metadata
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- recall
- f1
model-index:
- name: non_green_as_train_context_roberta-large
results: []
non_green_as_train_context_roberta-large
This model is a fine-tuned version of FacebookAI/roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1773
- Accuracy: 0.9776
- Recall: 0.6993
- F1: 0.7021
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: 1e-05
- train_batch_size: 16
- 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.0584 | 1.0 | 7739 | 0.0916 | 0.9725 | 0.6942 | 0.6562 |
| 0.0451 | 2.0 | 15478 | 0.0905 | 0.9773 | 0.6700 | 0.6902 |
| 0.0296 | 3.0 | 23217 | 0.1112 | 0.9775 | 0.6912 | 0.6986 |
| 0.0141 | 4.0 | 30956 | 0.1487 | 0.9759 | 0.7366 | 0.6979 |
| 0.0102 | 5.0 | 38695 | 0.1773 | 0.9776 | 0.6993 | 0.7021 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2