metadata
base_model: allenai/scibert_scivocab_uncased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: SciBERT_JNLPBA_NER
results: []
SciBERT_JNLPBA_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: 0.1456
- Precision: 0.8042
- Recall: 0.8228
- F1: 0.8134
- Accuracy: 0.9512
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|---|
| 0.234 | 1.0 | 582 | 0.1536 | 0.7820 | 0.7944 | 0.7882 | 0.9469 |
| 0.1398 | 2.0 | 1164 | 0.1489 | 0.7962 | 0.8033 | 0.7997 | 0.9495 |
| 0.1212 | 3.0 | 1746 | 0.1456 | 0.8042 | 0.8228 | 0.8134 | 0.9512 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0