upload

1e_4_5VQAlora2nd/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC
+---
+
+# 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 0.10.1.dev0

1e_4_5VQAlora2nd/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlavaMistralForCausalLM",
+    "parent_library": "llava.model.language_model.llava_mistral"
+  },
+  "base_model_name_or_path": "/workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "mm_projector"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

1e_4_5VQAlora2nd/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b507789928c1185809fe88cf9e9338c4d2d8e6a4dd2fd5b643e79bc44b6ae92
+size 122253960

1e_4_5VQAlora2nd/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60a1ee56456d3b3806208343cc707a04b9f707304c89603082cd68308697d19
+size 5048

2e_4VQAlora2nd/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC
+---
+
+# 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 0.10.1.dev0

2e_4VQAlora2nd/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlavaMistralForCausalLM",
+    "parent_library": "llava.model.language_model.llava_mistral"
+  },
+  "base_model_name_or_path": "/workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "mm_projector"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

2e_4VQAlora2nd/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4b4deeb65392c7018217ae04dfa46666d8fc66497eec74aa17ce1b7f02cf22
+size 122253960

2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC
+---
+
+# 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 0.10.1.dev0

2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlavaMistralForCausalLM",
+    "parent_library": "llava.model.language_model.llava_mistral"
+  },
+  "base_model_name_or_path": "/workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "mm_projector"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4b4deeb65392c7018217ae04dfa46666d8fc66497eec74aa17ce1b7f02cf22
+size 122253960

2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d774ce65502974f774cf40347737670dbc0ca67047de9ac0169410c9f9eb2f
+size 235243422

2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633d1564811aadc8cff03d10dcbf1246a96633cf1a7e2cc7340327ff91359be3
+size 14244

2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b345f6de2f2c60f45e2823074cc59e0f17987d968e5dd42664de99dc91e0be50
+size 1000

