| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 10023, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.75057368053477e-05, | |
| "loss": 3.0513, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.501147361069541e-05, | |
| "loss": 2.9178, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.25172104160431e-05, | |
| "loss": 2.7984, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.0022947221390805e-05, | |
| "loss": 2.7266, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3.75286840267385e-05, | |
| "loss": 2.6317, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.50344208320862e-05, | |
| "loss": 2.5775, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.2540157637433905e-05, | |
| "loss": 2.3763, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 3.00458944427816e-05, | |
| "loss": 2.0984, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 2.7551631248129307e-05, | |
| "loss": 2.0372, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.5057368053477002e-05, | |
| "loss": 1.9558, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.2563104858824705e-05, | |
| "loss": 1.9287, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.0068841664172404e-05, | |
| "loss": 1.8788, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.7574578469520103e-05, | |
| "loss": 1.828, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.5080315274867803e-05, | |
| "loss": 1.5557, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.2586052080215504e-05, | |
| "loss": 1.3987, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.0091788885563205e-05, | |
| "loss": 1.3584, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.597525690910905e-06, | |
| "loss": 1.3404, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 5.103262496258605e-06, | |
| "loss": 1.3025, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.6089993016063056e-06, | |
| "loss": 1.2926, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.147361069540058e-07, | |
| "loss": 1.2727, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 10023, | |
| "total_flos": 1.5233919932694528e+16, | |
| "train_loss": 2.0144441036196583, | |
| "train_runtime": 7319.7453, | |
| "train_samples_per_second": 2.739, | |
| "train_steps_per_second": 1.369 | |
| } | |
| ], | |
| "max_steps": 10023, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.5233919932694528e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |