qwen3-8b-warmstart-single-prompt-elbow

This model is a fine-tuned version of Qwen/Qwen3-8B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8567

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-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_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: 100
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.6929	0.1859	50	1.6164
1.3221	0.3717	100	1.2740
0.9668	0.5576	150	0.9806
0.8472	0.7435	200	0.8678
0.824	0.9294	250	0.8567

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0+cu128
• Datasets 4.1.1
• Tokenizers 0.22.1