MRR_QA_15K_UNTIL_2_08_FINRTUNED_ON_21_7_MODEL
This model is a fine-tuned version of am-infoweb/MRR-Latest-21-7 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0308
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: 1
- eval_batch_size: 1
- seed: 42
- 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 |
|---|---|---|---|
| 1.03 | 1.0 | 11594 | 1.0591 |
| 0.9616 | 2.0 | 23188 | 0.8061 |
| 0.8357 | 3.0 | 34782 | 0.9515 |
| 0.7217 | 4.0 | 46376 | 0.8091 |
| 0.6558 | 5.0 | 57970 | 0.8454 |
| 0.6175 | 6.0 | 69564 | 0.7826 |
| 0.4479 | 7.0 | 81158 | 0.9225 |
| 0.3561 | 8.0 | 92752 | 0.8987 |
| 0.3635 | 9.0 | 104346 | 0.9856 |
| 0.3647 | 10.0 | 115940 | 1.0308 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3