| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 5350, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 9.065420560747664e-06, | |
| "loss": 318405.12, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 8.130841121495327e-06, | |
| "loss": 0.5212, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 7.196261682242991e-06, | |
| "loss": 0.7034, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 6.2616822429906544e-06, | |
| "loss": 0.4659, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.67, | |
| "learning_rate": 5.3271028037383174e-06, | |
| "loss": 0.346, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 4.392523364485981e-06, | |
| "loss": 0.3146, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 3.457943925233645e-06, | |
| "loss": 0.2947, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "learning_rate": 2.5233644859813085e-06, | |
| "loss": 0.343, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 8.41, | |
| "learning_rate": 1.588785046728972e-06, | |
| "loss": 0.3041, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 6.542056074766355e-07, | |
| "loss": 0.2609, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 5350, | |
| "total_flos": 1340551406822400.0, | |
| "train_loss": 29757.83613023134, | |
| "train_runtime": 2069.8226, | |
| "train_samples_per_second": 41.313, | |
| "train_steps_per_second": 2.585 | |
| } | |
| ], | |
| "max_steps": 5350, | |
| "num_train_epochs": 10, | |
| "total_flos": 1340551406822400.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |