{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 782, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01278772378516624, "grad_norm": 0.17330682277679443, "learning_rate": 0.0001976982097186701, "loss": 1.4811, "step": 10 }, { "epoch": 0.02557544757033248, "grad_norm": 0.15069860219955444, "learning_rate": 0.00019514066496163684, "loss": 1.4092, "step": 20 }, { "epoch": 0.03836317135549872, "grad_norm": 0.1438504010438919, "learning_rate": 0.0001925831202046036, "loss": 1.3498, "step": 30 }, { "epoch": 0.05115089514066496, "grad_norm": 0.16118377447128296, "learning_rate": 0.00019002557544757034, "loss": 1.3031, "step": 40 }, { "epoch": 0.0639386189258312, "grad_norm": 0.15924590826034546, "learning_rate": 0.0001874680306905371, "loss": 1.3659, "step": 50 }, { "epoch": 0.07672634271099744, "grad_norm": 0.16134314239025116, "learning_rate": 0.00018491048593350385, "loss": 1.2793, "step": 60 }, { "epoch": 0.08951406649616368, "grad_norm": 0.17917372286319733, "learning_rate": 0.0001823529411764706, "loss": 1.2369, "step": 70 }, { "epoch": 0.10230179028132992, "grad_norm": 0.17515508830547333, "learning_rate": 0.00017979539641943735, "loss": 1.2174, "step": 80 }, { "epoch": 0.11508951406649616, "grad_norm": 0.16867513954639435, "learning_rate": 0.0001772378516624041, "loss": 1.2656, "step": 90 }, { "epoch": 0.1278772378516624, "grad_norm": 0.21344934403896332, "learning_rate": 0.00017468030690537086, "loss": 1.2513, "step": 100 }, { "epoch": 0.14066496163682865, "grad_norm": 0.19054637849330902, "learning_rate": 0.0001721227621483376, "loss": 1.2906, "step": 110 }, { "epoch": 0.1534526854219949, "grad_norm": 0.2011404037475586, "learning_rate": 0.00016956521739130436, "loss": 1.2156, "step": 120 }, { "epoch": 0.16624040920716113, "grad_norm": 0.190298929810524, "learning_rate": 0.0001670076726342711, "loss": 1.1907, "step": 130 }, { "epoch": 0.17902813299232737, "grad_norm": 0.20571213960647583, "learning_rate": 0.00016445012787723786, "loss": 1.2082, "step": 140 }, { "epoch": 0.1918158567774936, "grad_norm": 0.20900501310825348, "learning_rate": 0.00016189258312020462, "loss": 1.1588, "step": 150 }, { "epoch": 0.20460358056265984, "grad_norm": 0.21515554189682007, "learning_rate": 0.00015933503836317137, "loss": 1.2504, "step": 160 }, { "epoch": 0.21739130434782608, "grad_norm": 0.21124675869941711, "learning_rate": 0.00015677749360613812, "loss": 1.209, "step": 170 }, { "epoch": 0.23017902813299232, "grad_norm": 0.26808661222457886, "learning_rate": 0.00015421994884910487, "loss": 1.2274, "step": 180 }, { "epoch": 0.24296675191815856, "grad_norm": 0.21091195940971375, "learning_rate": 0.00015166240409207163, "loss": 1.1682, "step": 190 }, { "epoch": 0.2557544757033248, "grad_norm": 0.23372243344783783, "learning_rate": 0.00014910485933503838, "loss": 1.2151, "step": 200 }, { "epoch": 0.26854219948849106, "grad_norm": 0.20886382460594177, "learning_rate": 0.00014654731457800513, "loss": 1.1707, "step": 210 }, { "epoch": 0.2813299232736573, "grad_norm": 0.2718591094017029, "learning_rate": 0.00014398976982097188, "loss": 1.1818, "step": 220 }, { "epoch": 0.29411764705882354, "grad_norm": 0.20646598935127258, "learning_rate": 0.00014143222506393863, "loss": 1.2143, "step": 230 }, { "epoch": 0.3069053708439898, "grad_norm": 0.23880060017108917, "learning_rate": 0.00013887468030690539, "loss": 1.2, "step": 240 }, { "epoch": 0.319693094629156, "grad_norm": 0.21879994869232178, "learning_rate": 0.00013631713554987214, "loss": 1.1613, "step": 250 }, { "epoch": 0.33248081841432225, "grad_norm": 0.21538586914539337, "learning_rate": 0.0001337595907928389, "loss": 