A Lora Of BlackSheep Vision For Phi-3-Mini

BlackSheepVision-Phi-3/README.md

@@ -0,0 +1,202 @@
+---
+base_model: models\microsoft_Phi-3-vision-128k-instruct
+library_name: peft
+---
+
+# 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 0.12.0

BlackSheepVision-Phi-3/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models\\microsoft_Phi-3-vision-128k-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 4096,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 2048,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

BlackSheepVision-Phi-3/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7563b9393a75fd8525e5eba4c801f65a93ead90ddbc23f21ae202aada3242e
+size 5771408256

BlackSheepVision-Phi-3/checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: models\microsoft_Phi-3-vision-128k-instruct
+library_name: peft
+---
+
+# 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 0.12.0

BlackSheepVision-Phi-3/checkpoint-1000/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models\\microsoft_Phi-3-vision-128k-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 4096,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 2048,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

BlackSheepVision-Phi-3/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29aabdd5ebb2c0f9f9ca3e53f8f185afce27f1217865a83db49c9f645533bff7
+size 5771408256

BlackSheepVision-Phi-3/checkpoint-1000/training_log.json

@@ -0,0 +1,12 @@
+{
+  "base_model_name": "microsoft_Phi-3-vision-128k-instruct",
+  "base_model_class": "Phi3VForCausalLM",
+  "base_loaded_in_4bit": true,
+  "base_loaded_in_8bit": false,
+  "projections": "gate, down, up, q, v, k, o",
+  "loss": 1.0155,
+  "grad_norm": 0.855490505695343,
+  "learning_rate": 9.886842462960446e-05,
+  "epoch": 0.47573739295908657,
+  "current_steps": 999
+}

BlackSheepVision-Phi-3/checkpoint-1000/training_prompt.json

@@ -0,0 +1,16 @@
+{
+  "template_type": "dataset",
+  "template_1": "Who is your creator?\n\n%creator%",
+  "template_2": "%ChatML_CONVO%",
+  "template_3": "<|im_start|> I want you to say this next statement like a Gen-Z. \n %English% \n <|im_start|> %Gen-Z% <|im_end|>",
+  "template_4": "<|im_start|> %prompt% \n <|im_start|> %output% <|im_end|>",
+  "template_5": "<|im_start|> %instruction% \n <|im_start|> %output% <|im_end|>",
+  "template_6": "<|im_start|> %instruction%\n %input%\n <|im_start|> %output% <|im_end|>",
+  "template_7": "<|im_start|> %question% \n <|im_start|> %output% <|im_end|>",
+  "template_8": "<|im_start|> %question% \n <|im_start|> %response% <|im_end|>",
+  "template_9": "<|im_start|> %perspective% \n <|im_start|> %output% <|im_end|>",
+  "template_10": "<|im_start|> %perspective%\n %input%\n <|im_start|> %output% <|im_end|>",
+  "template_11": "<|im_start|> %instruction% \n <|im_start|> %toxic% <|im_end|>",
+  "template_12": "<|im_start|> %prompt% \n <|im_start|> %chosen% <|im_end|>",
+  "template_13": "<|im_start|> system\n : %system% \n <|im_end|> \n <|im_start|> %user% \n <|im_end|> \n <|im_start|> %assistant%"
+}

BlackSheepVision-Phi-3/checkpoint-2000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: models\microsoft_Phi-3-vision-128k-instruct
+library_name: peft
+---
+
+# 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 0.12.0

BlackSheepVision-Phi-3/checkpoint-2000/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models\\microsoft_Phi-3-vision-128k-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 4096,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 2048,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

BlackSheepVision-Phi-3/checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155b56140389f259fd74c3724efdca122ba6c3563feed3f652874f63e453fec7
+size 5771408256

