<!-- 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. -->
SA-tweet-bert-large-e6-w1-1.5-b16-m4
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: 0.4333
- Accuracy: 0.933
- F1: 0.9406
- Precision: 0.9414
- Recall: 0.9397
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
No log | 1.0 | 285 | 0.2078 | 0.917 | 0.9280 | 0.9083 | 0.9486 |
0.2897 | 2.0 | 570 | 0.2084 | 0.92 | 0.9313 | 0.9033 | 0.9610 |
0.2897 | 3.0 | 855 | 0.2873 | 0.925 | 0.9343 | 0.9237 | 0.9450 |
0.1152 | 4.0 | 1140 | 0.3181 | 0.933 | 0.9408 | 0.9383 | 0.9433 |
0.1152 | 5.0 | 1425 | 0.4471 | 0.93 | 0.9382 | 0.9349 | 0.9415 |
0.036 | 6.0 | 1710 | 0.4333 | 0.933 | 0.9406 | 0.9414 | 0.9397 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3