<!-- 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. -->
bert_large_top10
This model is a fine-tuned version of bert-large-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8335
- Precision Macro: 0.1511
- Recall Macro: 0.1679
- F1 Macro: 0.1567
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.3
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision Macro | Recall Macro | F1 Macro |
---|---|---|---|---|---|---|
0.7166 | 1.0 | 2804 | 0.6092 | 0.2917 | 0.1173 | 0.1017 |
0.7027 | 2.0 | 5608 | 0.6008 | 0.3011 | 0.1238 | 0.1082 |
0.6525 | 3.0 | 8412 | 0.5903 | 0.3419 | 0.1047 | 0.1022 |
0.6258 | 4.0 | 11216 | 0.5809 | 0.2583 | 0.1063 | 0.1036 |
0.6266 | 5.0 | 14020 | 0.6169 | 0.1295 | 0.1309 | 0.1235 |
0.5674 | 6.0 | 16824 | 0.6408 | 0.1340 | 0.1312 | 0.1190 |
0.5405 | 7.0 | 19628 | 0.6992 | 0.1490 | 0.1482 | 0.1458 |
0.4175 | 8.0 | 22432 | 0.7292 | 0.1442 | 0.1571 | 0.1450 |
0.3858 | 9.0 | 25236 | 0.8100 | 0.1476 | 0.1680 | 0.1544 |
0.3495 | 10.0 | 28040 | 0.8335 | 0.1511 | 0.1679 | 0.1567 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.6.dev0
- Tokenizers 0.14.0