| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 9657, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7411204307756033e-05, | |
| "loss": 2.5878, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.482240861551207e-05, | |
| "loss": 2.154, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.2233612923268096e-05, | |
| "loss": 1.9897, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 3.964481723102413e-05, | |
| "loss": 1.8927, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.7056021538780165e-05, | |
| "loss": 1.8394, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.4467225846536196e-05, | |
| "loss": 1.7611, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.187843015429223e-05, | |
| "loss": 1.5853, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 2.9289634462048254e-05, | |
| "loss": 1.4947, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.670083876980429e-05, | |
| "loss": 1.4477, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.411204307756032e-05, | |
| "loss": 1.4387, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.1523247385316354e-05, | |
| "loss": 1.4138, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.8934451693072382e-05, | |
| "loss": 1.4123, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 1.6345656000828417e-05, | |
| "loss": 1.359, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.3756860308584446e-05, | |
| "loss": 1.1492, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.1168064616340479e-05, | |
| "loss": 1.1347, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 8.57926892409651e-06, | |
| "loss": 1.1461, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 5.9904732318525425e-06, | |
| "loss": 1.1333, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.401677539608574e-06, | |
| "loss": 1.1301, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 8.12881847364606e-07, | |
| "loss": 1.0956, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 9657, | |
| "total_flos": 2.193258684727296e+16, | |
| "train_loss": 1.5281119021221854, | |
| "train_runtime": 2883.5293, | |
| "train_samples_per_second": 33.483, | |
| "train_steps_per_second": 3.349 | |
| } | |
| ], | |
| "max_steps": 9657, | |
| "num_train_epochs": 3, | |
| "total_flos": 2.193258684727296e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |