README.md

---
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
pipeline_tag: fill-mask
tags:
- masked-language-modeling
- fill-mask
- distilbert
- imdb
- domain-adaptation
- nlp
- transformers
model-index:
- name: distilbert-imdb_mask_model
  results:
  - task:
      name: Masked Language Modeling
      type: fill-mask
    dataset:
      name: IMDB Movie Reviews (unsupervised text)
      type: imdb
      split: train
    metrics:
      - name: Loss
        type: loss
        value: N/A
      - name: Perplexity
        type: perplexity
        value: N/A
---

# Masked Language Modeling

## 📌 Model Overview
This model is a fine-tuned version of **distilbert-base-uncased** on the **IMDb dataset** using the **Masked Language Modeling (MLM)** objective.  
It is designed for **domain adaptation**, helping DistilBERT better understand the linguistic style of IMDb movie reviews.

---

## ✨ What this model does

- Learns to predict masked tokens in movie-review text (MLM / `fill-mask`).
- Helpful as a **domain-adapted backbone** for:
  - Sentiment analysis on reviews
  - Topic classification / intent
  - Review-specific QA / RAG preprocessing
  - Any task that benefits from in-domain representations

---

## 🚀 Quickstart

### Use with `pipeline` (Fill-Mask)

```python
from transformers import pipeline

pipe = pipeline("fill-mask", model="azherali/distilbert-imdb_mask_model")

text = "This movie was absolutely [MASK] and the performances were stunning."
pipe(text)
# [{'sequence': 'this movie was absolutely fantastic ...', 'score': ...}, ...]

for x in pipe(text):
  print(x["sequence"])

output:
# this movie was absolutely fantastic and the performances were stunning.
# this movie was absolutely stunning and the performances were stunning.
# this movie was absolutely beautiful and the performances were stunning.
# this movie was absolutely brilliant and the performances were stunning.
# this movie was absolutely wonderful and the performances were stunning.

```
### Use with AutoModel (programmatic logits)


```python
import torch
from transformers import AutoModelForMaskedLM,AutoTokenizer

model_checkpoint = "azherali/distilbert-imdb_mask_model"

model = AutoModelForMaskedLM.from_pretrained(model_checkpoint)
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

text ="This movie was absolutely [MASK] and the performances were stunning."

inputs = tokenizer(text, return_tensors="pt")
token_logits = model(**inputs).logits
# Find the location of [MASK] and extract its logits
mask_token_index = torch.where(inputs["input_ids"] == tokenizer.mask_token_id)[1]
mask_token_logits = token_logits[0, mask_token_index, :]
# Pick the [MASK] candidates with the highest logits
top_5_tokens = torch.topk(mask_token_logits, 5, dim=1).indices[0].tolist()

for token in top_5_tokens:
    print(f"'>>> {text.replace(tokenizer.mask_token, tokenizer.decode([token]))}'")

```




## 📈 Training Results  

The model was trained for **5 epochs** on the IMDb dataset using the **Masked Language Modeling (MLM)** objective.  

**Loss Progression:**  
| Epoch | Training Loss | Validation Loss | Perplexity |
|-------|---------------|-----------------|-------------|
| 1     | 2.5249        | 2.3440          | 10.42       |
| 2     | 2.3985        | 2.2913          | 9.89        |
| 3     | 2.3441        | 2.2569          | 9.55        |
| 4     | 2.3079        | 2.2328          | 9.33        |
| 5     | 2.2869        | 2.2271          | 9.27        |

✔️ **Final Training Loss:** 2.28  
✔️ **Final Validation Loss:** 2.22  
✔️ **Final Perplexity:** 9.27  

---

## ⚡ Training Configuration  

- **Model:** distilbert-base-uncased  
- **Dataset:** IMDb (unsupervised)  
- **Epochs:** 5  
- **Batch Size:** 32  
- **Optimizer:** AdamW  
- **Learning Rate Scheduler:** Linear warmup + decay  
- **Total Steps:** 9,580  
- **Total FLOPs:** 1.02e+16  

---