| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9993890198132146, | |
| "eval_steps": 500, | |
| "global_step": 11450, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 9.563585580867592e-05, | |
| "loss": 0.3428, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.127171161735184e-05, | |
| "loss": 0.237, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 8.690756742602775e-05, | |
| "loss": 0.227, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 8.254342323470367e-05, | |
| "loss": 0.2196, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 7.817927904337959e-05, | |
| "loss": 0.213, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.381513485205552e-05, | |
| "loss": 0.2091, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.945099066073143e-05, | |
| "loss": 0.2098, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 6.508684646940735e-05, | |
| "loss": 0.2039, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 6.072270227808327e-05, | |
| "loss": 0.2036, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5.63585580867592e-05, | |
| "loss": 0.2022, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 5.1994413895435114e-05, | |
| "loss": 0.2029, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.7630269704111024e-05, | |
| "loss": 0.2007, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.326612551278694e-05, | |
| "loss": 0.1984, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.8901981321462864e-05, | |
| "loss": 0.1984, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.453783713013879e-05, | |
| "loss": 0.1986, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.01736929388147e-05, | |
| "loss": 0.1948, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.580954874749062e-05, | |
| "loss": 0.1941, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2.1445404556166537e-05, | |
| "loss": 0.1955, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.7081260364842456e-05, | |
| "loss": 0.1955, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.2717116173518373e-05, | |
| "loss": 0.1949, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 8.352971982194293e-06, | |
| "loss": 0.1951, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.988827790870211e-06, | |
| "loss": 0.1956, | |
| "step": 11000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 11457, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "total_flos": 1.23973090148352e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |