| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9986174205016789, | |
| "eval_steps": 16, | |
| "global_step": 158, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006320363420896702, | |
| "grad_norm": 0.48046875, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6497, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006320363420896702, | |
| "eval_loss": 0.5998793244361877, | |
| "eval_runtime": 56.2331, | |
| "eval_samples_per_second": 18.957, | |
| "eval_steps_per_second": 18.957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012640726841793404, | |
| "grad_norm": 0.470703125, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6349, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018961090262690106, | |
| "grad_norm": 0.46875, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5832, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.025281453683586808, | |
| "grad_norm": 0.47265625, | |
| "learning_rate": 8e-05, | |
| "loss": 0.557, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03160181710448351, | |
| "grad_norm": 0.35546875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4966, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03792218052538021, | |
| "grad_norm": 0.31640625, | |
| "learning_rate": 0.00012, | |
| "loss": 0.3771, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04424254394627691, | |
| "grad_norm": 0.298828125, | |
| "learning_rate": 0.00014, | |
| "loss": 0.318, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.050562907367173615, | |
| "grad_norm": 0.36328125, | |
| "learning_rate": 0.00016, | |
| "loss": 0.296, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05688327078807032, | |
| "grad_norm": 0.3046875, | |
| "learning_rate": 0.00018, | |
| "loss": 0.2682, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06320363420896702, | |
| "grad_norm": 0.29296875, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3039, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06952399762986372, | |
| "grad_norm": 0.1845703125, | |
| "learning_rate": 0.00019999770790755575, | |
| "loss": 0.3096, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07584436105076042, | |
| "grad_norm": 0.16796875, | |
| "learning_rate": 0.00019999083173529673, | |
| "loss": 0.2575, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08216472447165712, | |
| "grad_norm": 0.1689453125, | |
| "learning_rate": 0.00019997937179843937, | |
| "loss": 0.289, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08848508789255383, | |
| "grad_norm": 0.1572265625, | |
| "learning_rate": 0.0001999633286223284, | |
| "loss": 0.2878, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09480545131345053, | |
| "grad_norm": 0.12353515625, | |
| "learning_rate": 0.00019994270294241266, | |
| "loss": 0.2274, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10112581473434723, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 0.00019991749570421146, | |
| "loss": 0.2252, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10112581473434723, | |
| "eval_loss": 0.25023654103279114, | |
| "eval_runtime": 56.1603, | |
| "eval_samples_per_second": 18.981, | |
| "eval_steps_per_second": 18.981, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10744617815524393, | |
| "grad_norm": 0.1298828125, | |
| "learning_rate": 0.0001998877080632712, | |
| "loss": 0.2512, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11376654157614063, | |
| "grad_norm": 0.193359375, | |
| "learning_rate": 0.00019985334138511237, | |
| "loss": 0.2659, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12008690499703734, | |
| "grad_norm": 0.142578125, | |
| "learning_rate": 0.00019981439724516716, | |
| "loss": 0.2415, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12640726841793404, | |
| "grad_norm": 0.126953125, | |
| "learning_rate": 0.0001997708774287068, | |
| "loss": 0.2661, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13272763183883074, | |
| "grad_norm": 0.1142578125, | |
| "learning_rate": 0.00019972278393076023, | |
| "loss": 0.2046, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13904799525972744, | |
| "grad_norm": 0.11865234375, | |
| "learning_rate": 0.0001996701189560223, | |
| "loss": 0.2087, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14536835868062414, | |
| "grad_norm": 0.1435546875, | |
| "learning_rate": 0.00019961288491875278, | |
| "loss": 0.2246, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15168872210152085, | |
| "grad_norm": 0.119140625, | |
| "learning_rate": 0.00019955108444266585, | |
| "loss": 0.1831, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15800908552241755, | |
| "grad_norm": 0.1376953125, | |
| "learning_rate": 0.00019948472036080949, | |
| "loss": 0.2398, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16432944894331425, | |
| "grad_norm": 0.1201171875, | |
| "learning_rate": 0.00019941379571543596, | |
| "loss": 0.189, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.17064981236421095, | |
| "grad_norm": 0.12890625, | |
| "learning_rate": 0.00019933831375786216, | |
| "loss": 0.2156, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.17697017578510765, | |
| "grad_norm": 0.1259765625, | |
| "learning_rate": 0.00019925827794832056, | |
| "loss": 0.2012, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18329053920600435, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 0.00019917369195580063, | |
| "loss": 0.1602, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.18961090262690106, | |
| "grad_norm": 0.12890625, | |
| "learning_rate": 0.00019908455965788067, | |
| "loss": 0.1976, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19593126604779776, | |
| "grad_norm": 0.11279296875, | |
| "learning_rate": 0.00019899088514055004, | |
| "loss": 0.1874, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.20225162946869446, | |
| "grad_norm": 0.1357421875, | |
| "learning_rate": 0.00019889267269802176, | |
| "loss": 0.2024, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20225162946869446, | |
| "eval_loss": 0.2020280808210373, | |
| "eval_runtime": 56.2737, | |
| "eval_samples_per_second": 18.943, | |
| "eval_steps_per_second": 18.943, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20857199288959116, | |
| "grad_norm": 0.1123046875, | |
| "learning_rate": 0.00019878992683253582, | |
| "loss": 0.1819, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.21489235631048786, | |
| "grad_norm": 0.1123046875, | |
| "learning_rate": 0.00019868265225415265, | |
| "loss": 0.1794, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22121271973138457, | |
| "grad_norm": 0.12060546875, | |
| "learning_rate": 0.00019857085388053723, | |
| "loss": 0.1943, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22753308315228127, | |
| "grad_norm": 0.134765625, | |
| "learning_rate": 0.00019845453683673368, | |
| "loss": 0.2265, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.23385344657317797, | |
| "grad_norm": 0.115234375, | |
| "learning_rate": 0.00019833370645493047, | |
| "loss": 0.181, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.24017380999407467, | |
| "grad_norm": 0.12353515625, | |
| "learning_rate": 0.0001982083682742156, | |
| "loss": 0.1946, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.24649417341497137, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 0.1418, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2528145368358681, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 0.00019794419170536916, | |
| "loss": 0.1651, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2591349002567648, | |
| "grad_norm": 0.1337890625, | |
| "learning_rate": 0.00019780536542758, | |
| "loss": 0.1821, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2654552636776615, | |
| "grad_norm": 0.12353515625, | |
| "learning_rate": 0.00019766205557100868, | |
| "loss": 0.1913, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2717756270985582, | |
| "grad_norm": 0.12451171875, | |
| "learning_rate": 0.00019751426870524407, | |
| "loss": 0.194, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2780959905194549, | |
| "grad_norm": 0.1162109375, | |
| "learning_rate": 0.00019736201160510931, | |
| "loss": 0.1832, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2844163539403516, | |
| "grad_norm": 0.12353515625, | |
| "learning_rate": 0.0001972052912503514, | |
| "loss": 0.19, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2907367173612483, | |
| "grad_norm": 0.11474609375, | |
| "learning_rate": 0.00019704411482532116, | |
| "loss": 0.1875, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.297057080782145, | |
| "grad_norm": 0.1123046875, | |
| "learning_rate": 0.00019687848971864389, | |
| "loss": 0.184, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3033774442030417, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 0.0001967084235228807, | |
| "loss": 0.1581, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3033774442030417, | |
| "eval_loss": 0.18037649989128113, | |
| "eval_runtime": 56.5509, | |
| "eval_samples_per_second": 18.85, | |
| "eval_steps_per_second": 18.85, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3096978076239384, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 0.00019653392403418043, | |
| "loss": 0.1766, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3160181710448351, | |
| "grad_norm": 0.11669921875, | |
| "learning_rate": 0.0001963549992519223, | |
| "loss": 0.1888, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3223385344657318, | |
| "grad_norm": 0.10009765625, | |
| "learning_rate": 0.00019617165737834916, | |
| "loss": 0.139, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3286588978866285, | |
| "grad_norm": 0.12451171875, | |
| "learning_rate": 0.0001959839068181914, | |
