c59d1e50-0487-41bd-aa3d-6059dd63476e

This model is a fine-tuned version of Qwen/Qwen2.5-3B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2036

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: 0.000211
• train_batch_size: 4
• eval_batch_size: 4
• seed: 110
• 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	0.0001	1	0.5860
0.4108	0.0028	50	0.3611
0.3546	0.0055	100	0.4033
0.3824	0.0083	150	0.4016
0.3648	0.0111	200	0.2959
0.3564	0.0138	250	0.2622
0.3122	0.0166	300	0.2350
0.2545	0.0194	350	0.2235
0.2724	0.0221	400	0.2101
0.3281	0.0249	450	0.2047
0.281	0.0277	500	0.2036

Framework versions

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