qwen3-2b-ablation-D-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: 0.6792

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
1.0412	0.2270	20	0.9469
0.9196	0.4539	40	0.8538
0.8432	0.6809	60	0.7962
0.8124	0.9078	80	0.7525
0.6393	1.1248	100	0.7276
0.5909	1.3518	120	0.7036
0.6028	1.5787	140	0.6869
0.5754	1.8057	160	0.6801
0.5752	2.0	178	0.6792

Framework versions

• Transformers 5.5.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.4
• Tokenizers 0.22.2