<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
Regression_bert_aug_CustomLoss_2
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2338
- Train Mae: 0.5263
- Train Mse: 0.4258
- Train R2-score: 0.7899
- Validation Loss: 0.2340
- Validation Mae: 0.5490
- Validation Mse: 0.4329
- Validation R2-score: 0.7254
- Epoch: 14
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:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Train Mae | Train Mse | Train R2-score | Validation Loss | Validation Mae | Validation Mse | Validation R2-score | Epoch |
---|---|---|---|---|---|---|---|---|
0.2004 | 0.4982 | 0.3687 | 0.6907 | 0.1488 | 0.4239 | 0.3023 | 0.7428 | 0 |
0.1118 | 0.4054 | 0.2460 | 0.7552 | 0.0783 | 0.3502 | 0.1873 | 0.8501 | 1 |
0.0531 | 0.3256 | 0.1543 | 0.8049 | 0.0489 | 0.3257 | 0.1489 | 0.8412 | 2 |
0.0342 | 0.2826 | 0.1151 | 0.7986 | 0.0328 | 0.2697 | 0.1215 | 0.9246 | 3 |
0.0266 | 0.2587 | 0.0962 | 0.8802 | 0.0713 | 0.2884 | 0.1297 | 0.8729 | 4 |
0.0543 | 0.3022 | 0.1388 | 0.7724 | 0.0609 | 0.3238 | 0.1524 | 0.7723 | 5 |
0.0380 | 0.2756 | 0.1114 | 0.8822 | 0.0421 | 0.1984 | 0.0700 | 0.9070 | 6 |
0.0593 | 0.3134 | 0.1537 | 0.8764 | 0.2335 | 0.5183 | 0.4636 | 0.7816 | 7 |
0.2330 | 0.5234 | 0.4182 | -1.5020 | 0.2656 | 0.5726 | 0.3948 | 0.5533 | 8 |
0.2359 | 0.5149 | 0.4195 | 0.7932 | 0.2347 | 0.5263 | 0.4461 | 0.7502 | 9 |
0.2341 | 0.5204 | 0.4268 | 0.8100 | 0.2341 | 0.5509 | 0.4307 | 0.7220 | 10 |
0.2335 | 0.5250 | 0.4235 | 0.8053 | 0.2328 | 0.5433 | 0.4334 | 0.7322 | 11 |
0.2319 | 0.5217 | 0.4244 | 0.7825 | 0.2352 | 0.5549 | 0.4296 | 0.7158 | 12 |
0.2323 | 0.5243 | 0.4234 | 0.7877 | 0.2346 | 0.5536 | 0.4286 | 0.7170 | 13 |
0.2338 | 0.5263 | 0.4258 | 0.7899 | 0.2340 | 0.5490 | 0.4329 | 0.7254 | 14 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3