Grogros-gpt2-kgw-k1-delta2.0-logitDistill-ft-OpenMathInstruct

This model is a fine-tuned version of Grogros/gpt2-kgw-k1-delta2.0-logitDistill on an unknown 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: 2e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 2500

Training results

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1.post302
• Datasets 3.0.1
• Tokenizers 0.20.1