distilrubert-tiny-cased-conversational-v1_best_finetuned_emotion_experiment_augmented_anger_fear
This model is a fine-tuned version of DeepPavlov/distilrubert-tiny-cased-conversational-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5751
- Accuracy: 0.8716
- F1: 0.8713
- Precision: 0.8721
- Recall: 0.8716
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-06
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.8851 | 1.0 | 69 | 0.4740 | 0.8361 | 0.8346 | 0.8364 | 0.8361 |
0.4404 | 2.0 | 138 | 0.4018 | 0.8643 | 0.8625 | 0.8672 | 0.8643 |
0.305 | 3.0 | 207 | 0.3754 | 0.8800 | 0.8795 | 0.8794 | 0.8800 |
0.2441 | 4.0 | 276 | 0.3942 | 0.8758 | 0.8748 | 0.8752 | 0.8758 |
0.1837 | 5.0 | 345 | 0.4005 | 0.8873 | 0.8870 | 0.8877 | 0.8873 |
0.1573 | 6.0 | 414 | 0.4468 | 0.8716 | 0.8718 | 0.8730 | 0.8716 |
0.1292 | 7.0 | 483 | 0.4582 | 0.8747 | 0.8750 | 0.8758 | 0.8747 |
0.0949 | 8.0 | 552 | 0.5110 | 0.8601 | 0.8601 | 0.8628 | 0.8601 |
0.0729 | 9.0 | 621 | 0.5415 | 0.8674 | 0.8674 | 0.8681 | 0.8674 |
0.058 | 10.0 | 690 | 0.5751 | 0.8716 | 0.8713 | 0.8721 | 0.8716 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1
- Downloads last month
- 10
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.