metadata
base_model: jsylee/scibert_scivocab_uncased-finetuned-ner
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: AI_Workshop_Sonatafy_scibert-finetuned_ADEs
results: []
AI_Workshop_Sonatafy_scibert-finetuned_ADEs
This model is a fine-tuned version of jsylee/scibert_scivocab_uncased-finetuned-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2103
- Precision: 0.6454
- Recall: 0.6510
- F1: 0.6482
- Accuracy: 0.9098
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: 5e-07
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|
| 0.2952 | 1.0 | 640 | 0.2368 | 0.5806 | 0.6360 | 0.6071 | 0.8992 |
| 0.2315 | 2.0 | 1280 | 0.2196 | 0.6321 | 0.6403 | 0.6362 | 0.9047 |
| 0.2197 | 3.0 | 1920 | 0.2143 | 0.6340 | 0.6510 | 0.6424 | 0.9061 |
| 0.2105 | 4.0 | 2560 | 0.2112 | 0.6467 | 0.6488 | 0.6478 | 0.9092 |
| 0.2078 | 5.0 | 3200 | 0.2103 | 0.6454 | 0.6510 | 0.6482 | 0.9098 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1