3e503c6c-35e3-4e36-97fd-3ca1b6490aa2

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: 11.7886

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: 0.000212
• train_batch_size: 4
• eval_batch_size: 4
• seed: 120
• 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	0.0002	1	11.9334
11.8704	0.0082	50	11.8842
11.8571	0.0163	100	11.8636
11.8176	0.0245	150	11.8292
11.8139	0.0327	200	11.8095
11.8127	0.0408	250	11.7997
11.8078	0.0490	300	11.7957
11.7966	0.0572	350	11.7917
11.795	0.0653	400	11.7895
11.7874	0.0735	450	11.7888
11.7957	0.0817	500	11.7886

Framework versions

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