Qwen2-0.5B-SFT

This model is a fine-tuned version of Qwen/Qwen2-0.5B on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 1.5691

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: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.6625	0.1081	100	1.6427
1.5916	0.2162	200	1.6277
1.584	0.3242	300	1.6156
1.5852	0.4323	400	1.6043
1.6071	0.5404	500	1.5959
1.5758	0.6485	600	1.5859
1.5518	0.7566	700	1.5786
1.5974	0.8646	800	1.5724
1.5532	0.9727	900	1.5691

Framework versions

• Transformers 4.46.2
• Pytorch 2.4.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3