metadata
library_name: transformers
license: mit
base_model: m3rg-iitd/matscibert
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: VF_MatSciBERT_ST_1800
results: []
VF_MatSciBERT_ST_1800
This model is a fine-tuned version of m3rg-iitd/matscibert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1571
- Precision: 0.9763
- Recall: 0.9819
- F1: 0.9791
- Accuracy: 0.9755
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1492 | 1.0 | 569 | 0.0954 | 0.9709 | 0.9754 | 0.9732 | 0.9704 |
| 0.0548 | 2.0 | 1138 | 0.0934 | 0.9726 | 0.9785 | 0.9756 | 0.9726 |
| 0.0348 | 3.0 | 1707 | 0.1098 | 0.9749 | 0.9801 | 0.9775 | 0.9738 |
| 0.0213 | 4.0 | 2276 | 0.1268 | 0.9739 | 0.9813 | 0.9776 | 0.9735 |
| 0.0141 | 5.0 | 2845 | 0.1326 | 0.9748 | 0.9806 | 0.9777 | 0.9740 |
| 0.0093 | 6.0 | 3414 | 0.1402 | 0.9750 | 0.9808 | 0.9779 | 0.9743 |
| 0.0062 | 7.0 | 3983 | 0.1541 | 0.9741 | 0.9805 | 0.9773 | 0.9733 |
| 0.0033 | 8.0 | 4552 | 0.1682 | 0.9741 | 0.9814 | 0.9777 | 0.9732 |
| 0.0026 | 9.0 | 5121 | 0.1638 | 0.9749 | 0.9821 | 0.9785 | 0.9743 |
| 0.0021 | 10.0 | 5690 | 0.1571 | 0.9763 | 0.9819 | 0.9791 | 0.9755 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1