submit

VQARADQformer/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /workspace/ROCO_pmc_llava-v1.6-mistral_qfomer
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.1.dev0

VQARADQformer/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlavaMistralForCausalLM",
+    "parent_library": "llava.model.language_model.llava_mistral"
+  },
+  "base_model_name_or_path": "/workspace/ROCO_pmc_llava-v1.6-mistral_qfomer",
+  "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",
+    "query_tokens",
+    "post_projection",
+    "projection"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

VQARADQformer/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb1ae940353e6b6210220d0e9da3f7a45a7b3f3cf13989f03b54d4908e04cfa
+size 126715784

VQARADQformer/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb82d6ebe25102ea403df58aad611381e5b65a316fb950f364448549d2d8a4b
+size 4792

checkpoints/vqaradROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: /workspace/ROCO_pmc_llava-v1.6-mistral_qfomer
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.1.dev0

checkpoints/vqaradROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-100/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "LlavaMistralForCausalLM",
+    "parent_library": "llava.model.language_model.llava_mistral"
+  },
+  "base_model_name_or_path": "/workspace/ROCO_pmc_llava-v1.6-mistral_qfomer",
+  "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",
+    "query_tokens",
+    "post_projection",
+    "projection"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoints/vqaradROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb1ae940353e6b6210220d0e9da3f7a45a7b3f3cf13989f03b54d4908e04cfa
+size 126715784

checkpoints/vqaradROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a3ca3603fba5490b0e462e7910a4b36960a61a7dddb3af74baf415c9c47d579
+size 235244382

checkpoints/vqaradROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51def08afacaca5e0081db7583900ac5b21e1c142b3fb68bacc832d346402f93
+size 14244

checkpoints/vqaradROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc0a2ec6a5a0e5c2aad0c70581ed4fe830f5ed4fe8100cd54232df8cd96022d
+size 1000

checkpoints/vqaradROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-100/trainer_state.json

