library_name, license, base_model, tags, model-index

library_name	license	base_model	tags	model-index
transformers	apache-2.0	Qwen/Qwen3-1.7B	llama-factory full generated_from_trainer	name results qwen3-1.7b-fft-math

qwen3-1.7b-fft-math

This model is a fine-tuned version of Qwen/Qwen3-1.7B on the mft_metamath, the mft_numinamath_tir, the mft_numinamath_cot, the mft_tulu3_personas_math, the mft_tulu3_personas_math_grade and the mft_tulu3_personas_algebra datasets.

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: 2
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• total_eval_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 0.1
• num_epochs: 2.0

Training results

Framework versions

• Transformers 5.2.0
• Pytorch 2.10.0+cu130
• Datasets 4.0.0
• Tokenizers 0.22.2