metadata
library_name: transformers
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-135M
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: desired_run
results: []
desired_run
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: 0.5396
- Accuracy: 0.9214
- F1: 0.9214
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 2.5858 | 1.0 | 313 | 0.5200 | 0.9184 | 0.9185 |
| 1.8127 | 2.0 | 626 | 0.5246 | 0.9179 | 0.9178 |
| 1.5712 | 3.0 | 939 | 0.5342 | 0.9188 | 0.9186 |
| 1.4496 | 4.0 | 1252 | 0.5358 | 0.9201 | 0.9200 |
| 1.4135 | 5.0 | 1565 | 0.5396 | 0.9214 | 0.9214 |
| 1.4042 | 6.0 | 1878 | 0.5420 | 0.92 | 0.9200 |
| 1.4004 | 7.0 | 2191 | 0.5407 | 0.9196 | 0.9195 |
| 1.3981 | 8.0 | 2504 | 0.5414 | 0.9207 | 0.9205 |
| 1.3969 | 9.0 | 2817 | 0.5413 | 0.92 | 0.9199 |
| 1.3957 | 10.0 | 3130 | 0.5419 | 0.9195 | 0.9193 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1