metadata
library_name: transformers
license: mit
base_model: m3rg-iitd/matscibert
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: Final_Biomaterials_ST_single_dataset
results: []
Final_Biomaterials_ST_single_dataset
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: 0.1312
- Precision: 0.6382
- Recall: 0.6581
- F1: 0.6480
- Accuracy: 0.9631
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0925 | 1.0 | 3272 | 0.0913 | 0.6363 | 0.6521 | 0.6441 | 0.9624 |
| 0.0707 | 2.0 | 6544 | 0.0937 | 0.6491 | 0.6611 | 0.6550 | 0.9637 |
| 0.0607 | 3.0 | 9816 | 0.1028 | 0.6480 | 0.6591 | 0.6535 | 0.9626 |
| 0.0522 | 4.0 | 13088 | 0.1076 | 0.6175 | 0.6910 | 0.6522 | 0.9610 |
| 0.0485 | 5.0 | 16360 | 0.1087 | 0.6732 | 0.6208 | 0.6459 | 0.9640 |
| 0.0472 | 6.0 | 19632 | 0.1140 | 0.6431 | 0.6334 | 0.6382 | 0.9622 |
| 0.0454 | 7.0 | 22904 | 0.1232 | 0.6113 | 0.7110 | 0.6574 | 0.9609 |
| 0.0431 | 8.0 | 26176 | 0.1285 | 0.6750 | 0.6237 | 0.6484 | 0.9636 |
| 0.0427 | 9.0 | 29448 | 0.1301 | 0.6273 | 0.6609 | 0.6437 | 0.9610 |
| 0.0409 | 10.0 | 32720 | 0.1312 | 0.6382 | 0.6581 | 0.6480 | 0.9631 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1