metadata
library_name: transformers
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: roberta-large-tqacd
results: []
roberta-large-tqacd
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: 3.8956
- F1 Macro: 0.2608
- Precision: 0.3007
- Recall: 0.2456
- Accuracy: 0.4158
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | Precision | Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 114 | 2.4069 | 0.0094 | 0.0050 | 0.0909 | 0.0545 |
| No log | 2.0 | 228 | 2.3298 | 0.1595 | 0.2519 | 0.1597 | 0.3366 |
| No log | 3.0 | 342 | 2.2454 | 0.1746 | 0.2033 | 0.2052 | 0.2475 |
| No log | 4.0 | 456 | 2.1684 | 0.2588 | 0.2830 | 0.2813 | 0.3614 |
| 2.2272 | 5.0 | 570 | 2.3380 | 0.2425 | 0.2709 | 0.2786 | 0.3515 |
| 2.2272 | 6.0 | 684 | 2.4213 | 0.3017 | 0.3142 | 0.3231 | 0.3713 |
| 2.2272 | 7.0 | 798 | 2.7961 | 0.3100 | 0.3442 | 0.3141 | 0.3911 |
| 2.2272 | 8.0 | 912 | 3.0757 | 0.2478 | 0.2576 | 0.2722 | 0.3614 |
| 0.6491 | 9.0 | 1026 | 3.8956 | 0.2608 | 0.3007 | 0.2456 | 0.4158 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1