Upload folder using huggingface_hub

README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: codellama/CodeLlama-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]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.2.dev0

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f401595b47c3b38a3681abb36daa3be453108ba604a56bd931a2c61ff672b99
+size 319977229

checkpoint-118/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: codellama/CodeLlama-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]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.2.dev0

checkpoint-118/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-118/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a7093fd570d84977bbb3b8fad4808a806ebf74a41f6150aa34b05d247a37dd
+size 319977229

checkpoint-118/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d52acabf06598dc020e8bbf6f8e063b748a9ed3002548a155d55802fdb4cf75
+size 639908165

checkpoint-118/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb14416f3fde05f27e6bc711bef7700bc8c382e3b21abf322672df4f5491efd7
+size 14575

checkpoint-118/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e34d8128a244fa6cf229f0bc81147d32420a86c9a1a9e06d462b31bb885b780
+size 627

checkpoint-118/trainer_state.json

@@ -0,0 +1,967 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.019438444924406,
+  "eval_steps": 4,
+  "global_step": 118,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.3477,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 0.4987175166606903,
+      "eval_runtime": 3.1166,
+      "eval_samples_per_second": 6.417,
+      "eval_steps_per_second": 3.209,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3285,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-06,
+      "loss": 0.3754,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.3143,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.4986831247806549,
+      "eval_runtime": 3.101,
+      "eval_samples_per_second": 6.45,
+      "eval_steps_per_second": 3.225,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1e-05,
+      "loss": 0.4661,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2e-05,
+      "loss": 0.3726,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.3515,
+      "step": 7
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2981,
+      "step": 8
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 0.4983077645301819,
+      "eval_runtime": 3.1103,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8e-05,
+      "loss": 0.5434,
+      "step": 9
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 0.3998,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.31,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.4e-05,
+      "loss": 0.4314,
+      "step": 12
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.497723788022995,
+      "eval_runtime": 3.1104,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 12
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.3478,
+      "step": 13
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.3663,
+      "step": 14
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3e-05,
+      "loss": 0.3981,
+      "step": 15
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.3959,
+      "step": 16
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.49577316641807556,
+      "eval_runtime": 3.1093,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 16
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.4256,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.6e-05,
+      "loss": 0.3393,
+      "step": 18
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.8e-05,
+      "loss": 0.4055,
+      "step": 19
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4e-05,
+      "loss": 0.3353,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.4915711581707001,
+      "eval_runtime": 3.1139,
+      "eval_samples_per_second": 6.423,
+      "eval_steps_per_second": 3.211,
+      "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3431,
+      "step": 21
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.354,
+      "step": 22
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3472,
+      "step": 23
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4287,
+      "step": 24
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.4811338782310486,
+      "eval_runtime": 3.1059,
+      "eval_samples_per_second": 6.439,
+      "eval_steps_per_second": 3.22,
+      "step": 24
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5e-05,
+      "loss": 0.3663,
+      "step": 25
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.298,
+      "step": 26
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.3649,
+      "step": 27
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.4018,
+      "step": 28
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.46300894021987915,
+      "eval_runtime": 3.1124,
+      "eval_samples_per_second": 6.426,
+      "eval_steps_per_second": 3.213,
+      "step": 28
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 5.8e-05,
+      "loss": 0.3116,
+      "step": 29
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 6e-05,
+      "loss": 0.3147,
+      "step": 30
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 6.2e-05,
+      "loss": 0.2776,
+      "step": 31
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.3278,
+      "step": 32
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.4446893334388733,
+      "eval_runtime": 3.1075,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 32
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.6e-05,
+      "loss": 0.2848,
+      "step": 33
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.2776,
+      "step": 34
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 7e-05,
+      "loss": 0.3078,
+      "step": 35
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 7.2e-05,
+      "loss": 0.2566,
+      "step": 36
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.4287605881690979,
+      "eval_runtime": 3.1063,
+      "eval_samples_per_second": 6.438,
+      "eval_steps_per_second": 3.219,
+      "step": 36
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.4e-05,
+      "loss": 0.2715,
+      "step": 37
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.6e-05,
+      "loss": 0.3393,
+      "step": 38
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.2669,
+      "step": 39
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 8e-05,
+      "loss": 0.3797,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "eval_loss": 0.4169308543205261,
+      "eval_runtime": 3.1074,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 8.2e-05,
+      "loss": 0.2702,
+      "step": 41
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.4e-05,
+      "loss": 0.3824,
+      "step": 42
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.6e-05,
+      "loss": 0.274,
+      "step": 43
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.2966,
+      "step": 44
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.41074520349502563,
+      "eval_runtime": 3.1076,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 44
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9e-05,
+      "loss": 0.485,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.2395,
+      "step": 46
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.4e-05,
+      "loss": 0.3023,
+      "step": 47
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.6e-05,
+      "loss": 0.2676,
+      "step": 48
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.4023456573486328,
+      "eval_runtime": 3.1109,
+      "eval_samples_per_second": 6.429,
+      "eval_steps_per_second": 3.215,
+      "step": 48
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.8e-05,
+      "loss": 0.2378,
+      "step": 49
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001,
+      "loss": 0.2607,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 0.4538,
+      "step": 51
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.2456,
+      "step": 52
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.3957594335079193,
+      "eval_runtime": 3.1123,
+      "eval_samples_per_second": 6.426,
+      "eval_steps_per_second": 3.213,
+      "step": 52
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 0.3435,
+      "step": 53
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.3035,
+      "step": 54
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.3564,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.3267,
+      "step": 56
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.39143189787864685,
+      "eval_runtime": 3.1134,
+      "eval_samples_per_second": 6.424,
+      "eval_steps_per_second": 3.212,
+      "step": 56
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.2641,
+      "step": 57
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.000116,
+      "loss": 0.2805,
+      "step": 58
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.000118,
+      "loss": 0.2784,
+      "step": 59
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00012,
+      "loss": 0.2901,
+      "step": 60
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 0.38809266686439514,
+      "eval_runtime": 3.1079,
+      "eval_samples_per_second": 6.435,
+      "eval_steps_per_second": 3.218,
+      "step": 60
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000122,
+      "loss": 0.3039,
+      "step": 61
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.000124,
+      "loss": 0.2035,
+      "step": 62
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.000126,
+      "loss": 0.326,
+      "step": 63
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.1843,
+      "step": 64
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 0.3881237506866455,
+      "eval_runtime": 3.1107,
+      "eval_samples_per_second": 6.429,
+      "eval_steps_per_second": 3.215,
+      "step": 64
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.296,
+      "step": 65
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.000132,
+      "loss": 0.2766,
+      "step": 66
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000134,
+      "loss": 0.304,
+      "step": 67
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.2585,
+      "step": 68
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 0.3869483470916748,
+      "eval_runtime": 3.1091,
+      "eval_samples_per_second": 6.433,
+      "eval_steps_per_second": 3.216,
+      "step": 68
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.000138,
+      "loss": 0.2639,
+      "step": 69
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00014,
+      "loss": 0.3013,
+      "step": 70
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.000142,
+      "loss": 0.4263,
+      "step": 71
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.000144,
+      "loss": 0.3108,
+      "step": 72
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.3839200437068939,
+      "eval_runtime": 3.1098,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.216,
+      "step": 72
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000146,
+      "loss": 0.4283,
+      "step": 73
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.000148,
+      "loss": 0.2582,
+      "step": 74
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2703,
+      "step": 75
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000152,
+      "loss": 0.3799,
+      "step": 76
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 0.3816559314727783,
+      "eval_runtime": 3.1096,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 76
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.000154,
+      "loss": 0.252,
+      "step": 77
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.3297,
+      "step": 78
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.2607,
+      "step": 79
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00016,
+      "loss": 0.2064,
+      "step": 80
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 0.37915611267089844,
+      "eval_runtime": 3.1123,
+      "eval_samples_per_second": 6.426,
+      "eval_steps_per_second": 3.213,
+      "step": 80
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000162,
+      "loss": 0.3341,
+      "step": 81
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.000164,
+      "loss": 0.3159,
+      "step": 82
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000166,
+      "loss": 0.2457,
+      "step": 83
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.000168,
+      "loss": 0.3176,
+      "step": 84
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 0.3792770504951477,
+      "eval_runtime": 3.13,
+      "eval_samples_per_second": 6.39,
+      "eval_steps_per_second": 3.195,
+      "step": 84
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017,
+      "loss": 0.3043,
+      "step": 85
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000172,
+      "loss": 0.2346,
+      "step": 86
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000174,
+      "loss": 0.2872,
+      "step": 87
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.2307,
+      "step": 88
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.3768787384033203,
+      "eval_runtime": 3.1088,
+      "eval_samples_per_second": 6.433,
+      "eval_steps_per_second": 3.217,
+      "step": 88
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.2661,
+      "step": 89
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00018,
+      "loss": 0.3068,
+      "step": 90
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.000182,
+      "loss": 0.2866,
+      "step": 91
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.2826,
+      "step": 92
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.3746011555194855,
+      "eval_runtime": 3.1104,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 92
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 0.4888,
+      "step": 93
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000188,
+      "loss": 0.1667,
+      "step": 94
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00019,
+      "loss": 0.2683,
+      "step": 95
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.000192,
+      "loss": 0.2718,
+      "step": 96
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 0.373685747385025,
+      "eval_runtime": 3.1134,
+      "eval_samples_per_second": 6.424,
+      "eval_steps_per_second": 3.212,
+      "step": 96
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000194,
+      "loss": 0.2193,
+      "step": 97
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.000196,
+      "loss": 0.378,
+      "step": 98
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.2917,
+      "step": 99
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 0.2945,
+      "step": 100
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.3727183938026428,
+      "eval_runtime": 3.1085,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00019999177886783194,
+      "loss": 0.2355,
+      "step": 101
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.000199967116823068,
+      "loss": 0.2656,
+      "step": 102
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00019992601792070679,
+      "loss": 0.2803,
+      "step": 103
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00019986848891833845,
+      "loss": 0.2313,
+      "step": 104
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.371459424495697,
+      "eval_runtime": 3.1114,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 104
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 0.2983,
+      "step": 105
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0001997041811497882,
+      "loss": 0.2547,
+      "step": 106
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00019959742939952392,
+      "loss": 0.2463,
+      "step": 107
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00019947430157664576,
+      "loss": 0.2519,
+      "step": 108
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 0.37180376052856445,
+      "eval_runtime": 3.1113,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 108
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00019933481792615583,
+      "loss": 0.2032,
+      "step": 109
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 0.2868,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001990068775649202,
+      "loss": 0.2653,
+      "step": 111
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00019881847477499557,
+      "loss": 0.2468,
+      "step": 112
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 0.37166160345077515,
+      "eval_runtime": 3.1194,
+      "eval_samples_per_second": 6.412,
+      "eval_steps_per_second": 3.206,
+      "step": 112
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0001986138239902355,
+      "loss": 0.3997,
+      "step": 113
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00019839295885986296,
+      "loss": 0.172,
+      "step": 114
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00019815591569910654,
+      "loss": 0.2713,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001979027334832293,
+      "loss": 0.2034,
+      "step": 116
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.37163203954696655,
+      "eval_runtime": 3.1126,
+      "eval_samples_per_second": 6.425,
+      "eval_steps_per_second": 3.213,
+      "step": 116
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00019763345384112043,
+      "loss": 0.1824,
+      "step": 117
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00019734812104845047,
+      "loss": 0.3669,
+      "step": 118
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 345,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 5.999495556523622e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-118/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e119793adec89e061da62a7de24a1a71fb0682ce4c3e3f95d85eab584ad38284
+size 4539

