484a2597-3c72-457d-b7a1-01d08fc41818

This model is a fine-tuned version of katuni4ka/tiny-random-qwen1.5-moe on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.4863

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: 0.000204
• 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	11.8944
11.7364	0.0019	50	11.6697
11.7074	0.0039	100	11.5738
11.6798	0.0058	150	11.5285
11.6493	0.0078	200	11.5162
11.6444	0.0097	250	11.5060
11.6264	0.0117	300	11.4972
11.6124	0.0136	350	11.4911
11.6075	0.0156	400	11.4874
11.6008	0.0175	450	11.4864
11.5967	0.0194	500	11.4863

Framework versions

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