+      "loss": 0.8135,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000288581929876693,
+      "loss": 0.8852,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0002879813322582237,
+      "loss": 0.8446,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028736599899825856,
+      "loss": 0.8527,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0002867359958109792,
+      "loss": 0.85,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028609138997723397,
+      "loss": 0.871,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028543225033735313,
+      "loss": 0.8208,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002847586472837968,
+      "loss": 0.8125,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00028407065275363753,
+      "loss": 0.8421,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002833683402208777,
+      "loss": 0.8677,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002826517846886033,
+      "loss": 0.8242,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00028192106268097334,
+      "loss": 0.8747,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002811762522350481,
+      "loss": 0.815,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.000280417432892455,
+      "loss": 0.8432,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002796446856908939,
+      "loss": 0.8256,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002788580931554828,
+      "loss": 0.856,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002780577392899446,
+      "loss": 0.8366,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00027724370956763603,
+      "loss": 0.8666,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002764160909224196,
+      "loss": 0.84,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00027557497173937923,
+      "loss": 0.8468,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0002747204418453818,
+      "loss": 0.8057,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00027385259249948333,
+      "loss": 0.8228,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.000272971516383184,
+      "loss": 0.8424,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00027207730759052924,
+      "loss": 0.8181,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002711700616180619,
+      "loss": 0.8378,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002702498753546232,
+      "loss": 0.8903,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00026931684707100586,
+      "loss": 0.8211,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026837107640945905,
+      "loss": 0.8213,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026741266437304716,
+      "loss": 0.811,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0002664417133148636,
+      "loss": 0.8481,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026545832692709964,
+      "loss": 0.8715,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00026446261022997097,
+      "loss": 0.8717,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00026345466956050176,
+      "loss": 0.8589,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0002624346125611689,
+      "loss": 0.8298,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.000261402548168406,
+      "loss": 0.859,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002603585866009697,
+      "loss": 0.8108,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002593028393481692,
+      "loss": 0.8591,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002582354191579593,
+      "loss": 0.8521,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00025715644002489996,
+      "loss": 0.8394,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025606601717798207,
+      "loss": 0.8457,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025496426706832193,
+      "loss": 0.8656,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002538513073567244,
+      "loss": 0.8678,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025272725690111806,
+      "loss": 0.8367,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00025159223574386114,
+      "loss": 0.8449,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00025044636509892227,
+      "loss": 0.8003,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00024928976733893494,
+      "loss": 0.8312,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002481225659821294,
+      "loss": 0.8567,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024694488567914106,
+      "loss": 0.872,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002457568521996988,
+      "loss": 0.8735,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024455859241919326,
+      "loss": 0.8571,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002433502343051274,
+      "loss": 0.8395,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024213190690345018,
+      "loss": 0.8439,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00024090374032477533,
+      "loss": 0.8661,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002396658657304861,
+      "loss": 0.8679,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00023841841531872798,
+      "loss": 0.8151,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00023716152231029072,
+      "loss": 0.8517,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.000235895320934381,
+      "loss": 0.8591,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00023461994641428766,
+      "loss": 0.8638,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002333355349529403,
+      "loss": 0.8512,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00023204222371836405,
+      "loss": 0.835,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00023074015082903015,
+      "loss": 0.8611,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002294294553391063,
+      "loss": 0.7981,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022811027722360598,
+      "loss": 0.84,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022678275736344014,
+      "loss": 0.8008,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022544703753037178,
+      "loss": 0.8333,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022410326037187558,
+      "loss": 0.8197,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022275156939590392,
+      "loss": 0.8408,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022139210895556104,
+      "loss": 0.8608,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022002502423368678,
+      "loss": 0.8705,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002186504612273522,
+      "loss": 0.8388,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002172685667322676,
+      "loss": 0.8779,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00021587948832710554,
+      "loss": 0.8314,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002144833743577405,
+      "loss": 0.8249,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002130803739214061,
+      "loss": 0.8312,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00021167063685077262,
+      "loss": 0.8003,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002102543136979454,
+      "loss": 0.8513,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020883155571838692,
+      "loss": 0.835,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020740251485476345,
+      "loss": 0.8981,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020596734372071852,
+      "loss": 0.8353,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020452619558457446,
+      "loss": 0.8457,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00020307922435296443,
+      "loss": 0.8225,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002016265845543958,
+      "loss": 0.8342,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00020016843132274746,
+      "loss": 0.807,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00019870492038070252,
+      "loss": 0.8271,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019723620802311774,
+      "loss": 0.8731,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019576245110033231,
+      "loss": 0.8436,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019428380700141698,
+      "loss": 0.8816,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019280043363736579,
+      "loss": 0.8281,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0001913124894242322,
+      "loss": 0.8413,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018982013326621083,
+      "loss": 0.8318,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018832352453866777,
+      "loss": 0.8394,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018682282307111987,
+      "loss": 0.819,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018531818913016584,
+      "loss": 0.8598,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018380978340237092,
+      "loss": 0.8346,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018229776697710617,
+      "loss": 0.8523,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018078230132934512,
+      "loss": 0.8461,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017926354830241924,
+      "loss": 0.8368,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017774167009073377,
+      "loss": 0.8336,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017621682922244633,
+      "loss": 0.8049,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017468918854211007,
+      "loss": 0.8245,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001731589111932823,
+      "loss": 0.8474,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000171626160601102,
+      "loss": 0.8643,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001700911004548369,
+      "loss": 0.8448,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00016855389469040217,
+      "loss": 0.8822,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016701470747285317,
+      "loss": 0.8225,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016547370317885354,
+      "loss": 0.8269,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0001639310463791205,
+      "loss": 0.8365,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016238690182084986,
+      "loss": 0.8265,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016084143441012156,
+      "loss": 0.8439,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001592948091942892,
+      "loss": 0.8438,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001577471913443532,
+      "loss": 0.8595,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00015619874613732196,
+      "loss": 0.8313,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001546496389385611,
+      "loss": 0.8258,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015310003518413315,
+      "loss": 0.7778,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015155010036313008,
+      "loss": 0.8442,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015,
+      "loss": 0.8477,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014844989963686992,
+      "loss": 0.8447,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014689996481586688,
+      "loss": 0.8424,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014535036106143892,
+      "loss": 0.8357,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000143801253862678,
+      "loss": 0.8467,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001422528086556468,
+      "loss": 0.8105,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001407051908057108,
+      "loss": 0.8215,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001391585655898784,
+      "loss": 0.8452,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00013761309817915014,
+      "loss": 0.7967,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013606895362087949,
+      "loss": 0.8172,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013452629682114646,
+      "loss": 0.8837,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013298529252714684,
+      "loss": 0.8293,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013144610530959784,
+      "loss": 0.8493,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001299088995451631,
+      "loss": 0.7906,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012837383939889798,
+      "loss": 0.8201,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012684108880671772,
+      "loss": 0.7947,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012531081145788987,
+      "loss": 0.8238,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012378317077755362,
+      "loss": 0.8417,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012225832990926623,
+      "loss": 0.8728,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012073645169758076,
+      "loss": 0.798,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00011921769867065485,
+      "loss": 0.8053,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011770223302289385,
+      "loss": 0.7943,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001161902165976291,
+      "loss": 0.8407,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011468181086983412,
+      "loss": 0.8326,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011317717692888012,
+      "loss": 0.8355,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0001116764754613322,