checkpoint-236/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: codellama/CodeLlama-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]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.2.dev0

checkpoint-236/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-236/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7473a9433ef773d2635979551a58ea2ed02951345c4fe21fb79e3164a8fb8ff5
+size 319977229

checkpoint-236/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b9f600cc360a7a89c801026c462545dc2778523eded60ee3dac70dfda80273
+size 639908165

checkpoint-236/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0651b88029431b15b08d72edfc95c9f78985bf69797d0430716d76d491a6c6e6
+size 14575

checkpoint-236/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d25880d67522b3e746ffc650a73c9fd823cc40f7a6ecf385dfc3827145853b4
+size 627

checkpoint-236/trainer_state.json

@@ -0,0 +1,1915 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.019438444924406,
+  "eval_steps": 4,
+  "global_step": 236,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.3477,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 0.4987175166606903,
+      "eval_runtime": 3.1166,
+      "eval_samples_per_second": 6.417,
+      "eval_steps_per_second": 3.209,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3285,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-06,
+      "loss": 0.3754,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.3143,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.4986831247806549,
+      "eval_runtime": 3.101,
+      "eval_samples_per_second": 6.45,
+      "eval_steps_per_second": 3.225,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1e-05,
+      "loss": 0.4661,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2e-05,
+      "loss": 0.3726,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.3515,
+      "step": 7
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2981,
+      "step": 8
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 0.4983077645301819,
+      "eval_runtime": 3.1103,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8e-05,
+      "loss": 0.5434,
+      "step": 9
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 0.3998,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.31,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.4e-05,
+      "loss": 0.4314,
+      "step": 12
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.497723788022995,
+      "eval_runtime": 3.1104,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 12
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.3478,
+      "step": 13
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.3663,
+      "step": 14
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3e-05,
+      "loss": 0.3981,
+      "step": 15
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.3959,
+      "step": 16
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.49577316641807556,
+      "eval_runtime": 3.1093,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 16
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.4256,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.6e-05,
+      "loss": 0.3393,
+      "step": 18
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.8e-05,
+      "loss": 0.4055,
+      "step": 19
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4e-05,
+      "loss": 0.3353,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.4915711581707001,
+      "eval_runtime": 3.1139,
+      "eval_samples_per_second": 6.423,
+      "eval_steps_per_second": 3.211,
+      "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3431,
+      "step": 21
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.354,
+      "step": 22
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3472,
+      "step": 23
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4287,
+      "step": 24
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.4811338782310486,
+      "eval_runtime": 3.1059,
+      "eval_samples_per_second": 6.439,
+      "eval_steps_per_second": 3.22,
+      "step": 24
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5e-05,
+      "loss": 0.3663,
+      "step": 25
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.298,
+      "step": 26
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.3649,
+      "step": 27
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.4018,
+      "step": 28
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.46300894021987915,
+      "eval_runtime": 3.1124,
+      "eval_samples_per_second": 6.426,
+      "eval_steps_per_second": 3.213,
+      "step": 28
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 5.8e-05,
+      "loss": 0.3116,
+      "step": 29
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 6e-05,
+      "loss": 0.3147,
+      "step": 30
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 6.2e-05,
+      "loss": 0.2776,
+      "step": 31
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.3278,
+      "step": 32
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.4446893334388733,
+      "eval_runtime": 3.1075,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 32
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.6e-05,
+      "loss": 0.2848,
+      "step": 33
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.2776,
+      "step": 34
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 7e-05,
+      "loss": 0.3078,
+      "step": 35
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 7.2e-05,
+      "loss": 0.2566,
+      "step": 36
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.4287605881690979,
+      "eval_runtime": 3.1063,
+      "eval_samples_per_second": 6.438,
+      "eval_steps_per_second": 3.219,
+      "step": 36
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.4e-05,
+      "loss": 0.2715,
+      "step": 37
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.6e-05,
+      "loss": 0.3393,
+      "step": 38
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.2669,
+      "step": 39
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 8e-05,
+      "loss": 0.3797,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "eval_loss": 0.4169308543205261,
+      "eval_runtime": 3.1074,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 8.2e-05,
+      "loss": 0.2702,
+      "step": 41
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.4e-05,
+      "loss": 0.3824,
+      "step": 42
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.6e-05,
+      "loss": 0.274,
+      "step": 43
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.2966,
+      "step": 44
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.41074520349502563,
+      "eval_runtime": 3.1076,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 44
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9e-05,
+      "loss": 0.485,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.2395,
+      "step": 46
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.4e-05,
+      "loss": 0.3023,
+      "step": 47
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.6e-05,
+      "loss": 0.2676,
+      "step": 48
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.4023456573486328,
+      "eval_runtime": 3.1109,
+      "eval_samples_per_second": 6.429,
+      "eval_steps_per_second": 3.215,
+      "step": 48
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.8e-05,
+      "loss": 0.2378,
+      "step": 49
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001,
+      "loss": 0.2607,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 0.4538,
+      "step": 51
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.2456,
+      "step": 52
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.3957594335079193,
+      "eval_runtime": 3.1123,
+      "eval_samples_per_second": 6.426,
+      "eval_steps_per_second": 3.213,
+      "step": 52
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 0.3435,
+      "step": 53
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.3035,
+      "step": 54
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.3564,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.3267,
+      "step": 56
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.39143189787864685,
+      "eval_runtime": 3.1134,
+      "eval_samples_per_second": 6.424,
+      "eval_steps_per_second": 3.212,
+      "step": 56
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.2641,
+      "step": 57
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.000116,
+      "loss": 0.2805,
+      "step": 58
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.000118,
+      "loss": 0.2784,
+      "step": 59
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00012,
+      "loss": 0.2901,
+      "step": 60
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 0.38809266686439514,
+      "eval_runtime": 3.1079,
+      "eval_samples_per_second": 6.435,
+      "eval_steps_per_second": 3.218,
+      "step": 60
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000122,
+      "loss": 0.3039,
+      "step": 61
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.000124,
+      "loss": 0.2035,
+      "step": 62
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.000126,
+      "loss": 0.326,
+      "step": 63
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.1843,
+      "step": 64
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 0.3881237506866455,
+      "eval_runtime": 3.1107,
+      "eval_samples_per_second": 6.429,
+      "eval_steps_per_second": 3.215,
+      "step": 64
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.296,
+      "step": 65
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.000132,
+      "loss": 0.2766,
+      "step": 66
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000134,
+      "loss": 0.304,
+      "step": 67
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.2585,
+      "step": 68
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 0.3869483470916748,
+      "eval_runtime": 3.1091,
+      "eval_samples_per_second": 6.433,
+      "eval_steps_per_second": 3.216,
+      "step": 68
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.000138,
+      "loss": 0.2639,
+      "step": 69
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00014,
+      "loss": 0.3013,
+      "step": 70
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.000142,
+      "loss": 0.4263,
+      "step": 71
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.000144,
+      "loss": 0.3108,
+      "step": 72
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.3839200437068939,
+      "eval_runtime": 3.1098,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.216,
+      "step": 72
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000146,
+      "loss": 0.4283,
+      "step": 73
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.000148,
+      "loss": 0.2582,
+      "step": 74
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2703,
+      "step": 75
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000152,
+      "loss": 0.3799,
+      "step": 76
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 0.3816559314727783,
+      "eval_runtime": 3.1096,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 76
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.000154,
+      "loss": 0.252,
+      "step": 77
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.3297,
+      "step": 78
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.2607,
+      "step": 79
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00016,
+      "loss": 0.2064,
+      "step": 80
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 0.37915611267089844,
+      "eval_runtime": 3.1123,
+      "eval_samples_per_second": 6.426,
+      "eval_steps_per_second": 3.213,
+      "step": 80
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000162,
+      "loss": 0.3341,
+      "step": 81
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.000164,
+      "loss": 0.3159,
+      "step": 82
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000166,
+      "loss": 0.2457,
+      "step": 83
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.000168,
+      "loss": 0.3176,
