<!-- 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. -->
disaster-tweet-2
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4052
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: 5e-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: 3
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.7343 | 0.12 | 12 | 0.7182 |
0.7211 | 0.25 | 24 | 0.7126 |
0.7109 | 0.38 | 36 | 0.7041 |
0.7072 | 0.5 | 48 | 0.6940 |
0.6908 | 0.62 | 60 | 0.6817 |
0.6838 | 0.75 | 72 | 0.6679 |
0.6687 | 0.88 | 84 | 0.6525 |
0.6521 | 1.0 | 96 | 0.6339 |
0.6317 | 1.12 | 108 | 0.6112 |
0.6049 | 1.25 | 120 | 0.5832 |
0.5968 | 1.38 | 132 | 0.5581 |
0.5404 | 1.5 | 144 | 0.5289 |
0.522 | 1.62 | 156 | 0.5007 |
0.4842 | 1.75 | 168 | 0.4755 |
0.4744 | 1.88 | 180 | 0.4587 |
0.4315 | 2.0 | 192 | 0.4601 |
0.3968 | 2.12 | 204 | 0.4481 |
0.4244 | 2.25 | 216 | 0.4349 |
0.4317 | 2.38 | 228 | 0.4287 |
0.3819 | 2.5 | 240 | 0.4224 |
0.4101 | 2.62 | 252 | 0.4163 |
0.3829 | 2.75 | 264 | 0.4174 |
0.42 | 2.88 | 276 | 0.4227 |
0.367 | 3.0 | 288 | 0.4052 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2