metadata
library_name: transformers
license: mit
base_model: m3rg-iitd/matscibert
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: MatSciBERT_ST_DA_1800
results: []
MatSciBERT_ST_DA_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: 0.1671
- Precision: 0.8613
- Recall: 0.8455
- F1: 0.8533
- Accuracy: 0.9746
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0809 | 1.0 | 1050 | 0.1024 | 0.8455 | 0.8230 | 0.8341 | 0.9719 |
| 0.0424 | 2.0 | 2100 | 0.1023 | 0.8371 | 0.8365 | 0.8368 | 0.9714 |
| 0.025 | 3.0 | 3150 | 0.1397 | 0.8397 | 0.8223 | 0.8309 | 0.9702 |
| 0.0142 | 4.0 | 4200 | 0.1403 | 0.8592 | 0.8379 | 0.8484 | 0.9736 |
| 0.0074 | 5.0 | 5250 | 0.1271 | 0.8727 | 0.8641 | 0.8684 | 0.9771 |
| 0.0047 | 6.0 | 6300 | 0.1430 | 0.8742 | 0.8581 | 0.8661 | 0.9769 |
| 0.0023 | 7.0 | 7350 | 0.1777 | 0.8578 | 0.8310 | 0.8442 | 0.9733 |
| 0.0015 | 8.0 | 8400 | 0.1524 | 0.8637 | 0.8581 | 0.8609 | 0.9760 |
| 0.0013 | 9.0 | 9450 | 0.1683 | 0.8609 | 0.8441 | 0.8524 | 0.9745 |
| 0.0008 | 10.0 | 10500 | 0.1671 | 0.8613 | 0.8455 | 0.8533 | 0.9746 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1