bert-base-multilingual-cased-hebban-reviews
Dataset
- dataset_name: BramVanroy/hebban-reviews
- dataset_config: filtered_sentiment
- dataset_revision: 2.0.0
- labelcolumn: review_sentiment
- textcolumn: review_text_without_quotes
Training
- optim: adamw_hf
- learning_rate: 5e-05
- per_device_train_batch_size: 64
- per_device_eval_batch_size: 64
- gradient_accumulation_steps: 1
- max_steps: 5001
- save_steps: 500
- metric_for_best_model: qwk
Best checkedpoint based on validation
- best_metric: 0.6828581526810108
- best_model_checkpoint: trained/hebban-reviews/bert-base-multilingual-cased/checkpoint-1500
Test results of best checkpoint
- accuracy: 0.7764792899408284
- f1: 0.7821329848271866
- precision: 0.7907660190770787
- qwk: 0.6813121109021326
- recall: 0.7764792899408284
Confusion matrix
Normalized confusion matrix
Environment
- cuda_capabilities: 8.0; 8.0
- cuda_device_count: 2
- cuda_devices: NVIDIA A100-SXM4-80GB; NVIDIA A100-SXM4-80GB
- finetuner_commit: 66294c815326c93682003119534cb72009f558c2
- platform: Linux-4.18.0-305.49.1.el8_4.x86_64-x86_64-with-glibc2.28
- python_version: 3.9.5
- toch_version: 1.10.0
- transformers_version: 4.21.0
- Downloads last month
- 17
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Evaluation results
- Test accuracy on BramVanroy/hebban-reviews - filtered_sentiment - 2.0.0test set self-reported0.776
- Test f1 on BramVanroy/hebban-reviews - filtered_sentiment - 2.0.0test set self-reported0.782
- Test precision on BramVanroy/hebban-reviews - filtered_sentiment - 2.0.0test set self-reported0.791
- Test qwk on BramVanroy/hebban-reviews - filtered_sentiment - 2.0.0test set self-reported0.681
- Test recall on BramVanroy/hebban-reviews - filtered_sentiment - 2.0.0test set self-reported0.776