Upload folder using huggingface_hub

README.md

@@ -0,0 +1,138 @@
+---
+library_name: transformers
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+- language-modeling
+- causal-lm
+- gpt2
+- coco
+model-index:
+- name: COCO_no_sports_real_v1
+  results: []
+language:
+- en
+---
+
+# COCO_no_sports_real_v1
+
+## Model Description
+
+`COCO_no_sports_real_v1` is a causal language model based on [GPT-2](https://huggingface.co/gpt2), fine-tuned on the florence-generated image captions of a subset of [COCO](https://cocodataset.org/). This subset is labeled for physical activity content in the text:
+
+- **Label 0**: Not related to physical activity (e.g., indoor scenes, objects, people at rest)
+- **Label 1**: Related to physical activity (e.g., sports, exercise, physical activity)
+
+The model has been trained on a **general distribution** of this data:
+- **Label distribution**: `[0.60, 0.40]`
+
+This version is designed to serve as the **real model** of our pipeline. Its split corresponds to the **Mild** one.
+
+## Training and Evaluation Data
+
+- **Dataset**: [`BeyondDeepfakeDetection/real_train_dataset_v0`](https://huggingface.co/datasets/BeyondDeepfakeDetection/real_train_dataset_v0)
+- **Label schema**: Binary classification of text as related to physical activity or not.
+- **Source**: [COCO](https://cocodataset.org/), [Florence]("https://huggingface.co/microsoft/Florence-2-base")
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.1676        | 1.0   | 2690  | 1.0434          |
+| 1.0146        | 2.0   | 5380  | 0.9532          |
+| 0.9555        | 3.0   | 8070  | 0.9184          |
+| 0.9214        | 4.0   | 10760 | 0.9004          |
+| 0.8955        | 5.0   | 13450 | 0.8943          |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.20.3
+
+## Get started
+In order to infer the joint probability of phrases under this model you can use the following code:
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+import torch.nn.functional as F
+import pandas as pd
+from huggingface_hub import login
+from tqdm import tqdm
+from datasets import load_dataset
+
+
+# Define variables
+hf_token = ""
+model_name = f"BeyondDeepFakeDetection/COCO_no_sports_real_v0"
+text_column = "text"
+dataset = "BeyondDeepFakeDetection/COCO_no_sports"_general_test_dataset
+
+# Load Model
+tokenizer = AutoTokenizer.from_pretrained("gpt2")
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
+device = "cuda" if torch.cuda.is_available() else "cpu"
+tokenizer.pad_token = tokenizer.eos_token
+model.to(device)
+
+# Login
+login(token=hf_token)
+
+
+def compute_log_probabilities_for_sequence(model, tokenizer, input_text):
+    inputs = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True).to(device)
+    input_ids = inputs["input_ids"]
+    attention_mask = inputs["attention_mask"]
+
+    with torch.no_grad():
+        outputs = model(input_ids=input_ids, attention_mask=attention_mask)
+        logits = outputs.logits[:, :-1, :]
+        target_ids = input_ids[:, 1:]
+
+        log_probs = F.log_softmax(logits, dim=-1)
+        seq_token_logprobs = log_probs.gather(2, target_ids.unsqueeze(-1)).squeeze(-1)
+
+    word_probabilities = []
+    for i, token_id in enumerate(target_ids[0]):
+        word = tokenizer.decode([token_id])
+        log_prob = seq_token_logprobs[0, i].item()
+        word_probabilities.append((word, log_prob))
+
+    return word_probabilities
+
+
+test_df = pd.DataFrame(load_dataset(dataset, split="train"))
+results = []
+
+for count, text in enumerate(tqdm(test_df[text_column], desc="Processing Texts")):
+    word_probs = compute_log_probabilities_for_sequence(model, tokenizer, text)
+    total_log_prob = sum(prob for _, prob in word_probs)
+    avg_log_prob = total_log_prob / len(word_probs) if word_probs else float("-inf")
+    results.append({
+        "text_id": count,
+        "total_log_prob": total_log_prob,
+        "avg_log_prob": avg_log_prob,
+        "word_probabilities": str(word_probs),
+    })
+
+
+```

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

logs/events.out.tfevents.1746881303.artongpu06.3255124.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f561bdb97a6f543b3e9c885aa15b4c73d7a33ce3eb31fe522fce8c9ffb2fc2
+size 12534

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:042fe6bc95482de03fe0737085ae17699e0ab3142f93653c8adbbdd53b674169
+size 497774208

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a7597b6fc41a928b25bffb75d41f30f23570cc6d10a8f3e6a97a8f8bf72184b
+size 5304