fine_tuned_per_domain_balanced_moe

This model is a fine-tuned version of Qwen/Qwen1.5-MoE-A2.7B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.8781
• Accuracy: 0.5357

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
5.4785	0.0006	100	6.6629	0.5689
4.8644	0.0013	200	10.6619	0.5316
4.5014	0.0019	300	3.0574	0.5299
3.3262	0.0025	400	3.2657	0.4643
2.7274	0.0032	500	2.0543	0.5314
2.3305	0.0038	600	1.9673	0.4682
2.4483	0.0044	700	2.7203	0.5357
3.201	0.0051	800	3.5143	0.5357
2.8675	0.0057	900	2.8781	0.5357

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu126
• Datasets 3.3.2
• Tokenizers 0.21.0