Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+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
+
+```python
+# you will need to adjust code if you didnt use peft
+
+from PIL import Image
+from transformers import PaliGemmaForConditionalGeneration, PaliGemmaProcessor
+import torch
+import requests
+from peft import PeftModel
+
+base_model_id = BASE_MODEL_ID
+peft_model_id = THIS_MODEL_ID
+max_new_tokens = 100
+text = "Whats on the flower?"
+img_url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/bee.JPG?download=true"
+image = Image.open(requests.get(img_url, stream=True).raw)
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+base_model = PaliGemmaForConditionalGeneration.from_pretrained(base_model_id)
+processor = PaliGemmaProcessor.from_pretrained(base_model_id)
+
+model = PeftModel.from_pretrained(base_model, peft_model_id)
+model.merge_and_unload()
+
+model = model.eval().to(device)
+
+inputs = processor(text=text, images=image, return_tensors="pt").to(device)
+with torch.inference_mode():
+    generated_ids = model.generate(
+        **inputs,
+        max_new_tokens=max_new_tokens,
+        do_sample=False,
+    )
+result = processor.batch_decode(generated_ids, skip_special_tokens=True)
+print(result)
+```

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": [
+    "o_proj",
+    "v_proj",
+    "linear",
+    "up_proj",
+    "out_proj",
+    "down_proj",
+    "k_proj",
+    "lm_head",
+    "fc2",
+    "fc1",
+    "gate_proj",
+    "q_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 sha256:7fd55ccb9725cdd14eb840234ac5fc4db8d95acb943edf0de13f4a6c7ed1cc0c
+size 2237231056

checkpoint-281/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 0.12.0

checkpoint-281/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": [
+    "o_proj",
+    "v_proj",
+    "linear",
+    "up_proj",
+    "out_proj",
+    "down_proj",
+    "k_proj",
+    "lm_head",
+    "fc2",
+    "fc1",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-281/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd55ccb9725cdd14eb840234ac5fc4db8d95acb943edf0de13f4a6c7ed1cc0c
+size 2237231056

checkpoint-281/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d6710279ac800c2a985fe0c3ed7b79a2d82cf6e85db2d9ebb66b50d0071863
+size 190292282

checkpoint-281/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116fa21b44b3fb6fc207010c99c34936bd28b69f96f2a354fa1c0bc2c2540102
+size 14244

checkpoint-281/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7822001fdd8a375d3a21ed9d4bbe01bd7e7a70de9e735d6c42f9db269c561815
+size 1064

checkpoint-281/trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": 0.7993471622467041,
+  "best_model_checkpoint": "ryukijano-paligemma-finetuned\\checkpoint-281",
+  "epoch": 8.992,
+  "eval_steps": 500,
+  "global_step": 281,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.558422088623047,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 1.5484,
+      "step": 25
+    },
+    {
+      "epoch": 0.992,
+      "eval_loss": 1.8585567474365234,
+      "eval_runtime": 19.9397,
+      "eval_samples_per_second": 12.538,
+      "eval_steps_per_second": 6.269,
+      "step": 31
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 4.804387092590332,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 1.5841,
+      "step": 50
+    },
+    {
+      "epoch": 1.984,
+      "eval_loss": 1.803800106048584,
+      "eval_runtime": 20.1703,
+      "eval_samples_per_second": 12.394,
+      "eval_steps_per_second": 6.197,
+      "step": 62
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 4.384600639343262,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 1.5184,
+      "step": 75
+    },
+    {
+      "epoch": 2.976,
+      "eval_loss": 1.677108883857727,
+      "eval_runtime": 19.7443,
+      "eval_samples_per_second": 12.662,
+      "eval_steps_per_second": 6.331,
+      "step": 93
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 4.877094268798828,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 1.3985,
+      "step": 100
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.035943508148193,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 1.2081,
+      "step": 125
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4368913173675537,
+      "eval_runtime": 20.3141,
+      "eval_samples_per_second": 12.307,
+      "eval_steps_per_second": 6.153,
+      "step": 125
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 3.080859422683716,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 1.0413,
+      "step": 150
+    },
+    {
+      "epoch": 4.992,
+      "eval_loss": 1.1628715991973877,
+      "eval_runtime": 20.1314,
+      "eval_samples_per_second": 12.418,
+      "eval_steps_per_second": 6.209,
+      "step": 156
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 2.4689671993255615,
+      "learning_rate": 1.1290322580645164e-05,
+      "loss": 0.8372,
+      "step": 175
+    },
+    {
+      "epoch": 5.984,
+      "eval_loss": 0.9508486390113831,
+      "eval_runtime": 20.101,
+      "eval_samples_per_second": 12.437,
+      "eval_steps_per_second": 6.219,
+      "step": 187
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 1.9029561281204224,
+      "learning_rate": 1.2903225806451613e-05,
+      "loss": 0.7411,
+      "step": 200
+    },
+    {
+      "epoch": 6.976,
+      "eval_loss": 0.8626062870025635,
+      "eval_runtime": 19.8558,
+      "eval_samples_per_second": 12.591,
+      "eval_steps_per_second": 6.295,
+      "step": 218
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 2.5312154293060303,
+      "learning_rate": 1.4516129032258066e-05,
+      "loss": 0.6682,
+      "step": 225
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.895367383956909,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 0.5702,
+      "step": 250
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.8156193494796753,
+      "eval_runtime": 20.1295,
+      "eval_samples_per_second": 12.42,
+      "eval_steps_per_second": 6.21,
+      "step": 250
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 3.090899705886841,
+      "learning_rate": 1.774193548387097e-05,
+      "loss": 0.5168,
+      "step": 275
+    },
+    {
+      "epoch": 8.992,
+      "eval_loss": 0.7993471622467041,
+      "eval_runtime": 20.053,
+      "eval_samples_per_second": 12.467,
+      "eval_steps_per_second": 6.233,
+      "step": 281
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.5386074301492224e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-281/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b15a87654c40c305c7513355a0aa4ebd5cd4b669826e6a32fbcdd26b646a113
+size 5240

runs/Oct07_14-04-44_UOL-PBWS1004455/events.out.tfevents.1728306289.UOL-PBWS1004455.78452.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be3d19eb81dfb2d9407f2e54ea7d4e88805efef360e1511367b9fc95994d05a
-size 57578
+oid sha256:4fb598e2a6b8e0807b4ca8e74d94993eaf108f3fc3cd78e32cf69af7914d95d5
+size 59378

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b15a87654c40c305c7513355a0aa4ebd5cd4b669826e6a32fbcdd26b646a113
+size 5240

training_params.json

@@ -0,0 +1,37 @@
+{
+    "model": "google/paligemma-3b-pt-224",
+    "project_name": "ryukijano-paligemma-finetuned",
+    "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": 100,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 16,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "merge_adapter": false,
+    "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": "Ryukijano"
+}