metadata
library_name: transformers
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: roberta-large-pr
results: []
roberta-large-pr
This model is a fine-tuned version of FacebookAI/roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1086
- F1 Macro: 0.6212
- Precision: 0.6133
- Recall: 0.6330
- Accuracy: 0.7726
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: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | Precision | Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 240 | 1.6547 | 0.4481 | 0.4726 | 0.5217 | 0.5525 |
| No log | 2.0 | 480 | 0.7853 | 0.5905 | 0.6003 | 0.6054 | 0.7497 |
| 1.8301 | 3.0 | 720 | 0.8548 | 0.5993 | 0.6286 | 0.6309 | 0.7513 |
| 1.8301 | 4.0 | 960 | 0.7731 | 0.6257 | 0.6300 | 0.6352 | 0.7706 |
| 0.8772 | 5.0 | 1200 | 0.7724 | 0.6353 | 0.6364 | 0.6460 | 0.7846 |
| 0.8772 | 6.0 | 1440 | 0.8417 | 0.6325 | 0.6403 | 0.6354 | 0.7836 |
| 0.4566 | 7.0 | 1680 | 1.1086 | 0.6212 | 0.6133 | 0.6330 | 0.7726 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1