metadata
base_model: KISTI-AI/scideberta-cs
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: scideberta-cs-ner
results: []
scideberta-cs-ner
This model is a fine-tuned version of KISTI-AI/scideberta-cs on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1552
- Precision: 0.4943
- Recall: 0.5475
- F1: 0.5195
- Accuracy: 0.9589
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 | 0.1980 | 0.3445 | 0.2723 | 0.3042 | 0.9530 |
| No log | 2.0 | 120 | 0.1579 | 0.4444 | 0.4358 | 0.4401 | 0.9582 |
| No log | 3.0 | 180 | 0.1520 | 0.4751 | 0.5321 | 0.5020 | 0.9568 |
| No log | 4.0 | 240 | 0.1518 | 0.4955 | 0.5433 | 0.5183 | 0.9592 |
| No log | 5.0 | 300 | 0.1552 | 0.4943 | 0.5475 | 0.5195 | 0.9589 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1