| { | |
| "best_metric": 0.16011084616184235, | |
| "best_model_checkpoint": "d:\\\\whisper-medium-pt-cv16-fleurs2-lr\\checkpoint-5000", | |
| "epoch": 11.671335200746965, | |
| "eval_steps": 5000, | |
| "global_step": 25000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011671335200746966, | |
| "grad_norm": 18.578170776367188, | |
| "learning_rate": 2.875e-08, | |
| "loss": 0.7382, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02334267040149393, | |
| "grad_norm": 37.2661247253418, | |
| "learning_rate": 5.8750000000000007e-08, | |
| "loss": 1.2823, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0350140056022409, | |
| "grad_norm": 14.59357738494873, | |
| "learning_rate": 9e-08, | |
| "loss": 0.7512, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04668534080298786, | |
| "grad_norm": 37.37008285522461, | |
| "learning_rate": 1.2125e-07, | |
| "loss": 1.2251, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05835667600373483, | |
| "grad_norm": 14.07325553894043, | |
| "learning_rate": 1.5250000000000002e-07, | |
| "loss": 0.6841, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.0700280112044818, | |
| "grad_norm": 29.391014099121094, | |
| "learning_rate": 1.8375000000000001e-07, | |
| "loss": 1.1131, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08169934640522876, | |
| "grad_norm": 12.7340087890625, | |
| "learning_rate": 2.15e-07, | |
| "loss": 0.5693, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.09337068160597572, | |
| "grad_norm": 26.895967483520508, | |
| "learning_rate": 2.4624999999999997e-07, | |
| "loss": 0.7876, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10504201680672269, | |
| "grad_norm": 8.66826057434082, | |
| "learning_rate": 2.7750000000000004e-07, | |
| "loss": 0.2992, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.11671335200746966, | |
| "grad_norm": 25.45290756225586, | |
| "learning_rate": 3.0875e-07, | |
| "loss": 0.4386, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1283846872082166, | |
| "grad_norm": 10.706913948059082, | |
| "learning_rate": 3.4e-07, | |
| "loss": 0.214, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.1400560224089636, | |
| "grad_norm": 19.541522979736328, | |
| "learning_rate": 3.7125000000000005e-07, | |
| "loss": 0.345, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15172735760971054, | |
| "grad_norm": 6.879134654998779, | |
| "learning_rate": 4.025e-07, | |
| "loss": 0.2445, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.16339869281045752, | |
| "grad_norm": 23.4116268157959, | |
| "learning_rate": 4.3375000000000003e-07, | |
| "loss": 0.3121, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.17507002801120447, | |
| "grad_norm": 7.257847785949707, | |
| "learning_rate": 4.65e-07, | |
| "loss": 0.2013, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.18674136321195145, | |
| "grad_norm": 11.849136352539062, | |
| "learning_rate": 4.9625e-07, | |
| "loss": 0.2626, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1984126984126984, | |
| "grad_norm": 7.970053195953369, | |
| "learning_rate": 5.275e-07, | |
| "loss": 0.2131, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.21008403361344538, | |
| "grad_norm": 19.375301361083984, | |
| "learning_rate": 5.587499999999999e-07, | |
| "loss": 0.2652, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.22175536881419233, | |
| "grad_norm": 10.925929069519043, | |
| "learning_rate": 5.9e-07, | |
| "loss": 0.2046, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.2334267040149393, | |
| "grad_norm": 20.24220085144043, | |
| "learning_rate": 6.212500000000001e-07, | |
| "loss": 0.2571, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24509803921568626, | |
| "grad_norm": 8.06639575958252, | |
| "learning_rate": 6.525000000000001e-07, | |
| "loss": 0.2157, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.2567693744164332, | |
| "grad_norm": 16.64718246459961, | |
| "learning_rate": 6.8375e-07, | |
| "loss": 0.2745, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.2684407096171802, | |
| "grad_norm": 8.912382125854492, | |
| "learning_rate": 7.15e-07, | |
| "loss": 0.1999, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.2801120448179272, | |
| "grad_norm": 16.385353088378906, | |
| "learning_rate": 7.462500000000001e-07, | |
| "loss": 0.2234, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.29178338001867415, | |
| "grad_norm": 4.625432968139648, | |
| "learning_rate": 7.775e-07, | |
| "loss": 0.1847, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.3034547152194211, | |
| "grad_norm": 30.452251434326172, | |
| "learning_rate": 8.0875e-07, | |
| "loss": 0.2338, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.31512605042016806, | |
| "grad_norm": 9.238980293273926, | |
| "learning_rate": 8.4e-07, | |
| "loss": 0.1883, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.32679738562091504, | |
| "grad_norm": 19.22330093383789, | |
| "learning_rate": 8.7125e-07, | |
| "loss": 0.2387, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.338468720821662, | |
| "grad_norm": 3.236504316329956, | |
| "learning_rate": 9.025e-07, | |
| "loss": 0.162, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.35014005602240894, | |
| "grad_norm": 18.75830078125, | |
| "learning_rate": 9.337500000000001e-07, | |
| "loss": 0.2217, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3618113912231559, | |
| "grad_norm": 4.1586198806762695, | |
| "learning_rate": 9.65e-07, | |
| "loss": 0.1739, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.3734827264239029, | |
| "grad_norm": 16.235074996948242, | |
| "learning_rate": 9.9625e-07, | |
| "loss": 0.227, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3851540616246499, | |
| "grad_norm": 7.601698398590088, | |
| "learning_rate": 1.0275e-06, | |
| "loss": 0.1764, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.3968253968253968, | |
| "grad_norm": 17.789981842041016, | |
| "learning_rate": 1.05875e-06, | |
| "loss": 0.2138, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4084967320261438, | |
| "grad_norm": 5.891432285308838, | |
| "learning_rate": 1.0900000000000002e-06, | |
| "loss": 0.1753, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.42016806722689076, | |
| "grad_norm": 21.724348068237305, | |
| "learning_rate": 1.12125e-06, | |
| "loss": 0.206, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.43183940242763774, | |
| "grad_norm": 5.313950538635254, | |
| "learning_rate": 1.1525000000000002e-06, | |
| "loss": 0.167, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.44351073762838467, | |
| "grad_norm": 11.306236267089844, | |
| "learning_rate": 1.18375e-06, | |
| "loss": 0.1974, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.45518207282913165, | |
| "grad_norm": 8.582784652709961, | |
| "learning_rate": 1.215e-06, | |
| "loss": 0.192, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.4668534080298786, | |
| "grad_norm": 14.138503074645996, | |
| "learning_rate": 1.24625e-06, | |
| "loss": 0.1969, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4785247432306256, | |
| "grad_norm": 5.119744777679443, | |
| "learning_rate": 1.2775e-06, | |
| "loss": 0.1781, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.49019607843137253, | |
| "grad_norm": 16.845916748046875, | |
| "learning_rate": 1.3087500000000002e-06, | |
| "loss": 0.1714, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5018674136321195, | |
| "grad_norm": 8.487195014953613, | |
| "learning_rate": 1.34e-06, | |
| "loss": 0.1784, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.5135387488328664, | |
| "grad_norm": 10.874380111694336, | |
| "learning_rate": 1.3712500000000002e-06, | |
| "loss": 0.2085, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5252100840336135, | |
| "grad_norm": 5.2850661277771, | |
| "learning_rate": 1.4025e-06, | |
| "loss": 0.1731, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.5368814192343604, | |
| "grad_norm": 12.621524810791016, | |
| "learning_rate": 1.43375e-06, | |
| "loss": 0.2066, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.5485527544351074, | |
| "grad_norm": 6.700886249542236, | |
| "learning_rate": 1.465e-06, | |
| "loss": 0.1599, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.5602240896358543, | |
| "grad_norm": 13.19000244140625, | |
| "learning_rate": 1.49625e-06, | |
| "loss": 0.1982, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5718954248366013, | |
| "grad_norm": 5.436820030212402, | |
| "learning_rate": 1.5275000000000002e-06, | |
| "loss": 0.1671, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.5835667600373483, | |
| "grad_norm": 14.979127883911133, | |
| "learning_rate": 1.5587500000000001e-06, | |
| "loss": 0.192, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.5952380952380952, | |
| "grad_norm": 4.490325450897217, | |
| "learning_rate": 1.5900000000000002e-06, | |
| "loss": 0.1731, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.6069094304388422, | |
| "grad_norm": 17.244354248046875, | |
| "learning_rate": 1.6212500000000001e-06, | |
| "loss": 0.1763, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6185807656395892, | |
| "grad_norm": 8.09378433227539, | |
| "learning_rate": 1.6525000000000003e-06, | |
| "loss": 0.1511, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.6302521008403361, | |
| "grad_norm": 13.42496395111084, | |
| "learning_rate": 1.68375e-06, | |
| "loss": 0.2064, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6419234360410832, | |
| "grad_norm": 7.0393385887146, | |
| "learning_rate": 1.7149999999999999e-06, | |
| "loss": 0.1703, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.6535947712418301, | |
| "grad_norm": 11.562192916870117, | |
| "learning_rate": 1.74625e-06, | |
| "loss": 0.1743, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.665266106442577, | |
| "grad_norm": 8.296894073486328, | |
| "learning_rate": 1.7775e-06, | |
| "loss": 0.1762, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.676937441643324, | |
| "grad_norm": 15.146247863769531, | |
| "learning_rate": 1.80875e-06, | |
| "loss": 0.1877, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.688608776844071, | |
| "grad_norm": 6.557362079620361, | |
| "learning_rate": 1.84e-06, | |
| "loss": 0.1948, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.7002801120448179, | |
| "grad_norm": 9.744128227233887, | |
| "learning_rate": 1.87125e-06, | |
| "loss": 0.188, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7119514472455649, | |
| "grad_norm": 6.373684883117676, | |
| "learning_rate": 1.9025000000000002e-06, | |
| "loss": 0.1795, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.7236227824463118, | |
| "grad_norm": 12.318848609924316, | |
| "learning_rate": 1.9337500000000003e-06, | |
| "loss": 0.16, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.7352941176470589, | |
| "grad_norm": 8.32919979095459, | |
| "learning_rate": 1.9650000000000002e-06, | |
| "loss": 0.1559, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.7469654528478058, | |
| "grad_norm": 14.127927780151367, | |
| "learning_rate": 1.99625e-06, | |
| "loss": 0.18, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7586367880485527, | |
| "grad_norm": 4.867166519165039, | |
| "learning_rate": 2.0275e-06, | |
| "loss": 0.1502, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.7703081232492998, | |
| "grad_norm": 10.735671043395996, | |
| "learning_rate": 2.0587500000000004e-06, | |
| "loss": 0.1798, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.7819794584500467, | |
| "grad_norm": 7.60561990737915, | |
| "learning_rate": 2.09e-06, | |
| "loss": 0.1532, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.7936507936507936, | |
| "grad_norm": 14.279719352722168, | |
| "learning_rate": 2.12125e-06, | |
| "loss": 0.1761, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8053221288515406, | |
| "grad_norm": 6.583901882171631, | |
| "learning_rate": 2.1525e-06, | |
| "loss": 0.162, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.8169934640522876, | |
| "grad_norm": 12.237863540649414, | |
| "learning_rate": 2.18375e-06, | |
| "loss": 0.1644, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.8286647992530346, | |
| "grad_norm": 5.648594379425049, | |
| "learning_rate": 2.215e-06, | |
| "loss": 0.142, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.8403361344537815, | |
| "grad_norm": 15.333111763000488, | |
| "learning_rate": 2.24625e-06, | |
| "loss": 0.1932, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.8520074696545284, | |
| "grad_norm": 7.390342712402344, | |
| "learning_rate": 2.2775000000000002e-06, | |
| "loss": 0.1663, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.8636788048552755, | |
| "grad_norm": 15.47307300567627, | |
| "learning_rate": 2.30875e-06, | |
| "loss": 0.1864, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.8753501400560224, | |
| "grad_norm": 3.5743496417999268, | |
| "learning_rate": 2.34e-06, | |
| "loss": 0.1625, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.8870214752567693, | |
| "grad_norm": 12.931510925292969, | |
| "learning_rate": 2.3712500000000004e-06, | |
| "loss": 0.1674, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.8986928104575164, | |
| "grad_norm": 10.445046424865723, | |
| "learning_rate": 2.4025000000000003e-06, | |
| "loss": 0.1551, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.9103641456582633, | |
| "grad_norm": 15.884492874145508, | |
| "learning_rate": 2.43375e-06, | |
| "loss": 0.1797, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.9220354808590103, | |
| "grad_norm": 3.6354966163635254, | |
| "learning_rate": 2.465e-06, | |
| "loss": 0.1726, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.9337068160597572, | |
| "grad_norm": 10.952392578125, | |
| "learning_rate": 2.49625e-06, | |
| "loss": 0.1579, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9453781512605042, | |
| "grad_norm": 5.575680255889893, | |
| "learning_rate": 2.5275e-06, | |
| "loss": 0.1607, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.9570494864612512, | |
| "grad_norm": 9.334450721740723, | |
| "learning_rate": 2.55875e-06, | |
| "loss": 0.1819, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.9687208216619981, | |
| "grad_norm": 5.0021443367004395, | |
| "learning_rate": 2.59e-06, | |
| "loss": 0.1721, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.9803921568627451, | |
| "grad_norm": 11.442158699035645, | |
| "learning_rate": 2.62125e-06, | |
| "loss": 0.1696, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.9920634920634921, | |
| "grad_norm": 7.345489978790283, | |
| "learning_rate": 2.6525e-06, | |
| "loss": 0.1547, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 1.003734827264239, | |
| "grad_norm": 3.4940426349639893, | |
| "learning_rate": 2.6837500000000004e-06, | |
| "loss": 0.1642, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.015406162464986, | |
| "grad_norm": 5.598668098449707, | |
| "learning_rate": 2.7150000000000003e-06, | |
| "loss": 0.0863, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 1.0270774976657329, | |
| "grad_norm": 3.780421495437622, | |
| "learning_rate": 2.74625e-06, | |
| "loss": 0.136, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.03874883286648, | |
| "grad_norm": 3.801037311553955, | |
| "learning_rate": 2.7775e-06, | |
| "loss": 0.0962, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 1.050420168067227, | |
| "grad_norm": 4.065105438232422, | |
| "learning_rate": 2.8087500000000004e-06, | |
| "loss": 0.1418, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.0620915032679739, | |
| "grad_norm": 4.889001369476318, | |
| "learning_rate": 2.8400000000000003e-06, | |
| "loss": 0.1161, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 1.0737628384687208, | |
| "grad_norm": 6.3269944190979, | |
| "learning_rate": 2.87125e-06, | |
| "loss": 0.1363, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.0854341736694677, | |
| "grad_norm": 6.666966438293457, | |
| "learning_rate": 2.9025e-06, | |
| "loss": 0.1177, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 1.0971055088702149, | |
| "grad_norm": 3.8940012454986572, | |
| "learning_rate": 2.93375e-06, | |
| "loss": 0.1297, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.1087768440709618, | |
| "grad_norm": 5.189432144165039, | |
| "learning_rate": 2.965e-06, | |
| "loss": 0.1149, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 1.1204481792717087, | |
| "grad_norm": 4.866479873657227, | |
| "learning_rate": 2.99625e-06, | |
| "loss": 0.1341, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.1321195144724556, | |
| "grad_norm": 7.036620140075684, | |
| "learning_rate": 3.0275000000000002e-06, | |
| "loss": 0.102, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 1.1437908496732025, | |
| "grad_norm": 4.124939441680908, | |
| "learning_rate": 3.05875e-06, | |
| "loss": 0.1483, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.1554621848739495, | |
| "grad_norm": 6.803956508636475, | |
| "learning_rate": 3.09e-06, | |
| "loss": 0.095, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 1.1671335200746966, | |
| "grad_norm": 4.783279895782471, | |
| "learning_rate": 3.1212500000000004e-06, | |
| "loss": 0.1458, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.1788048552754435, | |
| "grad_norm": 5.567852020263672, | |
| "learning_rate": 3.1525e-06, | |
| "loss": 0.104, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 1.1904761904761905, | |
| "grad_norm": 4.637757301330566, | |
| "learning_rate": 3.18375e-06, | |
| "loss": 0.1335, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.2021475256769374, | |
| "grad_norm": 7.655948162078857, | |
| "learning_rate": 3.215e-06, | |
| "loss": 0.1229, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 1.2138188608776843, | |
| "grad_norm": 4.771119117736816, | |
| "learning_rate": 3.24625e-06, | |
| "loss": 0.1543, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.2254901960784315, | |
| "grad_norm": 5.286261558532715, | |
| "learning_rate": 3.2775e-06, | |
| "loss": 0.1093, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 1.2371615312791784, | |
| "grad_norm": 4.742598533630371, | |
| "learning_rate": 3.30875e-06, | |
| "loss": 0.1587, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.2488328664799253, | |
| "grad_norm": 7.248344898223877, | |
| "learning_rate": 3.34e-06, | |
| "loss": 0.0946, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 1.2605042016806722, | |
| "grad_norm": 4.244619846343994, | |
| "learning_rate": 3.37125e-06, | |
| "loss": 0.1408, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.2721755368814192, | |
| "grad_norm": 4.698862075805664, | |
| "learning_rate": 3.4025e-06, | |
| "loss": 0.1115, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 1.283846872082166, | |
| "grad_norm": 5.453229904174805, | |
| "learning_rate": 3.4337500000000004e-06, | |
| "loss": 0.1377, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.2955182072829132, | |
| "grad_norm": 5.513113498687744, | |
| "learning_rate": 3.4650000000000003e-06, | |
| "loss": 0.1052, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 1.3071895424836601, | |
| "grad_norm": 4.546627521514893, | |
| "learning_rate": 3.49625e-06, | |
| "loss": 0.1326, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.318860877684407, | |
| "grad_norm": 7.161789894104004, | |
| "learning_rate": 3.5275e-06, | |
| "loss": 0.106, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 1.330532212885154, | |
| "grad_norm": 4.164399147033691, | |
| "learning_rate": 3.5587500000000004e-06, | |
| "loss": 0.1358, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.3422035480859011, | |
| "grad_norm": 5.428344249725342, | |
| "learning_rate": 3.5900000000000004e-06, | |
| "loss": 0.0949, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 1.353874883286648, | |
| "grad_norm": 6.0663275718688965, | |
| "learning_rate": 3.6212500000000003e-06, | |
| "loss": 0.1361, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.365546218487395, | |
| "grad_norm": 6.05164909362793, | |
| "learning_rate": 3.6525e-06, | |
| "loss": 0.1098, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 1.377217553688142, | |
| "grad_norm": 5.027311325073242, | |
| "learning_rate": 3.6837500000000005e-06, | |
| "loss": 0.1299, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.3888888888888888, | |
| "grad_norm": 7.7624006271362305, | |
| "learning_rate": 3.7150000000000004e-06, | |
| "loss": 0.1109, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 1.4005602240896358, | |
| "grad_norm": 5.019223213195801, | |
| "learning_rate": 3.7462500000000003e-06, | |
| "loss": 0.1648, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.4122315592903827, | |
| "grad_norm": 6.924857139587402, | |
| "learning_rate": 3.7775000000000007e-06, | |
| "loss": 0.1078, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 1.4239028944911298, | |
| "grad_norm": 6.098647594451904, | |
| "learning_rate": 3.8087500000000006e-06, | |
| "loss": 0.1511, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.4355742296918768, | |
| "grad_norm": 8.425399780273438, | |
| "learning_rate": 3.84e-06, | |
| "loss": 0.1191, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 1.4472455648926237, | |
| "grad_norm": 5.609083652496338, | |
| "learning_rate": 3.8712499999999996e-06, | |
| "loss": 0.142, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.4589169000933706, | |
| "grad_norm": 6.1147050857543945, | |
| "learning_rate": 3.9025e-06, | |
| "loss": 0.0996, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 1.4705882352941178, | |
| "grad_norm": 2.957465648651123, | |
| "learning_rate": 3.93375e-06, | |
| "loss": 0.1439, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.4822595704948647, | |
