| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4353125544140693, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00010077567264729574, | |
| "loss": 0.5253, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00010075889723559493, | |
| "loss": 0.5001, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00010073092788158004, | |
| "loss": 0.4909, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00010069177148627061, | |
| "loss": 0.4848, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001006414377109213, | |
| "loss": 0.4811, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00010057993897463803, | |
| "loss": 0.4761, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00010050729045131372, | |
| "loss": 0.4736, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00010042351006588448, | |
| "loss": 0.4712, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00010032861848990674, | |
| "loss": 0.4694, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00010022263913645699, | |
| "loss": 0.4675, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.4460357427597046, | |
| "eval_runtime": 24.6462, | |
| "eval_samples_per_second": 202.871, | |
| "eval_steps_per_second": 3.205, | |
| "step": 5000 | |
| } | |
| ], | |
| "max_steps": 100000, | |
| "num_train_epochs": 9, | |
| "total_flos": 2.354930673647616e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |