diff --git a/.DS_Store b/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..8a90a932111834bb7dc56416fa5ed334bd80e639 Binary files /dev/null and b/.DS_Store differ diff --git a/1e_4_5VQAlora2nd/adapter_config.json b/1e_4_5VQAlora2nd/adapter_config.json deleted file mode 100644 index d87f1e6955efbf43dfb08ba879a8bc8980c148e9..0000000000000000000000000000000000000000 --- a/1e_4_5VQAlora2nd/adapter_config.json +++ /dev/null @@ -1,38 +0,0 @@ -{ - "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 -} \ No newline at end of file diff --git a/1e_4_5VQAlora2nd/adapter_model.safetensors b/1e_4_5VQAlora2nd/adapter_model.safetensors deleted file mode 100644 index 98bb514b2aae92afff65c79cc04eae486ba697c8..0000000000000000000000000000000000000000 --- a/1e_4_5VQAlora2nd/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5b507789928c1185809fe88cf9e9338c4d2d8e6a4dd2fd5b643e79bc44b6ae92 -size 122253960 diff --git a/1e_4_5VQAlora2nd/training_args.bin b/1e_4_5VQAlora2nd/training_args.bin deleted file mode 100644 index f3d55e7001bb557ab19b9c720be5f21127f8e996..0000000000000000000000000000000000000000 --- a/1e_4_5VQAlora2nd/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a60a1ee56456d3b3806208343cc707a04b9f707304c89603082cd68308697d19 -size 5048 diff --git a/2e_4VQAlora2nd/README.md b/2e_4VQAlora2nd/README.md deleted file mode 100644 index 27faf99f43040d0bd856edd8cd22569eb5c96a50..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/README.md +++ /dev/null @@ -1,202 +0,0 @@ ---- -library_name: peft -base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **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] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -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 - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -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] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[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 \ No newline at end of file diff --git a/2e_4VQAlora2nd/adapter_config.json b/2e_4VQAlora2nd/adapter_config.json deleted file mode 100644 index 312544964164a0282fd29c11bb7e94ea20c2c7bb..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/adapter_config.json +++ /dev/null @@ -1,38 +0,0 @@ -{ - "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 -} \ No newline at end of file diff --git a/2e_4VQAlora2nd/adapter_model.safetensors b/2e_4VQAlora2nd/adapter_model.safetensors deleted file mode 100644 index cafc7aa99f24e53376c0e77039ae1decccd6403d..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5a4b4deeb65392c7018217ae04dfa46666d8fc66497eec74aa17ce1b7f02cf22 -size 122253960 diff --git a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/README.md b/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/README.md deleted file mode 100644 index 27faf99f43040d0bd856edd8cd22569eb5c96a50..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/README.md +++ /dev/null @@ -1,202 +0,0 @@ ---- -library_name: peft -base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **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] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -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 - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -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] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[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 \ No newline at end of file diff --git a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/adapter_config.json b/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/adapter_config.json deleted file mode 100644 index 312544964164a0282fd29c11bb7e94ea20c2c7bb..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/adapter_config.json +++ /dev/null @@ -1,38 +0,0 @@ -{ - "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 -} \ No newline at end of file diff --git a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/adapter_model.safetensors b/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/adapter_model.safetensors deleted file mode 100644 index cafc7aa99f24e53376c0e77039ae1decccd6403d..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5a4b4deeb65392c7018217ae04dfa46666d8fc66497eec74aa17ce1b7f02cf22 -size 122253960 diff --git a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/optimizer.pt b/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/optimizer.pt deleted file mode 100644 index 34444940311dab24aa5a6239d418698f2937a883..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:88d774ce65502974f774cf40347737670dbc0ca67047de9ac0169410c9f9eb2f -size 235243422 diff --git a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/rng_state.pth b/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/rng_state.pth deleted file mode 100644 index e2a63890811d0a3387ae454d547303d1621fda3d..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:633d1564811aadc8cff03d10dcbf1246a96633cf1a7e2cc7340327ff91359be3 -size 14244 diff --git a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/scheduler.pt b/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/scheduler.pt deleted file mode 100644 index 0fed1c9b50bc80c2107a222f4e0f12120a8301f3..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b345f6de2f2c60f45e2823074cc59e0f17987d968e5dd42664de99dc91e0be50 -size 1000 diff --git a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/trainer_state.json b/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/trainer_state.json deleted file mode 100644 index a7d0bfb9ec532b8903f9716fb44bc7c32d04bca6..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/trainer_state.json +++ /dev/null @@ -1,387 +0,0 @@ -{ - "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 -} diff --git a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/training_args.bin b/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/training_args.bin deleted file mode 100644 index f65829e401dd5c47441c39275c04193731c3cdab..