+      "loss": 0.8015,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00011017986673378918,
+      "loss": 0.8426,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010868751057576782,
+      "loss": 0.858,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010719956636263423,
+      "loss": 0.8268,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010571619299858303,
+      "loss": 0.8244,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010423754889966769,
+      "loss": 0.8328,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010276379197688222,
+      "loss": 0.8201,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010129507961929748,
+      "loss": 0.804,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.983156867725255e-05,
+      "loss": 0.8273,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.837341544560423e-05,
+      "loss": 0.8222,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.692077564703555e-05,
+      "loss": 0.828,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.547380441542549e-05,
+      "loss": 0.8507,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.403265627928147e-05,
+      "loss": 0.8044,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.259748514523653e-05,
+      "loss": 0.8202,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.116844428161309e-05,
+      "loss": 0.7773,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.97456863020546e-05,
+      "loss": 0.8119,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.83293631492274e-05,
+      "loss": 0.8274,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.691962607859386e-05,
+      "loss": 0.8167,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.55166256422595e-05,
+      "loss": 0.8389,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.412051167289446e-05,
+      "loss": 0.8091,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.27314332677324e-05,
+      "loss": 0.8418,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.134953877264778e-05,
+      "loss": 0.8105,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.997497576631323e-05,
+      "loss": 0.8409,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.860789104443896e-05,
+      "loss": 0.8429,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.724843060409606e-05,
+      "loss": 0.8175,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.589673962812442e-05,
+      "loss": 0.8115,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.455296246962823e-05,
+      "loss": 0.846,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.321724263655988e-05,
+      "loss": 0.8175,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.188972277639405e-05,
+      "loss": 0.8177,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.057054466089371e-05,
+      "loss": 0.8441,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.925984917096985e-05,
+      "loss": 0.8272,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.795777628163599e-05,
+      "loss": 0.8525,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.66644650470597e-05,
+      "loss": 0.8533,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.538005358571234e-05,
+      "loss": 0.8436,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.410467906561896e-05,
+      "loss": 0.832,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.283847768970926e-05,
+      "loss": 0.7897,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.158158468127196e-05,
+      "loss": 0.824,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.0334134269513865e-05,
+      "loss": 0.8435,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.9096259675224647e-05,
+      "loss": 0.8233,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.786809309654982e-05,
+      "loss": 0.8333,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.664976569487263e-05,
+      "loss": 0.8658,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.5441407580806745e-05,
+      "loss": 0.8229,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.4243147800301134e-05,
+      "loss": 0.7847,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.305511432085884e-05,
+      "loss": 0.7924,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.187743401787054e-05,
+      "loss": 0.8458,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.071023266106502e-05,
+      "loss": 0.8492,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.955363490107777e-05,
+      "loss": 0.8584,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.840776425613886e-05,
+      "loss": 0.8262,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.727274309888191e-05,
+      "loss": 0.8299,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.614869264327553e-05,
+      "loss": 0.8267,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.503573293167805e-05,
+      "loss": 0.8352,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.3933982822017876e-05,
+      "loss": 0.8181,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.284355997510003e-05,
+      "loss": 0.8091,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.17645808420407e-05,
+      "loss": 0.8123,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.0697160651830814e-05,
+      "loss": 0.8075,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.964141339903026e-05,
+      "loss": 0.8576,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.8597451831594014e-05,
+      "loss": 0.8134,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.756538743883111e-05,
+      "loss": 0.8384,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.654533043949823e-05,
+      "loss": 0.8061,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.5537389770029046e-05,
+      "loss": 0.8438,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.454167307290036e-05,
+      "loss": 0.8024,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.3558286685136384e-05,
+      "loss": 0.8332,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.258733562695283e-05,
+      "loss": 0.8247,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.162892359054098e-05,
+      "loss": 0.8482,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.0683152928994105e-05,
+      "loss": 0.8171,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.9750124645376755e-05,
+      "loss": 0.8296,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.8829938381938117e-05,
+      "loss": 0.8403,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.792269240947076e-05,
+      "loss": 0.8472,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.702848361681605e-05,
+      "loss": 0.8305,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.6147407500516643e-05,
+      "loss": 0.8491,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.5279558154618197e-05,
+      "loss": 0.8299,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.4425028260620715e-05,
+      "loss": 0.8329,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.35839090775804e-05,
+      "loss": 0.8234,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.2756290432363957e-05,
+      "loss": 0.8197,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.1942260710055386e-05,
+      "loss": 0.8238,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.1141906844517203e-05,
+      "loss": 0.8051,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.0355314309106097e-05,
+      "loss": 0.8269,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.9582567107544962e-05,
+      "loss": 0.8325,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.882374776495187e-05,
+      "loss": 0.843,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.8078937319026654e-05,
+      "loss": 0.8352,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.734821531139667e-05,
+      "loss": 0.8756,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.663165977912221e-05,
+      "loss": 0.8193,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.5929347246362452e-05,
+      "loss": 0.8123,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.524135271620317e-05,
+      "loss": 0.807,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.456774966264685e-05,
+      "loss": 0.878,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.390861002276602e-05,
+      "loss": 0.8185,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.3264004189020777e-05,
+      "loss": 0.7939,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2634001001741373e-05,
+      "loss": 0.8163,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2018667741776266e-05,
+      "loss": 0.8429,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1418070123306989e-05,
+      "loss": 0.8292,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0832272286830285e-05,
+      "loss": 0.8241,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0261336792308167e-05,
+      "loss": 0.8438,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.705324612486936e-06,
+      "loss": 0.8631,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.164295126385562e-06,
+      "loss": 0.8359,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.638306112954452e-06,
+      "loss": 0.8304,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.127413744904804e-06,
+      "loss": 0.7995,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.631672582709808e-06,
+      "loss": 0.817,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.151135568777838e-06,
+      "loss": 0.8264,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.685854021798509e-06,
+      "loss": 0.8166,
+      "step": 375
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.214459938342994e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_SGD_Cosine/checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33222dfbebfe89abc6dfd2eda90df0b1c95c9ba8141e3518b9034d169c7a3c7
+size 5048

llama2_7b_SGD_Cosine/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_SGD_Cosine/checkpoint-400/adapter_config.json

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

llama2_7b_SGD_Cosine/checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860abd1d0427e526014005336cc4ace67500959fddb39857451167baf51aaf94
+size 8397056

llama2_7b_SGD_Cosine/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dfe41529bd1ca726c11c1351cbfbe6d1a6b7ce3fd1a3b8326baaa3ba25b04e
+size 16831290

llama2_7b_SGD_Cosine/checkpoint-400/rng_state.pth

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

llama2_7b_SGD_Cosine/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8790f05ffac6b12369fbd3dd7909021c14f6589551079c9012e0d1d5063c8ad
+size 1064

llama2_7b_SGD_Cosine/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": 2.9999999999999997e-06,
+      "loss": 1.8153,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 1.7198,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-06,
+      "loss": 1.8135,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 1.91,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 1.8073,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 1.848,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.1e-05,
+      "loss": 1.8294,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 1.9358,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 1.98,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.8625,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 1.8559,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 1.7621,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.9e-05,
+      "loss": 1.7816,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.2e-05,
+      "loss": 1.8272,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 1.8546,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 1.6863,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.1e-05,
+      "loss": 1.6002,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 1.7753,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 1.8031,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.7884,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.299999999999999e-05,
+      "loss": 1.6288,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.599999999999999e-05,
+      "loss": 1.672,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 6.9e-05,
+      "loss": 1.6625,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 1.6373,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.5e-05,
+      "loss": 1.5654,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.8e-05,
+      "loss": 1.5128,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.1e-05,
+      "loss": 1.5769,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.4e-05,
+      "loss": 1.4986,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 1.514,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.4492,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.3e-05,
+      "loss": 1.437,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.599999999999999e-05,
+      "loss": 1.4183,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.9e-05,
+      "loss": 1.3496,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000102,
+      "loss": 1.3538,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010499999999999999,
+      "loss": 1.2837,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010799999999999998,
