fine_tuned_per_domain_balanced_moe_lr

This model is a fine-tuned version of Qwen/Qwen1.5-MoE-A2.7B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6637
• Accuracy: 0.8800

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: 5e-06
• 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.2077	0.0029	500	1.9021	0.8317
0.9585	0.0057	1000	2.2812	0.8299
1.479	0.0086	1500	1.5268	0.8066
1.1161	0.0114	2000	0.9974	0.8550
0.8147	0.0143	2500	0.6406	0.8926
1.4377	0.0172	3000	1.5956	0.8156
0.6541	0.0200	3500	0.9456	0.8720
0.9445	0.0229	4000	0.6637	0.8800

Framework versions

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