| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 375, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.03799356892704964, | |
| "learning_rate": 0.00019783783783783784, | |
| "loss": 0.0301, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.02971748076379299, | |
| "learning_rate": 0.00019243243243243245, | |
| "loss": 0.0302, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.05119084566831589, | |
| "learning_rate": 0.00018702702702702703, | |
| "loss": 0.0307, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.05611675605177879, | |
| "learning_rate": 0.00018162162162162164, | |
| "loss": 0.0304, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.045043572783470154, | |
| "learning_rate": 0.00017621621621621622, | |
| "loss": 0.0327, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.06347468495368958, | |
| "learning_rate": 0.00017081081081081083, | |
| "loss": 0.0325, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.04858771339058876, | |
| "learning_rate": 0.0001654054054054054, | |
| "loss": 0.0304, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.047175925225019455, | |
| "learning_rate": 0.00016, | |
| "loss": 0.032, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.04721968621015549, | |
| "learning_rate": 0.0001545945945945946, | |
| "loss": 0.0306, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.0320628359913826, | |
| "learning_rate": 0.0001491891891891892, | |
| "loss": 0.0318, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.030629610642790794, | |
| "learning_rate": 0.00014378378378378378, | |
| "loss": 0.0311, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.02791382186114788, | |
| "learning_rate": 0.0001383783783783784, | |
| "loss": 0.031, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 0.03312250226736069, | |
| "learning_rate": 0.00013297297297297297, | |
| "loss": 0.0302, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 0.04184908792376518, | |
| "learning_rate": 0.00012756756756756758, | |
| "loss": 0.0304, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.038243941962718964, | |
| "learning_rate": 0.00012216216216216216, | |
| "loss": 0.0305, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 0.024454083293676376, | |
| "learning_rate": 0.00011675675675675676, | |
| "loss": 0.0307, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 0.021402811631560326, | |
| "learning_rate": 0.00011135135135135135, | |
| "loss": 0.0303, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.030341940000653267, | |
| "learning_rate": 0.00010594594594594595, | |
| "loss": 0.0309, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 0.030703404918313026, | |
| "learning_rate": 0.00010054054054054053, | |
| "loss": 0.0299, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.03214750811457634, | |
| "learning_rate": 9.513513513513514e-05, | |
| "loss": 0.0308, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 0.04272659495472908, | |
| "learning_rate": 8.972972972972973e-05, | |
| "loss": 0.0295, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 0.024962130934000015, | |
| "learning_rate": 8.432432432432433e-05, | |
| "loss": 0.0302, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 0.03459068015217781, | |
| "learning_rate": 7.891891891891892e-05, | |
| "loss": 0.0296, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 0.033658791333436966, | |
| "learning_rate": 7.351351351351352e-05, | |
| "loss": 0.0308, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.026565387845039368, | |
| "learning_rate": 6.810810810810811e-05, | |
| "loss": 0.0309, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 0.028347592800855637, | |
| "learning_rate": 6.27027027027027e-05, | |
| "loss": 0.0305, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 0.02861287258565426, | |
| "learning_rate": 5.7297297297297305e-05, | |
| "loss": 0.0298, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 0.01953195221722126, | |
| "learning_rate": 5.18918918918919e-05, | |
| "loss": 0.0302, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 0.025148887187242508, | |
| "learning_rate": 4.648648648648649e-05, | |
| "loss": 0.0297, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.021128997206687927, | |
| "learning_rate": 4.108108108108109e-05, | |
| "loss": 0.0296, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 0.020117945969104767, | |
| "learning_rate": 3.567567567567568e-05, | |
| "loss": 0.0295, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 0.021842550486326218, | |
| "learning_rate": 3.0270270270270272e-05, | |
| "loss": 0.0295, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 0.028773466125130653, | |
| "learning_rate": 2.486486486486487e-05, | |
| "loss": 0.03, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 0.024690190330147743, | |
| "learning_rate": 1.9459459459459463e-05, | |
| "loss": 0.0301, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.020363792777061462, | |
| "learning_rate": 1.4054054054054055e-05, | |
| "loss": 0.0291, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.027392864227294922, | |
| "learning_rate": 8.64864864864865e-06, | |
| "loss": 0.0293, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 0.02251037396490574, | |
| "learning_rate": 3.2432432432432437e-06, | |
| "loss": 0.0303, | |
| "step": 370 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 375, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3833317953683456e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |