Llama-3.2-1B-Instruct-sft_metamath

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Llama-3.2-1B-Instruct-sft_metamath

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the gohsyi/metamath-sft dataset. It achieves the following results on the evaluation set:

• Loss: 0.4330
• Accuracy: 0.8815

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: 1e-05
• train_batch_size: 14
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• gradient_accumulation_steps: 16
• total_train_batch_size: 448
• total_eval_batch_size: 16
• optimizer: Use adamw_torch 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: 0.1
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.46.2
• Pytorch 2.3.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3