<!-- 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. -->
scibert-demo-15-3
This model is a fine-tuned version of allenai/scibert_scivocab_uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1514
- Precision: 0.4465
- Recall: 0.5063
- F1: 0.4745
- Accuracy: 0.9565
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: 16
- eval_batch_size: 16
- seed: 42
- 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 |
---|---|---|---|---|---|---|---|
No log | 1.0 | 47 | 0.2048 | 0.4615 | 0.2259 | 0.3034 | 0.9511 |
No log | 2.0 | 94 | 0.1600 | 0.3968 | 0.4100 | 0.4033 | 0.9548 |
No log | 3.0 | 141 | 0.1496 | 0.4597 | 0.4540 | 0.4568 | 0.9566 |
No log | 4.0 | 188 | 0.1513 | 0.4758 | 0.4937 | 0.4846 | 0.9579 |
No log | 5.0 | 235 | 0.1514 | 0.4465 | 0.5063 | 0.4745 | 0.9565 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1