| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.17021131735049064, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00014999965456413008, | |
| "loss": 0.6484, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001499986182599296, | |
| "loss": 0.5436, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00014999689109762647, | |
| "loss": 0.5149, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00014999447309426713, | |
| "loss": 0.4996, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00014999136427371623, | |
| "loss": 0.4888, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001499875646666566, | |
| "loss": 0.4797, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00014998307431058887, | |
| "loss": 0.4711, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00014997789324983099, | |
| "loss": 0.463, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00014997202153551792, | |
| "loss": 0.4545, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001499654592256012, | |
| "loss": 0.4466, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001499582063848481, | |
| "loss": 0.4398, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00014995026308484122, | |
| "loss": 0.4337, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00014994162940397778, | |
| "loss": 0.4286, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00014993230542746872, | |
| "loss": 0.4242, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00014992229124733788, | |
| "loss": 0.4203, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001499115869624212, | |
| "loss": 0.4173, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00014990019267836565, | |
| "loss": 0.4141, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00014988810850762824, | |
| "loss": 0.4116, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00014987533456947482, | |
| "loss": 0.4095, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.000149861870989979, | |
| "loss": 0.4075, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 500000, | |
| "num_train_epochs": 9, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |