You can deploy this model and start earning money today!

RefalMachine/
ruadapt_qwen2.5_3B_unigram_32000_full_lr3e4_bs256

Name: ruadapt_qwen2.5_3B_unigram_32000_full_lr3e4_bs256
Availability: InStock

Views

No views yet

ruadapt_qwen2.5_3B_unigram_32000_full_lr3e4_bs256

This model is a fine-tuned version of RefalMachine/ruadapt_qwen2.5_3B_unigram_32000_mean_init on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.0	1	5.7145	0.1757
2.4952	0.16	2000	2.3789	0.5099
2.4744	0.32	4000	2.3542	0.5130
2.4546	0.48	6000	2.3463	0.5138
2.4433	0.64	8000	2.3432	0.5144
2.4458	0.8	10000	2.3423	0.5144
2.4381	0.96	12000	2.3422	0.5145