+      "step": 84
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 0.3792770504951477,
+      "eval_runtime": 3.13,
+      "eval_samples_per_second": 6.39,
+      "eval_steps_per_second": 3.195,
+      "step": 84
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017,
+      "loss": 0.3043,
+      "step": 85
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000172,
+      "loss": 0.2346,
+      "step": 86
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000174,
+      "loss": 0.2872,
+      "step": 87
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.2307,
+      "step": 88
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.3768787384033203,
+      "eval_runtime": 3.1088,
+      "eval_samples_per_second": 6.433,
+      "eval_steps_per_second": 3.217,
+      "step": 88
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.2661,
+      "step": 89
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00018,
+      "loss": 0.3068,
+      "step": 90
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.000182,
+      "loss": 0.2866,
+      "step": 91
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.2826,
+      "step": 92
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.3746011555194855,
+      "eval_runtime": 3.1104,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 92
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 0.4888,
+      "step": 93
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000188,
+      "loss": 0.1667,
+      "step": 94
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00019,
+      "loss": 0.2683,
+      "step": 95
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.000192,
+      "loss": 0.2718,
+      "step": 96
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 0.373685747385025,
+      "eval_runtime": 3.1134,
+      "eval_samples_per_second": 6.424,
+      "eval_steps_per_second": 3.212,
+      "step": 96
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000194,
+      "loss": 0.2193,
+      "step": 97
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.000196,
+      "loss": 0.378,
+      "step": 98
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.2917,
+      "step": 99
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 0.2945,
+      "step": 100
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.3727183938026428,
+      "eval_runtime": 3.1085,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00019999177886783194,
+      "loss": 0.2355,
+      "step": 101
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.000199967116823068,
+      "loss": 0.2656,
+      "step": 102
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00019992601792070679,
+      "loss": 0.2803,
+      "step": 103
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00019986848891833845,
+      "loss": 0.2313,
+      "step": 104
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.371459424495697,
+      "eval_runtime": 3.1114,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 104
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 0.2983,
+      "step": 105
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0001997041811497882,
+      "loss": 0.2547,
+      "step": 106
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00019959742939952392,
+      "loss": 0.2463,
+      "step": 107
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00019947430157664576,
+      "loss": 0.2519,
+      "step": 108
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 0.37180376052856445,
+      "eval_runtime": 3.1113,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 108
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00019933481792615583,
+      "loss": 0.2032,
+      "step": 109
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 0.2868,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001990068775649202,
+      "loss": 0.2653,
+      "step": 111
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00019881847477499557,
+      "loss": 0.2468,
+      "step": 112
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 0.37166160345077515,
+      "eval_runtime": 3.1194,
+      "eval_samples_per_second": 6.412,
+      "eval_steps_per_second": 3.206,
+      "step": 112
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0001986138239902355,
+      "loss": 0.3997,
+      "step": 113
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00019839295885986296,
+      "loss": 0.172,
+      "step": 114
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00019815591569910654,
+      "loss": 0.2713,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001979027334832293,
+      "loss": 0.2034,
+      "step": 116
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.37163203954696655,
+      "eval_runtime": 3.1126,
+      "eval_samples_per_second": 6.425,
+      "eval_steps_per_second": 3.213,
+      "step": 116
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00019763345384112043,
+      "loss": 0.1824,
+      "step": 117
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00019734812104845047,
+      "loss": 0.3669,
+      "step": 118
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0001970467820203915,
+      "loss": 0.229,
+      "step": 119
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 0.2639,
+      "step": 120
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.3714464008808136,
+      "eval_runtime": 3.1072,
+      "eval_samples_per_second": 6.437,
+      "eval_steps_per_second": 3.218,
+      "step": 120
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00019639628606958533,
+      "loss": 0.1806,
+      "step": 121
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00019604723610310194,
+      "loss": 0.2209,
+      "step": 122
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019568239379617088,
+      "loss": 0.2566,
+      "step": 123
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019530181913712872,
+      "loss": 0.2472,
+      "step": 124
+    },
+    {
+      "epoch": 1.05,
+      "eval_loss": 0.3729495108127594,
+      "eval_runtime": 3.1102,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 124
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019490557470106686,
+      "loss": 0.2303,
+      "step": 125
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019449372563954293,
+      "loss": 0.2203,
+      "step": 126
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019406633966986828,
+      "loss": 0.2226,
+      "step": 127
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00019362348706397373,
+      "loss": 0.1987,
+      "step": 128
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 0.36887192726135254,
+      "eval_runtime": 3.1178,
+      "eval_samples_per_second": 6.415,
+      "eval_steps_per_second": 3.207,
+      "step": 128
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001931652406368554,
+      "loss": 0.1859,
+      "step": 129
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001926916757346022,
+      "loss": 0.2408,
+      "step": 130
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00019220287022200707,
+      "loss": 0.2724,
+      "step": 131
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00019169890446976454,
+      "loss": 0.2296,
+      "step": 132
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.3678927719593048,
+      "eval_runtime": 3.1086,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 132
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001911798613412557,
+      "loss": 0.2069,
+      "step": 133
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0001906458261789238,
+      "loss": 0.2973,
+      "step": 134
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.2468,
+      "step": 135
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001895331334332753,
+      "loss": 0.1542,
+      "step": 136
+    },
+    {
+      "epoch": 1.16,
+      "eval_loss": 0.3685668408870697,
+      "eval_runtime": 3.1094,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 136
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001889546588018412,
+      "loss": 0.2935,
+      "step": 137
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00018836155801026753,
+      "loss": 0.2493,
+      "step": 138
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00018775392857775432,
+      "loss": 0.1597,
+      "step": 139
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00018713187041233896,
+      "loss": 0.1949,
+      "step": 140
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 0.3697265684604645,
+      "eval_runtime": 3.1097,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.216,
+      "step": 140
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00018649548579446936,
+      "loss": 0.2434,
+      "step": 141
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00018584487936018661,
+      "loss": 0.2348,
+      "step": 142
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00018518015808392045,
+      "loss": 0.2946,
+      "step": 143
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00018450143126090015,
+      "loss": 0.2239,
+      "step": 144
+    },
+    {
+      "epoch": 1.22,
+      "eval_loss": 0.36812636256217957,
+      "eval_runtime": 3.1112,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 144
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00018380881048918405,
+      "loss": 0.1824,
+      "step": 145
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00018310240965131041,
+      "loss": 0.302,
+      "step": 146
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00018238234489557215,
+      "loss": 0.3452,
+      "step": 147
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00018164873461691986,
+      "loss": 0.1943,
+      "step": 148
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.3690447211265564,
+      "eval_runtime": 3.111,
+      "eval_samples_per_second": 6.429,
+      "eval_steps_per_second": 3.214,
+      "step": 148
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.2775,
+      "step": 149
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00018014136218679567,
+      "loss": 0.3347,
+      "step": 150
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00017936784788148328,
+      "loss": 0.337,
+      "step": 151
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00017858128370482426,
+      "loss": 0.1487,
+      "step": 152
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.3705955445766449,
+      "eval_runtime": 3.1102,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.215,
+      "step": 152
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00017778179898577973,
+      "loss": 0.2416,
+      "step": 153
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00017696952517774062,
+      "loss": 0.2265,
+      "step": 154
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00017614459583691346,
+      "loss": 0.2106,
+      "step": 155
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00017530714660036112,
+      "loss": 0.2873,
+      "step": 156
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 0.37079566717147827,
+      "eval_runtime": 3.1213,
+      "eval_samples_per_second": 6.408,
+      "eval_steps_per_second": 3.204,
+      "step": 156
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001744573151637007,
+      "loss": 0.2134,
+      "step": 157
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0001735952412584635,
+      "loss": 0.3883,
+      "step": 158
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00017272106662911973,
+      "loss": 0.2018,
+      "step": 159
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00017183493500977278,
+      "loss": 0.2786,
+      "step": 160
+    },
+    {
+      "epoch": 1.36,
+      "eval_loss": 0.3699425756931305,
+      "eval_runtime": 3.1068,
+      "eval_samples_per_second": 6.438,
+      "eval_steps_per_second": 3.219,
+      "step": 160
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001709369921005258,
+      "loss": 0.2128,
+      "step": 161
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00017002738554352552,
+      "loss": 0.2264,
+      "step": 162
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00016910626489868649,
