pszemraj
/

griffin-1024-llama3t-8layer-simplewiki-silu

Text Generation

recurrent_gemma

generated_from_trainer

Inference Endpoints

Model card Files Files and versions Community

griffin-1024-llama3t-8layer-simplewiki-silu / train_results.json

pszemraj's picture

End of training

adf1478 verified about 1 month ago

raw history blame contribute delete

No virus

249 Bytes

	{
	"epoch": 1.995634549423137,
	"total_flos": 6.441101073108173e+16,
	"train_loss": 8.280340445041656,
	"train_runtime": 18888.2342,
	"train_samples": 51310,
	"train_samples_per_second": 5.433,
	"train_steps_per_second": 0.042
	}