metadata
library_name: transformers
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-135M
tags:
- generated_from_trainer
model-index:
- name: smollm2_desired
results: []
smollm2_desired
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: 2.8833
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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: 0.05
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.3819 | 0.32 | 200 | 3.1110 |
| 2.9887 | 0.64 | 400 | 2.9821 |
| 2.8406 | 0.96 | 600 | 2.9237 |
| 2.7739 | 1.28 | 800 | 2.8974 |
| 2.7301 | 1.6 | 1000 | 2.8859 |
| 2.7242 | 1.92 | 1200 | 2.8833 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.2.0
- Tokenizers 0.22.1