| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7599361653621096, | |
| "global_step": 10000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.810015958659473e-05, | |
| "loss": 7.3864, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.6200319173189456e-05, | |
| "loss": 6.8171, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.430047875978418e-05, | |
| "loss": 6.6465, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.240063834637891e-05, | |
| "loss": 6.5187, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.050079793297363e-05, | |
| "loss": 6.4542, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.860095751956836e-05, | |
| "loss": 6.392, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.6701117106163084e-05, | |
| "loss": 6.2944, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.480127669275781e-05, | |
| "loss": 6.1424, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.290143627935254e-05, | |
| "loss": 6.1603, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.1001595865947265e-05, | |
| "loss": 6.0149, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.910175545254199e-05, | |
| "loss": 5.9559, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.7201915039136716e-05, | |
| "loss": 5.8511, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5302074625731443e-05, | |
| "loss": 5.8782, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3402234212326166e-05, | |
| "loss": 5.8042, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.1502393798920893e-05, | |
| "loss": 5.7415, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9602553385515617e-05, | |
| "loss": 5.6506, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7702712972110344e-05, | |
| "loss": 5.699, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.580287255870507e-05, | |
| "loss": 5.627, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.3903032145299796e-05, | |
| "loss": 5.615, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2003191731894521e-05, | |
| "loss": 5.4553, | |
| "step": 10000 | |
| } | |
| ], | |
| "max_steps": 13159, | |
| "num_train_epochs": 1, | |
| "total_flos": 1084338745132032.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |