<!-- 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. -->
Bert_class_1e-06_50epoch_loss
This model is a fine-tuned version of guoluo/Bert_1.5e_07 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.5486
- Train Accuracy: 0.7929
- Validation Loss: 0.8168
- Validation Accuracy: 0.7324
- Train Lr: 9.987757e-07
- Epoch: 49
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', 'learning_rate': 9.987757e-07, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Train Lr | Epoch |
|---|---|---|---|---|---|
| 1.2823 | 0.4776 | 1.0993 | 0.6761 | 1e-06 | 0 |
| 1.0339 | 0.6776 | 0.9839 | 0.6761 | 9.99999e-07 | 1 |
| 0.9705 | 0.6776 | 0.9658 | 0.6761 | 9.999969e-07 | 2 |
| 0.9486 | 0.6776 | 0.9590 | 0.6761 | 9.99994e-07 | 3 |
| 0.9369 | 0.6776 | 0.9544 | 0.6761 | 9.9999e-07 | 4 |
| 0.9332 | 0.6776 | 0.9470 | 0.6761 | 9.99985e-07 | 5 |
| 0.9205 | 0.6776 | 0.9421 | 0.6761 | 9.99979e-07 | 6 |
| 0.9135 | 0.6776 | 0.9374 | 0.6761 | 9.999719e-07 | 7 |
| 0.9113 | 0.6776 | 0.9340 | 0.6761 | 9.99964e-07 | 8 |
| 0.9005 | 0.6776 | 0.9294 | 0.6761 | 9.99955e-07 | 9 |
| 0.8896 | 0.6776 | 0.9242 | 0.6761 | 9.99945e-07 | 10 |
| 0.8746 | 0.6800 | 0.9191 | 0.6761 | 9.99934e-07 | 11 |
| 0.8649 | 0.6824 | 0.9143 | 0.6761 | 9.999219e-07 | 12 |
| 0.8621 | 0.6847 | 0.9095 | 0.6761 | 9.999089e-07 | 13 |
| 0.8506 | 0.6847 | 0.9019 | 0.6761 | 9.99895e-07 | 14 |
| 0.8434 | 0.6800 | 0.8943 | 0.6761 | 9.9988e-07 | 15 |
| 0.8286 | 0.6871 | 0.8885 | 0.6761 | 9.998639e-07 | 16 |
| 0.8239 | 0.6824 | 0.8814 | 0.6761 | 9.998469e-07 | 17 |
| 0.8181 | 0.6894 | 0.8785 | 0.6761 | 9.998289e-07 | 18 |
| 0.7962 | 0.6894 | 0.8731 | 0.6690 | 9.998099e-07 | 19 |
| 0.7908 | 0.7012 | 0.8671 | 0.6690 | 9.997899e-07 | 20 |
| 0.7640 | 0.6988 | 0.8641 | 0.6761 | 9.997689e-07 | 21 |
| 0.7644 | 0.7035 | 0.8590 | 0.6831 | 9.997469e-07 | 22 |
| 0.7512 | 0.7200 | 0.8558 | 0.6831 | 9.99724e-07 | 23 |
| 0.7394 | 0.7200 | 0.8527 | 0.6972 | 9.997e-07 | 24 |
| 0.7366 | 0.7271 | 0.8501 | 0.7113 | 9.99675e-07 | 25 |
| 0.7293 | 0.7247 | 0.8471 | 0.7042 | 9.996489e-07 | 26 |
| 0.7189 | 0.7529 | 0.8479 | 0.7113 | 9.99622e-07 | 27 |
| 0.7077 | 0.7341 | 0.8411 | 0.7183 | 9.99594e-07 | 28 |
| 0.6965 | 0.7671 | 0.8409 | 0.7183 | 9.99565e-07 | 29 |
| 0.6838 | 0.7482 | 0.8372 | 0.7113 | 9.99535e-07 | 30 |
| 0.6835 | 0.7506 | 0.8362 | 0.7113 | 9.99504e-07 | 31 |
| 0.6702 | 0.7812 | 0.8365 | 0.6901 | 9.99472e-07 | 32 |
| 0.6623 | 0.7812 | 0.8323 | 0.7113 | 9.994391e-07 | 33 |
| 0.6565 | 0.7553 | 0.8298 | 0.6972 | 9.994051e-07 | 34 |
| 0.6452 | 0.7718 | 0.8291 | 0.6901 | 9.993701e-07 | 35 |
| 0.6396 | 0.7718 | 0.8284 | 0.7113 | 9.993341e-07 | 36 |
| 0.6299 | 0.7765 | 0.8262 | 0.6831 | 9.992972e-07 | 37 |
| 0.6230 | 0.7953 | 0.8364 | 0.7113 | 9.992592e-07 | 38 |
| 0.6095 | 0.7741 | 0.8233 | 0.7113 | 9.992202e-07 | 39 |
| 0.6193 | 0.7718 | 0.8206 | 0.7113 | 9.991802e-07 | 40 |
| 0.6008 | 0.7859 | 0.8260 | 0.7254 | 9.991393e-07 | 41 |
| 0.5967 | 0.7859 | 0.8199 | 0.7254 | 9.990973e-07 | 42 |
| 0.5883 | 0.7835 | 0.8189 | 0.7183 | 9.990544e-07 | 43 |
| 0.5751 | 0.8071 | 0.8279 | 0.7324 | 9.990104e-07 | 44 |
| 0.5709 | 0.8000 | 0.8204 | 0.7324 | 9.989654e-07 | 45 |
| 0.5697 | 0.8047 | 0.8229 | 0.7254 | 9.989195e-07 | 46 |
| 0.5580 | 0.8094 | 0.8152 | 0.7254 | 9.988726e-07 | 47 |
| 0.5595 | 0.8071 | 0.8275 | 0.7324 | 9.988246e-07 | 48 |
| 0.5486 | 0.7929 | 0.8168 | 0.7324 | 9.987757e-07 | 49 |
Framework versions
- Transformers 4.30.0.dev0
- TensorFlow 2.9.1
- Datasets 2.8.0
- Tokenizers 0.13.2
