add checkpoints

README.md

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

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-100/README.md

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

checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f874f4ba3edc90052241c7717501a02655e2297360d14d56b72da1cb37c3ff50
+size 134433530

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83980e6918d10a8b78990790050b48770758bad20f2137d55b21afba343f8ba
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1553fa3c9fa4158c1d95c29f303ea1c82da9959617b77d6296624e38c6ca27
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.16326530612245,
+  "eval_steps": 20,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.7509,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.6967,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 1.6115258932113647,
+      "eval_runtime": 30.6688,
+      "eval_samples_per_second": 12.619,
+      "eval_steps_per_second": 1.598,
+      "step": 20
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.5138,
+      "step": 30
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.0417,
+      "step": 40
+    },
+    {
+      "epoch": 3.27,
+      "eval_loss": 0.5990618467330933,
+      "eval_runtime": 45.282,
+      "eval_samples_per_second": 8.546,
+      "eval_steps_per_second": 1.082,
+      "step": 40
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.00015,
+      "loss": 0.4159,
+      "step": 50
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.3112,
+      "step": 60
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": 0.277026891708374,
+      "eval_runtime": 30.7302,
+      "eval_samples_per_second": 12.593,
+      "eval_steps_per_second": 1.595,
+      "step": 60
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.285,
+      "step": 70
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.27,
+      "step": 80
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": 0.24872899055480957,
+      "eval_runtime": 30.6498,
+      "eval_samples_per_second": 12.627,
+      "eval_steps_per_second": 1.599,
+      "step": 80
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 0.00027,
+      "loss": 0.2464,
+      "step": 90
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 0.0003,
+      "loss": 0.2276,
+      "step": 100
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": 0.22304466366767883,
+      "eval_runtime": 30.6362,
+      "eval_samples_per_second": 12.632,
+      "eval_steps_per_second": 1.599,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 2.5467399903903744e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d1856a7e88d5d206461b4fada83bde140b82a5a28df09559656cee017c5bce
+size 4664

checkpoint-120/README.md

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

checkpoint-120/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-120/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb63a7e3bd7b955d6919ac92ce44c227ae1fd0f5f284eb71d353294d5e45da6c
+size 134433530

checkpoint-120/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f836e8affa585842a356aad502d328cdc3e50fea8fcc717e527e492c41fee1
+size 14244

checkpoint-120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:915b81b2641ff3c1c29a91260eaebd9d13138742f1687cfcdc8c68bcb9ea698e
+size 1064

checkpoint-120/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.795918367346939,
+  "eval_steps": 20,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.7509,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.6967,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 1.6115258932113647,
+      "eval_runtime": 30.6688,
+      "eval_samples_per_second": 12.619,
+      "eval_steps_per_second": 1.598,
+      "step": 20
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.5138,
+      "step": 30
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.0417,
+      "step": 40
+    },
+    {
+      "epoch": 3.27,
+      "eval_loss": 0.5990618467330933,
+      "eval_runtime": 45.282,
+      "eval_samples_per_second": 8.546,
+      "eval_steps_per_second": 1.082,
+      "step": 40
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.00015,
+      "loss": 0.4159,
+      "step": 50
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.3112,
+      "step": 60
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": 0.277026891708374,
+      "eval_runtime": 30.7302,
+      "eval_samples_per_second": 12.593,
+      "eval_steps_per_second": 1.595,
+      "step": 60
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.285,
+      "step": 70
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.27,
+      "step": 80
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": 0.24872899055480957,
+      "eval_runtime": 30.6498,
+      "eval_samples_per_second": 12.627,
+      "eval_steps_per_second": 1.599,
+      "step": 80
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 0.00027,
+      "loss": 0.2464,
+      "step": 90
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 0.0003,
+      "loss": 0.2276,
+      "step": 100
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": 0.22304466366767883,
+      "eval_runtime": 30.6362,
+      "eval_samples_per_second": 12.632,
+      "eval_steps_per_second": 1.599,
+      "step": 100
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 0.00029,
+      "loss": 0.1993,
+      "step": 110
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 0.00028,
+      "loss": 0.1747,
+      "step": 120
+    },
+    {
+      "epoch": 9.8,
+      "eval_loss": 0.20949400961399078,
+      "eval_runtime": 30.5837,
+      "eval_samples_per_second": 12.654,
+      "eval_steps_per_second": 1.602,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 3.057919443515474e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d1856a7e88d5d206461b4fada83bde140b82a5a28df09559656cee017c5bce
+size 4664

checkpoint-140/README.md

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

checkpoint-140/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-140/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38597b5c11e9032f7857b2d4dca90788fcf80f6c01eba76d19895569d98c4028
+size 134433530

checkpoint-140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6ff023b8ad03758e2bf7962e97407004f6fa05830ced892f656565e28339a5
+size 14244

checkpoint-140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d5f7e9b17251247c39fdd59964f3693734ddb120bd20dcb453e9efae1445bd
+size 1064

checkpoint-140/trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.428571428571429,
+  "eval_steps": 20,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.7509,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.6967,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 1.6115258932113647,
+      "eval_runtime": 30.6688,
+      "eval_samples_per_second": 12.619,
+      "eval_steps_per_second": 1.598,
+      "step": 20
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.5138,
+      "step": 30
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.0417,
+      "step": 40
+    },
+    {
+      "epoch": 3.27,
+      "eval_loss": 0.5990618467330933,
+      "eval_runtime": 45.282,
+      "eval_samples_per_second": 8.546,
+      "eval_steps_per_second": 1.082,
+      "step": 40
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.00015,
+      "loss": 0.4159,
+      "step": 50
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.3112,
+      "step": 60
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": 0.277026891708374,
+      "eval_runtime": 30.7302,
+      "eval_samples_per_second": 12.593,
+      "eval_steps_per_second": 1.595,
+      "step": 60
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.285,
+      "step": 70
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.27,
+      "step": 80
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": 0.24872899055480957,
+      "eval_runtime": 30.6498,
+      "eval_samples_per_second": 12.627,
+      "eval_steps_per_second": 1.599,
+      "step": 80
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 0.00027,
+      "loss": 0.2464,
+      "step": 90
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 0.0003,
+      "loss": 0.2276,
+      "step": 100
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": 0.22304466366767883,
+      "eval_runtime": 30.6362,
+      "eval_samples_per_second": 12.632,
+      "eval_steps_per_second": 1.599,
+      "step": 100
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 0.00029,
+      "loss": 0.1993,
+      "step": 110
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 0.00028,
+      "loss": 0.1747,
+      "step": 120
+    },
+    {
+      "epoch": 9.8,
+      "eval_loss": 0.20949400961399078,
+      "eval_runtime": 30.5837,
+      "eval_samples_per_second": 12.654,
+      "eval_steps_per_second": 1.602,
+      "step": 120
+    },
+    {
+      "epoch": 10.61,
+      "learning_rate": 0.00027,
+      "loss": 0.1408,
+      "step": 130
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 0.00026,
+      "loss": 0.1131,
+      "step": 140
+    },
+    {
+      "epoch": 11.43,
+      "eval_loss": 0.20713694393634796,
+      "eval_runtime": 30.5887,
+      "eval_samples_per_second": 12.652,
+      "eval_steps_per_second": 1.602,
+      "step": 140
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 3.565334239043912e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d1856a7e88d5d206461b4fada83bde140b82a5a28df09559656cee017c5bce
+size 4664

checkpoint-160/README.md

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

checkpoint-160/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-160/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-160/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d666de4a36e9f322bf3bc17b971294f63e1062b91f96c542029442ec23e59c
+size 134433530

checkpoint-160/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696df26525098d79bb3e3b139111645ab2642f9fe3067f1ce1eb4c0c8eead651
+size 14244

checkpoint-160/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bc91ca4e04e59b6aa0def614e5d23daa02dfd514357b40e48edfe0bf128e03
+size 1064

checkpoint-160/trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.061224489795919,
+  "eval_steps": 20,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.7509,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.6967,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 1.6115258932113647,
+      "eval_runtime": 30.6688,
+      "eval_samples_per_second": 12.619,
+      "eval_steps_per_second": 1.598,
+      "step": 20
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.5138,
+      "step": 30
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.0417,
+      "step": 40
+    },
+    {
+      "epoch": 3.27,
+      "eval_loss": 0.5990618467330933,
+      "eval_runtime": 45.282,
+      "eval_samples_per_second": 8.546,
+      "eval_steps_per_second": 1.082,
+      "step": 40
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.00015,
+      "loss": 0.4159,
+      "step": 50
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.3112,
+      "step": 60
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": 0.277026891708374,
+      "eval_runtime": 30.7302,
+      "eval_samples_per_second": 12.593,
+      "eval_steps_per_second": 1.595,
+      "step": 60
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.285,
+      "step": 70
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.27,
+      "step": 80
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": 0.24872899055480957,
+      "eval_runtime": 30.6498,
+      "eval_samples_per_second": 12.627,
+      "eval_steps_per_second": 1.599,
+      "step": 80
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 0.00027,
+      "loss": 0.2464,
+      "step": 90
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 0.0003,
+      "loss": 0.2276,
+      "step": 100
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": 0.22304466366767883,
+      "eval_runtime": 30.6362,
+      "eval_samples_per_second": 12.632,
+      "eval_steps_per_second": 1.599,
+      "step": 100
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 0.00029,
+      "loss": 0.1993,
+      "step": 110
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 0.00028,
+      "loss": 0.1747,
+      "step": 120
+    },
+    {
+      "epoch": 9.8,
+      "eval_loss": 0.20949400961399078,
+      "eval_runtime": 30.5837,
+      "eval_samples_per_second": 12.654,
+      "eval_steps_per_second": 1.602,
+      "step": 120
+    },
+    {
+      "epoch": 10.61,
+      "learning_rate": 0.00027,
+      "loss": 0.1408,
+      "step": 130
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 0.00026,
+      "loss": 0.1131,
+      "step": 140
+    },
+    {
+      "epoch": 11.43,
+      "eval_loss": 0.20713694393634796,
+      "eval_runtime": 30.5887,
+      "eval_samples_per_second": 12.652,
+      "eval_steps_per_second": 1.602,
+      "step": 140
+    },
+    {
+      "epoch": 12.24,
+      "learning_rate": 0.00025,
+      "loss": 0.0839,
+      "step": 150
+    },
+    {
+      "epoch": 13.06,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.0644,
+      "step": 160
+    },
+    {
+      "epoch": 13.06,
+      "eval_loss": 0.2342994511127472,
+      "eval_runtime": 30.5213,
+      "eval_samples_per_second": 12.68,
+      "eval_steps_per_second": 1.605,
+      "step": 160
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 4.0727490345723494e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d1856a7e88d5d206461b4fada83bde140b82a5a28df09559656cee017c5bce
+size 4664

checkpoint-180/README.md

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

checkpoint-180/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-180/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8197ec33e4b8ca50ad19f31fddddc89bd576aa2c9094368dd4313d6168435d5c
+size 134433530

checkpoint-180/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba0b981dc12239aaf4850646865bbde8668564ad7178501587a5c65a1da4333
+size 14244

checkpoint-180/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5dfc3bc75009efe48747cf9948a244ecefe4e6b758242f83bed075794e9a377
+size 1064

