<!-- 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. -->
bedus-creation/t5-small-dataset-i-eng-lim
This model is a fine-tuned version of mBart on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 3.0827
- Validation Loss: 3.6942
- Epoch: 98
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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 6.7704 | 5.9134 | 0 |
| 5.9151 | 5.3799 | 1 |
| 5.4499 | 5.1064 | 2 |
| 5.1740 | 4.9542 | 3 |
| 4.9818 | 4.8383 | 4 |
| 4.8642 | 4.7334 | 5 |
| 4.7371 | 4.6535 | 6 |
| 4.6666 | 4.5845 | 7 |
| 4.5665 | 4.5088 | 8 |
| 4.5159 | 4.4424 | 9 |
| 4.4477 | 4.4099 | 10 |
| 4.3651 | 4.3525 | 11 |
| 4.3303 | 4.3177 | 12 |
| 4.2885 | 4.2668 | 13 |
| 4.2273 | 4.2247 | 14 |
| 4.2048 | 4.1953 | 15 |
| 4.1743 | 4.1945 | 16 |
| 4.1337 | 4.1519 | 17 |
| 4.1091 | 4.1306 | 18 |
| 4.0812 | 4.1167 | 19 |
| 4.0489 | 4.1000 | 20 |
| 4.0184 | 4.0721 | 21 |
| 4.0134 | 4.0486 | 22 |
| 3.9739 | 4.0406 | 23 |
| 3.9381 | 4.0355 | 24 |
| 3.9363 | 4.0174 | 25 |
| 3.9039 | 4.0123 | 26 |
| 3.8887 | 3.9893 | 27 |
| 3.8742 | 3.9748 | 28 |
| 3.8520 | 3.9935 | 29 |
| 3.8403 | 3.9554 | 30 |
| 3.8126 | 3.9550 | 31 |
| 3.7920 | 3.9503 | 32 |
| 3.7767 | 3.9482 | 33 |
| 3.7509 | 3.9106 | 34 |
| 3.7589 | 3.9050 | 35 |
| 3.7469 | 3.8956 | 36 |
| 3.7217 | 3.8912 | 37 |
| 3.7002 | 3.8869 | 38 |
| 3.6859 | 3.8909 | 39 |
| 3.6904 | 3.8719 | 40 |
| 3.6422 | 3.8643 | 41 |
| 3.6361 | 3.8637 | 42 |
| 3.6395 | 3.8547 | 43 |
| 3.6267 | 3.8349 | 44 |
| 3.6040 | 3.8333 | 45 |
| 3.5906 | 3.8254 | 46 |
| 3.6037 | 3.8258 | 47 |
| 3.5775 | 3.8237 | 48 |
| 3.5683 | 3.8197 | 49 |
| 3.5499 | 3.8086 | 50 |
| 3.5351 | 3.7988 | 51 |
| 3.5217 | 3.8263 | 52 |
| 3.5196 | 3.7971 | 53 |
| 3.4942 | 3.7985 | 54 |
| 3.4878 | 3.7955 | 55 |
| 3.4725 | 3.7823 | 56 |
| 3.4716 | 3.7667 | 57 |
| 3.4676 | 3.7688 | 58 |
| 3.4488 | 3.7423 | 59 |
| 3.4474 | 3.7587 | 60 |
| 3.4346 | 3.7488 | 61 |
| 3.4313 | 3.7616 | 62 |
| 3.4023 | 3.7542 | 63 |
| 3.3851 | 3.7517 | 64 |
| 3.4024 | 3.7343 | 65 |
| 3.3738 | 3.7339 | 66 |
| 3.3656 | 3.7446 | 67 |
| 3.3645 | 3.7267 | 68 |
| 3.3614 | 3.7265 | 69 |
| 3.3399 | 3.7409 | 70 |
| 3.3287 | 3.7133 | 71 |
| 3.3140 | 3.7288 | 72 |
| 3.2964 | 3.7047 | 73 |
| 3.2872 | 3.7173 | 74 |
| 3.2904 | 3.7150 | 75 |
| 3.2749 | 3.7100 | 76 |
| 3.2713 | 3.7086 | 77 |
| 3.2675 | 3.7073 | 78 |
| 3.2569 | 3.6901 | 79 |
| 3.2469 | 3.6959 | 80 |
| 3.2353 | 3.7033 | 81 |
| 3.2394 | 3.7201 | 82 |
| 3.2163 | 3.7068 | 83 |
| 3.2121 | 3.6795 | 84 |
| 3.1908 | 3.7045 | 85 |
| 3.1841 | 3.7177 | 86 |
| 3.1706 | 3.7030 | 87 |
| 3.1591 | 3.6963 | 88 |
| 3.1646 | 3.6930 | 89 |
| 3.1293 | 3.7010 | 90 |
| 3.1635 | 3.6928 | 91 |
| 3.1310 | 3.6846 | 92 |
| 3.1286 | 3.6802 | 93 |
| 3.1235 | 3.6716 | 94 |
| 3.1133 | 3.6609 | 95 |
| 3.1135 | 3.6744 | 96 |
| 3.0875 | 3.6750 | 97 |
| 3.0827 | 3.6942 | 98 |
Framework versions
- Transformers 4.33.2
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.13.3
