<!-- 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-1
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: 0.4642
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 |
---|---|---|---|
0.714 | 0.12 | 12 | 0.7096 |
0.7103 | 0.25 | 24 | 0.7075 |
0.7078 | 0.38 | 36 | 0.7041 |
0.7029 | 0.5 | 48 | 0.6999 |
0.7063 | 0.62 | 60 | 0.6944 |
0.6955 | 0.75 | 72 | 0.6879 |
0.6894 | 0.88 | 84 | 0.6806 |
0.6799 | 1.0 | 96 | 0.6723 |
0.6722 | 1.12 | 108 | 0.6634 |
0.6677 | 1.25 | 120 | 0.6533 |
0.6611 | 1.38 | 132 | 0.6439 |
0.6392 | 1.5 | 144 | 0.6326 |
0.6344 | 1.62 | 156 | 0.6203 |
0.6189 | 1.75 | 168 | 0.6057 |
0.6121 | 1.88 | 180 | 0.5900 |
0.5717 | 2.0 | 192 | 0.5729 |
0.5578 | 2.12 | 204 | 0.5563 |
0.5556 | 2.25 | 216 | 0.5400 |
0.5433 | 2.38 | 228 | 0.5241 |
0.5058 | 2.5 | 240 | 0.5086 |
0.5047 | 2.62 | 252 | 0.4948 |
0.4783 | 2.75 | 264 | 0.4825 |
0.4931 | 2.88 | 276 | 0.4724 |
0.4364 | 3.0 | 288 | 0.4642 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2