smollm2-1.7B-oh-dcft

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-1.7B on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini 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: 5e-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 32
• total_train_batch_size: 512
• total_eval_batch_size: 256
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.48.0
• Pytorch 2.5.0a0+b465a5843b.nv24.09
• Datasets 3.0.2
• Tokenizers 0.21.1