moe_tur_multi
This model is a fine-tuned version of on the arrow dataset. It achieves the following results on the evaluation set:
- Loss: 5.5168
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 9561
- training_steps: 95611
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0 | 0 | 10.9682 |
| 4.9234 | 1.0458 | 10000 | 4.9453 |
| 4.0315 | 2.0916 | 20000 | 4.2325 |
| 3.5346 | 3.1374 | 30000 | 4.0580 |
| 3.0638 | 4.1832 | 40000 | 4.0786 |
| 2.5829 | 5.2290 | 50000 | 4.2447 |
| 2.0567 | 6.2749 | 60000 | 4.5287 |
| 1.5775 | 7.3207 | 70000 | 4.8806 |
| 1.169 | 8.3665 | 80000 | 5.2304 |
| 0.8676 | 9.4123 | 90000 | 5.4825 |
Framework versions
- Transformers 4.51.0
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- -