+      "loss": 1.2471,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 1.2154,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.1819,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000117,
+      "loss": 1.16,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.1309,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00012299999999999998,
+      "loss": 1.1511,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 1.0796,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000129,
+      "loss": 1.0747,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013199999999999998,
+      "loss": 1.0301,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000135,
+      "loss": 1.0205,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000138,
+      "loss": 1.05,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014099999999999998,
+      "loss": 1.0128,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 1.0066,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000147,
+      "loss": 0.9924,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00015,
+      "loss": 1.0251,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00015299999999999998,
+      "loss": 0.9605,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000156,
+      "loss": 0.9755,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000159,
+      "loss": 0.9642,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000162,
+      "loss": 0.9631,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000165,
+      "loss": 0.9736,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000168,
+      "loss": 0.9673,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017099999999999998,
+      "loss": 1.0058,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017399999999999997,
+      "loss": 0.9245,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 0.8959,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.8951,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00018299999999999998,
+      "loss": 0.9796,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000186,
+      "loss": 0.9347,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00018899999999999999,
+      "loss": 0.8796,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019199999999999998,
+      "loss": 0.8916,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000195,
+      "loss": 0.8951,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000198,
+      "loss": 0.8821,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000201,
+      "loss": 0.8916,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000204,
+      "loss": 0.94,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 0.8569,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.8929,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021299999999999997,
+      "loss": 0.8895,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021599999999999996,
+      "loss": 0.8258,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021899999999999998,
+      "loss": 0.885,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00022199999999999998,
+      "loss": 0.8788,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000225,
+      "loss": 0.8865,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.8757,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00023099999999999998,
+      "loss": 0.8821,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000234,
+      "loss": 0.8786,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000237,
+      "loss": 0.8665,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.8617,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000243,
+      "loss": 0.8288,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00024599999999999996,
+      "loss": 0.8719,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000249,
+      "loss": 0.872,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00025199999999999995,
+      "loss": 0.8618,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00025499999999999996,
+      "loss": 0.8502,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000258,
+      "loss": 0.8855,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000261,
+      "loss": 0.8593,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00026399999999999997,
+      "loss": 0.878,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000267,
+      "loss": 0.8736,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00027,
+      "loss": 0.8757,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00027299999999999997,
+      "loss": 0.848,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000276,
+      "loss": 0.87,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000279,
+      "loss": 0.8922,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00028199999999999997,
+      "loss": 0.8581,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000285,
+      "loss": 0.8453,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00028799999999999995,
+      "loss": 0.8585,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00029099999999999997,
+      "loss": 0.8634,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000294,
+      "loss": 0.8409,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 0.8882,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8696,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029999199041570257,
+      "loss": 0.8779,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029996796251818966,
+      "loss": 0.8137,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029992791887350736,
+      "loss": 0.8419,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002998718637580951,
+      "loss": 0.8666,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002997998031583285,
+      "loss": 0.8451,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002997117447698802,
+      "loss": 0.875,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00029960769799689793,
+      "loss": 0.8658,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029948767395100045,
+      "loss": 0.8738,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002993516854500905,
+      "loss": 0.8324,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029919974701698635,
+      "loss": 0.8494,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029903187487787046,
+      "loss": 0.8624,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002988480869605567,
+      "loss": 0.8772,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002986484028925761,
+      "loss": 0.8527,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002984328439990804,
+      "loss": 0.8234,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002982014333005645,
+      "loss": 0.7951,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029795419551040833,
+      "loss": 0.8506,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029769115703223763,
+      "loss": 0.8084,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002974123459571039,
+      "loss": 0.8541,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029711779206048454,
+      "loss": 0.8425,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029680752679910315,
+      "loss": 0.8619,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029648158330756986,
+      "loss": 0.8502,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002961399963948431,
+      "loss": 0.8482,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002957828025405117,
+      "loss": 0.8647,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002954100398908995,
+      "loss": 0.8427,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00029502174825499146,
+      "loss": 0.8723,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000294617969100182,
+      "loss": 0.8716,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00029419874554784695,
+      "loss": 0.8385,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002937641223687379,
+      "loss": 0.841,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029331414597820145,
+      "loss": 0.838,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029284886443122214,
+      "loss": 0.8321,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029236832741729016,
+      "loss": 0.9036,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029187258625509513,
+      "loss": 0.8804,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002913616938870455,
+      "loss": 0.7992,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002908357048736144,
+      "loss": 0.8204,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029029467538751303,
+      "loss": 0.8584,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00028973866320769183,
+      "loss": 0.8478,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00028916772771316973,
+      "loss": 0.8135,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000288581929876693,
+      "loss": 0.8852,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0002879813322582237,
+      "loss": 0.8446,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028736599899825856,
+      "loss": 0.8527,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0002867359958109792,
+      "loss": 0.85,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028609138997723397,
+      "loss": 0.871,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028543225033735313,
+      "loss": 0.8208,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002847586472837968,
+      "loss": 0.8125,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00028407065275363753,
+      "loss": 0.8421,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002833683402208777,
+      "loss": 0.8677,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002826517846886033,
+      "loss": 0.8242,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00028192106268097334,
+      "loss": 0.8747,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002811762522350481,
+      "loss": 0.815,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.000280417432892455,
+      "loss": 0.8432,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002796446856908939,
+      "loss": 0.8256,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002788580931554828,
+      "loss": 0.856,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002780577392899446,
+      "loss": 0.8366,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00027724370956763603,
+      "loss": 0.8666,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002764160909224196,
+      "loss": 0.84,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00027557497173937923,
+      "loss": 0.8468,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0002747204418453818,
+      "loss": 0.8057,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00027385259249948333,
+      "loss": 0.8228,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.000272971516383184,
+      "loss": 0.8424,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00027207730759052924,
+      "loss": 0.8181,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002711700616180619,
+      "loss": 0.8378,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002702498753546232,
+      "loss": 0.8903,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00026931684707100586,
+      "loss": 0.8211,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026837107640945905,
+      "loss": 0.8213,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026741266437304716,
+      "loss": 0.811,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0002664417133148636,
+      "loss": 0.8481,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026545832692709964,
+      "loss": 0.8715,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00026446261022997097,
+      "loss": 0.8717,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00026345466956050176,
+      "loss": 0.8589,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0002624346125611689,
+      "loss": 0.8298,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.000261402548168406,
+      "loss": 0.859,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002603585866009697,
+      "loss": 0.8108,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002593028393481692,
+      "loss": 0.8591,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002582354191579593,
+      "loss": 0.8521,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00025715644002489996,
+      "loss": 0.8394,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025606601717798207,
+      "loss": 0.8457,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025496426706832193,
+      "loss": 0.8656,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002538513073567244,
+      "loss": 0.8678,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025272725690111806,
+      "loss": 0.8367,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00025159223574386114,
+      "loss": 0.8449,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00025044636509892227,
+      "loss": 0.8003,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00024928976733893494,
+      "loss": 0.8312,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002481225659821294,
+      "loss": 0.8567,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024694488567914106,