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/checkpoints/LVQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-50/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:89025018165da662a325262415e63725b8a9b5048c65b43e2fa1d0c1f35f79c1 -size 5048 diff --git a/2e_4VQAlora2nd/training_args.bin b/2e_4VQAlora2nd/training_args.bin deleted file mode 100644 index f65829e401dd5c47441c39275c04193731c3cdab..0000000000000000000000000000000000000000 --- a/2e_4VQAlora2nd/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:89025018165da662a325262415e63725b8a9b5048c65b43e2fa1d0c1f35f79c1 -size 5048 diff --git a/2e_5_r8_2VQAlora2nd/README.md b/2e_5_r8_2VQAlora2nd/README.md deleted file mode 100644 index 27faf99f43040d0bd856edd8cd22569eb5c96a50..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/README.md +++ /dev/null @@ -1,202 +0,0 @@ ---- -library_name: peft -base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **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] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -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 - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -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] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[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 \ No newline at end of file diff --git a/2e_5_r8_2VQAlora2nd/adapter_config.json b/2e_5_r8_2VQAlora2nd/adapter_config.json deleted file mode 100644 index fa28bb814a792d9d6ee7ee67fe43b9dafdcc88d3..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/adapter_config.json +++ /dev/null @@ -1,38 +0,0 @@ -{ - "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": 16, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": [ - "mm_projector" - ], - "peft_type": "LORA", - "r": 8, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "up_proj", - "q_proj", - "v_proj", - "down_proj", - "gate_proj", - "k_proj" - ], - "task_type": null, - "use_dora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/2e_5_r8_2VQAlora2nd/adapter_model.safetensors b/2e_5_r8_2VQAlora2nd/adapter_model.safetensors deleted file mode 100644 index fcdef91f36fbbb22bcaa81e466a610565290566e..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5b0232e69491294015ab0a4efd85b1b6e1b7d740369cb5272f16a0c3a0b1dd2e -size 82145000 diff --git a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md b/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md deleted file mode 100644 index 27faf99f43040d0bd856edd8cd22569eb5c96a50..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md +++ /dev/null @@ -1,202 +0,0 @@ ---- -library_name: peft -base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **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] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -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 - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -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] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[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 \ No newline at end of file diff --git a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json b/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json deleted file mode 100644 index fa28bb814a792d9d6ee7ee67fe43b9dafdcc88d3..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json +++ /dev/null @@ -1,38 +0,0 @@ -{ - "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": 16, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": [ - "mm_projector" - ], - "peft_type": "LORA", - "r": 8, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "up_proj", - "q_proj", - "v_proj", - "down_proj", - "gate_proj", - "k_proj" - ], - "task_type": null, - "use_dora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors b/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors deleted file mode 100644 index eed9f51abc656b2cfc481cad609e6fe1428f8f7f..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1ecd06d454a5ef19de39fef869cf97fd790549b09548406d84a8c939662c9951 -size 82145000 diff --git a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt b/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt deleted file mode 100644 index 6611e5d89a9624126c8bfea55b2c8689c7085aab..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e58c4171fc1708d1a7c9827f39f2780c58fa8c1147ac2040914171331cbcca38 -size 159745054 diff --git a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth b/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth deleted file mode 100644 index d5204691d3662b7c6ec312fcb04aea95bc448ce3..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d84d4f48c468a94fd4072c91a59f565bee1ca2a3e59f347bb7cf50192b12534d -size 14244 diff --git a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt b/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt deleted file mode 100644 index 3c35050719a3580dff388fb069dec838b09a2ea6..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3bf58c2acdbed25fa02315fba4c7735d145c4d933480a8c2806b5a368de6c669 -size 1000 diff --git a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json b/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json deleted file mode 100644 index ee30626187a05a0386d87d17d3d86389e1f7cb80..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json +++ /dev/null @@ -1,533 +0,0 @@ -{ - "best_metric": 0.623073935508728, - "best_model_checkpoint": "/workspace/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80", - "epoch": 1.4269788182831662, - "eval_steps": 20, - "global_step": 80, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [ - { - "epoch": 0.02, - "learning_rate": 5e-06, - "loss": 0.8086, - "step": 1 - }, - { - "epoch": 0.04, - "learning_rate": 1e-05, - "loss": 0.6797, - "step": 2 - }, - { - "epoch": 0.05, - "learning_rate": 1.5000000000000002e-05, - "loss": 0.4551, - "step": 3 - }, - { - "epoch": 0.07, - "learning_rate": 2e-05, - "loss": 0.543, - "step": 4 - }, - { - "epoch": 0.09, - "learning_rate": 1.9995769500822007e-05, - "loss": 0.3105, - "step": 5 - }, - { - "epoch": 0.11, - "learning_rate": 1.9983081582712684e-05, - "loss": 0.4727, - "step": 6 - }, - { - "epoch": 0.12, - "learning_rate": 1.9961946980917457e-05, - "loss": 0.6914, - "step": 7 - }, - { - "epoch": 0.14, - "learning_rate": 1.9932383577419432e-05, - "loss": 0.5586, - "step": 8 - }, - { - "epoch": 0.16, - "learning_rate": 1.9894416385809444e-05, - "loss": 0.4395, - "step": 9 - }, - { - "epoch": 0.18, - "learning_rate": 1.9848077530122083e-05, - "loss": 0.457, - "step": 10 - }, - { - "epoch": 0.2, - "learning_rate": 1.9793406217655516e-05, - "loss": 0.3574, - "step": 11 - }, - { - "epoch": 0.21, - "learning_rate": 1.973044870579824e-05, - "loss": 0.6641, - "step": 12 - }, - { - "epoch": 0.23, - "learning_rate": 1.9659258262890683e-05, - "loss": 0.5117, - "step": 13 - }, - { - "epoch": 0.25, - "learning_rate": 1.957989512315489e-05, - "loss": 0.5742, - "step": 14 - }, - { - "epoch": 0.27, - "learning_rate": 1.949242643573034e-05, - "loss": 0.4824, - "step": 15 - }, - { - "epoch": 0.29, - "learning_rate": 1.9396926207859085e-05, - "loss": 0.416, - "step": 16 - }, - { - "epoch": 0.3, - "learning_rate": 1.9293475242268224e-05, - "loss": 0.625, - "step": 17 - }, - { - "epoch": 0.32, - "learning_rate": 1.9182161068802742e-05, - "loss": 0.2354, - "step": 18 - }, - { - "epoch": 0.34, - "learning_rate": 1.9063077870366504e-05, - "loss": 0.7891, - "step": 19 - }, - { - "epoch": 0.36, - "learning_rate": 1.8936326403234125e-05, - "loss": 0.668, - "step": 20 - }, - { - "epoch": 0.36, - "eval_loss": 0.6457709074020386, - "eval_runtime": 330.0437, - "eval_samples_per_second": 1.366, - "eval_steps_per_second": 0.685, - "step": 20 - }, - { - "epoch": 0.37, - "learning_rate": 1.880201391180111e-05, - "loss": 0.5391, - "step": 21 - }, - { - "epoch": 0.39, - "learning_rate": 1.866025403784439e-05, - "loss": 0.3848, - "step": 22 - }, - { - "epoch": 0.41, - "learning_rate": 1.8511166724369997e-05, - "loss": 0.4434, - "step": 23 - }, - { - "epoch": 0.43, - "learning_rate": 1.8354878114129368e-05, - "loss": 0.5977, - "step": 24 - }, - { - "epoch": 0.45, - "learning_rate": 1.819152044288992e-05, - "loss": 0.543, - "step": 25 - }, - { - "epoch": 0.46, - "learning_rate": 1.802123192755044e-05, - "loss": 0.7422, - "step": 26 - }, - { - "epoch": 0.48, - "learning_rate": 1.784415664919576e-05, - "loss": 0.5039, - "step": 27 - }, - { - "epoch": 0.5, - "learning_rate": 1.766044443118978e-05, - "loss": 0.3848, - "step": 28 - }, - { - "epoch": 0.52, - "learning_rate": 1.7470250712409963e-05, - "loss": 0.5195, - "step": 29 - }, - { - "epoch": 0.54, - "learning_rate": 1.7273736415730488e-05, - "loss": 0.3945, - "step": 30 - }, - { - "epoch": 0.55, - "learning_rate": 1.7071067811865477e-05, - "loss": 0.5586, - "step": 31 - }, - { - "epoch": 0.57, - "learning_rate": 1.686241637868734e-05, - "loss": 0.4512, - "step": 32 - }, - { - "epoch": 0.59, - "learning_rate": 1.6647958656139377e-05, - "loss": 0.5273, - "step": 33 - }, - { - "epoch": 0.61, - "learning_rate": 1.6427876096865394e-05, - "loss": 0.5273, - "step": 34 - }, - { - "epoch": 0.62, - "learning_rate": 1.6202354912682602e-05, - "loss": 0.7734, - "step": 35 - }, - { - "epoch": 0.64, - "learning_rate": 1.5971585917027864e-05, - "loss": 0.875, - "step": 36 - }, - { - "epoch": 0.66, - "learning_rate": 1.573576436351046e-05, - "loss": 0.6602, - "step": 37 - }, - { - "epoch": 0.68, - "learning_rate": 1.5495089780708062e-05, - "loss": 0.8047, - "step": 38 - }, - { - "epoch": 0.7, - "learning_rate": 1.5249765803345602e-05, - "loss": 0.793, - "step": 39 - }, - { - "epoch": 0.71, - "learning_rate": 1.5000000000000002e-05, - "loss": 0.6562, - "step": 40 - }, - { - "epoch": 0.71, - "eval_loss": 0.6437277793884277, - "eval_runtime": 322.5002, - "eval_samples_per_second": 1.398, - "eval_steps_per_second": 0.701, - "step": 40 - }, - { - "epoch": 0.73, - "learning_rate": 1.4746003697476406e-05, - "loss": 0.5859, - "step": 41 - }, - { - "epoch": 0.75, - "learning_rate": 1.4487991802004625e-05, - "loss": 0.6328, - "step": 42 - }, - { - "epoch": 0.77, - "learning_rate": 1.4226182617406996e-05, - "loss": 0.4727, - "step": 43 - }, - { - "epoch": 0.78, - "learning_rate": 1.396079766039157e-05, - "loss": 0.6836, - "step": 44 - }, - { - "epoch": 0.8, - "learning_rate": 1.3692061473126845e-05, - "loss": 0.6875, - "step": 45 - }, - { - "epoch": 0.82, - "learning_rate": 1.342020143325669e-05, - "loss": 0.75, - "step": 46 - }, - { - "epoch": 0.84, - "learning_rate": 1.3145447561516138e-05, - "loss": 0.4512, - "step": 47 - }, - { - "epoch": 0.86, - "learning_rate": 1.2868032327110904e-05, - "loss": 0.6875, - "step": 48 - }, - { - "epoch": 0.87, - "learning_rate": 1.2588190451025209e-05, - "loss": 0.7734, - "step": 49 - }, - { - "epoch": 0.89, - "learning_rate": 1.2306158707424402e-05, - "loss": 0.6328, - "step": 50 - }, - { - "epoch": 0.91, - "learning_rate": 1.2022175723320382e-05, - "loss": 0.6992, - "step": 51 - }, - { - "epoch": 0.93, - "learning_rate": 1.1736481776669307e-05, - "loss": 0.5977, - "step": 52 - }, - { - "epoch": 0.95, - "learning_rate": 1.1449318593072468e-05, - "loss": 0.5742, - "step": 53 - }, - { - "epoch": 0.96, - "learning_rate": 1.1160929141252303e-05, - "loss": 0.3633, - "step": 54 - }, - { - "epoch": 0.98, - "learning_rate": 1.0871557427476585e-05, - "loss": 0.6836, - "step": 55 - }, - { - "epoch": 1.0, - "learning_rate": 1.0581448289104759e-05, - "loss": 0.8086, - "step": 56 - }, - { - "epoch": 1.02, - "learning_rate": 1.0290847187431115e-05, - "loss": 0.3984, - "step": 57 - }, - { - "epoch": 1.03, - "learning_rate": 1e-05, - "loss": 0.4531, - "step": 58 - }, - { - "epoch": 1.05, - "learning_rate": 9.709152812568886e-06, - "loss": 0.5039, - "step": 59 - }, - { - "epoch": 1.07, - "learning_rate": 9.418551710895243e-06, - "loss": 0.6211, - "step": 60 - }, - { - "epoch": 1.07, - "eval_loss": 0.6246171593666077, - "eval_runtime": 327.5115, - "eval_samples_per_second": 1.377, - "eval_steps_per_second": 0.69, - "step": 60 - }, - { - "epoch": 1.09, - "learning_rate": 9.128442572523418e-06, - "loss": 0.3184, - "step": 61 - }, - { - "epoch": 1.11, - "learning_rate": 8.839070858747697e-06, - "loss": 0.4434, - "step": 62 - }, - { - "epoch": 1.12, - "learning_rate": 8.550681406927534e-06, - "loss": 0.4141, - "step": 63 - }, - { - "epoch": 1.14, - "learning_rate": 8.263518223330698e-06, - "loss": 0.3477, - "step": 64 - }, - { - "epoch": 1.16, - "learning_rate": 7.977824276679623e-06, - "loss": 0.4844, - "step": 65 - }, - { - "epoch": 1.18, - "learning_rate": 7.6938412925756e-06, - "loss": 0.4902, - "step": 66 - }, - { - "epoch": 1.2, - "learning_rate": 7.411809548974792e-06, - "loss": 0.5547, - "step": 67 - }, - { - "epoch": 1.21, - "learning_rate": 7.131967672889101e-06, - "loss": 0.3965, - "step": 68 - }, - { - "epoch": 1.23, - "learning_rate": 6.854552438483866e-06, - "loss": 0.6133, - "step": 69 - }, - { - "epoch": 1.25, - "learning_rate": 6.579798566743314e-06, - "loss": 0.5312, - "step": 70 - }, - { - "epoch": 1.27, - "learning_rate": 6.3079385268731575e-06, - "loss": 0.4766, - "step": 71 - }, - { - "epoch": 1.28, - "learning_rate": 6.039202339608432e-06, - "loss": 0.8125, - "step": 72 - }, - { - "epoch": 1.3, - "learning_rate": 5.773817382593008e-06, - "loss": 0.4551, - "step": 73 - }, - { - "epoch": 1.32, - "learning_rate": 5.512008197995379e-06, - "loss": 0.4219, - "step": 74 - }, - { - "epoch": 1.34, - "learning_rate": 5.253996302523596e-06, - "loss": 0.3867, - "step": 75 - }, - { - "epoch": 1.36, - "learning_rate": 5.000000000000003e-06, - "loss": 0.5156, - "step": 76 - }, - { - "epoch": 1.37, - "learning_rate": 4.7502341966544e-06, - "loss": 0.5469, - "step": 77 - }, - { - "epoch": 1.39, - "learning_rate": 4.504910219291941e-06, - "loss": 0.3984, - "step": 78 - }, - { - "epoch": 1.41, - "learning_rate": 4.264235636489542e-06, - "loss": 0.4395, - "step": 79 - }, - { - "epoch": 1.43, - "learning_rate": 4.028414082972141e-06, - "loss": 0.6719, - "step": 80 - }, - { - "epoch": 1.43, - "eval_loss": 0.623073935508728, - "eval_runtime": 322.1595, - "eval_samples_per_second": 1.4, - "eval_steps_per_second": 0.702, - "step": 80 - } - ], - "logging_steps": 1, - "max_steps": 112, - "num_input_tokens_seen": 0, - "num_train_epochs": 2, - "save_steps": 40, - "total_flos": 4979777395845120.0, - "train_batch_size": 2, - "trial_name": null, - "trial_params": null -} diff --git a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin b/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin deleted file mode 100644 index c76ae208240a43ff75e8b756d2cd7560eca75321..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/checkpoints/r82_2e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a3fb2b54d9ce3c79a2533cc4f7113f96de9b3af85fa1d22489c50d5969473c5a -size 4792 diff --git a/2e_5_r8_2VQAlora2nd/training_args.bin b/2e_5_r8_2VQAlora2nd/training_args.bin deleted file mode 100644 index c76ae208240a43ff75e8b756d2cd7560eca75321..0000000000000000000000000000000000000000 --- a/2e_5_r8_2VQAlora2nd/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a3fb2b54d9ce3c79a2533cc4f7113f96de9b3af85fa1d22489c50d5969473c5a -size 4792 diff --git a/2ndvqarad/.DS_Store b/2ndvqarad/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..73138837059344e4f45430dac5e468212693e783 Binary files /dev/null and b/2ndvqarad/.DS_Store differ diff --git a/1e_4_5VQAlora2nd/README.md b/2ndvqarad/README.md similarity index 100% rename from 1e_4_5VQAlora2nd/README.md rename to 2ndvqarad/README.md diff --git a/4e_5_2VQAlora2nd/adapter_config.json b/2ndvqarad/adapter_config.json similarity index 100% rename from 4e_5_2VQAlora2nd/adapter_config.json rename to 2ndvqarad/adapter_config.json diff --git a/4e_5_2VQAlora2nd/adapter_model.safetensors b/2ndvqarad/adapter_model.safetensors similarity index 100% rename from 4e_5_2VQAlora2nd/adapter_model.safetensors rename to 2ndvqarad/adapter_model.safetensors diff --git a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin b/2ndvqarad/training_args.bin similarity index 100% rename from 4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin rename to 2ndvqarad/training_args.bin diff --git a/4e_5_2VQAlora2nd/README.md b/4e_5_2VQAlora2nd/README.md deleted file mode 100644 index 27faf99f43040d0bd856edd8cd22569eb5c96a50..0000000000000000000000000000000000000000 --- a/4e_5_2VQAlora2nd/README.md +++ /dev/null @@ -1,202 +0,0 @@ ---- -library_name: peft -base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **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] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -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 - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -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] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[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 \ No newline at end of file diff --git a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md b/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md deleted file mode 100644 index 27faf99f43040d0bd856edd8cd22569eb5c96a50..0000000000000000000000000000000000000000 --- a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md +++ /dev/null @@ -1,202 +0,0 @@ ---- -library_name: peft -base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **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] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -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 - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -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] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[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 \ No newline at end of file diff --git a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json b/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json deleted file mode 100644 index c1504f6015bef5a39c4448190a5564810c283a99..0000000000000000000000000000000000000000 --- a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json +++ /dev/null @@ -1,38 +0,0 @@ -{ - "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": [ - "k_proj", - "q_proj", - "v_proj", - "up_proj", - "gate_proj", - "down_proj" - ], - "task_type": null, - "use_dora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors b/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors deleted file mode 100644 index bed51d98375adb8a5c5a25f2f028a9286b7b550c..0000000000000000000000000000000000000000 --- a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6ec223b0f496bb70eced664b2e732b675e4285577505c475ba9c48886f4fbcd5 -size 122253960 diff --git a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt b/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt deleted file mode 100644 index 9bccb98ae4905b0d60a8b3fc72bb35b1ba9d1511..0000000000000000000000000000000000000000 --- a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0ba45b246b37370bda13027e4d8bd1349db0353bb2b3a540a7892a9d76989300 -size 235243422 diff --git a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth b/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth deleted file mode 100644 index d5204691d3662b7c6ec312fcb04aea95bc448ce3..0000000000000000000000000000000000000000 --- a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d84d4f48c468a94fd4072c91a59f565bee1ca2a3e59f347bb7cf50192b12534d -size 14244 diff --git a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt b/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt deleted file mode 100644 index 6b380f18d82af6736c34685a14b1ef1279308df9..0000000000000000000000000000000000000000 --- a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:91de2e5150296a3888b9d86e8412c0c3aac23a6d23700fef3e75d90a2393e8e1 -size 1000 diff --git a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json b/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json deleted file mode 100644 index fddcbddc3b5463f5dc5d9a74e8dd28bd3ebb3ab4..0000000000000000000000000000000000000000 --- a/4e_5_2VQAlora2nd/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json +++ /dev/null @@ -1,149 +0,0 @@ -{ - "best_metric": 0.6341778635978699, - "best_model_checkpoint": "/workspace/checkpoints/2_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80", - "epoch": 1.4269788182831662, - "eval_steps": 20, - "global_step": 80, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [ - { - "epoch": 0.09, - "learning_rate": 3.9991539001644015e-05, - "loss": 0.5469, - "step": 5 - }, - { - "epoch": 0.18, - "learning_rate": 3.9696155060244166e-05, - "loss": 0.5094, - "step": 10 - }, - { - "epoch": 0.27, - "learning_rate": 3.898485287146068e-05, - "loss": 0.4844, - "step": 15 - }, - { - "epoch": 0.36, - "learning_rate": 3.787265280646825e-05, - "loss": 0.5625, - "step": 20 - }, - { - "epoch": 0.36, - "eval_loss": 0.6666426062583923, - "eval_runtime": 313.5071, - "eval_samples_per_second": 1.439, - "eval_steps_per_second": 0.721, - "step": 20 - }, - { - "epoch": 0.45, - "learning_rate": 3.638304088577984e-05, - "loss": 0.4938, - "step": 25 - }, - { - "epoch": 0.54, - "learning_rate": 3.4547472831460976e-05, - "loss": 0.4969, - "step": 30 - }, - { - "epoch": 0.62, - "learning_rate": 3.2404709825365204e-05, - "loss": 0.5219, - "step": 35 - }, - { - "epoch": 0.71, - "learning_rate": 3.0000000000000004e-05, - "loss": 0.7219, - "step": 40 - }, - { - "epoch": 0.71, - "eval_loss": 0.6467391848564148, - "eval_runtime": 318.6731, - "eval_samples_per_second": 1.415, - "eval_steps_per_second": 0.709, - "step": 40 - }, - { - "epoch": 0.8, - "learning_rate": 2.738412294625369e-05, - "loss": 0.575, - "step": 45 - }, - { - "epoch": 0.89, - "learning_rate": 2.4612317414848804e-05, - "loss": 0.6344, - "step": 50 - }, - { - "epoch": 0.98, - "learning_rate": 2.174311485495317e-05, - "loss": 0.5469, - "step": 55 - }, - { - "epoch": 1.07, - "learning_rate": 1.8837103421790486e-05, - "loss": 0.4469, - "step": 60 - }, - { - "epoch": 1.07, - "eval_loss": 0.6086602210998535, - "eval_runtime": 320.0767, - "eval_samples_per_second": 1.409, - "eval_steps_per_second": 0.706, - "step": 60 - }, - { - "epoch": 1.16, - "learning_rate": 1.5955648553359247e-05, - "loss": 0.3141, - "step": 65 - }, - { - "epoch": 1.25, - "learning_rate": 1.3159597133486628e-05, - "loss": 0.3953, - "step": 70 - }, - { - "epoch": 1.34, - "learning_rate": 1.0507992605047193e-05, - "loss": 0.3875, - "step": 75 - }, - { - "epoch": 1.43, - "learning_rate": 8.056828165944282e-06, - "loss": 0.3766, - "step": 80 - }, - { - "epoch": 1.43, - "eval_loss": 0.6341778635978699, - "eval_runtime": 315.0947, - "eval_samples_per_second": 1.431, - "eval_steps_per_second": 0.717, - "step": 80 - } - ], - "logging_steps": 5, - "max_steps": 112, - "num_input_tokens_seen": 0, - "num_train_epochs": 2, - "save_steps": 40, - "total_flos": 4993136137955328.0, - "train_batch_size": 2, - "trial_name": null, - "trial_params": null -} diff --git a/4e_5_2VQAlora2nd/training_args.bin b/4e_5_2VQAlora2nd/training_args.bin deleted file mode 100644 index d9b9d439868c14e5310dacaa003c4c82bfe3b5af..0000000000000000000000000000000000000000 --- a/4e_5_2VQAlora2nd/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1a68ac9690d72595e0b21c7496fbf44aa8a0d4c5bd0264468e35b12eddd8e350 -size 4792 diff --git a/4e_5_r8_2VQAlora2nd/README.md b/4e_5_r8_2VQAlora2nd/README.md deleted file mode 100644 index 27faf99f43040d0bd856edd8cd22569eb5c96a50..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/README.md +++ /dev/null @@ -1,202 +0,0 @@ ---- -library_name: peft -base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **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] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -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 - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -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] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[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 \ No newline at end of file diff --git a/4e_5_r8_2VQAlora2nd/adapter_config.json b/4e_5_r8_2VQAlora2nd/adapter_config.json deleted file mode 100644 index 74a1471fc99b92776e0688ffd948b96eea6a40d3..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/adapter_config.json +++ /dev/null @@ -1,38 +0,0 @@ -{ - "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": 16, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": [ - "mm_projector" - ], - "peft_type": "LORA", - "r": 8, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "down_proj", - "v_proj", - "up_proj", - "gate_proj", - "q_proj" - ], - "task_type": null, - "use_dora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/4e_5_r8_2VQAlora2nd/adapter_model.safetensors b/4e_5_r8_2VQAlora2nd/adapter_model.safetensors deleted file mode 100644 index d64db7300957c43748fb55147d9d60cb67f81d49..