metadata
license: mit
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: >-
fine-tuned-DatasetQAS-IDK-MRC-with-xlm-roberta-large-with-ITTL-with-freeze-LR-1e-05
results: []
fine-tuned-DatasetQAS-IDK-MRC-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: 0.8236
- Exact Match: 75.9162
- F1: 81.7215
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- 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 |
|---|---|---|---|---|---|
| 6.4323 | 0.49 | 36 | 2.3534 | 50.0 | 50.0 |
| 3.6036 | 0.98 | 72 | 1.7984 | 47.5131 | 48.0031 |
| 1.8711 | 1.48 | 108 | 1.1297 | 59.1623 | 67.4774 |
| 1.8711 | 1.97 | 144 | 1.0215 | 62.9581 | 70.7402 |
| 1.1663 | 2.46 | 180 | 0.8500 | 69.1099 | 76.2124 |
| 0.9042 | 2.95 | 216 | 0.8389 | 68.8482 | 76.0043 |
| 0.7502 | 3.45 | 252 | 0.8404 | 70.9424 | 78.2197 |
| 0.7502 | 3.94 | 288 | 0.9341 | 68.5864 | 75.3916 |
| 0.6715 | 4.44 | 324 | 0.7647 | 74.2147 | 80.2681 |
| 0.576 | 4.92 | 360 | 0.7881 | 75.6545 | 81.9120 |
| 0.576 | 5.42 | 396 | 0.8022 | 74.7382 | 80.7782 |
| 0.5213 | 5.91 | 432 | 0.8218 | 74.2147 | 80.6803 |
| 0.4811 | 6.41 | 468 | 0.8236 | 75.9162 | 81.7215 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu117
- Datasets 2.2.0
- Tokenizers 0.13.2