<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
fine-tuned-DatasetQAS-Squad-ID-with-xlm-roberta-large-with-ITTL-with-freeze-LR-1e-05
This model is a fine-tuned version of xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4039
- Exact Match: 53.6774
- F1: 69.6967
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
---|---|---|---|---|---|
1.5208 | 0.5 | 463 | 1.4095 | 50.0294 | 67.1298 |
1.3903 | 1.0 | 926 | 1.3159 | 52.1644 | 69.1681 |
1.2662 | 1.5 | 1389 | 1.2718 | 53.1058 | 69.4729 |
1.1754 | 2.0 | 1852 | 1.2603 | 53.2655 | 69.6756 |
1.0681 | 2.5 | 2315 | 1.2586 | 53.6186 | 69.8988 |
1.0887 | 3.0 | 2778 | 1.2555 | 53.6690 | 70.2968 |
0.9549 | 3.5 | 3241 | 1.3076 | 54.1481 | 70.1900 |
0.9549 | 4.0 | 3704 | 1.2922 | 54.0977 | 70.2654 |
0.8528 | 4.49 | 4167 | 1.3767 | 53.9212 | 70.6362 |
0.8467 | 4.99 | 4630 | 1.3384 | 53.8371 | 69.7755 |
0.7709 | 5.49 | 5093 | 1.3847 | 53.7615 | 70.0607 |
0.763 | 5.99 | 5556 | 1.4039 | 53.6774 | 69.6967 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2