metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: token_fine_tunned_flipkart_2_gl
results: []
token_fine_tunned_flipkart_2_gl
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0275
- Precision: 0.9888
- Recall: 0.9900
- F1: 0.9894
- Accuracy: 0.9924
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:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 136 | 0.1945 | 0.9023 | 0.9338 | 0.9178 | 0.9331 |
| No log | 2.0 | 272 | 0.1232 | 0.9469 | 0.9572 | 0.9520 | 0.9658 |
| No log | 3.0 | 408 | 0.0852 | 0.9595 | 0.9688 | 0.9641 | 0.9747 |
| 0.2214 | 4.0 | 544 | 0.0603 | 0.9723 | 0.9760 | 0.9741 | 0.9831 |
| 0.2214 | 5.0 | 680 | 0.0455 | 0.9770 | 0.9819 | 0.9794 | 0.9865 |
| 0.2214 | 6.0 | 816 | 0.0357 | 0.9823 | 0.9863 | 0.9843 | 0.9887 |
| 0.2214 | 7.0 | 952 | 0.0307 | 0.9869 | 0.9894 | 0.9882 | 0.9916 |
| 0.0938 | 8.0 | 1088 | 0.0275 | 0.9888 | 0.9900 | 0.9894 | 0.9924 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu102
- Datasets 2.2.2
- Tokenizers 0.12.1