{'train_runtime': 1463.2595, 'train_samples_per_second': 17.495, 'train_steps_per_second': 0.068, 'total_flos': 2.2273992454832128e+18, 'train_loss': 2.4370877647399904, 'epoch': 0.3714020427112349} |
{'train_runtime': 1463.2595, 'train_samples_per_second': 17.495, 'train_steps_per_second': 0.068, 'total_flos': 2.2273992454832128e+18, 'train_loss': 2.4370877647399904, 'epoch': 0.3714020427112349} |