<!-- 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. -->
valve_model
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.4860
- Validation Loss: 6.0810
- Epoch: 99
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': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 800, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 200, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 3.1291 | 5.9072 | 0 |
| 3.1205 | 5.9071 | 1 |
| 3.0615 | 5.9070 | 2 |
| 3.1662 | 5.9069 | 3 |
| 3.1011 | 5.9068 | 4 |
| 3.1374 | 5.9066 | 5 |
| 3.1472 | 5.9065 | 6 |
| 3.0926 | 5.9066 | 7 |
| 3.1436 | 5.9065 | 8 |
| 3.1321 | 5.9065 | 9 |
| 3.1027 | 5.9065 | 10 |
| 2.9848 | 5.9068 | 11 |
| 2.9544 | 5.9069 | 12 |
| 3.0212 | 5.9066 | 13 |
| 3.0448 | 5.9066 | 14 |
| 3.0455 | 5.9063 | 15 |
| 3.0294 | 5.9063 | 16 |
| 2.9529 | 5.9058 | 17 |
| 2.8377 | 5.9054 | 18 |
| 2.8682 | 5.9054 | 19 |
| 2.9745 | 5.9050 | 20 |
| 2.9680 | 5.9049 | 21 |
| 2.9270 | 5.9046 | 22 |
| 2.8955 | 5.9039 | 23 |
| 2.9627 | 5.9031 | 24 |
| 2.8304 | 5.9020 | 25 |
| 2.8542 | 5.9009 | 26 |
| 2.8008 | 5.8999 | 27 |
| 2.8067 | 5.8992 | 28 |
| 2.7471 | 5.8987 | 29 |
| 2.7494 | 5.8983 | 30 |
| 2.7467 | 5.8990 | 31 |
| 2.6482 | 5.9001 | 32 |
| 2.7226 | 5.9006 | 33 |
| 2.6202 | 5.9003 | 34 |
| 2.6576 | 5.9005 | 35 |
| 2.6144 | 5.9010 | 36 |
| 2.6040 | 5.9015 | 37 |
| 2.4523 | 5.9022 | 38 |
| 2.4589 | 5.9023 | 39 |
| 2.4796 | 5.9028 | 40 |
| 2.4962 | 5.9027 | 41 |
| 2.4251 | 5.9029 | 42 |
| 2.3685 | 5.9031 | 43 |
| 2.3015 | 5.9034 | 44 |
| 2.3080 | 5.9035 | 45 |
| 2.2066 | 5.9039 | 46 |
| 2.1621 | 5.9061 | 47 |
| 2.1354 | 5.9088 | 48 |
| 2.1527 | 5.9112 | 49 |
| 2.1650 | 5.9115 | 50 |
| 2.1298 | 5.9117 | 51 |
| 2.0993 | 5.9106 | 52 |
| 2.0044 | 5.9099 | 53 |
| 1.9764 | 5.9102 | 54 |
| 1.9662 | 5.9116 | 55 |
| 1.9702 | 5.9145 | 56 |
| 1.9012 | 5.9152 | 57 |
| 1.8061 | 5.9175 | 58 |
| 1.7831 | 5.9211 | 59 |
| 1.8015 | 5.9253 | 60 |
| 1.7642 | 5.9298 | 61 |
| 1.7484 | 5.9328 | 62 |
| 1.5452 | 5.9342 | 63 |
| 1.5996 | 5.9369 | 64 |
| 1.4831 | 5.9396 | 65 |
| 1.4367 | 5.9421 | 66 |
| 1.4981 | 5.9435 | 67 |
| 1.4513 | 5.9475 | 68 |
| 1.3897 | 5.9532 | 69 |
| 1.3108 | 5.9603 | 70 |
| 1.3337 | 5.9664 | 71 |
| 1.2564 | 5.9728 | 72 |
| 1.2671 | 5.9770 | 73 |
| 1.1286 | 5.9814 | 74 |
| 1.1349 | 5.9843 | 75 |
| 1.1645 | 5.9842 | 76 |
| 1.1462 | 5.9806 | 77 |
| 1.1028 | 5.9791 | 78 |
| 0.9843 | 5.9770 | 79 |
| 0.9734 | 5.9768 | 80 |
| 0.9831 | 5.9795 | 81 |
| 1.0021 | 5.9823 | 82 |
| 0.8903 | 5.9826 | 83 |
| 0.8244 | 5.9837 | 84 |
| 0.8597 | 5.9863 | 85 |
| 0.8703 | 5.9907 | 86 |
| 0.7864 | 5.9996 | 87 |
| 0.7394 | 6.0086 | 88 |
| 0.6764 | 6.0188 | 89 |
| 0.7007 | 6.0278 | 90 |
| 0.6247 | 6.0355 | 91 |
| 0.6640 | 6.0430 | 92 |
| 0.6407 | 6.0498 | 93 |
| 0.5903 | 6.0565 | 94 |
| 0.6226 | 6.0614 | 95 |
| 0.5934 | 6.0662 | 96 |
| 0.5140 | 6.0713 | 97 |
| 0.5300 | 6.0766 | 98 |
| 0.4860 | 6.0810 | 99 |
Framework versions
- Transformers 4.29.0.dev0
- TensorFlow 2.9.1
- Datasets 2.5.1
- Tokenizers 0.13.3
