business-news-generator
This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5782
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1453 | 0.2667 | 2000 | 2.9693 |
| 2.8051 | 0.5333 | 4000 | 2.8105 |
| 2.6904 | 0.8 | 6000 | 2.7251 |
| 2.5723 | 1.0667 | 8000 | 2.6785 |
| 2.4023 | 1.3333 | 10000 | 2.6394 |
| 2.3717 | 1.6 | 12000 | 2.6095 |
| 2.3554 | 1.8667 | 14000 | 2.5820 |
| 2.2466 | 2.1333 | 16000 | 2.5917 |
| 2.1586 | 2.4 | 18000 | 2.5847 |
| 2.1441 | 2.6667 | 20000 | 2.5795 |
| 2.1513 | 2.9333 | 22000 | 2.5783 |
Framework versions
- Transformers 4.56.2
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1