| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 30.0, | |
| "global_step": 17040, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.9413145539906104e-05, | |
| "loss": 0.1627, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.882629107981221e-05, | |
| "loss": 0.1324, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 1.8239436619718312e-05, | |
| "loss": 0.1168, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.7652582159624414e-05, | |
| "loss": 0.1056, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 1.706572769953052e-05, | |
| "loss": 0.0945, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 1.6478873239436623e-05, | |
| "loss": 0.0872, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 1.5892018779342725e-05, | |
| "loss": 0.0804, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 1.5305164319248827e-05, | |
| "loss": 0.0753, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 1.4718309859154931e-05, | |
| "loss": 0.0694, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 1.4131455399061034e-05, | |
| "loss": 0.065, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 1.3544600938967136e-05, | |
| "loss": 0.0606, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 1.2957746478873242e-05, | |
| "loss": 0.0587, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "learning_rate": 1.2370892018779344e-05, | |
| "loss": 0.0543, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 1.1784037558685446e-05, | |
| "loss": 0.052, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 1.119718309859155e-05, | |
| "loss": 0.0489, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 1.0610328638497653e-05, | |
| "loss": 0.0466, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 14.96, | |
| "learning_rate": 1.0023474178403755e-05, | |
| "loss": 0.0437, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 15.85, | |
| "learning_rate": 9.43661971830986e-06, | |
| "loss": 0.0416, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 16.73, | |
| "learning_rate": 8.849765258215963e-06, | |
| "loss": 0.0387, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 17.61, | |
| "learning_rate": 8.262910798122067e-06, | |
| "loss": 0.0371, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 18.49, | |
| "learning_rate": 7.67605633802817e-06, | |
| "loss": 0.0359, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 19.37, | |
| "learning_rate": 7.089201877934273e-06, | |
| "loss": 0.0334, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 20.25, | |
| "learning_rate": 6.502347417840375e-06, | |
| "loss": 0.0323, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 21.13, | |
| "learning_rate": 5.915492957746479e-06, | |
| "loss": 0.0309, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "learning_rate": 5.328638497652583e-06, | |
| "loss": 0.0294, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 22.89, | |
| "learning_rate": 4.741784037558686e-06, | |
| "loss": 0.0278, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 23.77, | |
| "learning_rate": 4.154929577464789e-06, | |
| "loss": 0.0266, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 24.65, | |
| "learning_rate": 3.568075117370892e-06, | |
| "loss": 0.0256, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 25.53, | |
| "learning_rate": 2.9812206572769952e-06, | |
| "loss": 0.0248, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 26.41, | |
| "learning_rate": 2.3943661971830984e-06, | |
| "loss": 0.024, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 27.29, | |
| "learning_rate": 1.807511737089202e-06, | |
| "loss": 0.0236, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 28.17, | |
| "learning_rate": 1.2206572769953053e-06, | |
| "loss": 0.0227, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 29.05, | |
| "learning_rate": 6.338028169014085e-07, | |
| "loss": 0.022, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 29.93, | |
| "learning_rate": 4.694835680751174e-08, | |
| "loss": 0.0219, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 17040, | |
| "total_flos": 3.651708270625563e+16, | |
| "train_loss": 0.05439845494960955, | |
| "train_runtime": 9683.1827, | |
| "train_samples_per_second": 112.509, | |
| "train_steps_per_second": 1.76 | |
| } | |
| ], | |
| "max_steps": 17040, | |
| "num_train_epochs": 30, | |
| "total_flos": 3.651708270625563e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |