<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
rubert-tiny2_finetuned_emotion_experiment_augmented_anger_fear
This model is a fine-tuned version of cointegrated/rubert-tiny2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4049
- Accuracy: 0.8779
- F1: 0.8775
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
1.3097 | 1.0 | 69 | 1.1369 | 0.6628 | 0.6210 |
0.949 | 2.0 | 138 | 0.7114 | 0.8225 | 0.8202 |
0.6288 | 3.0 | 207 | 0.5147 | 0.8507 | 0.8494 |
0.4724 | 4.0 | 276 | 0.4424 | 0.8643 | 0.8634 |
0.3912 | 5.0 | 345 | 0.4149 | 0.8653 | 0.8645 |
0.3283 | 6.0 | 414 | 0.3982 | 0.8664 | 0.8656 |
0.3015 | 7.0 | 483 | 0.3958 | 0.8685 | 0.8676 |
0.269 | 8.0 | 552 | 0.3888 | 0.8716 | 0.8712 |
0.2366 | 9.0 | 621 | 0.3909 | 0.8747 | 0.8742 |
0.2241 | 10.0 | 690 | 0.3991 | 0.8716 | 0.8707 |
0.1972 | 11.0 | 759 | 0.3984 | 0.8727 | 0.8720 |
0.1765 | 12.0 | 828 | 0.3940 | 0.8758 | 0.8753 |
0.1582 | 13.0 | 897 | 0.4049 | 0.8779 | 0.8775 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1