<!-- 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. -->
MRR-Latest-27-7
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: 2.1198
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.9033 | 1.0 | 630 | 0.6143 |
0.6184 | 2.0 | 1260 | 0.8534 |
0.5676 | 3.0 | 1890 | 0.6799 |
0.4571 | 4.0 | 2520 | 0.7548 |
0.4373 | 5.0 | 3150 | 0.9901 |
0.4133 | 6.0 | 3780 | 0.7865 |
0.3761 | 7.0 | 4410 | 0.8389 |
0.367 | 8.0 | 5040 | 0.8556 |
0.3665 | 9.0 | 5670 | 1.0920 |
0.3377 | 10.0 | 6300 | 1.0847 |
0.2857 | 11.0 | 6930 | 1.1071 |
0.2991 | 12.0 | 7560 | 1.0964 |
0.2647 | 13.0 | 8190 | 1.3036 |
0.2518 | 14.0 | 8820 | 1.3547 |
0.2543 | 15.0 | 9450 | 1.5333 |
0.2156 | 16.0 | 10080 | 1.4622 |
0.1856 | 17.0 | 10710 | 1.4964 |
0.2144 | 18.0 | 11340 | 1.7252 |
0.1993 | 19.0 | 11970 | 1.7526 |
0.1723 | 20.0 | 12600 | 1.8491 |
0.1257 | 21.0 | 13230 | 2.0100 |
0.1555 | 22.0 | 13860 | 1.9707 |
0.1276 | 23.0 | 14490 | 2.0484 |
0.1216 | 24.0 | 15120 | 2.1069 |
0.1252 | 25.0 | 15750 | 2.1198 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3