Text Generation
Transformers
Safetensors
English
mega
Generated from Trainer
Inference Endpoints
mega-ar-350m-v0.13 / train_results.json
pszemraj's picture
End of training
26fd756 verified
{
"epoch": 0.9999893708612791,
"num_input_tokens_seen": 3468165120,
"total_flos": 4.540784328132526e+18,
"train_loss": 2.065564124978859,
"train_runtime": 98524.0638,
"train_samples": 846729,
"train_samples_per_second": 8.594,
"train_steps_per_second": 0.09
}