| "grad_norm": 3.472870111465454, | |
| "learning_rate": 3.965e-06, | |
| "loss": 0.0993, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 1.4939309056956116, | |
| "grad_norm": 5.71575927734375, | |
| "learning_rate": 3.99625e-06, | |
| "loss": 0.1438, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.5056022408963585, | |
| "grad_norm": 3.8211705684661865, | |
| "learning_rate": 4.0275e-06, | |
| "loss": 0.0941, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 1.5172735760971054, | |
| "grad_norm": 5.43381929397583, | |
| "learning_rate": 4.05875e-06, | |
| "loss": 0.1565, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.5289449112978524, | |
| "grad_norm": 5.146786212921143, | |
| "learning_rate": 4.09e-06, | |
| "loss": 0.1125, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 1.5406162464985993, | |
| "grad_norm": 4.331883430480957, | |
| "learning_rate": 4.12125e-06, | |
| "loss": 0.1393, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.5522875816993464, | |
| "grad_norm": 7.666718482971191, | |
| "learning_rate": 4.1525000000000005e-06, | |
| "loss": 0.116, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 1.5639589169000934, | |
| "grad_norm": 3.27604079246521, | |
| "learning_rate": 4.18375e-06, | |
| "loss": 0.1487, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.5756302521008403, | |
| "grad_norm": 8.548047065734863, | |
| "learning_rate": 4.215e-06, | |
| "loss": 0.114, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 1.5873015873015874, | |
| "grad_norm": 3.315171003341675, | |
| "learning_rate": 4.24625e-06, | |
| "loss": 0.1372, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.5989729225023344, | |
| "grad_norm": 6.508883953094482, | |
| "learning_rate": 4.2775e-06, | |
| "loss": 0.1054, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 1.6106442577030813, | |
| "grad_norm": 4.305449485778809, | |
| "learning_rate": 4.30875e-06, | |
| "loss": 0.1449, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.6223155929038282, | |
| "grad_norm": 8.238191604614258, | |
| "learning_rate": 4.34e-06, | |
| "loss": 0.1052, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 1.6339869281045751, | |
| "grad_norm": 3.1781492233276367, | |
| "learning_rate": 4.371250000000001e-06, | |
| "loss": 0.1462, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.645658263305322, | |
| "grad_norm": 5.8778557777404785, | |
| "learning_rate": 4.402500000000001e-06, | |
| "loss": 0.1213, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 1.657329598506069, | |
| "grad_norm": 3.6947333812713623, | |
| "learning_rate": 4.4337500000000005e-06, | |
| "loss": 0.1626, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.669000933706816, | |
| "grad_norm": 7.086148738861084, | |
| "learning_rate": 4.4650000000000004e-06, | |
| "loss": 0.1254, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 1.680672268907563, | |
| "grad_norm": 4.603717803955078, | |
| "learning_rate": 4.49625e-06, | |
| "loss": 0.1403, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.69234360410831, | |
| "grad_norm": 4.92815637588501, | |
| "learning_rate": 4.5275e-06, | |
| "loss": 0.1032, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 1.7040149393090571, | |
| "grad_norm": 3.701477289199829, | |
| "learning_rate": 4.55875e-06, | |
| "loss": 0.1349, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.715686274509804, | |
| "grad_norm": 13.451651573181152, | |
| "learning_rate": 4.590000000000001e-06, | |
| "loss": 0.1238, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 1.727357609710551, | |
| "grad_norm": 5.369861125946045, | |
| "learning_rate": 4.62125e-06, | |
| "loss": 0.1596, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.739028944911298, | |
| "grad_norm": 6.7364702224731445, | |
| "learning_rate": 4.6525e-06, | |
| "loss": 0.1288, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 1.7507002801120448, | |
| "grad_norm": 5.925997734069824, | |
| "learning_rate": 4.68375e-06, | |
| "loss": 0.1462, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.7623716153127917, | |
| "grad_norm": 4.7654829025268555, | |
| "learning_rate": 4.715e-06, | |
| "loss": 0.1146, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 1.7740429505135387, | |
| "grad_norm": 3.232302188873291, | |
| "learning_rate": 4.74625e-06, | |
| "loss": 0.1341, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.7857142857142856, | |
| "grad_norm": 6.663305282592773, | |
| "learning_rate": 4.7775e-06, | |
| "loss": 0.1047, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 1.7973856209150327, | |
| "grad_norm": 4.3404340744018555, | |
| "learning_rate": 4.80875e-06, | |
| "loss": 0.1425, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.8090569561157797, | |
| "grad_norm": 7.439436912536621, | |
| "learning_rate": 4.84e-06, | |
| "loss": 0.1056, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 1.8207282913165266, | |
| "grad_norm": 4.493560314178467, | |
| "learning_rate": 4.87125e-06, | |
| "loss": 0.152, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.8323996265172737, | |
| "grad_norm": 8.294795036315918, | |
| "learning_rate": 4.9025e-06, | |
| "loss": 0.1048, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 1.8440709617180207, | |
| "grad_norm": 4.7361884117126465, | |
| "learning_rate": 4.93375e-06, | |
| "loss": 0.1424, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.8557422969187676, | |
| "grad_norm": 6.927464485168457, | |
| "learning_rate": 4.965e-06, | |
| "loss": 0.0982, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 1.8674136321195145, | |
| "grad_norm": 6.300534248352051, | |
| "learning_rate": 4.996250000000001e-06, | |
| "loss": 0.1273, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.8790849673202614, | |
| "grad_norm": 4.410505294799805, | |
| "learning_rate": 5.0275000000000006e-06, | |
| "loss": 0.1223, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 1.8907563025210083, | |
| "grad_norm": 7.067946434020996, | |
| "learning_rate": 5.0587500000000005e-06, | |
| "loss": 0.1447, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.9024276377217553, | |
| "grad_norm": 5.033799171447754, | |
| "learning_rate": 5.09e-06, | |
| "loss": 0.1066, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 1.9140989729225022, | |
| "grad_norm": 4.994957447052002, | |
| "learning_rate": 5.12e-06, | |
| "loss": 0.14, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.9257703081232493, | |
| "grad_norm": 7.51298189163208, | |
| "learning_rate": 5.151250000000001e-06, | |
| "loss": 0.1065, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 1.9374416433239963, | |
| "grad_norm": 4.488656997680664, | |
| "learning_rate": 5.182500000000001e-06, | |
| "loss": 0.1495, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.9491129785247432, | |
| "grad_norm": 6.328264236450195, | |
| "learning_rate": 5.213750000000001e-06, | |
| "loss": 0.1047, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 1.9607843137254903, | |
| "grad_norm": 3.9831016063690186, | |
| "learning_rate": 5.245e-06, | |
| "loss": 0.1483, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.9724556489262373, | |
| "grad_norm": 9.204850196838379, | |
| "learning_rate": 5.27625e-06, | |
| "loss": 0.1076, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 1.9841269841269842, | |
| "grad_norm": 4.560220241546631, | |
| "learning_rate": 5.3075e-06, | |
| "loss": 0.1319, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.995798319327731, | |
| "grad_norm": 6.272380828857422, | |
| "learning_rate": 5.33875e-06, | |
| "loss": 0.1127, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 2.007469654528478, | |
| "grad_norm": 2.819856882095337, | |
| "learning_rate": 5.37e-06, | |
| "loss": 0.0898, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.019140989729225, | |
| "grad_norm": 3.3237640857696533, | |
| "learning_rate": 5.40125e-06, | |
| "loss": 0.0556, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 2.030812324929972, | |
| "grad_norm": 2.4771931171417236, | |
| "learning_rate": 5.4325e-06, | |
| "loss": 0.0807, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 2.042483660130719, | |
| "grad_norm": 3.640773296356201, | |
| "learning_rate": 5.46375e-06, | |
| "loss": 0.0528, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 2.0541549953314657, | |
| "grad_norm": 4.329100131988525, | |
| "learning_rate": 5.495e-06, | |
| "loss": 0.0852, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.065826330532213, | |
| "grad_norm": 4.2357916831970215, | |
| "learning_rate": 5.52625e-06, | |
| "loss": 0.0473, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 2.07749766573296, | |
| "grad_norm": 4.033267974853516, | |
| "learning_rate": 5.557500000000001e-06, | |
| "loss": 0.0802, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 2.089169000933707, | |
| "grad_norm": 6.817841529846191, | |
| "learning_rate": 5.5887500000000005e-06, | |
| "loss": 0.0602, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 2.100840336134454, | |
| "grad_norm": 4.568445682525635, | |
| "learning_rate": 5.62e-06, | |
| "loss": 0.083, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.112511671335201, | |
| "grad_norm": 8.219367980957031, | |
| "learning_rate": 5.65125e-06, | |
| "loss": 0.066, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 2.1241830065359477, | |
| "grad_norm": 1.9845637083053589, | |
| "learning_rate": 5.6825e-06, | |
| "loss": 0.0878, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 2.1358543417366946, | |
| "grad_norm": 7.169174671173096, | |
| "learning_rate": 5.71375e-06, | |
| "loss": 0.0651, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 2.1475256769374416, | |
| "grad_norm": 3.6445248126983643, | |
| "learning_rate": 5.745e-06, | |
| "loss": 0.1006, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.1591970121381885, | |
| "grad_norm": 4.955069541931152, | |
| "learning_rate": 5.776250000000001e-06, | |
| "loss": 0.0572, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 2.1708683473389354, | |
| "grad_norm": 3.909029245376587, | |
| "learning_rate": 5.807500000000001e-06, | |
| "loss": 0.0841, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 2.1825396825396823, | |
| "grad_norm": 2.1477255821228027, | |
| "learning_rate": 5.838750000000001e-06, | |
| "loss": 0.0717, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 2.1942110177404297, | |
| "grad_norm": 5.743031978607178, | |
| "learning_rate": 5.8700000000000005e-06, | |
| "loss": 0.0808, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.2058823529411766, | |
| "grad_norm": 4.362875461578369, | |
| "learning_rate": 5.9012500000000005e-06, | |
| "loss": 0.0609, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 2.2175536881419236, | |
| "grad_norm": 3.8198697566986084, | |
| "learning_rate": 5.9325e-06, | |
| "loss": 0.0892, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.2292250233426705, | |
| "grad_norm": 3.9962849617004395, | |
| "learning_rate": 5.96375e-06, | |
| "loss": 0.0656, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 2.2408963585434174, | |
| "grad_norm": 2.613006830215454, | |
| "learning_rate": 5.995e-06, | |
| "loss": 0.0812, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.2525676937441643, | |
| "grad_norm": 5.6209540367126465, | |
| "learning_rate": 6.02625e-06, | |
| "loss": 0.0814, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 2.2642390289449112, | |
| "grad_norm": 4.349456787109375, | |
| "learning_rate": 6.0575e-06, | |
| "loss": 0.084, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 2.275910364145658, | |
| "grad_norm": 6.475245952606201, | |
| "learning_rate": 6.08875e-06, | |
| "loss": 0.0798, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 2.287581699346405, | |
| "grad_norm": 2.503551959991455, | |
| "learning_rate": 6.12e-06, | |
| "loss": 0.0836, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.299253034547152, | |
| "grad_norm": 7.365092754364014, | |
| "learning_rate": 6.15125e-06, | |
| "loss": 0.07, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 2.310924369747899, | |
| "grad_norm": 4.494143486022949, | |
| "learning_rate": 6.1825e-06, | |
| "loss": 0.1019, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 2.3225957049486463, | |
| "grad_norm": 9.088369369506836, | |
| "learning_rate": 6.2137500000000004e-06, | |
| "loss": 0.0741, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 2.3342670401493932, | |
| "grad_norm": 3.5182809829711914, | |
| "learning_rate": 6.245e-06, | |
| "loss": 0.0856, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.3342670401493932, | |
| "eval_loss": 0.16011084616184235, | |
| "eval_runtime": 6234.0593, | |
| "eval_samples_per_second": 1.51, | |
| "eval_steps_per_second": 0.189, | |
| "eval_wer": 0.103035685451316, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.34593837535014, | |
| "grad_norm": 3.4111175537109375, | |
| "learning_rate": 6.2434375e-06, | |
| "loss": 0.0694, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 2.357609710550887, | |
| "grad_norm": 5.693511486053467, | |
| "learning_rate": 6.235625e-06, | |
| "loss": 0.0952, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 2.369281045751634, | |
| "grad_norm": 7.079166412353516, | |
| "learning_rate": 6.2278125e-06, | |
| "loss": 0.0605, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 2.9197869300842285, | |
| "learning_rate": 6.22e-06, | |
| "loss": 0.0941, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.392623716153128, | |
| "grad_norm": 6.79939603805542, | |
| "learning_rate": 6.2121875e-06, | |
| "loss": 0.0725, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 2.404295051353875, | |
| "grad_norm": 6.609640121459961, | |
| "learning_rate": 6.204375e-06, | |
| "loss": 0.0976, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 2.4159663865546217, | |
| "grad_norm": 7.591739654541016, | |
| "learning_rate": 6.196562500000001e-06, | |
| "loss": 0.0697, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 2.4276377217553686, | |
| "grad_norm": 7.580626964569092, | |
| "learning_rate": 6.18875e-06, | |
| "loss": 0.0921, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.439309056956116, | |
| "grad_norm": 7.333129405975342, | |
| "learning_rate": 6.1809375000000005e-06, | |
| "loss": 0.0727, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 2.450980392156863, | |
| "grad_norm": 6.632033348083496, | |
| "learning_rate": 6.173125e-06, | |
| "loss": 0.0891, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 2.46265172735761, | |
| "grad_norm": 5.526509761810303, | |
| "learning_rate": 6.165312500000001e-06, | |
| "loss": 0.077, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 2.4743230625583568, | |
| "grad_norm": 6.0735602378845215, | |
| "learning_rate": 6.1575e-06, | |
| "loss": 0.101, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.4859943977591037, | |
| "grad_norm": 7.87660026550293, | |
| "learning_rate": 6.1496875000000006e-06, | |
| "loss": 0.0737, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 2.4976657329598506, | |
| "grad_norm": 4.01476526260376, | |
| "learning_rate": 6.141875e-06, | |
| "loss": 0.0928, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 2.5093370681605975, | |
| "grad_norm": 5.005721569061279, | |
| "learning_rate": 6.1340625e-06, | |
| "loss": 0.0717, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 2.5210084033613445, | |
| "grad_norm": 5.76194429397583, | |
| "learning_rate": 6.12625e-06, | |
| "loss": 0.0922, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.5326797385620914, | |
| "grad_norm": 5.3504157066345215, | |
| "learning_rate": 6.1184375e-06, | |
| "loss": 0.0658, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 2.5443510737628383, | |
| "grad_norm": 4.85629415512085, | |
| "learning_rate": 6.1106250000000005e-06, | |
| "loss": 0.0825, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 2.5560224089635852, | |
| "grad_norm": 5.944486141204834, | |
| "learning_rate": 6.1028125e-06, | |
| "loss": 0.0775, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 2.567693744164332, | |
| "grad_norm": 6.294357776641846, | |
| "learning_rate": 6.095e-06, | |
| "loss": 0.0915, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.5793650793650795, | |
| "grad_norm": 5.524097919464111, | |
| "learning_rate": 6.0871875e-06, | |
| "loss": 0.0662, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 2.5910364145658265, | |
| "grad_norm": 4.0100812911987305, | |
| "learning_rate": 6.0793750000000006e-06, | |
| "loss": 0.0914, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 2.6027077497665734, | |
| "grad_norm": 7.9108123779296875, | |
| "learning_rate": 6.0715625e-06, | |
| "loss": 0.0774, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 2.6143790849673203, | |
| "grad_norm": 2.5471160411834717, | |
| "learning_rate": 6.06375e-06, | |
| "loss": 0.0839, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.6260504201680672, | |
| "grad_norm": 3.6380198001861572, | |
| "learning_rate": 6.0559375e-06, | |
| "loss": 0.0621, | |
| "step": 5625 | |
| }, | |
| { | |
| "epoch": 2.637721755368814, | |
| "grad_norm": 2.9542012214660645, | |
| "learning_rate": 6.048125000000001e-06, | |
| "loss": 0.0784, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 2.649393090569561, | |
| "grad_norm": 4.753948211669922, | |
| "learning_rate": 6.0403125000000005e-06, | |
| "loss": 0.0768, | |
| "step": 5675 | |
| }, | |
| { | |
| "epoch": 2.661064425770308, | |
| "grad_norm": 2.410440444946289, | |
| "learning_rate": 6.0325e-06, | |
| "loss": 0.088, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.6727357609710554, | |
| "grad_norm": 5.084535121917725, | |
| "learning_rate": 6.0246875e-06, | |
| "loss": 0.0743, | |
| "step": 5725 | |
| }, | |
| { | |
| "epoch": 2.6844070961718023, | |
| "grad_norm": 1.9251270294189453, | |
| "learning_rate": 6.016875e-06, | |
| "loss": 0.0882, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 2.696078431372549, | |
| "grad_norm": 6.866667747497559, | |
| "learning_rate": 6.0090625000000005e-06, | |
| "loss": 0.0675, | |
| "step": 5775 | |
| }, | |
| { | |
| "epoch": 2.707749766573296, | |
| "grad_norm": 5.318982124328613, | |
| "learning_rate": 6.00125e-06, | |
| "loss": 0.0856, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.719421101774043, | |
| "grad_norm": 4.362662315368652, | |
| "learning_rate": 5.9934375e-06, | |
| "loss": 0.0787, | |
| "step": 5825 | |
| }, | |
| { | |
| "epoch": 2.73109243697479, | |
| "grad_norm": 3.6322102546691895, | |
| "learning_rate": 5.985625e-06, | |
| "loss": 0.0907, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 2.742763772175537, | |
| "grad_norm": 6.347275257110596, | |
| "learning_rate": 5.977812500000001e-06, | |
| "loss": 0.0689, | |
| "step": 5875 | |
| }, | |
| { | |
| "epoch": 2.754435107376284, | |
| "grad_norm": 4.315841197967529, | |
| "learning_rate": 5.9700000000000004e-06, | |
| "loss": 0.0971, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 2.7661064425770308, | |
| "grad_norm": 3.1454360485076904, | |
| "learning_rate": 5.9621875e-06, | |
| "loss": 0.0615, | |
| "step": 5925 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "grad_norm": 3.9786288738250732, | |
| "learning_rate": 5.954375e-06, | |
| "loss": 0.0988, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 2.7894491129785246, | |
| "grad_norm": 7.057102680206299, | |
| "learning_rate": 5.946562500000001e-06, | |
| "loss": 0.0768, | |
| "step": 5975 | |
| }, | |
| { | |
| "epoch": 2.8011204481792715, | |
| "grad_norm": 4.522549629211426, | |
| "learning_rate": 5.9387500000000005e-06, | |
| "loss": 0.0847, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.8127917833800185, | |
| "grad_norm": 6.361202716827393, | |
| "learning_rate": 5.9309375e-06, | |
| "loss": 0.0525, | |
| "step": 6025 | |
| }, | |
| { | |
| "epoch": 2.8244631185807654, | |
| "grad_norm": 3.8292720317840576, | |
| "learning_rate": 5.923125e-06, | |
| "loss": 0.0841, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 2.8361344537815127, | |
| "grad_norm": 6.834649085998535, | |
| "learning_rate": 5.9153125e-06, | |
| "loss": 0.0687, | |
| "step": 6075 | |
| }, | |
| { | |
| "epoch": 2.8478057889822597, | |
| "grad_norm": 6.25474214553833, | |
| "learning_rate": 5.907500000000001e-06, | |
| "loss": 0.0895, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 2.8594771241830066, | |
| "grad_norm": 5.775394439697266, | |
| "learning_rate": 5.8996875000000004e-06, | |
| "loss": 0.0727, | |
| "step": 6125 | |
| }, | |
| { | |
| "epoch": 2.8711484593837535, | |
| "grad_norm": 4.371216297149658, | |
| "learning_rate": 5.891875e-06, | |
| "loss": 0.1085, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 2.8828197945845004, | |
| "grad_norm": 3.050452947616577, | |
| "learning_rate": 5.8840625e-06, | |
| "loss": 0.0654, | |
| "step": 6175 | |
| }, | |
| { | |
| "epoch": 2.8944911297852474, | |
| "grad_norm": 3.992262840270996, | |
| "learning_rate": 5.876250000000001e-06, | |
| "loss": 0.0945, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 2.9061624649859943, | |
| "grad_norm": 5.945260047912598, | |
| "learning_rate": 5.8684375e-06, | |
| "loss": 0.0724, | |
| "step": 6225 | |
| }, | |
| { | |
| "epoch": 2.917833800186741, | |
| "grad_norm": 3.371884822845459, | |
| "learning_rate": 5.860625e-06, | |
| "loss": 0.0961, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 2.9295051353874886, | |
| "grad_norm": 4.842737674713135, | |
| "learning_rate": 5.8528125e-06, | |
| "loss": 0.0748, | |
| "step": 6275 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 3.629974603652954, | |
| "learning_rate": 5.845000000000001e-06, | |
| "loss": 0.0897, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 2.9528478057889824, | |
