add slake

SLAKEQformer/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

SLAKEQformer/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": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "mm_projector",
+    "query_tokens",
+    "post_projection",
+    "projection"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

SLAKEQformer/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f48565332da35719c306688363069a9e90ddc7e7ad1b8cd787311e08dff637
+size 206932176

SLAKEQformer/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c952e743fb5bb7660f1301baa3dd9076ecdf5d57bf7bc408bd3a4a151cdb3ea4
+size 4792

checkpoints/SLAKEROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-150/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/SLAKEROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-150/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": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "mm_projector",
+    "query_tokens",
+    "post_projection",
+    "projection"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoints/SLAKEROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f48565332da35719c306688363069a9e90ddc7e7ad1b8cd787311e08dff637
+size 206932176

checkpoints/SLAKEROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f60f205907fcb609ee9b15df875089977f7cad526f5396e9c6bd52fb7257b00
+size 386239326

checkpoints/SLAKEROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ab200adcc7415adf5d1c3b0962cf45153ed2fce54d7a4e6cc88dd98282e329
+size 14244

checkpoints/SLAKEROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f7a4ac76cf8abf095b00db440d71d496a5c29a0354356b04dd83c0f5f74c50
+size 1000

checkpoints/SLAKEROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-150/trainer_state.json

@@ -0,0 +1,961 @@
+{
+  "best_metric": 0.24133720993995667,
+  "best_model_checkpoint": "/workspace/checkpoints/SLAKEROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-150",
+  "epoch": 0.975609756097561,
+  "eval_steps": 30,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.3594,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.6094,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.4e-05,
+      "loss": 1.5859,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.3438,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4e-05,
+      "loss": 0.7969,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.999549432349539e-05,
+      "loss": 0.7383,
+      "step": 6
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.998197932409364e-05,
+      "loss": 1.1797,
+      "step": 7
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.9959461091216256e-05,
+      "loss": 0.582,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.9927949770850535e-05,
+      "loss": 0.5625,
+      "step": 9
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.988745956097806e-05,
+      "loss": 0.5273,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.9838008705177537e-05,
+      "loss": 0.6641,
+      "step": 11
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.977961948440491e-05,
+      "loss": 0.7266,
+      "step": 12
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.971231820695417e-05,
+      "loss": 0.8281,
+      "step": 13
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.963613519660379e-05,
+      "loss": 0.5664,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.955110477895373e-05,
+      "loss": 0.7891,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.945726526595949e-05,
+      "loss": 0.4141,
+      "step": 16
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.935465893866998e-05,
+      "loss": 0.6328,
+      "step": 17
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.924333202817699e-05,
+      "loss": 0.6211,
+      "step": 18
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.912333469478502e-05,
+      "loss": 0.3438,
+      "step": 19
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.899472100541064e-05,
+      "loss": 0.4531,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.885754890922169e-05,
+      "loss": 0.9258,
+      "step": 21
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.8711880211527244e-05,
+      "loss": 0.4023,
+      "step": 22
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.8557780545930194e-05,
+      "loss": 0.4453,
+      "step": 23
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.8395319344754776e-05,
+      "loss": 0.4766,
+      "step": 24
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.822456980776272e-05,
+      "loss": 0.3887,
+      "step": 25
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.804560886917171e-05,
+      "loss": 0.4062,
+      "step": 26
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.7858517162991375e-05,
+      "loss": 0.4863,
+      "step": 27
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.766337898669219e-05,
+      "loss": 0.3926,
+      "step": 28
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.7460282263223764e-05,
+      "loss": 0.3965,
+      "step": 29
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.7249318501399613e-05,
+      "loss": 0.4355,
+      "step": 30
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.4406982958316803,
+      "eval_runtime": 6292.7173,
+      "eval_samples_per_second": 0.167,
+      "eval_steps_per_second": 0.084,
+      "step": 30
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.703058275466623e-05,
+      "loss": 0.4922,
+      "step": 31
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.6804173578275094e-05,
+      "loss": 0.4688,
+      "step": 32
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.657019298487685e-05,
+      "loss": 0.3711,
+      "step": 33
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 3.6328746398557715e-05,
+      "loss": 0.3438,
+      "step": 34
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.607994260733881e-05,
+      "loss": 0.6016,
+      "step": 35
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.582389371415977e-05,
+      "loss": 0.3672,
+      "step": 36
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.556071508636879e-05,
+      "loss": 0.5547,
+      "step": 37
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.529052530374185e-05,
+      "loss": 0.2969,
+      "step": 38
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.5013446105054486e-05,
+      "loss": 0.3223,
+      "step": 39
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.472960233323025e-05,
+      "loss": 0.4219,
+      "step": 40
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.443912187909049e-05,
+      "loss": 0.4336,
+      "step": 41
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.4142135623730954e-05,
+      "loss": 0.3984,
+      "step": 42
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.3838777379550926e-05,
+      "loss": 0.2354,
+      "step": 43
