amd/zebra_qwen3_7MLA21GDN_noT_SFT_1M_combined_fCE

<!-- 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. -->

zebraqwen37MLA21GDNnoTSFT1Mcombined_fCE

This model is a fine-tuned version of Qwen/Qwen3-1.7B on the JunxiongWang/sftdatasetv3, the amd/OpenMathInstruct-2ZebraLlama2M, the amd/ZebraLlamaOpenThoughts-114k-math, the amd/OpenR1-Math-220K and the amd/ZebraLlamaChatQA2-Long-SFTlongsft_QA 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: 6e-05
• —trainbatchsize: 2
• —evalbatchsize: 1
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —totaltrainbatch_size: 16
• —totalevalbatch_size: 8
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 200
• —num_epochs: 1

Training results

Framework versions

• —Transformers 4.52.4
• —Pytorch 2.10.0.dev20251112+rocm7.1
• —Datasets 3.6.0
• —Tokenizers 0.21.4