<!-- 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. -->
distilgpt_new2_0020
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 2.6019
- Validation Loss: 2.4890
- Epoch: 19
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 |
---|---|---|
2.6241 | 2.5129 | 0 |
2.6228 | 2.5112 | 1 |
2.6216 | 2.5105 | 2 |
2.6204 | 2.5101 | 3 |
2.6191 | 2.5088 | 4 |
2.6180 | 2.5064 | 5 |
2.6166 | 2.5045 | 6 |
2.6155 | 2.5038 | 7 |
2.6143 | 2.5024 | 8 |
2.6132 | 2.5009 | 9 |
2.6120 | 2.5014 | 10 |
2.6108 | 2.4984 | 11 |
2.6097 | 2.4983 | 12 |
2.6085 | 2.4976 | 13 |
2.6073 | 2.4948 | 14 |
2.6064 | 2.4945 | 15 |
2.6052 | 2.4939 | 16 |
2.6039 | 2.4925 | 17 |
2.6030 | 2.4912 | 18 |
2.6019 | 2.4890 | 19 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.8.2
- Datasets 2.3.2
- Tokenizers 0.12.1