| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9656004828002414, | |
| "eval_steps": 500, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9325842696629215e-05, | |
| "loss": 1.8646, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.8426966292134835e-05, | |
| "loss": 1.9283, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.752808988764045e-05, | |
| "loss": 1.9027, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.662921348314607e-05, | |
| "loss": 1.8583, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.5730337078651687e-05, | |
| "loss": 1.8618, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 1.4831460674157305e-05, | |
| "loss": 1.8233, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.3932584269662923e-05, | |
| "loss": 1.9046, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.303370786516854e-05, | |
| "loss": 1.8505, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.213483146067416e-05, | |
| "loss": 1.8608, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.1235955056179778e-05, | |
| "loss": 1.7992, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.0337078651685396e-05, | |
| "loss": 1.8869, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.438202247191012e-06, | |
| "loss": 1.839, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 8.53932584269663e-06, | |
| "loss": 1.8787, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 7.640449438202247e-06, | |
| "loss": 1.8828, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 6.741573033707865e-06, | |
| "loss": 1.8479, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 5.842696629213483e-06, | |
| "loss": 1.9063, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.943820224719101e-06, | |
| "loss": 1.8693, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.04494382022472e-06, | |
| "loss": 1.827, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 3.146067415730337e-06, | |
| "loss": 1.8259, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.2471910112359554e-06, | |
| "loss": 1.8419, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 450, | |
| "num_train_epochs": 2, | |
| "save_steps": 20, | |
| "total_flos": 2.786099516669952e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |