metadata
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: SciBERT_CRAFT_NER_new
results: []
SciBERT_CRAFT_NER_new
This model is a fine-tuned version of allenai/scibert_scivocab_uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1199
- Precision: 0.9743
- Recall: 0.9761
- F1: 0.9752
- Accuracy: 0.9740
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1537 | 1.0 | 695 | 0.1140 | 0.9707 | 0.9727 | 0.9717 | 0.9704 |
| 0.0452 | 2.0 | 1390 | 0.1128 | 0.9733 | 0.9750 | 0.9741 | 0.9731 |
| 0.0185 | 3.0 | 2085 | 0.1199 | 0.9743 | 0.9761 | 0.9752 | 0.9740 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0