BlackSheepVision-Phi-3/checkpoint-2000/training_log.json

@@ -0,0 +1,12 @@
+{
+  "base_model_name": "microsoft_Phi-3-vision-128k-instruct",
+  "base_model_class": "Phi3VForCausalLM",
+  "base_loaded_in_4bit": true,
+  "base_loaded_in_8bit": false,
+  "projections": "gate, down, up, q, v, k, o",
+  "loss": 0.9775,
+  "grad_norm": 1.721966028213501,
+  "learning_rate": 9.773684925920892e-05,
+  "epoch": 0.9514747859181731,
+  "current_steps": 1999
+}

BlackSheepVision-Phi-3/checkpoint-2000/training_prompt.json

@@ -0,0 +1,16 @@
+{
+  "template_type": "dataset",
+  "template_1": "Who is your creator?\n\n%creator%",
+  "template_2": "%ChatML_CONVO%",
+  "template_3": "<|im_start|> I want you to say this next statement like a Gen-Z. \n %English% \n <|im_start|> %Gen-Z% <|im_end|>",
+  "template_4": "<|im_start|> %prompt% \n <|im_start|> %output% <|im_end|>",
+  "template_5": "<|im_start|> %instruction% \n <|im_start|> %output% <|im_end|>",
+  "template_6": "<|im_start|> %instruction%\n %input%\n <|im_start|> %output% <|im_end|>",
+  "template_7": "<|im_start|> %question% \n <|im_start|> %output% <|im_end|>",
+  "template_8": "<|im_start|> %question% \n <|im_start|> %response% <|im_end|>",
+  "template_9": "<|im_start|> %perspective% \n <|im_start|> %output% <|im_end|>",
+  "template_10": "<|im_start|> %perspective%\n %input%\n <|im_start|> %output% <|im_end|>",
+  "template_11": "<|im_start|> %instruction% \n <|im_start|> %toxic% <|im_end|>",
+  "template_12": "<|im_start|> %prompt% \n <|im_start|> %chosen% <|im_end|>",
+  "template_13": "<|im_start|> system\n : %system% \n <|im_end|> \n <|im_start|> %user% \n <|im_end|> \n <|im_start|> %assistant%"
+}

BlackSheepVision-Phi-3/checkpoint-3000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: models\microsoft_Phi-3-vision-128k-instruct
+library_name: peft
+---
+
+# 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 0.12.0

BlackSheepVision-Phi-3/checkpoint-3000/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models\\microsoft_Phi-3-vision-128k-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 4096,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 2048,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

BlackSheepVision-Phi-3/checkpoint-3000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f506d681fc893c8d5306386ad1e56f5feaaf3eecbf94a3bf92c0a6d35a33a4
+size 5771408256

BlackSheepVision-Phi-3/checkpoint-3000/training_log.json

@@ -0,0 +1,12 @@
+{
+  "base_model_name": "microsoft_Phi-3-vision-128k-instruct",
+  "base_model_class": "Phi3VForCausalLM",
+  "base_loaded_in_4bit": true,
+  "base_loaded_in_8bit": false,
+  "projections": "gate, down, up, q, v, k, o",
+  "loss": 0.5155,
+  "grad_norm": 1.1744245290756226,
+  "learning_rate": 9.660527388881338e-05,
+  "epoch": 1.4272121788772598,
+  "current_steps": 2999
+}

