rauma-gpt-1.7B-Instruct
This model is a fine-tuned version of utter-project/EuroLLM-1.7B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1424
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9481 | 1.0 | 808 | 3.0060 |
| 1.994 | 2.0 | 1616 | 2.3556 |
| 1.1262 | 3.0 | 2424 | 2.1424 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1