metadata
base_model: manucos/finetuned__roberta-base-bne__augmented-ultrasounds
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: test-finetuned__roberta-base-bne__augmented-ultrasounds-ner
results: []
test-finetuned__roberta-base-bne__augmented-ultrasounds-ner
This model is a fine-tuned version of manucos/finetuned__roberta-base-bne__augmented-ultrasounds on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3332
- Precision: 0.7926
- Recall: 0.8856
- F1: 0.8365
- Accuracy: 0.9236
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 | 0.2753 | 0.7460 | 0.8411 | 0.7907 | 0.9106 |
| No log | 2.0 | 412 | 0.2692 | 0.7770 | 0.8603 | 0.8165 | 0.9238 |
| 0.2993 | 3.0 | 618 | 0.3276 | 0.7493 | 0.8472 | 0.7952 | 0.9087 |
| 0.2993 | 4.0 | 824 | 0.2983 | 0.7847 | 0.8704 | 0.8253 | 0.9180 |
| 0.054 | 5.0 | 1030 | 0.3066 | 0.7852 | 0.8806 | 0.8302 | 0.9221 |
| 0.054 | 6.0 | 1236 | 0.3211 | 0.7652 | 0.8806 | 0.8188 | 0.9211 |
| 0.054 | 7.0 | 1442 | 0.3314 | 0.7883 | 0.8704 | 0.8273 | 0.9189 |
| 0.0205 | 8.0 | 1648 | 0.3245 | 0.7827 | 0.8785 | 0.8278 | 0.9224 |
| 0.0205 | 9.0 | 1854 | 0.3306 | 0.7825 | 0.8846 | 0.8304 | 0.9235 |
| 0.0128 | 10.0 | 2060 | 0.3332 | 0.7926 | 0.8856 | 0.8365 | 0.9236 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1