2.0 KiB
2.0 KiB
library_name, license, base_model, tags, model-index
| library_name | license | base_model | tags | model-index | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
| transformers | apache-2.0 | HuggingFaceTB/SmolLM2-135M |
|
|
v5SmolLM2-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: 3.0644
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-06
- train_batch_size: 8
- 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
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.6465 | 0.08 | 100 | 3.4739 |
| 3.3588 | 0.16 | 200 | 3.3058 |
| 3.2424 | 0.24 | 300 | 3.2164 |
| 3.1289 | 0.32 | 400 | 3.1625 |
| 3.0872 | 0.4 | 500 | 3.1281 |
| 3.0701 | 0.48 | 600 | 3.1049 |
| 3.0425 | 0.56 | 700 | 3.0895 |
| 3.101 | 0.64 | 800 | 3.0783 |
| 2.9676 | 0.72 | 900 | 3.0710 |
| 3.0192 | 0.8 | 1000 | 3.0668 |
| 2.9593 | 0.88 | 1100 | 3.0648 |
| 2.9943 | 0.96 | 1200 | 3.0644 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1