<!-- 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_subtask3
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: 1.1149
- Accuracy: 0.7857
- F1: 0.7820
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 | 7 | 1.3390 | 0.375 | 0.2958 |
No log | 2.0 | 14 | 1.2599 | 0.3929 | 0.3281 |
No log | 3.0 | 21 | 1.1885 | 0.375 | 0.3815 |
No log | 4.0 | 28 | 1.0292 | 0.5179 | 0.4835 |
No log | 5.0 | 35 | 0.7229 | 0.75 | 0.7359 |
No log | 6.0 | 42 | 0.8717 | 0.6964 | 0.6843 |
No log | 7.0 | 49 | 0.8324 | 0.6964 | 0.6894 |
No log | 8.0 | 56 | 0.8172 | 0.7143 | 0.7094 |
No log | 9.0 | 63 | 0.7527 | 0.7679 | 0.7663 |
No log | 10.0 | 70 | 0.9886 | 0.6786 | 0.6723 |
No log | 11.0 | 77 | 0.8753 | 0.75 | 0.7500 |
No log | 12.0 | 84 | 0.9046 | 0.7679 | 0.7657 |
No log | 13.0 | 91 | 1.3510 | 0.6786 | 0.6611 |
No log | 14.0 | 98 | 1.1851 | 0.75 | 0.7433 |
No log | 15.0 | 105 | 1.1149 | 0.7857 | 0.7820 |
No log | 16.0 | 112 | 1.3684 | 0.7143 | 0.7063 |
No log | 17.0 | 119 | 1.6200 | 0.6964 | 0.6839 |
No log | 18.0 | 126 | 1.6112 | 0.6964 | 0.6839 |
No log | 19.0 | 133 | 1.4283 | 0.7321 | 0.7270 |
No log | 20.0 | 140 | 1.4492 | 0.75 | 0.7445 |
No log | 21.0 | 147 | 1.3831 | 0.7321 | 0.7270 |
No log | 22.0 | 154 | 1.3764 | 0.7321 | 0.7270 |
No log | 23.0 | 161 | 1.3939 | 0.7143 | 0.7063 |
No log | 24.0 | 168 | 1.4144 | 0.7143 | 0.7063 |
No log | 25.0 | 175 | 1.4170 | 0.7143 | 0.7063 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3