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f4251bacf03189ccc18b2f3b80149c2984023e37d29f135866c07d3b3ea7f27d -size 82145000 diff --git a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md b/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md deleted file mode 100644 index 27faf99f43040d0bd856edd8cd22569eb5c96a50..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/README.md +++ /dev/null @@ -1,202 +0,0 @@ ---- -library_name: peft -base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **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] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -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 - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -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] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[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 \ No newline at end of file diff --git a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json b/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json deleted file mode 100644 index 74a1471fc99b92776e0688ffd948b96eea6a40d3..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_config.json +++ /dev/null @@ -1,38 +0,0 @@ -{ - "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": 16, - "lora_dropout": 0.05, - "megatron_config": null, - "megatron_core": "megatron.core", - "modules_to_save": [ - "mm_projector" - ], - "peft_type": "LORA", - "r": 8, - "rank_pattern": {}, - "revision": null, - "target_modules": [ - "k_proj", - "down_proj", - "v_proj", - "up_proj", - "gate_proj", - "q_proj" - ], - "task_type": null, - "use_dora": false, - "use_rslora": false -} \ No newline at end of file diff --git a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors b/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors deleted file mode 100644 index d64db7300957c43748fb55147d9d60cb67f81d49..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f4251bacf03189ccc18b2f3b80149c2984023e37d29f135866c07d3b3ea7f27d -size 82145000 diff --git a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt b/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt deleted file mode 100644 index 74169215d6c73d3380638946755b7ec8a5d7a5ea..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:142e2e403e738467fe0ae0d0cad7e4805d9c808c4ce3bb564c84cab83eae59f8 -size 159745054 diff --git a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth b/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth deleted file mode 100644 index d5204691d3662b7c6ec312fcb04aea95bc448ce3..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d84d4f48c468a94fd4072c91a59f565bee1ca2a3e59f347bb7cf50192b12534d -size 14244 diff --git a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt b/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt deleted file mode 100644 index 6b380f18d82af6736c34685a14b1ef1279308df9..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:91de2e5150296a3888b9d86e8412c0c3aac23a6d23700fef3e75d90a2393e8e1 -size 1000 diff --git a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json b/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json deleted file mode 100644 index 8080f02f6daefd0dd0ae3c0853d31f065f8308b9..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/trainer_state.json +++ /dev/null @@ -1,533 +0,0 @@ -{ - "best_metric": 0.6239878535270691, - "best_model_checkpoint": "/workspace/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80", - "epoch": 1.4269788182831662, - "eval_steps": 20, - "global_step": 80, - "is_hyper_param_search": false, - "is_local_process_zero": true, - "is_world_process_zero": true, - "log_history": [ - { - "epoch": 0.02, - "learning_rate": 1e-05, - "loss": 0.8086, - "step": 1 - }, - { - "epoch": 0.04, - "learning_rate": 2e-05, - "loss": 0.6797, - "step": 2 - }, - { - "epoch": 0.05, - "learning_rate": 3.0000000000000004e-05, - "loss": 0.4492, - "step": 3 - }, - { - "epoch": 0.07, - "learning_rate": 4e-05, - "loss": 0.5117, - "step": 4 - }, - { - "epoch": 0.09, - "learning_rate": 3.9991539001644015e-05, - "loss": 0.3027, - "step": 5 - }, - { - "epoch": 0.11, - "learning_rate": 3.996616316542537e-05, - "loss": 0.4629, - "step": 6 - }, - { - "epoch": 0.12, - "learning_rate": 3.9923893961834914e-05, - "loss": 0.6875, - "step": 7 - }, - { - "epoch": 0.14, - "learning_rate": 3.9864767154838864e-05, - "loss": 0.5586, - "step": 8 - }, - { - "epoch": 0.16, - "learning_rate": 3.978883277161889e-05, - "loss": 0.4551, - "step": 9 - }, - { - "epoch": 0.18, - "learning_rate": 3.9696155060244166e-05, - "loss": 0.4297, - "step": 10 - }, - { - "epoch": 0.2, - "learning_rate": 3.958681243531103e-05, - "loss": 0.3301, - "step": 11 - }, - { - "epoch": 0.21, - "learning_rate": 3.946089741159648e-05, - "loss": 0.6367, - "step": 12 - }, - { - "epoch": 0.23, - "learning_rate": 3.931851652578137e-05, - "loss": 0.4883, - "step": 13 - }, - { - "epoch": 0.25, - "learning_rate": 3.915979024630978e-05, - "loss": 0.5625, - "step": 14 - }, - { - "epoch": 0.27, - "learning_rate": 3.898485287146068e-05, - "loss": 0.4492, - "step": 15 - }, - { - "epoch": 0.29, - "learning_rate": 3.879385241571817e-05, - "loss": 0.4395, - "step": 16 - }, - { - "epoch": 0.3, - "learning_rate": 3.858695048453645e-05, - "loss": 0.6016, - "step": 17 - }, - { - "epoch": 0.32, - "learning_rate": 3.8364322137605484e-05, - "loss": 0.2266, - "step": 18 - }, - { - "epoch": 0.34, - "learning_rate": 3.812615574073301e-05, - "loss": 0.8047, - "step": 19 - }, - { - "epoch": 0.36, - "learning_rate": 3.787265280646825e-05, - "loss": 0.6797, - "step": 20 - }, - { - "epoch": 0.36, - "eval_loss": 0.6560852527618408, - "eval_runtime": 313.3213, - "eval_samples_per_second": 1.439, - "eval_steps_per_second": 0.721, - "step": 20 - }, - { - "epoch": 0.37, - "learning_rate": 3.760402782360222e-05, - "loss": 0.5625, - "step": 21 - }, - { - "epoch": 0.39, - "learning_rate": 3.732050807568878e-05, - "loss": 0.3496, - "step": 22 - }, - { - "epoch": 0.41, - "learning_rate": 3.702233344873999e-05, - "loss": 0.4316, - "step": 23 - }, - { - "epoch": 0.43, - "learning_rate": 3.6709756228258735e-05, - "loss": 0.5938, - "step": 24 - }, - { - "epoch": 0.45, - "learning_rate": 3.638304088577984e-05, - "loss": 0.543, - "step": 25 - }, - { - "epoch": 0.46, - "learning_rate": 3.604246385510088e-05, - "loss": 0.7305, - "step": 26 - }, - { - "epoch": 0.48, - "learning_rate": 3.568831329839152e-05, - "loss": 0.4941, - "step": 27 - }, - { - "epoch": 0.5, - "learning_rate": 3.532088886237956e-05, - "loss": 0.3711, - "step": 28 - }, - { - "epoch": 0.52, - "learning_rate": 3.4940501424819927e-05, - "loss": 0.5, - "step": 29 - }, - { - "epoch": 0.54, - "learning_rate": 3.4547472831460976e-05, - "loss": 0.4004, - "step": 30 - }, - { - "epoch": 0.55, - "learning_rate": 3.4142135623730954e-05, - "loss": 0.5547, - "step": 31 - }, - { - "epoch": 0.57, - "learning_rate": 3.372483275737468e-05, - "loss": 0.4336, - "step": 32 - }, - { - "epoch": 0.59, - "learning_rate": 3.3295917312278754e-05, - "loss": 0.4766, - "step": 33 - }, - { - "epoch": 0.61, - "learning_rate": 3.285575219373079e-05, - "loss": 0.4824, - "step": 34 - }, - { - "epoch": 0.62, - "learning_rate": 3.2404709825365204e-05, - "loss": 0.7305, - "step": 35 - }, - { - "epoch": 0.64, - "learning_rate": 3.194317183405573e-05, - "loss": 0.8555, - "step": 36 - }, - { - "epoch": 0.66, - "learning_rate": 3.147152872702092e-05, - "loss": 0.6484, - "step": 37 - }, - { - "epoch": 0.68, - "learning_rate": 3.0990179561416124e-05, - "loss": 0.8008, - "step": 38 - }, - { - "epoch": 0.7, - "learning_rate": 3.0499531606691204e-05, - "loss": 0.7617, - "step": 39 - }, - { - "epoch": 0.71, - "learning_rate": 3.0000000000000004e-05, - "loss": 0.6445, - "step": 40 - }, - { - "epoch": 0.71, - "eval_loss": 0.6416881680488586, - "eval_runtime": 321.2436, - "eval_samples_per_second": 1.404, - "eval_steps_per_second": 0.704, - "step": 40 - }, - { - "epoch": 0.73, - "learning_rate": 2.9492007394952812e-05, - "loss": 0.5781, - "step": 41 - }, - { - "epoch": 0.75, - "learning_rate": 2.897598360400925e-05, - "loss": 0.6133, - "step": 42 - }, - { - "epoch": 0.77, - "learning_rate": 2.8452365234813992e-05, - "loss": 0.4551, - "step": 43 - }, - { - "epoch": 0.78, - "learning_rate": 2.792159532078314e-05, - "loss": 0.6562, - "step": 44 - }, - { - "epoch": 0.8, - "learning_rate": 2.738412294625369e-05, - "loss": 0.6484, - "step": 45 - }, - { - "epoch": 0.82, - "learning_rate": 2.684040286651338e-05, - "loss": 0.7695, - "step": 46 - }, - { - "epoch": 0.84, - "learning_rate": 2.6290895123032277e-05, - "loss": 0.4355, - "step": 47 - }, - { - "epoch": 0.86, - "learning_rate": 2.5736064654221808e-05, - "loss": 0.6445, - "step": 48 - }, - { - "epoch": 0.87, - "learning_rate": 2.5176380902050418e-05, - "loss": 0.7656, - "step": 49 - }, - { - "epoch": 0.89, - "learning_rate": 2.4612317414848804e-05, - "loss": 0.6172, - "step": 50 - }, - { - "epoch": 0.91, - "learning_rate": 2.4044351446640763e-05, - "loss": 0.6836, - "step": 51 - }, - { - "epoch": 0.93, - "learning_rate": 2.3472963553338614e-05, - "loss": 0.5859, - "step": 52 - }, - { - "epoch": 0.95, - "learning_rate": 2.2898637186144935e-05, - "loss": 0.5078, - "step": 53 - }, - { - "epoch": 0.96, - "learning_rate": 2.2321858282504606e-05, - "loss": 0.332, - "step": 54 - }, - { - "epoch": 0.98, - "learning_rate": 2.174311485495317e-05, - "loss": 0.6758, - "step": 55 - }, - { - "epoch": 1.0, - "learning_rate": 2.1162896578209517e-05, - "loss": 0.7812, - "step": 56 - }, - { - "epoch": 1.02, - "learning_rate": 2.058169437486223e-05, - "loss": 0.3379, - "step": 57 - }, - { - "epoch": 1.03, - "learning_rate": 2e-05, - "loss": 0.3945, - "step": 58 - }, - { - "epoch": 1.05, - "learning_rate": 1.9418305625137773e-05, - "loss": 0.4141, - "step": 59 - }, - { - "epoch": 1.07, - "learning_rate": 1.8837103421790486e-05, - "loss": 0.5352, - "step": 60 - }, - { - "epoch": 1.07, - "eval_loss": 0.6122210621833801, - "eval_runtime": 324.6814, - "eval_samples_per_second": 1.389, - "eval_steps_per_second": 0.696, - "step": 60 - }, - { - "epoch": 1.09, - "learning_rate": 1.8256885145046837e-05, - "loss": 0.293, - "step": 61 - }, - { - "epoch": 1.11, - "learning_rate": 1.7678141717495394e-05, - "loss": 0.3887, - "step": 62 - }, - { - "epoch": 1.12, - "learning_rate": 1.7101362813855068e-05, - "loss": 0.3613, - "step": 63 - }, - { - "epoch": 1.14, - "learning_rate": 1.6527036446661396e-05, - "loss": 0.2754, - "step": 64 - }, - { - "epoch": 1.16, - "learning_rate": 1.5955648553359247e-05, - "loss": 0.4277, - "step": 65 - }, - { - "epoch": 1.18, - "learning_rate": 1.53876825851512e-05, - "loss": 0.4199, - "step": 66 - }, - { - "epoch": 1.2, - "learning_rate": 1.4823619097949584e-05, - "loss": 0.5, - "step": 67 - }, - { - "epoch": 1.21, - "learning_rate": 1.4263935345778202e-05, - "loss": 0.3555, - "step": 68 - }, - { - "epoch": 1.23, - "learning_rate": 1.3709104876967732e-05, - "loss": 0.5, - "step": 69 - }, - { - "epoch": 1.25, - "learning_rate": 1.3159597133486628e-05, - "loss": 0.4609, - "step": 70 - }, - { - "epoch": 1.27, - "learning_rate": 1.2615877053746315e-05, - "loss": 0.3887, - "step": 71 - }, - { - "epoch": 1.28, - "learning_rate": 1.2078404679216864e-05, - "loss": 0.7617, - "step": 72 - }, - { - "epoch": 1.3, - "learning_rate": 1.1547634765186016e-05, - "loss": 0.377, - "step": 73 - }, - { - "epoch": 1.32, - "learning_rate": 1.1024016395990758e-05, - "loss": 0.3477, - "step": 74 - }, - { - "epoch": 1.34, - "learning_rate": 1.0507992605047193e-05, - "loss": 0.3223, - "step": 75 - }, - { - "epoch": 1.36, - "learning_rate": 1.0000000000000006e-05, - "loss": 0.457, - "step": 76 - }, - { - "epoch": 1.37, - "learning_rate": 9.5004683933088e-06, - "loss": 0.4785, - "step": 77 - }, - { - "epoch": 1.39, - "learning_rate": 9.009820438583881e-06, - "loss": 0.3438, - "step": 78 - }, - { - "epoch": 1.41, - "learning_rate": 8.528471272979083e-06, - "loss": 0.3867, - "step": 79 - }, - { - "epoch": 1.43, - "learning_rate": 8.056828165944282e-06, - "loss": 0.5742, - "step": 80 - }, - { - "epoch": 1.43, - "eval_loss": 0.6239878535270691, - "eval_runtime": 319.0711, - "eval_samples_per_second": 1.413, - "eval_steps_per_second": 0.708, - "step": 80 - } - ], - "logging_steps": 1, - "max_steps": 112, - "num_input_tokens_seen": 0, - "num_train_epochs": 2, - "save_steps": 40, - "total_flos": 4979777395845120.0, - "train_batch_size": 2, - "trial_name": null, - "trial_params": null -} diff --git a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin b/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin deleted file mode 100644 index 3202a33058eba63c1f2ea64297da4dcda7e0539b..