KhoiBui/qwen2.5-math-1.5b-finetuned-vi

results

This model is a fine-tuned version of Qwen/Qwen2.5-Math-1.5B on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.4586
• eval_runtime: 1359.1386
• eval_samples_per_second: 29.063
• eval_steps_per_second: 3.633
• epoch: 1.4402
• step: 8000

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: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 2

Framework versions

• PEFT 0.17.1
• Transformers 4.57.1
• Pytorch 2.9.0+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1