1.2349, "step": 260 }, { "epoch": 0.3452685421994885, "grad_norm": 0.20641756057739258, "learning_rate": 0.00013120204603580564, "loss": 1.1739, "step": 270 }, { "epoch": 0.35805626598465473, "grad_norm": 0.24804268777370453, "learning_rate": 0.0001286445012787724, "loss": 1.1915, "step": 280 }, { "epoch": 0.37084398976982097, "grad_norm": 0.24932831525802612, "learning_rate": 0.00012608695652173915, "loss": 1.1843, "step": 290 }, { "epoch": 0.3836317135549872, "grad_norm": 0.26308584213256836, "learning_rate": 0.0001235294117647059, "loss": 1.1992, "step": 300 }, { "epoch": 0.39641943734015345, "grad_norm": 0.2279403656721115, "learning_rate": 0.00012097186700767265, "loss": 1.1884, "step": 310 }, { "epoch": 0.4092071611253197, "grad_norm": 0.2214374542236328, "learning_rate": 0.0001184143222506394, "loss": 1.1879, "step": 320 }, { "epoch": 0.4219948849104859, "grad_norm": 0.20924842357635498, "learning_rate": 0.00011585677749360616, "loss": 1.1716, "step": 330 }, { "epoch": 0.43478260869565216, "grad_norm": 0.2850317358970642, "learning_rate": 0.00011329923273657291, "loss": 1.1537, "step": 340 }, { "epoch": 0.4475703324808184, "grad_norm": 0.2727545499801636, "learning_rate": 0.00011074168797953966, "loss": 1.1924, "step": 350 }, { "epoch": 0.46035805626598464, "grad_norm": 0.21406596899032593, "learning_rate": 0.00010818414322250641, "loss": 1.1935, "step": 360 }, { "epoch": 0.4731457800511509, "grad_norm": 0.26856428384780884, "learning_rate": 0.00010562659846547316, "loss": 1.1473, "step": 370 }, { "epoch": 0.4859335038363171, "grad_norm": 0.31214985251426697, "learning_rate": 0.00010306905370843992, "loss": 1.1869, "step": 380 }, { "epoch": 0.49872122762148335, "grad_norm": 0.25869354605674744, "learning_rate": 0.00010051150895140667, "loss": 1.1726, "step": 390 }, { "epoch": 0.5115089514066496, "grad_norm": 0.25544413924217224, "learning_rate": 9.79539641943734e-05, "loss": 1.2077, "step": 400 }, { "epoch": 0.5242966751918159, "grad_norm": 0.24060559272766113, "learning_rate": 9.539641943734016e-05, "loss": 1.1651, "step": 410 }, { "epoch": 0.5370843989769821, "grad_norm": 0.2562996447086334, "learning_rate": 9.283887468030691e-05, "loss": 1.1922, "step": 420 }, { "epoch": 0.5498721227621484, "grad_norm": 0.24809622764587402, "learning_rate": 9.028132992327366e-05, "loss": 1.1622, "step": 430 }, { "epoch": 0.5626598465473146, "grad_norm": 0.23276326060295105, "learning_rate": 8.772378516624042e-05, "loss": 1.1461, "step": 440 }, { "epoch": 0.5754475703324808, "grad_norm": 0.26975592970848083, "learning_rate": 8.516624040920717e-05, "loss": 1.1719, "step": 450 }, { "epoch": 0.5882352941176471, "grad_norm": 0.2104811817407608, "learning_rate": 8.260869565217392e-05, "loss": 1.1957, "step": 460 }, { "epoch": 0.6010230179028133, "grad_norm": 0.25681132078170776, "learning_rate": 8.005115089514067e-05, "loss": 1.1508, "step": 470 }, { "epoch": 0.6138107416879796, "grad_norm": 0.2409922480583191, "learning_rate": 7.749360613810742e-05, "loss": 1.169, "step": 480 }, { "epoch": 0.6265984654731458, "grad_norm": 0.22748278081417084, "learning_rate": 7.493606138107418e-05, "loss": 1.1102, "step": 490 }, { "epoch": 0.639386189258312, "grad_norm": 0.27332964539527893, "learning_rate": 7.237851662404093e-05, "loss": 1.162, "step": 500 }, { "epoch": 0.6521739130434783, "grad_norm": 0.2509157955646515, "learning_rate": 6.982097186700768e-05, "loss": 1.1518, "step": 510 }, { "epoch": 0.6649616368286445, "grad_norm": 0.2574126720428467, "learning_rate": 6.726342710997443e-05, "loss": 1.1643, "step": 520 }, { "epoch": 0.6777493606138107, "grad_norm": 0.23611821234226227, "learning_rate": 