25cadc3c-ac7e-4bda-b89a-9557c9c25363

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: 11.6837

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: 0.000208
• train_batch_size: 4
• eval_batch_size: 4
• seed: 80
• 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	11.9445
11.9011	0.0100	50	11.8831
11.8342	0.0200	100	11.8398
11.7711	0.0299	150	11.7947
11.653	0.0399	200	11.7309
11.5869	0.0499	250	11.7058
11.5578	0.0599	300	11.6941
11.555	0.0699	350	11.6881
11.5242	0.0798	400	11.6847
11.4812	0.0898	450	11.6838
11.5104	0.0998	500	11.6837

Framework versions

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