BlackSheepVision-Phi-3/checkpoint-3000/training_prompt.json

@@ -0,0 +1,16 @@
+{
+  "template_type": "dataset",
+  "template_1": "Who is your creator?\n\n%creator%",
+  "template_2": "%ChatML_CONVO%",
+  "template_3": "<|im_start|> I want you to say this next statement like a Gen-Z. \n %English% \n <|im_start|> %Gen-Z% <|im_end|>",
+  "template_4": "<|im_start|> %prompt% \n <|im_start|> %output% <|im_end|>",
+  "template_5": "<|im_start|> %instruction% \n <|im_start|> %output% <|im_end|>",
+  "template_6": "<|im_start|> %instruction%\n %input%\n <|im_start|> %output% <|im_end|>",
+  "template_7": "<|im_start|> %question% \n <|im_start|> %output% <|im_end|>",
+  "template_8": "<|im_start|> %question% \n <|im_start|> %response% <|im_end|>",
+  "template_9": "<|im_start|> %perspective% \n <|im_start|> %output% <|im_end|>",
+  "template_10": "<|im_start|> %perspective%\n %input%\n <|im_start|> %output% <|im_end|>",
+  "template_11": "<|im_start|> %instruction% \n <|im_start|> %toxic% <|im_end|>",
+  "template_12": "<|im_start|> %prompt% \n <|im_start|> %chosen% <|im_end|>",
+  "template_13": "<|im_start|> system\n : %system% \n <|im_end|> \n <|im_start|> %user% \n <|im_end|> \n <|im_start|> %assistant%"
+}

BlackSheepVision-Phi-3/checkpoint-4000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: models\microsoft_Phi-3-vision-128k-instruct
+library_name: peft
+---
+
+# 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 0.12.0

BlackSheepVision-Phi-3/checkpoint-4000/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "models\\microsoft_Phi-3-vision-128k-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 4096,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 2048,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

BlackSheepVision-Phi-3/checkpoint-4000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e15d106bbc8ea868b631b6263e27c80d0d16bdf27ef70c23e92db1c5b07f35ae
+size 5771408256

BlackSheepVision-Phi-3/checkpoint-4000/training_log.json

@@ -0,0 +1,12 @@
+{
+  "base_model_name": "microsoft_Phi-3-vision-128k-instruct",
+  "base_model_class": "Phi3VForCausalLM",
+  "base_loaded_in_4bit": true,
+  "base_loaded_in_8bit": false,
+  "projections": "gate, down, up, q, v, k, o",
+  "loss": 0.649,
+  "grad_norm": 1.225587248802185,
+  "learning_rate": 9.547369851841784e-05,
+  "epoch": 1.9029495718363463,
+  "current_steps": 3999
+}

BlackSheepVision-Phi-3/checkpoint-4000/training_prompt.json

@@ -0,0 +1,16 @@
+{
+  "template_type": "dataset",
+  "template_1": "Who is your creator?\n\n%creator%",
+  "template_2": "%ChatML_CONVO%",
+  "template_3": "<|im_start|> I want you to say this next statement like a Gen-Z. \n %English% \n <|im_start|> %Gen-Z% <|im_end|>",
+  "template_4": "<|im_start|> %prompt% \n <|im_start|> %output% <|im_end|>",
+  "template_5": "<|im_start|> %instruction% \n <|im_start|> %output% <|im_end|>",
+  "template_6": "<|im_start|> %instruction%\n %input%\n <|im_start|> %output% <|im_end|>",
+  "template_7": "<|im_start|> %question% \n <|im_start|> %output% <|im_end|>",
+  "template_8": "<|im_start|> %question% \n <|im_start|> %response% <|im_end|>",
+  "template_9": "<|im_start|> %perspective% \n <|im_start|> %output% <|im_end|>",
+  "template_10": "<|im_start|> %perspective%\n %input%\n <|im_start|> %output% <|im_end|>",
+  "template_11": "<|im_start|> %instruction% \n <|im_start|> %toxic% <|im_end|>",
+  "template_12": "<|im_start|> %prompt% \n <|im_start|> %chosen% <|im_end|>",
+  "template_13": "<|im_start|> system\n : %system% \n <|im_end|> \n <|im_start|> %user% \n <|im_end|> \n <|im_start|> %assistant%"
+}

BlackSheepVision-Phi-3/runs/Aug10_10-40-54_Troy-New-PC/events.out.tfevents.1723311654.Troy-New-PC.22016.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:099c012ba940bb7d2e790d86a7c955fc0f4ed8cb5245bdde209a7a29d5eb43c2
+size 63880

BlackSheepVision-Phi-3/runs/Aug10_15-02-36_Troy-New-PC/events.out.tfevents.1723327356.Troy-New-PC.19660.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c5a67d71062f0d9d8248bed764eed4575f8a7717b22b4899c55734fab5e4ff
+size 6358

BlackSheepVision-Phi-3/runs/Aug10_15-12-06_Troy-New-PC/events.out.tfevents.1723327926.Troy-New-PC.19660.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f698f4c18c619fe51ffea7ba82fd68d3f9048c018bb98b633a84005a8c7e65
+size 6346

BlackSheepVision-Phi-3/runs/Aug10_15-40-50_Troy-New-PC/events.out.tfevents.1723329650.Troy-New-PC.19660.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b7fc195da52fd1b181e23b725973caa6408e88358ac01d297dbed180655770
+size 6553

BlackSheepVision-Phi-3/runs/Aug10_15-48-28_Troy-New-PC/events.out.tfevents.1723330108.Troy-New-PC.19660.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b83801e1c45219db42779330b54432ee8d0681a650926ebfa588ca25c82282
+size 5378

BlackSheepVision-Phi-3/runs/Aug10_15-50-50_Troy-New-PC/events.out.tfevents.1723330250.Troy-New-PC.26212.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c3a9fcb9a6c720b44f6f816bb4a04909fb8bc504a13030c034939e397cf5cc
+size 5378

BlackSheepVision-Phi-3/runs/Aug10_15-54-59_Troy-New-PC/events.out.tfevents.1723330499.Troy-New-PC.24024.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93bbca065ef1cc0131af9debb6b4bfaf94ef650e866fdbdc91c238b33c5f509
+size 8690

BlackSheepVision-Phi-3/runs/Aug10_16-25-11_Troy-New-PC/events.out.tfevents.1723332311.Troy-New-PC.16236.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb3163f967d46380f3cf70d0ffbf0cbcdcc3b15caefce9de3581082d72f4308
+size 5933

BlackSheepVision-Phi-3/runs/Aug10_16-32-57_Troy-New-PC/events.out.tfevents.1723332777.Troy-New-PC.16236.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a3254dc1542ea44995a2daf31ee1880d12b0c5c2d1f891af3c020f71ca8a8c
+size 5378

BlackSheepVision-Phi-3/runs/Aug10_16-35-16_Troy-New-PC/events.out.tfevents.1723332916.Troy-New-PC.15040.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41985da8e645d226d39d9c81a1f57231a6adde20bf2a3bb8a51c45bfb15d3d2e
+size 12595

BlackSheepVision-Phi-3/runs/Aug10_17-21-18_Troy-New-PC/events.out.tfevents.1723335678.Troy-New-PC.9632.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31a5d9db85b4c9a8dd5544d62f229a0ea141b5147ad3c3f95163d56ca894750
+size 47832

BlackSheepVision-Phi-3/runs/Aug10_17-56-02_Troy-New-PC/events.out.tfevents.1723337762.Troy-New-PC.22188.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d758a24bd567853a3c50507f4b9b7468e946049103f268547b3f2dcfeb9fc815
+size 5378

BlackSheepVision-Phi-3/runs/Aug10_17-57-40_Troy-New-PC/events.out.tfevents.1723337860.Troy-New-PC.15172.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e326817cb78581d8b21921f8c1b3a9d56bb69bcde8aa5de9c5af59abe3148637
+size 5378

BlackSheepVision-Phi-3/runs/Aug10_17-58-53_Troy-New-PC/events.out.tfevents.1723337933.Troy-New-PC.22412.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de0e5d9d0b68ab9d41aa1e969c132bf1cb161ce63f3171384593af197b62daf
+size 5378

BlackSheepVision-Phi-3/runs/Aug10_18-00-16_Troy-New-PC/events.out.tfevents.1723338016.Troy-New-PC.9200.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bf93777958ccae26cfd15308e5c6b763f860b3bdfe2597759947396a358a32
+size 36438

