Update README.md

README.md

@@ -1,199 +1,179 @@
----
-library_name: transformers
-tags: []
----
-
-# 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. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **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]
+import os
+
+import torch
+from torch.utils.data import DataLoader
+from tqdm import tqdm
+from transformers import (AdamW, AutoModelForCausalLM, AutoProcessor,
+                          get_scheduler)
+
+from data import ObjectDetectionDataset
+
+# Set device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load the model and processor
+# model = AutoModelForCausalLM.from_pretrained("model/Florence-2-base-ft", trust_remote_code=True).to(device)
+# processor = AutoProcessor.from_pretrained("model/Florence-2-base-ft", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large-ft", revision="refs/pr/10", trust_remote_code=True, device_map="cuda") # load the model on GPU
+processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large-ft", revision="refs/pr/10", trust_remote_code=True)
+
+IGNORE_ID = -100 # Pytorch ignore index when computing loss
+MAX_LENGTH = 512
+
+def collate_fn(examples):
+    prompt_texts = [example[0] for example in examples]
+    label_texts = [example[1] for example in examples]
+    images = [example[2] for example in examples]
+
+    inputs = processor(
+        images=images,
+        text=prompt_texts,
+        return_tensors="pt",
+        padding="longest",
+        max_length=MAX_LENGTH,
+    ).to(device)
+
+    return inputs, label_texts
+
+
+# Create datasets
+train_dataset = ObjectDetectionDataset("train", processor=processor)
+val_dataset = ObjectDetectionDataset("test", processor=processor)
+
+# Create DataLoader
+batch_size = 4
+num_workers = 0
+
+train_loader = DataLoader(
+    train_dataset,
+    batch_size=batch_size,
+    collate_fn=collate_fn,
+    num_workers=num_workers,
+    shuffle=True,
+)
+val_loader = DataLoader(
+    val_dataset, batch_size=batch_size, collate_fn=collate_fn, num_workers=num_workers
+)
+
+
+def train_model(train_loader, val_loader, model, processor, epochs=10, lr=1e-6):
+    optimizer = AdamW(model.parameters(), lr=lr)
+    num_training_steps = epochs * len(train_loader)
+    lr_scheduler = get_scheduler(
+        name="cosine",
+        optimizer=optimizer,
+        num_warmup_steps=100,
+        num_training_steps=num_training_steps,
+    )
+
+    for epoch in range(epochs):
+        # Training phase
+        model.train()
+        train_loss = 0
+        i = -1
+        for batch in tqdm(train_loader, desc=f"Training Epoch {epoch + 1}/{epochs}"):
+            i += 1
+            inputs, label_texts = batch
+
+            labels = processor.tokenizer(
+                label_texts,
+                return_tensors="pt",
+                padding="longest",
+                max_length=MAX_LENGTH,
+                return_token_type_ids=False, # no need to set this to True since BART does not use token type ids
+            )["input_ids"].to(device)
+
+            labels[labels == processor.tokenizer.pad_token_id] = IGNORE_ID # do not learn to predict pad tokens during training
+
+            input_ids = inputs["input_ids"]
+            pixel_values = inputs["pixel_values"]
+
+            outputs = model(
+                input_ids=input_ids, pixel_values=pixel_values, labels=labels
+            )
+            loss = outputs.loss
+
+            if i % 25 == 0:
+                print(loss)
+
+                generated_ids = model.generate(
+                    input_ids=inputs["input_ids"],
+                    pixel_values=inputs["pixel_values"],
+                    max_new_tokens=128,
+                    early_stopping=False,
+                    do_sample=False,
+                    num_beams=3,
+                )
+                generated_texts = processor.batch_decode(
+                    generated_ids, skip_special_tokens=False
+                )
+
+                for generated_text, answer in zip(generated_texts, label_texts):
+                    parsed_answer = processor.post_process_generation(
+                        generated_text,
+                        task="<OD>",
+                        image_size=(
+                            inputs["pixel_values"].shape[-2],
+                            inputs["pixel_values"].shape[-1],
+                        ),
+                    )
+                    print("GT:", answer)
+                    print("Generated Text:", generated_text)
+                    print("Pred:", parsed_answer["<OD>"])
+
+            loss.backward()
+            optimizer.step()
+            lr_scheduler.step()
+            optimizer.zero_grad()
+
+            train_loss += loss.item()
+
+        avg_train_loss = train_loss / len(train_loader)
+        print(f"Average Training Loss: {avg_train_loss}")
+
+        # Validation phase
+        model.eval()
+        val_loss = 0
+        with torch.no_grad():
+            for batch in tqdm(
+                val_loader, desc=f"Validation Epoch {epoch + 1}/{epochs}"
+            ):
+                inputs, labels = batch
+
+                input_ids = inputs["input_ids"]
+                pixel_values = inputs["pixel_values"]
+                labels = processor.tokenizer(
+                    text=labels,
+                    return_tensors="pt",
+                    padding=True,
+                    return_token_type_ids=False,
+                ).input_ids.to(device)
+
+                outputs = model(
+                    input_ids=input_ids, pixel_values=pixel_values, labels=labels
+                )
+                loss = outputs.loss
+
+                val_loss += loss.item()
+
+        avg_val_loss = val_loss / len(val_loader)
+        print(f"Average Validation Loss: {avg_val_loss}")
+
+        # Save model checkpoint
+        output_dir = f"./model_checkpoints/epoch_{epoch+1}"
+        os.makedirs(output_dir, exist_ok=True)
+        model.save_pretrained(output_dir)
+        processor.save_pretrained(output_dir)
+
+for param in model.vision_tower.parameters():
+    param.requires_grad = False
+
+model_total_params = sum(p.numel() for p in model.parameters())
+model_train_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
+
+print(f"Number of trainable parameters {model_train_params} out of {model_total_params}, rate: {model_train_params/model_total_params:0.3f}")
+
+train_model(train_loader, val_loader, model, processor, epochs=3, lr=1e-6)
+
+model.push_to_hub("danelcsb/Florence-2-FT-cppe-5")
+processor.push_to_hub("danelcsb/Florence-2-FT-cppe-5")