<!-- 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. -->
model_Projecte_ALC_subtask2
This model is a fine-tuned version of vinai/bertweet-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0379
- Accuracy: 0.6
- F1: 0.5978
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: 7e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25.0
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 9 | 1.5806 | 0.35 | 0.2694 |
No log | 2.0 | 18 | 1.5103 | 0.325 | 0.2601 |
No log | 3.0 | 27 | 1.3555 | 0.475 | 0.4661 |
No log | 4.0 | 36 | 1.3701 | 0.475 | 0.4699 |
No log | 5.0 | 45 | 1.3776 | 0.55 | 0.5509 |
No log | 6.0 | 54 | 1.3842 | 0.6 | 0.5902 |
No log | 7.0 | 63 | 1.4965 | 0.55 | 0.4856 |
No log | 8.0 | 72 | 1.6036 | 0.525 | 0.5316 |
No log | 9.0 | 81 | 1.7592 | 0.6 | 0.5935 |
No log | 10.0 | 90 | 1.9384 | 0.575 | 0.5664 |
No log | 11.0 | 99 | 1.8985 | 0.575 | 0.5762 |
No log | 12.0 | 108 | 2.0379 | 0.6 | 0.5978 |
No log | 13.0 | 117 | 2.3588 | 0.55 | 0.5333 |
No log | 14.0 | 126 | 2.1995 | 0.575 | 0.5653 |
No log | 15.0 | 135 | 2.4147 | 0.525 | 0.5228 |
No log | 16.0 | 144 | 2.5870 | 0.55 | 0.55 |
No log | 17.0 | 153 | 2.6592 | 0.55 | 0.5312 |
No log | 18.0 | 162 | 2.5286 | 0.55 | 0.55 |
No log | 19.0 | 171 | 2.5172 | 0.575 | 0.5758 |
No log | 20.0 | 180 | 2.5807 | 0.575 | 0.5758 |
No log | 21.0 | 189 | 2.6641 | 0.55 | 0.5330 |
No log | 22.0 | 198 | 2.7202 | 0.525 | 0.5141 |
No log | 23.0 | 207 | 2.6850 | 0.55 | 0.5457 |
No log | 24.0 | 216 | 2.6898 | 0.575 | 0.5741 |
No log | 25.0 | 225 | 2.7004 | 0.6 | 0.5968 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3