metadata
library_name: transformers
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-135M
tags:
- generated_from_trainer
model-index:
- name: business-news-generator-v4
results: []
business-news-generator-v4
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: 2.4468
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: 0.0004
- train_batch_size: 32
- 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.721 | 0.1066 | 100 | 2.5413 |
| 1.7099 | 0.2132 | 200 | 2.5191 |
| 1.7419 | 0.3198 | 300 | 2.5133 |
| 1.7112 | 0.4264 | 400 | 2.4781 |
| 1.7117 | 0.5330 | 500 | 2.4521 |
| 1.7492 | 0.6397 | 600 | 2.4189 |
| 1.691 | 0.7463 | 700 | 2.3948 |
| 1.6631 | 0.8529 | 800 | 2.3661 |
| 1.6642 | 0.9595 | 900 | 2.3370 |
| 1.2417 | 1.0661 | 1000 | 2.4726 |
| 0.9986 | 1.1727 | 1100 | 2.4814 |
| 0.9757 | 1.2793 | 1200 | 2.4765 |
| 0.9743 | 1.3859 | 1300 | 2.4615 |
| 0.9819 | 1.4925 | 1400 | 2.4594 |
| 0.9739 | 1.5991 | 1500 | 2.4506 |
| 0.9461 | 1.7058 | 1600 | 2.4477 |
| 0.9671 | 1.8124 | 1700 | 2.4458 |
| 0.9275 | 1.9190 | 1800 | 2.4468 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1