metadata
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: relatives_psr
results: []
relatives_psr
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0529
- Precision: 0.6343
- Recall: 0.6546
- F1: 0.6432
- Accuracy: 0.9789
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 49 | 0.0582 | 0.5838 | 0.5942 | 0.5267 | 0.9766 |
| No log | 2.0 | 98 | 0.0570 | 0.6645 | 0.6360 | 0.6064 | 0.9781 |
| No log | 3.0 | 147 | 0.0573 | 0.6458 | 0.6423 | 0.5958 | 0.9779 |
| No log | 4.0 | 196 | 0.0558 | 0.6254 | 0.6647 | 0.6365 | 0.9781 |
| No log | 5.0 | 245 | 0.0529 | 0.6343 | 0.6546 | 0.6432 | 0.9789 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1