distilbert_new2_0040
This model is a fine-tuned version of [/content/drive/MyDrive/Colab Notebooks/oscar/trybackup_distilbert/new_backup_0105105](https://huggingface.co//content/drive/MyDrive/Colab Notebooks/oscar/trybackup_distilbert/new_backup_0105105) on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.9702
- Validation Loss: 0.9482
- Epoch: 39
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 |
---|---|---|
1.0180 | 0.9873 | 0 |
1.0163 | 0.9878 | 1 |
1.0145 | 0.9856 | 2 |
1.0139 | 0.9830 | 3 |
1.0122 | 0.9831 | 4 |
1.0118 | 0.9830 | 5 |
1.0094 | 0.9800 | 6 |
1.0075 | 0.9809 | 7 |
1.0066 | 0.9784 | 8 |
1.0062 | 0.9768 | 9 |
1.0032 | 0.9751 | 10 |
1.0023 | 0.9764 | 11 |
1.0008 | 0.9735 | 12 |
0.9994 | 0.9730 | 13 |
0.9986 | 0.9761 | 14 |
0.9975 | 0.9714 | 15 |
0.9953 | 0.9708 | 16 |
0.9941 | 0.9683 | 17 |
0.9933 | 0.9681 | 18 |
0.9920 | 0.9688 | 19 |
0.9907 | 0.9648 | 20 |
0.9897 | 0.9625 | 21 |
0.9890 | 0.9642 | 22 |
0.9873 | 0.9633 | 23 |
0.9867 | 0.9618 | 24 |
0.9857 | 0.9600 | 25 |
0.9839 | 0.9598 | 26 |
0.9827 | 0.9585 | 27 |
0.9821 | 0.9607 | 28 |
0.9809 | 0.9579 | 29 |
0.9803 | 0.9561 | 30 |
0.9786 | 0.9563 | 31 |
0.9774 | 0.9536 | 32 |
0.9766 | 0.9542 | 33 |
0.9756 | 0.9523 | 34 |
0.9743 | 0.9525 | 35 |
0.9730 | 0.9513 | 36 |
0.9721 | 0.9507 | 37 |
0.9715 | 0.9506 | 38 |
0.9702 | 0.9482 | 39 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.8.2
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.