hahayhe/ToolSpace-Full-SFT-Qwen3-8B

<!-- 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. -->

toolspacedapomath_sft

This model is a fine-tuned version of /inspire/hdd/global_user/baoyu-253108120126/models/Qwen3-8B on the toolspacedapomath_sft 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: 1e-05
• —trainbatchsize: 2
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 64
• —totalevalbatch_size: 32
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 3

Training results

Framework versions

• —Transformers 4.57.1
• —Pytorch 2.6.0+cu124
• —Datasets 4.0.0
• —Tokenizers 0.22.2