| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 16370, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.938912645082468e-05, | |
| "loss": 0.436, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.8778252901649362e-05, | |
| "loss": 0.3499, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.816737935247404e-05, | |
| "loss": 0.3294, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.755650580329872e-05, | |
| "loss": 0.3049, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.69456322541234e-05, | |
| "loss": 0.3031, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.6334758704948076e-05, | |
| "loss": 0.2854, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 1.5723885155772757e-05, | |
| "loss": 0.2433, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.5113011606597437e-05, | |
| "loss": 0.1896, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 1.4502138057422115e-05, | |
| "loss": 0.1873, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 1.3891264508246794e-05, | |
| "loss": 0.1893, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 1.3280390959071474e-05, | |
| "loss": 0.1914, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.2669517409896153e-05, | |
| "loss": 0.1888, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.2058643860720831e-05, | |
| "loss": 0.1822, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.1447770311545512e-05, | |
| "loss": 0.1094, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.083689676237019e-05, | |
| "loss": 0.115, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 1.0226023213194869e-05, | |
| "loss": 0.1123, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 9.615149664019549e-06, | |
| "loss": 0.1135, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 9.004276114844227e-06, | |
| "loss": 0.1155, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 8.393402565668908e-06, | |
| "loss": 0.1159, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.782529016493586e-06, | |
| "loss": 0.098, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.171655467318266e-06, | |
| "loss": 0.0701, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 6.560781918142944e-06, | |
| "loss": 0.071, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 5.949908368967624e-06, | |
| "loss": 0.0745, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 5.339034819792304e-06, | |
| "loss": 0.0659, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 4.728161270616982e-06, | |
| "loss": 0.0704, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 4.117287721441662e-06, | |
| "loss": 0.0675, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 3.506414172266341e-06, | |
| "loss": 0.0456, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 2.8955406230910206e-06, | |
| "loss": 0.0449, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 2.2846670739156996e-06, | |
| "loss": 0.0383, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 1.6737935247403788e-06, | |
| "loss": 0.0416, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 1.0629199755650582e-06, | |
| "loss": 0.0476, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 4.5204642638973736e-07, | |
| "loss": 0.0403, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 16370, | |
| "total_flos": 3.44488015894656e+16, | |
| "train_loss": 0.14878162798826186, | |
| "train_runtime": 9315.5537, | |
| "train_samples_per_second": 56.219, | |
| "train_steps_per_second": 1.757 | |
| } | |
| ], | |
| "max_steps": 16370, | |
| "num_train_epochs": 5, | |
| "total_flos": 3.44488015894656e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |