deqing/llama_3.2_1b_megamath_fourier_full_2025_05_02

llama_3.2_1b_megamath_full_2025_05_02

This model is a fine-tuned version of llama-3.2-1B on MegaMath's Web-Pro subset with 15.1B tokens.

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-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 6 (A6000)
• gradient_accumulation_steps: 16
• total_train_batch_size: 96
• total_eval_batch_size: 48
• 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_steps: 500
• num_epochs: 1
• context_length: 4096

Training results

Framework versions

• Transformers 4.51.3
• Pytorch 2.3.1+cu118
• Datasets 3.5.0
• Tokenizers 0.21.0