| {"step": 620, "train_runtime": 0.0031, "train_samples_per_second": 12601132.816, "train_steps_per_second": 198191.333, "total_flos": 0.0, "train_loss": 0.0, "epoch": 20.0} | |
| {"step": 620, "train_runtime": 0.0149, "train_samples_per_second": 2648779.476, "train_steps_per_second": 41660.154, "total_flos": 0.0, "train_loss": 0.0, "epoch": 20.0} | |
| {"step": 620, "train_runtime": 0.0031, "train_samples_per_second": 12895988.119, "train_steps_per_second": 202828.834, "total_flos": 0.0, "train_loss": 0.0, "epoch": 20.0} | |
| {"step": 620, "train_runtime": 0.0024, "train_samples_per_second": 16349200.403, "train_steps_per_second": 257141.153, "total_flos": 0.0, "train_loss": 0.0, "epoch": 20.0} | |
| {"step": 620, "train_runtime": 0.0026, "train_samples_per_second": 15254125.259, "train_steps_per_second": 239917.749, "total_flos": 0.0, "train_loss": 0.0, "epoch": 20.0} | |
| {"step": 620, "train_runtime": 0.0149, "train_samples_per_second": 2640277.597, "train_steps_per_second": 41526.436, "total_flos": 0.0, "train_loss": 0.0, "epoch": 20.0} | |
| {"step": 620, "train_runtime": 0.0041, "train_samples_per_second": 9537898.107, "train_steps_per_second": 150012.603, "total_flos": 0.0, "train_loss": 0.0, "epoch": 20.0} | |
| {"step": 620, "train_runtime": 0.0049, "train_samples_per_second": 8070063.631, "train_steps_per_second": 126926.419, "total_flos": 0.0, "train_loss": 0.0, "epoch": 20.0} | |
| {"step": 620, "train_runtime": 0.0038, "train_samples_per_second": 10465847.809, "train_steps_per_second": 164607.449, "total_flos": 0.0, "train_loss": 0.0, "epoch": 20.0} | |
| {"step": 620, "train_runtime": 0.0232, "train_samples_per_second": 1697373.586, "train_steps_per_second": 26696.388, "total_flos": 0.0, "train_loss": 0.0, "epoch": 20.0} | |