initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+mistral-finetune filter=lfs diff=lfs merge=lfs -text

mistral-finetune/checkpoint-10/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## 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 0.6.3.dev0

mistral-finetune/checkpoint-10/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

mistral-finetune/checkpoint-10/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c63d4ef034dce4230fe2889badf30ad55cee5ba9e385d1110ff7d2f35b5f7e0
+size 340225224

mistral-finetune/checkpoint-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df68c3f6f11c9a0cc120521d605201a11d52103ddb67e67caf50ebe524a4f151
+size 170951068

mistral-finetune/checkpoint-10/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b61f55cfd4c21c97ef9c110d90f7c3b398be35ef6c0cee4ee24bf0940d369c2
+size 14244

mistral-finetune/checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70520427b653bb8423e280b7d7c2fe058746573b9bc95b7b9a1d6434d294f84
+size 1064

mistral-finetune/checkpoint-10/trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.025,
+  "eval_steps": 10,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 1726968299520000.0,
+  "trial_name": null,
+  "trial_params": null
+}

mistral-finetune/checkpoint-10/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600

mistral-finetune/checkpoint-100/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## 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 0.6.3.dev0

mistral-finetune/checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

mistral-finetune/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af310d5cf3b1351634e4e0b1f060023d3002be79a937fa5d0262942504088170
+size 340225224

mistral-finetune/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db707e2ce9e6b240070f57c268f24aee523e03a159383bff52ab4e270e17587
+size 170951068

mistral-finetune/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb35848be78a9672c2de9c9ea1cb1d4557f79a6caf73eb10ba23b4d7bd8a3fe
+size 14244

mistral-finetune/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223c492754e7d0cc7c6aeaee1fe7206a93415033615b3379f11649bd0f09644e
+size 1064

mistral-finetune/checkpoint-100/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25,
+  "eval_steps": 10,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.2044088176352705e-05,
+      "loss": 1.578,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.425429344177246,
+      "eval_runtime": 221.7329,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.1543086172344688e-05,
+      "loss": 1.3322,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.4246026277542114,
+      "eval_runtime": 221.7499,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.1042084168336674e-05,
+      "loss": 1.4031,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.4232592582702637,
+      "eval_runtime": 221.7409,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.054108216432866e-05,
+      "loss": 1.454,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.4188882112503052,
+      "eval_runtime": 221.7396,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 90
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.0040080160320643e-05,
+      "loss": 1.4341,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.416797161102295,
+      "eval_runtime": 221.7427,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 1.72696829952e+16,
+  "trial_name": null,
+  "trial_params": null
+}

mistral-finetune/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600

mistral-finetune/checkpoint-110/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## 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 0.6.3.dev0

mistral-finetune/checkpoint-110/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

mistral-finetune/checkpoint-110/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a4a154192e76123afaf4cc8d24337b1a065618eedf4fbf61ca1797ecb2c4dd
+size 340225224

mistral-finetune/checkpoint-110/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed59d79d82c25eba858eaf972b9148fc76e7a8c938933c444dcc4146edb66e3c
+size 170951068

mistral-finetune/checkpoint-110/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de951edb99ec057e0535ef0ec8bb69b7c53da2e3e5d9da128bd471689d04a492
+size 14244

mistral-finetune/checkpoint-110/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a98376fc2f0573046cc61f0f7d3d2abb920e8da027d876164c598937cdba2225
+size 1064

mistral-finetune/checkpoint-110/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.275,
+  "eval_steps": 10,
+  "global_step": 110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.2044088176352705e-05,
+      "loss": 1.578,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.425429344177246,
+      "eval_runtime": 221.7329,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.1543086172344688e-05,
+      "loss": 1.3322,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.4246026277542114,
+      "eval_runtime": 221.7499,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.1042084168336674e-05,
+      "loss": 1.4031,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.4232592582702637,
+      "eval_runtime": 221.7409,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.054108216432866e-05,
+      "loss": 1.454,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.4188882112503052,
+      "eval_runtime": 221.7396,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 90
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.0040080160320643e-05,
+      "loss": 1.4341,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.416797161102295,
+      "eval_runtime": 221.7427,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9539078156312626e-05,
+      "loss": 1.4684,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.4176369905471802,
+      "eval_runtime": 221.7309,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 1.899665129472e+16,
+  "trial_name": null,
+  "trial_params": null
+}

mistral-finetune/checkpoint-110/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600

mistral-finetune/checkpoint-120/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## 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 0.6.3.dev0

mistral-finetune/checkpoint-120/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

mistral-finetune/checkpoint-120/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304b78450733e7f3ebcfb1e54c544d2cffa6f9f4ed2c760b70beda2fe4db5315
+size 340225224

mistral-finetune/checkpoint-120/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4fdaa9307c3654b770d22104b0603837a78c7f2b872c3ffdf0973e4bfa3234
+size 170951068

mistral-finetune/checkpoint-120/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3785253b2a2cd1c32045ff55ab786308b69aa6389827f0371daf27f9e5310394
+size 14244

mistral-finetune/checkpoint-120/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9791fab4c3a763dba5281d6ca071c917b80084acdd9a02fabb44788c90d8f4b
+size 1064

mistral-finetune/checkpoint-120/trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3,
+  "eval_steps": 10,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.304609218436874e-05,
+      "loss": 1.5474,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.430722951889038,
+      "eval_runtime": 221.7555,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.2545090180360722e-05,
+      "loss": 1.3972,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.4295932054519653,
+      "eval_runtime": 221.7379,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.2044088176352705e-05,
+      "loss": 1.578,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.425429344177246,
+      "eval_runtime": 221.7329,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.1543086172344688e-05,
+      "loss": 1.3322,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.4246026277542114,
+      "eval_runtime": 221.7499,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 70
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.1042084168336674e-05,
+      "loss": 1.4031,
+      "step": 80
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.4232592582702637,
+      "eval_runtime": 221.7409,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.054108216432866e-05,
+      "loss": 1.454,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.4188882112503052,
+      "eval_runtime": 221.7396,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 90
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.0040080160320643e-05,
+      "loss": 1.4341,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.416797161102295,
+      "eval_runtime": 221.7427,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9539078156312626e-05,
+      "loss": 1.4684,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.4176369905471802,
+      "eval_runtime": 221.7309,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 110
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.903807615230461e-05,
+      "loss": 1.2462,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 1.4165884256362915,
+      "eval_runtime": 221.7346,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 120
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 2.072361959424e+16,
+  "trial_name": null,
+  "trial_params": null
+}

mistral-finetune/checkpoint-120/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600

mistral-finetune/checkpoint-20/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## 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 0.6.3.dev0

mistral-finetune/checkpoint-20/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

mistral-finetune/checkpoint-20/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a8ea207882ba8096c212ea65254f666345a895ad5518a92200e633d853650ac
+size 340225224

mistral-finetune/checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0086171fbd835609a4716345d0f75122fbeed52d410553a73fd35457f1b3ddff
+size 170951068

mistral-finetune/checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2418da8f729fea94d8af00ab12b2b4d7369a07a94da147759498d89b5d74f6ce
+size 14244

mistral-finetune/checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9aa8d6b210f5857d64e00d2d5b5bf8d1606b011a7810b84dbbb874aedd0d56e
+size 1064

mistral-finetune/checkpoint-20/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05,
+  "eval_steps": 10,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 3453936599040000.0,
+  "trial_name": null,
+  "trial_params": null
+}

mistral-finetune/checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600

mistral-finetune/checkpoint-30/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## 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 0.6.3.dev0

mistral-finetune/checkpoint-30/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "filipealmeida/Mistral-7B-v0.1-sharded",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

mistral-finetune/checkpoint-30/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20f7e366d48ae58f58911c8a8b1a34de310010037a1dc3f15e481b77a9b78dc
+size 340225224

mistral-finetune/checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d78cae13032442b0c5f29a7138cc9f6cc8ca89798ad01096f50dc49163b0740
+size 170951068

mistral-finetune/checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a381c2e890979e6338e01c3198be40d18103ef1cf97f05c682cfd1dc6ee504
+size 14244

mistral-finetune/checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e32004f632ac46e32797254a8bbdba4c1bc2a634bf0de930a2f2c3db5631a8f
+size 1064

mistral-finetune/checkpoint-30/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.075,
+  "eval_steps": 10,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4549098196392788e-05,
+      "loss": 1.5765,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.4641923904418945,
+      "eval_runtime": 221.9956,
+      "eval_samples_per_second": 0.901,
+      "eval_steps_per_second": 0.113,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.404809619238477e-05,
+      "loss": 1.5681,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.4410793781280518,
+      "eval_runtime": 221.7333,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.3547094188376757e-05,
+      "loss": 1.2801,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.4293081760406494,
+      "eval_runtime": 221.7604,
+      "eval_samples_per_second": 0.902,
+      "eval_steps_per_second": 0.113,
+      "step": 30
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 10,
+  "total_flos": 5180904898560000.0,
+  "trial_name": null,
+  "trial_params": null
+}

mistral-finetune/checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa60f08d6af67edbafca8b9cbcbb0067beec5a9a8336ba7c9d20d4d84336c11f
+size 4600

mistral-finetune/checkpoint-40/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: filipealmeida/Mistral-7B-v0.1-sharded
+---
+
+# 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]
+
+
+## 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 0.6.3.dev0