{'train_runtime': 1470.1893, 'train_samples_per_second': 17.413, 'train_steps_per_second': 0.068, 'total_flos': 2.2273992454832128e+18, 'train_loss': 1.309400005340576, 'epoch': 0.9864364981504316} |
{'train_runtime': 1470.1893, 'train_samples_per_second': 17.413, 'train_steps_per_second': 0.068, 'total_flos': 2.2273992454832128e+18, 'train_loss': 1.309400005340576, 'epoch': 0.9864364981504316} |