Mdist_8B_SelfDistill_Chem_from_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. -->

aligned_5w_data_from_upsampled_M0_Qwen3-8B_upsampled_50k_all_subtasks_cutoff16384_20260314_004828

This model is a fine-tuned version of Qwen/Qwen3-8B on the aligned_5w_data_from_upsampled_M0_Qwen3-8B_upsampled_50k_all_subtasks 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
• 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=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine_with_min_lr
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 1.0

Training results

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.0