a0e58d38-9c0c-4c70-a915-2a7d7f329b1d

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2596

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: 0.00021
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0000	1	0.3769
0.2684	0.0011	50	0.3158
0.3281	0.0021	100	0.3241
0.3242	0.0032	150	0.3167
0.2813	0.0043	200	0.3057
0.2835	0.0053	250	0.2960
0.2907	0.0064	300	0.2850
0.2737	0.0075	350	0.2704
0.2648	0.0085	400	0.2633
0.2715	0.0096	450	0.2601
0.3065	0.0107	500	0.2596

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1