metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
model-index:
- name: RoBERTa-MGT-Crossdomain
results: []
RoBERTa-MGT-Crossdomain
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7562
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 2400 | 0.3634 |
| No log | 2.0 | 4800 | 0.5188 |
| 0.4912 | 3.0 | 7200 | 0.5234 |
| 0.4912 | 4.0 | 9600 | 0.4002 |
| 0.2956 | 5.0 | 12000 | 0.5178 |
| 0.2956 | 6.0 | 14400 | 0.4614 |
| 0.2048 | 7.0 | 16800 | 0.5688 |
| 0.2048 | 8.0 | 19200 | 0.7062 |
| 0.1194 | 9.0 | 21600 | 0.6674 |
| 0.1194 | 10.0 | 24000 | 0.7562 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1