qwen3-2b-ablation-A-multi-answer

This model is a fine-tuned version of Qwen/Qwen3-2B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8505

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 46
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• 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: linear
• lr_scheduler_warmup_steps: 0.03
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.9733	0.8889	20	0.9032
0.6871	1.7556	40	0.8520
0.6871	2.0	46	0.8505

Framework versions

• Transformers 5.4.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.4
• Tokenizers 0.22.2