+      "loss": 0.872,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002457568521996988,
+      "loss": 0.8735,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024455859241919326,
+      "loss": 0.8571,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002433502343051274,
+      "loss": 0.8395,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024213190690345018,
+      "loss": 0.8439,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00024090374032477533,
+      "loss": 0.8661,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002396658657304861,
+      "loss": 0.8679,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00023841841531872798,
+      "loss": 0.8151,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00023716152231029072,
+      "loss": 0.8517,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.000235895320934381,
+      "loss": 0.8591,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00023461994641428766,
+      "loss": 0.8638,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002333355349529403,
+      "loss": 0.8512,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00023204222371836405,
+      "loss": 0.835,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00023074015082903015,
+      "loss": 0.8611,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002294294553391063,
+      "loss": 0.7981,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022811027722360598,
+      "loss": 0.84,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022678275736344014,
+      "loss": 0.8008,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022544703753037178,
+      "loss": 0.8333,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022410326037187558,
+      "loss": 0.8197,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022275156939590392,
+      "loss": 0.8408,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022139210895556104,
+      "loss": 0.8608,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022002502423368678,
+      "loss": 0.8705,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002186504612273522,
+      "loss": 0.8388,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002172685667322676,
+      "loss": 0.8779,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00021587948832710554,
+      "loss": 0.8314,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002144833743577405,
+      "loss": 0.8249,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002130803739214061,
+      "loss": 0.8312,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00021167063685077262,
+      "loss": 0.8003,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002102543136979454,
+      "loss": 0.8513,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020883155571838692,
+      "loss": 0.835,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020740251485476345,
+      "loss": 0.8981,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020596734372071852,
+      "loss": 0.8353,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020452619558457446,
+      "loss": 0.8457,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00020307922435296443,
+      "loss": 0.8225,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002016265845543958,
+      "loss": 0.8342,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00020016843132274746,
+      "loss": 0.807,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00019870492038070252,
+      "loss": 0.8271,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019723620802311774,
+      "loss": 0.8731,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019576245110033231,
+      "loss": 0.8436,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019428380700141698,
+      "loss": 0.8816,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019280043363736579,
+      "loss": 0.8281,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0001913124894242322,
+      "loss": 0.8413,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018982013326621083,
+      "loss": 0.8318,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018832352453866777,
+      "loss": 0.8394,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018682282307111987,
+      "loss": 0.819,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018531818913016584,
+      "loss": 0.8598,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018380978340237092,
+      "loss": 0.8346,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018229776697710617,
+      "loss": 0.8523,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018078230132934512,
+      "loss": 0.8461,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017926354830241924,
+      "loss": 0.8368,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017774167009073377,
+      "loss": 0.8336,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017621682922244633,
+      "loss": 0.8049,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017468918854211007,
+      "loss": 0.8245,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001731589111932823,
+      "loss": 0.8474,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000171626160601102,
+      "loss": 0.8643,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001700911004548369,
+      "loss": 0.8448,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00016855389469040217,
+      "loss": 0.8822,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016701470747285317,
+      "loss": 0.8225,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016547370317885354,
+      "loss": 0.8269,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0001639310463791205,
+      "loss": 0.8365,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016238690182084986,
+      "loss": 0.8265,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016084143441012156,
+      "loss": 0.8439,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001592948091942892,
+      "loss": 0.8438,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001577471913443532,
+      "loss": 0.8595,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00015619874613732196,
+      "loss": 0.8313,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001546496389385611,
+      "loss": 0.8258,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015310003518413315,
+      "loss": 0.7778,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015155010036313008,
+      "loss": 0.8442,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015,
+      "loss": 0.8477,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014844989963686992,
+      "loss": 0.8447,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014689996481586688,
+      "loss": 0.8424,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014535036106143892,
+      "loss": 0.8357,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000143801253862678,
+      "loss": 0.8467,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001422528086556468,
+      "loss": 0.8105,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001407051908057108,
+      "loss": 0.8215,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001391585655898784,
+      "loss": 0.8452,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00013761309817915014,
+      "loss": 0.7967,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013606895362087949,
+      "loss": 0.8172,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013452629682114646,
+      "loss": 0.8837,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013298529252714684,
+      "loss": 0.8293,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013144610530959784,
+      "loss": 0.8493,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001299088995451631,
+      "loss": 0.7906,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012837383939889798,
+      "loss": 0.8201,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012684108880671772,
+      "loss": 0.7947,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012531081145788987,
+      "loss": 0.8238,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012378317077755362,
+      "loss": 0.8417,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012225832990926623,
+      "loss": 0.8728,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012073645169758076,
+      "loss": 0.798,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00011921769867065485,
+      "loss": 0.8053,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011770223302289385,
+      "loss": 0.7943,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001161902165976291,
+      "loss": 0.8407,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011468181086983412,
+      "loss": 0.8326,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011317717692888012,
+      "loss": 0.8355,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0001116764754613322,
+      "loss": 0.8015,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00011017986673378918,
+      "loss": 0.8426,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010868751057576782,
+      "loss": 0.858,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010719956636263423,
+      "loss": 0.8268,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010571619299858303,
+      "loss": 0.8244,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010423754889966769,
+      "loss": 0.8328,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010276379197688222,
+      "loss": 0.8201,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010129507961929748,
+      "loss": 0.804,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.983156867725255e-05,
+      "loss": 0.8273,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.837341544560423e-05,
+      "loss": 0.8222,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.692077564703555e-05,
+      "loss": 0.828,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.547380441542549e-05,
+      "loss": 0.8507,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.403265627928147e-05,
+      "loss": 0.8044,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.259748514523653e-05,
+      "loss": 0.8202,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.116844428161309e-05,
+      "loss": 0.7773,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.97456863020546e-05,
+      "loss": 0.8119,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.83293631492274e-05,
+      "loss": 0.8274,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.691962607859386e-05,
+      "loss": 0.8167,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.55166256422595e-05,
+      "loss": 0.8389,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.412051167289446e-05,
+      "loss": 0.8091,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.27314332677324e-05,
+      "loss": 0.8418,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.134953877264778e-05,
+      "loss": 0.8105,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.997497576631323e-05,
+      "loss": 0.8409,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.860789104443896e-05,
+      "loss": 0.8429,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.724843060409606e-05,
+      "loss": 0.8175,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.589673962812442e-05,
+      "loss": 0.8115,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.455296246962823e-05,
+      "loss": 0.846,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.321724263655988e-05,
+      "loss": 0.8175,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.188972277639405e-05,
+      "loss": 0.8177,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.057054466089371e-05,
+      "loss": 0.8441,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.925984917096985e-05,
+      "loss": 0.8272,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.795777628163599e-05,
+      "loss": 0.8525,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.66644650470597e-05,
+      "loss": 0.8533,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.538005358571234e-05,
+      "loss": 0.8436,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.410467906561896e-05,
+      "loss": 0.832,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.283847768970926e-05,
+      "loss": 0.7897,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.158158468127196e-05,
+      "loss": 0.824,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.0334134269513865e-05,
+      "loss": 0.8435,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.9096259675224647e-05,
+      "loss": 0.8233,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.786809309654982e-05,
+      "loss": 0.8333,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.664976569487263e-05,
+      "loss": 0.8658,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.5441407580806745e-05,
+      "loss": 0.8229,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.4243147800301134e-05,
+      "loss": 0.7847,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.305511432085884e-05,
+      "loss": 0.7924,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.187743401787054e-05,
+      "loss": 0.8458,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.071023266106502e-05,
+      "loss": 0.8492,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.955363490107777e-05,
+      "loss": 0.8584,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.840776425613886e-05,
+      "loss": 0.8262,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.727274309888191e-05,
+      "loss": 0.8299,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.614869264327553e-05,
+      "loss": 0.8267,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.503573293167805e-05,
+      "loss": 0.8352,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.3933982822017876e-05,
+      "loss": 0.8181,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.284355997510003e-05,
+      "loss": 0.8091,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.17645808420407e-05,
+      "loss": 0.8123,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.0697160651830814e-05,
+      "loss": 0.8075,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.964141339903026e-05,
+      "loss": 0.8576,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.8597451831594014e-05,
+      "loss": 0.8134,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.756538743883111e-05,
+      "loss": 0.8384,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.654533043949823e-05,
+      "loss": 0.8061,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.5537389770029046e-05,
+      "loss": 0.8438,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.454167307290036e-05,
+      "loss": 0.8024,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.3558286685136384e-05,
+      "loss": 0.8332,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.258733562695283e-05,
+      "loss": 0.8247,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.162892359054098e-05,
+      "loss": 0.8482,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.0683152928994105e-05,
+      "loss": 0.8171,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.9750124645376755e-05,
+      "loss": 0.8296,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.8829938381938117e-05,
+      "loss": 0.8403,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.792269240947076e-05,
+      "loss": 0.8472,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.702848361681605e-05,
+      "loss": 0.8305,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.6147407500516643e-05,
+      "loss": 0.8491,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.5279558154618197e-05,
+      "loss": 0.8299,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.4425028260620715e-05,
+      "loss": 0.8329,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.35839090775804e-05,
+      "loss": 0.8234,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.2756290432363957e-05,
+      "loss": 0.8197,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.1942260710055386e-05,
+      "loss": 0.8238,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.1141906844517203e-05,
+      "loss": 0.8051,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.0355314309106097e-05,
+      "loss": 0.8269,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.9582567107544962e-05,
+      "loss": 0.8325,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.882374776495187e-05,
+      "loss": 0.843,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.8078937319026654e-05,
+      "loss": 0.8352,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.734821531139667e-05,
+      "loss": 0.8756,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.663165977912221e-05,
+      "loss": 0.8193,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.5929347246362452e-05,
+      "loss": 0.8123,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.524135271620317e-05,
+      "loss": 0.807,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.456774966264685e-05,
+      "loss": 0.878,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.390861002276602e-05,
+      "loss": 0.8185,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.3264004189020777e-05,
+      "loss": 0.7939,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2634001001741373e-05,
+      "loss": 0.8163,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2018667741776266e-05,
+      "loss": 0.8429,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1418070123306989e-05,
+      "loss": 0.8292,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0832272286830285e-05,
+      "loss": 0.8241,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0261336792308167e-05,
+      "loss": 0.8438,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.705324612486936e-06,
+      "loss": 0.8631,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.164295126385562e-06,
+      "loss": 0.8359,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.638306112954452e-06,
+      "loss": 0.8304,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.127413744904804e-06,
+      "loss": 0.7995,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.631672582709808e-06,
+      "loss": 0.817,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.151135568777838e-06,
+      "loss": 0.8264,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.685854021798509e-06,
+      "loss": 0.8166,
+      "step": 375
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.235877631262093e-06,
+      "loss": 0.8215,
+      "step": 376
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.801254452153081e-06,
+      "loss": 0.8611,
+      "step": 377
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.3820308998179575e-06,
+      "loss": 0.8002,
+      "step": 378
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.978251745008527e-06,
+      "loss": 0.8199,
+      "step": 379
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.589960109100444e-06,
+      "loss": 0.8412,
+      "step": 380
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.217197459488292e-06,
+      "loss": 0.8421,
+      "step": 381
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.86000360515688e-06,
+      "loss": 0.8425,
+      "step": 382
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.518416692430076e-06,
+      "loss": 0.8426,
+      "step": 383
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.192473200896828e-06,
+      "loss": 0.833,
+      "step": 384
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.882207939515435e-06,
+      "loss": 0.825,
+      "step": 385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.587654042896087e-06,
+      "loss": 0.8433,
+      "step": 386
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.3088429677623423e-06,
+      "loss": 0.8065,
+      "step": 387
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.0458044895916513e-06,
+      "loss": 0.789,
+      "step": 388
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.7985666994355164e-06,
+      "loss": 0.8071,
+      "step": 389
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5671560009195894e-06,
+      "loss": 0.8675,
+      "step": 390
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.351597107423813e-06,
+      "loss": 0.8259,
+      "step": 391
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.1519130394432474e-06,
+      "loss": 0.8523,
+      "step": 392
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.681251221295539e-07,
+      "loss": 0.8201,
+      "step": 393
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.002529830136162e-07,
+      "loss": 0.8393,
+      "step": 394
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 6.483145499094344e-07,
+      "loss": 0.8057,
+      "step": 395
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 5.123260489995229e-07,
+      "loss": 0.8385,
+      "step": 396
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.923020031020296e-07,
+      "loss": 0.841,
+      "step": 397
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.8825523011977715e-07,
+      "loss": 0.834,
+      "step": 398
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.001968416714572e-07,
+      "loss": 0.8385,
+      "step": 399
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.2813624190484705e-07,
+      "loss": 0.8088,
+      "step": 400
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.495223430237389e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_SGD_Cosine/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33222dfbebfe89abc6dfd2eda90df0b1c95c9ba8141e3518b9034d169c7a3c7
+size 5048

llama2_7b_SGD_Cosine/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.9254943004043976,
+    "train_runtime": 17197.3779,
+    "train_samples_per_second": 3.01,
+    "train_steps_per_second": 0.023
+}

llama2_7b_SGD_Cosine/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": 2.9999999999999997e-06,
+      "loss": 1.8153,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.999999999999999e-06,
+      "loss": 1.7198,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-06,
+      "loss": 1.8135,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1999999999999999e-05,
+      "loss": 1.91,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4999999999999999e-05,
+      "loss": 1.8073,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7999999999999997e-05,
+      "loss": 1.848,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.1e-05,
+      "loss": 1.8294,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3999999999999997e-05,
+      "loss": 1.9358,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.6999999999999996e-05,
+      "loss": 1.98,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.8625,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.2999999999999996e-05,
+      "loss": 1.8559,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.5999999999999994e-05,
+      "loss": 1.7621,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.9e-05,
+      "loss": 1.7816,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.2e-05,
+      "loss": 1.8272,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.4999999999999996e-05,
+      "loss": 1.8546,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.7999999999999994e-05,
+      "loss": 1.6863,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.1e-05,
+      "loss": 1.6002,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.399999999999999e-05,
+      "loss": 1.7753,
+      "step": 18
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 1.8031,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.7884,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.299999999999999e-05,
+      "loss": 1.6288,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 6.599999999999999e-05,
+      "loss": 1.672,
+      "step": 22
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 6.9e-05,
+      "loss": 1.6625,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.199999999999999e-05,
+      "loss": 1.6373,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.5e-05,
+      "loss": 1.5654,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 7.8e-05,
+      "loss": 1.5128,
+      "step": 26
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.1e-05,
+      "loss": 1.5769,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.4e-05,
+      "loss": 1.4986,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.699999999999999e-05,
+      "loss": 1.514,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.4492,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.3e-05,
+      "loss": 1.437,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.599999999999999e-05,
+      "loss": 1.4183,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.9e-05,
+      "loss": 1.3496,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.000102,
+      "loss": 1.3538,
+      "step": 34
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010499999999999999,
+      "loss": 1.2837,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00010799999999999998,
+      "loss": 1.2471,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011099999999999999,
+      "loss": 1.2154,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 1.1819,
+      "step": 38
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000117,
+      "loss": 1.16,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.1309,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00012299999999999998,
+      "loss": 1.1511,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00012599999999999997,
+      "loss": 1.0796,
+      "step": 42
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000129,
+      "loss": 1.0747,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013199999999999998,
+      "loss": 1.0301,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000135,
+      "loss": 1.0205,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.000138,
+      "loss": 1.05,
+      "step": 46
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014099999999999998,
+      "loss": 1.0128,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00014399999999999998,
+      "loss": 1.0066,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.000147,
+      "loss": 0.9924,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00015,
+      "loss": 1.0251,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00015299999999999998,
+      "loss": 0.9605,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000156,
+      "loss": 0.9755,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000159,
+      "loss": 0.9642,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000162,
+      "loss": 0.9631,
+      "step": 54
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000165,
+      "loss": 0.9736,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000168,
+      "loss": 0.9673,
+      "step": 56
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017099999999999998,
+      "loss": 1.0058,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00017399999999999997,
+      "loss": 0.9245,
+      "step": 58
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017699999999999997,
+      "loss": 0.8959,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.8951,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00018299999999999998,
+      "loss": 0.9796,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000186,
+      "loss": 0.9347,
+      "step": 62
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00018899999999999999,
+      "loss": 0.8796,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019199999999999998,
+      "loss": 0.8916,
+      "step": 64
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000195,
+      "loss": 0.8951,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.000198,
+      "loss": 0.8821,
+      "step": 66
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000201,
+      "loss": 0.8916,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000204,
+      "loss": 0.94,
+      "step": 68
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00020699999999999996,
+      "loss": 0.8569,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.8929,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021299999999999997,
+      "loss": 0.8895,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021599999999999996,
+      "loss": 0.8258,
+      "step": 72
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00021899999999999998,
+      "loss": 0.885,
+      "step": 73
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00022199999999999998,
+      "loss": 0.8788,
+      "step": 74
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000225,
+      "loss": 0.8865,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00022799999999999999,
+      "loss": 0.8757,
+      "step": 76
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00023099999999999998,
+      "loss": 0.8821,
+      "step": 77
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.000234,
+      "loss": 0.8786,
+      "step": 78
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000237,
+      "loss": 0.8665,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.8617,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000243,
+      "loss": 0.8288,
+      "step": 81
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00024599999999999996,
+      "loss": 0.8719,
+      "step": 82
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000249,
+      "loss": 0.872,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00025199999999999995,
+      "loss": 0.8618,
+      "step": 84
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00025499999999999996,
+      "loss": 0.8502,
+      "step": 85
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000258,
+      "loss": 0.8855,
+      "step": 86
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000261,
+      "loss": 0.8593,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00026399999999999997,
+      "loss": 0.878,
+      "step": 88
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000267,
+      "loss": 0.8736,
+      "step": 89
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00027,
+      "loss": 0.8757,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00027299999999999997,
+      "loss": 0.848,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000276,
+      "loss": 0.87,
+      "step": 92
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000279,
+      "loss": 0.8922,
+      "step": 93
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00028199999999999997,
+      "loss": 0.8581,
+      "step": 94
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.000285,
+      "loss": 0.8453,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00028799999999999995,
+      "loss": 0.8585,
+      "step": 96
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00029099999999999997,
+      "loss": 0.8634,
+      "step": 97
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000294,
+      "loss": 0.8409,
+      "step": 98
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00029699999999999996,
+      "loss": 0.8882,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0003,
+      "loss": 0.8696,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029999199041570257,
+      "loss": 0.8779,
+      "step": 101
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029996796251818966,
+      "loss": 0.8137,
+      "step": 102
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00029992791887350736,
+      "loss": 0.8419,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002998718637580951,
+      "loss": 0.8666,
+      "step": 104
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002997998031583285,
+      "loss": 0.8451,
+      "step": 105
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0002997117447698802,
+      "loss": 0.875,
+      "step": 106
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00029960769799689793,
+      "loss": 0.8658,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029948767395100045,
+      "loss": 0.8738,
+      "step": 108
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002993516854500905,
+      "loss": 0.8324,
+      "step": 109
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029919974701698635,
+      "loss": 0.8494,
+      "step": 110
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00029903187487787046,
+      "loss": 0.8624,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002988480869605567,
+      "loss": 0.8772,
+      "step": 112
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002986484028925761,
+      "loss": 0.8527,
+      "step": 113
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002984328439990804,
+      "loss": 0.8234,
+      "step": 114
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002982014333005645,
+      "loss": 0.7951,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029795419551040833,
+      "loss": 0.8506,
+      "step": 116
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029769115703223763,
+      "loss": 0.8084,
+      "step": 117
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0002974123459571039,
+      "loss": 0.8541,
+      "step": 118
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00029711779206048454,
+      "loss": 0.8425,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029680752679910315,
+      "loss": 0.8619,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00029648158330756986,
+      "loss": 0.8502,
+      "step": 121
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002961399963948431,
+      "loss": 0.8482,
+      "step": 122
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002957828025405117,
+      "loss": 0.8647,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002954100398908995,
+      "loss": 0.8427,
+      "step": 124
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00029502174825499146,
+      "loss": 0.8723,
+      "step": 125
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.000294617969100182,
+      "loss": 0.8716,
+      "step": 126
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00029419874554784695,
+      "loss": 0.8385,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0002937641223687379,
+      "loss": 0.841,
+      "step": 128
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029331414597820145,
+      "loss": 0.838,
+      "step": 129
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029284886443122214,
+      "loss": 0.8321,
+      "step": 130
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00029236832741729016,
+      "loss": 0.9036,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029187258625509513,
+      "loss": 0.8804,
+      "step": 132
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002913616938870455,
+      "loss": 0.7992,
+      "step": 133
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002908357048736144,
+      "loss": 0.8204,
+      "step": 134
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00029029467538751303,
+      "loss": 0.8584,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00028973866320769183,
+      "loss": 0.8478,
+      "step": 136
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00028916772771316973,
+      "loss": 0.8135,
+      "step": 137
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.000288581929876693,
+      "loss": 0.8852,
+      "step": 138
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0002879813322582237,
+      "loss": 0.8446,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028736599899825856,
+      "loss": 0.8527,
+      "step": 140
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0002867359958109792,
+      "loss": 0.85,
+      "step": 141
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028609138997723397,
+      "loss": 0.871,
+      "step": 142
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00028543225033735313,
+      "loss": 0.8208,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002847586472837968,
+      "loss": 0.8125,
+      "step": 144
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00028407065275363753,
+      "loss": 0.8421,
+      "step": 145
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002833683402208777,
+      "loss": 0.8677,
+      "step": 146
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0002826517846886033,
+      "loss": 0.8242,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00028192106268097334,
+      "loss": 0.8747,
+      "step": 148
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002811762522350481,
+      "loss": 0.815,
+      "step": 149
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.000280417432892455,
+      "loss": 0.8432,
+      "step": 150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0002796446856908939,
+      "loss": 0.8256,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002788580931554828,
+      "loss": 0.856,
+      "step": 152
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002780577392899446,
+      "loss": 0.8366,
+      "step": 153
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00027724370956763603,
+      "loss": 0.8666,
+      "step": 154
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0002764160909224196,
+      "loss": 0.84,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00027557497173937923,
+      "loss": 0.8468,
+      "step": 156
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0002747204418453818,
+      "loss": 0.8057,
+      "step": 157
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00027385259249948333,
+      "loss": 0.8228,
+      "step": 158
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.000272971516383184,
+      "loss": 0.8424,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00027207730759052924,
+      "loss": 0.8181,
+      "step": 160
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002711700616180619,
+      "loss": 0.8378,
+      "step": 161
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002702498753546232,
+      "loss": 0.8903,
+      "step": 162
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00026931684707100586,
+      "loss": 0.8211,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026837107640945905,
+      "loss": 0.8213,
+      "step": 164
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026741266437304716,
+      "loss": 0.811,
+      "step": 165
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0002664417133148636,
+      "loss": 0.8481,
+      "step": 166
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026545832692709964,
+      "loss": 0.8715,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00026446261022997097,
+      "loss": 0.8717,
+      "step": 168
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00026345466956050176,
+      "loss": 0.8589,
+      "step": 169
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0002624346125611689,
+      "loss": 0.8298,
+      "step": 170
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.000261402548168406,
+      "loss": 0.859,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002603585866009697,
+      "loss": 0.8108,
+      "step": 172
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002593028393481692,
+      "loss": 0.8591,
+      "step": 173
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0002582354191579593,
+      "loss": 0.8521,
+      "step": 174
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00025715644002489996,
+      "loss": 0.8394,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025606601717798207,
+      "loss": 0.8457,
+      "step": 176
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025496426706832193,
+      "loss": 0.8656,
+      "step": 177
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0002538513073567244,
+      "loss": 0.8678,
+      "step": 178
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025272725690111806,
+      "loss": 0.8367,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00025159223574386114,
+      "loss": 0.8449,
+      "step": 180
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00025044636509892227,
+      "loss": 0.8003,
+      "step": 181
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00024928976733893494,
+      "loss": 0.8312,
+      "step": 182
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0002481225659821294,
+      "loss": 0.8567,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024694488567914106,
+      "loss": 0.872,
+      "step": 184
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002457568521996988,
+      "loss": 0.8735,
+      "step": 185
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024455859241919326,
+      "loss": 0.8571,
+      "step": 186
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0002433502343051274,
+      "loss": 0.8395,
+      "step": 187
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00024213190690345018,
+      "loss": 0.8439,
+      "step": 188
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00024090374032477533,
+      "loss": 0.8661,
+      "step": 189
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002396658657304861,
+      "loss": 0.8679,
+      "step": 190
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00023841841531872798,
+      "loss": 0.8151,
+      "step": 191
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00023716152231029072,
+      "loss": 0.8517,
+      "step": 192
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.000235895320934381,
+      "loss": 0.8591,
+      "step": 193
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00023461994641428766,
+      "loss": 0.8638,
+      "step": 194
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002333355349529403,
+      "loss": 0.8512,
+      "step": 195
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00023204222371836405,
+      "loss": 0.835,
+      "step": 196
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00023074015082903015,
+      "loss": 0.8611,
+      "step": 197
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0002294294553391063,
+      "loss": 0.7981,
+      "step": 198
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022811027722360598,
+      "loss": 0.84,
+      "step": 199
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00022678275736344014,
+      "loss": 0.8008,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022544703753037178,
+      "loss": 0.8333,
+      "step": 201
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022410326037187558,
+      "loss": 0.8197,
+      "step": 202
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022275156939590392,
+      "loss": 0.8408,
+      "step": 203
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00022139210895556104,
+      "loss": 0.8608,
+      "step": 204
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022002502423368678,
+      "loss": 0.8705,
+      "step": 205
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002186504612273522,
+      "loss": 0.8388,
+      "step": 206
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0002172685667322676,
+      "loss": 0.8779,
+      "step": 207
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00021587948832710554,
+      "loss": 0.8314,
+      "step": 208
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002144833743577405,
+      "loss": 0.8249,
+      "step": 209
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002130803739214061,
+      "loss": 0.8312,
+      "step": 210
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00021167063685077262,
+      "loss": 0.8003,
+      "step": 211
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0002102543136979454,
+      "loss": 0.8513,
+      "step": 212
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020883155571838692,
+      "loss": 0.835,
+      "step": 213
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020740251485476345,
+      "loss": 0.8981,
+      "step": 214
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020596734372071852,
+      "loss": 0.8353,
+      "step": 215
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00020452619558457446,
+      "loss": 0.8457,
+      "step": 216
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00020307922435296443,
+      "loss": 0.8225,
+      "step": 217
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0002016265845543958,
+      "loss": 0.8342,
+      "step": 218
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00020016843132274746,
+      "loss": 0.807,
+      "step": 219
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00019870492038070252,
+      "loss": 0.8271,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019723620802311774,
+      "loss": 0.8731,
+      "step": 221
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019576245110033231,
+      "loss": 0.8436,
+      "step": 222
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019428380700141698,
+      "loss": 0.8816,
+      "step": 223
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00019280043363736579,
+      "loss": 0.8281,
+      "step": 224
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0001913124894242322,
+      "loss": 0.8413,
+      "step": 225
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018982013326621083,
+      "loss": 0.8318,
+      "step": 226
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018832352453866777,
+      "loss": 0.8394,
+      "step": 227
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018682282307111987,
+      "loss": 0.819,
+      "step": 228
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018531818913016584,
+      "loss": 0.8598,
+      "step": 229
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018380978340237092,
+      "loss": 0.8346,
+      "step": 230
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018229776697710617,
+      "loss": 0.8523,
+      "step": 231
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00018078230132934512,
+      "loss": 0.8461,
+      "step": 232
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017926354830241924,
+      "loss": 0.8368,
+      "step": 233
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017774167009073377,
+      "loss": 0.8336,
+      "step": 234
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017621682922244633,
+      "loss": 0.8049,
+      "step": 235
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017468918854211007,
+      "loss": 0.8245,
+      "step": 236
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001731589111932823,
+      "loss": 0.8474,
+      "step": 237
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000171626160601102,
+      "loss": 0.8643,
+      "step": 238
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001700911004548369,
+      "loss": 0.8448,
+      "step": 239
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00016855389469040217,
+      "loss": 0.8822,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016701470747285317,
+      "loss": 0.8225,
+      "step": 241
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016547370317885354,
+      "loss": 0.8269,
+      "step": 242
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0001639310463791205,
+      "loss": 0.8365,
+      "step": 243
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016238690182084986,
+      "loss": 0.8265,
+      "step": 244
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016084143441012156,
+      "loss": 0.8439,
+      "step": 245
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001592948091942892,
+      "loss": 0.8438,
+      "step": 246
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0001577471913443532,
+      "loss": 0.8595,
+      "step": 247
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00015619874613732196,
+      "loss": 0.8313,
+      "step": 248
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0001546496389385611,
+      "loss": 0.8258,
+      "step": 249
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015310003518413315,
+      "loss": 0.7778,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015155010036313008,
+      "loss": 0.8442,
+      "step": 251
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00015,
+      "loss": 0.8477,
+      "step": 252
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014844989963686992,
+      "loss": 0.8447,
+      "step": 253
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014689996481586688,
+      "loss": 0.8424,
+      "step": 254
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00014535036106143892,
+      "loss": 0.8357,
+      "step": 255
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000143801253862678,
+      "loss": 0.8467,
+      "step": 256
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001422528086556468,
+      "loss": 0.8105,
+      "step": 257
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001407051908057108,
+      "loss": 0.8215,
+      "step": 258
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001391585655898784,
+      "loss": 0.8452,
+      "step": 259
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00013761309817915014,
+      "loss": 0.7967,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013606895362087949,
+      "loss": 0.8172,
+      "step": 261
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013452629682114646,
+      "loss": 0.8837,
+      "step": 262
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013298529252714684,
+      "loss": 0.8293,
+      "step": 263
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00013144610530959784,
+      "loss": 0.8493,
+      "step": 264
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001299088995451631,
+      "loss": 0.7906,
+      "step": 265
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012837383939889798,
+      "loss": 0.8201,
+      "step": 266
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012684108880671772,
+      "loss": 0.7947,
+      "step": 267
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00012531081145788987,
+      "loss": 0.8238,
+      "step": 268
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012378317077755362,
+      "loss": 0.8417,
+      "step": 269
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012225832990926623,
+      "loss": 0.8728,
+      "step": 270
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00012073645169758076,
+      "loss": 0.798,
+      "step": 271
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00011921769867065485,
+      "loss": 0.8053,
+      "step": 272
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011770223302289385,
+      "loss": 0.7943,
+      "step": 273
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001161902165976291,
+      "loss": 0.8407,
+      "step": 274
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011468181086983412,
+      "loss": 0.8326,
+      "step": 275
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00011317717692888012,
+      "loss": 0.8355,
+      "step": 276
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0001116764754613322,
+      "loss": 0.8015,
+      "step": 277
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00011017986673378918,
+      "loss": 0.8426,
+      "step": 278
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010868751057576782,
+      "loss": 0.858,
+      "step": 279
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010719956636263423,
+      "loss": 0.8268,
+      "step": 280
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00010571619299858303,
+      "loss": 0.8244,
+      "step": 281
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010423754889966769,
+      "loss": 0.8328,
+      "step": 282
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010276379197688222,
+      "loss": 0.8201,
+      "step": 283
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00010129507961929748,
+      "loss": 0.804,
+      "step": 284
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.983156867725255e-05,
+      "loss": 0.8273,
+      "step": 285
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.837341544560423e-05,
+      "loss": 0.8222,
+      "step": 286
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.692077564703555e-05,
+      "loss": 0.828,
+      "step": 287
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.547380441542549e-05,
+      "loss": 0.8507,
+      "step": 288
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.403265627928147e-05,
+      "loss": 0.8044,
+      "step": 289
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.259748514523653e-05,
+      "loss": 0.8202,
+      "step": 290
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.116844428161309e-05,
+      "loss": 0.7773,
+      "step": 291
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.97456863020546e-05,
+      "loss": 0.8119,
+      "step": 292
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 8.83293631492274e-05,
+      "loss": 0.8274,
+      "step": 293
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.691962607859386e-05,
+      "loss": 0.8167,
+      "step": 294
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.55166256422595e-05,
+      "loss": 0.8389,
+      "step": 295
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.412051167289446e-05,
+      "loss": 0.8091,
+      "step": 296
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.27314332677324e-05,
+      "loss": 0.8418,
+      "step": 297
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.134953877264778e-05,
+      "loss": 0.8105,
+      "step": 298
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.997497576631323e-05,
+      "loss": 0.8409,
+      "step": 299
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.860789104443896e-05,
+      "loss": 0.8429,
+      "step": 300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.724843060409606e-05,
+      "loss": 0.8175,
+      "step": 301
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.589673962812442e-05,
+      "loss": 0.8115,
+      "step": 302
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.455296246962823e-05,
+      "loss": 0.846,
+      "step": 303
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.321724263655988e-05,
+      "loss": 0.8175,
+      "step": 304
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.188972277639405e-05,
+      "loss": 0.8177,
+      "step": 305
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.057054466089371e-05,
+      "loss": 0.8441,
+      "step": 306
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.925984917096985e-05,
+      "loss": 0.8272,
+      "step": 307
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.795777628163599e-05,
+      "loss": 0.8525,
+      "step": 308
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.66644650470597e-05,
+      "loss": 0.8533,
+      "step": 309
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.538005358571234e-05,
+      "loss": 0.8436,
+      "step": 310
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.410467906561896e-05,
+      "loss": 0.832,
+      "step": 311
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.283847768970926e-05,
+      "loss": 0.7897,
+      "step": 312
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.158158468127196e-05,
+      "loss": 0.824,
+      "step": 313
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.0334134269513865e-05,
+      "loss": 0.8435,
+      "step": 314
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.9096259675224647e-05,
+      "loss": 0.8233,
+      "step": 315
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.786809309654982e-05,
+      "loss": 0.8333,
+      "step": 316
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.664976569487263e-05,
+      "loss": 0.8658,
+      "step": 317
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.5441407580806745e-05,
+      "loss": 0.8229,
+      "step": 318
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.4243147800301134e-05,
+      "loss": 0.7847,
+      "step": 319
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.305511432085884e-05,
+      "loss": 0.7924,
+      "step": 320
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.187743401787054e-05,
+      "loss": 0.8458,
+      "step": 321
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5.071023266106502e-05,
+      "loss": 0.8492,
+      "step": 322
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.955363490107777e-05,
+      "loss": 0.8584,
+      "step": 323
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.840776425613886e-05,
+      "loss": 0.8262,
+      "step": 324
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.727274309888191e-05,
+      "loss": 0.8299,
+      "step": 325
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.614869264327553e-05,
+      "loss": 0.8267,
+      "step": 326
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.503573293167805e-05,
+      "loss": 0.8352,
+      "step": 327
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.3933982822017876e-05,
+      "loss": 0.8181,
+      "step": 328
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.284355997510003e-05,
+      "loss": 0.8091,
+      "step": 329
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.17645808420407e-05,
+      "loss": 0.8123,
+      "step": 330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.0697160651830814e-05,
+      "loss": 0.8075,
+      "step": 331
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.964141339903026e-05,
+      "loss": 0.8576,
+      "step": 332
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.8597451831594014e-05,
+      "loss": 0.8134,
+      "step": 333
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.756538743883111e-05,
+      "loss": 0.8384,
+      "step": 334
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.654533043949823e-05,
+      "loss": 0.8061,
+      "step": 335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.5537389770029046e-05,
+      "loss": 0.8438,
+      "step": 336
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.454167307290036e-05,
+      "loss": 0.8024,
+      "step": 337
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.3558286685136384e-05,
+      "loss": 0.8332,
+      "step": 338
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.258733562695283e-05,
+      "loss": 0.8247,
+      "step": 339
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.162892359054098e-05,
+      "loss": 0.8482,
+      "step": 340
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.0683152928994105e-05,
+      "loss": 0.8171,
+      "step": 341
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.9750124645376755e-05,
+      "loss": 0.8296,
+      "step": 342
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.8829938381938117e-05,
+      "loss": 0.8403,
+      "step": 343
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.792269240947076e-05,
+      "loss": 0.8472,
+      "step": 344
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.702848361681605e-05,
+      "loss": 0.8305,
+      "step": 345
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.6147407500516643e-05,
+      "loss": 0.8491,
+      "step": 346
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.5279558154618197e-05,
+      "loss": 0.8299,
+      "step": 347
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.4425028260620715e-05,
+      "loss": 0.8329,
+      "step": 348
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.35839090775804e-05,
+      "loss": 0.8234,
+      "step": 349
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.2756290432363957e-05,
+      "loss": 0.8197,
+      "step": 350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.1942260710055386e-05,
+      "loss": 0.8238,
+      "step": 351
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.1141906844517203e-05,
+      "loss": 0.8051,
+      "step": 352
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.0355314309106097e-05,
+      "loss": 0.8269,
+      "step": 353
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.9582567107544962e-05,
+      "loss": 0.8325,
+      "step": 354
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.882374776495187e-05,
+      "loss": 0.843,
+      "step": 355
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.8078937319026654e-05,
+      "loss": 0.8352,
+      "step": 356
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.734821531139667e-05,
+      "loss": 0.8756,
+      "step": 357
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.663165977912221e-05,
+      "loss": 0.8193,
+      "step": 358
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.5929347246362452e-05,
+      "loss": 0.8123,
+      "step": 359
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.524135271620317e-05,
+      "loss": 0.807,
+      "step": 360
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.456774966264685e-05,
+      "loss": 0.878,
+      "step": 361
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.390861002276602e-05,
+      "loss": 0.8185,
+      "step": 362
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.3264004189020777e-05,
+      "loss": 0.7939,
+      "step": 363
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2634001001741373e-05,
+      "loss": 0.8163,
+      "step": 364
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.2018667741776266e-05,
+      "loss": 0.8429,
+      "step": 365
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1418070123306989e-05,
+      "loss": 0.8292,
+      "step": 366
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0832272286830285e-05,
+      "loss": 0.8241,
+      "step": 367
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0261336792308167e-05,
+      "loss": 0.8438,
+      "step": 368
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.705324612486936e-06,
+      "loss": 0.8631,
+      "step": 369
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.164295126385562e-06,
+      "loss": 0.8359,
+      "step": 370
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.638306112954452e-06,
+      "loss": 0.8304,
+      "step": 371
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.127413744904804e-06,
+      "loss": 0.7995,
+      "step": 372
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.631672582709808e-06,
+      "loss": 0.817,
+      "step": 373
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.151135568777838e-06,
+      "loss": 0.8264,
+      "step": 374
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.685854021798509e-06,
+      "loss": 0.8166,
+      "step": 375
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.235877631262093e-06,
+      "loss": 0.8215,
+      "step": 376
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.801254452153081e-06,
+      "loss": 0.8611,
+      "step": 377
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.3820308998179575e-06,
+      "loss": 0.8002,
+      "step": 378
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.978251745008527e-06,
+      "loss": 0.8199,
+      "step": 379
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.589960109100444e-06,
+      "loss": 0.8412,
+      "step": 380
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.217197459488292e-06,
+      "loss": 0.8421,
+      "step": 381
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.86000360515688e-06,
+      "loss": 0.8425,
+      "step": 382
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.518416692430076e-06,
+      "loss": 0.8426,
+      "step": 383
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.192473200896828e-06,
+      "loss": 0.833,
+      "step": 384
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.882207939515435e-06,
+      "loss": 0.825,
+      "step": 385
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.587654042896087e-06,
+      "loss": 0.8433,
+      "step": 386
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.3088429677623423e-06,
+      "loss": 0.8065,
+      "step": 387
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.0458044895916513e-06,
+      "loss": 0.789,
+      "step": 388
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.7985666994355164e-06,
+      "loss": 0.8071,
+      "step": 389
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5671560009195894e-06,
+      "loss": 0.8675,
+      "step": 390
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.351597107423813e-06,
+      "loss": 0.8259,
+      "step": 391
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.1519130394432474e-06,
+      "loss": 0.8523,
+      "step": 392
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 9.681251221295539e-07,
+      "loss": 0.8201,
+      "step": 393
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 8.002529830136162e-07,
+      "loss": 0.8393,
+      "step": 394
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 6.483145499094344e-07,
+      "loss": 0.8057,
+      "step": 395
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 5.123260489995229e-07,
+      "loss": 0.8385,
+      "step": 396
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.923020031020296e-07,
+      "loss": 0.841,
+      "step": 397
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.8825523011977715e-07,
+      "loss": 0.834,
+      "step": 398
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.001968416714572e-07,
+      "loss": 0.8385,
+      "step": 399
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.2813624190484705e-07,
+      "loss": 0.8088,
+      "step": 400
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.208112649259578e-08,
+      "loss": 0.8244,
+      "step": 401
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.2037481810348594e-08,
+      "loss": 0.8159,
+      "step": 402
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.009584297391514e-09,
+      "loss": 0.8425,
+      "step": 403
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.8223,
+      "step": 404
+    },
+    {
+      "epoch": 1.0,
+      "step": 404,
+      "total_flos": 4.5406536857338675e+17,
+      "train_loss": 0.9254943004043976,
+      "train_runtime": 17197.3779,
+      "train_samples_per_second": 3.01,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 404,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 4.5406536857338675e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_7b_SGD_Cosine/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33222dfbebfe89abc6dfd2eda90df0b1c95c9ba8141e3518b9034d169c7a3c7
+size 5048