metadata
base_model: manucos/finetuned__beto-clinical-wl-es__augmented-ultrasounds
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: finetuned__beto-clinical-wl-es__augmented-ultrasounds-ner
results: []
finetuned__beto-clinical-wl-es__augmented-ultrasounds-ner
This model is a fine-tuned version of manucos/finetuned__beto-clinical-wl-es__augmented-ultrasounds on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3556
- Precision: 0.8057
- Recall: 0.8897
- F1: 0.8456
- Accuracy: 0.9216
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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 206 | 0.2470 | 0.7303 | 0.8441 | 0.7831 | 0.9080 |
| No log | 2.0 | 412 | 0.2471 | 0.7632 | 0.8644 | 0.8106 | 0.9182 |
| 0.3075 | 3.0 | 618 | 0.2838 | 0.7661 | 0.8553 | 0.8082 | 0.9106 |
| 0.3075 | 4.0 | 824 | 0.3057 | 0.7802 | 0.8765 | 0.8255 | 0.9170 |
| 0.0622 | 5.0 | 1030 | 0.2932 | 0.7844 | 0.8836 | 0.8310 | 0.9204 |
| 0.0622 | 6.0 | 1236 | 0.3435 | 0.8037 | 0.8907 | 0.8449 | 0.9211 |
| 0.0622 | 7.0 | 1442 | 0.3464 | 0.8013 | 0.8856 | 0.8413 | 0.9196 |
| 0.0255 | 8.0 | 1648 | 0.3470 | 0.7980 | 0.8877 | 0.8404 | 0.9224 |
| 0.0255 | 9.0 | 1854 | 0.3556 | 0.8055 | 0.8887 | 0.8450 | 0.9201 |
| 0.0159 | 10.0 | 2060 | 0.3556 | 0.8057 | 0.8897 | 0.8456 | 0.9216 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1