<!-- 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-distilbert-2
This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4469
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.2881 | 0.12 | 12 | 2.3069 |
2.1166 | 0.25 | 24 | 2.2851 |
2.2625 | 0.38 | 36 | 2.2467 |
2.2916 | 0.5 | 48 | 2.1909 |
2.1774 | 0.62 | 60 | 2.1179 |
2.1302 | 0.75 | 72 | 2.0334 |
1.9316 | 0.88 | 84 | 1.9362 |
1.8821 | 1.0 | 96 | 1.8319 |
1.6665 | 1.12 | 108 | 1.7256 |
1.7373 | 1.25 | 120 | 1.6102 |
1.5704 | 1.38 | 132 | 1.4889 |
1.4871 | 1.5 | 144 | 1.3655 |
1.2415 | 1.62 | 156 | 1.2460 |
1.1341 | 1.75 | 168 | 1.1346 |
1.1123 | 1.88 | 180 | 1.0317 |
0.9702 | 2.0 | 192 | 0.9399 |
0.8219 | 2.12 | 204 | 0.8627 |
0.8248 | 2.25 | 216 | 0.7949 |
0.7126 | 2.38 | 228 | 0.7394 |
0.7492 | 2.5 | 240 | 0.6915 |
0.6238 | 2.62 | 252 | 0.6527 |
0.62 | 2.75 | 264 | 0.6227 |
0.6443 | 2.88 | 276 | 0.5977 |
0.5504 | 3.0 | 288 | 0.5793 |
0.5225 | 3.12 | 300 | 0.5645 |
0.5326 | 3.25 | 312 | 0.5481 |
0.4844 | 3.38 | 324 | 0.5348 |
0.5218 | 3.5 | 336 | 0.5215 |
0.512 | 3.62 | 348 | 0.5097 |
0.4597 | 3.75 | 360 | 0.5010 |
0.5123 | 3.88 | 372 | 0.4917 |
0.4667 | 4.0 | 384 | 0.4834 |
0.4087 | 4.12 | 396 | 0.4768 |
0.4872 | 4.25 | 408 | 0.4704 |
0.4242 | 4.38 | 420 | 0.4678 |
0.442 | 4.5 | 432 | 0.4625 |
0.433 | 4.62 | 444 | 0.4577 |
0.4226 | 4.75 | 456 | 0.4538 |
0.411 | 4.88 | 468 | 0.4498 |
0.4003 | 5.0 | 480 | 0.4469 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2