+      "loss": 0.3394,
+      "step": 163
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00016817378161909996,
+      "loss": 0.2486,
+      "step": 164
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 0.3689553737640381,
+      "eval_runtime": 3.111,
+      "eval_samples_per_second": 6.429,
+      "eval_steps_per_second": 3.214,
+      "step": 164
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 0.1954,
+      "step": 165
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0001662753422842123,
+      "loss": 0.1786,
+      "step": 166
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00016530969837532487,
+      "loss": 0.2595,
+      "step": 167
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00016433331607319343,
+      "loss": 0.2048,
+      "step": 168
+    },
+    {
+      "epoch": 1.43,
+      "eval_loss": 0.3692178726196289,
+      "eval_runtime": 3.1102,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 168
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00016334635591717703,
+      "loss": 0.1574,
+      "step": 169
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.2797,
+      "step": 170
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00016134135287043669,
+      "loss": 0.2279,
+      "step": 171
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00016032363964761363,
+      "loss": 0.1669,
+      "step": 172
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 0.3703743815422058,
+      "eval_runtime": 3.1096,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 172
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00015929600785250257,
+      "loss": 0.188,
+      "step": 173
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0001582586264510396,
+      "loss": 0.2964,
+      "step": 174
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 0.2548,
+      "step": 175
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0001561552986800375,
+      "loss": 0.2339,
+      "step": 176
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.369620144367218,
+      "eval_runtime": 3.1104,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 176
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00015508969814521025,
+      "loss": 0.3109,
+      "step": 177
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00015401503961659204,
+      "loss": 0.2787,
+      "step": 178
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00015293149979237876,
+      "loss": 0.2867,
+      "step": 179
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00015183925683105254,
+      "loss": 0.2676,
+      "step": 180
+    },
+    {
+      "epoch": 1.54,
+      "eval_loss": 0.3678538203239441,
+      "eval_runtime": 3.1087,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 180
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00015073849032208822,
+      "loss": 0.2537,
+      "step": 181
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00014962938125642503,
+      "loss": 0.23,
+      "step": 182
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00014851211199670721,
+      "loss": 0.1883,
+      "step": 183
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00014738686624729986,
+      "loss": 0.2565,
+      "step": 184
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 0.36626869440078735,
+      "eval_runtime": 3.109,
+      "eval_samples_per_second": 6.433,
+      "eval_steps_per_second": 3.216,
+      "step": 184
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00014625382902408356,
+      "loss": 0.3444,
+      "step": 185
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00014511318662403347,
+      "loss": 0.3072,
+      "step": 186
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00014396512659458824,
+      "loss": 0.2074,
+      "step": 187
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0001428098377028126,
+      "loss": 0.1769,
+      "step": 188
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.367279052734375,
+      "eval_runtime": 3.11,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.215,
+      "step": 188
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0001416475099043599,
+      "loss": 0.2805,
+      "step": 189
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00014047833431223938,
+      "loss": 0.2003,
+      "step": 190
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00013930250316539238,
+      "loss": 0.2478,
+      "step": 191
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00013812020979708418,
+      "loss": 0.2435,
+      "step": 192
+    },
+    {
+      "epoch": 1.64,
+      "eval_loss": 0.3666362464427948,
+      "eval_runtime": 3.1113,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 192
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00013693164860311565,
+      "loss": 0.2149,
+      "step": 193
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001357370150098601,
+      "loss": 0.1893,
+      "step": 194
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00013453650544213076,
+      "loss": 0.2509,
+      "step": 195
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00013333031729088419,
+      "loss": 0.2145,
+      "step": 196
+    },
+    {
+      "epoch": 1.67,
+      "eval_loss": 0.36739152669906616,
+      "eval_runtime": 3.1249,
+      "eval_samples_per_second": 6.4,
+      "eval_steps_per_second": 3.2,
+      "step": 196
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00013211864888076457,
+      "loss": 0.1946,
+      "step": 197
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.2008,
+      "step": 198
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00012967966905511906,
+      "loss": 0.3234,
+      "step": 199
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00012845275866310324,
+      "loss": 0.2082,
+      "step": 200
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 0.36528101563453674,
+      "eval_runtime": 3.1155,
+      "eval_samples_per_second": 6.42,
+      "eval_steps_per_second": 3.21,
+      "step": 200
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00012722116999329712,
+      "loss": 0.2492,
+      "step": 201
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0001259851055467653,
+      "loss": 0.1468,
+      "step": 202
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00012474476856049144,
+      "loss": 0.4099,
+      "step": 203
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00012350036297396154,
+      "loss": 0.2416,
+      "step": 204
+    },
+    {
+      "epoch": 1.74,
+      "eval_loss": 0.3635335862636566,
+      "eval_runtime": 3.1079,
+      "eval_samples_per_second": 6.435,
+      "eval_steps_per_second": 3.218,
+      "step": 204
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.2295,
+      "step": 205
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00012100016506928493,
+      "loss": 0.2825,
+      "step": 206
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00011974478384028672,
+      "loss": 0.303,
+      "step": 207
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00011848615612173688,
+      "loss": 0.1884,
+      "step": 208
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 0.36344197392463684,
+      "eval_runtime": 3.1145,
+      "eval_samples_per_second": 6.422,
+      "eval_steps_per_second": 3.211,
+      "step": 208
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0001172244888605319,
+      "loss": 0.2423,
+      "step": 209
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00011595998950333793,
+      "loss": 0.2338,
+      "step": 210
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00011469286596248181,
+      "loss": 0.246,
+      "step": 211
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00011342332658176555,
+      "loss": 0.275,
+      "step": 212
+    },
+    {
+      "epoch": 1.81,
+      "eval_loss": 0.3634224236011505,
+      "eval_runtime": 3.1116,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 212
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00011215158010221005,
+      "loss": 0.3584,
+      "step": 213
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00011087783562773311,
+      "loss": 0.2247,
+      "step": 214
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00010960230259076818,
+      "loss": 0.2911,
+      "step": 215
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00010832519071782894,
+      "loss": 0.2518,
+      "step": 216
+    },
+    {
+      "epoch": 1.85,
+      "eval_loss": 0.3610054850578308,
+      "eval_runtime": 3.1068,
+      "eval_samples_per_second": 6.437,
+      "eval_steps_per_second": 3.219,
+      "step": 216
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0001070467099950254,
+      "loss": 0.2468,
+      "step": 217
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00010576707063353746,
+      "loss": 0.1837,
+      "step": 218
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00010448648303505151,
+      "loss": 0.355,
+      "step": 219
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00010320515775716555,
+      "loss": 0.2462,
+      "step": 220
+    },
+    {
+      "epoch": 1.88,
+      "eval_loss": 0.36076828837394714,
+      "eval_runtime": 3.112,
+      "eval_samples_per_second": 6.427,
+      "eval_steps_per_second": 3.213,
+      "step": 220
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00010192330547876871,
+      "loss": 0.289,
+      "step": 221
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00010064113696540111,
+      "loss": 0.2711,
+      "step": 222
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 9.93588630345989e-05,
+      "loss": 0.1961,
+      "step": 223
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.80766945212313e-05,
+      "loss": 0.2509,
+      "step": 224
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.36051902174949646,
+      "eval_runtime": 3.1093,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 224
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 0.228,
+      "step": 225
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 9.551351696494854e-05,
+      "loss": 0.2148,
+      "step": 226
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 9.423292936646257e-05,
+      "loss": 0.2076,
+      "step": 227
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 9.29532900049746e-05,
+      "loss": 0.2749,
+      "step": 228
+    },
+    {
+      "epoch": 1.95,
+      "eval_loss": 0.3603048324584961,
+      "eval_runtime": 3.1096,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 228
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 9.167480928217108e-05,
+      "loss": 0.21,
+      "step": 229
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 9.039769740923183e-05,
+      "loss": 0.2771,
+      "step": 230
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 8.912216437226693e-05,
+      "loss": 0.3317,
+      "step": 231
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 8.784841989778996e-05,
+      "loss": 0.2162,
+      "step": 232
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 0.3595748245716095,
+      "eval_runtime": 3.1118,
+      "eval_samples_per_second": 6.427,
+      "eval_steps_per_second": 3.214,
+      "step": 232
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 8.657667341823448e-05,
+      "loss": 0.227,
+      "step": 233
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.530713403751821e-05,
+      "loss": 0.1645,
+      "step": 234
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 0.2724,
+      "step": 235
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 8.277551113946812e-05,
+      "loss": 0.3927,
+      "step": 236
+    },
+    {
+      "epoch": 2.02,
+      "eval_loss": 0.3591071665287018,
+      "eval_runtime": 3.1142,
+      "eval_samples_per_second": 6.422,
+      "eval_steps_per_second": 3.211,
+      "step": 236
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 345,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.199924790778921e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-236/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e119793adec89e061da62a7de24a1a71fb0682ce4c3e3f95d85eab584ad38284
+size 4539

