metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- 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:
- Loss: 0.8272
- Precision-macro: 0.6089
- Recall-macro: 0.5868
- Macro-f1: 0.5926
- Precision-micro: 0.7798
- Recall-micro: 0.7798
- Micro-f1: 0.7798
- Accuracy: 0.7798
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 | Validation Loss | Precision-macro | Recall-macro | Macro-f1 | Precision-micro | Recall-micro | Micro-f1 | Accuracy |
---|---|---|---|---|---|---|---|---|---|---|
No log | 1.0 | 62 | 1.1797 | 0.3651 | 0.2425 | 0.2406 | 0.6509 | 0.6509 | 0.6509 | 0.6509 |
No log | 2.0 | 124 | 0.8354 | 0.5350 | 0.5291 | 0.5255 | 0.7350 | 0.7350 | 0.7350 | 0.7350 |
No log | 3.0 | 186 | 0.8058 | 0.5559 | 0.5382 | 0.5366 | 0.7343 | 0.7343 | 0.7343 | 0.7343 |
No log | 4.0 | 248 | 0.7718 | 0.6246 | 0.5201 | 0.5300 | 0.7503 | 0.7503 | 0.7503 | 0.7503 |
No log | 5.0 | 310 | 0.7307 | 0.5890 | 0.5463 | 0.5579 | 0.7642 | 0.7642 | 0.7642 | 0.7642 |
No log | 6.0 | 372 | 0.7099 | 0.6076 | 0.5431 | 0.5481 | 0.7746 | 0.7746 | 0.7746 | 0.7746 |
No log | 7.0 | 434 | 0.7072 | 0.6090 | 0.5126 | 0.5261 | 0.7812 | 0.7812 | 0.7812 | 0.7812 |
No log | 8.0 | 496 | 0.6919 | 0.6321 | 0.5471 | 0.5676 | 0.7826 | 0.7826 | 0.7826 | 0.7826 |
0.8758 | 9.0 | 558 | 0.7503 | 0.5666 | 0.5818 | 0.5696 | 0.7735 | 0.7735 | 0.7735 | 0.7735 |
0.8758 | 10.0 | 620 | 0.7512 | 0.6054 | 0.5656 | 0.5755 | 0.7784 | 0.7784 | 0.7784 | 0.7784 |
0.8758 | 11.0 | 682 | 0.7656 | 0.6086 | 0.5835 | 0.5913 | 0.7829 | 0.7829 | 0.7829 | 0.7829 |
0.8758 | 12.0 | 744 | 0.7861 | 0.5972 | 0.5885 | 0.5843 | 0.7739 | 0.7739 | 0.7739 | 0.7739 |
0.8758 | 13.0 | 806 | 0.8239 | 0.5975 | 0.5749 | 0.5701 | 0.7780 | 0.7780 | 0.7780 | 0.7780 |
0.8758 | 14.0 | 868 | 0.8272 | 0.6089 | 0.5868 | 0.5926 | 0.7798 | 0.7798 | 0.7798 | 0.7798 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1