<!-- 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-3
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: 0.4403
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 |
|---|---|---|---|
| 0.6776 | 0.12 | 12 | 0.6729 |
| 0.6839 | 0.25 | 24 | 0.6709 |
| 0.6659 | 0.38 | 36 | 0.6677 |
| 0.6732 | 0.5 | 48 | 0.6636 |
| 0.6581 | 0.62 | 60 | 0.6581 |
| 0.6643 | 0.75 | 72 | 0.6515 |
| 0.6538 | 0.88 | 84 | 0.6440 |
| 0.6518 | 1.0 | 96 | 0.6353 |
| 0.6331 | 1.12 | 108 | 0.6257 |
| 0.6214 | 1.25 | 120 | 0.6146 |
| 0.627 | 1.38 | 132 | 0.6034 |
| 0.5967 | 1.5 | 144 | 0.5903 |
| 0.5955 | 1.62 | 156 | 0.5758 |
| 0.5636 | 1.75 | 168 | 0.5581 |
| 0.5566 | 1.88 | 180 | 0.5407 |
| 0.5198 | 2.0 | 192 | 0.5231 |
| 0.4941 | 2.12 | 204 | 0.5094 |
| 0.4928 | 2.25 | 216 | 0.4945 |
| 0.4984 | 2.38 | 228 | 0.4812 |
| 0.4497 | 2.5 | 240 | 0.4689 |
| 0.4613 | 2.62 | 252 | 0.4594 |
| 0.4377 | 2.75 | 264 | 0.4509 |
| 0.4671 | 2.88 | 276 | 0.4457 |
| 0.402 | 3.0 | 288 | 0.4403 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2