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.352918382996174e-05,
+      "loss": 0.4336,
+      "step": 44
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.321349446780163e-05,
+      "loss": 0.3457,
+      "step": 45
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.2891851532484784e-05,
+      "loss": 0.5039,
+      "step": 46
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.256439994591285e-05,
+      "loss": 0.3184,
+      "step": 47
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.223128724717783e-05,
+      "loss": 0.3613,
+      "step": 48
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.189266352608574e-05,
+      "loss": 0.2949,
+      "step": 49
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.1548681355530966e-05,
+      "loss": 0.5195,
+      "step": 50
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.1199495722751914e-05,
+      "loss": 0.2354,
+      "step": 51
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.084526395949871e-05,
+      "loss": 0.3945,
+      "step": 52
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.0486145671144637e-05,
+      "loss": 0.3066,
+      "step": 53
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.012230266477313e-05,
+      "loss": 0.3926,
+      "step": 54
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.9753898876272695e-05,
+      "loss": 0.4102,
+      "step": 55
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.9381100296472742e-05,
+      "loss": 0.2871,
+      "step": 56
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.9004074896353468e-05,
+      "loss": 0.2656,
+      "step": 57
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.862299255136357e-05,
+      "loss": 0.4492,
+      "step": 58
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 2.8238024964879857e-05,
+      "loss": 0.3379,
+      "step": 59
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.7849345590843276e-05,
+      "loss": 0.377,
+      "step": 60
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 0.34713810682296753,
+      "eval_runtime": 6307.1462,
+      "eval_samples_per_second": 0.167,
+      "eval_steps_per_second": 0.084,
+      "step": 60
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.7457129555606177e-05,
+      "loss": 0.209,
+      "step": 61
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.7061553579026017e-05,
+      "loss": 0.2617,
+      "step": 62
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.6662795894841155e-05,
+      "loss": 0.291,
+      "step": 63
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.6261036170364448e-05,
+      "loss": 0.2451,
+      "step": 64
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.585645542553101e-05,
+      "loss": 0.5625,
+      "step": 65
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.5449235951336458e-05,
+      "loss": 0.2158,
+      "step": 66
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.5039561227702507e-05,
+      "loss": 0.3145,
+      "step": 67
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.4627615840806837e-05,
+      "loss": 0.3145,
+      "step": 68
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.4213585399914528e-05,
+      "loss": 0.2617,
+      "step": 69
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.3797656453748567e-05,
+      "loss": 0.4473,
+      "step": 70
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.3380016406436986e-05,
+      "loss": 0.3184,
+      "step": 71
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.296085343307463e-05,
+      "loss": 0.2949,
+      "step": 72
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.2540356394937577e-05,
+      "loss": 0.4062,
+      "step": 73
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.2118714754388323e-05,
+      "loss": 0.5195,
+      "step": 74
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.1696118489510186e-05,
+      "loss": 0.373,
+      "step": 75
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.127275800850933e-05,
+      "loss": 0.3301,
+      "step": 76
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.084882406392297e-05,
+      "loss": 0.3047,
+      "step": 77
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.0424507666672473e-05,
+      "loss": 0.2578,
+      "step": 78
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2e-05,
+      "loss": 0.2852,
+      "step": 79
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.957549233332753e-05,
+      "loss": 0.2314,
+      "step": 80
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.915117593607704e-05,
+      "loss": 0.3164,
+      "step": 81
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8727241991490674e-05,
+      "loss": 0.291,
+      "step": 82
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8303881510489824e-05,
+      "loss": 0.3613,
+      "step": 83
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.788128524561168e-05,
+      "loss": 0.2158,
+      "step": 84
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7459643605062427e-05,
+      "loss": 0.5234,
+      "step": 85
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.7039146566925376e-05,
+      "loss": 0.3613,
+      "step": 86
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6619983593563024e-05,
+      "loss": 0.2871,
+      "step": 87
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.6202343546251432e-05,
+      "loss": 0.2363,
+      "step": 88
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.578641460008548e-05,
+      "loss": 0.2021,
+      "step": 89
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.5372384159193173e-05,
+      "loss": 0.2676,
+      "step": 90
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 0.2674311399459839,
+      "eval_runtime": 6309.5363,
+      "eval_samples_per_second": 0.167,
+      "eval_steps_per_second": 0.084,
+      "step": 90
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.4960438772297501e-05,
+      "loss": 0.2637,
+      "step": 91
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.4550764048663547e-05,
+      "loss": 0.2559,
+      "step": 92
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.4143544574468995e-05,
+      "loss": 0.2451,
+      "step": 93
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.3738963829635559e-05,
+      "loss": 0.2305,
+      "step": 94
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.333720410515885e-05,
+      "loss": 0.1494,
+      "step": 95
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.2938446420973984e-05,
+      "loss": 0.1875,
+      "step": 96
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.2542870444393831e-05,
+      "loss": 0.4883,
+      "step": 97
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.2150654409156725e-05,
+      "loss": 0.248,
+      "step": 98
