| { | |
| "best_metric": 0.969, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-1053", | |
| "epoch": 2.9936034115138592, | |
| "eval_steps": 500, | |
| "global_step": 1053, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 5.63645601272583, | |
| "learning_rate": 4.716981132075472e-06, | |
| "loss": 2.3306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 6.468899726867676, | |
| "learning_rate": 9.433962264150944e-06, | |
| "loss": 2.2678, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 6.23107385635376, | |
| "learning_rate": 1.4150943396226415e-05, | |
| "loss": 2.1477, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 6.676746368408203, | |
| "learning_rate": 1.8867924528301888e-05, | |
| "loss": 1.9591, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 10.20413875579834, | |
| "learning_rate": 2.358490566037736e-05, | |
| "loss": 1.6696, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 12.014700889587402, | |
| "learning_rate": 2.830188679245283e-05, | |
| "loss": 1.3329, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 13.840166091918945, | |
| "learning_rate": 3.30188679245283e-05, | |
| "loss": 1.1415, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 14.116910934448242, | |
| "learning_rate": 3.7735849056603776e-05, | |
| "loss": 1.024, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 10.790963172912598, | |
| "learning_rate": 4.245283018867925e-05, | |
| "loss": 0.9195, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 14.884149551391602, | |
| "learning_rate": 4.716981132075472e-05, | |
| "loss": 0.8209, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 14.443344116210938, | |
| "learning_rate": 4.978880675818374e-05, | |
| "loss": 0.7393, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 15.056041717529297, | |
| "learning_rate": 4.9260823653643085e-05, | |
| "loss": 0.7175, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 10.33287525177002, | |
| "learning_rate": 4.8732840549102435e-05, | |
| "loss": 0.7329, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 12.791647911071777, | |
| "learning_rate": 4.820485744456177e-05, | |
| "loss": 0.7075, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 12.029749870300293, | |
| "learning_rate": 4.767687434002112e-05, | |
| "loss": 0.6584, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 11.643570899963379, | |
| "learning_rate": 4.7148891235480466e-05, | |
| "loss": 0.6047, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 19.02515983581543, | |
| "learning_rate": 4.662090813093981e-05, | |
| "loss": 0.6052, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 10.113385200500488, | |
| "learning_rate": 4.609292502639916e-05, | |
| "loss": 0.6043, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 12.620966911315918, | |
| "learning_rate": 4.55649419218585e-05, | |
| "loss": 0.5803, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 8.98147201538086, | |
| "learning_rate": 4.503695881731785e-05, | |
| "loss": 0.5365, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 11.942453384399414, | |
| "learning_rate": 4.45089757127772e-05, | |
| "loss": 0.6061, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 8.406760215759277, | |
| "learning_rate": 4.398099260823654e-05, | |
| "loss": 0.4963, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 8.798361778259277, | |
| "learning_rate": 4.3453009503695884e-05, | |
| "loss": 0.552, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 8.614947319030762, | |
| "learning_rate": 4.292502639915523e-05, | |
| "loss": 0.5015, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 9.218803405761719, | |
| "learning_rate": 4.239704329461457e-05, | |
| "loss": 0.5246, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 9.763008117675781, | |
| "learning_rate": 4.186906019007392e-05, | |
| "loss": 0.5188, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 10.057807922363281, | |
| "learning_rate": 4.1341077085533265e-05, | |
| "loss": 0.4884, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 10.842576026916504, | |
| "learning_rate": 4.081309398099261e-05, | |
| "loss": 0.5345, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 8.137351036071777, | |
| "learning_rate": 4.028511087645195e-05, | |
| "loss": 0.5157, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 14.897061347961426, | |
| "learning_rate": 3.97571277719113e-05, | |
| "loss": 0.5212, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 11.816178321838379, | |
| "learning_rate": 3.9229144667370646e-05, | |
| "loss": 0.5337, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 10.712966918945312, | |
| "learning_rate": 3.870116156282999e-05, | |
| "loss": 0.5154, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 7.876273155212402, | |
| "learning_rate": 3.817317845828934e-05, | |
| "loss": 0.4833, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 14.542892456054688, | |
| "learning_rate": 3.764519535374868e-05, | |
| "loss": 0.5037, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.809218406677246, | |
| "learning_rate": 3.711721224920803e-05, | |
| "loss": 0.5592, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9538, | |
| "eval_loss": 0.14359258115291595, | |
| "eval_runtime": 31.1413, | |
| "eval_samples_per_second": 160.558, | |
| "eval_steps_per_second": 5.042, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 8.733403205871582, | |
| "learning_rate": 3.658922914466738e-05, | |
| "loss": 0.4327, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 9.024731636047363, | |
| "learning_rate": 3.6061246040126714e-05, | |
| "loss": 0.4674, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 8.668274879455566, | |
| "learning_rate": 3.5533262935586064e-05, | |
| "loss": 0.4807, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 11.616405487060547, | |
| "learning_rate": 3.500527983104541e-05, | |
| "loss": 0.51, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 8.094477653503418, | |
| "learning_rate": 3.447729672650475e-05, | |
| "loss": 0.4959, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 11.38330364227295, | |
| "learning_rate": 3.3949313621964095e-05, | |
| "loss": 0.4142, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 13.148619651794434, | |
| "learning_rate": 3.3421330517423445e-05, | |
| "loss": 0.4217, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 20.912269592285156, | |
| "learning_rate": 3.289334741288279e-05, | |
| "loss": 0.4437, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 12.211991310119629, | |
| "learning_rate": 3.236536430834213e-05, | |
| "loss": 0.4687, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 11.126351356506348, | |
| "learning_rate": 3.183738120380148e-05, | |
| "loss": 0.4691, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 9.944380760192871, | |
| "learning_rate": 3.130939809926082e-05, | |
| "loss": 0.4593, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 10.881024360656738, | |
| "learning_rate": 3.078141499472017e-05, | |
| "loss": 0.4594, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 7.276984214782715, | |
| "learning_rate": 3.0253431890179517e-05, | |
| "loss": 0.4566, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 11.3895263671875, | |
| "learning_rate": 2.972544878563886e-05, | |
| "loss": 0.4061, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 8.26075267791748, | |
| "learning_rate": 2.9197465681098207e-05, | |
| "loss": 0.4233, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 9.681741714477539, | |
| "learning_rate": 2.8669482576557548e-05, | |
| "loss": 0.4564, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 12.245609283447266, | |
| "learning_rate": 2.8141499472016898e-05, | |
| "loss": 0.4561, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 10.530965805053711, | |
| "learning_rate": 2.7613516367476245e-05, | |
| "loss": 0.429, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 6.2105889320373535, | |
| "learning_rate": 2.7085533262935585e-05, | |
| "loss": 0.3995, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 9.41408920288086, | |
| "learning_rate": 2.6557550158394935e-05, | |
| "loss": 0.4159, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 10.506197929382324, | |
| "learning_rate": 2.6029567053854276e-05, | |
| "loss": 0.4396, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 9.805855751037598, | |
| "learning_rate": 2.5501583949313622e-05, | |
| "loss": 0.4258, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 6.874490261077881, | |
| "learning_rate": 2.497360084477297e-05, | |
| "loss": 0.4014, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 9.369732856750488, | |
| "learning_rate": 2.4445617740232313e-05, | |
| "loss": 0.4045, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 10.258170127868652, | |
| "learning_rate": 2.391763463569166e-05, | |
| "loss": 0.4133, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 9.34408950805664, | |
| "learning_rate": 2.3389651531151003e-05, | |
| "loss": 0.4196, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 9.928686141967773, | |
| "learning_rate": 2.286166842661035e-05, | |
| "loss": 0.4014, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 10.1293306350708, | |
| "learning_rate": 2.2333685322069694e-05, | |
| "loss": 0.427, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 10.649211883544922, | |
| "learning_rate": 2.180570221752904e-05, | |
| "loss": 0.3947, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 12.145565032958984, | |
| "learning_rate": 2.1277719112988384e-05, | |
| "loss": 0.4131, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 9.348143577575684, | |
| "learning_rate": 2.074973600844773e-05, | |
| "loss": 0.459, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 8.802924156188965, | |
| "learning_rate": 2.0221752903907075e-05, | |
| "loss": 0.3921, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 18.41295051574707, | |
| "learning_rate": 1.9693769799366422e-05, | |
| "loss": 0.3756, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 8.476001739501953, | |
| "learning_rate": 1.9165786694825765e-05, | |
| "loss": 0.3941, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 9.943327903747559, | |
| "learning_rate": 1.863780359028511e-05, | |
| "loss": 0.3338, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9632, | |
| "eval_loss": 0.11315808445215225, | |
| "eval_runtime": 31.2355, | |
| "eval_samples_per_second": 160.074, | |
| "eval_steps_per_second": 5.026, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 10.112526893615723, | |
| "learning_rate": 1.810982048574446e-05, | |
| "loss": 0.3586, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 9.651534080505371, | |
| "learning_rate": 1.7581837381203803e-05, | |
| "loss": 0.3957, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 7.620846748352051, | |
| "learning_rate": 1.7053854276663146e-05, | |
| "loss": 0.402, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 10.414019584655762, | |
| "learning_rate": 1.6525871172122493e-05, | |
| "loss": 0.3809, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 9.351815223693848, | |
| "learning_rate": 1.5997888067581837e-05, | |
| "loss": 0.3745, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 10.798675537109375, | |
| "learning_rate": 1.5469904963041184e-05, | |
| "loss": 0.3507, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 10.772116661071777, | |
| "learning_rate": 1.4941921858500529e-05, | |
| "loss": 0.3589, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "grad_norm": 9.006869316101074, | |
| "learning_rate": 1.4413938753959874e-05, | |
| "loss": 0.359, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 7.237900257110596, | |
| "learning_rate": 1.388595564941922e-05, | |
| "loss": 0.3636, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "grad_norm": 8.02499008178711, | |
| "learning_rate": 1.3357972544878563e-05, | |
| "loss": 0.3817, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 7.373661041259766, | |
| "learning_rate": 1.2829989440337912e-05, | |
| "loss": 0.3812, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 9.66775131225586, | |
| "learning_rate": 1.2302006335797255e-05, | |
| "loss": 0.3681, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 9.115776062011719, | |
| "learning_rate": 1.17740232312566e-05, | |
| "loss": 0.4156, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "grad_norm": 8.92050838470459, | |
| "learning_rate": 1.1246040126715946e-05, | |
| "loss": 0.3629, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "grad_norm": 7.8812031745910645, | |
| "learning_rate": 1.0718057022175291e-05, | |
| "loss": 0.356, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 5.577208518981934, | |
| "learning_rate": 1.0190073917634636e-05, | |
| "loss": 0.3653, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "grad_norm": 9.963196754455566, | |
| "learning_rate": 9.662090813093982e-06, | |
| "loss": 0.3648, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 10.441061973571777, | |
| "learning_rate": 9.134107708553327e-06, | |
| "loss": 0.3671, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "grad_norm": 11.808416366577148, | |
| "learning_rate": 8.606124604012672e-06, | |
| "loss": 0.3012, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 7.2837138175964355, | |
| "learning_rate": 8.078141499472017e-06, | |
| "loss": 0.4002, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "grad_norm": 7.841160297393799, | |
| "learning_rate": 7.5501583949313625e-06, | |
| "loss": 0.424, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "grad_norm": 11.717653274536133, | |
| "learning_rate": 7.022175290390708e-06, | |
| "loss": 0.3432, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 7.797212600708008, | |
| "learning_rate": 6.494192185850054e-06, | |
| "loss": 0.3618, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 9.33782958984375, | |
| "learning_rate": 5.966209081309398e-06, | |
| "loss": 0.3559, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 8.307150840759277, | |
| "learning_rate": 5.438225976768744e-06, | |
| "loss": 0.3601, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "grad_norm": 8.53368854522705, | |
| "learning_rate": 4.910242872228089e-06, | |
| "loss": 0.3319, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "grad_norm": 8.487812042236328, | |
| "learning_rate": 4.382259767687434e-06, | |
| "loss": 0.3331, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 10.636713027954102, | |
| "learning_rate": 3.854276663146779e-06, | |
| "loss": 0.359, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "grad_norm": 13.220087051391602, | |
| "learning_rate": 3.326293558606125e-06, | |
| "loss": 0.3598, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 7.285949230194092, | |
| "learning_rate": 2.79831045406547e-06, | |
| "loss": 0.3503, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "grad_norm": 8.310001373291016, | |
| "learning_rate": 2.2703273495248154e-06, | |
| "loss": 0.3566, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 9.105748176574707, | |
| "learning_rate": 1.7423442449841606e-06, | |
| "loss": 0.3345, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": 7.4982008934021, | |
| "learning_rate": 1.2143611404435059e-06, | |
| "loss": 0.3398, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 11.533191680908203, | |
| "learning_rate": 6.863780359028511e-07, | |
| "loss": 0.3275, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "grad_norm": 7.991899013519287, | |
| "learning_rate": 1.5839493136219642e-07, | |
| "loss": 0.3196, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.969, | |
| "eval_loss": 0.09590400755405426, | |
| "eval_runtime": 31.5821, | |
| "eval_samples_per_second": 158.318, | |
| "eval_steps_per_second": 4.971, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 1053, | |
| "total_flos": 3.3497451642252165e+18, | |
| "train_loss": 0.5486761254009924, | |
| "train_runtime": 2094.2938, | |
| "train_samples_per_second": 64.461, | |
| "train_steps_per_second": 0.503 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1053, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3.3497451642252165e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |