75934fce-c53d-4ed4-a8b8-ce30644d4408

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1964

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: 0.000208
• 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: 483

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0021	1	1.8547
0.5027	0.1035	50	0.2691
0.3573	0.2070	100	0.2200
0.3111	0.3106	150	0.2220
0.4188	0.4141	200	0.2153
0.2728	0.5176	250	0.2107
0.2365	0.6211	300	0.2101
0.2971	0.7246	350	0.2001
0.3151	0.8282	400	0.1974
0.3327	0.9317	450	0.1964

Framework versions

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