OTE-DAPT-CAMEL-MSA-HARD-6580SUBSAMPLE-run1
This model is a fine-tuned version of salohnana2018/HARD_without_dp_6580_camel_prepocessed_OTE on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1747
- Precision: 0.7539
- Recall: 0.7952
- F1: 0.7740
- Accuracy: 0.9544
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 25
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1466 | 1.0 | 121 | 0.1154 | 0.8219 | 0.7060 | 0.7596 | 0.9558 |
0.0871 | 2.0 | 242 | 0.1157 | 0.7818 | 0.7588 | 0.7702 | 0.9566 |
0.0585 | 3.0 | 363 | 0.1323 | 0.7773 | 0.7862 | 0.7818 | 0.9566 |
0.0365 | 4.0 | 484 | 0.1593 | 0.7434 | 0.7982 | 0.7698 | 0.9539 |
0.0248 | 5.0 | 605 | 0.1747 | 0.7539 | 0.7952 | 0.7740 | 0.9544 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 4
Invalid base_model specified in model card
metadata. Needs to be a model id from
hf.co/models.