| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.975609756097561, | |
| "eval_steps": 500, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.024390243902439025, | |
| "grad_norm": 0.16707786917686462, | |
| "learning_rate": 0.00019631901840490797, | |
| "loss": 2.635, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 0.13998350501060486, | |
| "learning_rate": 0.0001914110429447853, | |
| "loss": 2.3435, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07317073170731707, | |
| "grad_norm": 0.1309942603111267, | |
| "learning_rate": 0.00018650306748466258, | |
| "loss": 2.3362, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.15228970348834991, | |
| "learning_rate": 0.00018159509202453987, | |
| "loss": 2.278, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12195121951219512, | |
| "grad_norm": 0.13835516571998596, | |
| "learning_rate": 0.0001766871165644172, | |
| "loss": 2.2551, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 0.21494311094284058, | |
| "learning_rate": 0.0001717791411042945, | |
| "loss": 2.2077, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17073170731707318, | |
| "grad_norm": 0.21518772840499878, | |
| "learning_rate": 0.00016687116564417177, | |
| "loss": 2.3031, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.14484964311122894, | |
| "learning_rate": 0.00016196319018404909, | |
| "loss": 2.1937, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21951219512195122, | |
| "grad_norm": 0.242563858628273, | |
| "learning_rate": 0.0001570552147239264, | |
| "loss": 2.1975, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 0.1661764532327652, | |
| "learning_rate": 0.0001521472392638037, | |
| "loss": 2.2523, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2682926829268293, | |
| "grad_norm": 0.15373563766479492, | |
| "learning_rate": 0.00014723926380368098, | |
| "loss": 2.214, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 0.13464413583278656, | |
| "learning_rate": 0.00014233128834355828, | |
| "loss": 2.2028, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.3170731707317073, | |
| "grad_norm": 0.16624805331230164, | |
| "learning_rate": 0.0001374233128834356, | |
| "loss": 2.1833, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 0.1389687955379486, | |
| "learning_rate": 0.00013251533742331288, | |
| "loss": 2.1687, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.36585365853658536, | |
| "grad_norm": 0.15641051530838013, | |
| "learning_rate": 0.00012760736196319017, | |
| "loss": 2.187, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.1625806838274002, | |
| "learning_rate": 0.0001226993865030675, | |
| "loss": 2.1797, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.4146341463414634, | |
| "grad_norm": 0.14962390065193176, | |
| "learning_rate": 0.0001177914110429448, | |
| "loss": 2.2401, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 0.15027175843715668, | |
| "learning_rate": 0.00011288343558282209, | |
| "loss": 2.1078, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4634146341463415, | |
| "grad_norm": 0.1398533135652542, | |
| "learning_rate": 0.00010797546012269939, | |
| "loss": 2.2348, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.18960897624492645, | |
| "learning_rate": 0.0001030674846625767, | |
| "loss": 2.2566, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5121951219512195, | |
| "grad_norm": 0.17258687317371368, | |
| "learning_rate": 9.815950920245399e-05, | |
| "loss": 2.214, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 0.16552983224391937, | |
| "learning_rate": 9.325153374233129e-05, | |
| "loss": 2.1728, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5609756097560976, | |
| "grad_norm": 0.15598084032535553, | |
| "learning_rate": 8.83435582822086e-05, | |
| "loss": 2.2111, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 0.18658678233623505, | |
| "learning_rate": 8.343558282208588e-05, | |
| "loss": 2.1649, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.6097560975609756, | |
| "grad_norm": 0.13376082479953766, | |
| "learning_rate": 7.85276073619632e-05, | |
| "loss": 2.2003, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 0.17194202542304993, | |
| "learning_rate": 7.361963190184049e-05, | |
| "loss": 2.1423, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6585365853658537, | |
| "grad_norm": 0.18158170580863953, | |
| "learning_rate": 6.87116564417178e-05, | |
| "loss": 2.1567, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 0.16745077073574066, | |
| "learning_rate": 6.380368098159509e-05, | |
| "loss": 2.1775, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.7073170731707317, | |
| "grad_norm": 0.17525842785835266, | |
| "learning_rate": 5.88957055214724e-05, | |
| "loss": 2.1736, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 0.17679478228092194, | |
| "learning_rate": 5.3987730061349695e-05, | |
| "loss": 2.1711, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7560975609756098, | |
| "grad_norm": 0.13690592348575592, | |
| "learning_rate": 4.907975460122699e-05, | |
| "loss": 2.2247, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.21975897252559662, | |
| "learning_rate": 4.41717791411043e-05, | |
| "loss": 2.1804, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.8048780487804879, | |
| "grad_norm": 0.1626081019639969, | |
| "learning_rate": 3.92638036809816e-05, | |
| "loss": 2.1812, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 0.15699782967567444, | |
| "learning_rate": 3.43558282208589e-05, | |
| "loss": 2.1145, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8536585365853658, | |
| "grad_norm": 0.15588204562664032, | |
| "learning_rate": 2.94478527607362e-05, | |
| "loss": 2.2064, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 0.2222682237625122, | |
| "learning_rate": 2.4539877300613496e-05, | |
| "loss": 2.1562, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.9024390243902439, | |
| "grad_norm": 0.16220204532146454, | |
| "learning_rate": 1.96319018404908e-05, | |
| "loss": 2.2139, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 0.20664212107658386, | |
| "learning_rate": 1.47239263803681e-05, | |
| "loss": 2.1842, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9512195121951219, | |
| "grad_norm": 0.15472255647182465, | |
| "learning_rate": 9.8159509202454e-06, | |
| "loss": 2.1798, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.17610955238342285, | |
| "learning_rate": 4.9079754601227e-06, | |
| "loss": 2.1404, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 820, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.965872212082688e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |