fro-distil-xlstm
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.0458
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 33.2811 | 0.32 | 100 | 7.5666 |
| 29.407 | 0.64 | 200 | 7.2904 |
| 28.5722 | 0.96 | 300 | 7.1566 |
| 27.7729 | 1.2784 | 400 | 7.0902 |
| 27.673 | 1.5984 | 500 | 7.0559 |
| 27.596 | 1.9184 | 600 | 7.0458 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 6