eb4538e8-4f9a-4e8f-a703-84f7a3ff2d29

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

• Loss: 2.4215

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	0.0003	1	2.9154
2.3769	0.0174	50	2.5811
2.5278	0.0348	100	2.5295
2.441	0.0523	150	2.5220
2.3443	0.0697	200	2.4987
2.3729	0.0871	250	2.4651
2.378	0.1045	300	2.4467
2.3093	0.1219	350	2.4346
2.4795	0.1393	400	2.4266
2.323	0.1568	450	2.4221
2.3047	0.1742	500	2.4215

Framework versions

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