metadata
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: scibert-ner
results: []
scibert-ner
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: 0.1809
- Precision: 0.4499
- Recall: 0.4637
- F1: 0.4567
- Accuracy: 0.9536
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 60 | 0.1967 | 0.3563 | 0.3184 | 0.3363 | 0.9509 |
| No log | 2.0 | 120 | 0.1726 | 0.4077 | 0.3855 | 0.3963 | 0.9525 |
| No log | 3.0 | 180 | 0.1723 | 0.4204 | 0.4721 | 0.4447 | 0.9529 |
| No log | 4.0 | 240 | 0.1775 | 0.4248 | 0.4735 | 0.4478 | 0.9526 |
| No log | 5.0 | 300 | 0.1809 | 0.4499 | 0.4637 | 0.4567 | 0.9536 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1