BlackSheepVision-Phi-3/runs/Aug10_21-03-19_Troy-New-PC/events.out.tfevents.1723349000.Troy-New-PC.9200.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34dcd9366d7dd19c3805392402914b8f52fd7cc6281a2dd832b5e5c21b705ca9
+size 5378

BlackSheepVision-Phi-3/runs/Aug10_21-10-34_Troy-New-PC/events.out.tfevents.1723349435.Troy-New-PC.8440.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6abf58b49a5c23030c57f3910b52f41f82e05415f7bbd0e6798628a6a5aa5fa
+size 5933

BlackSheepVision-Phi-3/runs/Aug10_21-14-10_Troy-New-PC/events.out.tfevents.1723349650.Troy-New-PC.8440.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb457e4e01809c81f204571868046ae827686fc28e0d25ecb21482f47c89dddb
+size 171478

BlackSheepVision-Phi-3/runs/Aug11_07-57-56_Troy-New-PC/events.out.tfevents.1723388276.Troy-New-PC.8440.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d8b2b45072fe1a703ecaf7165db2c4e786352c86227eae55da8d560945a779
+size 25677

BlackSheepVision-Phi-3/runs/Aug11_09-22-10_Troy-New-PC/events.out.tfevents.1723393331.Troy-New-PC.8440.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a24b3234092e7cdb7890f921e535ef333b3a0998b6233a53f43c0fddab1238
+size 64025

BlackSheepVision-Phi-3/runs/Aug11_10-11-33_Troy-New-PC/events.out.tfevents.1723396293.Troy-New-PC.3004.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb53c22488cf45e8761d87b1ab893cd32045ef70188eefe73902ab189e8cccf8
+size 8422

BlackSheepVision-Phi-3/runs/Aug11_10-13-19_Troy-New-PC/events.out.tfevents.1723396399.Troy-New-PC.5380.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eec9410902a0ba3e90218a30d0f3cf9bbe66d37df319ca2f5d175320ce1c88c
+size 8423

BlackSheepVision-Phi-3/runs/Aug11_10-14-32_Troy-New-PC/events.out.tfevents.1723396473.Troy-New-PC.9536.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff3401af62daff04da24364673f03a58c8f834d480f126e76e06ae570b6d75e4
+size 8423

BlackSheepVision-Phi-3/runs/Aug11_10-15-46_Troy-New-PC/events.out.tfevents.1723396546.Troy-New-PC.21572.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c645d3e65856f03feb6baf4b1856c99c0c1109720f6408017f8a77a83cbd95e
+size 8423

BlackSheepVision-Phi-3/runs/Aug11_10-18-58_Troy-New-PC/events.out.tfevents.1723396738.Troy-New-PC.12708.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db83d9102cb1cca251756088221070b64cef098dcd44f3fb0ba15cdeba546b5
+size 8423

BlackSheepVision-Phi-3/runs/Aug11_10-22-18_Troy-New-PC/events.out.tfevents.1723396938.Troy-New-PC.13048.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0cd51958843cce9335c9b7e6a5612d887b8b830cb37500d52a5234d5b5c0cef
+size 113333

BlackSheepVision-Phi-3/training_log.json

@@ -0,0 +1,17 @@
+{
+  "base_model_name": "microsoft_Phi-3-vision-128k-instruct",
+  "base_model_class": "Phi3VForCausalLM",
+  "base_loaded_in_4bit": true,
+  "base_loaded_in_8bit": false,
+  "projections": "gate, down, up, q, v, k, o",
+  "loss": 0.3423,
+  "grad_norm": 1.8447479009628296,
+  "learning_rate": 9.438738616283812e-05,
+  "epoch": 2.3596574690770695,
+  "current_steps": 4961,
+  "train_runtime": 14910.6647,
+  "train_samples_per_second": 5.921,
+  "train_steps_per_second": 2.96,
+  "total_flos": 6.693944118843802e+17,
+  "train_loss": 0.7060681312735523
+}