| "grad_norm": 8.20695972442627, | |
| "learning_rate": 5.8371875e-06, | |
| "loss": 0.0718, | |
| "step": 6325 | |
| }, | |
| { | |
| "epoch": 2.9645191409897294, | |
| "grad_norm": 3.662733554840088, | |
| "learning_rate": 5.8296875e-06, | |
| "loss": 0.0885, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 2.9761904761904763, | |
| "grad_norm": 7.424181938171387, | |
| "learning_rate": 5.821875e-06, | |
| "loss": 0.0631, | |
| "step": 6375 | |
| }, | |
| { | |
| "epoch": 2.987861811391223, | |
| "grad_norm": 3.9309329986572266, | |
| "learning_rate": 5.814062500000001e-06, | |
| "loss": 0.0894, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 2.99953314659197, | |
| "grad_norm": 10.30614185333252, | |
| "learning_rate": 5.8062500000000005e-06, | |
| "loss": 0.087, | |
| "step": 6425 | |
| }, | |
| { | |
| "epoch": 3.011204481792717, | |
| "grad_norm": 4.544281005859375, | |
| "learning_rate": 5.7984375e-06, | |
| "loss": 0.04, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 3.022875816993464, | |
| "grad_norm": 9.070793151855469, | |
| "learning_rate": 5.790625e-06, | |
| "loss": 0.0373, | |
| "step": 6475 | |
| }, | |
| { | |
| "epoch": 3.034547152194211, | |
| "grad_norm": 7.368350982666016, | |
| "learning_rate": 5.782812500000001e-06, | |
| "loss": 0.0485, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.046218487394958, | |
| "grad_norm": 6.376898765563965, | |
| "learning_rate": 5.775000000000001e-06, | |
| "loss": 0.0474, | |
| "step": 6525 | |
| }, | |
| { | |
| "epoch": 3.0578898225957047, | |
| "grad_norm": 5.481170654296875, | |
| "learning_rate": 5.7671875e-06, | |
| "loss": 0.0458, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 3.069561157796452, | |
| "grad_norm": 10.094844818115234, | |
| "learning_rate": 5.759375e-06, | |
| "loss": 0.0451, | |
| "step": 6575 | |
| }, | |
| { | |
| "epoch": 3.081232492997199, | |
| "grad_norm": 0.9469685554504395, | |
| "learning_rate": 5.7515625e-06, | |
| "loss": 0.0465, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 3.092903828197946, | |
| "grad_norm": 4.808952331542969, | |
| "learning_rate": 5.743750000000001e-06, | |
| "loss": 0.0441, | |
| "step": 6625 | |
| }, | |
| { | |
| "epoch": 3.104575163398693, | |
| "grad_norm": 8.131449699401855, | |
| "learning_rate": 5.7359375e-06, | |
| "loss": 0.0396, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 3.11624649859944, | |
| "grad_norm": 6.750060081481934, | |
| "learning_rate": 5.728125e-06, | |
| "loss": 0.0611, | |
| "step": 6675 | |
| }, | |
| { | |
| "epoch": 3.1279178338001867, | |
| "grad_norm": 6.601670742034912, | |
| "learning_rate": 5.7203125e-06, | |
| "loss": 0.0415, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 3.1395891690009337, | |
| "grad_norm": 13.884129524230957, | |
| "learning_rate": 5.712500000000001e-06, | |
| "loss": 0.0417, | |
| "step": 6725 | |
| }, | |
| { | |
| "epoch": 3.1512605042016806, | |
| "grad_norm": 7.539254188537598, | |
| "learning_rate": 5.7046875e-06, | |
| "loss": 0.0413, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 3.1629318394024275, | |
| "grad_norm": 6.866730213165283, | |
| "learning_rate": 5.696875e-06, | |
| "loss": 0.055, | |
| "step": 6775 | |
| }, | |
| { | |
| "epoch": 3.1746031746031744, | |
| "grad_norm": 2.3453876972198486, | |
| "learning_rate": 5.6890625e-06, | |
| "loss": 0.0314, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 3.186274509803922, | |
| "grad_norm": 5.64259672164917, | |
| "learning_rate": 5.681250000000001e-06, | |
| "loss": 0.0446, | |
| "step": 6825 | |
| }, | |
| { | |
| "epoch": 3.1979458450046687, | |
| "grad_norm": 1.9124208688735962, | |
| "learning_rate": 5.6734375e-06, | |
| "loss": 0.0413, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 3.2096171802054156, | |
| "grad_norm": 8.153667449951172, | |
| "learning_rate": 5.6656250000000005e-06, | |
| "loss": 0.0482, | |
| "step": 6875 | |
| }, | |
| { | |
| "epoch": 3.2212885154061626, | |
| "grad_norm": 3.0059521198272705, | |
| "learning_rate": 5.6578125e-06, | |
| "loss": 0.0391, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 3.2329598506069095, | |
| "grad_norm": 7.093464374542236, | |
| "learning_rate": 5.65e-06, | |
| "loss": 0.0473, | |
| "step": 6925 | |
| }, | |
| { | |
| "epoch": 3.2446311858076564, | |
| "grad_norm": 2.2140514850616455, | |
| "learning_rate": 5.642187500000001e-06, | |
| "loss": 0.0472, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 3.2563025210084033, | |
| "grad_norm": 5.731634616851807, | |
| "learning_rate": 5.634375e-06, | |
| "loss": 0.0454, | |
| "step": 6975 | |
| }, | |
| { | |
| "epoch": 3.2679738562091503, | |
| "grad_norm": 2.6004838943481445, | |
| "learning_rate": 5.6265625e-06, | |
| "loss": 0.0379, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.279645191409897, | |
| "grad_norm": 6.271092414855957, | |
| "learning_rate": 5.61875e-06, | |
| "loss": 0.0447, | |
| "step": 7025 | |
| }, | |
| { | |
| "epoch": 3.291316526610644, | |
| "grad_norm": 14.229198455810547, | |
| "learning_rate": 5.610937500000001e-06, | |
| "loss": 0.0433, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 3.302987861811391, | |
| "grad_norm": 7.76876974105835, | |
| "learning_rate": 5.603125e-06, | |
| "loss": 0.0417, | |
| "step": 7075 | |
| }, | |
| { | |
| "epoch": 3.314659197012138, | |
| "grad_norm": 5.000005722045898, | |
| "learning_rate": 5.5953125000000005e-06, | |
| "loss": 0.0365, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 3.3263305322128853, | |
| "grad_norm": 5.754938125610352, | |
| "learning_rate": 5.5875e-06, | |
| "loss": 0.0483, | |
| "step": 7125 | |
| }, | |
| { | |
| "epoch": 3.3380018674136323, | |
| "grad_norm": 2.836254835128784, | |
| "learning_rate": 5.579687500000001e-06, | |
| "loss": 0.0439, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 3.349673202614379, | |
| "grad_norm": 6.115027904510498, | |
| "learning_rate": 5.571875e-06, | |
| "loss": 0.0518, | |
| "step": 7175 | |
| }, | |
| { | |
| "epoch": 3.361344537815126, | |
| "grad_norm": 4.021732330322266, | |
| "learning_rate": 5.5640625000000006e-06, | |
| "loss": 0.0413, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 3.373015873015873, | |
| "grad_norm": 12.889508247375488, | |
| "learning_rate": 5.55625e-06, | |
| "loss": 0.0608, | |
| "step": 7225 | |
| }, | |
| { | |
| "epoch": 3.38468720821662, | |
| "grad_norm": 5.332011699676514, | |
| "learning_rate": 5.5484375e-06, | |
| "loss": 0.0458, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 3.396358543417367, | |
| "grad_norm": 9.390791893005371, | |
| "learning_rate": 5.540625e-06, | |
| "loss": 0.0418, | |
| "step": 7275 | |
| }, | |
| { | |
| "epoch": 3.408029878618114, | |
| "grad_norm": 5.002245903015137, | |
| "learning_rate": 5.5328125e-06, | |
| "loss": 0.0431, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 3.4197012138188607, | |
| "grad_norm": 9.859498023986816, | |
| "learning_rate": 5.5250000000000005e-06, | |
| "loss": 0.0511, | |
| "step": 7325 | |
| }, | |
| { | |
| "epoch": 3.431372549019608, | |
| "grad_norm": 12.415291786193848, | |
| "learning_rate": 5.5171875e-06, | |
| "loss": 0.0441, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 3.443043884220355, | |
| "grad_norm": 4.821508884429932, | |
| "learning_rate": 5.509375e-06, | |
| "loss": 0.0466, | |
| "step": 7375 | |
| }, | |
| { | |
| "epoch": 3.454715219421102, | |
| "grad_norm": 3.222395420074463, | |
| "learning_rate": 5.5015625e-06, | |
| "loss": 0.043, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 3.466386554621849, | |
| "grad_norm": 11.607864379882812, | |
| "learning_rate": 5.4937500000000006e-06, | |
| "loss": 0.044, | |
| "step": 7425 | |
| }, | |
| { | |
| "epoch": 3.478057889822596, | |
| "grad_norm": 2.7468137741088867, | |
| "learning_rate": 5.4859375e-06, | |
| "loss": 0.0494, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 3.4897292250233427, | |
| "grad_norm": 5.353877067565918, | |
| "learning_rate": 5.478125e-06, | |
| "loss": 0.0439, | |
| "step": 7475 | |
| }, | |
| { | |
| "epoch": 3.5014005602240896, | |
| "grad_norm": 5.521659851074219, | |
| "learning_rate": 5.4703125e-06, | |
| "loss": 0.043, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.5130718954248366, | |
| "grad_norm": 11.562368392944336, | |
| "learning_rate": 5.462500000000001e-06, | |
| "loss": 0.0611, | |
| "step": 7525 | |
| }, | |
| { | |
| "epoch": 3.5247432306255835, | |
| "grad_norm": 2.4676475524902344, | |
| "learning_rate": 5.4546875000000004e-06, | |
| "loss": 0.0372, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 3.5364145658263304, | |
| "grad_norm": 7.735954761505127, | |
| "learning_rate": 5.446875e-06, | |
| "loss": 0.0434, | |
| "step": 7575 | |
| }, | |
| { | |
| "epoch": 3.5480859010270773, | |
| "grad_norm": 3.367266893386841, | |
| "learning_rate": 5.4390625e-06, | |
| "loss": 0.0488, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 3.5597572362278243, | |
| "grad_norm": 6.3219990730285645, | |
| "learning_rate": 5.43125e-06, | |
| "loss": 0.0488, | |
| "step": 7625 | |
| }, | |
| { | |
| "epoch": 3.571428571428571, | |
| "grad_norm": 5.415238857269287, | |
| "learning_rate": 5.4234375000000005e-06, | |
| "loss": 0.0481, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 3.5830999066293185, | |
| "grad_norm": 7.6133832931518555, | |
| "learning_rate": 5.415625e-06, | |
| "loss": 0.0379, | |
| "step": 7675 | |
| }, | |
| { | |
| "epoch": 3.5947712418300655, | |
| "grad_norm": 3.2077534198760986, | |
| "learning_rate": 5.4078125e-06, | |
| "loss": 0.0469, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 3.6064425770308124, | |
| "grad_norm": 9.553058624267578, | |
| "learning_rate": 5.4e-06, | |
| "loss": 0.044, | |
| "step": 7725 | |
| }, | |
| { | |
| "epoch": 3.6181139122315593, | |
| "grad_norm": 6.475897312164307, | |
| "learning_rate": 5.392187500000001e-06, | |
| "loss": 0.0388, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 3.6297852474323062, | |
| "grad_norm": 7.829625129699707, | |
| "learning_rate": 5.3843750000000004e-06, | |
| "loss": 0.0543, | |
| "step": 7775 | |
| }, | |
| { | |
| "epoch": 3.641456582633053, | |
| "grad_norm": 2.857725143432617, | |
| "learning_rate": 5.3765625e-06, | |
| "loss": 0.0456, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 3.6531279178338, | |
| "grad_norm": 9.913888931274414, | |
| "learning_rate": 5.36875e-06, | |
| "loss": 0.0588, | |
| "step": 7825 | |
| }, | |
| { | |
| "epoch": 3.664799253034547, | |
| "grad_norm": 6.124692916870117, | |
| "learning_rate": 5.360937500000001e-06, | |
| "loss": 0.0487, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 3.6764705882352944, | |
| "grad_norm": 5.036586284637451, | |
| "learning_rate": 5.3531250000000005e-06, | |
| "loss": 0.0381, | |
| "step": 7875 | |
| }, | |
| { | |
| "epoch": 3.6881419234360413, | |
| "grad_norm": 2.280762195587158, | |
| "learning_rate": 5.3453125e-06, | |
| "loss": 0.041, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 3.6998132586367882, | |
| "grad_norm": 5.175332546234131, | |
| "learning_rate": 5.3375e-06, | |
| "loss": 0.0439, | |
| "step": 7925 | |
| }, | |
| { | |
| "epoch": 3.711484593837535, | |
| "grad_norm": 6.605205535888672, | |
| "learning_rate": 5.3296875e-06, | |
| "loss": 0.052, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 3.723155929038282, | |
| "grad_norm": 8.107190132141113, | |
| "learning_rate": 5.321875000000001e-06, | |
| "loss": 0.0513, | |
| "step": 7975 | |
| }, | |
| { | |
| "epoch": 3.734827264239029, | |
| "grad_norm": 4.808969497680664, | |
| "learning_rate": 5.3140624999999996e-06, | |
| "loss": 0.0474, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.746498599439776, | |
| "grad_norm": 13.523513793945312, | |
| "learning_rate": 5.30625e-06, | |
| "loss": 0.0472, | |
| "step": 8025 | |
| }, | |
| { | |
| "epoch": 3.758169934640523, | |
| "grad_norm": 4.2439751625061035, | |
| "learning_rate": 5.2984375e-06, | |
| "loss": 0.0493, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 3.7698412698412698, | |
| "grad_norm": 19.3562068939209, | |
| "learning_rate": 5.290625000000001e-06, | |
| "loss": 0.0559, | |
| "step": 8075 | |
| }, | |
| { | |
| "epoch": 3.7815126050420167, | |
| "grad_norm": 5.023294448852539, | |
| "learning_rate": 5.2828125e-06, | |
| "loss": 0.0444, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 3.7931839402427636, | |
| "grad_norm": 10.296977996826172, | |
| "learning_rate": 5.275e-06, | |
| "loss": 0.0485, | |
| "step": 8125 | |
| }, | |
| { | |
| "epoch": 3.8048552754435105, | |
| "grad_norm": 1.339447259902954, | |
| "learning_rate": 5.2671875e-06, | |
| "loss": 0.0408, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 3.8165266106442575, | |
| "grad_norm": 8.966866493225098, | |
| "learning_rate": 5.259375000000001e-06, | |
| "loss": 0.0481, | |
| "step": 8175 | |
| }, | |
| { | |
| "epoch": 3.828197945845005, | |
| "grad_norm": 4.252060413360596, | |
| "learning_rate": 5.251562500000001e-06, | |
| "loss": 0.0452, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 3.8398692810457518, | |
| "grad_norm": 10.229138374328613, | |
| "learning_rate": 5.24375e-06, | |
| "loss": 0.0592, | |
| "step": 8225 | |
| }, | |
| { | |
| "epoch": 3.8515406162464987, | |
| "grad_norm": 1.4391601085662842, | |
| "learning_rate": 5.2359375e-06, | |
| "loss": 0.0453, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 3.8632119514472456, | |
| "grad_norm": 6.556412696838379, | |
| "learning_rate": 5.228125e-06, | |
| "loss": 0.0436, | |
| "step": 8275 | |
| }, | |
| { | |
| "epoch": 3.8748832866479925, | |
| "grad_norm": 4.541426658630371, | |
| "learning_rate": 5.220312500000001e-06, | |
| "loss": 0.0399, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 3.8865546218487395, | |
| "grad_norm": 5.626660346984863, | |
| "learning_rate": 5.2125e-06, | |
| "loss": 0.0526, | |
| "step": 8325 | |
| }, | |
| { | |
| "epoch": 3.8982259570494864, | |
| "grad_norm": 3.5642924308776855, | |
| "learning_rate": 5.2046875e-06, | |
| "loss": 0.041, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 3.9098972922502333, | |
| "grad_norm": 5.301916599273682, | |
| "learning_rate": 5.196875e-06, | |
| "loss": 0.0505, | |
| "step": 8375 | |
| }, | |
| { | |
| "epoch": 3.9215686274509802, | |
| "grad_norm": 4.125392913818359, | |
| "learning_rate": 5.189062500000001e-06, | |
| "loss": 0.0413, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 3.9332399626517276, | |
| "grad_norm": 10.192436218261719, | |
| "learning_rate": 5.18125e-06, | |
| "loss": 0.0531, | |
| "step": 8425 | |
| }, | |
| { | |
| "epoch": 3.9449112978524745, | |
| "grad_norm": 3.3052845001220703, | |
| "learning_rate": 5.1734375e-06, | |
| "loss": 0.0398, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 3.9565826330532214, | |
| "grad_norm": 6.241024494171143, | |
| "learning_rate": 5.165625e-06, | |
| "loss": 0.0408, | |
| "step": 8475 | |
| }, | |
| { | |
| "epoch": 3.9682539682539684, | |
| "grad_norm": 6.708200454711914, | |
| "learning_rate": 5.157812500000001e-06, | |
| "loss": 0.0516, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.9799253034547153, | |
| "grad_norm": 11.930779457092285, | |
| "learning_rate": 5.15e-06, | |
| "loss": 0.0452, | |
| "step": 8525 | |
| }, | |
| { | |
| "epoch": 3.991596638655462, | |
| "grad_norm": 7.160813808441162, | |
| "learning_rate": 5.1421875000000005e-06, | |
| "loss": 0.0455, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 4.003267973856209, | |
| "grad_norm": 1.401731014251709, | |
| "learning_rate": 5.134375e-06, | |
| "loss": 0.0453, | |
| "step": 8575 | |
| }, | |
| { | |
| "epoch": 4.014939309056956, | |
| "grad_norm": 1.890440821647644, | |
| "learning_rate": 5.1265625e-06, | |
| "loss": 0.0177, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 4.026610644257703, | |
| "grad_norm": 1.3520216941833496, | |
| "learning_rate": 5.11875e-06, | |
| "loss": 0.0305, | |
| "step": 8625 | |
| }, | |
| { | |
| "epoch": 4.03828197945845, | |
| "grad_norm": 4.4095025062561035, | |
| "learning_rate": 5.1109375e-06, | |
| "loss": 0.0227, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 4.049953314659197, | |
| "grad_norm": 2.4577364921569824, | |
| "learning_rate": 5.103125e-06, | |
| "loss": 0.036, | |
| "step": 8675 | |
| }, | |
| { | |
| "epoch": 4.061624649859944, | |
| "grad_norm": 3.378568410873413, | |
| "learning_rate": 5.0953125e-06, | |
| "loss": 0.0235, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 4.073295985060691, | |
| "grad_norm": 1.7685190439224243, | |
| "learning_rate": 5.0875e-06, | |
| "loss": 0.031, | |
| "step": 8725 | |
| }, | |
| { | |
| "epoch": 4.084967320261438, | |
| "grad_norm": 1.426932454109192, | |
| "learning_rate": 5.0796875e-06, | |
| "loss": 0.0184, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 4.0966386554621845, | |
| "grad_norm": 2.890690803527832, | |
| "learning_rate": 5.0718750000000005e-06, | |
| "loss": 0.0319, | |
| "step": 8775 | |
| }, | |
| { | |
| "epoch": 4.1083099906629315, | |
| "grad_norm": 2.438765287399292, | |
| "learning_rate": 5.0640625e-06, | |
| "loss": 0.0191, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 4.119981325863678, | |
| "grad_norm": 1.9891207218170166, | |
| "learning_rate": 5.056250000000001e-06, | |
| "loss": 0.031, | |
| "step": 8825 | |
| }, | |
| { | |
| "epoch": 4.131652661064426, | |
| "grad_norm": 2.288236141204834, | |
| "learning_rate": 5.0484375e-06, | |
| "loss": 0.0174, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 4.143323996265173, | |
| "grad_norm": 2.097827434539795, | |
| "learning_rate": 5.0406250000000005e-06, | |
| "loss": 0.0244, | |
| "step": 8875 | |
| }, | |
| { | |
| "epoch": 4.15499533146592, | |
| "grad_norm": 0.7743799090385437, | |
| "learning_rate": 5.0328125e-06, | |
| "loss": 0.0209, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 4.166666666666667, | |
| "grad_norm": 2.9196207523345947, | |
| "learning_rate": 5.025e-06, | |
| "loss": 0.0275, | |
| "step": 8925 | |
| }, | |
| { | |
| "epoch": 4.178338001867414, | |
| "grad_norm": 1.094561219215393, | |
| "learning_rate": 5.0171875e-06, | |
| "loss": 0.026, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 4.190009337068161, | |
| "grad_norm": 2.849806070327759, | |
| "learning_rate": 5.0096875000000005e-06, | |
| "loss": 0.0374, | |
| "step": 8975 | |
| }, | |
| { | |
| "epoch": 4.201680672268908, | |
| "grad_norm": 9.60171890258789, | |
| "learning_rate": 5.001875e-06, | |
| "loss": 0.0264, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 4.213352007469655, | |
| "grad_norm": 3.694355010986328, | |
| "learning_rate": 4.9940625e-06, | |
| "loss": 0.0355, | |
| "step": 9025 | |
| }, | |
| { | |
| "epoch": 4.225023342670402, | |
| "grad_norm": 5.392662525177002, | |
| "learning_rate": 4.98625e-06, | |
| "loss": 0.0242, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 4.2366946778711485, | |
| "grad_norm": 2.1022627353668213, | |
| "learning_rate": 4.9784375e-06, | |
| "loss": 0.0327, | |
| "step": 9075 | |
| }, | |
| { | |
| "epoch": 4.248366013071895, | |
| "grad_norm": 3.802021026611328, | |
| "learning_rate": 4.970625e-06, | |
| "loss": 0.0211, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 4.260037348272642, | |
| "grad_norm": 0.9553838968276978, | |
| "learning_rate": 4.9628125e-06, | |
| "loss": 0.0291, | |
| "step": 9125 | |
| }, | |
| { | |
| "epoch": 4.271708683473389, | |
| "grad_norm": 5.334795951843262, | |
| "learning_rate": 4.955e-06, | |
| "loss": 0.0209, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 4.283380018674136, | |
| "grad_norm": 1.5590300559997559, | |
| "learning_rate": 4.9471875e-06, | |
| "loss": 0.032, | |
| "step": 9175 | |
| }, | |
| { | |
| "epoch": 4.295051353874883, | |
| "grad_norm": 1.9582746028900146, | |
| "learning_rate": 4.9393750000000005e-06, | |
| "loss": 0.0285, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 4.30672268907563, | |
| "grad_norm": 5.399374485015869, | |
| "learning_rate": 4.9315625e-06, | |
| "loss": 0.0385, | |
| "step": 9225 | |
| }, | |
| { | |
| "epoch": 4.318394024276377, | |
| "grad_norm": 3.4703786373138428, | |
| "learning_rate": 4.92375e-06, | |
| "loss": 0.0185, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 4.330065359477124, | |
| "grad_norm": 3.748854637145996, | |
| "learning_rate": 4.9159375e-06, | |
| "loss": 0.0361, | |
| "step": 9275 | |
| }, | |
| { | |
| "epoch": 4.341736694677871, | |
| "grad_norm": 2.3994362354278564, | |
| "learning_rate": 4.9081250000000005e-06, | |
| "loss": 0.0257, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 4.353408029878618, | |
| "grad_norm": 1.0170806646347046, | |
| "learning_rate": 4.9003125e-06, | |
| "loss": 0.0344, | |
| "step": 9325 | |
| }, | |
| { | |
| "epoch": 4.365079365079365, | |
| "grad_norm": 1.4588912725448608, | |
| "learning_rate": 4.8925e-06, | |
| "loss": 0.0225, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 4.3767507002801125, | |
| "grad_norm": 2.9339776039123535, | |
| "learning_rate": 4.8846875e-06, | |
| "loss": 0.0317, | |
| "step": 9375 | |
| }, | |
| { | |
| "epoch": 4.388422035480859, | |
| "grad_norm": 3.1433396339416504, | |
| "learning_rate": 4.876875e-06, | |
| "loss": 0.0231, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 4.400093370681606, | |
| "grad_norm": 3.174156427383423, | |
| "learning_rate": 4.8690625000000004e-06, | |
| "loss": 0.0269, | |
| "step": 9425 | |
| }, | |
| { | |
| "epoch": 4.411764705882353, | |
| "grad_norm": 1.8732781410217285, | |
| "learning_rate": 4.86125e-06, | |
| "loss": 0.0305, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 4.4234360410831, | |
| "grad_norm": 1.5500296354293823, | |
| "learning_rate": 4.8534375e-06, | |
| "loss": 0.0351, | |
| "step": 9475 | |
| }, | |
| { | |
| "epoch": 4.435107376283847, | |
| "grad_norm": 3.1208136081695557, | |
| "learning_rate": 4.845625e-06, | |
| "loss": 0.022, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.446778711484594, | |
| "grad_norm": 2.964061975479126, | |
| "learning_rate": 4.8378125000000005e-06, | |
| "loss": 0.0383, | |
| "step": 9525 | |
| }, | |
| { | |
| "epoch": 4.458450046685341, | |
| "grad_norm": 4.548437118530273, | |
| "learning_rate": 4.83e-06, | |
| "loss": 0.0263, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 4.470121381886088, | |
| "grad_norm": 2.4414591789245605, | |
| "learning_rate": 4.8221875e-06, | |
| "loss": 0.0314, | |
| "step": 9575 | |
| }, | |
| { | |
| "epoch": 4.481792717086835, | |
| "grad_norm": 2.8750803470611572, | |
| "learning_rate": 4.814375e-06, | |
| "loss": 0.0254, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 4.493464052287582, | |
| "grad_norm": 1.9113430976867676, | |
| "learning_rate": 4.806562500000001e-06, | |
| "loss": 0.0365, | |
| "step": 9625 | |
| }, | |
| { | |
| "epoch": 4.505135387488329, | |
| "grad_norm": 1.8737727403640747, | |
| "learning_rate": 4.7987500000000004e-06, | |
| "loss": 0.0251, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 4.516806722689076, | |
| "grad_norm": 3.6277358531951904, | |
| "learning_rate": 4.7909375e-06, | |
| "loss": 0.0357, | |
| "step": 9675 | |
| }, | |
| { | |
| "epoch": 4.5284780578898225, | |
| "grad_norm": 0.974403440952301, | |
| "learning_rate": 4.783125e-06, | |
| "loss": 0.0172, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 4.540149393090569, | |
| "grad_norm": 5.103818893432617, | |
| "learning_rate": 4.7753125e-06, | |
| "loss": 0.0262, | |
| "step": 9725 | |
| }, | |
| { | |
| "epoch": 4.551820728291316, | |
| "grad_norm": 4.358363151550293, | |
| "learning_rate": 4.7675000000000005e-06, | |
| "loss": 0.0268, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 4.563492063492063, | |
| "grad_norm": 1.1133219003677368, | |
| "learning_rate": 4.7596875e-06, | |
| "loss": 0.0371, | |
| "step": 9775 | |
| }, | |
| { | |
| "epoch": 4.57516339869281, | |
| "grad_norm": 2.639396905899048, | |
| "learning_rate": 4.751875e-06, | |
| "loss": 0.0277, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 4.586834733893557, | |
| "grad_norm": 0.8341067433357239, | |
| "learning_rate": 4.7440625e-06, | |
| "loss": 0.0267, | |
| "step": 9825 | |
| }, | |
| { | |
| "epoch": 4.598506069094304, | |
| "grad_norm": 2.7689151763916016, | |
| "learning_rate": 4.736250000000001e-06, | |
| "loss": 0.0211, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 4.610177404295051, | |
| "grad_norm": 3.2999351024627686, | |
| "learning_rate": 4.7284374999999996e-06, | |
| "loss": 0.0374, | |
| "step": 9875 | |
| }, | |
| { | |
| "epoch": 4.621848739495798, | |
| "grad_norm": 1.2019790410995483, | |
| "learning_rate": 4.720625e-06, | |
| "loss": 0.0181, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 4.633520074696545, | |
| "grad_norm": 2.8706002235412598, | |
| "learning_rate": 4.7128125e-06, | |
| "loss": 0.0304, | |
| "step": 9925 | |
| }, | |
| { | |
| "epoch": 4.645191409897293, | |
| "grad_norm": 5.747146129608154, | |
| "learning_rate": 4.705000000000001e-06, | |
| "loss": 0.0229, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 4.6568627450980395, | |
| "grad_norm": 1.8742387294769287, | |
| "learning_rate": 4.6971875000000005e-06, | |
| "loss": 0.0418, | |
| "step": 9975 | |
| }, | |
| { | |
| "epoch": 4.6685340802987865, | |
| "grad_norm": 1.8577946424484253, | |
| "learning_rate": 4.689375e-06, | |
| "loss": 0.0156, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.6685340802987865, | |
| "eval_loss": 0.18312382698059082, | |
| "eval_runtime": 5443.8581, | |
| "eval_samples_per_second": 1.729, | |
| "eval_steps_per_second": 0.216, | |
| "eval_wer": 0.10030679799773938, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.680205415499533, | |
| "grad_norm": 1.9401777982711792, | |
| "learning_rate": 4.6815625e-06, | |
| "loss": 0.0271, | |
| "step": 10025 | |
| }, | |
| { | |
| "epoch": 4.69187675070028, | |
| "grad_norm": 5.094863414764404, | |
| "learning_rate": 4.67375e-06, | |
| "loss": 0.0245, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 4.703548085901027, | |
| "grad_norm": 3.0759990215301514, | |
| "learning_rate": 4.665937500000001e-06, | |
| "loss": 0.0408, | |
| "step": 10075 | |
| }, | |
| { | |
| "epoch": 4.715219421101774, | |
| "grad_norm": 1.7008417844772339, | |
| "learning_rate": 4.658125e-06, | |
| "loss": 0.0259, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 4.726890756302521, | |
| "grad_norm": 2.5551605224609375, | |
| "learning_rate": 4.6503125e-06, | |
| "loss": 0.0356, | |
| "step": 10125 | |
| }, | |
| { | |
| "epoch": 4.738562091503268, | |
| "grad_norm": 1.278176188468933, | |
| "learning_rate": 4.6425e-06, | |
| "loss": 0.024, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 4.750233426704015, | |
| "grad_norm": 3.679241418838501, | |
| "learning_rate": 4.634687500000001e-06, | |
| "loss": 0.038, | |
| "step": 10175 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 3.3556320667266846, | |
| "learning_rate": 4.626875e-06, | |
| "loss": 0.0295, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 4.773576097105509, | |
| "grad_norm": 2.3901469707489014, | |
| "learning_rate": 4.6190625e-06, | |
| "loss": 0.0326, | |
| "step": 10225 | |
| }, | |
| { | |
| "epoch": 4.785247432306256, | |
| "grad_norm": 2.4672956466674805, | |
| "learning_rate": 4.61125e-06, | |
| "loss": 0.0255, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 4.796918767507003, | |
| "grad_norm": 1.856067419052124, | |
| "learning_rate": 4.603437500000001e-06, | |
| "loss": 0.0472, | |
| "step": 10275 | |
| }, | |
| { | |
| "epoch": 4.80859010270775, | |
| "grad_norm": 3.6307425498962402, | |
| "learning_rate": 4.595625e-06, | |
| "loss": 0.0204, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 4.8202614379084965, | |
| "grad_norm": 3.4470720291137695, | |
| "learning_rate": 4.5878125e-06, | |
| "loss": 0.0266, | |
| "step": 10325 | |
| }, | |
| { | |
| "epoch": 4.831932773109243, | |
| "grad_norm": 3.720325231552124, | |
| "learning_rate": 4.58e-06, | |
| "loss": 0.0174, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 4.84360410830999, | |
| "grad_norm": 3.147507429122925, | |
| "learning_rate": 4.572187500000001e-06, | |
| "loss": 0.0353, | |
| "step": 10375 | |
| }, | |
| { | |
| "epoch": 4.855275443510737, | |
| "grad_norm": 0.47896313667297363, | |
| "learning_rate": 4.564375e-06, | |
| "loss": 0.0198, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 4.866946778711485, | |
| "grad_norm": 1.2566039562225342, | |
| "learning_rate": 4.5565625000000005e-06, | |
| "loss": 0.0326, | |
| "step": 10425 | |
| }, | |
| { | |
| "epoch": 4.878618113912232, | |
| "grad_norm": 6.644142150878906, | |
| "learning_rate": 4.54875e-06, | |
| "loss": 0.0292, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 4.890289449112979, | |
| "grad_norm": 4.639550685882568, | |
| "learning_rate": 4.5409375e-06, | |
| "loss": 0.0378, | |
| "step": 10475 | |
| }, | |
| { | |
| "epoch": 4.901960784313726, | |
| "grad_norm": 2.032776117324829, | |
| "learning_rate": 4.533125e-06, | |
| "loss": 0.0226, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.913632119514473, | |
| "grad_norm": 1.344425916671753, | |
| "learning_rate": 4.5253125e-06, | |
| "loss": 0.0368, | |
| "step": 10525 | |
| }, | |
| { | |
| "epoch": 4.92530345471522, | |
| "grad_norm": 0.8881208300590515, | |
| "learning_rate": 4.5175e-06, | |
| "loss": 0.0224, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 4.936974789915967, | |
| "grad_norm": 2.743755340576172, | |
| "learning_rate": 4.5096875e-06, | |
| "loss": 0.0417, | |
| "step": 10575 | |
| }, | |
| { | |
| "epoch": 4.9486461251167135, | |
| "grad_norm": 1.9883514642715454, | |
| "learning_rate": 4.501875000000001e-06, | |
| "loss": 0.0207, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 4.9603174603174605, | |
| "grad_norm": 4.254443168640137, | |
| "learning_rate": 4.4940625e-06, | |
| "loss": 0.0344, | |
| "step": 10625 | |
| }, | |
| { | |
| "epoch": 4.971988795518207, | |
| "grad_norm": 2.9644615650177, | |
| "learning_rate": 4.4862500000000005e-06, | |
| "loss": 0.0242, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 4.983660130718954, | |
| "grad_norm": 4.65371036529541, | |
| "learning_rate": 4.4784375e-06, | |
| "loss": 0.0402, | |
| "step": 10675 | |
| }, | |
| { | |
| "epoch": 4.995331465919701, | |
| "grad_norm": 1.430145025253296, | |
| "learning_rate": 4.470625000000001e-06, | |
| "loss": 0.0193, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 5.007002801120448, | |
| "grad_norm": 2.433776378631592, | |
| "learning_rate": 4.4628125e-06, | |
| "loss": 0.0217, | |
| "step": 10725 | |
| }, | |
| { | |
| "epoch": 5.018674136321195, | |
| "grad_norm": 0.8967903256416321, | |
| "learning_rate": 4.4550000000000005e-06, | |
| "loss": 0.0167, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 5.030345471521942, | |
| "grad_norm": 3.4592394828796387, | |
| "learning_rate": 4.4471875e-06, | |
| "loss": 0.0275, | |
| "step": 10775 | |
| }, | |
| { | |
| "epoch": 5.042016806722689, | |
| "grad_norm": 0.6761863827705383, | |
| "learning_rate": 4.439375e-06, | |
| "loss": 0.0153, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 5.053688141923436, | |
| "grad_norm": 0.43812835216522217, | |
| "learning_rate": 4.4315625e-06, | |
| "loss": 0.0195, | |
| "step": 10825 | |
| }, | |
| { | |
| "epoch": 5.065359477124183, | |
| "grad_norm": 1.3948005437850952, | |
| "learning_rate": 4.42375e-06, | |
| "loss": 0.017, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 5.07703081232493, | |
| "grad_norm": 2.06145977973938, | |
| "learning_rate": 4.4159375000000004e-06, | |
| "loss": 0.026, | |
| "step": 10875 | |
| }, | |
| { | |
| "epoch": 5.088702147525677, | |
| "grad_norm": 3.0333502292633057, | |
| "learning_rate": 4.408125e-06, | |
| "loss": 0.0146, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 5.1003734827264235, | |
| "grad_norm": 2.764770746231079, | |
| "learning_rate": 4.4003125e-06, | |
| "loss": 0.0186, | |
| "step": 10925 | |
| }, | |
| { | |
| "epoch": 5.1120448179271705, | |
| "grad_norm": 2.536029577255249, | |
| "learning_rate": 4.3925e-06, | |
| "loss": 0.0161, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 5.123716153127917, | |
| "grad_norm": 2.648541212081909, | |
| "learning_rate": 4.3846875000000005e-06, | |
| "loss": 0.0217, | |
| "step": 10975 | |
| }, | |
| { | |
| "epoch": 5.135387488328665, | |
| "grad_norm": 4.795249938964844, | |
| "learning_rate": 4.376875e-06, | |
| "loss": 0.0116, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 5.147058823529412, | |
| "grad_norm": 0.7834287285804749, | |
| "learning_rate": 4.3690625e-06, | |
| "loss": 0.023, | |
| "step": 11025 | |
| }, | |
| { | |
| "epoch": 5.158730158730159, | |
| "grad_norm": 6.7206010818481445, | |
| "learning_rate": 4.36125e-06, | |
| "loss": 0.0188, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 5.170401493930906, | |
| "grad_norm": 0.3784288763999939, | |
| "learning_rate": 4.353437500000001e-06, | |
| "loss": 0.0187, | |
| "step": 11075 | |
| }, | |
| { | |
| "epoch": 5.182072829131653, | |
| "grad_norm": 5.990387439727783, | |
| "learning_rate": 4.3456250000000004e-06, | |
| "loss": 0.0131, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 5.1937441643324, | |
| "grad_norm": 2.445591449737549, | |
| "learning_rate": 4.3378125e-06, | |
| "loss": 0.0293, | |
| "step": 11125 | |
| }, | |
| { | |
| "epoch": 5.205415499533147, | |
| "grad_norm": 3.114480495452881, | |
| "learning_rate": 4.33e-06, | |
| "loss": 0.0132, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 5.217086834733894, | |
| "grad_norm": 0.6976014971733093, | |
| "learning_rate": 4.3221875e-06, | |
| "loss": 0.0254, | |
| "step": 11175 | |
| }, | |
| { | |
| "epoch": 5.228758169934641, | |
| "grad_norm": 6.35882568359375, | |
| "learning_rate": 4.3143750000000005e-06, | |
| "loss": 0.017, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 5.2404295051353875, | |
| "grad_norm": 2.0138509273529053, | |
| "learning_rate": 4.3065625e-06, | |
| "loss": 0.0236, | |
| "step": 11225 | |
| }, | |
| { | |
| "epoch": 5.2521008403361344, | |
| "grad_norm": 3.1038243770599365, | |
| "learning_rate": 4.29875e-06, | |
| "loss": 0.015, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 5.263772175536881, | |
| "grad_norm": 2.8752825260162354, | |
| "learning_rate": 4.2909375e-06, | |
| "loss": 0.0193, | |
| "step": 11275 | |
| }, | |
| { | |
| "epoch": 5.275443510737628, | |
| "grad_norm": 1.1929106712341309, | |
| "learning_rate": 4.283125000000001e-06, | |
| "loss": 0.0114, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 5.287114845938375, | |
| "grad_norm": 2.3317930698394775, | |
| "learning_rate": 4.2753125e-06, | |
| "loss": 0.0236, | |
| "step": 11325 | |
| }, | |
| { | |
| "epoch": 5.298786181139122, | |
| "grad_norm": 2.8288731575012207, | |
| "learning_rate": 4.2675e-06, | |
| "loss": 0.0182, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 5.310457516339869, | |
| "grad_norm": 4.622555255889893, | |
| "learning_rate": 4.2596875e-06, | |
| "loss": 0.0317, | |
| "step": 11375 | |
| }, | |
| { | |
| "epoch": 5.322128851540616, | |
| "grad_norm": 0.40077078342437744, | |
| "learning_rate": 4.251875000000001e-06, | |
| "loss": 0.0117, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 5.333800186741363, | |
| "grad_norm": 0.6447650194168091, | |
| "learning_rate": 4.2440625000000005e-06, | |
| "loss": 0.0213, | |
| "step": 11425 | |
| }, | |
| { | |
| "epoch": 5.34547152194211, | |
| "grad_norm": 4.721693992614746, | |
| "learning_rate": 4.23625e-06, | |
| "loss": 0.0145, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 5.357142857142857, | |
| "grad_norm": 4.699221134185791, | |
| "learning_rate": 4.2284375e-06, | |
| "loss": 0.0213, | |
| "step": 11475 | |
| }, | |
| { | |
| "epoch": 5.368814192343605, | |
| "grad_norm": 1.0902756452560425, | |
| "learning_rate": 4.220625e-06, | |
| "loss": 0.0135, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 5.3804855275443515, | |
| "grad_norm": 3.20731258392334, | |
| "learning_rate": 4.212812500000001e-06, | |
| "loss": 0.0192, | |
| "step": 11525 | |
| }, | |
| { | |
| "epoch": 5.392156862745098, | |
| "grad_norm": 3.498342752456665, | |
| "learning_rate": 4.2049999999999996e-06, | |
| "loss": 0.0131, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 5.403828197945845, | |
| "grad_norm": 0.2736945152282715, | |
| "learning_rate": 4.1971875e-06, | |
| "loss": 0.0191, | |
| "step": 11575 | |
| }, | |
| { | |
| "epoch": 5.415499533146592, | |
| "grad_norm": 0.33990904688835144, | |
| "learning_rate": 4.189375e-06, | |
| "loss": 0.0131, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 5.427170868347339, | |
| "grad_norm": 4.783412456512451, | |
| "learning_rate": 4.181562500000001e-06, | |
| "loss": 0.0235, | |
| "step": 11625 | |
| }, | |
| { | |
| "epoch": 5.438842203548086, | |
| "grad_norm": 4.162958145141602, | |
| "learning_rate": 4.17375e-06, | |
| "loss": 0.0168, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 5.450513538748833, | |
| "grad_norm": 2.0236053466796875, | |
| "learning_rate": 4.1659375e-06, | |
| "loss": 0.0321, | |
| "step": 11675 | |
| }, | |
| { | |
| "epoch": 5.46218487394958, | |
| "grad_norm": 5.59421443939209, | |
| "learning_rate": 4.158125e-06, | |
| "loss": 0.0116, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 5.473856209150327, | |
| "grad_norm": 1.2957547903060913, | |
| "learning_rate": 4.150312500000001e-06, | |
| "loss": 0.0187, | |
| "step": 11725 | |
| }, | |
| { | |
| "epoch": 5.485527544351074, | |
| "grad_norm": 2.75832462310791, | |
| "learning_rate": 4.1425e-06, | |
| "loss": 0.0189, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 5.497198879551821, | |
| "grad_norm": 2.776012659072876, | |
| "learning_rate": 4.1346875e-06, | |
| "loss": 0.0235, | |
| "step": 11775 | |
| }, | |
| { | |
| "epoch": 5.508870214752568, | |
| "grad_norm": 4.952755451202393, | |
| "learning_rate": 4.126875e-06, | |
| "loss": 0.024, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 5.520541549953315, | |
| "grad_norm": 1.2413980960845947, | |
| "learning_rate": 4.1190625e-06, | |
| "loss": 0.0248, | |
| "step": 11825 | |
| }, | |
| { | |
| "epoch": 5.5322128851540615, | |
| "grad_norm": 4.319220066070557, | |
| "learning_rate": 4.111250000000001e-06, | |
| "loss": 0.0176, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 5.543884220354808, | |
| "grad_norm": 2.8155884742736816, | |
| "learning_rate": 4.1034375e-06, | |
| "loss": 0.0226, | |
| "step": 11875 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 3.499506950378418, | |
| "learning_rate": 4.095625e-06, | |
| "loss": 0.0118, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 5.567226890756302, | |
| "grad_norm": 3.1512813568115234, | |
| "learning_rate": 4.0878125e-06, | |
| "loss": 0.0157, | |
| "step": 11925 | |
| }, | |
| { | |
| "epoch": 5.578898225957049, | |
| "grad_norm": 4.766519546508789, | |
| "learning_rate": 4.080000000000001e-06, | |
| "loss": 0.0184, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 5.590569561157796, | |
| "grad_norm": 2.901200294494629, | |
| "learning_rate": 4.0721875e-06, | |
| "loss": 0.0198, | |
| "step": 11975 | |
| }, | |
| { | |
| "epoch": 5.602240896358543, | |
| "grad_norm": 2.888226270675659, | |
| "learning_rate": 4.064375e-06, | |
| "loss": 0.0191, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 5.61391223155929, | |
| "grad_norm": 1.0496464967727661, | |
| "learning_rate": 4.0565625e-06, | |
| "loss": 0.0219, | |
| "step": 12025 | |
| }, | |
| { | |
| "epoch": 5.625583566760037, | |
| "grad_norm": 0.7852717041969299, | |
| "learning_rate": 4.048750000000001e-06, | |
| "loss": 0.0177, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 5.637254901960784, | |
| "grad_norm": 2.5804331302642822, | |
| "learning_rate": 4.0409375e-06, | |
| "loss": 0.0241, | |
| "step": 12075 | |
| }, | |
| { | |
| "epoch": 5.648926237161532, | |
| "grad_norm": 1.4901975393295288, | |
| "learning_rate": 4.0331250000000005e-06, | |
| "loss": 0.0183, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 5.660597572362279, | |
| "grad_norm": 3.2913360595703125, | |
| "learning_rate": 4.0253125e-06, | |
| "loss": 0.0194, | |
| "step": 12125 | |
| }, | |
| { | |
| "epoch": 5.6722689075630255, | |
| "grad_norm": 3.6681406497955322, | |
| "learning_rate": 4.0175e-06, | |
| "loss": 0.0149, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 5.683940242763772, | |
| "grad_norm": 2.2549614906311035, | |
| "learning_rate": 4.0096875e-06, | |
| "loss": 0.023, | |
| "step": 12175 | |
| }, | |
| { | |
| "epoch": 5.695611577964519, | |
| "grad_norm": 10.556268692016602, | |
| "learning_rate": 4.001875e-06, | |
| "loss": 0.0179, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 5.707282913165266, | |
| "grad_norm": 2.5755960941314697, | |
| "learning_rate": 3.9940625e-06, | |
| "loss": 0.0215, | |
| "step": 12225 | |
| }, | |
| { | |
| "epoch": 5.718954248366013, | |
| "grad_norm": 1.8617174625396729, | |
| "learning_rate": 3.98625e-06, | |
| "loss": 0.017, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 5.73062558356676, | |
| "grad_norm": 3.4985668659210205, | |
| "learning_rate": 3.9784375e-06, | |
| "loss": 0.0299, | |
| "step": 12275 | |
| }, | |
| { | |
| "epoch": 5.742296918767507, | |
| "grad_norm": 9.18930435180664, | |
| "learning_rate": 3.970625e-06, | |
| "loss": 0.0157, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 5.753968253968254, | |
| "grad_norm": 3.4537224769592285, | |
| "learning_rate": 3.9628125000000004e-06, | |
| "loss": 0.0231, | |
| "step": 12325 | |
| }, | |
| { | |
| "epoch": 5.765639589169001, | |
| "grad_norm": 3.9688210487365723, | |
| "learning_rate": 3.955e-06, | |
| "loss": 0.0205, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 5.777310924369748, | |
| "grad_norm": 1.72626793384552, | |
| "learning_rate": 3.9471875e-06, | |
| "loss": 0.0225, | |
| "step": 12375 | |
| }, | |
| { | |
| "epoch": 5.788982259570495, | |
| "grad_norm": 2.350785493850708, | |
| "learning_rate": 3.939375e-06, | |
| "loss": 0.0137, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 5.800653594771242, | |
| "grad_norm": 3.5603792667388916, | |
| "learning_rate": 3.931875e-06, | |
| "loss": 0.0252, | |
| "step": 12425 | |
| }, | |
| { | |
| "epoch": 5.812324929971989, | |
| "grad_norm": 0.25176432728767395, | |
| "learning_rate": 3.9240625e-06, | |
| "loss": 0.0202, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 5.8239962651727355, | |
| "grad_norm": 4.103959083557129, | |
| "learning_rate": 3.916250000000001e-06, | |
| "loss": 0.0201, | |
| "step": 12475 | |
| }, | |
| { | |
| "epoch": 5.835667600373482, | |
| "grad_norm": 5.1462202072143555, | |
| "learning_rate": 3.9084375e-06, | |
| "loss": 0.014, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 5.847338935574229, | |
| "grad_norm": 1.2658880949020386, | |
| "learning_rate": 3.9006250000000005e-06, | |
| "loss": 0.0224, | |
| "step": 12525 | |
| }, | |
| { | |
| "epoch": 5.859010270774976, | |
| "grad_norm": 1.1250051259994507, | |
| "learning_rate": 3.8928125e-06, | |
| "loss": 0.013, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 5.870681605975724, | |
| "grad_norm": 0.4671033024787903, | |
| "learning_rate": 3.885e-06, | |
| "loss": 0.0222, | |
| "step": 12575 | |
| }, | |
| { | |
| "epoch": 5.882352941176471, | |
| "grad_norm": 4.812198638916016, | |
| "learning_rate": 3.8771875e-06, | |
| "loss": 0.013, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 5.894024276377218, | |
| "grad_norm": 6.955799102783203, | |
| "learning_rate": 3.869375e-06, | |
| "loss": 0.0216, | |
| "step": 12625 | |
| }, | |
| { | |
| "epoch": 5.905695611577965, | |
| "grad_norm": 9.038055419921875, | |
| "learning_rate": 3.8615625e-06, | |
| "loss": 0.0147, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 5.917366946778712, | |
| "grad_norm": 2.660266399383545, | |
| "learning_rate": 3.85375e-06, | |
| "loss": 0.0179, | |
| "step": 12675 | |
| }, | |
| { | |
| "epoch": 5.929038281979459, | |
| "grad_norm": 3.986816167831421, | |
| "learning_rate": 3.8459375e-06, | |
| "loss": 0.0175, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 5.940709617180206, | |
| "grad_norm": 1.7132847309112549, | |
| "learning_rate": 3.838125e-06, | |
| "loss": 0.0243, | |
| "step": 12725 | |
| }, | |
| { | |
| "epoch": 5.9523809523809526, | |
| "grad_norm": 1.878422498703003, | |
| "learning_rate": 3.8303125000000004e-06, | |
| "loss": 0.0191, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 5.9640522875816995, | |
| "grad_norm": 1.7959318161010742, | |
| "learning_rate": 3.8225e-06, | |
| "loss": 0.0285, | |
| "step": 12775 | |
| }, | |
| { | |
| "epoch": 5.975723622782446, | |
| "grad_norm": 7.094222068786621, | |
| "learning_rate": 3.8146875e-06, | |
| "loss": 0.019, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 5.987394957983193, | |
| "grad_norm": 2.3803250789642334, | |
| "learning_rate": 3.806875e-06, | |
| "loss": 0.027, | |
| "step": 12825 | |
| }, | |
| { | |
| "epoch": 5.99906629318394, | |
| "grad_norm": 5.211573123931885, | |
| "learning_rate": 3.7990625e-06, | |
| "loss": 0.0239, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 6.010737628384687, | |
| "grad_norm": 2.943984270095825, | |
| "learning_rate": 3.7912500000000003e-06, | |
| "loss": 0.0156, | |
| "step": 12875 | |
| }, | |
| { | |
| "epoch": 6.022408963585434, | |
| "grad_norm": 2.1434903144836426, | |
| "learning_rate": 3.7834375000000006e-06, | |
| "loss": 0.0147, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 6.034080298786181, | |
| "grad_norm": 0.33908581733703613, | |
| "learning_rate": 3.775625e-06, | |
| "loss": 0.0089, | |
| "step": 12925 | |
| }, | |
| { | |
| "epoch": 6.045751633986928, | |
| "grad_norm": 7.022948265075684, | |
| "learning_rate": 3.7678125e-06, | |
| "loss": 0.0165, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 6.057422969187675, | |
| "grad_norm": 1.1056474447250366, | |
| "learning_rate": 3.7600000000000004e-06, | |
| "loss": 0.0154, | |
| "step": 12975 | |
| }, | |
| { | |
| "epoch": 6.069094304388422, | |
| "grad_norm": 3.8569955825805664, | |
| "learning_rate": 3.7521875000000007e-06, | |
| "loss": 0.0149, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 6.080765639589169, | |
| "grad_norm": 2.6585159301757812, | |
| "learning_rate": 3.744375e-06, | |
| "loss": 0.0147, | |
| "step": 13025 | |
| }, | |
| { | |
| "epoch": 6.092436974789916, | |
| "grad_norm": 3.2226240634918213, | |
| "learning_rate": 3.7365625000000003e-06, | |
| "loss": 0.0119, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 6.104108309990663, | |
| "grad_norm": 1.7068639993667603, | |
| "learning_rate": 3.7290625000000003e-06, | |
| "loss": 0.013, | |
| "step": 13075 | |
| }, | |
| { | |
| "epoch": 6.1157796451914095, | |
| "grad_norm": 0.6673070788383484, | |
| "learning_rate": 3.7212500000000006e-06, | |
| "loss": 0.0097, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 6.127450980392156, | |
| "grad_norm": 0.041345566511154175, | |
| "learning_rate": 3.7134375e-06, | |
| "loss": 0.0115, | |
| "step": 13125 | |
| }, | |
| { | |
| "epoch": 6.139122315592904, | |
| "grad_norm": 0.7863844037055969, | |
| "learning_rate": 3.705625e-06, | |
| "loss": 0.0126, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 6.150793650793651, | |
| "grad_norm": 2.8898963928222656, | |
| "learning_rate": 3.6978125000000004e-06, | |
| "loss": 0.0151, | |
| "step": 13175 | |
| }, | |
| { | |
| "epoch": 6.162464985994398, | |
| "grad_norm": 4.4687299728393555, | |
| "learning_rate": 3.6900000000000002e-06, | |
| "loss": 0.0145, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 6.174136321195145, | |
| "grad_norm": 2.697178602218628, | |
| "learning_rate": 3.6821875e-06, | |
| "loss": 0.0136, | |
| "step": 13225 | |
| }, | |
| { | |
| "epoch": 6.185807656395892, | |
| "grad_norm": 7.974569320678711, | |
| "learning_rate": 3.674375e-06, | |
| "loss": 0.0129, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 6.197478991596639, | |
| "grad_norm": 0.35622915625572205, | |
| "learning_rate": 3.6665625e-06, | |
| "loss": 0.0168, | |
| "step": 13275 | |
| }, | |
| { | |
| "epoch": 6.209150326797386, | |
| "grad_norm": 6.407752990722656, | |
| "learning_rate": 3.6587500000000003e-06, | |
| "loss": 0.0135, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 6.220821661998133, | |
| "grad_norm": 0.7060608267784119, | |
| "learning_rate": 3.6509374999999997e-06, | |
| "loss": 0.0113, | |
| "step": 13325 | |
| }, | |
| { | |
| "epoch": 6.23249299719888, | |
| "grad_norm": 0.6277226805686951, | |
| "learning_rate": 3.643125e-06, | |
| "loss": 0.0124, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 6.2441643323996265, | |
| "grad_norm": 3.3179471492767334, | |
| "learning_rate": 3.6353125e-06, | |
| "loss": 0.0128, | |
| "step": 13375 | |
| }, | |
| { | |
| "epoch": 6.2558356676003735, | |
| "grad_norm": 2.2590084075927734, | |
| "learning_rate": 3.6275000000000004e-06, | |
| "loss": 0.0137, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 6.26750700280112, | |
| "grad_norm": 0.3138970136642456, | |
| "learning_rate": 3.6196875000000007e-06, | |
| "loss": 0.0105, | |
| "step": 13425 | |
| }, | |
| { | |
| "epoch": 6.279178338001867, | |
| "grad_norm": 4.370602607727051, | |
| "learning_rate": 3.611875e-06, | |
| "loss": 0.0106, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 6.290849673202614, | |
| "grad_norm": 0.7395113706588745, | |
| "learning_rate": 3.6040625000000003e-06, | |
| "loss": 0.0074, | |
| "step": 13475 | |
| }, | |
| { | |
| "epoch": 6.302521008403361, | |
| "grad_norm": 4.352066516876221, | |
| "learning_rate": 3.5962500000000005e-06, | |
| "loss": 0.0148, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 6.314192343604108, | |
| "grad_norm": 4.510288715362549, | |
| "learning_rate": 3.5884375000000003e-06, | |
| "loss": 0.0127, | |
| "step": 13525 | |
| }, | |
| { | |
| "epoch": 6.325863678804855, | |
| "grad_norm": 6.977252960205078, | |
| "learning_rate": 3.580625e-06, | |
| "loss": 0.0163, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 6.337535014005602, | |
| "grad_norm": 3.6490318775177, | |
| "learning_rate": 3.5728125e-06, | |
| "loss": 0.0127, | |
| "step": 13575 | |
| }, | |
| { | |
| "epoch": 6.349206349206349, | |
| "grad_norm": 2.546675682067871, | |
| "learning_rate": 3.565e-06, | |
| "loss": 0.0123, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 6.360877684407096, | |
| "grad_norm": 9.396807670593262, | |
| "learning_rate": 3.5571875000000004e-06, | |
| "loss": 0.0155, | |
| "step": 13625 | |
| }, | |
| { | |
| "epoch": 6.372549019607844, | |
| "grad_norm": 5.870864391326904, | |
| "learning_rate": 3.549375e-06, | |
| "loss": 0.0153, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 6.3842203548085905, | |
| "grad_norm": 0.08212006092071533, | |
| "learning_rate": 3.5415625e-06, | |
| "loss": 0.0113, | |
| "step": 13675 | |
| }, | |
| { | |
| "epoch": 6.395891690009337, | |
| "grad_norm": 1.5073678493499756, | |
| "learning_rate": 3.5337500000000003e-06, | |
| "loss": 0.0148, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 6.407563025210084, | |
| "grad_norm": 1.6626029014587402, | |
| "learning_rate": 3.5259375000000005e-06, | |
| "loss": 0.0206, | |
| "step": 13725 | |
| }, | |
| { | |
| "epoch": 6.419234360410831, | |
| "grad_norm": 5.561774730682373, | |
| "learning_rate": 3.518125e-06, | |
| "loss": 0.0219, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 6.430905695611578, | |
| "grad_norm": 3.8881995677948, | |
| "learning_rate": 3.5103125e-06, | |
| "loss": 0.0194, | |
| "step": 13775 | |
| }, | |
| { | |
| "epoch": 6.442577030812325, | |
| "grad_norm": 6.549841403961182, | |
| "learning_rate": 3.5025000000000003e-06, | |
| "loss": 0.014, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 6.454248366013072, | |
| "grad_norm": 0.38337138295173645, | |
| "learning_rate": 3.4946875000000006e-06, | |
| "loss": 0.0125, | |
| "step": 13825 | |
| }, | |
| { | |
| "epoch": 6.465919701213819, | |
| "grad_norm": 7.83842658996582, | |
| "learning_rate": 3.486875e-06, | |
| "loss": 0.0117, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 6.477591036414566, | |
| "grad_norm": 2.4902381896972656, | |
| "learning_rate": 3.4790625e-06, | |
| "loss": 0.0154, | |
| "step": 13875 | |
| }, | |
| { | |
| "epoch": 6.489262371615313, | |
| "grad_norm": 2.7067272663116455, | |
| "learning_rate": 3.47125e-06, | |
| "loss": 0.0145, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 6.50093370681606, | |
| "grad_norm": 0.13609760999679565, | |
| "learning_rate": 3.4634375000000002e-06, | |
| "loss": 0.013, | |
| "step": 13925 | |
| }, | |
| { | |
| "epoch": 6.512605042016807, | |
| "grad_norm": 7.123418807983398, | |
| "learning_rate": 3.4556249999999996e-06, | |
| "loss": 0.0135, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 6.524276377217554, | |
| "grad_norm": 2.5809738636016846, | |
| "learning_rate": 3.4478125e-06, | |
| "loss": 0.013, | |
| "step": 13975 | |
| }, | |
| { | |
| "epoch": 6.5359477124183005, | |
| "grad_norm": 3.8302764892578125, | |
| "learning_rate": 3.44e-06, | |
| "loss": 0.0123, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 6.5476190476190474, | |
| "grad_norm": 0.38114723563194275, | |
| "learning_rate": 3.4321875000000003e-06, | |
| "loss": 0.0123, | |
| "step": 14025 | |
| }, | |
| { | |
| "epoch": 6.559290382819794, | |
| "grad_norm": 1.6169977188110352, | |
| "learning_rate": 3.4243750000000006e-06, | |
| "loss": 0.0139, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 6.570961718020541, | |
| "grad_norm": 0.527672529220581, | |
| "learning_rate": 3.4165625e-06, | |
| "loss": 0.0137, | |
| "step": 14075 | |
| }, | |
| { | |
| "epoch": 6.582633053221288, | |
| "grad_norm": 4.989930152893066, | |
| "learning_rate": 3.40875e-06, | |
| "loss": 0.0108, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 6.594304388422035, | |
| "grad_norm": 0.13473570346832275, | |
| "learning_rate": 3.4009375000000004e-06, | |
| "loss": 0.0159, | |
| "step": 14125 | |
| }, | |
| { | |
| "epoch": 6.605975723622782, | |
| "grad_norm": 3.537700891494751, | |
| "learning_rate": 3.3931250000000007e-06, | |
| "loss": 0.0201, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 6.617647058823529, | |
| "grad_norm": 2.97955060005188, | |
| "learning_rate": 3.3853125e-06, | |
| "loss": 0.0106, | |
| "step": 14175 | |
| }, | |
| { | |
| "epoch": 6.629318394024276, | |
| "grad_norm": 0.7965431809425354, | |
| "learning_rate": 3.3775000000000003e-06, | |
| "loss": 0.016, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 6.640989729225024, | |
| "grad_norm": 2.8173744678497314, | |
| "learning_rate": 3.3696875e-06, | |
| "loss": 0.0169, | |
| "step": 14225 | |
| }, | |
| { | |
| "epoch": 6.652661064425771, | |
| "grad_norm": 0.6731769442558289, | |
| "learning_rate": 3.3618750000000003e-06, | |
| "loss": 0.0118, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 6.664332399626518, | |
| "grad_norm": 3.4868786334991455, | |
| "learning_rate": 3.3540624999999997e-06, | |
| "loss": 0.0149, | |
| "step": 14275 | |
| }, | |
| { | |
| "epoch": 6.6760037348272645, | |
| "grad_norm": 7.706684112548828, | |
| "learning_rate": 3.34625e-06, | |
| "loss": 0.0211, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 6.687675070028011, | |
| "grad_norm": 3.9315950870513916, | |
| "learning_rate": 3.3384375e-06, | |
| "loss": 0.0122, | |
| "step": 14325 | |
| }, | |
| { | |
| "epoch": 6.699346405228758, | |
| "grad_norm": 0.4107113778591156, | |
| "learning_rate": 3.3306250000000004e-06, | |
| "loss": 0.0132, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 6.711017740429505, | |
| "grad_norm": 0.8928655982017517, | |
| "learning_rate": 3.3228125e-06, | |
| "loss": 0.0132, | |
| "step": 14375 | |
| }, | |
| { | |
| "epoch": 6.722689075630252, | |
| "grad_norm": 0.32426151633262634, | |
| "learning_rate": 3.315e-06, | |
| "loss": 0.0121, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 6.734360410830999, | |
| "grad_norm": 0.9105150103569031, | |
| "learning_rate": 3.3071875000000003e-06, | |
| "loss": 0.0134, | |
| "step": 14425 | |
| }, | |
| { | |
| "epoch": 6.746031746031746, | |
| "grad_norm": 4.484381198883057, | |
| "learning_rate": 3.2993750000000005e-06, | |
| "loss": 0.012, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 6.757703081232493, | |
| "grad_norm": 1.9971312284469604, | |
| "learning_rate": 3.2915625e-06, | |
| "loss": 0.0129, | |
| "step": 14475 | |
| }, | |
| { | |
| "epoch": 6.76937441643324, | |
| "grad_norm": 5.409192085266113, | |
| "learning_rate": 3.28375e-06, | |
| "loss": 0.0142, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 6.781045751633987, | |
| "grad_norm": 0.35186824202537537, | |
| "learning_rate": 3.2759375000000003e-06, | |
| "loss": 0.0155, | |
| "step": 14525 | |
| }, | |
| { | |
| "epoch": 6.792717086834734, | |
| "grad_norm": 8.460790634155273, | |
| "learning_rate": 3.268125e-06, | |
| "loss": 0.0119, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 6.804388422035481, | |
| "grad_norm": 2.0943799018859863, | |
| "learning_rate": 3.2603125e-06, | |
| "loss": 0.0121, | |
| "step": 14575 | |
| }, | |
| { | |
| "epoch": 6.816059757236228, | |
| "grad_norm": 7.832350730895996, | |
| "learning_rate": 3.2525e-06, | |
| "loss": 0.0189, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 6.8277310924369745, | |
| "grad_norm": 0.39846083521842957, | |
| "learning_rate": 3.2446875e-06, | |
| "loss": 0.0134, | |
| "step": 14625 | |
| }, | |
| { | |
| "epoch": 6.839402427637721, | |
| "grad_norm": 7.057211875915527, | |
| "learning_rate": 3.2368750000000002e-06, | |
| "loss": 0.0133, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 6.851073762838468, | |
| "grad_norm": 0.2746317684650421, | |
| "learning_rate": 3.2290625000000005e-06, | |
| "loss": 0.0137, | |
| "step": 14675 | |
| }, | |
| { | |
| "epoch": 6.862745098039216, | |
| "grad_norm": 5.0260396003723145, | |
| "learning_rate": 3.22125e-06, | |
| "loss": 0.0173, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 6.874416433239963, | |
| "grad_norm": 4.125462532043457, | |
| "learning_rate": 3.2134375e-06, | |
| "loss": 0.0176, | |
| "step": 14725 | |
| }, | |
| { | |
| "epoch": 6.88608776844071, | |
| "grad_norm": 6.75167179107666, | |
| "learning_rate": 3.2056250000000003e-06, | |
| "loss": 0.0145, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 6.897759103641457, | |
| "grad_norm": 1.9314770698547363, | |
| "learning_rate": 3.1978125000000006e-06, | |
| "loss": 0.013, | |
| "step": 14775 | |
| }, | |
| { | |
| "epoch": 6.909430438842204, | |
| "grad_norm": 2.6127073764801025, | |
| "learning_rate": 3.19e-06, | |
| "loss": 0.0105, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 6.921101774042951, | |
| "grad_norm": 1.5826447010040283, | |
| "learning_rate": 3.1821875e-06, | |
| "loss": 0.0127, | |
| "step": 14825 | |
| }, | |
| { | |
| "epoch": 6.932773109243698, | |
| "grad_norm": 0.6113137006759644, | |
| "learning_rate": 3.1743750000000004e-06, | |
| "loss": 0.0126, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 6.944444444444445, | |
| "grad_norm": 3.849680185317993, | |
| "learning_rate": 3.1665625000000002e-06, | |
| "loss": 0.015, | |
| "step": 14875 | |
| }, | |
| { | |
| "epoch": 6.956115779645192, | |
| "grad_norm": 5.097741603851318, | |
| "learning_rate": 3.15875e-06, | |
| "loss": 0.0072, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 6.9677871148459385, | |
| "grad_norm": 4.420420169830322, | |
| "learning_rate": 3.1509375000000003e-06, | |
| "loss": 0.0135, | |
| "step": 14925 | |
| }, | |
| { | |
| "epoch": 6.979458450046685, | |
| "grad_norm": 3.5658352375030518, | |
| "learning_rate": 3.143125e-06, | |
| "loss": 0.012, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 6.991129785247432, | |
| "grad_norm": 0.9113016128540039, | |
| "learning_rate": 3.1353125000000003e-06, | |
| "loss": 0.008, | |
| "step": 14975 | |
| }, | |
| { | |
| "epoch": 7.002801120448179, | |
| "grad_norm": 2.622985363006592, | |
| "learning_rate": 3.1274999999999997e-06, | |
| "loss": 0.0189, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 7.002801120448179, | |
| "eval_loss": 0.19959864020347595, | |
| "eval_runtime": 5339.534, | |
| "eval_samples_per_second": 1.763, | |
| "eval_steps_per_second": 0.22, | |
| "eval_wer": 0.09801388664621347, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 7.014472455648926, | |
| "grad_norm": 0.3408145606517792, | |
| "learning_rate": 3.1196875e-06, | |
| "loss": 0.0108, | |
| "step": 15025 | |
| }, | |
| { | |
| "epoch": 7.026143790849673, | |
| "grad_norm": 1.0346554517745972, | |
| "learning_rate": 3.111875e-06, | |
| "loss": 0.0135, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 7.03781512605042, | |
| "grad_norm": 0.08663380146026611, | |
| "learning_rate": 3.1040625e-06, | |
| "loss": 0.0088, | |
| "step": 15075 | |
| }, | |
| { | |
| "epoch": 7.049486461251167, | |
| "grad_norm": 0.6362659335136414, | |
| "learning_rate": 3.0962500000000002e-06, | |
| "loss": 0.0072, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 7.061157796451914, | |
| "grad_norm": 0.1300945281982422, | |
| "learning_rate": 3.0884375e-06, | |
| "loss": 0.0074, | |
| "step": 15125 | |
| }, | |
| { | |
| "epoch": 7.072829131652661, | |
| "grad_norm": 4.269519805908203, | |
| "learning_rate": 3.0806250000000003e-06, | |
| "loss": 0.0158, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 7.084500466853408, | |
| "grad_norm": 5.42411994934082, | |
| "learning_rate": 3.0728125e-06, | |
| "loss": 0.0112, | |
| "step": 15175 | |
| }, | |
| { | |
| "epoch": 7.096171802054155, | |
| "grad_norm": 0.7867230176925659, | |
| "learning_rate": 3.0650000000000003e-06, | |
| "loss": 0.0204, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 7.107843137254902, | |
| "grad_norm": 0.30360114574432373, | |
| "learning_rate": 3.0571875e-06, | |
| "loss": 0.01, | |
| "step": 15225 | |
| }, | |
| { | |
| "epoch": 7.1195144724556485, | |
| "grad_norm": 3.1817336082458496, | |
| "learning_rate": 3.0493750000000003e-06, | |
| "loss": 0.0126, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 7.131185807656396, | |
| "grad_norm": 1.1198678016662598, | |
| "learning_rate": 3.0415625e-06, | |
| "loss": 0.0059, | |
| "step": 15275 | |
| }, | |
| { | |
| "epoch": 7.142857142857143, | |
| "grad_norm": 1.7146356105804443, | |
| "learning_rate": 3.03375e-06, | |
| "loss": 0.0101, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 7.15452847805789, | |
| "grad_norm": 0.09200263023376465, | |
| "learning_rate": 3.0259375e-06, | |
| "loss": 0.0098, | |
| "step": 15325 | |
| }, | |
| { | |
| "epoch": 7.166199813258637, | |
| "grad_norm": 2.3543612957000732, | |
| "learning_rate": 3.018125e-06, | |
| "loss": 0.0172, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 7.177871148459384, | |
| "grad_norm": 0.4582861661911011, | |
| "learning_rate": 3.0103125000000002e-06, | |
| "loss": 0.0082, | |
| "step": 15375 | |
| }, | |
| { | |
| "epoch": 7.189542483660131, | |
| "grad_norm": 3.5268125534057617, | |
| "learning_rate": 3.0025e-06, | |
| "loss": 0.015, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 7.201213818860878, | |
| "grad_norm": 3.0377275943756104, | |
| "learning_rate": 2.9946875000000003e-06, | |
| "loss": 0.0079, | |
| "step": 15425 | |
| }, | |
| { | |
| "epoch": 7.212885154061625, | |
| "grad_norm": 1.1198071241378784, | |
| "learning_rate": 2.986875e-06, | |
| "loss": 0.0175, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 7.224556489262372, | |
| "grad_norm": 0.33140361309051514, | |
| "learning_rate": 2.9790625000000003e-06, | |
| "loss": 0.0078, | |
| "step": 15475 | |
| }, | |
| { | |
| "epoch": 7.236227824463119, | |
| "grad_norm": 2.4766924381256104, | |
| "learning_rate": 2.97125e-06, | |
| "loss": 0.0162, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 7.2478991596638656, | |
| "grad_norm": 0.24502252042293549, | |
| "learning_rate": 2.9634375000000004e-06, | |
| "loss": 0.0083, | |
| "step": 15525 | |
| }, | |
| { | |
| "epoch": 7.2595704948646125, | |
| "grad_norm": 0.837504506111145, | |
| "learning_rate": 2.955625e-06, | |
| "loss": 0.0145, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 7.271241830065359, | |
| "grad_norm": 0.06051575765013695, | |
| "learning_rate": 2.9478125000000004e-06, | |
| "loss": 0.0071, | |
| "step": 15575 | |
| }, | |
| { | |
| "epoch": 7.282913165266106, | |
| "grad_norm": 2.0014054775238037, | |
| "learning_rate": 2.9400000000000002e-06, | |
| "loss": 0.0146, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 7.294584500466853, | |
| "grad_norm": 0.5527703762054443, | |
| "learning_rate": 2.9321875e-06, | |
| "loss": 0.0093, | |
| "step": 15625 | |
| }, | |
| { | |
| "epoch": 7.3062558356676, | |
| "grad_norm": 0.5724664330482483, | |
| "learning_rate": 2.924375e-06, | |
| "loss": 0.0147, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 7.317927170868347, | |
| "grad_norm": 0.18703560531139374, | |
| "learning_rate": 2.9165625e-06, | |
| "loss": 0.0129, | |
| "step": 15675 | |
| }, | |
| { | |
| "epoch": 7.329598506069094, | |
| "grad_norm": 2.189370632171631, | |
| "learning_rate": 2.90875e-06, | |
| "loss": 0.0133, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 7.341269841269841, | |
| "grad_norm": 0.19430263340473175, | |
| "learning_rate": 2.9009375e-06, | |
| "loss": 0.0109, | |
| "step": 15725 | |
| }, | |
| { | |
| "epoch": 7.352941176470588, | |
| "grad_norm": 2.84920597076416, | |
| "learning_rate": 2.893125e-06, | |
| "loss": 0.0099, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 7.364612511671335, | |
| "grad_norm": 1.7251280546188354, | |
| "learning_rate": 2.8853125e-06, | |
| "loss": 0.0074, | |
| "step": 15775 | |
| }, | |
| { | |
| "epoch": 7.376283846872083, | |
| "grad_norm": 0.5282366871833801, | |
| "learning_rate": 2.8775e-06, | |
| "loss": 0.0184, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 7.3879551820728295, | |
| "grad_norm": 7.1876420974731445, | |
| "learning_rate": 2.8696875000000002e-06, | |
| "loss": 0.011, | |
| "step": 15825 | |
| }, | |
| { | |
| "epoch": 7.3996265172735765, | |
| "grad_norm": 0.14123250544071198, | |
| "learning_rate": 2.861875e-06, | |
| "loss": 0.0115, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 7.411297852474323, | |
| "grad_norm": 0.15596270561218262, | |
| "learning_rate": 2.8540625000000003e-06, | |
| "loss": 0.0117, | |
| "step": 15875 | |
| }, | |
| { | |
| "epoch": 7.42296918767507, | |
| "grad_norm": 0.23796889185905457, | |
| "learning_rate": 2.8462500000000005e-06, | |
| "loss": 0.0153, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 7.434640522875817, | |
| "grad_norm": 3.0602948665618896, | |
| "learning_rate": 2.8384375000000003e-06, | |
| "loss": 0.0116, | |
| "step": 15925 | |
| }, | |
| { | |
| "epoch": 7.446311858076564, | |
| "grad_norm": 0.32861384749412537, | |
| "learning_rate": 2.830625e-06, | |
| "loss": 0.0121, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 7.457983193277311, | |
| "grad_norm": 0.5478546023368835, | |
| "learning_rate": 2.8228125e-06, | |
| "loss": 0.0112, | |
| "step": 15975 | |
| }, | |
| { | |
| "epoch": 7.469654528478058, | |
| "grad_norm": 0.2652440667152405, | |
| "learning_rate": 2.815e-06, | |
| "loss": 0.0218, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 7.481325863678805, | |
| "grad_norm": 1.3157047033309937, | |
| "learning_rate": 2.8071875e-06, | |
| "loss": 0.0077, | |
| "step": 16025 | |
| }, | |
| { | |
| "epoch": 7.492997198879552, | |
| "grad_norm": 0.28366702795028687, | |
| "learning_rate": 2.799375e-06, | |
| "loss": 0.0136, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 7.504668534080299, | |
| "grad_norm": 5.81749963760376, | |
| "learning_rate": 2.7915625e-06, | |
| "loss": 0.0083, | |
| "step": 16075 | |
| }, | |
| { | |
| "epoch": 7.516339869281046, | |
| "grad_norm": 2.328474760055542, | |
| "learning_rate": 2.7837500000000002e-06, | |
| "loss": 0.0138, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 7.528011204481793, | |
| "grad_norm": 0.3001089096069336, | |
| "learning_rate": 2.7759375e-06, | |
| "loss": 0.0063, | |
| "step": 16125 | |
| }, | |
| { | |
| "epoch": 7.5396825396825395, | |
| "grad_norm": 0.8168843388557434, | |
| "learning_rate": 2.7681250000000003e-06, | |
| "loss": 0.0153, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 7.5513538748832865, | |
| "grad_norm": 0.5548914074897766, | |
| "learning_rate": 2.7603125e-06, | |
| "loss": 0.0075, | |
| "step": 16175 | |
| }, | |
| { | |
| "epoch": 7.563025210084033, | |
| "grad_norm": 1.3669456243515015, | |
| "learning_rate": 2.7525000000000003e-06, | |
| "loss": 0.0135, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 7.57469654528478, | |
| "grad_norm": 0.7598258852958679, | |
| "learning_rate": 2.7446875e-06, | |
| "loss": 0.0056, | |
| "step": 16225 | |
| }, | |
| { | |
| "epoch": 7.586367880485527, | |
| "grad_norm": 0.4459327757358551, | |
| "learning_rate": 2.7368750000000004e-06, | |
| "loss": 0.0102, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 7.598039215686274, | |
| "grad_norm": 0.2884249985218048, | |
| "learning_rate": 2.7290625e-06, | |
| "loss": 0.0097, | |
| "step": 16275 | |
| }, | |
| { | |
| "epoch": 7.609710550887021, | |
| "grad_norm": 0.1581568568944931, | |
| "learning_rate": 2.72125e-06, | |
| "loss": 0.0121, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 7.621381886087768, | |
| "grad_norm": 0.3975503444671631, | |
| "learning_rate": 2.7134375e-06, | |
| "loss": 0.0107, | |
| "step": 16325 | |
| }, | |
| { | |
| "epoch": 7.633053221288515, | |
| "grad_norm": 1.209242582321167, | |
| "learning_rate": 2.705625e-06, | |
| "loss": 0.0148, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 7.644724556489263, | |
| "grad_norm": 0.27312788367271423, | |
| "learning_rate": 2.6978125e-06, | |
| "loss": 0.0035, | |
| "step": 16375 | |
| }, | |
| { | |
| "epoch": 7.65639589169001, | |
| "grad_norm": 1.0958424806594849, | |
| "learning_rate": 2.69e-06, | |
| "loss": 0.0171, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 7.668067226890757, | |
| "grad_norm": 0.2819930911064148, | |
| "learning_rate": 2.6821875e-06, | |
| "loss": 0.0056, | |
| "step": 16425 | |
| }, | |
| { | |
| "epoch": 7.6797385620915035, | |
| "grad_norm": 0.7688259482383728, | |
| "learning_rate": 2.674375e-06, | |
| "loss": 0.0097, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 7.69140989729225, | |
| "grad_norm": 0.7461805939674377, | |
| "learning_rate": 2.6665625e-06, | |
| "loss": 0.0097, | |
| "step": 16475 | |
| }, | |
| { | |
| "epoch": 7.703081232492997, | |
| "grad_norm": 0.4246864914894104, | |
| "learning_rate": 2.65875e-06, | |
| "loss": 0.0142, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 7.714752567693744, | |
| "grad_norm": 0.32187584042549133, | |
| "learning_rate": 2.6509375000000004e-06, | |
| "loss": 0.0069, | |
| "step": 16525 | |
| }, | |
| { | |
| "epoch": 7.726423902894491, | |
| "grad_norm": 0.9666975736618042, | |
| "learning_rate": 2.643125e-06, | |
| "loss": 0.0139, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 7.738095238095238, | |
| "grad_norm": 0.4001488983631134, | |
| "learning_rate": 2.6353125000000004e-06, | |
| "loss": 0.0078, | |
| "step": 16575 | |
| }, | |
| { | |
| "epoch": 7.749766573295985, | |
| "grad_norm": 1.532838225364685, | |
| "learning_rate": 2.6275000000000003e-06, | |
| "loss": 0.0131, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 7.761437908496732, | |
| "grad_norm": 5.185120582580566, | |
| "learning_rate": 2.6196875e-06, | |
| "loss": 0.0086, | |
| "step": 16625 | |
| }, | |
| { | |
| "epoch": 7.773109243697479, | |
| "grad_norm": 2.4308927059173584, | |
| "learning_rate": 2.611875e-06, | |
| "loss": 0.0143, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 7.784780578898226, | |
| "grad_norm": 3.3174314498901367, | |
| "learning_rate": 2.6040625e-06, | |
| "loss": 0.0069, | |
| "step": 16675 | |
| }, | |
| { | |
| "epoch": 7.796451914098973, | |
| "grad_norm": 1.5750664472579956, | |
| "learning_rate": 2.59625e-06, | |
| "loss": 0.0223, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 7.80812324929972, | |
| "grad_norm": 0.2341316193342209, | |
| "learning_rate": 2.5884375e-06, | |
| "loss": 0.0054, | |
| "step": 16725 | |
| }, | |
| { | |
| "epoch": 7.819794584500467, | |
| "grad_norm": 1.4788146018981934, | |
| "learning_rate": 2.580625e-06, | |
| "loss": 0.0136, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 7.8314659197012135, | |
| "grad_norm": 1.1940587759017944, | |
| "learning_rate": 2.5728125e-06, | |
| "loss": 0.006, | |
| "step": 16775 | |
| }, | |
| { | |
| "epoch": 7.8431372549019605, | |
| "grad_norm": 1.383323073387146, | |
| "learning_rate": 2.565e-06, | |
| "loss": 0.0115, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 7.854808590102707, | |
| "grad_norm": 0.6506948471069336, | |
| "learning_rate": 2.5571875000000002e-06, | |
| "loss": 0.008, | |
| "step": 16825 | |
| }, | |
| { | |
| "epoch": 7.866479925303455, | |
| "grad_norm": 1.9429287910461426, | |
| "learning_rate": 2.549375e-06, | |
| "loss": 0.018, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 7.878151260504202, | |
| "grad_norm": 1.7122925519943237, | |
| "learning_rate": 2.5415625000000003e-06, | |
| "loss": 0.011, | |
| "step": 16875 | |
| }, | |
| { | |
| "epoch": 7.889822595704949, | |
| "grad_norm": 0.38340166211128235, | |
| "learning_rate": 2.53375e-06, | |
| "loss": 0.0163, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 7.901493930905696, | |
| "grad_norm": 4.114197731018066, | |
| "learning_rate": 2.5259375000000003e-06, | |
| "loss": 0.0114, | |
| "step": 16925 | |
| }, | |
| { | |
| "epoch": 7.913165266106443, | |
| "grad_norm": 2.0275721549987793, | |
| "learning_rate": 2.518125e-06, | |
| "loss": 0.0131, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 7.92483660130719, | |
| "grad_norm": 3.8220088481903076, | |
| "learning_rate": 2.5103125000000004e-06, | |
| "loss": 0.0126, | |
| "step": 16975 | |
| }, | |
| { | |
| "epoch": 7.936507936507937, | |
| "grad_norm": 2.1761302947998047, | |
| "learning_rate": 2.5025e-06, | |
| "loss": 0.0164, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 7.948179271708684, | |
| "grad_norm": 6.142478942871094, | |
| "learning_rate": 2.4946875e-06, | |
| "loss": 0.0063, | |
| "step": 17025 | |
| }, | |
| { | |
| "epoch": 7.959850606909431, | |
| "grad_norm": 2.5636518001556396, | |
| "learning_rate": 2.486875e-06, | |
| "loss": 0.0142, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 7.9715219421101775, | |
| "grad_norm": 0.4117043614387512, | |
| "learning_rate": 2.4790625e-06, | |
| "loss": 0.0082, | |
| "step": 17075 | |
| }, | |
| { | |
| "epoch": 7.983193277310924, | |
| "grad_norm": 2.189190626144409, | |
| "learning_rate": 2.47125e-06, | |
| "loss": 0.0139, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 7.994864612511671, | |
| "grad_norm": 2.0030508041381836, | |
| "learning_rate": 2.4634375e-06, | |
| "loss": 0.0084, | |
| "step": 17125 | |
| }, | |
| { | |
| "epoch": 8.006535947712418, | |
| "grad_norm": 0.26142677664756775, | |
| "learning_rate": 2.4556250000000003e-06, | |
| "loss": 0.0091, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 8.018207282913165, | |
| "grad_norm": 0.4059411585330963, | |
| "learning_rate": 2.4478125e-06, | |
| "loss": 0.0055, | |
| "step": 17175 | |
| }, | |
| { | |
| "epoch": 8.029878618113912, | |
| "grad_norm": 0.09706517308950424, | |
| "learning_rate": 2.4400000000000004e-06, | |
| "loss": 0.0126, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 8.041549953314659, | |
| "grad_norm": 6.117686748504639, | |
| "learning_rate": 2.4321875e-06, | |
| "loss": 0.0077, | |
| "step": 17225 | |
| }, | |
| { | |
| "epoch": 8.053221288515406, | |
| "grad_norm": 1.4079279899597168, | |
| "learning_rate": 2.4243750000000004e-06, | |
| "loss": 0.0099, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 8.064892623716153, | |
| "grad_norm": 0.329962819814682, | |
| "learning_rate": 2.4165625e-06, | |
| "loss": 0.0101, | |
| "step": 17275 | |
| }, | |
| { | |
| "epoch": 8.0765639589169, | |
| "grad_norm": 0.14133867621421814, | |
| "learning_rate": 2.4087500000000004e-06, | |
| "loss": 0.0166, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 8.088235294117647, | |
| "grad_norm": 0.3688430190086365, | |
| "learning_rate": 2.4009375000000003e-06, | |
| "loss": 0.0074, | |
| "step": 17325 | |
| }, | |
| { | |
| "epoch": 8.099906629318394, | |
| "grad_norm": 2.421675205230713, | |
| "learning_rate": 2.393125e-06, | |
| "loss": 0.0119, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 8.11157796451914, | |
| "grad_norm": 0.39900481700897217, | |
| "learning_rate": 2.3853125e-06, | |
| "loss": 0.0087, | |
| "step": 17375 | |
| }, | |
| { | |
| "epoch": 8.123249299719888, | |
| "grad_norm": 9.060256004333496, | |
| "learning_rate": 2.3778125000000004e-06, | |
| "loss": 0.0193, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 8.134920634920634, | |
| "grad_norm": 3.6718103885650635, | |
| "learning_rate": 2.37e-06, | |
| "loss": 0.0034, | |
| "step": 17425 | |
| }, | |
| { | |
| "epoch": 8.146591970121381, | |
| "grad_norm": 1.8826625347137451, | |
| "learning_rate": 2.3621875e-06, | |
| "loss": 0.0108, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 8.158263305322128, | |
| "grad_norm": 5.267531871795654, | |
| "learning_rate": 2.354375e-06, | |
| "loss": 0.0051, | |
| "step": 17475 | |
| }, | |
| { | |
| "epoch": 8.169934640522875, | |
| "grad_norm": 1.7462451457977295, | |
| "learning_rate": 2.3465625e-06, | |
| "loss": 0.0098, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 8.181605975723622, | |
| "grad_norm": 3.9560678005218506, | |
| "learning_rate": 2.33875e-06, | |
| "loss": 0.0074, | |
| "step": 17525 | |
| }, | |
| { | |
| "epoch": 8.193277310924369, | |
| "grad_norm": 0.9454758763313293, | |
| "learning_rate": 2.3309375e-06, | |
| "loss": 0.0124, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 8.204948646125116, | |
| "grad_norm": 4.392622947692871, | |
| "learning_rate": 2.323125e-06, | |
| "loss": 0.0092, | |
| "step": 17575 | |
| }, | |
| { | |
| "epoch": 8.216619981325863, | |
| "grad_norm": 0.15422876179218292, | |
| "learning_rate": 2.3153125e-06, | |
| "loss": 0.0112, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 8.22829131652661, | |
| "grad_norm": 4.900958061218262, | |
| "learning_rate": 2.3075e-06, | |
| "loss": 0.0062, | |
| "step": 17625 | |
| }, | |
| { | |
| "epoch": 8.239962651727357, | |
| "grad_norm": 0.7558678388595581, | |
| "learning_rate": 2.2996875e-06, | |
| "loss": 0.0202, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 8.251633986928105, | |
| "grad_norm": 1.5306479930877686, | |
| "learning_rate": 2.2918750000000004e-06, | |
| "loss": 0.0045, | |
| "step": 17675 | |
| }, | |
| { | |
| "epoch": 8.263305322128852, | |
| "grad_norm": 0.20347028970718384, | |
| "learning_rate": 2.2840625e-06, | |
| "loss": 0.0078, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 8.2749766573296, | |
| "grad_norm": 1.3202959299087524, | |
| "learning_rate": 2.2762500000000004e-06, | |
| "loss": 0.0086, | |
| "step": 17725 | |
| }, | |
| { | |
| "epoch": 8.286647992530346, | |
| "grad_norm": 0.9320886731147766, | |
| "learning_rate": 2.2684375000000003e-06, | |
| "loss": 0.0108, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 8.298319327731093, | |
| "grad_norm": 3.197519063949585, | |
| "learning_rate": 2.260625e-06, | |
| "loss": 0.0077, | |
| "step": 17775 | |
| }, | |
| { | |
| "epoch": 8.30999066293184, | |
| "grad_norm": 1.24087655544281, | |
| "learning_rate": 2.2528125e-06, | |
| "loss": 0.0132, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 8.321661998132587, | |
| "grad_norm": 5.21552848815918, | |
| "learning_rate": 2.245e-06, | |
| "loss": 0.0063, | |
| "step": 17825 | |
| }, | |
| { | |
| "epoch": 8.333333333333334, | |
| "grad_norm": 1.1258479356765747, | |
| "learning_rate": 2.2371875e-06, | |
| "loss": 0.0163, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 8.34500466853408, | |
| "grad_norm": 4.139800071716309, | |
| "learning_rate": 2.229375e-06, | |
| "loss": 0.0056, | |
| "step": 17875 | |
| }, | |
| { | |
| "epoch": 8.356676003734828, | |
| "grad_norm": 0.32767072319984436, | |
| "learning_rate": 2.2215625e-06, | |
| "loss": 0.0075, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 8.368347338935575, | |
| "grad_norm": 1.2744501829147339, | |
| "learning_rate": 2.21375e-06, | |
| "loss": 0.007, | |
| "step": 17925 | |
| }, | |
| { | |
| "epoch": 8.380018674136322, | |
| "grad_norm": 1.00862717628479, | |
| "learning_rate": 2.2059375e-06, | |
| "loss": 0.0154, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 8.391690009337069, | |
| "grad_norm": 0.4900611340999603, | |
| "learning_rate": 2.1981250000000002e-06, | |
| "loss": 0.0085, | |
| "step": 17975 | |
| }, | |
| { | |
| "epoch": 8.403361344537815, | |
| "grad_norm": 3.439101219177246, | |
| "learning_rate": 2.1903125e-06, | |
| "loss": 0.0193, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 8.415032679738562, | |
| "grad_norm": 0.17414799332618713, | |
| "learning_rate": 2.1825000000000003e-06, | |
| "loss": 0.0092, | |
| "step": 18025 | |
| }, | |
| { | |
| "epoch": 8.42670401493931, | |
| "grad_norm": 0.3426636755466461, | |
| "learning_rate": 2.1746875e-06, | |
| "loss": 0.0149, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 8.438375350140056, | |
| "grad_norm": 0.722213089466095, | |
| "learning_rate": 2.1668750000000003e-06, | |
| "loss": 0.007, | |
| "step": 18075 | |
| }, | |
| { | |
| "epoch": 8.450046685340803, | |
| "grad_norm": 0.1770373433828354, | |
| "learning_rate": 2.1590625e-06, | |
| "loss": 0.0106, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 8.46171802054155, | |
| "grad_norm": 1.1311222314834595, | |
| "learning_rate": 2.15125e-06, | |
| "loss": 0.0105, | |
| "step": 18125 | |
| }, | |
| { | |
| "epoch": 8.473389355742297, | |
| "grad_norm": 3.256246328353882, | |
| "learning_rate": 2.1434374999999998e-06, | |
| "loss": 0.0117, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 8.485060690943044, | |
| "grad_norm": 2.979933977127075, | |
| "learning_rate": 2.135625e-06, | |
| "loss": 0.0065, | |
| "step": 18175 | |
| }, | |
| { | |
| "epoch": 8.49673202614379, | |
| "grad_norm": 5.483570098876953, | |
| "learning_rate": 2.1278125e-06, | |
| "loss": 0.0117, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 8.508403361344538, | |
| "grad_norm": 0.9835972189903259, | |
| "learning_rate": 2.12e-06, | |
| "loss": 0.0068, | |
| "step": 18225 | |
| }, | |
| { | |
| "epoch": 8.520074696545285, | |
| "grad_norm": 0.053934112191200256, | |
| "learning_rate": 2.1121875e-06, | |
| "loss": 0.0064, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 8.531746031746032, | |
| "grad_norm": 0.5441355109214783, | |
| "learning_rate": 2.104375e-06, | |
| "loss": 0.0076, | |
| "step": 18275 | |
| }, | |
| { | |
| "epoch": 8.543417366946779, | |
| "grad_norm": 2.9546403884887695, | |
| "learning_rate": 2.0965625000000003e-06, | |
| "loss": 0.0132, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 8.555088702147525, | |
| "grad_norm": 1.0984193086624146, | |
| "learning_rate": 2.08875e-06, | |
| "loss": 0.006, | |
| "step": 18325 | |
| }, | |
| { | |
| "epoch": 8.566760037348272, | |
| "grad_norm": 0.058905456215143204, | |
| "learning_rate": 2.0809375000000004e-06, | |
| "loss": 0.0086, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 8.57843137254902, | |
| "grad_norm": 1.6285549402236938, | |
| "learning_rate": 2.073125e-06, | |
| "loss": 0.0055, | |
| "step": 18375 | |
| }, | |
| { | |
| "epoch": 8.590102707749766, | |
| "grad_norm": 2.7696332931518555, | |
| "learning_rate": 2.0653125000000004e-06, | |
| "loss": 0.0093, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 8.601774042950513, | |
| "grad_norm": 0.25450074672698975, | |
| "learning_rate": 2.0575e-06, | |
| "loss": 0.0027, | |
| "step": 18425 | |
| }, | |
| { | |
| "epoch": 8.61344537815126, | |
| "grad_norm": 0.13693825900554657, | |
| "learning_rate": 2.0496875e-06, | |
| "loss": 0.0154, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 8.625116713352007, | |
| "grad_norm": 0.07830255478620529, | |
| "learning_rate": 2.041875e-06, | |
| "loss": 0.0063, | |
| "step": 18475 | |
| }, | |
| { | |
| "epoch": 8.636788048552754, | |
| "grad_norm": 3.4713680744171143, | |
| "learning_rate": 2.0340625e-06, | |
| "loss": 0.0222, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 8.6484593837535, | |
| "grad_norm": 0.6259431838989258, | |
| "learning_rate": 2.02625e-06, | |
| "loss": 0.0088, | |
| "step": 18525 | |
| }, | |
| { | |
| "epoch": 8.660130718954248, | |
| "grad_norm": 2.6433568000793457, | |
| "learning_rate": 2.0184375e-06, | |
| "loss": 0.0104, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 8.671802054154995, | |
| "grad_norm": 4.890020370483398, | |
| "learning_rate": 2.010625e-06, | |
| "loss": 0.0049, | |
| "step": 18575 | |
| }, | |
| { | |
| "epoch": 8.683473389355742, | |
| "grad_norm": 0.13995322585105896, | |
| "learning_rate": 2.0028125e-06, | |
| "loss": 0.0132, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 8.695144724556489, | |
| "grad_norm": 3.4847798347473145, | |
| "learning_rate": 1.995e-06, | |
| "loss": 0.0083, | |
| "step": 18625 | |
| }, | |
| { | |
| "epoch": 8.706816059757235, | |
| "grad_norm": 0.990917980670929, | |
| "learning_rate": 1.9871875e-06, | |
| "loss": 0.0067, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 8.718487394957982, | |
| "grad_norm": 3.6839520931243896, | |
| "learning_rate": 1.979375e-06, | |
| "loss": 0.0063, | |
| "step": 18675 | |
| }, | |
| { | |
| "epoch": 8.73015873015873, | |
| "grad_norm": 2.492249011993408, | |
| "learning_rate": 1.9715625000000002e-06, | |
| "loss": 0.01, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 8.741830065359476, | |
| "grad_norm": 1.4780845642089844, | |
| "learning_rate": 1.96375e-06, | |
| "loss": 0.0058, | |
| "step": 18725 | |
| }, | |
| { | |
| "epoch": 8.753501400560225, | |
| "grad_norm": 0.1961933821439743, | |
| "learning_rate": 1.9559375000000003e-06, | |
| "loss": 0.01, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 8.76517273576097, | |
| "grad_norm": 1.2011662721633911, | |
| "learning_rate": 1.948125e-06, | |
| "loss": 0.0075, | |
| "step": 18775 | |
| }, | |
| { | |
| "epoch": 8.776844070961719, | |
| "grad_norm": 1.7209523916244507, | |
| "learning_rate": 1.9403125000000003e-06, | |
| "loss": 0.014, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 8.788515406162466, | |
| "grad_norm": 0.40629979968070984, | |
| "learning_rate": 1.9325e-06, | |
| "loss": 0.0047, | |
| "step": 18825 | |
| }, | |
| { | |
| "epoch": 8.800186741363213, | |
| "grad_norm": 1.7460086345672607, | |
| "learning_rate": 1.9246875e-06, | |
| "loss": 0.0075, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 8.81185807656396, | |
| "grad_norm": 0.1296474188566208, | |
| "learning_rate": 1.9168749999999998e-06, | |
| "loss": 0.004, | |
| "step": 18875 | |
| }, | |
| { | |
| "epoch": 8.823529411764707, | |
| "grad_norm": 3.629750967025757, | |
| "learning_rate": 1.9090625e-06, | |
| "loss": 0.0118, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 8.835200746965453, | |
| "grad_norm": 0.17966805398464203, | |
| "learning_rate": 1.9012500000000002e-06, | |
| "loss": 0.007, | |
| "step": 18925 | |
| }, | |
| { | |
| "epoch": 8.8468720821662, | |
| "grad_norm": 1.5354282855987549, | |
| "learning_rate": 1.8934375e-06, | |
| "loss": 0.0185, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 8.858543417366947, | |
| "grad_norm": 4.741540908813477, | |
| "learning_rate": 1.8856250000000003e-06, | |
| "loss": 0.0086, | |
| "step": 18975 | |
| }, | |
| { | |
| "epoch": 8.870214752567694, | |
| "grad_norm": 0.33261170983314514, | |
| "learning_rate": 1.8778125e-06, | |
| "loss": 0.0145, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 8.881886087768441, | |
| "grad_norm": 0.1079050749540329, | |
| "learning_rate": 1.8700000000000003e-06, | |
| "loss": 0.0084, | |
| "step": 19025 | |
| }, | |
| { | |
| "epoch": 8.893557422969188, | |
| "grad_norm": 0.7272719740867615, | |
| "learning_rate": 1.8621875000000001e-06, | |
| "loss": 0.0065, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 8.905228758169935, | |
| "grad_norm": 2.8611772060394287, | |
| "learning_rate": 1.8543750000000001e-06, | |
| "loss": 0.0085, | |
| "step": 19075 | |
| }, | |
| { | |
| "epoch": 8.916900093370682, | |
| "grad_norm": 0.06473066657781601, | |
| "learning_rate": 1.8465625e-06, | |
| "loss": 0.0118, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 8.928571428571429, | |
| "grad_norm": 0.5498653054237366, | |
| "learning_rate": 1.8387500000000002e-06, | |
| "loss": 0.0071, | |
| "step": 19125 | |
| }, | |
| { | |
| "epoch": 8.940242763772176, | |
| "grad_norm": 0.0627368837594986, | |
| "learning_rate": 1.8309375e-06, | |
| "loss": 0.0094, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 8.951914098972923, | |
| "grad_norm": 2.6687510013580322, | |
| "learning_rate": 1.8231250000000002e-06, | |
| "loss": 0.0054, | |
| "step": 19175 | |
| }, | |
| { | |
| "epoch": 8.96358543417367, | |
| "grad_norm": 1.0596753358840942, | |
| "learning_rate": 1.8153125e-06, | |
| "loss": 0.0069, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 8.975256769374417, | |
| "grad_norm": 1.5671969652175903, | |
| "learning_rate": 1.8075000000000003e-06, | |
| "loss": 0.0041, | |
| "step": 19225 | |
| }, | |
| { | |
| "epoch": 8.986928104575163, | |
| "grad_norm": 3.649564266204834, | |
| "learning_rate": 1.7996875e-06, | |
| "loss": 0.0123, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 8.99859943977591, | |
| "grad_norm": 4.41900110244751, | |
| "learning_rate": 1.791875e-06, | |
| "loss": 0.0074, | |
| "step": 19275 | |
| }, | |
| { | |
| "epoch": 9.010270774976657, | |
| "grad_norm": 1.1093493700027466, | |
| "learning_rate": 1.7840625e-06, | |
| "loss": 0.0056, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 9.021942110177404, | |
| "grad_norm": 2.091535806655884, | |
| "learning_rate": 1.7762500000000001e-06, | |
| "loss": 0.007, | |
| "step": 19325 | |
| }, | |
| { | |
| "epoch": 9.033613445378151, | |
| "grad_norm": 4.006499767303467, | |
| "learning_rate": 1.7684375e-06, | |
| "loss": 0.0095, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 9.045284780578898, | |
| "grad_norm": 0.13656963407993317, | |
| "learning_rate": 1.7606250000000002e-06, | |
| "loss": 0.0095, | |
| "step": 19375 | |
| }, | |
| { | |
| "epoch": 9.056956115779645, | |
| "grad_norm": 2.558016538619995, | |
| "learning_rate": 1.7528125e-06, | |
| "loss": 0.0125, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 9.068627450980392, | |
| "grad_norm": 0.15220613777637482, | |
| "learning_rate": 1.745e-06, | |
| "loss": 0.0074, | |
| "step": 19425 | |
| }, | |
| { | |
| "epoch": 9.080298786181139, | |
| "grad_norm": 2.0453782081604004, | |
| "learning_rate": 1.7371874999999998e-06, | |
| "loss": 0.0063, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 9.091970121381886, | |
| "grad_norm": 5.893077373504639, | |
| "learning_rate": 1.729375e-06, | |
| "loss": 0.0093, | |
| "step": 19475 | |
| }, | |
| { | |
| "epoch": 9.103641456582633, | |
| "grad_norm": 1.2152618169784546, | |
| "learning_rate": 1.7215624999999999e-06, | |
| "loss": 0.0058, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 9.11531279178338, | |
| "grad_norm": 0.9248460531234741, | |
| "learning_rate": 1.7137500000000001e-06, | |
| "loss": 0.0095, | |
| "step": 19525 | |
| }, | |
| { | |
| "epoch": 9.126984126984127, | |
| "grad_norm": 0.35303401947021484, | |
| "learning_rate": 1.7059375000000003e-06, | |
| "loss": 0.0074, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 9.138655462184873, | |
| "grad_norm": 0.8544372320175171, | |
| "learning_rate": 1.6981250000000002e-06, | |
| "loss": 0.0116, | |
| "step": 19575 | |
| }, | |
| { | |
| "epoch": 9.15032679738562, | |
| "grad_norm": 0.38176584243774414, | |
| "learning_rate": 1.6903125000000002e-06, | |
| "loss": 0.0131, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 9.161998132586367, | |
| "grad_norm": 3.0445823669433594, | |
| "learning_rate": 1.6825e-06, | |
| "loss": 0.0073, | |
| "step": 19625 | |
| }, | |
| { | |
| "epoch": 9.173669467787114, | |
| "grad_norm": 0.1117783859372139, | |
| "learning_rate": 1.6746875000000002e-06, | |
| "loss": 0.0067, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 9.185340802987861, | |
| "grad_norm": 1.0190069675445557, | |
| "learning_rate": 1.666875e-06, | |
| "loss": 0.0096, | |
| "step": 19675 | |
| }, | |
| { | |
| "epoch": 9.197012138188608, | |
| "grad_norm": 0.07005083560943604, | |
| "learning_rate": 1.6590625000000003e-06, | |
| "loss": 0.0125, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 9.208683473389355, | |
| "grad_norm": 1.7159433364868164, | |
| "learning_rate": 1.65125e-06, | |
| "loss": 0.0078, | |
| "step": 19725 | |
| }, | |
| { | |
| "epoch": 9.220354808590102, | |
| "grad_norm": 0.325469046831131, | |
| "learning_rate": 1.6437500000000001e-06, | |
| "loss": 0.0068, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 9.232026143790849, | |
| "grad_norm": 0.516471803188324, | |
| "learning_rate": 1.6359375e-06, | |
| "loss": 0.0064, | |
| "step": 19775 | |
| }, | |
| { | |
| "epoch": 9.243697478991596, | |
| "grad_norm": 0.18785762786865234, | |
| "learning_rate": 1.6281250000000002e-06, | |
| "loss": 0.0083, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 9.255368814192344, | |
| "grad_norm": 7.891486167907715, | |
| "learning_rate": 1.6203125e-06, | |
| "loss": 0.0075, | |
| "step": 19825 | |
| }, | |
| { | |
| "epoch": 9.267040149393091, | |
| "grad_norm": 0.1949397474527359, | |
| "learning_rate": 1.6125e-06, | |
| "loss": 0.0079, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 9.278711484593838, | |
| "grad_norm": 3.992004632949829, | |
| "learning_rate": 1.6046875e-06, | |
| "loss": 0.0111, | |
| "step": 19875 | |
| }, | |
| { | |
| "epoch": 9.290382819794585, | |
| "grad_norm": 1.5781553983688354, | |
| "learning_rate": 1.596875e-06, | |
| "loss": 0.005, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 9.302054154995332, | |
| "grad_norm": 0.28434544801712036, | |
| "learning_rate": 1.5890624999999999e-06, | |
| "loss": 0.0121, | |
| "step": 19925 | |
| }, | |
| { | |
| "epoch": 9.313725490196079, | |
| "grad_norm": 0.04462061822414398, | |
| "learning_rate": 1.5812500000000001e-06, | |
| "loss": 0.01, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 9.325396825396826, | |
| "grad_norm": 0.1574648916721344, | |
| "learning_rate": 1.5734375e-06, | |
| "loss": 0.0047, | |
| "step": 19975 | |
| }, | |
| { | |
| "epoch": 9.337068160597573, | |
| "grad_norm": 3.997842788696289, | |
| "learning_rate": 1.5656250000000002e-06, | |
| "loss": 0.0052, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 9.337068160597573, | |
| "eval_loss": 0.20788420736789703, | |
| "eval_runtime": 5359.6354, | |
| "eval_samples_per_second": 1.756, | |
| "eval_steps_per_second": 0.22, | |
| "eval_wer": 0.09564023897949298, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 9.34873949579832, | |
| "grad_norm": 0.07767148315906525, | |
| "learning_rate": 1.5578125000000002e-06, | |
| "loss": 0.0071, | |
| "step": 20025 | |
| }, | |
| { | |
| "epoch": 9.360410830999067, | |
| "grad_norm": 0.03903215005993843, | |
| "learning_rate": 1.55e-06, | |
| "loss": 0.0056, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 9.372082166199814, | |
| "grad_norm": 5.785853385925293, | |
| "learning_rate": 1.5421875e-06, | |
| "loss": 0.0087, | |
| "step": 20075 | |
| }, | |
| { | |
| "epoch": 9.38375350140056, | |
| "grad_norm": 0.3732275366783142, | |
| "learning_rate": 1.534375e-06, | |
| "loss": 0.0079, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 9.395424836601308, | |
| "grad_norm": 0.7682175636291504, | |
| "learning_rate": 1.5265625e-06, | |
| "loss": 0.0113, | |
| "step": 20125 | |
| }, | |
| { | |
| "epoch": 9.407096171802054, | |
| "grad_norm": 0.3410235345363617, | |
| "learning_rate": 1.51875e-06, | |
| "loss": 0.0058, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 9.418767507002801, | |
| "grad_norm": 6.657580375671387, | |
| "learning_rate": 1.5109375e-06, | |
| "loss": 0.0071, | |
| "step": 20175 | |
| }, | |
| { | |
| "epoch": 9.430438842203548, | |
| "grad_norm": 1.331062912940979, | |
| "learning_rate": 1.5031250000000001e-06, | |
| "loss": 0.0064, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 9.442110177404295, | |
| "grad_norm": 0.032236941158771515, | |
| "learning_rate": 1.4953125e-06, | |
| "loss": 0.0073, | |
| "step": 20225 | |
| }, | |
| { | |
| "epoch": 9.453781512605042, | |
| "grad_norm": 3.0221993923187256, | |
| "learning_rate": 1.4875e-06, | |
| "loss": 0.0053, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 9.465452847805789, | |
| "grad_norm": 3.605405569076538, | |
| "learning_rate": 1.4796875e-06, | |
| "loss": 0.0127, | |
| "step": 20275 | |
| }, | |
| { | |
| "epoch": 9.477124183006536, | |
| "grad_norm": 0.11760404706001282, | |
| "learning_rate": 1.471875e-06, | |
| "loss": 0.0067, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 9.488795518207283, | |
| "grad_norm": 2.5941033363342285, | |
| "learning_rate": 1.4640625000000002e-06, | |
| "loss": 0.0072, | |
| "step": 20325 | |
| }, | |
| { | |
| "epoch": 9.50046685340803, | |
| "grad_norm": 5.615445613861084, | |
| "learning_rate": 1.4562500000000002e-06, | |
| "loss": 0.0116, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 9.512138188608777, | |
| "grad_norm": 0.22926200926303864, | |
| "learning_rate": 1.4484375e-06, | |
| "loss": 0.0082, | |
| "step": 20375 | |
| }, | |
| { | |
| "epoch": 9.523809523809524, | |
| "grad_norm": 0.8798258304595947, | |
| "learning_rate": 1.440625e-06, | |
| "loss": 0.0036, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 9.53548085901027, | |
| "grad_norm": 2.885864496231079, | |
| "learning_rate": 1.4328125e-06, | |
| "loss": 0.0076, | |
| "step": 20425 | |
| }, | |
| { | |
| "epoch": 9.547152194211018, | |
| "grad_norm": 2.137159824371338, | |
| "learning_rate": 1.4250000000000001e-06, | |
| "loss": 0.0136, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 9.558823529411764, | |
| "grad_norm": 0.8029230237007141, | |
| "learning_rate": 1.4171875000000001e-06, | |
| "loss": 0.0067, | |
| "step": 20475 | |
| }, | |
| { | |
| "epoch": 9.570494864612511, | |
| "grad_norm": 0.14883463084697723, | |
| "learning_rate": 1.4093750000000002e-06, | |
| "loss": 0.0095, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 9.582166199813258, | |
| "grad_norm": 10.01462459564209, | |
| "learning_rate": 1.4015625000000002e-06, | |
| "loss": 0.0069, | |
| "step": 20525 | |
| }, | |
| { | |
| "epoch": 9.593837535014005, | |
| "grad_norm": 1.3217803239822388, | |
| "learning_rate": 1.39375e-06, | |
| "loss": 0.0058, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 9.605508870214752, | |
| "grad_norm": 5.664200782775879, | |
| "learning_rate": 1.3859375e-06, | |
| "loss": 0.0086, | |
| "step": 20575 | |
| }, | |
| { | |
| "epoch": 9.6171802054155, | |
| "grad_norm": 3.8610246181488037, | |
| "learning_rate": 1.378125e-06, | |
| "loss": 0.0085, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 9.628851540616246, | |
| "grad_norm": 0.11504428088665009, | |
| "learning_rate": 1.3703125e-06, | |
| "loss": 0.006, | |
| "step": 20625 | |
| }, | |
| { | |
| "epoch": 9.640522875816993, | |
| "grad_norm": 0.9499320387840271, | |
| "learning_rate": 1.3625e-06, | |
| "loss": 0.0061, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 9.65219421101774, | |
| "grad_norm": 0.2915020287036896, | |
| "learning_rate": 1.3546875e-06, | |
| "loss": 0.0059, | |
| "step": 20675 | |
| }, | |
| { | |
| "epoch": 9.663865546218487, | |
| "grad_norm": 1.0401633977890015, | |
| "learning_rate": 1.3468750000000001e-06, | |
| "loss": 0.0089, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 9.675536881419234, | |
| "grad_norm": 0.8448579907417297, | |
| "learning_rate": 1.3390625e-06, | |
| "loss": 0.0115, | |
| "step": 20725 | |
| }, | |
| { | |
| "epoch": 9.68720821661998, | |
| "grad_norm": 0.22094358503818512, | |
| "learning_rate": 1.33125e-06, | |
| "loss": 0.0092, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 9.698879551820728, | |
| "grad_norm": 5.222804546356201, | |
| "learning_rate": 1.3234375e-06, | |
| "loss": 0.008, | |
| "step": 20775 | |
| }, | |
| { | |
| "epoch": 9.710550887021475, | |
| "grad_norm": 0.35005176067352295, | |
| "learning_rate": 1.315625e-06, | |
| "loss": 0.008, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 9.722222222222221, | |
| "grad_norm": 1.9022040367126465, | |
| "learning_rate": 1.3078125e-06, | |
| "loss": 0.0045, | |
| "step": 20825 | |
| }, | |
| { | |
| "epoch": 9.733893557422968, | |
| "grad_norm": 2.139233350753784, | |
| "learning_rate": 1.3e-06, | |
| "loss": 0.0054, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 9.745564892623715, | |
| "grad_norm": 4.1651482582092285, | |
| "learning_rate": 1.2921875e-06, | |
| "loss": 0.0053, | |
| "step": 20875 | |
| }, | |
| { | |
| "epoch": 9.757236227824464, | |
| "grad_norm": 2.2410309314727783, | |
| "learning_rate": 1.284375e-06, | |
| "loss": 0.0062, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 9.768907563025211, | |
| "grad_norm": 6.774412631988525, | |
| "learning_rate": 1.2765625e-06, | |
| "loss": 0.0082, | |
| "step": 20925 | |
| }, | |
| { | |
| "epoch": 9.780578898225958, | |
| "grad_norm": 6.076715469360352, | |
| "learning_rate": 1.2687500000000001e-06, | |
| "loss": 0.0066, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 9.792250233426705, | |
| "grad_norm": 0.3256414234638214, | |
| "learning_rate": 1.2609375000000002e-06, | |
| "loss": 0.0058, | |
| "step": 20975 | |
| }, | |
| { | |
| "epoch": 9.803921568627452, | |
| "grad_norm": 0.03926245495676994, | |
| "learning_rate": 1.2531250000000002e-06, | |
| "loss": 0.0081, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 9.815592903828199, | |
| "grad_norm": 14.117586135864258, | |
| "learning_rate": 1.2453125000000002e-06, | |
| "loss": 0.0031, | |
| "step": 21025 | |
| }, | |
| { | |
| "epoch": 9.827264239028946, | |
| "grad_norm": 0.3628706634044647, | |
| "learning_rate": 1.2375000000000002e-06, | |
| "loss": 0.009, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 9.838935574229692, | |
| "grad_norm": 4.5739827156066895, | |
| "learning_rate": 1.2296875e-06, | |
| "loss": 0.0038, | |
| "step": 21075 | |
| }, | |
| { | |
| "epoch": 9.85060690943044, | |
| "grad_norm": 0.16507214307785034, | |
| "learning_rate": 1.221875e-06, | |
| "loss": 0.0101, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 9.862278244631186, | |
| "grad_norm": 7.189055919647217, | |
| "learning_rate": 1.2140625e-06, | |
| "loss": 0.0078, | |
| "step": 21125 | |
| }, | |
| { | |
| "epoch": 9.873949579831933, | |
| "grad_norm": 5.090521812438965, | |
| "learning_rate": 1.20625e-06, | |
| "loss": 0.0083, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 9.88562091503268, | |
| "grad_norm": 2.5861196517944336, | |
| "learning_rate": 1.1984375000000001e-06, | |
| "loss": 0.0047, | |
| "step": 21175 | |
| }, | |
| { | |
| "epoch": 9.897292250233427, | |
| "grad_norm": 0.09222248196601868, | |
| "learning_rate": 1.1906250000000001e-06, | |
| "loss": 0.0099, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 9.908963585434174, | |
| "grad_norm": 4.3550004959106445, | |
| "learning_rate": 1.1828125000000002e-06, | |
| "loss": 0.008, | |
| "step": 21225 | |
| }, | |
| { | |
| "epoch": 9.920634920634921, | |
| "grad_norm": 0.043043483048677444, | |
| "learning_rate": 1.175e-06, | |
| "loss": 0.0083, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 9.932306255835668, | |
| "grad_norm": 0.07931485772132874, | |
| "learning_rate": 1.1671875e-06, | |
| "loss": 0.0082, | |
| "step": 21275 | |
| }, | |
| { | |
| "epoch": 9.943977591036415, | |
| "grad_norm": 0.08949258923530579, | |
| "learning_rate": 1.159375e-06, | |
| "loss": 0.0075, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 9.955648926237162, | |
| "grad_norm": 0.6334654092788696, | |
| "learning_rate": 1.1515625e-06, | |
| "loss": 0.0049, | |
| "step": 21325 | |
| }, | |
| { | |
| "epoch": 9.967320261437909, | |
| "grad_norm": 1.3037919998168945, | |
| "learning_rate": 1.14375e-06, | |
| "loss": 0.0069, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 9.978991596638656, | |
| "grad_norm": 4.038185119628906, | |
| "learning_rate": 1.1359375e-06, | |
| "loss": 0.0099, | |
| "step": 21375 | |
| }, | |
| { | |
| "epoch": 9.990662931839402, | |
| "grad_norm": 0.7718151211738586, | |
| "learning_rate": 1.128125e-06, | |
| "loss": 0.0063, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 10.00233426704015, | |
| "grad_norm": 1.5029001235961914, | |
| "learning_rate": 1.1203125e-06, | |
| "loss": 0.013, | |
| "step": 21425 | |
| }, | |
| { | |
| "epoch": 10.014005602240896, | |
| "grad_norm": 1.8782932758331299, | |
| "learning_rate": 1.1125e-06, | |
| "loss": 0.0048, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 10.025676937441643, | |
| "grad_norm": 1.411063313484192, | |
| "learning_rate": 1.1046875e-06, | |
| "loss": 0.0098, | |
| "step": 21475 | |
| }, | |
| { | |
| "epoch": 10.03734827264239, | |
| "grad_norm": 0.08655665069818497, | |
| "learning_rate": 1.096875e-06, | |
| "loss": 0.0047, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 10.049019607843137, | |
| "grad_norm": 0.7511602640151978, | |
| "learning_rate": 1.0890625e-06, | |
| "loss": 0.0077, | |
| "step": 21525 | |
| }, | |
| { | |
| "epoch": 10.060690943043884, | |
| "grad_norm": 2.6931838989257812, | |
| "learning_rate": 1.08125e-06, | |
| "loss": 0.0036, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 10.072362278244631, | |
| "grad_norm": 1.6642050743103027, | |
| "learning_rate": 1.0734375e-06, | |
| "loss": 0.009, | |
| "step": 21575 | |
| }, | |
| { | |
| "epoch": 10.084033613445378, | |
| "grad_norm": 5.0585503578186035, | |
| "learning_rate": 1.065625e-06, | |
| "loss": 0.0054, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 10.095704948646125, | |
| "grad_norm": 1.2419428825378418, | |
| "learning_rate": 1.0578125e-06, | |
| "loss": 0.0049, | |
| "step": 21625 | |
| }, | |
| { | |
| "epoch": 10.107376283846872, | |
| "grad_norm": 0.0439959391951561, | |
| "learning_rate": 1.0500000000000001e-06, | |
| "loss": 0.006, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 10.119047619047619, | |
| "grad_norm": 0.7057489156723022, | |
| "learning_rate": 1.0421875000000001e-06, | |
| "loss": 0.0069, | |
| "step": 21675 | |
| }, | |
| { | |
| "epoch": 10.130718954248366, | |
| "grad_norm": 0.08024278283119202, | |
| "learning_rate": 1.0343750000000002e-06, | |
| "loss": 0.0028, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 10.142390289449112, | |
| "grad_norm": 0.21487966179847717, | |
| "learning_rate": 1.0265625000000002e-06, | |
| "loss": 0.0033, | |
| "step": 21725 | |
| }, | |
| { | |
| "epoch": 10.15406162464986, | |
| "grad_norm": 0.19071203470230103, | |
| "learning_rate": 1.01875e-06, | |
| "loss": 0.0036, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 10.165732959850606, | |
| "grad_norm": 0.27428773045539856, | |
| "learning_rate": 1.0109375e-06, | |
| "loss": 0.0103, | |
| "step": 21775 | |
| }, | |
| { | |
| "epoch": 10.177404295051353, | |
| "grad_norm": 1.418234944343567, | |
| "learning_rate": 1.003125e-06, | |
| "loss": 0.0058, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 10.1890756302521, | |
| "grad_norm": 0.8873878717422485, | |
| "learning_rate": 9.953125e-07, | |
| "loss": 0.0139, | |
| "step": 21825 | |
| }, | |
| { | |
| "epoch": 10.200746965452847, | |
| "grad_norm": 0.583903431892395, | |
| "learning_rate": 9.875e-07, | |
| "loss": 0.0033, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 10.212418300653594, | |
| "grad_norm": 0.245305597782135, | |
| "learning_rate": 9.796875e-07, | |
| "loss": 0.0097, | |
| "step": 21875 | |
| }, | |
| { | |
| "epoch": 10.224089635854341, | |
| "grad_norm": 3.605557441711426, | |
| "learning_rate": 9.718750000000001e-07, | |
| "loss": 0.0073, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 10.235760971055088, | |
| "grad_norm": 0.19548866152763367, | |
| "learning_rate": 9.640625000000001e-07, | |
| "loss": 0.0063, | |
| "step": 21925 | |
| }, | |
| { | |
| "epoch": 10.247432306255835, | |
| "grad_norm": 0.807528555393219, | |
| "learning_rate": 9.5625e-07, | |
| "loss": 0.0033, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 10.259103641456583, | |
| "grad_norm": 0.32932284474372864, | |