checkpoint-345/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: codellama/CodeLlama-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]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.2.dev0

checkpoint-345/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-345/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f401595b47c3b38a3681abb36daa3be453108ba604a56bd931a2c61ff672b99
+size 319977229

checkpoint-345/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4857539a232e753d3c9a1e26e9b487cef69656ca18421ec02eb38d1a025cf2d
+size 639908613

checkpoint-345/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86693ef0be553da9731a4034081d897e78baa24a8c7b3b7a91fdd78132c6996f
+size 14575

checkpoint-345/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183041b5e7ed7fe25be7309cdaff66dc81489ed30d447e4f3ecd9cf6fd87e9ae
+size 627

checkpoint-345/trainer_state.json

@@ -0,0 +1,2785 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9416846652267816,
+  "eval_steps": 4,
+  "global_step": 345,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.3477,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "eval_loss": 0.4987175166606903,
+      "eval_runtime": 3.1166,
+      "eval_samples_per_second": 6.417,
+      "eval_steps_per_second": 3.209,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.3285,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6e-06,
+      "loss": 0.3754,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.3143,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.4986831247806549,
+      "eval_runtime": 3.101,
+      "eval_samples_per_second": 6.45,
+      "eval_steps_per_second": 3.225,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1e-05,
+      "loss": 0.4661,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.2e-05,
+      "loss": 0.3726,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 0.3515,
+      "step": 7
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.2981,
+      "step": 8
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 0.4983077645301819,
+      "eval_runtime": 3.1103,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.8e-05,
+      "loss": 0.5434,
+      "step": 9
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 0.3998,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.31,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.4e-05,
+      "loss": 0.4314,
+      "step": 12
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.497723788022995,
+      "eval_runtime": 3.1104,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 12
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 0.3478,
+      "step": 13
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.3663,
+      "step": 14
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3e-05,
+      "loss": 0.3981,
+      "step": 15
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.3959,
+      "step": 16
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.49577316641807556,
+      "eval_runtime": 3.1093,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 16
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.4256,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.6e-05,
+      "loss": 0.3393,
+      "step": 18
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.8e-05,
+      "loss": 0.4055,
+      "step": 19
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4e-05,
+      "loss": 0.3353,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.4915711581707001,
+      "eval_runtime": 3.1139,
+      "eval_samples_per_second": 6.423,
+      "eval_steps_per_second": 3.211,
+      "step": 20
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.2e-05,
+      "loss": 0.3431,
+      "step": 21
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.354,
+      "step": 22
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.3472,
+      "step": 23
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.8e-05,
+      "loss": 0.4287,
+      "step": 24
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.4811338782310486,
+      "eval_runtime": 3.1059,
+      "eval_samples_per_second": 6.439,
+      "eval_steps_per_second": 3.22,
+      "step": 24
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5e-05,
+      "loss": 0.3663,
+      "step": 25
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.298,
+      "step": 26
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.3649,
+      "step": 27
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.4018,
+      "step": 28
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.46300894021987915,
+      "eval_runtime": 3.1124,
+      "eval_samples_per_second": 6.426,
+      "eval_steps_per_second": 3.213,
+      "step": 28
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 5.8e-05,
+      "loss": 0.3116,
+      "step": 29
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 6e-05,
+      "loss": 0.3147,
+      "step": 30
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 6.2e-05,
+      "loss": 0.2776,
+      "step": 31
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.3278,
+      "step": 32
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.4446893334388733,
+      "eval_runtime": 3.1075,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 32
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.6e-05,
+      "loss": 0.2848,
+      "step": 33
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.2776,
+      "step": 34
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 7e-05,
+      "loss": 0.3078,
+      "step": 35
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 7.2e-05,
+      "loss": 0.2566,
+      "step": 36
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.4287605881690979,
+      "eval_runtime": 3.1063,
+      "eval_samples_per_second": 6.438,
+      "eval_steps_per_second": 3.219,
+      "step": 36
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.4e-05,
+      "loss": 0.2715,
+      "step": 37
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.6e-05,
+      "loss": 0.3393,
+      "step": 38
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 0.2669,
+      "step": 39
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 8e-05,
+      "loss": 0.3797,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "eval_loss": 0.4169308543205261,
+      "eval_runtime": 3.1074,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 8.2e-05,
+      "loss": 0.2702,
+      "step": 41
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.4e-05,
+      "loss": 0.3824,
+      "step": 42
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.6e-05,
+      "loss": 0.274,
+      "step": 43
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.2966,
+      "step": 44
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.41074520349502563,
+      "eval_runtime": 3.1076,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 44
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9e-05,
+      "loss": 0.485,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.2395,
+      "step": 46
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.4e-05,
+      "loss": 0.3023,
+      "step": 47
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.6e-05,
+      "loss": 0.2676,
+      "step": 48
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.4023456573486328,
+      "eval_runtime": 3.1109,
+      "eval_samples_per_second": 6.429,
+      "eval_steps_per_second": 3.215,
+      "step": 48
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.8e-05,
+      "loss": 0.2378,
+      "step": 49
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001,
+      "loss": 0.2607,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00010200000000000001,
+      "loss": 0.4538,
+      "step": 51
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.2456,
+      "step": 52
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.3957594335079193,
+      "eval_runtime": 3.1123,
+      "eval_samples_per_second": 6.426,
+      "eval_steps_per_second": 3.213,
+      "step": 52
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00010600000000000002,
+      "loss": 0.3435,
+      "step": 53
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.3035,
+      "step": 54
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.3564,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.3267,
+      "step": 56
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.39143189787864685,
+      "eval_runtime": 3.1134,
+      "eval_samples_per_second": 6.424,
+      "eval_steps_per_second": 3.212,
+      "step": 56
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00011399999999999999,
+      "loss": 0.2641,
+      "step": 57
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.000116,
+      "loss": 0.2805,
+      "step": 58
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.000118,
+      "loss": 0.2784,
+      "step": 59
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00012,
+      "loss": 0.2901,
+      "step": 60
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 0.38809266686439514,
+      "eval_runtime": 3.1079,
+      "eval_samples_per_second": 6.435,
+      "eval_steps_per_second": 3.218,
+      "step": 60
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000122,
+      "loss": 0.3039,
+      "step": 61
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.000124,
+      "loss": 0.2035,
+      "step": 62
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.000126,
+      "loss": 0.326,
+      "step": 63
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.1843,
+      "step": 64
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 0.3881237506866455,
+      "eval_runtime": 3.1107,
+      "eval_samples_per_second": 6.429,
+      "eval_steps_per_second": 3.215,
+      "step": 64
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.296,
+      "step": 65
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.000132,
+      "loss": 0.2766,
+      "step": 66
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000134,
+      "loss": 0.304,
+      "step": 67
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.2585,
+      "step": 68
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 0.3869483470916748,
+      "eval_runtime": 3.1091,
+      "eval_samples_per_second": 6.433,
+      "eval_steps_per_second": 3.216,
+      "step": 68
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.000138,
+      "loss": 0.2639,
+      "step": 69
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00014,
+      "loss": 0.3013,
+      "step": 70
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.000142,
+      "loss": 0.4263,
+      "step": 71
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.000144,
+      "loss": 0.3108,
+      "step": 72
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.3839200437068939,
+      "eval_runtime": 3.1098,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.216,
+      "step": 72
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.000146,
+      "loss": 0.4283,
+      "step": 73
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.000148,
+      "loss": 0.2582,
+      "step": 74
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.2703,
+      "step": 75
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.000152,
+      "loss": 0.3799,
+      "step": 76
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 0.3816559314727783,
+      "eval_runtime": 3.1096,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 76
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.000154,
+      "loss": 0.252,
+      "step": 77
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.3297,
+      "step": 78
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 0.2607,
+      "step": 79
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00016,
+      "loss": 0.2064,
+      "step": 80
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 0.37915611267089844,
+      "eval_runtime": 3.1123,
+      "eval_samples_per_second": 6.426,
+      "eval_steps_per_second": 3.213,
+      "step": 80
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000162,
+      "loss": 0.3341,
+      "step": 81
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.000164,
+      "loss": 0.3159,
+      "step": 82
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.000166,
+      "loss": 0.2457,
+      "step": 83
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.000168,
+      "loss": 0.3176,
+      "step": 84
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 0.3792770504951477,
+      "eval_runtime": 3.13,
+      "eval_samples_per_second": 6.39,
+      "eval_steps_per_second": 3.195,
+      "step": 84
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017,
+      "loss": 0.3043,
+      "step": 85
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000172,
+      "loss": 0.2346,
+      "step": 86
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.000174,
+      "loss": 0.2872,
+      "step": 87
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.2307,
+      "step": 88
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.3768787384033203,
+      "eval_runtime": 3.1088,
+      "eval_samples_per_second": 6.433,
+      "eval_steps_per_second": 3.217,
+      "step": 88
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 0.2661,
+      "step": 89
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00018,
+      "loss": 0.3068,
+      "step": 90
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.000182,
+      "loss": 0.2866,
+      "step": 91
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.2826,
+      "step": 92
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.3746011555194855,
+      "eval_runtime": 3.1104,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 92
