Upload folder using huggingface_hub

README.md

@@ -0,0 +1,19 @@
+---
+tags:
+- autotrain
+- text-generation-inference
+- image-text-to-text
+- text-generation
+- peft
+library_name: transformers
+base_model: google/paligemma-3b-pt-224
+license: other
+datasets:
+- abhishek/vqa_small
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/paligemma-3b-pt-224",
+  "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": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "out_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "lm_head",
+    "linear",
+    "fc1",
+    "v_proj",
+    "k_proj",
+    "fc2",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76d132961c6ca6b2420542b5d24225dc99daf883a89dddc4b7925b8e10a2bff
+size 2237231056

checkpoint-375/README.md

@@ -0,0 +1,202 @@
+---
+base_model: google/paligemma-3b-pt-224
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-375/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/paligemma-3b-pt-224",
+  "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": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "out_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "lm_head",
+    "linear",
+    "fc1",
+    "v_proj",
+    "k_proj",
+    "fc2",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76d132961c6ca6b2420542b5d24225dc99daf883a89dddc4b7925b8e10a2bff
+size 2237231056

checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1e351e175d52d45c91df6ba2af877dd108b58d0713fd37fb85fbeb5285604cd
+size 190292282

checkpoint-375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40dd10453491a5e0534f4a7742924919ec1bfe4affa9ce237c2deb4e764f2302
+size 14244

checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048eb1b2749cc837959436178b94ff7ddbedc471e5b68efde70aa0f283323e9b
+size 1064

checkpoint-375/trainer_state.json

@@ -0,0 +1,162 @@
+{
+  "best_metric": 0.8111211061477661,
+  "best_model_checkpoint": "autotrain-paligemma-finetuned-vqa/checkpoint-375",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.544835567474365,
+      "learning_rate": 1.3157894736842108e-05,
+      "loss": 1.6534,
+      "step": 25
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.025909423828125,
+      "learning_rate": 1.9287833827893176e-05,
+      "loss": 1.6205,
+      "step": 50
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 8.462043762207031,
+      "learning_rate": 1.7804154302670624e-05,
+      "loss": 1.1119,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.2696471214294434,
+      "learning_rate": 1.6320474777448072e-05,
+      "loss": 0.7722,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.208315372467041,
+      "learning_rate": 1.483679525222552e-05,
+      "loss": 0.8746,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.912371039390564,
+      "eval_runtime": 24.3232,
+      "eval_samples_per_second": 10.278,
+      "eval_steps_per_second": 5.139,
+      "step": 125
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 3.5270237922668457,
+      "learning_rate": 1.3353115727002968e-05,
+      "loss": 0.6841,
+      "step": 150
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 3.0572621822357178,
+      "learning_rate": 1.1869436201780416e-05,
+      "loss": 0.7057,
+      "step": 175
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.3405561447143555,
+      "learning_rate": 1.0385756676557866e-05,
+      "loss": 0.6459,
+      "step": 200
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 4.48429012298584,
+      "learning_rate": 8.902077151335312e-06,
+      "loss": 0.6645,
+      "step": 225
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.817482948303223,
+      "learning_rate": 7.41839762611276e-06,
+      "loss": 0.6855,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.827422022819519,
+      "eval_runtime": 24.2956,
+      "eval_samples_per_second": 10.29,
+      "eval_steps_per_second": 5.145,
+      "step": 250
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 3.3924331665039062,
+      "learning_rate": 5.934718100890208e-06,
+      "loss": 0.5572,
+      "step": 275
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 8.049240112304688,
+      "learning_rate": 4.451038575667656e-06,
+      "loss": 0.5909,
+      "step": 300
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 3.2632410526275635,
+      "learning_rate": 2.967359050445104e-06,
+      "loss": 0.6251,
+      "step": 325
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 6.481785297393799,
+      "learning_rate": 1.483679525222552e-06,
+      "loss": 0.4504,
+      "step": 350
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.444954872131348,
+      "learning_rate": 5.934718100890208e-08,
+      "loss": 0.6476,
+      "step": 375
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8111211061477661,
+      "eval_runtime": 24.2844,
+      "eval_samples_per_second": 10.295,
+      "eval_steps_per_second": 5.147,
+      "step": 375
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1793929907551424e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f28921e86366c18209a12c589c30a7e6804d8653c1ae08569de9ae968eac56
+size 5240

runs/Jul24_07-26-22_beast/events.out.tfevents.1721798919.beast.937151.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a597ba8e4499d7bbb5139f74d07eb8c60cac471bc0fbccb9f4d43c85e45e28a
-size 9057
+oid sha256:af6031ef8b3f9e8aad5a4c9b5d9b5bb793477c3efacd0874946f2a61ccea6db2
+size 10104

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f28921e86366c18209a12c589c30a7e6804d8653c1ae08569de9ae968eac56
+size 5240

training_params.json

@@ -0,0 +1,36 @@
+{
+    "model": "google/paligemma-3b-pt-224",
+    "project_name": "autotrain-paligemma-finetuned-vqa",
+    "data_path": "abhishek/vqa_small",
+    "train_split": "train",
+    "valid_split": "validation",
+    "trainer": "vqa",
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "eval_strategy": "epoch",
+    "save_total_limit": 1,
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "lr": 2e-05,
+    "epochs": 3,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "image_column": "image",
+    "text_column": "multiple_choice_answer",
+    "prompt_text_column": "question",
+    "push_to_hub": true,
+    "username": "abhishek"
+}