2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/trainer_state.json

@@ -0,0 +1,387 @@
+{
+  "best_metric": 0.6941810250282288,
+  "best_model_checkpoint": "/workspace/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50",
+  "epoch": 0.8918617614269788,
+  "eval_steps": 25,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017837235228539576,
+      "grad_norm": 8.9375,
+      "learning_rate": 5e-05,
+      "loss": 0.9688,
+      "step": 1
+    },
+    {
+      "epoch": 0.03567447045707915,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.0001,
+      "loss": 0.4082,
+      "step": 2
+    },
+    {
+      "epoch": 0.05351170568561873,
+      "grad_norm": 3.75,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.7148,
+      "step": 3
+    },
+    {
+      "epoch": 0.0713489409141583,
+      "grad_norm": 3.546875,
+      "learning_rate": 0.0002,
+      "loss": 0.918,
+      "step": 4
+    },
+    {
+      "epoch": 0.08918617614269789,
+      "grad_norm": 2.65625,
+      "learning_rate": 0.0001999576950082201,
+      "loss": 0.5273,
+      "step": 5
+    },
+    {
+      "epoch": 0.10702341137123746,
+      "grad_norm": 3.03125,
+      "learning_rate": 0.00019983081582712685,
+      "loss": 0.4492,
+      "step": 6
+    },
+    {
+      "epoch": 0.12486064659977704,
+      "grad_norm": 6.59375,
+      "learning_rate": 0.00019961946980917456,
+      "loss": 0.9805,
+      "step": 7
+    },
+    {
+      "epoch": 0.1426978818283166,
+      "grad_norm": 2.890625,
+      "learning_rate": 0.00019932383577419432,
+      "loss": 0.6289,
+      "step": 8
+    },
+    {
+      "epoch": 0.1605351170568562,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.00019894416385809444,
+      "loss": 0.8203,
+      "step": 9
+    },
+    {
+      "epoch": 0.17837235228539577,
+      "grad_norm": 2.609375,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.5859,
+      "step": 10
+    },
+    {
+      "epoch": 0.19620958751393533,
+      "grad_norm": 3.015625,
+      "learning_rate": 0.00019793406217655517,
+      "loss": 0.6523,
+      "step": 11
+    },
+    {
+      "epoch": 0.2140468227424749,
+      "grad_norm": 2.78125,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 0.5,
+      "step": 12
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 2.328125,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 0.4648,
+      "step": 13
+    },
+    {
+      "epoch": 0.24972129319955408,
+      "grad_norm": 3.875,
+      "learning_rate": 0.0001957989512315489,
+      "loss": 0.5742,
+      "step": 14
+    },
+    {
+      "epoch": 0.26755852842809363,
+      "grad_norm": 3.296875,
+      "learning_rate": 0.0001949242643573034,
+      "loss": 0.4785,
+      "step": 15
+    },
+    {
+      "epoch": 0.2853957636566332,
+      "grad_norm": 3.109375,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.6953,
+      "step": 16
+    },
+    {
+      "epoch": 0.3032329988851728,
+      "grad_norm": 3.296875,
+      "learning_rate": 0.00019293475242268223,
+      "loss": 0.6445,
+      "step": 17
+    },
+    {
+      "epoch": 0.3210702341137124,
+      "grad_norm": 3.046875,
+      "learning_rate": 0.00019182161068802741,
+      "loss": 0.8047,
+      "step": 18
+    },
+    {
+      "epoch": 0.33890746934225197,
+      "grad_norm": 3.171875,
+      "learning_rate": 0.000190630778703665,
+      "loss": 0.8047,
+      "step": 19
+    },
+    {
+      "epoch": 0.35674470457079155,
+      "grad_norm": 2.640625,
+      "learning_rate": 0.00018936326403234125,
+      "loss": 0.5664,
+      "step": 20
+    },
+    {
+      "epoch": 0.3745819397993311,
+      "grad_norm": 2.984375,
+      "learning_rate": 0.00018802013911801112,
+      "loss": 0.5352,
+      "step": 21
+    },
+    {
+      "epoch": 0.39241917502787066,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.7227,
+      "step": 22
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 2.625,
+      "learning_rate": 0.00018511166724369997,
+      "loss": 0.7852,
+      "step": 23
+    },
+    {
+      "epoch": 0.4280936454849498,
+      "grad_norm": 2.953125,
+      "learning_rate": 0.00018354878114129367,
+      "loss": 0.5391,
+      "step": 24
+    },
+    {
+      "epoch": 0.4459308807134894,
+      "grad_norm": 2.125,
+      "learning_rate": 0.0001819152044288992,
+      "loss": 0.4434,
+      "step": 25
+    },
+    {
+      "epoch": 0.4459308807134894,
+      "eval_loss": 0.6694146394729614,
+      "eval_runtime": 170.6904,
+      "eval_samples_per_second": 2.642,
+      "eval_steps_per_second": 1.324,
+      "step": 25
+    },
+    {
+      "epoch": 0.463768115942029,
+      "grad_norm": 2.25,
+      "learning_rate": 0.0001802123192755044,
+      "loss": 0.3809,
+      "step": 26
+    },
+    {
+      "epoch": 0.4816053511705686,
+      "grad_norm": 2.734375,
+      "learning_rate": 0.00017844156649195759,
+      "loss": 0.6016,
+      "step": 27
+    },
+    {
+      "epoch": 0.49944258639910816,
+      "grad_norm": 3.015625,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.6406,
+      "step": 28
+    },
+    {
+      "epoch": 0.5172798216276477,
+      "grad_norm": 2.65625,
+      "learning_rate": 0.0001747025071240996,
+      "loss": 0.4551,
+      "step": 29
+    },
+    {
+      "epoch": 0.5351170568561873,
+      "grad_norm": 3.015625,
+      "learning_rate": 0.00017273736415730488,
+      "loss": 0.7344,
+      "step": 30
+    },
+    {
+      "epoch": 0.5529542920847269,
+      "grad_norm": 3.25,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.6602,
+      "step": 31
+    },
+    {
+      "epoch": 0.5707915273132664,
+      "grad_norm": 3.34375,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 0.6523,
+      "step": 32
+    },
+    {
+      "epoch": 0.5886287625418061,
+      "grad_norm": 3.328125,
+      "learning_rate": 0.00016647958656139378,
+      "loss": 0.4199,
+      "step": 33
+    },
+    {
+      "epoch": 0.6064659977703456,
+      "grad_norm": 2.859375,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.7227,
+      "step": 34
+    },
+    {
+      "epoch": 0.6243032329988851,
+      "grad_norm": 2.96875,
+      "learning_rate": 0.000162023549126826,
+      "loss": 0.6211,
+      "step": 35
+    },
+    {
+      "epoch": 0.6421404682274248,
+      "grad_norm": 2.59375,
+      "learning_rate": 0.00015971585917027862,
+      "loss": 0.7539,
+      "step": 36
+    },
+    {
+      "epoch": 0.6599777034559643,
+      "grad_norm": 3.4375,
+      "learning_rate": 0.0001573576436351046,
+      "loss": 0.918,
+      "step": 37
+    },
+    {
+      "epoch": 0.6778149386845039,
+      "grad_norm": 3.5,
+      "learning_rate": 0.0001549508978070806,
+      "loss": 0.793,
+      "step": 38
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 2.03125,
+      "learning_rate": 0.000152497658033456,
+      "loss": 0.4609,
+      "step": 39
+    },
+    {
+      "epoch": 0.7134894091415831,
+      "grad_norm": 1.796875,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.5117,
+      "step": 40
+    },
+    {
+      "epoch": 0.7313266443701226,
+      "grad_norm": 1.625,
+      "learning_rate": 0.00014746003697476404,
+      "loss": 0.3906,
+      "step": 41
+    },
+    {
+      "epoch": 0.7491638795986622,
+      "grad_norm": 3.140625,
+      "learning_rate": 0.00014487991802004623,
+      "loss": 0.7383,
+      "step": 42
+    },
+    {
+      "epoch": 0.7670011148272018,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.00014226182617406996,
+      "loss": 0.5664,
+      "step": 43
+    },
+    {
+      "epoch": 0.7848383500557413,
+      "grad_norm": 2.796875,
+      "learning_rate": 0.0001396079766039157,
+      "loss": 0.5391,
+      "step": 44
+    },
+    {
+      "epoch": 0.802675585284281,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00013692061473126845,
+      "loss": 0.5469,
+      "step": 45
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 2.796875,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.6172,
+      "step": 46
+    },
+    {
+      "epoch": 0.8383500557413601,
+      "grad_norm": 2.421875,
+      "learning_rate": 0.00013145447561516138,
+      "loss": 0.5,
+      "step": 47
+    },
+    {
+      "epoch": 0.8561872909698997,
+      "grad_norm": 2.46875,
+      "learning_rate": 0.00012868032327110904,
+      "loss": 0.4844,
+      "step": 48
+    },
+    {
+      "epoch": 0.8740245261984393,
+      "grad_norm": 3.125,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 0.4883,
+      "step": 49
+    },
+    {
+      "epoch": 0.8918617614269788,
+      "grad_norm": 2.125,
+      "learning_rate": 0.00012306158707424403,
+      "loss": 0.3809,
+      "step": 50
+    },
+    {
+      "epoch": 0.8918617614269788,
+      "eval_loss": 0.6941810250282288,
+      "eval_runtime": 169.4879,
+      "eval_samples_per_second": 2.661,
+      "eval_steps_per_second": 1.333,
+      "step": 50
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 112,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "total_flos": 3116060910391296.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89025018165da662a325262415e63725b8a9b5048c65b43e2fa1d0c1f35f79c1
+size 5048

2e_4VQAlora2nd/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89025018165da662a325262415e63725b8a9b5048c65b43e2fa1d0c1f35f79c1
+size 5048

checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC
+---
+
+# 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 0.10.1.dev0

checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlavaMistralForCausalLM",
+    "parent_library": "llava.model.language_model.llava_mistral"
+  },
+  "base_model_name_or_path": "/workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "mm_projector"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b507789928c1185809fe88cf9e9338c4d2d8e6a4dd2fd5b643e79bc44b6ae92
+size 122253960

checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f937dc0b915de8b810c3059bdf63fda57bfb77fa5a8591d9aa6c1f14a68697
+size 235243422

checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e501bba40214b8f4e27489a653a60666f8af098a4fe783aa1409edd5605a2911
+size 14244

checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb06cf1988f8b371306fe0191cdbdd4b95231eb8ed9a174e04262abd00fb9a4
+size 1000

checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_metric": 0.7661157846450806,
+  "best_model_checkpoint": "/workspace/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100",
+  "epoch": 1.7837235228539576,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08918617614269789,
+      "grad_norm": 3.3125,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.7,
+      "step": 5
+    },
+    {
+      "epoch": 0.17837235228539577,
+      "grad_norm": 3.3125,
+      "learning_rate": 9.999664033241933e-05,
+      "loss": 0.6,
+      "step": 10
+    },
+    {
+      "epoch": 0.26755852842809363,
+      "grad_norm": 2.765625,
+      "learning_rate": 9.987909936723858e-05,
+      "loss": 0.5094,
+      "step": 15
+    },
+    {
+      "epoch": 0.35674470457079155,
+      "grad_norm": 2.765625,
+      "learning_rate": 9.959402624501636e-05,
+      "loss": 0.6687,
+      "step": 20
+    },
+    {
+      "epoch": 0.4459308807134894,
+      "grad_norm": 2.421875,
+      "learning_rate": 9.914237845928573e-05,
+      "loss": 0.5563,
+      "step": 25
+    },
+    {
+      "epoch": 0.5351170568561873,
+      "grad_norm": 3.203125,
+      "learning_rate": 9.852567298867557e-05,
+      "loss": 0.5156,
+      "step": 30
+    },
+    {
+      "epoch": 0.6243032329988851,
+      "grad_norm": 4.0625,
+      "learning_rate": 9.774598120173624e-05,
+      "loss": 0.575,
+      "step": 35
+    },
+    {
+      "epoch": 0.7134894091415831,
+      "grad_norm": 2.046875,
+      "learning_rate": 9.680592189970015e-05,
+      "loss": 0.6156,
+      "step": 40
+    },
+    {
+      "epoch": 0.802675585284281,
+      "grad_norm": 2.421875,
+      "learning_rate": 9.570865252054461e-05,
+      "loss": 0.5156,
+      "step": 45
+    },
+    {
+      "epoch": 0.8918617614269788,
+      "grad_norm": 1.6875,
+      "learning_rate": 9.445785853390073e-05,
+      "loss": 0.5094,
+      "step": 50
+    },
+    {
+      "epoch": 0.8918617614269788,
+      "eval_loss": 0.6585525274276733,
+      "eval_runtime": 171.0487,
+      "eval_samples_per_second": 2.637,
+      "eval_steps_per_second": 1.321,
+      "step": 50
+    },
+    {
+      "epoch": 0.9810479375696767,
+      "grad_norm": 2.421875,
+      "learning_rate": 9.305774106242823e-05,
+      "loss": 0.5875,
+      "step": 55
+    },
+    {
+      "epoch": 1.0702341137123745,
+      "grad_norm": 1.8359375,
+      "learning_rate": 9.151300277123301e-05,
+      "loss": 0.3156,
+      "step": 60
+    },
+    {
+      "epoch": 1.1594202898550725,
+      "grad_norm": 1.859375,
+      "learning_rate": 8.982883207272163e-05,
+      "loss": 0.2859,
+      "step": 65
+    },
+    {
+      "epoch": 1.2486064659977703,
+      "grad_norm": 4.25,
+      "learning_rate": 8.801088569994522e-05,
+      "loss": 0.2984,
+      "step": 70
+    },
+    {
+      "epoch": 1.3377926421404682,
+      "grad_norm": 2.875,
+      "learning_rate": 8.606526970696409e-05,
+      "loss": 0.3203,
+      "step": 75
+    },
+    {
+      "epoch": 1.4269788182831662,
+      "grad_norm": 1.7578125,
+      "learning_rate": 8.399851896004913e-05,
+      "loss": 0.2625,
+      "step": 80
+    },
+    {
+      "epoch": 1.516164994425864,
+      "grad_norm": 1.6796875,
+      "learning_rate": 8.181757518860387e-05,
+      "loss": 0.2531,
+      "step": 85
+    },
+    {
+      "epoch": 1.605351170568562,
+      "grad_norm": 2.078125,
+      "learning_rate": 7.952976366952888e-05,
+      "loss": 0.2703,
+      "step": 90
+    },
+    {
+      "epoch": 1.6945373467112597,
+      "grad_norm": 2.875,
+      "learning_rate": 7.714276862334051e-05,
+      "loss": 0.2953,
+      "step": 95
+    },
+    {
+      "epoch": 1.7837235228539576,
+      "grad_norm": 3.0625,
+      "learning_rate": 7.466460740468245e-05,
+      "loss": 0.275,
+      "step": 100
+    },
+    {
+      "epoch": 1.7837235228539576,
+      "eval_loss": 0.7661157846450806,
+      "eval_runtime": 168.1711,
+      "eval_samples_per_second": 2.682,
+      "eval_steps_per_second": 1.344,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "total_flos": 6225195841794048.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60a1ee56456d3b3806208343cc707a04b9f707304c89603082cd68308697d19
+size 5048