| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 3159, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4748338081671415, | |
| "learning_rate": 1.6834441278885725e-05, | |
| "loss": 0.2771715087890625, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.949667616334283, | |
| "learning_rate": 1.3668882557771448e-05, | |
| "loss": 0.17857017517089843, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.4245014245014245, | |
| "learning_rate": 1.0503323836657171e-05, | |
| "loss": 0.1144794921875, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.899335232668566, | |
| "learning_rate": 7.337765115542894e-06, | |
| "loss": 0.11068717193603515, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.3741690408357075, | |
| "learning_rate": 4.172206394428617e-06, | |
| "loss": 0.08253809356689454, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.849002849002849, | |
| "learning_rate": 1.00664767331434e-06, | |
| "loss": 0.07098492431640625, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 3159, | |
| "train_runtime": 488.8595, | |
| "train_samples_per_second": 6.462 | |
| } | |
| ], | |
| "max_steps": 3159, | |
| "num_train_epochs": 3, | |
| "total_flos": 16806970579253760, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |