roberta-base-finetuned-coling24
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3002
- Accuracy: 0.9599
- F1: 0.9594
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 9544 | 0.0976 | 0.9654 | 0.9652 |
| 0.0773 | 2.0 | 19088 | 0.1342 | 0.9580 | 0.9575 |
| 0.0773 | 3.0 | 28632 | 0.2332 | 0.9514 | 0.9507 |
| 0.0249 | 4.0 | 38176 | 0.2737 | 0.9566 | 0.9560 |
| 0.0249 | 5.0 | 47720 | 0.3002 | 0.9599 | 0.9594 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 22
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model's library.
Model tree for andricValdez/roberta-base-finetuned-coling24
Base model
FacebookAI/roberta-base