knowledge-distilled-sm-smolm-135m-instruct-tm-smolm-360m-instruct

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M-Instruct on the None dataset.

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 galore_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.01
• lr_scheduler_warmup_steps: 2502
• training_steps: 50

Training results

Framework versions

• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.0.0
• Tokenizers 0.21.0