metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta-base-downstream-build_rr
results: []
roberta-base-downstream-build_rr
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Precision: 0.1983
- Recall: 0.3587
- F1: 0.2554
- Micro-f1: 0.2554
- Accuracy: 0.9191
- Loss: 0.2640
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Precision | Recall | F1 | Micro-f1 | Accuracy | Validation Loss |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 62 | 0.0835 | 0.1152 | 0.0968 | 0.0968 | 0.8780 | 0.4226 |
| No log | 2.0 | 124 | 0.1537 | 0.2696 | 0.1957 | 0.1957 | 0.8931 | 0.3475 |
| No log | 3.0 | 186 | 0.1875 | 0.3391 | 0.2415 | 0.2415 | 0.9052 | 0.2912 |
| No log | 4.0 | 248 | 0.1992 | 0.3304 | 0.2486 | 0.2486 | 0.9003 | 0.2991 |
| No log | 5.0 | 310 | 0.1784 | 0.3870 | 0.2442 | 0.2442 | 0.9066 | 0.2833 |
| No log | 6.0 | 372 | 0.2206 | 0.3543 | 0.2719 | 0.2719 | 0.9148 | 0.2642 |
| No log | 7.0 | 434 | 0.2300 | 0.3630 | 0.2816 | 0.2816 | 0.9177 | 0.2584 |
| No log | 8.0 | 496 | 0.2179 | 0.3696 | 0.2742 | 0.2742 | 0.9177 | 0.2523 |
| 0.4245 | 9.0 | 558 | 0.1921 | 0.3696 | 0.2528 | 0.2528 | 0.9167 | 0.2630 |
| 0.4245 | 10.0 | 620 | 0.1983 | 0.3587 | 0.2554 | 0.2554 | 0.9191 | 0.2640 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1