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.176197503512015e-05,
+      "loss": 0.1709,
+      "step": 99
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.1377007448636434e-05,
+      "loss": 0.2295,
+      "step": 100
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.0995925103646532e-05,
+      "loss": 0.2988,
+      "step": 101
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.0618899703527265e-05,
+      "loss": 0.332,
+      "step": 102
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.0246101123727315e-05,
+      "loss": 0.2119,
+      "step": 103
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.877697335226872e-06,
+      "loss": 0.1865,
+      "step": 104
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 9.51385432885537e-06,
+      "loss": 0.3418,
+      "step": 105
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 9.1547360405013e-06,
+      "loss": 0.2061,
+      "step": 106
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.800504277248094e-06,
+      "loss": 0.2188,
+      "step": 107
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.451318644469037e-06,
+      "loss": 0.3438,
+      "step": 108
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 8.10733647391427e-06,
+      "loss": 0.3457,
+      "step": 109
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.768712752822179e-06,
+      "loss": 0.2217,
+      "step": 110
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.435600054087153e-06,
+      "loss": 0.2275,
+      "step": 111
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.108148467515217e-06,
+      "loss": 0.3984,
+      "step": 112
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 6.7865055321983754e-06,
+      "loss": 0.1797,
+      "step": 113
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 6.4708161700382655e-06,
+      "loss": 0.3203,
+      "step": 114
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 6.161222620449079e-06,
+      "loss": 0.2227,
+      "step": 115
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.857864376269051e-06,
+      "loss": 0.2354,
+      "step": 116
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.560878120909512e-06,
+      "loss": 0.1816,
+      "step": 117
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 5.2703976667697575e-06,
+      "loss": 0.5,
+      "step": 118
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.986553894945512e-06,
+      "loss": 0.2002,
+      "step": 119
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.709474696258154e-06,
+      "loss": 0.3242,
+      "step": 120
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 0.24586248397827148,
+      "eval_runtime": 6268.6185,
+      "eval_samples_per_second": 0.168,
+      "eval_steps_per_second": 0.084,
+      "step": 120
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.439284913631215e-06,
+      "loss": 0.2598,
+      "step": 121
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.176106285840229e-06,
+      "loss": 0.2031,
+      "step": 122
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.920057392661192e-06,
+      "loss": 0.2598,
+      "step": 123
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.6712536014422885e-06,
+      "loss": 0.2363,
+      "step": 124
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.429807015123159e-06,
+      "loss": 0.2441,
+      "step": 125
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.1958264217249145e-06,
+      "loss": 0.2119,
+      "step": 126
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.9694172453337743e-06,
+      "loss": 0.332,
+      "step": 127
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.7506814986003937e-06,
+      "loss": 0.3105,
+      "step": 128
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.539717736776237e-06,
+      "loss": 0.1367,
+      "step": 129
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.3366210133078136e-06,
+      "loss": 0.2598,
+      "step": 130
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.1414828370086326e-06,
+      "loss": 0.2256,
+      "step": 131
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.9543911308282992e-06,
+      "loss": 0.1982,
+      "step": 132
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.775430192237284e-06,
+      "loss": 0.1406,
+      "step": 133
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6046806552452254e-06,
+      "loss": 0.3027,
+      "step": 134
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.442219454069813e-06,
+      "loss": 0.4297,
+      "step": 135
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.2881197884727592e-06,
+      "loss": 0.2715,
+      "step": 136
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.142451090778316e-06,
+      "loss": 0.334,
+      "step": 137
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.0052789945893625e-06,
+      "loss": 0.3242,
+      "step": 138
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.766653052149831e-07,
+      "loss": 0.2676,
+      "step": 139
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 7.56667971823013e-07,
+      "loss": 0.2578,
+      "step": 140
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 6.453410613300226e-07,
+      "loss": 0.1514,
+      "step": 141
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.427347340405087e-07,
+      "loss": 0.1953,
+      "step": 142
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.4889522104627715e-07,
+      "loss": 0.3125,
+      "step": 143
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.6386480339621886e-07,
+      "loss": 0.2441,
+      "step": 144
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.8768179304583087e-07,
+      "loss": 0.3125,
+      "step": 145
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.2038051559509333e-07,
+      "loss": 0.2373,
+      "step": 146
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.6199129482246335e-07,
+      "loss": 0.1973,
+      "step": 147
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1254043902195089e-07,
+      "loss": 0.3496,
+      "step": 148
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.205022914946957e-08,
+      "loss": 0.291,
+      "step": 149
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.053890878374933e-08,
+      "loss": 0.2754,
+      "step": 150
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 0.24133720993995667,
+      "eval_runtime": 6310.9443,
+      "eval_samples_per_second": 0.167,
+      "eval_steps_per_second": 0.084,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 153,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 30,
+  "total_flos": 9543693401269248.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/SLAKEROCO_pmc_llava-v1.6-mistral_qfomer/checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c952e743fb5bb7660f1301baa3dd9076ecdf5d57bf7bc408bd3a4a151cdb3ea4
+size 4792