checkpoint-180/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.693877551020408,
+  "eval_steps": 20,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.7509,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.6967,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 1.6115258932113647,
+      "eval_runtime": 30.6688,
+      "eval_samples_per_second": 12.619,
+      "eval_steps_per_second": 1.598,
+      "step": 20
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.5138,
+      "step": 30
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.0417,
+      "step": 40
+    },
+    {
+      "epoch": 3.27,
+      "eval_loss": 0.5990618467330933,
+      "eval_runtime": 45.282,
+      "eval_samples_per_second": 8.546,
+      "eval_steps_per_second": 1.082,
+      "step": 40
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 0.00015,
+      "loss": 0.4159,
+      "step": 50
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.3112,
+      "step": 60
+    },
+    {
+      "epoch": 4.9,
+      "eval_loss": 0.277026891708374,
+      "eval_runtime": 30.7302,
+      "eval_samples_per_second": 12.593,
+      "eval_steps_per_second": 1.595,
+      "step": 60
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.285,
+      "step": 70
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.27,
+      "step": 80
+    },
+    {
+      "epoch": 6.53,
+      "eval_loss": 0.24872899055480957,
+      "eval_runtime": 30.6498,
+      "eval_samples_per_second": 12.627,
+      "eval_steps_per_second": 1.599,
+      "step": 80
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 0.00027,
+      "loss": 0.2464,
+      "step": 90
+    },
+    {
+      "epoch": 8.16,
+      "learning_rate": 0.0003,
+      "loss": 0.2276,
+      "step": 100
+    },
+    {
+      "epoch": 8.16,
+      "eval_loss": 0.22304466366767883,
+      "eval_runtime": 30.6362,
+      "eval_samples_per_second": 12.632,
+      "eval_steps_per_second": 1.599,
+      "step": 100
+    },
+    {
+      "epoch": 8.98,
+      "learning_rate": 0.00029,
+      "loss": 0.1993,
+      "step": 110
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 0.00028,
+      "loss": 0.1747,
+      "step": 120
+    },
+    {
+      "epoch": 9.8,
+      "eval_loss": 0.20949400961399078,
+      "eval_runtime": 30.5837,
+      "eval_samples_per_second": 12.654,
+      "eval_steps_per_second": 1.602,
+      "step": 120
+    },
+    {
+      "epoch": 10.61,
+      "learning_rate": 0.00027,
+      "loss": 0.1408,
+      "step": 130
+    },
+    {
+      "epoch": 11.43,
+      "learning_rate": 0.00026,
+      "loss": 0.1131,
+      "step": 140
+    },
+    {
+      "epoch": 11.43,
+      "eval_loss": 0.20713694393634796,
+      "eval_runtime": 30.5887,
+      "eval_samples_per_second": 12.652,
+      "eval_steps_per_second": 1.602,
+      "step": 140
+    },
+    {
+      "epoch": 12.24,
+      "learning_rate": 0.00025,
+      "loss": 0.0839,
+      "step": 150
+    },
+    {
+      "epoch": 13.06,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.0644,
+      "step": 160
+    },
+    {
+      "epoch": 13.06,
+      "eval_loss": 0.2342994511127472,
+      "eval_runtime": 30.5213,
+      "eval_samples_per_second": 12.68,
+      "eval_steps_per_second": 1.605,
+      "step": 160
+    },
+    {
+      "epoch": 13.88,
+      "learning_rate": 0.00023,
+      "loss": 0.0466,
+      "step": 170
+    },
+    {
+      "epoch": 14.69,
+      "learning_rate": 0.00021999999999999995,
+      "loss": 0.0365,
+      "step": 180
+    },
+    {
+      "epoch": 14.69,
+      "eval_loss": 0.263688862323761,
+      "eval_runtime": 30.5969,
+      "eval_samples_per_second": 12.648,
+      "eval_steps_per_second": 1.601,
+      "step": 180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 4.584742467718349e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-180/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d1856a7e88d5d206461b4fada83bde140b82a5a28df09559656cee017c5bce
+size 4664

checkpoint-20/README.md

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

checkpoint-20/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-20/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b3740dfb324e345a0eea52b52c7c4e483dda810c019fad2bf567e2b9726fff
+size 134433530

checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f61e883dcc30853d98a024849c79c146662f7571765d5c6ec7e0f3fc38c998c0
+size 14244

checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc30782c80f39b95ece53e16ed533d0eb1d775796dc4d2c39691e355b142ab4
+size 1064

checkpoint-20/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6326530612244898,
+  "eval_steps": 20,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.7509,
+      "step": 10
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.6967,
+      "step": 20
+    },
+    {
+      "epoch": 1.63,
+      "eval_loss": 1.6115258932113647,
+      "eval_runtime": 30.6688,
+      "eval_samples_per_second": 12.619,
+      "eval_steps_per_second": 1.598,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 20,
+  "total_flos": 5.116881906381619e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}