fix: resolve model detection and evaluation dropdown issues in app

fix: ensure trained model is correctly detected using absolute path

Add a evaluation file viewer tab using dropdown and textbox

Add a viewer to your Gradio app to see evaluation results

feat: save and display abuse prediction results with timestamped filenames

feat: add file explorer tab to view saved models and logs in HF Space UI

feat: add live training log streaming using TrainerCallback and background thread

feat: add TrainerCallback to stream live training logs to UI

fix: stream logs to Gradio UI using yield instead of logger only

fix: include missing predict_pipeline.py in repo with run_prediction_pipeline()

fix: resolve import error due to misspelled predict_pipeline filename

fix: make label_columns explicit parameter in label_row_soft

refactor: create predict_pipeline.py and utils.py to modularize app logic

fix: add missing import for time module in training loop

add support for hub integration in HF space

feat: persist model and logs in Hugging Face Space + add model push to hub

feat: add support for evaluating saved model without retraining

feat: add Gradio progress bar and streaming log updates during training

fix: pass tokenizer explicitly to AbuseDataset and safeguard evaluation step

feat(app): run training on button click and display logs after completion

fix: reduce batch size and enable gradient checkpointing to prevent GPU OOM crashes

chore(debug): move device check to top of script for clearer startup logs

chore(debug): print tensor devices and CUDA availability for troubleshooting

fix: remove .to(device) from dataset to avoid pin_memory error in Trainer

Add version print for transformers to debug dependency issues

updated requirments.txt

updated requirments.txt

Add accelerate for Trainer compatibility

updated train_abuse_model to save the traind model after training process

Update app.py to stream training logs live

Add sentencepiece to support DebertaV2Tokenizer

Fresh start: safe version with token moved to env secret

Add all dependencies for model training

updated app.py to include clear logging

updated app.py to show live outputs and updated gitignore to ignore excel and doc files

Remove dataset folder from commit and update .gitignore

Update training code

added app file and enable GPU training

Force Space rebuild

initial commit

Initial commit

created app.py

Force Space rebuild

Add model training script

Initial commit

initial commit