metadata
license: mit
base_model: m3rg-iitd/matscibert
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: MatSciBERT_BIOMAT_NER2
results: []
MatSciBERT_BIOMAT_NER2
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: 0.5316
- Precision: 0.9596
- Recall: 0.9442
- F1: 0.9518
- Accuracy: 0.9428
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 |
|---|---|---|---|---|---|---|---|
| 0.1601 | 1.0 | 793 | 0.2740 | 0.9603 | 0.9459 | 0.9530 | 0.9444 |
| 0.0276 | 2.0 | 1586 | 0.3631 | 0.9599 | 0.9447 | 0.9522 | 0.9431 |
| 0.0139 | 3.0 | 2379 | 0.3745 | 0.9602 | 0.9445 | 0.9523 | 0.9430 |
| 0.0054 | 4.0 | 3172 | 0.4634 | 0.9601 | 0.9441 | 0.9521 | 0.9429 |
| 0.0039 | 5.0 | 3965 | 0.4709 | 0.9594 | 0.9440 | 0.9517 | 0.9423 |
| 0.0018 | 6.0 | 4758 | 0.5042 | 0.9587 | 0.9440 | 0.9513 | 0.9426 |
| 0.0011 | 7.0 | 5551 | 0.5223 | 0.9598 | 0.9439 | 0.9518 | 0.9425 |
| 0.0009 | 8.0 | 6344 | 0.5241 | 0.9594 | 0.9438 | 0.9515 | 0.9424 |
| 0.0004 | 9.0 | 7137 | 0.5277 | 0.9595 | 0.9441 | 0.9517 | 0.9428 |
| 0.0004 | 10.0 | 7930 | 0.5316 | 0.9596 | 0.9442 | 0.9518 | 0.9428 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1