results
This model is a fine-tuned version of aubmindlab/aragpt2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.3519
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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 |
|---|---|---|---|
| 5.6158 | 0.9976 | 258 | 4.4942 |
| 5.394 | 1.9990 | 517 | 4.4081 |
| 5.2155 | 2.9966 | 775 | 4.3753 |
| 5.1119 | 3.9981 | 1034 | 4.3581 |
| 5.2103 | 4.9879 | 1290 | 4.3519 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 1
Model tree for xfoxxe/results
Base model
aubmindlab/aragpt2-base