ab37478f-15bb-4d01-970f-78a9c6215753

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

• Loss: 2.7255

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: 0.000205
• train_batch_size: 4
• eval_batch_size: 4
• seed: 50
• 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	4.5647
3.2376	0.0023	50	3.3136
3.173	0.0045	100	3.0686
3.3612	0.0068	150	2.9804
3.3344	0.0090	200	2.9288
2.9887	0.0113	250	2.8600
3.2181	0.0135	300	2.8021
3.2327	0.0158	350	2.7587
3.1479	0.0181	400	2.7355
3.1241	0.0203	450	2.7267
2.8884	0.0226	500	2.7255

Framework versions

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