hubert-base-ls960-finetuned-ie-finetuned-bmd-V1-20241110_122026-LOSO-section-out1
This model is a fine-tuned version of minoosh/hubert-base-ls960-finetuned-ie on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0535
- Accuracy: 0.5172
- F1: 0.5170
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1968
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 0.8571 | 3 | 1.0950 | 0.3793 | 0.3080 |
| No log | 2.0 | 7 | 1.0368 | 0.5862 | 0.4954 |
| 1.0818 | 2.8571 | 10 | 1.0912 | 0.3793 | 0.2891 |
| 1.0818 | 4.0 | 14 | 1.1516 | 0.2759 | 0.2156 |
| 1.0818 | 4.8571 | 17 | 1.1741 | 0.3103 | 0.2585 |
| 1.0362 | 6.0 | 21 | 1.1000 | 0.4483 | 0.4188 |
| 1.0362 | 6.8571 | 24 | 1.1781 | 0.4138 | 0.3508 |
| 1.0362 | 8.0 | 28 | 1.1275 | 0.4138 | 0.3034 |
| 0.9687 | 8.8571 | 31 | 1.1096 | 0.4483 | 0.4413 |
| 0.9687 | 10.0 | 35 | 1.0533 | 0.5172 | 0.5089 |
| 0.9687 | 10.8571 | 38 | 1.0434 | 0.5862 | 0.5839 |
| 0.8942 | 12.0 | 42 | 1.0420 | 0.5172 | 0.5252 |
| 0.8942 | 12.8571 | 45 | 1.0535 | 0.5172 | 0.5170 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3