| epoch = 3.0 | |
| train_loss = 0.616782742018053 | |
| train_runtime = 696.2812 | |
| train_samples = 7978 | |
| train_samples_per_second = 34.374 | |
| train_steps_per_second = 4.3 | |
| epoch = 3.0 | |
| train_loss = 0.616782742018053 | |
| train_runtime = 696.2812 | |
| train_samples = 7978 | |
| train_samples_per_second = 34.374 | |
| train_steps_per_second = 4.3 | |