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 0.4888,
+      "step": 93
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000188,
+      "loss": 0.1667,
+      "step": 94
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00019,
+      "loss": 0.2683,
+      "step": 95
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.000192,
+      "loss": 0.2718,
+      "step": 96
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 0.373685747385025,
+      "eval_runtime": 3.1134,
+      "eval_samples_per_second": 6.424,
+      "eval_steps_per_second": 3.212,
+      "step": 96
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.000194,
+      "loss": 0.2193,
+      "step": 97
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.000196,
+      "loss": 0.378,
+      "step": 98
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 0.2917,
+      "step": 99
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 0.2945,
+      "step": 100
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.3727183938026428,
+      "eval_runtime": 3.1085,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00019999177886783194,
+      "loss": 0.2355,
+      "step": 101
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.000199967116823068,
+      "loss": 0.2656,
+      "step": 102
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00019992601792070679,
+      "loss": 0.2803,
+      "step": 103
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00019986848891833845,
+      "loss": 0.2313,
+      "step": 104
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.371459424495697,
+      "eval_runtime": 3.1114,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 104
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 0.2983,
+      "step": 105
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0001997041811497882,
+      "loss": 0.2547,
+      "step": 106
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00019959742939952392,
+      "loss": 0.2463,
+      "step": 107
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00019947430157664576,
+      "loss": 0.2519,
+      "step": 108
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 0.37180376052856445,
+      "eval_runtime": 3.1113,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 108
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00019933481792615583,
+      "loss": 0.2032,
+      "step": 109
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 0.2868,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001990068775649202,
+      "loss": 0.2653,
+      "step": 111
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00019881847477499557,
+      "loss": 0.2468,
+      "step": 112
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 0.37166160345077515,
+      "eval_runtime": 3.1194,
+      "eval_samples_per_second": 6.412,
+      "eval_steps_per_second": 3.206,
+      "step": 112
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0001986138239902355,
+      "loss": 0.3997,
+      "step": 113
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00019839295885986296,
+      "loss": 0.172,
+      "step": 114
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00019815591569910654,
+      "loss": 0.2713,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001979027334832293,
+      "loss": 0.2034,
+      "step": 116
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.37163203954696655,
+      "eval_runtime": 3.1126,
+      "eval_samples_per_second": 6.425,
+      "eval_steps_per_second": 3.213,
+      "step": 116
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00019763345384112043,
+      "loss": 0.1824,
+      "step": 117
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00019734812104845047,
+      "loss": 0.3669,
+      "step": 118
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0001970467820203915,
+      "loss": 0.229,
+      "step": 119
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 0.2639,
+      "step": 120
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 0.3714464008808136,
+      "eval_runtime": 3.1072,
+      "eval_samples_per_second": 6.437,
+      "eval_steps_per_second": 3.218,
+      "step": 120
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00019639628606958533,
+      "loss": 0.1806,
+      "step": 121
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00019604723610310194,
+      "loss": 0.2209,
+      "step": 122
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00019568239379617088,
+      "loss": 0.2566,
+      "step": 123
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00019530181913712872,
+      "loss": 0.2472,
+      "step": 124
+    },
+    {
+      "epoch": 1.05,
+      "eval_loss": 0.3729495108127594,
+      "eval_runtime": 3.1102,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 124
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00019490557470106686,
+      "loss": 0.2303,
+      "step": 125
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00019449372563954293,
+      "loss": 0.2203,
+      "step": 126
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00019406633966986828,
+      "loss": 0.2226,
+      "step": 127
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00019362348706397373,
+      "loss": 0.1987,
+      "step": 128
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 0.36887192726135254,
+      "eval_runtime": 3.1178,
+      "eval_samples_per_second": 6.415,
+      "eval_steps_per_second": 3.207,
+      "step": 128
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001931652406368554,
+      "loss": 0.1859,
+      "step": 129
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001926916757346022,
+      "loss": 0.2408,
+      "step": 130
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00019220287022200707,
+      "loss": 0.2724,
+      "step": 131
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00019169890446976454,
+      "loss": 0.2296,
+      "step": 132
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.3678927719593048,
+      "eval_runtime": 3.1086,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 132
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001911798613412557,
+      "loss": 0.2069,
+      "step": 133
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0001906458261789238,
+      "loss": 0.2973,
+      "step": 134
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.2468,
+      "step": 135
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001895331334332753,
+      "loss": 0.1542,
+      "step": 136
+    },
+    {
+      "epoch": 1.16,
+      "eval_loss": 0.3685668408870697,
+      "eval_runtime": 3.1094,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 136
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001889546588018412,
+      "loss": 0.2935,
+      "step": 137
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00018836155801026753,
+      "loss": 0.2493,
+      "step": 138
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00018775392857775432,
+      "loss": 0.1597,
+      "step": 139
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00018713187041233896,
+      "loss": 0.1949,
+      "step": 140
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 0.3697265684604645,
+      "eval_runtime": 3.1097,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.216,
+      "step": 140
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00018649548579446936,
+      "loss": 0.2434,
+      "step": 141
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00018584487936018661,
+      "loss": 0.2348,
+      "step": 142
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00018518015808392045,
+      "loss": 0.2946,
+      "step": 143
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00018450143126090015,
+      "loss": 0.2239,
+      "step": 144
+    },
+    {
+      "epoch": 1.22,
+      "eval_loss": 0.36812636256217957,
+      "eval_runtime": 3.1112,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 144
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00018380881048918405,
+      "loss": 0.1824,
+      "step": 145
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00018310240965131041,
+      "loss": 0.302,
+      "step": 146
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00018238234489557215,
+      "loss": 0.3452,
+      "step": 147
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00018164873461691986,
+      "loss": 0.1943,
+      "step": 148
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.3690447211265564,
+      "eval_runtime": 3.111,
+      "eval_samples_per_second": 6.429,
+      "eval_steps_per_second": 3.214,
+      "step": 148
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.2775,
+      "step": 149
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00018014136218679567,
+      "loss": 0.3347,
+      "step": 150
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00017936784788148328,
+      "loss": 0.337,
+      "step": 151
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00017858128370482426,
+      "loss": 0.1487,
+      "step": 152
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.3705955445766449,
+      "eval_runtime": 3.1102,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.215,
+      "step": 152
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00017778179898577973,
+      "loss": 0.2416,
+      "step": 153
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00017696952517774062,
+      "loss": 0.2265,
+      "step": 154
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00017614459583691346,
+      "loss": 0.2106,
+      "step": 155
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00017530714660036112,
+      "loss": 0.2873,
+      "step": 156
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 0.37079566717147827,
+      "eval_runtime": 3.1213,
+      "eval_samples_per_second": 6.408,
+      "eval_steps_per_second": 3.204,
+      "step": 156
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001744573151637007,
+      "loss": 0.2134,
+      "step": 157
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0001735952412584635,
+      "loss": 0.3883,
+      "step": 158
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00017272106662911973,
+      "loss": 0.2018,
+      "step": 159
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00017183493500977278,
+      "loss": 0.2786,
+      "step": 160
+    },
+    {
+      "epoch": 1.36,
+      "eval_loss": 0.3699425756931305,
+      "eval_runtime": 3.1068,
+      "eval_samples_per_second": 6.438,
+      "eval_steps_per_second": 3.219,
+      "step": 160
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.0001709369921005258,
+      "loss": 0.2128,
+      "step": 161
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00017002738554352552,
+      "loss": 0.2264,
+      "step": 162
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00016910626489868649,
+      "loss": 0.3394,
+      "step": 163
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00016817378161909996,
+      "loss": 0.2486,
+      "step": 164
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 0.3689553737640381,
+      "eval_runtime": 3.111,
+      "eval_samples_per_second": 6.429,
+      "eval_steps_per_second": 3.214,
+      "step": 164
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 0.1954,
+      "step": 165
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.0001662753422842123,
+      "loss": 0.1786,
+      "step": 166
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00016530969837532487,
+      "loss": 0.2595,
+      "step": 167
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00016433331607319343,
+      "loss": 0.2048,
+      "step": 168
+    },
+    {
+      "epoch": 1.43,
+      "eval_loss": 0.3692178726196289,
+      "eval_runtime": 3.1102,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 168
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00016334635591717703,
+      "loss": 0.1574,
+      "step": 169
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.2797,
+      "step": 170
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00016134135287043669,
+      "loss": 0.2279,
+      "step": 171
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00016032363964761363,
+      "loss": 0.1669,
+      "step": 172
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 0.3703743815422058,
+      "eval_runtime": 3.1096,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 172
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00015929600785250257,
+      "loss": 0.188,
+      "step": 173
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0001582586264510396,
+      "loss": 0.2964,
+      "step": 174
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 0.2548,
+      "step": 175
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0001561552986800375,
+      "loss": 0.2339,
+      "step": 176
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.369620144367218,
+      "eval_runtime": 3.1104,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 176
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00015508969814521025,
+      "loss": 0.3109,
+      "step": 177
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.00015401503961659204,
+      "loss": 0.2787,
+      "step": 178
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00015293149979237876,
+      "loss": 0.2867,
+      "step": 179
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00015183925683105254,
+      "loss": 0.2676,
+      "step": 180
+    },
+    {
+      "epoch": 1.54,
+      "eval_loss": 0.3678538203239441,
+      "eval_runtime": 3.1087,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 180
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00015073849032208822,
+      "loss": 0.2537,
+      "step": 181
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00014962938125642503,
+      "loss": 0.23,
+      "step": 182
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00014851211199670721,
+      "loss": 0.1883,
+      "step": 183
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00014738686624729986,
+      "loss": 0.2565,
+      "step": 184
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 0.36626869440078735,
+      "eval_runtime": 3.109,
+      "eval_samples_per_second": 6.433,
+      "eval_steps_per_second": 3.216,
+      "step": 184
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00014625382902408356,
+      "loss": 0.3444,
+      "step": 185
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00014511318662403347,
+      "loss": 0.3072,
+      "step": 186
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00014396512659458824,
+      "loss": 0.2074,
+      "step": 187
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0001428098377028126,
+      "loss": 0.1769,
+      "step": 188
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.367279052734375,
+      "eval_runtime": 3.11,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.215,
+      "step": 188
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0001416475099043599,
+      "loss": 0.2805,
+      "step": 189
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00014047833431223938,
+      "loss": 0.2003,
+      "step": 190
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00013930250316539238,
+      "loss": 0.2478,
+      "step": 191
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00013812020979708418,
+      "loss": 0.2435,
+      "step": 192
+    },
+    {
+      "epoch": 1.64,
+      "eval_loss": 0.3666362464427948,
+      "eval_runtime": 3.1113,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 192
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00013693164860311565,
+      "loss": 0.2149,
+      "step": 193
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001357370150098601,
+      "loss": 0.1893,
+      "step": 194
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00013453650544213076,
+      "loss": 0.2509,
+      "step": 195
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00013333031729088419,
+      "loss": 0.2145,
+      "step": 196
+    },
+    {
+      "epoch": 1.67,
+      "eval_loss": 0.36739152669906616,
+      "eval_runtime": 3.1249,
+      "eval_samples_per_second": 6.4,
+      "eval_steps_per_second": 3.2,
+      "step": 196
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00013211864888076457,
+      "loss": 0.1946,
+      "step": 197
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.2008,
+      "step": 198
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00012967966905511906,
+      "loss": 0.3234,
+      "step": 199
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00012845275866310324,
+      "loss": 0.2082,
+      "step": 200
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 0.36528101563453674,
+      "eval_runtime": 3.1155,
+      "eval_samples_per_second": 6.42,
+      "eval_steps_per_second": 3.21,
+      "step": 200
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00012722116999329712,
+      "loss": 0.2492,
+      "step": 201
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0001259851055467653,
+      "loss": 0.1468,
+      "step": 202
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00012474476856049144,
+      "loss": 0.4099,
+      "step": 203
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00012350036297396154,
+      "loss": 0.2416,
+      "step": 204
+    },
+    {
+      "epoch": 1.74,
+      "eval_loss": 0.3635335862636566,
+      "eval_runtime": 3.1079,
+      "eval_samples_per_second": 6.435,
+      "eval_steps_per_second": 3.218,
+      "step": 204
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.2295,
+      "step": 205
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00012100016506928493,
+      "loss": 0.2825,
+      "step": 206
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00011974478384028672,
+      "loss": 0.303,
+      "step": 207
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00011848615612173688,
+      "loss": 0.1884,
+      "step": 208
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 0.36344197392463684,
+      "eval_runtime": 3.1145,
+      "eval_samples_per_second": 6.422,
+      "eval_steps_per_second": 3.211,
+      "step": 208
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.0001172244888605319,
+      "loss": 0.2423,
+      "step": 209
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00011595998950333793,
+      "loss": 0.2338,
+      "step": 210
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00011469286596248181,
+      "loss": 0.246,
+      "step": 211
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00011342332658176555,
+      "loss": 0.275,
+      "step": 212
+    },
+    {
+      "epoch": 1.81,
+      "eval_loss": 0.3634224236011505,
+      "eval_runtime": 3.1116,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 212
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00011215158010221005,
+      "loss": 0.3584,
+      "step": 213
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00011087783562773311,
+      "loss": 0.2247,
+      "step": 214
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00010960230259076818,
+      "loss": 0.2911,
+      "step": 215
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00010832519071782894,
+      "loss": 0.2518,
+      "step": 216
+    },
+    {
+      "epoch": 1.85,
+      "eval_loss": 0.3610054850578308,
+      "eval_runtime": 3.1068,
+      "eval_samples_per_second": 6.437,
+      "eval_steps_per_second": 3.219,
+      "step": 216
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0001070467099950254,
+      "loss": 0.2468,
+      "step": 217
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00010576707063353746,
+      "loss": 0.1837,
+      "step": 218
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00010448648303505151,
+      "loss": 0.355,
+      "step": 219
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00010320515775716555,
+      "loss": 0.2462,
+      "step": 220
+    },
+    {
+      "epoch": 1.88,
+      "eval_loss": 0.36076828837394714,
+      "eval_runtime": 3.112,
+      "eval_samples_per_second": 6.427,
+      "eval_steps_per_second": 3.213,
+      "step": 220
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00010192330547876871,
+      "loss": 0.289,
+      "step": 221
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00010064113696540111,
+      "loss": 0.2711,
+      "step": 222
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 9.93588630345989e-05,
+      "loss": 0.1961,
+      "step": 223
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.80766945212313e-05,
+      "loss": 0.2509,
+      "step": 224
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 0.36051902174949646,
+      "eval_runtime": 3.1093,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 224
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 0.228,
+      "step": 225
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 9.551351696494854e-05,
+      "loss": 0.2148,
+      "step": 226
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 9.423292936646257e-05,
+      "loss": 0.2076,
+      "step": 227
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 9.29532900049746e-05,
+      "loss": 0.2749,
+      "step": 228
+    },
+    {
+      "epoch": 1.95,
+      "eval_loss": 0.3603048324584961,
+      "eval_runtime": 3.1096,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 228
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 9.167480928217108e-05,
+      "loss": 0.21,
+      "step": 229
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 9.039769740923183e-05,
+      "loss": 0.2771,
+      "step": 230
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 8.912216437226693e-05,
+      "loss": 0.3317,
+      "step": 231
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 8.784841989778996e-05,
+      "loss": 0.2162,
+      "step": 232
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 0.3595748245716095,
+      "eval_runtime": 3.1118,
+      "eval_samples_per_second": 6.427,
+      "eval_steps_per_second": 3.214,
+      "step": 232
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 8.657667341823448e-05,
+      "loss": 0.227,
+      "step": 233
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.530713403751821e-05,
+      "loss": 0.1645,
+      "step": 234
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 0.2724,
+      "step": 235
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 8.277551113946812e-05,
+      "loss": 0.3927,
+      "step": 236
+    },
+    {
+      "epoch": 2.02,
+      "eval_loss": 0.3591071665287018,
+      "eval_runtime": 3.1142,
+      "eval_samples_per_second": 6.422,
+      "eval_steps_per_second": 3.211,
+      "step": 236
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 8.151384387826313e-05,
+      "loss": 0.1859,
+      "step": 237
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 8.02552161597133e-05,
+      "loss": 0.1292,
+      "step": 238
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 7.899983493071507e-05,
+      "loss": 0.1601,
+      "step": 239
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 0.2169,
+      "step": 240
+    },
+    {
+      "epoch": 2.03,
+      "eval_loss": 0.36295366287231445,
+      "eval_runtime": 3.1096,
+      "eval_samples_per_second": 6.432,
+      "eval_steps_per_second": 3.216,
+      "step": 240
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 7.649963702603849e-05,
+      "loss": 0.1255,
+      "step": 241
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 7.525523143950859e-05,
+      "loss": 0.1482,
+      "step": 242
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 7.401489445323473e-05,
+      "loss": 0.1793,
+      "step": 243
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 7.27788300067029e-05,
+      "loss": 0.1822,
+      "step": 244
+    },
+    {
+      "epoch": 2.07,
+      "eval_loss": 0.3715473711490631,
+      "eval_runtime": 3.1084,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 244
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 7.154724133689677e-05,
+      "loss": 0.205,
+      "step": 245
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 7.032033094488095e-05,
+      "loss": 0.1724,
+      "step": 246
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.167,
+      "step": 247
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 6.788135111923545e-05,
+      "loss": 0.2968,
+      "step": 248
+    },
+    {
+      "epoch": 2.1,
+      "eval_loss": 0.379179447889328,
+      "eval_runtime": 3.1105,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 248
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 6.666968270911584e-05,
+      "loss": 0.1403,
+      "step": 249
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 6.546349455786926e-05,
+      "loss": 0.1491,
+      "step": 250
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 6.426298499013994e-05,
+      "loss": 0.2384,
+      "step": 251
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 6.306835139688438e-05,
+      "loss": 0.2022,
+      "step": 252
+    },
+    {
+      "epoch": 2.14,
+      "eval_loss": 0.3767882287502289,
+      "eval_runtime": 3.1079,
+      "eval_samples_per_second": 6.435,
+      "eval_steps_per_second": 3.218,
+      "step": 252
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 6.187979020291583e-05,
+      "loss": 0.1408,
+      "step": 253
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 6.069749683460765e-05,
+      "loss": 0.1376,
+      "step": 254
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 5.952166568776062e-05,
+      "loss": 0.175,
+      "step": 255
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 5.835249009564012e-05,
+      "loss": 0.1384,
+      "step": 256
+    },
+    {
+      "epoch": 2.17,
+      "eval_loss": 0.37171897292137146,
+      "eval_runtime": 3.1106,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 256
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 5.7190162297187475e-05,
+      "loss": 0.1422,
+      "step": 257
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 5.60348734054118e-05,
+      "loss": 0.1683,
+      "step": 258
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5.488681337596653e-05,
+      "loss": 0.2688,
+      "step": 259
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 5.37461709759165e-05,
+      "loss": 0.2045,
+      "step": 260
+    },
+    {
+      "epoch": 2.21,
+      "eval_loss": 0.37158870697021484,
+      "eval_runtime": 3.1106,
+      "eval_samples_per_second": 6.43,
+      "eval_steps_per_second": 3.215,
+      "step": 260
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 5.261313375270014e-05,
+      "loss": 0.2776,
+      "step": 261
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 5.148788800329278e-05,
+      "loss": 0.131,
+      "step": 262
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 5.0370618743575026e-05,
+      "loss": 0.2729,
+      "step": 263
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 4.92615096779118e-05,
+      "loss": 0.2492,
+      "step": 264
+    },
+    {
+      "epoch": 2.24,
+      "eval_loss": 0.37324967980384827,
+      "eval_runtime": 3.1091,
+      "eval_samples_per_second": 6.433,
+      "eval_steps_per_second": 3.216,
+      "step": 264
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 4.8160743168947496e-05,
+      "loss": 0.1436,
+      "step": 265
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 4.706850020762126e-05,
+      "loss": 0.1558,
+      "step": 266
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 4.5984960383408005e-05,
+      "loss": 0.1629,
+      "step": 267
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 4.491030185478976e-05,
+      "loss": 0.1719,
+      "step": 268
+    },
+    {
+      "epoch": 2.28,
+      "eval_loss": 0.37554189562797546,
+      "eval_runtime": 3.1081,
+      "eval_samples_per_second": 6.435,
+      "eval_steps_per_second": 3.217,
+      "step": 268
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 4.384470131996252e-05,
+      "loss": 0.2066,
+      "step": 269
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 4.278833398778306e-05,
+      "loss": 0.1934,
+      "step": 270
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 4.174137354896039e-05,
+      "loss": 0.146,
+      "step": 271
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 4.0703992147497425e-05,
+      "loss": 0.1684,
+      "step": 272
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 0.37683507800102234,
+      "eval_runtime": 3.1132,
+      "eval_samples_per_second": 6.424,
+      "eval_steps_per_second": 3.212,
+      "step": 272
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 3.9676360352386356e-05,
+      "loss": 0.1512,
+      "step": 273
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 3.8658647129563364e-05,
+      "loss": 0.2222,
+      "step": 274
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.1904,
+      "step": 275
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 3.665364408282305e-05,
+      "loss": 0.1927,
+      "step": 276
+    },
+    {
+      "epoch": 2.35,
+      "eval_loss": 0.37731653451919556,
+      "eval_runtime": 3.1196,
+      "eval_samples_per_second": 6.411,
+      "eval_steps_per_second": 3.206,
+      "step": 276
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 3.566668392680662e-05,
+      "loss": 0.1277,
+      "step": 277
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 3.469030162467513e-05,
+      "loss": 0.1867,
+      "step": 278
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 3.372465771578771e-05,
+      "loss": 0.2013,
+      "step": 279
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 3.276991097386831e-05,
+      "loss": 0.218,
+      "step": 280
+    },
+    {
+      "epoch": 2.38,
+      "eval_loss": 0.3782224655151367,
+      "eval_runtime": 3.11,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.215,
+      "step": 280
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 3.1826218380900064e-05,
+      "loss": 0.2087,
+      "step": 281
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 3.089373510131354e-05,
+      "loss": 0.2147,
+      "step": 282
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.9972614456474536e-05,
+      "loss": 0.1804,
+      "step": 283
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.9063007899474216e-05,
+      "loss": 0.1984,
+      "step": 284
+    },
+    {
+      "epoch": 2.41,
+      "eval_loss": 0.3790702223777771,
+      "eval_runtime": 3.1101,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.215,
+      "step": 284
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 0.2094,
+      "step": 285
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 2.7278933370880265e-05,
+      "loss": 0.2664,
+      "step": 286
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 2.6404758741536505e-05,
+      "loss": 0.2505,
+      "step": 287
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 2.5542684836299313e-05,
+      "loss": 0.1435,
+      "step": 288
+    },
+    {
+      "epoch": 2.45,
+      "eval_loss": 0.37862634658813477,
+      "eval_runtime": 3.11,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.215,
+      "step": 288
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 2.4692853399638917e-05,
+      "loss": 0.2423,
+      "step": 289
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 2.3855404163086558e-05,
+      "loss": 0.2061,
+      "step": 290
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 2.3030474822259397e-05,
+      "loss": 0.1276,
+      "step": 291
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 2.2218201014220263e-05,
+      "loss": 0.1672,
+      "step": 292
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 0.378492146730423,
+      "eval_runtime": 3.1099,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.215,
+      "step": 292
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 2.141871629517577e-05,
+      "loss": 0.1699,
+      "step": 293
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.063215211851678e-05,
+      "loss": 0.1806,
+      "step": 294
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 0.138,
+      "step": 295
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.1819,
+      "step": 296
+    },
+    {
+      "epoch": 2.52,
+      "eval_loss": 0.37836065888404846,
+      "eval_runtime": 3.1101,
+      "eval_samples_per_second": 6.431,
+      "eval_steps_per_second": 3.215,
+      "step": 296
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.835126538308013e-05,
+      "loss": 0.1794,
+      "step": 297
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.7617655104427832e-05,
+      "loss": 0.18,
+      "step": 298
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.689759034868961e-05,
+      "loss": 0.241,
+      "step": 299
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.619118951081594e-05,
+      "loss": 0.1647,
+      "step": 300
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 0.37813514471054077,
+      "eval_runtime": 3.1084,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 300
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.5498568739099906e-05,
+      "loss": 0.2419,
+      "step": 301
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 1.481984191607959e-05,
+      "loss": 0.1949,
+      "step": 302
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.415512063981339e-05,
+      "loss": 0.144,
+      "step": 303
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 1.350451420553065e-05,
+      "loss": 0.1531,
+      "step": 304
+    },
+    {
+      "epoch": 2.59,
+      "eval_loss": 0.3778517246246338,
+      "eval_runtime": 3.1114,
+      "eval_samples_per_second": 6.428,
+      "eval_steps_per_second": 3.214,
+      "step": 304
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 0.2153,
+      "step": 305
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.224607142224572e-05,
+      "loss": 0.1835,
+      "step": 306
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.1638441989732473e-05,
+      "loss": 0.2181,
+      "step": 307
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.1045341198158831e-05,
+      "loss": 0.2988,
+      "step": 308
+    },
+    {
+      "epoch": 2.62,
+      "eval_loss": 0.37788671255111694,
+      "eval_runtime": 3.1084,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 308
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 1.0466866566724698e-05,
+      "loss": 0.214,
+      "step": 309
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 0.1431,
+      "step": 310
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 9.354173821076184e-06,
+      "loss": 0.2165,
+      "step": 311
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 8.820138658744304e-06,
+      "loss": 0.153,
+      "step": 312
+    },
+    {
+      "epoch": 2.66,
+      "eval_loss": 0.37841156125068665,
+      "eval_runtime": 3.1062,
+      "eval_samples_per_second": 6.439,
+      "eval_steps_per_second": 3.219,
+      "step": 312
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 8.301095530235492e-06,
+      "loss": 0.1963,
+      "step": 313
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 7.797129777992952e-06,
+      "loss": 0.1444,
+      "step": 314
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 0.2277,
+      "step": 315
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.834759363144594e-06,
+      "loss": 0.1877,
+      "step": 316
+    },
+    {
+      "epoch": 2.69,
+      "eval_loss": 0.3786165714263916,
+      "eval_runtime": 3.1085,
+      "eval_samples_per_second": 6.434,
+      "eval_steps_per_second": 3.217,
+      "step": 316
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.37651293602628e-06,
+      "loss": 0.2029,
+      "step": 317
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 5.933660330131752e-06,
+      "loss": 0.2068,
+      "step": 318
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 5.506274360457086e-06,
+      "loss": 0.2556,
+      "step": 319
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 5.094425298933136e-06,
+      "loss": 0.1873,
+      "step": 320
+    },
+    {
+      "epoch": 2.73,
+      "eval_loss": 0.378797322511673,
+      "eval_runtime": 3.108,
+      "eval_samples_per_second": 6.435,
+      "eval_steps_per_second": 3.217,
+      "step": 320
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.698180862871282e-06,
+      "loss": 0.1367,
+      "step": 321
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.317606203829127e-06,
+      "loss": 0.1721,
+      "step": 322
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.952763896898071e-06,
+      "loss": 0.1383,
+      "step": 323
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.6037139304146762e-06,
+      "loss": 0.1722,
+      "step": 324
+    },
+    {
+      "epoch": 2.76,
+      "eval_loss": 0.3789643943309784,
+      "eval_runtime": 3.1067,
+      "eval_samples_per_second": 6.438,
+      "eval_steps_per_second": 3.219,
+      "step": 324
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 0.1906,
+      "step": 325
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.9532179796085356e-06,
+      "loss": 0.207,
+      "step": 326
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.651878951549536e-06,
+      "loss": 0.2667,
+      "step": 327
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 2.36654615887959e-06,
+      "loss": 0.2007,
+      "step": 328
+    },
+    {
+      "epoch": 2.79,
+      "eval_loss": 0.3788919746875763,
+      "eval_runtime": 3.1077,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 328
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.0972665167707126e-06,
+      "loss": 0.2,
+      "step": 329
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.8440843008934561e-06,
+      "loss": 0.169,
+      "step": 330
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.6070411401370334e-06,
+      "loss": 0.1048,
+      "step": 331
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.386176009764506e-06,
+      "loss": 0.266,
+      "step": 332
+    },
+    {
+      "epoch": 2.83,
+      "eval_loss": 0.37898656725883484,
+      "eval_runtime": 3.1077,
+      "eval_samples_per_second": 6.436,
+      "eval_steps_per_second": 3.218,
+      "step": 332
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.1815252250044318e-06,
+      "loss": 0.1435,
+      "step": 333
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 9.931224350798185e-07,
+      "loss": 0.2048,
+      "step": 334
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 0.1466,
+      "step": 335
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 6.651820738441949e-07,
+      "loss": 0.2055,
+      "step": 336
+    },
+    {
+      "epoch": 2.86,
+      "eval_loss": 0.3791235387325287,
+      "eval_runtime": 3.1193,
+      "eval_samples_per_second": 6.412,
+      "eval_steps_per_second": 3.206,
+      "step": 336
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.256984233542595e-07,
+      "loss": 0.1953,
+      "step": 337
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 4.025706004760932e-07,
+      "loss": 0.1906,
+      "step": 338
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 2.9581885021181533e-07,
+      "loss": 0.2208,
+      "step": 339
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2.054607249663665e-07,
+      "loss": 0.2702,
+      "step": 340
+    },
+    {
+      "epoch": 2.9,
+      "eval_loss": 0.3788047134876251,
+      "eval_runtime": 3.1079,
+      "eval_samples_per_second": 6.435,
+      "eval_steps_per_second": 3.218,
+      "step": 340
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.3151108166156168e-07,
+      "loss": 0.2008,
+      "step": 341
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 7.39820792932333e-08,
+      "loss": 0.1559,
+      "step": 342
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.288317693201926e-08,
+      "loss": 0.2126,
+      "step": 343
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 8.221132168073631e-09,
+      "loss": 0.1416,
+      "step": 344
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 0.3789215087890625,
+      "eval_runtime": 3.1064,
+      "eval_samples_per_second": 6.438,
+      "eval_steps_per_second": 3.219,
+      "step": 344
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.0,
+      "loss": 0.1994,
+      "step": 345
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 345,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.757605931903877e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-345/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e119793adec89e061da62a7de24a1a71fb0682ce4c3e3f95d85eab584ad38284
+size 4539

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "codellama/CodeLlama-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32016
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e119793adec89e061da62a7de24a1a71fb0682ce4c3e3f95d85eab584ad38284
+size 4539