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/checkpoints/r82_4e-5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-80/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1f73ff44b36523bfd37fc79f37cdae3c4041859200e83d922156941e7db0343f -size 4792 diff --git a/4e_5_r8_2VQAlora2nd/training_args.bin b/4e_5_r8_2VQAlora2nd/training_args.bin deleted file mode 100644 index 3202a33058eba63c1f2ea64297da4dcda7e0539b..0000000000000000000000000000000000000000 --- a/4e_5_r8_2VQAlora2nd/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1f73ff44b36523bfd37fc79f37cdae3c4041859200e83d922156941e7db0343f -size 4792 diff --git a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/README.md b/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/README.md deleted file mode 100644 index 27faf99f43040d0bd856edd8cd22569eb5c96a50..0000000000000000000000000000000000000000 --- a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/README.md +++ /dev/null @@ -1,202 +0,0 @@ ---- -library_name: peft -base_model: /workspace/ROCO2nd_RSV_llava-v1.6-mistral_PMC ---- - -# Model Card for Model ID - - - - - -## Model Details - -### Model Description - - - - - -- **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] - - - -- **Repository:** [More Information Needed] -- **Paper [optional]:** [More Information Needed] -- **Demo [optional]:** [More Information Needed] - -## Uses - - - -### Direct Use - - - -[More Information Needed] - -### Downstream Use [optional] - - - -[More Information Needed] - -### Out-of-Scope Use - - - -[More Information Needed] - -## Bias, Risks, and Limitations - - - -[More Information Needed] - -### Recommendations - - - -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 - - - -[More Information Needed] - -### Training Procedure - - - -#### Preprocessing [optional] - -[More Information Needed] - - -#### Training Hyperparameters - -- **Training regime:** [More Information Needed] - -#### Speeds, Sizes, Times [optional] - - - -[More Information Needed] - -## Evaluation - - - -### Testing Data, Factors & Metrics - -#### Testing Data - - - -[More Information Needed] - -#### Factors - - - -[More Information Needed] - -#### Metrics - - - -[More Information Needed] - -### Results - -[More Information Needed] - -#### Summary - - - -## Model Examination [optional] - - - -[More Information Needed] - -## Environmental Impact - - - -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] - - - -**BibTeX:** - -[More Information Needed] - -**APA:** - -[More Information Needed] - -## Glossary [optional] - - - -[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 \ No newline at end of file diff --git a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/adapter_config.json b/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/adapter_config.json deleted file mode 100644 index d87f1e6955efbf43dfb08ba879a8bc8980c148e9..0000000000000000000000000000000000000000 --- a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/adapter_config.json +++ /dev/null @@ -1,38 +0,0 @@ -{ - "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 -} \ No newline at end of file diff --git a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/adapter_model.safetensors b/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/adapter_model.safetensors deleted file mode 100644 index 98bb514b2aae92afff65c79cc04eae486ba697c8..0000000000000000000000000000000000000000 --- a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/adapter_model.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5b507789928c1185809fe88cf9e9338c4d2d8e6a4dd2fd5b643e79bc44b6ae92 -size 122253960 diff --git a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/optimizer.pt b/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/optimizer.pt deleted file mode 100644 index f58a52d09349ce70883f324ea1d82cd03b8a8280..0000000000000000000000000000000000000000 --- a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/optimizer.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:36f937dc0b915de8b810c3059bdf63fda57bfb77fa5a8591d9aa6c1f14a68697 -size 235243422 diff --git a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/rng_state.pth b/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/rng_state.pth deleted file mode 100644 index 0c31d5b80f688c46264e86a43549618187174292..0000000000000000000000000000000000000000 --- a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/rng_state.pth +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e501bba40214b8f4e27489a653a60666f8af098a4fe783aa1409edd5605a2911 -size 14244 diff --git a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/scheduler.pt b/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/scheduler.pt deleted file mode 100644 index 24ceb4b619d72820eec52618efc48e9b99f6271a..0000000000000000000000000000000000000000 --- a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/scheduler.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:eeb06cf1988f8b371306fe0191cdbdd4b95231eb8ed9a174e04262abd00fb9a4 -size 1000 diff --git a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/trainer_state.json b/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/trainer_state.json deleted file mode 100644 index 127685c0fd4ba40d747698b010c682ca3c6a8fcd..0000000000000000000000000000000000000000 --- a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/trainer_state.json +++ /dev/null @@ -1,177 +0,0 @@ -{ - "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 -} diff --git a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/training_args.bin b/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/training_args.bin deleted file mode 100644 index f3d55e7001bb557ab19b9c720be5f21127f8e996..0000000000000000000000000000000000000000 --- a/checkpoints/5VQA_ROCO2nd_RSV_llava-v1.6-mistral_PMC/checkpoint-100/training_args.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a60a1ee56456d3b3806208343cc707a04b9f707304c89603082cd68308697d19 -size 5048