| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 45.45454545454545, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 3e-06, | |
| "loss": 7.7644, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 6e-06, | |
| "loss": 4.0219, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 9e-06, | |
| "loss": 2.3865, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 9.09, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.0278, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.8286, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.721, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 15.91, | |
| "learning_rate": 2.1e-05, | |
| "loss": 1.6587, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 18.18, | |
| "learning_rate": 2.4e-05, | |
| "loss": 1.6102, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 20.45, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 1.5738, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 22.73, | |
| "learning_rate": 3e-05, | |
| "loss": 1.5536, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 2.911764705882353e-05, | |
| "loss": 1.5398, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 27.27, | |
| "learning_rate": 2.823529411764706e-05, | |
| "loss": 1.5346, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 29.55, | |
| "learning_rate": 2.735294117647059e-05, | |
| "loss": 1.5068, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 31.82, | |
| "learning_rate": 2.647058823529412e-05, | |
| "loss": 1.5084, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 34.09, | |
| "learning_rate": 2.5588235294117648e-05, | |
| "loss": 1.497, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 36.36, | |
| "learning_rate": 2.4705882352941174e-05, | |
| "loss": 1.4906, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 38.64, | |
| "learning_rate": 2.3823529411764704e-05, | |
| "loss": 1.4887, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 40.91, | |
| "learning_rate": 2.2941176470588233e-05, | |
| "loss": 1.4765, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 43.18, | |
| "learning_rate": 2.2058823529411766e-05, | |
| "loss": 1.4792, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 45.45, | |
| "learning_rate": 2.1176470588235296e-05, | |
| "loss": 1.473, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 2200, | |
| "num_train_epochs": 100, | |
| "total_flos": 2356631411097600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |