metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: medlid-identify
results: []
medlid-identify
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1248
- Precision: 0.4410
- Recall: 0.4209
- F1: 0.4307
- Accuracy: 0.9541
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: 81
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 381 | 0.1297 | 0.3898 | 0.3032 | 0.3411 | 0.9525 |
0.1774 | 2.0 | 762 | 0.1191 | 0.4485 | 0.3489 | 0.3925 | 0.9551 |
0.1177 | 3.0 | 1143 | 0.1216 | 0.4341 | 0.4209 | 0.4274 | 0.9544 |
0.0974 | 4.0 | 1524 | 0.1248 | 0.4410 | 0.4209 | 0.4307 | 0.9541 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.11.0
- Datasets 2.13.1
- Tokenizers 0.13.3