@@ -0,0 +1,653 @@
+{
+  "best_metric": 0.6763745546340942,
+  "best_model_checkpoint": "/workspace/checkpoints/vqaradROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-100",
+  "epoch": 1.7837235228539576,
+  "eval_steps": 25,
+  "global_step": 100,
+  "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": 3.6094,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1e-05,
+      "loss": 3.7344,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 3.75,
+      "step": 3
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2e-05,
+      "loss": 3.5625,
+      "step": 4
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9995769500822007e-05,
+      "loss": 2.3125,
+      "step": 5
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9983081582712684e-05,
+      "loss": 2.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9961946980917457e-05,
+      "loss": 1.8203,
+      "step": 7
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 1.2812,
+      "step": 8
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9894416385809444e-05,
+      "loss": 0.8438,
+      "step": 9
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9848077530122083e-05,
+      "loss": 0.875,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9793406217655516e-05,
+      "loss": 0.793,
+      "step": 11
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 1.0312,
+      "step": 12
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 0.9648,
+      "step": 13
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.957989512315489e-05,
+      "loss": 1.1094,
+      "step": 14
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.949242643573034e-05,
+      "loss": 0.8281,
+      "step": 15
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.6602,
+      "step": 16
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9293475242268224e-05,
+      "loss": 0.9688,
+      "step": 17
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9182161068802742e-05,
+      "loss": 0.6641,
+      "step": 18
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9063077870366504e-05,
+      "loss": 1.0781,
+      "step": 19
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 1.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.880201391180111e-05,
+      "loss": 0.8086,
+      "step": 21
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 0.7227,
+      "step": 22
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8511166724369997e-05,
+      "loss": 0.6406,
+      "step": 23
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 0.8906,
+      "step": 24
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.819152044288992e-05,
+      "loss": 0.7656,
+      "step": 25
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 0.7382526993751526,
+      "eval_runtime": 2683.2319,
+      "eval_samples_per_second": 0.168,
+      "eval_steps_per_second": 0.084,
+      "step": 25
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.802123192755044e-05,
+      "loss": 1.0312,
+      "step": 26
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.784415664919576e-05,
+      "loss": 0.7656,
+      "step": 27
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.7539,
+      "step": 28
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7470250712409963e-05,
+      "loss": 0.6562,
+      "step": 29
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7273736415730488e-05,
+      "loss": 0.5938,
+      "step": 30
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.7852,
+      "step": 31
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.5352,
+      "step": 32
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6647958656139377e-05,
+      "loss": 0.6875,
+      "step": 33
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 0.6406,
+      "step": 34
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.6202354912682602e-05,
+      "loss": 0.8125,
+      "step": 35
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 0.8555,
+      "step": 36
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.573576436351046e-05,
+      "loss": 0.8789,
+      "step": 37
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5495089780708062e-05,
+      "loss": 0.8438,
+      "step": 38
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5249765803345602e-05,
+      "loss": 0.8945,
+      "step": 39
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7773,
+      "step": 40
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.4746003697476406e-05,
+      "loss": 0.7305,
+      "step": 41
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4487991802004625e-05,
+      "loss": 0.6641,
+      "step": 42
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.4226182617406996e-05,
+      "loss": 0.5664,
+      "step": 43
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 0.7148,
+      "step": 44
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3692061473126845e-05,
+      "loss": 0.7969,
+      "step": 45
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 0.8008,
+      "step": 46
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3145447561516138e-05,
+      "loss": 0.5234,
+      "step": 47
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 0.8125,
+      "step": 48
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.2588190451025209e-05,
+      "loss": 0.8867,
+      "step": 49
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.2306158707424402e-05,
+      "loss": 0.6641,
+      "step": 50
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 0.6922495365142822,
+      "eval_runtime": 2680.3182,
+      "eval_samples_per_second": 0.168,
+      "eval_steps_per_second": 0.084,
+      "step": 50
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.2022175723320382e-05,
+      "loss": 0.832,
+      "step": 51
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.6562,
+      "step": 52
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1449318593072468e-05,
+      "loss": 0.5469,
+      "step": 53
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1160929141252303e-05,
+      "loss": 0.4609,
+      "step": 54
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0871557427476585e-05,
+      "loss": 0.6719,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 0.9102,
+      "step": 56
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.0290847187431115e-05,
+      "loss": 0.4551,
+      "step": 57
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1e-05,
+      "loss": 0.5195,
+      "step": 58
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.709152812568886e-06,
+      "loss": 0.6875,
+      "step": 59
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 0.7383,
+      "step": 60
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.128442572523418e-06,
+      "loss": 0.4355,
+      "step": 61
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.839070858747697e-06,
+      "loss": 0.5703,
+      "step": 62
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.550681406927534e-06,
+      "loss": 0.5781,
+      "step": 63
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.4902,
+      "step": 64
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.977824276679623e-06,
+      "loss": 0.6602,
+      "step": 65
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 7.6938412925756e-06,
+      "loss": 0.5742,
+      "step": 66
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.411809548974792e-06,
+      "loss": 0.6562,
+      "step": 67
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 0.5039,
+      "step": 68
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.854552438483866e-06,
+      "loss": 0.875,
+      "step": 69
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.579798566743314e-06,
+      "loss": 0.6445,
+      "step": 70
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.3079385268731575e-06,
+      "loss": 0.6055,
+      "step": 71
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.9336,
+      "step": 72
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.773817382593008e-06,
+      "loss": 0.5469,
+      "step": 73
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.512008197995379e-06,
+      "loss": 0.543,
+      "step": 74
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.253996302523596e-06,
+      "loss": 0.498,
+      "step": 75
+    },
+    {
+      "epoch": 1.34,
+      "eval_loss": 0.6778966188430786,
+      "eval_runtime": 2674.086,
+      "eval_samples_per_second": 0.169,
+      "eval_steps_per_second": 0.085,
+      "step": 75
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.6641,
+      "step": 76
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 4.7502341966544e-06,
+      "loss": 0.6797,
+      "step": 77
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 4.504910219291941e-06,
+      "loss": 0.4668,
+      "step": 78
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 4.264235636489542e-06,
+      "loss": 0.6055,
+      "step": 79
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 4.028414082972141e-06,
+      "loss": 0.8516,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.797645087317401e-06,
+      "loss": 0.5664,
+      "step": 81
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 3.5721239031346067e-06,
+      "loss": 0.4219,
+      "step": 82
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 3.3520413438606215e-06,
+      "loss": 0.6641,
+      "step": 83
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.1375836213126653e-06,
+      "loss": 0.291,
+      "step": 84
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.4648,
+      "step": 85
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.726263584269513e-06,
+      "loss": 0.4922,
+      "step": 86
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.529749287590042e-06,
+      "loss": 0.6953,
+      "step": 87
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.5039,
+      "step": 88
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.155843350804243e-06,
+      "loss": 0.7305,
+      "step": 89
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.9787680724495617e-06,
+      "loss": 0.4824,
+      "step": 90
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.808479557110081e-06,
+      "loss": 0.4863,
+      "step": 91
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 0.4883,
+      "step": 92
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.4888332756300027e-06,
+      "loss": 0.8008,
+      "step": 93
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.5234,
+      "step": 94
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1979860881988903e-06,
+      "loss": 0.5703,
+      "step": 95
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.0636735967658785e-06,
+      "loss": 0.4668,
+      "step": 96
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 9.369221296335007e-07,
+      "loss": 0.5039,
+      "step": 97
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 8.178389311972612e-07,
+      "loss": 0.9141,
+      "step": 98
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.065247577317747e-07,
+      "loss": 0.5391,
+      "step": 99
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.5586,
+      "step": 100
+    },
+    {
+      "epoch": 1.78,
+      "eval_loss": 0.6763745546340942,
+      "eval_runtime": 2672.3202,
+      "eval_samples_per_second": 0.169,
+      "eval_steps_per_second": 0.085,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 112,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 25,
+  "total_flos": 6378259418184192.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/vqaradROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb82d6ebe25102ea403df58aad611381e5b65a316fb950f364448549d2d8a4b
+size 4792