| { | |
| "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": 0.2627893388271332, | |
| "learning_rate": 0.00019631901840490797, | |
| "loss": 2.6021, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 0.22776605188846588, | |
| "learning_rate": 0.0001914110429447853, | |
| "loss": 2.3247, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07317073170731707, | |
| "grad_norm": 0.219473734498024, | |
| "learning_rate": 0.00018650306748466258, | |
| "loss": 2.327, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.2347700446844101, | |
| "learning_rate": 0.00018159509202453987, | |
| "loss": 2.2708, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.12195121951219512, | |
| "grad_norm": 0.22764651477336884, | |
| "learning_rate": 0.0001766871165644172, | |
| "loss": 2.2459, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 0.2603573799133301, | |
| "learning_rate": 0.0001717791411042945, | |
| "loss": 2.1985, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.17073170731707318, | |
| "grad_norm": 0.30507025122642517, | |
| "learning_rate": 0.00016687116564417177, | |
| "loss": 2.297, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.21570216119289398, | |
| "learning_rate": 0.00016196319018404909, | |
| "loss": 2.188, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.21951219512195122, | |
| "grad_norm": 0.3292004466056824, | |
| "learning_rate": 0.0001570552147239264, | |
| "loss": 2.1902, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 0.24518953263759613, | |
| "learning_rate": 0.0001521472392638037, | |
| "loss": 2.2467, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2682926829268293, | |
| "grad_norm": 0.23216311633586884, | |
| "learning_rate": 0.00014723926380368098, | |
| "loss": 2.2083, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 0.20361796021461487, | |
| "learning_rate": 0.00014233128834355828, | |
| "loss": 2.1973, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.3170731707317073, | |
| "grad_norm": 0.24827799201011658, | |
| "learning_rate": 0.0001374233128834356, | |
| "loss": 2.1774, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 0.20967458188533783, | |
| "learning_rate": 0.00013251533742331288, | |
| "loss": 2.1627, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.36585365853658536, | |
| "grad_norm": 0.2206897735595703, | |
| "learning_rate": 0.00012760736196319017, | |
| "loss": 2.1811, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.23732008039951324, | |
| "learning_rate": 0.0001226993865030675, | |
| "loss": 2.1742, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.4146341463414634, | |
| "grad_norm": 0.22148175537586212, | |
| "learning_rate": 0.0001177914110429448, | |
| "loss": 2.2337, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 0.2142496407032013, | |
| "learning_rate": 0.00011288343558282209, | |
| "loss": 2.1012, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4634146341463415, | |
| "grad_norm": 0.2130177915096283, | |
| "learning_rate": 0.00010797546012269939, | |
| "loss": 2.2286, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.2707054018974304, | |
| "learning_rate": 0.0001030674846625767, | |
| "loss": 2.2509, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.5121951219512195, | |
| "grad_norm": 0.25327154994010925, | |
| "learning_rate": 9.815950920245399e-05, | |
| "loss": 2.2075, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 0.2448398917913437, | |
| "learning_rate": 9.325153374233129e-05, | |
| "loss": 2.1658, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5609756097560976, | |
| "grad_norm": 0.22938354313373566, | |
| "learning_rate": 8.83435582822086e-05, | |
| "loss": 2.2044, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 0.2697414755821228, | |
| "learning_rate": 8.343558282208588e-05, | |
| "loss": 2.1591, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.6097560975609756, | |
| "grad_norm": 0.1953606903553009, | |
| "learning_rate": 7.85276073619632e-05, | |
| "loss": 2.1933, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 0.25183743238449097, | |
| "learning_rate": 7.361963190184049e-05, | |
| "loss": 2.1351, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6585365853658537, | |
| "grad_norm": 0.2615358531475067, | |
| "learning_rate": 6.87116564417178e-05, | |
| "loss": 2.1501, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 0.24008150398731232, | |
| "learning_rate": 6.380368098159509e-05, | |
| "loss": 2.1712, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.7073170731707317, | |
| "grad_norm": 0.23081189393997192, | |
| "learning_rate": 5.88957055214724e-05, | |
| "loss": 2.1677, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 0.2541828155517578, | |
| "learning_rate": 5.3987730061349695e-05, | |
| "loss": 2.1638, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7560975609756098, | |
| "grad_norm": 0.19970808923244476, | |
| "learning_rate": 4.907975460122699e-05, | |
| "loss": 2.2178, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.3092334568500519, | |
| "learning_rate": 4.41717791411043e-05, | |
| "loss": 2.1742, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.8048780487804879, | |
| "grad_norm": 0.23249533772468567, | |
| "learning_rate": 3.92638036809816e-05, | |
| "loss": 2.1742, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 0.22389353811740875, | |
| "learning_rate": 3.43558282208589e-05, | |
| "loss": 2.1082, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8536585365853658, | |
| "grad_norm": 0.23446932435035706, | |
| "learning_rate": 2.94478527607362e-05, | |
| "loss": 2.1984, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 0.3031781315803528, | |
| "learning_rate": 2.4539877300613496e-05, | |
| "loss": 2.1486, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.9024390243902439, | |
| "grad_norm": 0.23885215818881989, | |
| "learning_rate": 1.96319018404908e-05, | |
| "loss": 2.2071, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 0.2940409481525421, | |
| "learning_rate": 1.47239263803681e-05, | |
| "loss": 2.176, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9512195121951219, | |
| "grad_norm": 0.222421795129776, | |
| "learning_rate": 9.8159509202454e-06, | |
| "loss": 2.1733, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.2580586075782776, | |
| "learning_rate": 4.9079754601227e-06, | |
| "loss": 2.1337, | |
| "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": 1.948430886764544e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |