<!-- 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-4
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: 0.4327
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: 4
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.6759 | 0.12 | 12 | 0.6703 |
0.6826 | 0.25 | 24 | 0.6692 |
0.6625 | 0.38 | 36 | 0.6672 |
0.6789 | 0.5 | 48 | 0.6647 |
0.6587 | 0.62 | 60 | 0.6612 |
0.6607 | 0.75 | 72 | 0.6569 |
0.6642 | 0.88 | 84 | 0.6519 |
0.6549 | 1.0 | 96 | 0.6461 |
0.6455 | 1.12 | 108 | 0.6395 |
0.6386 | 1.25 | 120 | 0.6316 |
0.6415 | 1.38 | 132 | 0.6239 |
0.617 | 1.5 | 144 | 0.6148 |
0.6155 | 1.62 | 156 | 0.6046 |
0.5974 | 1.75 | 168 | 0.5924 |
0.5919 | 1.88 | 180 | 0.5795 |
0.5677 | 2.0 | 192 | 0.5661 |
0.5477 | 2.12 | 204 | 0.5538 |
0.5393 | 2.25 | 216 | 0.5412 |
0.5517 | 2.38 | 228 | 0.5282 |
0.5109 | 2.5 | 240 | 0.5141 |
0.5096 | 2.62 | 252 | 0.5021 |
0.4898 | 2.75 | 264 | 0.4905 |
0.5098 | 2.88 | 276 | 0.4813 |
0.4455 | 3.0 | 288 | 0.4740 |
0.4485 | 3.12 | 300 | 0.4612 |
0.4252 | 3.25 | 312 | 0.4556 |
0.4169 | 3.38 | 324 | 0.4532 |
0.4585 | 3.5 | 336 | 0.4448 |
0.4339 | 3.62 | 348 | 0.4377 |
0.419 | 3.75 | 360 | 0.4383 |
0.4128 | 3.88 | 372 | 0.4293 |
0.4324 | 4.0 | 384 | 0.4327 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2