| { | |
| "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": 0.21254414319992065, | |
| "learning_rate": 0.00019631901840490797, | |
| "loss": 2.6924, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 0.15234693884849548, | |
| "learning_rate": 0.0001914110429447853, | |
| "loss": 2.395, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07317073170731707, | |
| "grad_norm": 0.14660173654556274, | |
| "learning_rate": 0.00018650306748466258, | |
| "loss": 2.3598, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.1487397700548172, | |
| "learning_rate": 0.00018159509202453987, | |
| "loss": 2.3004, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12195121951219512, | |
| "grad_norm": 0.1340309977531433, | |
| "learning_rate": 0.0001766871165644172, | |
| "loss": 2.2839, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 0.16995489597320557, | |
| "learning_rate": 0.0001717791411042945, | |
| "loss": 2.2511, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17073170731707318, | |
| "grad_norm": 0.19542120397090912, | |
| "learning_rate": 0.00016687116564417177, | |
| "loss": 2.3543, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.1439371407032013, | |
| "learning_rate": 0.00016196319018404909, | |
| "loss": 2.2475, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21951219512195122, | |
| "grad_norm": 0.20567895472049713, | |
| "learning_rate": 0.0001570552147239264, | |
| "loss": 2.2536, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 0.16278642416000366, | |
| "learning_rate": 0.0001521472392638037, | |
| "loss": 2.3064, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2682926829268293, | |
| "grad_norm": 0.1587420403957367, | |
| "learning_rate": 0.00014723926380368098, | |
| "loss": 2.2682, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 0.13855259120464325, | |
| "learning_rate": 0.00014233128834355828, | |
| "loss": 2.2584, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.3170731707317073, | |
| "grad_norm": 0.17585845291614532, | |
| "learning_rate": 0.0001374233128834356, | |
| "loss": 2.2395, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 0.14558349549770355, | |
| "learning_rate": 0.00013251533742331288, | |
| "loss": 2.2272, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.36585365853658536, | |
| "grad_norm": 0.14745678007602692, | |
| "learning_rate": 0.00012760736196319017, | |
| "loss": 2.2415, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.1681157350540161, | |
| "learning_rate": 0.0001226993865030675, | |
| "loss": 2.2406, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.4146341463414634, | |
| "grad_norm": 0.15694855153560638, | |
| "learning_rate": 0.0001177914110429448, | |
| "loss": 2.2975, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 0.1510026901960373, | |
| "learning_rate": 0.00011288343558282209, | |
| "loss": 2.1714, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4634146341463415, | |
| "grad_norm": 0.14791268110275269, | |
| "learning_rate": 0.00010797546012269939, | |
| "loss": 2.294, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.1750643402338028, | |
| "learning_rate": 0.0001030674846625767, | |
| "loss": 2.3125, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5121951219512195, | |
| "grad_norm": 0.17560966312885284, | |
| "learning_rate": 9.815950920245399e-05, | |
| "loss": 2.2704, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 0.1715686172246933, | |
| "learning_rate": 9.325153374233129e-05, | |
| "loss": 2.2342, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5609756097560976, | |
| "grad_norm": 0.16171425580978394, | |
| "learning_rate": 8.83435582822086e-05, | |
| "loss": 2.2715, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 0.18964745104312897, | |
| "learning_rate": 8.343558282208588e-05, | |
| "loss": 2.2252, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.6097560975609756, | |
| "grad_norm": 0.13548357784748077, | |
| "learning_rate": 7.85276073619632e-05, | |
| "loss": 2.2612, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 0.16821901500225067, | |
| "learning_rate": 7.361963190184049e-05, | |
| "loss": 2.2098, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6585365853658537, | |
| "grad_norm": 0.18043252825737, | |
| "learning_rate": 6.87116564417178e-05, | |
| "loss": 2.2148, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 0.16026543080806732, | |
| "learning_rate": 6.380368098159509e-05, | |
| "loss": 2.2398, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.7073170731707317, | |
| "grad_norm": 0.14593158662319183, | |
| "learning_rate": 5.88957055214724e-05, | |
| "loss": 2.2333, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 0.17370396852493286, | |
| "learning_rate": 5.3987730061349695e-05, | |
| "loss": 2.2348, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7560975609756098, | |
| "grad_norm": 0.13942942023277283, | |
| "learning_rate": 4.907975460122699e-05, | |
| "loss": 2.2848, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.20677496492862701, | |
| "learning_rate": 4.41717791411043e-05, | |
| "loss": 2.2419, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.8048780487804879, | |
| "grad_norm": 0.15424074232578278, | |
| "learning_rate": 3.92638036809816e-05, | |
| "loss": 2.2451, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 0.15367330610752106, | |
| "learning_rate": 3.43558282208589e-05, | |
| "loss": 2.1768, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8536585365853658, | |
| "grad_norm": 0.15632031857967377, | |
| "learning_rate": 2.94478527607362e-05, | |
| "loss": 2.2686, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 0.19434422254562378, | |
| "learning_rate": 2.4539877300613496e-05, | |
| "loss": 2.2204, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.9024390243902439, | |
| "grad_norm": 0.16645264625549316, | |
| "learning_rate": 1.96319018404908e-05, | |
| "loss": 2.2703, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 0.20547692477703094, | |
| "learning_rate": 1.47239263803681e-05, | |
| "loss": 2.2495, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9512195121951219, | |
| "grad_norm": 0.15441441535949707, | |
| "learning_rate": 9.8159509202454e-06, | |
| "loss": 2.2408, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.18379011750221252, | |
| "learning_rate": 4.9079754601227e-06, | |
| "loss": 2.2041, | |
| "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": 1.9309895614464e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |