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. -->

zebra_qwen3_7MLA21GDN_noT_SFT_1M_combined_fCE

This model is a fine-tuned version of Qwen/Qwen3-1.7B on the JunxiongWang/sftdatasetv3, the amd/OpenMathInstruct-2_ZebraLlama_2M, the amd/Zebra_Llama_OpenThoughts-114k-math, the amd/OpenR1-Math-220K and the amd/Zebra_Llama_ChatQA2-Long-SFT_long_sft_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
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 16
• total_eval_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_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