6.470588235294118e-05, "loss": 1.1975, "step": 530 }, { "epoch": 0.690537084398977, "grad_norm": 0.2839568257331848, "learning_rate": 6.214833759590794e-05, "loss": 1.1611, "step": 540 }, { "epoch": 0.7033248081841432, "grad_norm": 0.2545911967754364, "learning_rate": 5.959079283887469e-05, "loss": 1.1711, "step": 550 }, { "epoch": 0.7161125319693095, "grad_norm": 0.24425293505191803, "learning_rate": 5.703324808184144e-05, "loss": 1.16, "step": 560 }, { "epoch": 0.7289002557544757, "grad_norm": 0.21479295194149017, "learning_rate": 5.447570332480819e-05, "loss": 1.1918, "step": 570 }, { "epoch": 0.7416879795396419, "grad_norm": 0.28247973322868347, "learning_rate": 5.1918158567774945e-05, "loss": 1.1219, "step": 580 }, { "epoch": 0.7544757033248082, "grad_norm": 0.2444392889738083, "learning_rate": 4.936061381074169e-05, "loss": 1.1619, "step": 590 }, { "epoch": 0.7672634271099744, "grad_norm": 0.2738865911960602, "learning_rate": 4.680306905370844e-05, "loss": 1.1875, "step": 600 }, { "epoch": 0.7800511508951407, "grad_norm": 0.2427508682012558, "learning_rate": 4.4245524296675195e-05, "loss": 1.1554, "step": 610 }, { "epoch": 0.7928388746803069, "grad_norm": 0.2514194846153259, "learning_rate": 4.168797953964195e-05, "loss": 1.0994, "step": 620 }, { "epoch": 0.8056265984654731, "grad_norm": 0.3031892776489258, "learning_rate": 3.91304347826087e-05, "loss": 1.1534, "step": 630 }, { "epoch": 0.8184143222506394, "grad_norm": 0.26739251613616943, "learning_rate": 3.657289002557545e-05, "loss": 1.1519, "step": 640 }, { "epoch": 0.8312020460358056, "grad_norm": 0.24512003362178802, "learning_rate": 3.40153452685422e-05, "loss": 1.1461, "step": 650 }, { "epoch": 0.8439897698209718, "grad_norm": 0.25903940200805664, "learning_rate": 3.145780051150895e-05, "loss": 1.2031, "step": 660 }, { "epoch": 0.8567774936061381, "grad_norm": 0.2628057599067688, "learning_rate": 2.89002557544757e-05, "loss": 1.0987, "step": 670 }, { "epoch": 0.8695652173913043, "grad_norm": 0.2536948621273041, "learning_rate": 2.6342710997442456e-05, "loss": 1.1747, "step": 680 }, { "epoch": 0.8823529411764706, "grad_norm": 0.24911293387413025, "learning_rate": 2.378516624040921e-05, "loss": 1.134, "step": 690 }, { "epoch": 0.8951406649616368, "grad_norm": 0.25777775049209595, "learning_rate": 2.122762148337596e-05, "loss": 1.1314, "step": 700 }, { "epoch": 0.907928388746803, "grad_norm": 0.2719346582889557, "learning_rate": 1.8670076726342713e-05, "loss": 1.1481, "step": 710 }, { "epoch": 0.9207161125319693, "grad_norm": 0.2559177279472351, "learning_rate": 1.6112531969309465e-05, "loss": 1.1892, "step": 720 }, { "epoch": 0.9335038363171355, "grad_norm": 0.25907379388809204, "learning_rate": 1.3554987212276215e-05, "loss": 1.1818, "step": 730 }, { "epoch": 0.9462915601023018, "grad_norm": 0.24793638288974762, "learning_rate": 1.0997442455242967e-05, "loss": 1.1825, "step": 740 }, { "epoch": 0.959079283887468, "grad_norm": 0.2763022184371948, "learning_rate": 8.439897698209718e-06, "loss": 1.1252, "step": 750 }, { "epoch": 0.9718670076726342, "grad_norm": 0.2603158950805664, "learning_rate": 5.882352941176471e-06, "loss": 1.1759, "step": 760 }, { "epoch": 0.9846547314578005, "grad_norm": 0.2559683620929718, "learning_rate": 3.324808184143223e-06, "loss": 1.1206, "step": 770 }, { "epoch": 0.9974424552429667, "grad_norm": 0.2707849442958832, "learning_rate": 7.672634271099745e-07, "loss": 1.1607, "step": 780 } ], "logging_steps": 10, "max_steps": 782, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 2.54046633984e+17, "train_batch_size": 32, "trial_name": null, "trial_params": null }