| "loss": 0.1845, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3349792613075252, | |
| "grad_norm": 0.12060546875, | |
| "learning_rate": 0.00019579175617828187, | |
| "loss": 0.2043, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3412996247284219, | |
| "grad_norm": 0.1142578125, | |
| "learning_rate": 0.00019559521426716118, | |
| "loss": 0.1678, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3476199881493186, | |
| "grad_norm": 0.11669921875, | |
| "learning_rate": 0.0001953942900946739, | |
| "loss": 0.1671, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3539403515702153, | |
| "grad_norm": 0.115234375, | |
| "learning_rate": 0.00019518899287155556, | |
| "loss": 0.1724, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.360260714991112, | |
| "grad_norm": 0.126953125, | |
| "learning_rate": 0.0001949793320090105, | |
| "loss": 0.177, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.3665810784120087, | |
| "grad_norm": 0.1259765625, | |
| "learning_rate": 0.00019476531711828027, | |
| "loss": 0.1644, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.3729014418329054, | |
| "grad_norm": 0.1142578125, | |
| "learning_rate": 0.0001945469580102031, | |
| "loss": 0.1564, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.3792218052538021, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 0.0001943242646947643, | |
| "loss": 0.1353, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 0.00019409724738063714, | |
| "loss": 0.1622, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3918625320955955, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 0.00019386591647471506, | |
| "loss": 0.1564, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.3981828955164922, | |
| "grad_norm": 0.11376953125, | |
| "learning_rate": 0.00019363028258163447, | |
| "loss": 0.176, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4045032589373889, | |
| "grad_norm": 0.1162109375, | |
| "learning_rate": 0.00019339035650328869, | |
| "loss": 0.1912, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4045032589373889, | |
| "eval_loss": 0.1681559830904007, | |
| "eval_runtime": 56.4912, | |
| "eval_samples_per_second": 18.87, | |
| "eval_steps_per_second": 18.87, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4108236223582856, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 0.0001931461492383327, | |
| "loss": 0.1959, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4171439857791823, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 0.00019289767198167916, | |
| "loss": 0.1379, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.423464349200079, | |
| "grad_norm": 0.1142578125, | |
| "learning_rate": 0.00019264493612398481, | |
| "loss": 0.1669, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.42978471262097573, | |
| "grad_norm": 0.09619140625, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.1279, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.43610507604187243, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.0001921267351436808, | |
| "loss": 0.1535, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.44242543946276913, | |
| "grad_norm": 0.11962890625, | |
| "learning_rate": 0.0001918612937763622, | |
| "loss": 0.1697, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44874580288366583, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 0.00019159164131749587, | |
| "loss": 0.166, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.45506616630456254, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.00019131779012844912, | |
| "loss": 0.1508, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.46138652972545924, | |
| "grad_norm": 0.1201171875, | |
| "learning_rate": 0.00019103975276306678, | |
| "loss": 0.1617, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.46770689314635594, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 0.00019075754196709572, | |
| "loss": 0.1436, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.47402725656725264, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 0.0001904711706776006, | |
| "loss": 0.1408, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.48034761998814934, | |
| "grad_norm": 0.1171875, | |
| "learning_rate": 0.00019018065202237083, | |
| "loss": 0.1594, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.48666798340904605, | |
| "grad_norm": 0.10546875, | |
| "learning_rate": 0.00018988599931931866, | |
| "loss": 0.1394, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.49298834682994275, | |
| "grad_norm": 0.111328125, | |
| "learning_rate": 0.0001895872260758688, | |
| "loss": 0.1448, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.49930871025083945, | |
| "grad_norm": 0.111328125, | |
| "learning_rate": 0.00018928434598833912, | |
| "loss": 0.156, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.5056290736717362, | |
| "grad_norm": 0.125, | |
| "learning_rate": 0.00018897737294131284, | |
| "loss": 0.1692, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5056290736717362, | |
| "eval_loss": 0.15801414847373962, | |
| "eval_runtime": 57.0109, | |
| "eval_samples_per_second": 18.698, | |
| "eval_steps_per_second": 18.698, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5119494370926329, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 0.00018866632100700197, | |
| "loss": 0.1318, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5182698005135296, | |
| "grad_norm": 0.1357421875, | |
| "learning_rate": 0.0001883512044446023, | |
| "loss": 0.203, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 0.126953125, | |
| "learning_rate": 0.00018803203769963967, | |
| "loss": 0.1968, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.530910527355323, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 0.0001877088354033077, | |
| "loss": 0.139, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5372308907762197, | |
| "grad_norm": 0.1044921875, | |
| "learning_rate": 0.0001873816123717973, | |
| "loss": 0.1301, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5435512541971164, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 0.0001870503836056172, | |
| "loss": 0.1253, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5498716176180131, | |
| "grad_norm": 0.11474609375, | |
| "learning_rate": 0.00018671516428890648, | |
| "loss": 0.1575, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5561919810389098, | |
| "grad_norm": 0.12353515625, | |
| "learning_rate": 0.00018637596978873835, | |
| "loss": 0.1627, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5625123444598065, | |
| "grad_norm": 0.1279296875, | |
| "learning_rate": 0.00018603281565441585, | |
| "loss": 0.1762, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.5688327078807032, | |
| "grad_norm": 0.1259765625, | |
| "learning_rate": 0.00018568571761675893, | |
| "loss": 0.1537, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5751530713015999, | |
| "grad_norm": 0.1259765625, | |
| "learning_rate": 0.00018533469158738344, | |
| "loss": 0.1752, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.5814734347224966, | |
| "grad_norm": 0.11865234375, | |
| "learning_rate": 0.0001849797536579715, | |
| "loss": 0.1441, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.5877937981433933, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 0.00018462092009953408, | |
| "loss": 0.1471, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.59411416156429, | |
| "grad_norm": 0.1201171875, | |
| "learning_rate": 0.0001842582073616649, | |
| "loss": 0.1584, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6004345249851867, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.00018389163207178656, | |
| "loss": 0.1255, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6067548884060834, | |
| "grad_norm": 0.10595703125, | |
| "learning_rate": 0.000183521211034388, | |
| "loss": 0.1401, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6067548884060834, | |
| "eval_loss": 0.1516103893518448, | |
| "eval_runtime": 57.9856, | |
| "eval_samples_per_second": 18.384, | |
| "eval_steps_per_second": 18.384, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6130752518269801, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.1359, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6193956152478768, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 0.00018276889981568906, | |
| "loss": 0.1354, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6257159786687735, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.00018238704412172586, | |
| "loss": 0.1315, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6320363420896702, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 0.0001820014116533359, | |
| "loss": 0.1522, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6383567055105669, | |
| "grad_norm": 0.11767578125, | |
| "learning_rate": 0.00018161202008862458, | |
| "loss": 0.1754, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.6446770689314636, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 0.00018121888727802113, | |
| "loss": 0.1368, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.6509974323523603, | |
| "grad_norm": 0.09814453125, | |
| "learning_rate": 0.00018082203124346045, | |
| "loss": 0.14, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.657317795773257, | |
| "grad_norm": 0.115234375, | |
| "learning_rate": 0.0001804214701775569, | |
| "loss": 0.157, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.6636381591941537, | |
| "grad_norm": 0.11376953125, | |
| "learning_rate": 0.00018001722244277035, | |
| "loss": 0.1575, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6699585226150504, | |
| "grad_norm": 0.09765625, | |
| "learning_rate": 0.00017960930657056438, | |
| "loss": 0.1229, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.6762788860359471, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 0.00017919774126055673, | |
| "loss": 0.1294, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.6825992494568438, | |
| "grad_norm": 0.09716796875, | |
| "learning_rate": 0.00017878254537966216, | |
| "loss": 0.1381, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6889196128777405, | |
| "grad_norm": 0.11083984375, | |
| "learning_rate": 0.0001783637379612275, | |
| "loss": 0.1494, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.6952399762986372, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 0.00017794133820415916, | |
| "loss": 0.1527, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7015603397195339, | |
| "grad_norm": 0.111328125, | |
| "learning_rate": 0.00017751536547204295, | |
| "loss": 0.1335, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7078807031404306, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 0.0001770858392922565, | |
| "loss": 0.1204, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7078807031404306, | |
| "eval_loss": 0.14627417922019958, | |
| "eval_runtime": 56.8973, | |
| "eval_samples_per_second": 18.736, | |
| "eval_steps_per_second": 18.736, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7142010665613273, | |
| "grad_norm": 0.09814453125, | |
| "learning_rate": 0.00017665277935507398, | |
| "loss": 0.122, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.720521429982224, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 0.00017621620551276366, | |
| "loss": 0.134, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.7268417934031207, | |
| "grad_norm": 0.09765625, | |
| "learning_rate": 0.00017577613777867762, | |
| "loss": 0.1185, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7331621568240174, | |
| "grad_norm": 0.1064453125, | |
| "learning_rate": 0.00017533259632633442, | |
| "loss": 0.1337, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.7394825202449141, | |
| "grad_norm": 0.130859375, | |
| "learning_rate": 0.00017488560148849427, | |
| "loss": 0.1503, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.7458028836658108, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 0.00017443517375622704, | |
| "loss": 0.1594, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.7521232470867075, | |
| "grad_norm": 0.1181640625, | |
| "learning_rate": 0.0001739813337779727, | |
| "loss": 0.1397, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.7584436105076042, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 0.00017352410235859503, | |
| "loss": 0.1314, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7647639739285009, | |
| "grad_norm": 0.115234375, | |
| "learning_rate": 0.0001730635004584276, | |
| "loss": 0.1466, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.7710843373493976, | |
| "grad_norm": 0.0986328125, | |
| "learning_rate": 0.0001725995491923131, | |
| "loss": 0.1147, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.7774047007702943, | |
| "grad_norm": 0.134765625, | |
| "learning_rate": 0.0001721322698286354, | |
| "loss": 0.1637, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.783725064191191, | |
| "grad_norm": 0.11279296875, | |
| "learning_rate": 0.00017166168378834448, | |
| "loss": 0.138, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.7900454276120877, | |
| "grad_norm": 0.11767578125, | |
| "learning_rate": 0.00017118781264397446, | |
| "loss": 0.1511, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7963657910329844, | |
| "grad_norm": 0.115234375, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.1407, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8026861544538811, | |
| "grad_norm": 0.1064453125, | |
| "learning_rate": 0.0001702303020851142, | |
| "loss": 0.1342, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.8090065178747778, | |
| "grad_norm": 0.11865234375, | |
| "learning_rate": 0.00016974670656467824, | |
| "loss": 0.1336, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8090065178747778, | |
| "eval_loss": 0.14203742146492004, | |
| "eval_runtime": 58.4188, | |
| "eval_samples_per_second": 18.248, | |
| "eval_steps_per_second": 18.248, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8153268812956745, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 0.0001692599137262597, | |
| "loss": 0.1543, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.8216472447165712, | |
| "grad_norm": 0.0888671875, | |
| "learning_rate": 0.00016876994588534234, | |
| "loss": 0.1116, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.827967608137468, | |
| "grad_norm": 0.1044921875, | |
| "learning_rate": 0.00016827682550295785, | |
| "loss": 0.1267, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.8342879715583646, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 0.0001677805751846563, | |
| "loss": 0.1361, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8406083349792614, | |
| "grad_norm": 0.11376953125, | |
| "learning_rate": 0.00016728121767946977, | |
| "loss": 0.1372, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.846928698400158, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 0.00016677877587886956, | |
| "loss": 0.1258, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.8532490618210548, | |
| "grad_norm": 0.11669921875, | |
| "learning_rate": 0.00016627327281571678, | |
| "loss": 0.1427, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8595694252419515, | |
| "grad_norm": 0.1328125, | |
| "learning_rate": 0.00016576473166320644, | |
| "loss": 0.187, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.8658897886628482, | |
| "grad_norm": 0.1044921875, | |
| "learning_rate": 0.00016525317573380525, | |
| "loss": 0.1417, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.8722101520837449, | |
| "grad_norm": 0.10107421875, | |
| "learning_rate": 0.00016473862847818277, | |
| "loss": 0.1399, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.8785305155046416, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 0.00016422111348413657, | |
| "loss": 0.141, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.8848508789255383, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.00016370065447551078, | |
| "loss": 0.1236, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.891171242346435, | |
| "grad_norm": 0.10205078125, | |
| "learning_rate": 0.0001631772753111086, | |
| "loss": 0.1236, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.8974916057673317, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 0.00016265099998359866, | |
| "loss": 0.128, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.9038119691882284, | |
| "grad_norm": 0.09814453125, | |
| "learning_rate": 0.00016212185261841499, | |
| "loss": 0.1227, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.9101323326091251, | |
| "grad_norm": 0.1064453125, | |
| "learning_rate": 0.00016158985747265108, | |
| "loss": 0.1339, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9101323326091251, | |
| "eval_loss": 0.1379576325416565, | |
| "eval_runtime": 61.2763, | |
| "eval_samples_per_second": 17.397, | |
| "eval_steps_per_second": 17.397, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9164526960300218, | |
| "grad_norm": 0.10009765625, | |
| "learning_rate": 0.00016105503893394806, | |
| "loss": 0.1255, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.9227730594509185, | |
| "grad_norm": 0.103515625, | |
| "learning_rate": 0.00016051742151937655, | |
| "loss": 0.1237, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.9290934228718152, | |
| "grad_norm": 0.10009765625, | |
| "learning_rate": 0.0001599770298743128, | |
| "loss": 0.1212, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.9354137862927119, | |
| "grad_norm": 0.1123046875, | |
| "learning_rate": 0.000159433888771309, | |
| "loss": 0.1402, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.9417341497136086, | |
| "grad_norm": 0.11865234375, | |
| "learning_rate": 0.00015888802310895742, | |
| "loss": 0.1475, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.9480545131345053, | |
| "grad_norm": 0.1064453125, | |
| "learning_rate": 0.00015833945791074943, | |
| "loss": 0.1133, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.954374876555402, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.00015778821832392777, | |
| "loss": 0.1336, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.9606952399762987, | |
| "grad_norm": 0.1162109375, | |
| "learning_rate": 0.0001572343296183344, | |
| "loss": 0.1479, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.9670156033971954, | |
| "grad_norm": 0.10546875, | |
| "learning_rate": 0.00015667781718525157, | |
| "loss": 0.1291, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.9733359668180921, | |
| "grad_norm": 0.11181640625, | |
| "learning_rate": 0.00015611870653623825, | |
| "loss": 0.1337, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.9796563302389888, | |
| "grad_norm": 0.09228515625, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.1024, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9859766936598855, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 0.0001549927932310155, | |
| "loss": 0.1565, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.9922970570807822, | |
| "grad_norm": 0.10595703125, | |
| "learning_rate": 0.0001544260421887537, | |
| "loss": 0.1328, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.9986174205016789, | |
| "grad_norm": 0.1142578125, | |
| "learning_rate": 0.00015385679615609042, | |
| "loss": 0.164, | |
| "step": 158 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 474, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 79, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7720565660267315e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |