SmolLM-135M-Instruct-lora-text-classification

This model is a fine-tuned version of HuggingFaceTB/SmolLM-135M-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6511
• Accuracy: {'accuracy': 0.923}

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: 0.001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	250	0.2663	{'accuracy': 0.909}
0.3466	2.0	500	0.3337	{'accuracy': 0.92}
0.3466	3.0	750	0.7002	{'accuracy': 0.9}
0.0511	4.0	1000	0.6349	{'accuracy': 0.92}
0.0511	5.0	1250	0.6064	{'accuracy': 0.929}
0.0008	6.0	1500	0.6528	{'accuracy': 0.921}
0.0008	7.0	1750	0.6513	{'accuracy': 0.921}
0.0	8.0	2000	0.6510	{'accuracy': 0.921}
0.0	9.0	2250	0.6511	{'accuracy': 0.923}
0.0	10.0	2500	0.6511	{'accuracy': 0.923}

Framework versions

• PEFT 0.14.0
• Transformers 4.48.0
• Pytorch 2.5.1+cpu
• Datasets 3.2.0
• Tokenizers 0.21.0