metadata
tags:
- generated_from_trainer
model-index:
- name: ontochem_biobert_cross_valid_4
results: []
ontochem_biobert_cross_valid_4
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0427
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 5 | 0.0443 |
| No log | 2.0 | 10 | 0.0443 |
| No log | 3.0 | 15 | 0.0442 |
| No log | 4.0 | 20 | 0.0441 |
| No log | 5.0 | 25 | 0.0439 |
| No log | 6.0 | 30 | 0.0437 |
| No log | 7.0 | 35 | 0.0435 |
| No log | 8.0 | 40 | 0.0433 |
| No log | 9.0 | 45 | 0.0430 |
| No log | 10.0 | 50 | 0.0427 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2