e09736da-0f07-4c50-9194-576480ad71c6
This model is a fine-tuned version of TitanML/tiny-mixtral on the None dataset. It achieves the following results on the evaluation set:
- Loss: 7.5590
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: 0.000217
- train_batch_size: 4
- eval_batch_size: 4
- seed: 170
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0005 | 1 | 10.5960 |
| 8.8231 | 0.0260 | 50 | 9.0441 |
| 8.5389 | 0.0521 | 100 | 8.7888 |
| 8.2707 | 0.0781 | 150 | 8.5514 |
| 8.0217 | 0.1042 | 200 | 8.2811 |
| 7.7506 | 0.1302 | 250 | 8.0106 |
| 7.2649 | 0.1562 | 300 | 7.7972 |
| 7.1247 | 0.1823 | 350 | 7.6784 |
| 7.334 | 0.2083 | 400 | 7.5868 |
| 7.1146 | 0.2344 | 450 | 7.5549 |
| 7.3558 | 0.2604 | 500 | 7.5590 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 10
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for lesso17/e09736da-0f07-4c50-9194-576480ad71c6
Base model
TitanML/tiny-mixtral