metadata
license: mit
base_model: m3rg-iitd/matscibert
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: MatSciBERT_BIOMAT_NER3600
results: []
MatSciBERT_BIOMAT_NER3600
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: 0.4022
- Precision: 0.9708
- Recall: 0.9629
- F1: 0.9669
- Accuracy: 0.9638
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 |
|---|---|---|---|---|---|---|---|
| 0.1486 | 1.0 | 601 | 0.2452 | 0.9584 | 0.9499 | 0.9541 | 0.9494 |
| 0.0464 | 2.0 | 1202 | 0.2348 | 0.9658 | 0.9590 | 0.9624 | 0.9589 |
| 0.0265 | 3.0 | 1803 | 0.2845 | 0.9659 | 0.9599 | 0.9629 | 0.9592 |
| 0.0164 | 4.0 | 2404 | 0.3016 | 0.9689 | 0.9613 | 0.9650 | 0.9619 |
| 0.0063 | 5.0 | 3005 | 0.3531 | 0.9699 | 0.9623 | 0.9661 | 0.9631 |
| 0.0043 | 6.0 | 3606 | 0.3540 | 0.9701 | 0.9620 | 0.9660 | 0.9628 |
| 0.0033 | 7.0 | 4207 | 0.3730 | 0.9708 | 0.9630 | 0.9669 | 0.9638 |
| 0.0023 | 8.0 | 4808 | 0.3796 | 0.9710 | 0.9631 | 0.9670 | 0.9640 |
| 0.0019 | 9.0 | 5409 | 0.3892 | 0.9712 | 0.9634 | 0.9673 | 0.9642 |
| 0.0011 | 10.0 | 6010 | 0.4022 | 0.9708 | 0.9629 | 0.9669 | 0.9638 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1