silx-ai
/

Quasar-2.5-7B-Pro

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Quasar-2.5-7B-Pro / train_results.json

eyad-silx's picture

Model save

d5f4350 verified 16 days ago

213 Bytes

	{
	"total_flos": 120709586092032.0,
	"train_loss": 0.5114190966404718,
	"train_runtime": 2623.0811,
	"train_samples": 10000,
	"train_samples_per_second": 5.684,
	"train_steps_per_second": 0.044
	}