| "learning_rate": 9.484375e-07, | |
| "loss": 0.0047, | |
| "step": 21975 | |
| }, | |
| { | |
| "epoch": 10.27077497665733, | |
| "grad_norm": 0.1796354502439499, | |
| "learning_rate": 9.40625e-07, | |
| "loss": 0.0091, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 10.282446311858077, | |
| "grad_norm": 1.3611717224121094, | |
| "learning_rate": 9.328125e-07, | |
| "loss": 0.0075, | |
| "step": 22025 | |
| }, | |
| { | |
| "epoch": 10.294117647058824, | |
| "grad_norm": 0.0766756534576416, | |
| "learning_rate": 9.25e-07, | |
| "loss": 0.0055, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 10.305788982259571, | |
| "grad_norm": 0.7175803184509277, | |
| "learning_rate": 9.171875e-07, | |
| "loss": 0.01, | |
| "step": 22075 | |
| }, | |
| { | |
| "epoch": 10.317460317460318, | |
| "grad_norm": 0.23721574246883392, | |
| "learning_rate": 9.09375e-07, | |
| "loss": 0.0039, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 10.329131652661065, | |
| "grad_norm": 0.23020412027835846, | |
| "learning_rate": 9.015625e-07, | |
| "loss": 0.0052, | |
| "step": 22125 | |
| }, | |
| { | |
| "epoch": 10.340802987861812, | |
| "grad_norm": 1.632659912109375, | |
| "learning_rate": 8.9375e-07, | |
| "loss": 0.0058, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 10.352474323062559, | |
| "grad_norm": 1.804761528968811, | |
| "learning_rate": 8.859374999999999e-07, | |
| "loss": 0.0055, | |
| "step": 22175 | |
| }, | |
| { | |
| "epoch": 10.364145658263306, | |
| "grad_norm": 0.08536524325609207, | |
| "learning_rate": 8.781250000000002e-07, | |
| "loss": 0.0026, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 10.375816993464053, | |
| "grad_norm": 1.1236313581466675, | |
| "learning_rate": 8.703125000000001e-07, | |
| "loss": 0.0097, | |
| "step": 22225 | |
| }, | |
| { | |
| "epoch": 10.3874883286648, | |
| "grad_norm": 0.6604540944099426, | |
| "learning_rate": 8.625000000000001e-07, | |
| "loss": 0.0041, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 10.399159663865547, | |
| "grad_norm": 0.28819596767425537, | |
| "learning_rate": 8.546875000000001e-07, | |
| "loss": 0.0035, | |
| "step": 22275 | |
| }, | |
| { | |
| "epoch": 10.410830999066294, | |
| "grad_norm": 0.0771021619439125, | |
| "learning_rate": 8.468750000000002e-07, | |
| "loss": 0.0045, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 10.42250233426704, | |
| "grad_norm": 1.4627320766448975, | |
| "learning_rate": 8.390625000000001e-07, | |
| "loss": 0.0084, | |
| "step": 22325 | |
| }, | |
| { | |
| "epoch": 10.434173669467787, | |
| "grad_norm": 1.7134203910827637, | |
| "learning_rate": 8.312500000000001e-07, | |
| "loss": 0.0053, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 10.445845004668534, | |
| "grad_norm": 0.29320698976516724, | |
| "learning_rate": 8.234375000000001e-07, | |
| "loss": 0.0095, | |
| "step": 22375 | |
| }, | |
| { | |
| "epoch": 10.457516339869281, | |
| "grad_norm": 4.652510643005371, | |
| "learning_rate": 8.15625e-07, | |
| "loss": 0.0033, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 10.469187675070028, | |
| "grad_norm": 0.07530553638935089, | |
| "learning_rate": 8.078125e-07, | |
| "loss": 0.0135, | |
| "step": 22425 | |
| }, | |
| { | |
| "epoch": 10.480859010270775, | |
| "grad_norm": 5.351443290710449, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.0051, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 10.492530345471522, | |
| "grad_norm": 1.0543556213378906, | |
| "learning_rate": 7.921875000000001e-07, | |
| "loss": 0.0126, | |
| "step": 22475 | |
| }, | |
| { | |
| "epoch": 10.504201680672269, | |
| "grad_norm": 0.12515470385551453, | |
| "learning_rate": 7.84375e-07, | |
| "loss": 0.004, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 10.515873015873016, | |
| "grad_norm": 0.6163919568061829, | |
| "learning_rate": 7.765625e-07, | |
| "loss": 0.0062, | |
| "step": 22525 | |
| }, | |
| { | |
| "epoch": 10.527544351073763, | |
| "grad_norm": 1.1225354671478271, | |
| "learning_rate": 7.6875e-07, | |
| "loss": 0.0046, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 10.53921568627451, | |
| "grad_norm": 1.0655065774917603, | |
| "learning_rate": 7.609375e-07, | |
| "loss": 0.0049, | |
| "step": 22575 | |
| }, | |
| { | |
| "epoch": 10.550887021475257, | |
| "grad_norm": 2.211533308029175, | |
| "learning_rate": 7.53125e-07, | |
| "loss": 0.0034, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 10.562558356676004, | |
| "grad_norm": 0.19352863729000092, | |
| "learning_rate": 7.453125e-07, | |
| "loss": 0.0048, | |
| "step": 22625 | |
| }, | |
| { | |
| "epoch": 10.57422969187675, | |
| "grad_norm": 0.6760672926902771, | |
| "learning_rate": 7.375e-07, | |
| "loss": 0.0041, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 10.585901027077497, | |
| "grad_norm": 1.2626034021377563, | |
| "learning_rate": 7.296875000000001e-07, | |
| "loss": 0.0089, | |
| "step": 22675 | |
| }, | |
| { | |
| "epoch": 10.597572362278244, | |
| "grad_norm": 4.768553256988525, | |
| "learning_rate": 7.218750000000001e-07, | |
| "loss": 0.0047, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 10.609243697478991, | |
| "grad_norm": 0.35717836022377014, | |
| "learning_rate": 7.140625000000001e-07, | |
| "loss": 0.0077, | |
| "step": 22725 | |
| }, | |
| { | |
| "epoch": 10.620915032679738, | |
| "grad_norm": 0.17013007402420044, | |
| "learning_rate": 7.0625e-07, | |
| "loss": 0.0047, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 10.632586367880485, | |
| "grad_norm": 0.8509282469749451, | |
| "learning_rate": 6.984375e-07, | |
| "loss": 0.0101, | |
| "step": 22775 | |
| }, | |
| { | |
| "epoch": 10.644257703081232, | |
| "grad_norm": 3.9586565494537354, | |
| "learning_rate": 6.906250000000001e-07, | |
| "loss": 0.0025, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 10.655929038281979, | |
| "grad_norm": 0.7251598238945007, | |
| "learning_rate": 6.828125000000001e-07, | |
| "loss": 0.0079, | |
| "step": 22825 | |
| }, | |
| { | |
| "epoch": 10.667600373482726, | |
| "grad_norm": 0.039994291961193085, | |
| "learning_rate": 6.75e-07, | |
| "loss": 0.0048, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 10.679271708683473, | |
| "grad_norm": 1.6940975189208984, | |
| "learning_rate": 6.671875e-07, | |
| "loss": 0.0095, | |
| "step": 22875 | |
| }, | |
| { | |
| "epoch": 10.69094304388422, | |
| "grad_norm": 3.833244562149048, | |
| "learning_rate": 6.59375e-07, | |
| "loss": 0.004, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 10.702614379084967, | |
| "grad_norm": 0.6546738743782043, | |
| "learning_rate": 6.515625e-07, | |
| "loss": 0.0084, | |
| "step": 22925 | |
| }, | |
| { | |
| "epoch": 10.714285714285714, | |
| "grad_norm": 0.04062287509441376, | |
| "learning_rate": 6.4375e-07, | |
| "loss": 0.0059, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 10.72595704948646, | |
| "grad_norm": 0.1445113569498062, | |
| "learning_rate": 6.359375e-07, | |
| "loss": 0.0135, | |
| "step": 22975 | |
| }, | |
| { | |
| "epoch": 10.73762838468721, | |
| "grad_norm": 0.029490185901522636, | |
| "learning_rate": 6.28125e-07, | |
| "loss": 0.0033, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 10.749299719887954, | |
| "grad_norm": 1.9724853038787842, | |
| "learning_rate": 6.203125e-07, | |
| "loss": 0.0078, | |
| "step": 23025 | |
| }, | |
| { | |
| "epoch": 10.760971055088703, | |
| "grad_norm": 0.8680882453918457, | |
| "learning_rate": 6.125000000000001e-07, | |
| "loss": 0.0035, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 10.77264239028945, | |
| "grad_norm": 0.0470956526696682, | |
| "learning_rate": 6.046875000000001e-07, | |
| "loss": 0.0055, | |
| "step": 23075 | |
| }, | |
| { | |
| "epoch": 10.784313725490197, | |
| "grad_norm": 0.06983581185340881, | |
| "learning_rate": 5.96875e-07, | |
| "loss": 0.0058, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 10.795985060690944, | |
| "grad_norm": 0.3825051784515381, | |
| "learning_rate": 5.890625e-07, | |
| "loss": 0.0168, | |
| "step": 23125 | |
| }, | |
| { | |
| "epoch": 10.80765639589169, | |
| "grad_norm": 2.345949649810791, | |
| "learning_rate": 5.8125e-07, | |
| "loss": 0.0038, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 10.819327731092438, | |
| "grad_norm": 1.4795840978622437, | |
| "learning_rate": 5.734375000000001e-07, | |
| "loss": 0.0095, | |
| "step": 23175 | |
| }, | |
| { | |
| "epoch": 10.830999066293185, | |
| "grad_norm": 0.686439037322998, | |
| "learning_rate": 5.65625e-07, | |
| "loss": 0.0091, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 10.842670401493931, | |
| "grad_norm": 0.14041809737682343, | |
| "learning_rate": 5.578125e-07, | |
| "loss": 0.01, | |
| "step": 23225 | |
| }, | |
| { | |
| "epoch": 10.854341736694678, | |
| "grad_norm": 4.803620338439941, | |
| "learning_rate": 5.5e-07, | |
| "loss": 0.0057, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 10.866013071895425, | |
| "grad_norm": 0.07831548154354095, | |
| "learning_rate": 5.421874999999999e-07, | |
| "loss": 0.0062, | |
| "step": 23275 | |
| }, | |
| { | |
| "epoch": 10.877684407096172, | |
| "grad_norm": 1.9763298034667969, | |
| "learning_rate": 5.343750000000001e-07, | |
| "loss": 0.0038, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 10.88935574229692, | |
| "grad_norm": 0.3448634445667267, | |
| "learning_rate": 5.265625000000001e-07, | |
| "loss": 0.0082, | |
| "step": 23325 | |
| }, | |
| { | |
| "epoch": 10.901027077497666, | |
| "grad_norm": 0.04117899760603905, | |
| "learning_rate": 5.1875e-07, | |
| "loss": 0.0031, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 10.912698412698413, | |
| "grad_norm": 0.21676640212535858, | |
| "learning_rate": 5.109375e-07, | |
| "loss": 0.0049, | |
| "step": 23375 | |
| }, | |
| { | |
| "epoch": 10.92436974789916, | |
| "grad_norm": 3.311768054962158, | |
| "learning_rate": 5.031250000000001e-07, | |
| "loss": 0.007, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 10.936041083099907, | |
| "grad_norm": 2.6684231758117676, | |
| "learning_rate": 4.953125000000001e-07, | |
| "loss": 0.0054, | |
| "step": 23425 | |
| }, | |
| { | |
| "epoch": 10.947712418300654, | |
| "grad_norm": 0.7720322012901306, | |
| "learning_rate": 4.875e-07, | |
| "loss": 0.0052, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 10.9593837535014, | |
| "grad_norm": 1.1452654600143433, | |
| "learning_rate": 4.796875e-07, | |
| "loss": 0.0059, | |
| "step": 23475 | |
| }, | |
| { | |
| "epoch": 10.971055088702148, | |
| "grad_norm": 0.04618614539504051, | |
| "learning_rate": 4.71875e-07, | |
| "loss": 0.0063, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 10.982726423902895, | |
| "grad_norm": 2.9821794033050537, | |
| "learning_rate": 4.640625e-07, | |
| "loss": 0.0042, | |
| "step": 23525 | |
| }, | |
| { | |
| "epoch": 10.994397759103641, | |
| "grad_norm": 3.0062246322631836, | |
| "learning_rate": 4.5624999999999997e-07, | |
| "loss": 0.0077, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 11.006069094304388, | |
| "grad_norm": 2.828244209289551, | |
| "learning_rate": 4.484375e-07, | |
| "loss": 0.0078, | |
| "step": 23575 | |
| }, | |
| { | |
| "epoch": 11.017740429505135, | |
| "grad_norm": 4.736670970916748, | |
| "learning_rate": 4.4062499999999996e-07, | |
| "loss": 0.0074, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 11.029411764705882, | |
| "grad_norm": 1.2825249433517456, | |
| "learning_rate": 4.3281250000000004e-07, | |
| "loss": 0.0111, | |
| "step": 23625 | |
| }, | |
| { | |
| "epoch": 11.04108309990663, | |
| "grad_norm": 2.528594732284546, | |
| "learning_rate": 4.2500000000000006e-07, | |
| "loss": 0.006, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 11.052754435107376, | |
| "grad_norm": 0.05410047993063927, | |
| "learning_rate": 4.1718750000000003e-07, | |
| "loss": 0.0059, | |
| "step": 23675 | |
| }, | |
| { | |
| "epoch": 11.064425770308123, | |
| "grad_norm": 1.0883435010910034, | |
| "learning_rate": 4.0937500000000005e-07, | |
| "loss": 0.0031, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 11.07609710550887, | |
| "grad_norm": 1.926758885383606, | |
| "learning_rate": 4.015625e-07, | |
| "loss": 0.0095, | |
| "step": 23725 | |
| }, | |
| { | |
| "epoch": 11.087768440709617, | |
| "grad_norm": 0.09137524664402008, | |
| "learning_rate": 3.940625e-07, | |
| "loss": 0.0083, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 11.099439775910364, | |
| "grad_norm": 0.14325258135795593, | |
| "learning_rate": 3.8625e-07, | |
| "loss": 0.0039, | |
| "step": 23775 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 0.04979300498962402, | |
| "learning_rate": 3.7843750000000003e-07, | |
| "loss": 0.0052, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 11.122782446311858, | |
| "grad_norm": 0.8827780485153198, | |
| "learning_rate": 3.70625e-07, | |
| "loss": 0.0046, | |
| "step": 23825 | |
| }, | |
| { | |
| "epoch": 11.134453781512605, | |
| "grad_norm": 2.0285470485687256, | |
| "learning_rate": 3.628125e-07, | |
| "loss": 0.002, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 11.146125116713351, | |
| "grad_norm": 0.05097728595137596, | |
| "learning_rate": 3.5500000000000004e-07, | |
| "loss": 0.0082, | |
| "step": 23875 | |
| }, | |
| { | |
| "epoch": 11.157796451914098, | |
| "grad_norm": 1.0123631954193115, | |
| "learning_rate": 3.471875e-07, | |
| "loss": 0.002, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 11.169467787114845, | |
| "grad_norm": 0.06493563950061798, | |
| "learning_rate": 3.3937500000000003e-07, | |
| "loss": 0.0065, | |
| "step": 23925 | |
| }, | |
| { | |
| "epoch": 11.181139122315592, | |
| "grad_norm": 0.05671960860490799, | |
| "learning_rate": 3.315625e-07, | |
| "loss": 0.0074, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 11.19281045751634, | |
| "grad_norm": 0.06837425380945206, | |
| "learning_rate": 3.2375e-07, | |
| "loss": 0.0062, | |
| "step": 23975 | |
| }, | |
| { | |
| "epoch": 11.204481792717086, | |
| "grad_norm": 0.38731399178504944, | |
| "learning_rate": 3.159375e-07, | |
| "loss": 0.0057, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 11.216153127917833, | |
| "grad_norm": 1.3272087574005127, | |
| "learning_rate": 3.084375e-07, | |
| "loss": 0.0071, | |
| "step": 24025 | |
| }, | |
| { | |
| "epoch": 11.22782446311858, | |
| "grad_norm": 0.15108473598957062, | |
| "learning_rate": 3.00625e-07, | |
| "loss": 0.0066, | |
| "step": 24050 | |
| }, | |
| { | |
| "epoch": 11.239495798319327, | |
| "grad_norm": 1.1661783456802368, | |
| "learning_rate": 2.9281250000000006e-07, | |
| "loss": 0.007, | |
| "step": 24075 | |
| }, | |
| { | |
| "epoch": 11.251167133520074, | |
| "grad_norm": 0.22821743786334991, | |
| "learning_rate": 2.85e-07, | |
| "loss": 0.0045, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 11.262838468720823, | |
| "grad_norm": 0.8526090383529663, | |
| "learning_rate": 2.771875e-07, | |
| "loss": 0.0056, | |
| "step": 24125 | |
| }, | |
| { | |
| "epoch": 11.27450980392157, | |
| "grad_norm": 0.3976341784000397, | |
| "learning_rate": 2.69375e-07, | |
| "loss": 0.0076, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 11.286181139122316, | |
| "grad_norm": 0.0741284042596817, | |
| "learning_rate": 2.615625e-07, | |
| "loss": 0.0079, | |
| "step": 24175 | |
| }, | |
| { | |
| "epoch": 11.297852474323063, | |
| "grad_norm": 0.057843729853630066, | |
| "learning_rate": 2.5375e-07, | |
| "loss": 0.0042, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 11.30952380952381, | |
| "grad_norm": 1.2884389162063599, | |
| "learning_rate": 2.4593750000000003e-07, | |
| "loss": 0.0062, | |
| "step": 24225 | |
| }, | |
| { | |
| "epoch": 11.321195144724557, | |
| "grad_norm": 4.889528274536133, | |
| "learning_rate": 2.3812500000000002e-07, | |
| "loss": 0.0062, | |
| "step": 24250 | |
| }, | |
| { | |
| "epoch": 11.332866479925304, | |
| "grad_norm": 0.019720420241355896, | |
| "learning_rate": 2.3031250000000002e-07, | |
| "loss": 0.0062, | |
| "step": 24275 | |
| }, | |
| { | |
| "epoch": 11.344537815126051, | |
| "grad_norm": 0.22723744809627533, | |
| "learning_rate": 2.2250000000000001e-07, | |
| "loss": 0.0035, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 11.356209150326798, | |
| "grad_norm": 0.05429434776306152, | |
| "learning_rate": 2.146875e-07, | |
| "loss": 0.009, | |
| "step": 24325 | |
| }, | |
| { | |
| "epoch": 11.367880485527545, | |
| "grad_norm": 0.10212606936693192, | |
| "learning_rate": 2.06875e-07, | |
| "loss": 0.0058, | |
| "step": 24350 | |
| }, | |
| { | |
| "epoch": 11.379551820728292, | |
| "grad_norm": 1.9913432598114014, | |
| "learning_rate": 1.9906250000000003e-07, | |
| "loss": 0.0097, | |
| "step": 24375 | |
| }, | |
| { | |
| "epoch": 11.391223155929039, | |
| "grad_norm": 0.32066085934638977, | |
| "learning_rate": 1.9125e-07, | |
| "loss": 0.0039, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 11.402894491129786, | |
| "grad_norm": 0.029058467596769333, | |
| "learning_rate": 1.8343750000000002e-07, | |
| "loss": 0.004, | |
| "step": 24425 | |
| }, | |
| { | |
| "epoch": 11.414565826330533, | |
| "grad_norm": 1.6832449436187744, | |
| "learning_rate": 1.75625e-07, | |
| "loss": 0.004, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 11.42623716153128, | |
| "grad_norm": 0.04252633824944496, | |
| "learning_rate": 1.678125e-07, | |
| "loss": 0.0093, | |
| "step": 24475 | |
| }, | |
| { | |
| "epoch": 11.437908496732026, | |
| "grad_norm": 4.079598903656006, | |
| "learning_rate": 1.6e-07, | |
| "loss": 0.0073, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 11.449579831932773, | |
| "grad_norm": 2.663240432739258, | |
| "learning_rate": 1.521875e-07, | |
| "loss": 0.003, | |
| "step": 24525 | |
| }, | |
| { | |
| "epoch": 11.46125116713352, | |
| "grad_norm": 0.06202975660562515, | |
| "learning_rate": 1.44375e-07, | |
| "loss": 0.0051, | |
| "step": 24550 | |
| }, | |
| { | |
| "epoch": 11.472922502334267, | |
| "grad_norm": 0.111959308385849, | |
| "learning_rate": 1.3656250000000002e-07, | |
| "loss": 0.0067, | |
| "step": 24575 | |
| }, | |
| { | |
| "epoch": 11.484593837535014, | |
| "grad_norm": 0.02303888648748398, | |
| "learning_rate": 1.2875e-07, | |
| "loss": 0.0074, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 11.496265172735761, | |
| "grad_norm": 0.43197059631347656, | |
| "learning_rate": 1.209375e-07, | |
| "loss": 0.0071, | |
| "step": 24625 | |
| }, | |
| { | |
| "epoch": 11.507936507936508, | |
| "grad_norm": 3.6830546855926514, | |
| "learning_rate": 1.1312500000000002e-07, | |
| "loss": 0.0068, | |
| "step": 24650 | |
| }, | |
| { | |
| "epoch": 11.519607843137255, | |
| "grad_norm": 0.06097732484340668, | |
| "learning_rate": 1.0531250000000001e-07, | |
| "loss": 0.0089, | |
| "step": 24675 | |
| }, | |
| { | |
| "epoch": 11.531279178338002, | |
| "grad_norm": 0.06942930817604065, | |
| "learning_rate": 9.75e-08, | |
| "loss": 0.003, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 11.542950513538749, | |
| "grad_norm": 2.829679012298584, | |
| "learning_rate": 8.96875e-08, | |
| "loss": 0.0075, | |
| "step": 24725 | |
| }, | |
| { | |
| "epoch": 11.554621848739496, | |
| "grad_norm": 3.9653916358947754, | |
| "learning_rate": 8.187500000000001e-08, | |
| "loss": 0.0063, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 11.566293183940243, | |
| "grad_norm": 0.29860720038414, | |
| "learning_rate": 7.40625e-08, | |
| "loss": 0.0068, | |
| "step": 24775 | |
| }, | |
| { | |
| "epoch": 11.57796451914099, | |
| "grad_norm": 0.04515097290277481, | |
| "learning_rate": 6.625e-08, | |
| "loss": 0.0041, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 11.589635854341736, | |
| "grad_norm": 0.026890119537711143, | |
| "learning_rate": 5.843750000000001e-08, | |
| "loss": 0.0051, | |
| "step": 24825 | |
| }, | |
| { | |
| "epoch": 11.601307189542483, | |
| "grad_norm": 0.44632381200790405, | |
| "learning_rate": 5.0625e-08, | |
| "loss": 0.0047, | |
| "step": 24850 | |
| }, | |
| { | |
| "epoch": 11.61297852474323, | |
| "grad_norm": 0.17215296626091003, | |
| "learning_rate": 4.28125e-08, | |
| "loss": 0.0079, | |
| "step": 24875 | |
| }, | |
| { | |
| "epoch": 11.624649859943977, | |
| "grad_norm": 2.4952566623687744, | |
| "learning_rate": 3.5e-08, | |
| "loss": 0.0043, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 11.636321195144724, | |
| "grad_norm": 2.0370965003967285, | |
| "learning_rate": 2.7187499999999998e-08, | |
| "loss": 0.0075, | |
| "step": 24925 | |
| }, | |
| { | |
| "epoch": 11.647992530345471, | |
| "grad_norm": 2.6626877784729004, | |
| "learning_rate": 1.9375e-08, | |
| "loss": 0.0057, | |
| "step": 24950 | |
| }, | |
| { | |
| "epoch": 11.659663865546218, | |
| "grad_norm": 0.16452664136886597, | |
| "learning_rate": 1.1562500000000002e-08, | |
| "loss": 0.0091, | |
| "step": 24975 | |
| }, | |
| { | |
| "epoch": 11.671335200746965, | |
| "grad_norm": 0.11460210382938385, | |
| "learning_rate": 3.75e-09, | |
| "loss": 0.0035, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 11.671335200746965, | |
| "eval_loss": 0.20881079137325287, | |
| "eval_runtime": 5358.5345, | |
| "eval_samples_per_second": 1.757, | |
| "eval_steps_per_second": 0.22, | |
| "eval_wer": 0.09323429678669466, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 11.671335200746965, | |
| "step": 25000, | |
| "total_flos": 4.081858297380864e+20, | |
| "train_loss": 0.052512485960870985, | |
| "train_runtime": 210665.5128, | |
| "train_samples_per_second": 1.899, | |
| "train_steps_per_second": 0.119 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 25000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.081858297380864e+20, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |