| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.996415770609319, | |
| "eval_steps": 500, | |
| "global_step": 1254, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023894862604540025, | |
| "grad_norm": 6.081180104447192, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9213, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04778972520908005, | |
| "grad_norm": 2.5675420707703682, | |
| "learning_rate": 5e-06, | |
| "loss": 0.8064, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07168458781362007, | |
| "grad_norm": 1.116884956350582, | |
| "learning_rate": 5e-06, | |
| "loss": 0.764, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0955794504181601, | |
| "grad_norm": 0.9827896973879405, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7456, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11947431302270012, | |
| "grad_norm": 1.1716177346699552, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7252, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14336917562724014, | |
| "grad_norm": 1.054189475268262, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7144, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16726403823178015, | |
| "grad_norm": 0.7494472231038515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.7153, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1911589008363202, | |
| "grad_norm": 0.5903583553666529, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6941, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21505376344086022, | |
| "grad_norm": 0.7850320924725688, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6917, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23894862604540024, | |
| "grad_norm": 0.8082497951696401, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6931, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2628434886499403, | |
| "grad_norm": 0.5831514385960807, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6808, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2867383512544803, | |
| "grad_norm": 0.7344040626713287, | |
| "learning_rate": 5e-06, | |
| "loss": 0.689, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3106332138590203, | |
| "grad_norm": 0.8291631762782786, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6852, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3345280764635603, | |
| "grad_norm": 0.555446198309624, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6746, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35842293906810035, | |
| "grad_norm": 0.8214482724693175, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6789, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3823178016726404, | |
| "grad_norm": 0.5332479678739207, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6676, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4062126642771804, | |
| "grad_norm": 1.0446840993388027, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6669, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 0.5354819297917649, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6671, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4540023894862604, | |
| "grad_norm": 0.5790753975231967, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6637, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4778972520908005, | |
| "grad_norm": 0.5611754139446838, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6706, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5017921146953405, | |
| "grad_norm": 0.541229197735182, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6678, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.5256869772998806, | |
| "grad_norm": 0.6290230152316767, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6615, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5495818399044206, | |
| "grad_norm": 0.5103134958958712, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6621, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5734767025089605, | |
| "grad_norm": 0.4963914880777678, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6587, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5973715651135006, | |
| "grad_norm": 0.7047770736230026, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6633, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.6212664277180406, | |
| "grad_norm": 0.6875405023947134, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6602, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 0.5469403807072362, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6649, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6690561529271206, | |
| "grad_norm": 0.6301316104025243, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6605, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6929510155316607, | |
| "grad_norm": 0.7436109186331767, | |
| "learning_rate": 5e-06, | |
| "loss": 0.657, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.7168458781362007, | |
| "grad_norm": 0.6316182942840975, | |
| "learning_rate": 5e-06, | |
| "loss": 0.659, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.5862276185836299, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6543, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7646356033452808, | |
| "grad_norm": 0.5727274506679324, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6578, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7885304659498208, | |
| "grad_norm": 0.8637237307062305, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6572, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.8124253285543608, | |
| "grad_norm": 0.5716637099962937, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6544, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.8363201911589009, | |
| "grad_norm": 0.5267829079741267, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6542, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8602150537634409, | |
| "grad_norm": 0.5819870889688735, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6524, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8841099163679809, | |
| "grad_norm": 0.5230379233220511, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6561, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.9080047789725209, | |
| "grad_norm": 0.5405733925967506, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6576, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.931899641577061, | |
| "grad_norm": 0.6252081499402665, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6431, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.955794504181601, | |
| "grad_norm": 0.5241989931128205, | |
| "learning_rate": 5e-06, | |
| "loss": 0.645, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9796893667861409, | |
| "grad_norm": 0.5917706193349264, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6548, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.998805256869773, | |
| "eval_loss": 0.6481666564941406, | |
| "eval_runtime": 225.2584, | |
| "eval_samples_per_second": 50.045, | |
| "eval_steps_per_second": 0.395, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 1.003584229390681, | |
| "grad_norm": 0.8892508812440383, | |
| "learning_rate": 5e-06, | |
| "loss": 0.645, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.027479091995221, | |
| "grad_norm": 0.6856782905740205, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6088, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.0513739545997611, | |
| "grad_norm": 0.5419930096362386, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6083, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.075268817204301, | |
| "grad_norm": 0.6254120282769089, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6102, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.099163679808841, | |
| "grad_norm": 0.7886162221301777, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6022, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.1230585424133812, | |
| "grad_norm": 0.5575253634257799, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6008, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.146953405017921, | |
| "grad_norm": 0.5457321558023005, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6076, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1708482676224612, | |
| "grad_norm": 0.4910125465988992, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5998, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.194743130227001, | |
| "grad_norm": 0.5851438416753514, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6095, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.2186379928315412, | |
| "grad_norm": 0.5544196352892787, | |
| "learning_rate": 5e-06, | |
| "loss": 0.608, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.2425328554360813, | |
| "grad_norm": 0.5835218258508235, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6053, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.2664277180406214, | |
| "grad_norm": 0.6402155111012049, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6086, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 0.5274545363597922, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6082, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.3142174432497014, | |
| "grad_norm": 0.5023370306863523, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6097, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.3381123058542412, | |
| "grad_norm": 0.5336199850801069, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6037, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.3620071684587813, | |
| "grad_norm": 0.7734469958692578, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6066, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.3859020310633214, | |
| "grad_norm": 0.8452375931165987, | |
| "learning_rate": 5e-06, | |
| "loss": 0.604, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.4097968936678615, | |
| "grad_norm": 0.5907657942794627, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6042, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.4336917562724014, | |
| "grad_norm": 0.6105214261701881, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6077, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.4575866188769415, | |
| "grad_norm": 0.6803070474017702, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6145, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 0.5137151572440128, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6068, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.5053763440860215, | |
| "grad_norm": 0.5526611853120886, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6023, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.5292712066905616, | |
| "grad_norm": 0.5276740317417068, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6066, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.5531660692951017, | |
| "grad_norm": 0.5266173782221237, | |
| "learning_rate": 5e-06, | |
| "loss": 0.604, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.5770609318996416, | |
| "grad_norm": 0.5879899658739348, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6062, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.6009557945041815, | |
| "grad_norm": 0.6426153237314072, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6044, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.6248506571087216, | |
| "grad_norm": 0.5633170243940351, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5975, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.6487455197132617, | |
| "grad_norm": 0.5448798915341956, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5969, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.6726403823178018, | |
| "grad_norm": 0.484774901310647, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6069, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6965352449223416, | |
| "grad_norm": 0.5257867856081395, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5985, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.7204301075268817, | |
| "grad_norm": 0.5602525718442715, | |
| "learning_rate": 5e-06, | |
| "loss": 0.612, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.7443249701314216, | |
| "grad_norm": 0.5040592279383703, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6021, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.7682198327359617, | |
| "grad_norm": 0.6140508371910811, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6029, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.7921146953405018, | |
| "grad_norm": 0.526723228546995, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6051, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.816009557945042, | |
| "grad_norm": 0.5485611376004595, | |
| "learning_rate": 5e-06, | |
| "loss": 0.602, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.8399044205495818, | |
| "grad_norm": 0.4925549773889819, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5976, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.863799283154122, | |
| "grad_norm": 0.5127568984869073, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6015, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.8876941457586618, | |
| "grad_norm": 0.7953660178238419, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5983, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.911589008363202, | |
| "grad_norm": 0.4644171655680959, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6043, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "grad_norm": 0.5504656432596945, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5991, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.959378733572282, | |
| "grad_norm": 0.5014583862445193, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6027, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.983273596176822, | |
| "grad_norm": 0.5169701196971361, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6065, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6383097767829895, | |
| "eval_runtime": 225.1334, | |
| "eval_samples_per_second": 50.073, | |
| "eval_steps_per_second": 0.395, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 2.007168458781362, | |
| "grad_norm": 0.9522384301889181, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5892, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.031063321385902, | |
| "grad_norm": 0.5604355482368693, | |
| "learning_rate": 5e-06, | |
| "loss": 0.555, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.054958183990442, | |
| "grad_norm": 0.8454377137422782, | |
| "learning_rate": 5e-06, | |
| "loss": 0.559, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.078853046594982, | |
| "grad_norm": 0.6125609351007736, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5588, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.1027479091995223, | |
| "grad_norm": 0.550684661961655, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5566, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.126642771804062, | |
| "grad_norm": 0.5268020228547002, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5509, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.150537634408602, | |
| "grad_norm": 0.5374686724727457, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5558, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.174432497013142, | |
| "grad_norm": 0.6591728468868026, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5523, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.198327359617682, | |
| "grad_norm": 0.5758411262414109, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5626, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.5974631029863997, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5633, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.2461170848267624, | |
| "grad_norm": 0.6693430289411901, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5569, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.270011947431302, | |
| "grad_norm": 0.5235798291837075, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5592, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.293906810035842, | |
| "grad_norm": 0.5951063252000355, | |
| "learning_rate": 5e-06, | |
| "loss": 0.558, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.3178016726403823, | |
| "grad_norm": 0.7007904171286725, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5585, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.3416965352449224, | |
| "grad_norm": 0.6157005538099132, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5584, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.3655913978494625, | |
| "grad_norm": 0.5560793638442904, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5536, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.389486260454002, | |
| "grad_norm": 0.5994284875647052, | |
| "learning_rate": 5e-06, | |
| "loss": 0.559, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.4133811230585422, | |
| "grad_norm": 0.6178447526276027, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5622, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.4372759856630823, | |
| "grad_norm": 0.598268249438012, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5617, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.4611708482676224, | |
| "grad_norm": 0.6456807780700198, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5598, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.4850657108721625, | |
| "grad_norm": 0.5838521623874042, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5565, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.5089605734767026, | |
| "grad_norm": 0.6160425605583054, | |
| "learning_rate": 5e-06, | |
| "loss": 0.561, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.5328554360812428, | |
| "grad_norm": 0.6471012332418825, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5609, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.5567502986857824, | |
| "grad_norm": 0.7438495174826055, | |
| "learning_rate": 5e-06, | |
| "loss": 0.559, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.5806451612903225, | |
| "grad_norm": 0.5965448247540126, | |
| "learning_rate": 5e-06, | |
| "loss": 0.57, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.6045400238948626, | |
| "grad_norm": 0.6030850533182174, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5619, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.6284348864994027, | |
| "grad_norm": 0.5627845167167422, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5615, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.652329749103943, | |
| "grad_norm": 0.5586383353478368, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5567, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.6762246117084825, | |
| "grad_norm": 0.6169226364241693, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5614, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.7001194743130226, | |
| "grad_norm": 0.5655962840268283, | |
| "learning_rate": 5e-06, | |
| "loss": 0.566, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.7240143369175627, | |
| "grad_norm": 0.5379947967296507, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5585, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.7479091995221028, | |
| "grad_norm": 0.6022462071356245, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5647, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.771804062126643, | |
| "grad_norm": 0.5630793813942363, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5701, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.795698924731183, | |
| "grad_norm": 0.7669976902930744, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5584, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.819593787335723, | |
| "grad_norm": 0.6081830710715922, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5619, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.8434886499402627, | |
| "grad_norm": 0.5471146843592755, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5607, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.867383512544803, | |
| "grad_norm": 0.500432815577127, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5605, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.891278375149343, | |
| "grad_norm": 0.5513789797790463, | |
| "learning_rate": 5e-06, | |
| "loss": 0.558, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.915173237753883, | |
| "grad_norm": 0.5699534515350526, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5626, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.9390681003584227, | |
| "grad_norm": 0.6140827402540434, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5648, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.6486122276400309, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5627, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.986857825567503, | |
| "grad_norm": 0.5448840278284515, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5672, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.996415770609319, | |
| "eval_loss": 0.6404265761375427, | |
| "eval_runtime": 226.6238, | |
| "eval_samples_per_second": 49.743, | |
| "eval_steps_per_second": 0.393, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 2.996415770609319, | |
| "step": 1254, | |
| "total_flos": 2100077946470400.0, | |
| "train_loss": 0.6158634758832162, | |
| "train_runtime": 37532.7652, | |
| "train_samples_per_second": 17.12, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1254, | |
| "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": 2100077946470400.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |