| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.496543551254197, | |
| "eval_steps": 16, | |
| "global_step": 395, | |
| "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 | |
| }, | |
| { | |
| "epoch": 1.0049377839225755, | |
| "grad_norm": 0.09814453125, | |
| "learning_rate": 0.00015328508122831636, | |
| "loss": 0.1184, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 1.0112581473434723, | |
| "grad_norm": 0.08935546875, | |
| "learning_rate": 0.00015271092361390077, | |
| "loss": 0.101, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0112581473434723, | |
| "eval_loss": 0.13463501632213593, | |
| "eval_runtime": 57.8932, | |
| "eval_samples_per_second": 18.413, | |
| "eval_steps_per_second": 18.413, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.017578510764369, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.0001521343496332903, | |
| "loss": 0.118, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.0238988741852657, | |
| "grad_norm": 0.087890625, | |
| "learning_rate": 0.00015155538571770218, | |
| "loss": 0.0956, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.0302192376061623, | |
| "grad_norm": 0.09912109375, | |
| "learning_rate": 0.00015097405840791276, | |
| "loss": 0.1089, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.036539601027059, | |
| "grad_norm": 0.0927734375, | |
| "learning_rate": 0.00015039039435304078, | |
| "loss": 0.093, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.0428599644479557, | |
| "grad_norm": 0.126953125, | |
| "learning_rate": 0.00014980442030932558, | |
| "loss": 0.1443, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.0491803278688525, | |
| "grad_norm": 0.10009765625, | |
| "learning_rate": 0.00014921616313890072, | |
| "loss": 0.1039, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.055500691289749, | |
| "grad_norm": 0.09619140625, | |
| "learning_rate": 0.00014862564980856258, | |
| "loss": 0.0798, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.061821054710646, | |
| "grad_norm": 0.12060546875, | |
| "learning_rate": 0.00014803290738853395, | |
| "loss": 0.1199, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.0681414181315425, | |
| "grad_norm": 0.11572265625, | |
| "learning_rate": 0.00014743796305122331, | |
| "loss": 0.1028, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.0744617815524393, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 0.00014684084406997903, | |
| "loss": 0.097, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.080782144973336, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 0.00014624157781783926, | |
| "loss": 0.0943, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.0871025083942327, | |
| "grad_norm": 0.1123046875, | |
| "learning_rate": 0.0001456401917662769, | |
| "loss": 0.0981, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.0934228718151293, | |
| "grad_norm": 0.10595703125, | |
| "learning_rate": 0.00014503671348394057, | |
| "loss": 0.1008, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.0997432352360261, | |
| "grad_norm": 0.12060546875, | |
| "learning_rate": 0.00014443117063539038, | |
| "loss": 0.1239, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.1060635986569227, | |
| "grad_norm": 0.11474609375, | |
| "learning_rate": 0.00014382359097983013, | |
| "loss": 0.1035, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.1123839620778195, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 0.00014321400236983457, | |
| "loss": 0.0871, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.1123839620778195, | |
| "eval_loss": 0.13297832012176514, | |
| "eval_runtime": 57.7156, | |
| "eval_samples_per_second": 18.47, | |
| "eval_steps_per_second": 18.47, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.1187043254987161, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 0.00014260243275007265, | |
| "loss": 0.1073, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.125024688919613, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 0.00014198891015602646, | |
| "loss": 0.1054, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.1313450523405095, | |
| "grad_norm": 0.0947265625, | |
| "learning_rate": 0.00014137346271270604, | |
| "loss": 0.0977, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.1376654157614063, | |
| "grad_norm": 0.08837890625, | |
| "learning_rate": 0.0001407561186333601, | |
| "loss": 0.0839, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.143985779182303, | |
| "grad_norm": 0.11181640625, | |
| "learning_rate": 0.00014013690621818262, | |
| "loss": 0.1173, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.1503061426031997, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 0.00013951585385301555, | |
| "loss": 0.113, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.1566265060240963, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 0.0001388929900080476, | |
| "loss": 0.0938, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.1629468694449931, | |
| "grad_norm": 0.10205078125, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0953, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.1692672328658897, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 0.00013764194217336264, | |
| "loss": 0.0954, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.1755875962867866, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 0.00013701381553399145, | |
| "loss": 0.0971, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.1819079597076831, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 0.00013638399211288188, | |
| "loss": 0.0995, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.18822832312858, | |
| "grad_norm": 0.11328125, | |
| "learning_rate": 0.000135752500782304, | |
| "loss": 0.1199, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.1945486865494765, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 0.00013511937049098805, | |
| "loss": 0.0885, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.2008690499703734, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.00013448463026279704, | |
| "loss": 0.0957, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.20718941339127, | |
| "grad_norm": 0.08740234375, | |
| "learning_rate": 0.0001338483091953967, | |
| "loss": 0.0753, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.2135097768121668, | |
| "grad_norm": 0.12353515625, | |
| "learning_rate": 0.0001332104364589212, | |
| "loss": 0.1035, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.2135097768121668, | |
| "eval_loss": 0.13200590014457703, | |
| "eval_runtime": 58.9558, | |
| "eval_samples_per_second": 18.081, | |
| "eval_steps_per_second": 18.081, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.2198301402330634, | |
| "grad_norm": 0.115234375, | |
| "learning_rate": 0.00013257104129463614, | |
| "loss": 0.104, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.2261505036539602, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 0.000131930153013598, | |
| "loss": 0.0966, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.2324708670748568, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 0.00013128780099531056, | |
| "loss": 0.1062, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.2387912304957536, | |
| "grad_norm": 0.10888671875, | |
| "learning_rate": 0.00013064401468637792, | |
| "loss": 0.1027, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.2451115939166502, | |
| "grad_norm": 0.10546875, | |
| "learning_rate": 0.0001299988235991548, | |
| "loss": 0.0927, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.251431957337547, | |
| "grad_norm": 0.11865234375, | |
| "learning_rate": 0.00012935225731039348, | |
| "loss": 0.1031, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.2577523207584436, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.00012870434545988812, | |
| "loss": 0.109, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.2640726841793404, | |
| "grad_norm": 0.0888671875, | |
| "learning_rate": 0.00012805511774911584, | |
| "loss": 0.0835, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.270393047600237, | |
| "grad_norm": 0.09228515625, | |
| "learning_rate": 0.00012740460393987526, | |
| "loss": 0.0902, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.2767134110211338, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.00012675283385292212, | |
| "loss": 0.114, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.2830337744420304, | |
| "grad_norm": 0.095703125, | |
| "learning_rate": 0.0001260998373666022, | |
| "loss": 0.0887, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.2893541378629272, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 0.00012544564441548182, | |
| "loss": 0.095, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.2956745012838238, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 0.00012479028498897535, | |
| "loss": 0.0883, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.3019948647047206, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 0.00012413378912997058, | |
| "loss": 0.0824, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.3083152281256172, | |
| "grad_norm": 0.091796875, | |
| "learning_rate": 0.0001234761869334515, | |
| "loss": 0.0736, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.314635591546514, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 0.0001228175085451186, | |
| "loss": 0.1025, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.314635591546514, | |
| "eval_loss": 0.13002794981002808, | |
| "eval_runtime": 57.2937, | |
| "eval_samples_per_second": 18.606, | |
| "eval_steps_per_second": 18.606, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.3209559549674106, | |
| "grad_norm": 0.1220703125, | |
| "learning_rate": 0.00012215778416000707, | |
| "loss": 0.1188, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.3272763183883074, | |
| "grad_norm": 0.1123046875, | |
| "learning_rate": 0.00012149704402110243, | |
| "loss": 0.101, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.333596681809204, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 0.00012083531841795425, | |
| "loss": 0.1031, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.3399170452301008, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 0.00012017263768528775, | |
| "loss": 0.0974, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.3462374086509974, | |
| "grad_norm": 0.11181640625, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.1009, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.3525577720718942, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 0.00011884453238783185, | |
| "loss": 0.1017, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.3588781354927908, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.00011817916870584482, | |
| "loss": 0.095, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.3651984989136876, | |
| "grad_norm": 0.103515625, | |
| "learning_rate": 0.00011751297165715309, | |
| "loss": 0.1064, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.3715188623345842, | |
| "grad_norm": 0.11181640625, | |
| "learning_rate": 0.00011684597178146115, | |
| "loss": 0.106, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.377839225755481, | |
| "grad_norm": 0.1015625, | |
| "learning_rate": 0.0001161781996552765, | |
| "loss": 0.0836, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.3841595891763776, | |
| "grad_norm": 0.10107421875, | |
| "learning_rate": 0.00011550968589050799, | |
| "loss": 0.0933, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.3904799525972744, | |
| "grad_norm": 0.09619140625, | |
| "learning_rate": 0.00011484046113306262, | |
| "loss": 0.0874, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.396800316018171, | |
| "grad_norm": 0.11669921875, | |
| "learning_rate": 0.0001141705560614406, | |
| "loss": 0.1175, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 1.4031206794390678, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 0.00011350000138532902, | |
| "loss": 0.1018, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.4094410428599644, | |
| "grad_norm": 0.11865234375, | |
| "learning_rate": 0.00011282882784419398, | |
| "loss": 0.1207, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.4157614062808612, | |
| "grad_norm": 0.103515625, | |
| "learning_rate": 0.00011215706620587149, | |
| "loss": 0.0936, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.4157614062808612, | |
| "eval_loss": 0.12633191049098969, | |
| "eval_runtime": 57.953, | |
| "eval_samples_per_second": 18.394, | |
| "eval_steps_per_second": 18.394, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.4220817697017578, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.00011148474726515716, | |
| "loss": 0.0982, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.4284021331226546, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 0.00011081190184239419, | |
| "loss": 0.0912, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 1.4347224965435512, | |
| "grad_norm": 0.11083984375, | |
| "learning_rate": 0.0001101385607820608, | |
| "loss": 0.1165, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.441042859964448, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 0.0001094647549513561, | |
| "loss": 0.0996, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.4473632233853446, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 0.00010879051523878522, | |
| "loss": 0.0946, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 1.4536835868062414, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 0.00010811587255274313, | |
| "loss": 0.1126, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.460003950227138, | |
| "grad_norm": 0.09765625, | |
| "learning_rate": 0.00010744085782009792, | |
| "loss": 0.0875, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.4663243136480348, | |
| "grad_norm": 0.109375, | |
| "learning_rate": 0.00010676550198477293, | |
| "loss": 0.0989, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.4726446770689314, | |
| "grad_norm": 0.11376953125, | |
| "learning_rate": 0.00010608983600632831, | |
| "loss": 0.1057, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 1.4789650404898282, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 0.00010541389085854176, | |
| "loss": 0.0906, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.4852854039107248, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 0.00010473769752798859, | |
| "loss": 0.0872, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.4916057673316216, | |
| "grad_norm": 0.109375, | |
| "learning_rate": 0.00010406128701262128, | |
| "loss": 0.1047, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 1.4979261307525182, | |
| "grad_norm": 0.11083984375, | |
| "learning_rate": 0.00010338469032034845, | |
| "loss": 0.0926, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 1.5042464941734148, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 0.00010270793846761347, | |
| "loss": 0.0905, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.5105668575943116, | |
| "grad_norm": 0.11279296875, | |
| "learning_rate": 0.00010203106247797243, | |
| "loss": 0.0996, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 1.5168872210152085, | |
| "grad_norm": 0.09326171875, | |
| "learning_rate": 0.00010135409338067219, | |
| "loss": 0.0797, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.5168872210152085, | |
| "eval_loss": 0.1241099089384079, | |
| "eval_runtime": 60.1424, | |
| "eval_samples_per_second": 17.725, | |
| "eval_steps_per_second": 17.725, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.523207584436105, | |
| "grad_norm": 0.11083984375, | |
| "learning_rate": 0.00010067706220922785, | |
| "loss": 0.0839, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 1.5295279478570016, | |
| "grad_norm": 0.123046875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0984, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.5358483112778984, | |
| "grad_norm": 0.1015625, | |
| "learning_rate": 9.932293779077216e-05, | |
| "loss": 0.0893, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.5421686746987953, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 9.864590661932783e-05, | |
| "loss": 0.0972, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.5484890381196919, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 9.796893752202758e-05, | |
| "loss": 0.0886, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.5548094015405884, | |
| "grad_norm": 0.1044921875, | |
| "learning_rate": 9.729206153238657e-05, | |
| "loss": 0.0971, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.5611297649614853, | |
| "grad_norm": 0.11083984375, | |
| "learning_rate": 9.661530967965156e-05, | |
| "loss": 0.108, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.567450128382382, | |
| "grad_norm": 0.09521484375, | |
| "learning_rate": 9.59387129873787e-05, | |
| "loss": 0.0826, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 1.5737704918032787, | |
| "grad_norm": 0.09326171875, | |
| "learning_rate": 9.526230247201142e-05, | |
| "loss": 0.0875, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 1.5800908552241753, | |
| "grad_norm": 0.078125, | |
| "learning_rate": 9.458610914145826e-05, | |
| "loss": 0.0742, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.586411218645072, | |
| "grad_norm": 0.1064453125, | |
| "learning_rate": 9.391016399367172e-05, | |
| "loss": 0.0981, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.5927315820659689, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 9.323449801522709e-05, | |
| "loss": 0.1035, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.5990519454868655, | |
| "grad_norm": 0.119140625, | |
| "learning_rate": 9.255914217990211e-05, | |
| "loss": 0.111, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 1.605372308907762, | |
| "grad_norm": 0.10205078125, | |
| "learning_rate": 9.18841274472569e-05, | |
| "loss": 0.0855, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.6116926723286589, | |
| "grad_norm": 0.09423828125, | |
| "learning_rate": 9.120948476121479e-05, | |
| "loss": 0.0889, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.6180130357495557, | |
| "grad_norm": 0.11328125, | |
| "learning_rate": 9.05352450486439e-05, | |
| "loss": 0.1014, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.6180130357495557, | |
| "eval_loss": 0.12204406410455704, | |
| "eval_runtime": 58.4358, | |
| "eval_samples_per_second": 18.242, | |
| "eval_steps_per_second": 18.242, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.6243333991704523, | |
| "grad_norm": 0.10205078125, | |
| "learning_rate": 8.986143921793923e-05, | |
| "loss": 0.0858, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 1.6306537625913489, | |
| "grad_norm": 0.11474609375, | |
| "learning_rate": 8.918809815760585e-05, | |
| "loss": 0.1131, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 1.6369741260122457, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 8.851525273484286e-05, | |
| "loss": 0.1018, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.6432944894331425, | |
| "grad_norm": 0.126953125, | |
| "learning_rate": 8.78429337941285e-05, | |
| "loss": 0.1183, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.649614852854039, | |
| "grad_norm": 0.123046875, | |
| "learning_rate": 8.717117215580606e-05, | |
| "loss": 0.1097, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.6559352162749357, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 8.649999861467099e-05, | |
| "loss": 0.095, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 1.6622555796958325, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 8.582944393855941e-05, | |
| "loss": 0.0839, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 1.6685759431167293, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 8.515953886693739e-05, | |
| "loss": 0.0958, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.674896306537626, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 8.449031410949206e-05, | |
| "loss": 0.0951, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.6812166699585225, | |
| "grad_norm": 0.103515625, | |
| "learning_rate": 8.382180034472353e-05, | |
| "loss": 0.0948, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 1.6875370333794193, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 8.315402821853886e-05, | |
| "loss": 0.0828, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 1.693857396800316, | |
| "grad_norm": 0.10546875, | |
| "learning_rate": 8.248702834284693e-05, | |
| "loss": 0.0984, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.7001777602212127, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 8.18208312941552e-05, | |
| "loss": 0.0949, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 1.7064981236421093, | |
| "grad_norm": 0.1240234375, | |
| "learning_rate": 8.115546761216822e-05, | |
| "loss": 0.1149, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.712818487063006, | |
| "grad_norm": 0.11474609375, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.1048, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 1.719138850483903, | |
| "grad_norm": 0.109375, | |
| "learning_rate": 7.982736231471224e-05, | |
| "loss": 0.0984, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 1.719138850483903, | |
| "eval_loss": 0.11962020397186279, | |
| "eval_runtime": 57.5297, | |
| "eval_samples_per_second": 18.53, | |
| "eval_steps_per_second": 18.53, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 1.7254592139047995, | |
| "grad_norm": 0.10546875, | |
| "learning_rate": 7.916468158204576e-05, | |
| "loss": 0.0984, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.731779577325696, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 7.85029559788976e-05, | |
| "loss": 0.1061, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 1.738099940746593, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 7.784221583999298e-05, | |
| "loss": 0.087, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.7444203041674897, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 7.718249145488142e-05, | |
| "loss": 0.0869, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 1.7507406675883863, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 7.652381306654851e-05, | |
| "loss": 0.112, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 1.757061031009283, | |
| "grad_norm": 0.0849609375, | |
| "learning_rate": 7.586621087002945e-05, | |
| "loss": 0.0796, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 1.7633813944301797, | |
| "grad_norm": 0.09375, | |
| "learning_rate": 7.520971501102469e-05, | |
| "loss": 0.0835, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 1.7697017578510765, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 7.455435558451823e-05, | |
| "loss": 0.1032, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.7760221212719731, | |
| "grad_norm": 0.1064453125, | |
| "learning_rate": 7.390016263339782e-05, | |
| "loss": 0.0877, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 1.7823424846928697, | |
| "grad_norm": 0.0986328125, | |
| "learning_rate": 7.324716614707793e-05, | |
| "loss": 0.086, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 1.7886628481137665, | |
| "grad_norm": 0.09619140625, | |
| "learning_rate": 7.259539606012478e-05, | |
| "loss": 0.0813, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 1.7949832115346633, | |
| "grad_norm": 0.10595703125, | |
| "learning_rate": 7.194488225088417e-05, | |
| "loss": 0.0899, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 1.80130357495556, | |
| "grad_norm": 0.1171875, | |
| "learning_rate": 7.129565454011189e-05, | |
| "loss": 0.1086, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.8076239383764565, | |
| "grad_norm": 0.1142578125, | |
| "learning_rate": 7.064774268960653e-05, | |
| "loss": 0.1115, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 1.8139443017973533, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 7.000117640084526e-05, | |
| "loss": 0.0908, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.8202646652182501, | |
| "grad_norm": 0.11181640625, | |
| "learning_rate": 6.93559853136221e-05, | |
| "loss": 0.1078, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.8202646652182501, | |
| "eval_loss": 0.11839400231838226, | |
| "eval_runtime": 58.7653, | |
| "eval_samples_per_second": 18.14, | |
| "eval_steps_per_second": 18.14, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.8265850286391467, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 6.871219900468947e-05, | |
| "loss": 0.0937, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 1.8329053920600433, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 6.806984698640202e-05, | |
| "loss": 0.0832, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.8392257554809401, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 6.742895870536388e-05, | |
| "loss": 0.0926, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 1.845546118901837, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 6.678956354107882e-05, | |
| "loss": 0.0926, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 1.8518664823227335, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 6.615169080460331e-05, | |
| "loss": 0.0896, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 1.8581868457436301, | |
| "grad_norm": 0.109375, | |
| "learning_rate": 6.551536973720298e-05, | |
| "loss": 0.0857, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.864507209164527, | |
| "grad_norm": 0.09765625, | |
| "learning_rate": 6.488062950901198e-05, | |
| "loss": 0.0735, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.8708275725854238, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 6.4247499217696e-05, | |
| "loss": 0.0998, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 1.8771479360063204, | |
| "grad_norm": 0.10205078125, | |
| "learning_rate": 6.361600788711816e-05, | |
| "loss": 0.0926, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 1.883468299427217, | |
| "grad_norm": 0.10595703125, | |
| "learning_rate": 6.298618446600856e-05, | |
| "loss": 0.0913, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 1.8897886628481138, | |
| "grad_norm": 0.09033203125, | |
| "learning_rate": 6.23580578266374e-05, | |
| "loss": 0.0759, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 1.8961090262690106, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0897, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.9024293896899072, | |
| "grad_norm": 0.10546875, | |
| "learning_rate": 6.11070099919524e-05, | |
| "loss": 0.0881, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 1.9087497531108037, | |
| "grad_norm": 0.1181640625, | |
| "learning_rate": 6.048414614698448e-05, | |
| "loss": 0.1177, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 1.9150701165317006, | |
| "grad_norm": 0.1171875, | |
| "learning_rate": 5.9863093781817394e-05, | |
| "loss": 0.1063, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 1.9213904799525974, | |
| "grad_norm": 0.09912109375, | |
| "learning_rate": 5.924388136663992e-05, | |
| "loss": 0.0803, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 1.9213904799525974, | |
| "eval_loss": 0.1170881986618042, | |
| "eval_runtime": 57.9811, | |
| "eval_samples_per_second": 18.385, | |
| "eval_steps_per_second": 18.385, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 1.927710843373494, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 5.862653728729397e-05, | |
| "loss": 0.0821, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.9340312067943906, | |
| "grad_norm": 0.09716796875, | |
| "learning_rate": 5.801108984397354e-05, | |
| "loss": 0.0752, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 1.9403515702152874, | |
| "grad_norm": 0.0947265625, | |
| "learning_rate": 5.739756724992736e-05, | |
| "loss": 0.0751, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 1.9466719336361842, | |
| "grad_norm": 0.10302734375, | |
| "learning_rate": 5.6785997630165435e-05, | |
| "loss": 0.1088, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 1.9529922970570808, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 5.61764090201699e-05, | |
| "loss": 0.0907, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 1.9593126604779774, | |
| "grad_norm": 0.12158203125, | |
| "learning_rate": 5.5568829364609664e-05, | |
| "loss": 0.0985, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.9656330238988742, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 5.4963286516059496e-05, | |
| "loss": 0.0851, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 1.971953387319771, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 5.435980823372311e-05, | |
| "loss": 0.0865, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.9782737507406676, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 5.375842218216076e-05, | |
| "loss": 0.0911, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 1.9845941141615642, | |
| "grad_norm": 0.1025390625, | |
| "learning_rate": 5.3159155930021e-05, | |
| "loss": 0.0886, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 1.990914477582461, | |
| "grad_norm": 0.10107421875, | |
| "learning_rate": 5.25620369487767e-05, | |
| "loss": 0.0853, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.9972348410033578, | |
| "grad_norm": 0.09423828125, | |
| "learning_rate": 5.196709261146606e-05, | |
| "loss": 0.0692, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 2.0035552044242544, | |
| "grad_norm": 0.087890625, | |
| "learning_rate": 5.1374350191437446e-05, | |
| "loss": 0.0688, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 2.009875567845151, | |
| "grad_norm": 0.08251953125, | |
| "learning_rate": 5.078383686109926e-05, | |
| "loss": 0.0725, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 2.016195931266048, | |
| "grad_norm": 0.08447265625, | |
| "learning_rate": 5.0195579690674447e-05, | |
| "loss": 0.0642, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 2.0225162946869446, | |
| "grad_norm": 0.0869140625, | |
| "learning_rate": 4.9609605646959226e-05, | |
| "loss": 0.0658, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.0225162946869446, | |
| "eval_loss": 0.1164059117436409, | |
| "eval_runtime": 59.182, | |
| "eval_samples_per_second": 18.012, | |
| "eval_steps_per_second": 18.012, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.028836658107841, | |
| "grad_norm": 0.0751953125, | |
| "learning_rate": 4.902594159208723e-05, | |
| "loss": 0.0557, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 2.035157021528738, | |
| "grad_norm": 0.083984375, | |
| "learning_rate": 4.844461428229782e-05, | |
| "loss": 0.0746, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 2.041477384949635, | |
| "grad_norm": 0.08447265625, | |
| "learning_rate": 4.786565036670972e-05, | |
| "loss": 0.0609, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 2.0477977483705314, | |
| "grad_norm": 0.08837890625, | |
| "learning_rate": 4.728907638609925e-05, | |
| "loss": 0.0649, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 2.054118111791428, | |
| "grad_norm": 0.0888671875, | |
| "learning_rate": 4.6714918771683646e-05, | |
| "loss": 0.0517, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.0604384752123246, | |
| "grad_norm": 0.09326171875, | |
| "learning_rate": 4.614320384390959e-05, | |
| "loss": 0.0733, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 2.0667588386332216, | |
| "grad_norm": 0.0947265625, | |
| "learning_rate": 4.557395781124632e-05, | |
| "loss": 0.0671, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 2.073079202054118, | |
| "grad_norm": 0.0908203125, | |
| "learning_rate": 4.500720676898452e-05, | |
| "loss": 0.0593, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 2.079399565475015, | |
| "grad_norm": 0.09765625, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.0666, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 2.0857199288959114, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 4.388129346376178e-05, | |
| "loss": 0.0788, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.092040292316808, | |
| "grad_norm": 0.0869140625, | |
| "learning_rate": 4.3322182814748436e-05, | |
| "loss": 0.0504, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 2.098360655737705, | |
| "grad_norm": 0.08837890625, | |
| "learning_rate": 4.276567038166563e-05, | |
| "loss": 0.0472, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 2.1046810191586016, | |
| "grad_norm": 0.10205078125, | |
| "learning_rate": 4.221178167607226e-05, | |
| "loss": 0.0598, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.111001382579498, | |
| "grad_norm": 0.087890625, | |
| "learning_rate": 4.16605420892506e-05, | |
| "loss": 0.0528, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 2.1173217460003952, | |
| "grad_norm": 0.10595703125, | |
| "learning_rate": 4.111197689104258e-05, | |
| "loss": 0.0621, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.123642109421292, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 4.0566111228691064e-05, | |
| "loss": 0.0517, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 2.123642109421292, | |
| "eval_loss": 0.12141799181699753, | |
| "eval_runtime": 58.3864, | |
| "eval_samples_per_second": 18.258, | |
| "eval_steps_per_second": 18.258, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 2.1299624728421884, | |
| "grad_norm": 0.10205078125, | |
| "learning_rate": 4.002297012568722e-05, | |
| "loss": 0.0682, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 2.136282836263085, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 3.948257848062351e-05, | |
| "loss": 0.0599, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 2.1426031996839816, | |
| "grad_norm": 0.09326171875, | |
| "learning_rate": 3.894496106605197e-05, | |
| "loss": 0.0565, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 2.1489235631048786, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 3.841014252734896e-05, | |
| "loss": 0.0807, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.1552439265257752, | |
| "grad_norm": 0.09375, | |
| "learning_rate": 3.787814738158504e-05, | |
| "loss": 0.0604, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 2.161564289946672, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 3.734900001640135e-05, | |
| "loss": 0.0576, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 2.167884653367569, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 3.6822724688891416e-05, | |
| "loss": 0.0784, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 2.1742050167884654, | |
| "grad_norm": 0.1103515625, | |
| "learning_rate": 3.629934552448925e-05, | |
| "loss": 0.0648, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 2.180525380209362, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 3.5778886515863474e-05, | |
| "loss": 0.0664, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.1868457436302586, | |
| "grad_norm": 0.10498046875, | |
| "learning_rate": 3.5261371521817244e-05, | |
| "loss": 0.0655, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 2.1931661070511552, | |
| "grad_norm": 0.10400390625, | |
| "learning_rate": 3.4746824266194744e-05, | |
| "loss": 0.0628, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 2.1994864704720523, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 3.423526833679355e-05, | |
| "loss": 0.064, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 2.205806833892949, | |
| "grad_norm": 0.111328125, | |
| "learning_rate": 3.3726727184283236e-05, | |
| "loss": 0.0692, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 2.2121271973138454, | |
| "grad_norm": 0.09619140625, | |
| "learning_rate": 3.322122412113047e-05, | |
| "loss": 0.0604, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.2184475607347425, | |
| "grad_norm": 0.1064453125, | |
| "learning_rate": 3.271878232053025e-05, | |
| "loss": 0.0802, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 2.224767924155639, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 3.2219424815343735e-05, | |
| "loss": 0.0598, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 2.224767924155639, | |
| "eval_loss": 0.12026113271713257, | |
| "eval_runtime": 59.3025, | |
| "eval_samples_per_second": 17.976, | |
| "eval_steps_per_second": 17.976, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 2.2310882875765357, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 3.172317449704216e-05, | |
| "loss": 0.0664, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 2.2374086509974322, | |
| "grad_norm": 0.09619140625, | |
| "learning_rate": 3.123005411465766e-05, | |
| "loss": 0.0519, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 2.243729014418329, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 3.0740086273740295e-05, | |
| "loss": 0.0685, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.250049377839226, | |
| "grad_norm": 0.09912109375, | |
| "learning_rate": 3.0253293435321793e-05, | |
| "loss": 0.0597, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 2.2563697412601225, | |
| "grad_norm": 0.107421875, | |
| "learning_rate": 2.9769697914885862e-05, | |
| "loss": 0.0543, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 2.262690104681019, | |
| "grad_norm": 0.1123046875, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0827, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 2.269010468101916, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 2.881218735602553e-05, | |
| "loss": 0.0663, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 2.2753308315228127, | |
| "grad_norm": 0.109375, | |
| "learning_rate": 2.8338316211655536e-05, | |
| "loss": 0.0665, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.2816511949437093, | |
| "grad_norm": 0.10205078125, | |
| "learning_rate": 2.7867730171364624e-05, | |
| "loss": 0.0671, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 2.287971558364606, | |
| "grad_norm": 0.1015625, | |
| "learning_rate": 2.7400450807686938e-05, | |
| "loss": 0.0564, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 2.2942919217855025, | |
| "grad_norm": 0.09814453125, | |
| "learning_rate": 2.6936499541572445e-05, | |
| "loss": 0.058, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 2.3006122852063995, | |
| "grad_norm": 0.09814453125, | |
| "learning_rate": 2.647589764140499e-05, | |
| "loss": 0.0643, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 2.306932648627296, | |
| "grad_norm": 0.1044921875, | |
| "learning_rate": 2.60186662220273e-05, | |
| "loss": 0.0642, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.3132530120481927, | |
| "grad_norm": 0.09765625, | |
| "learning_rate": 2.5564826243772966e-05, | |
| "loss": 0.0612, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 2.3195733754690897, | |
| "grad_norm": 0.10791015625, | |
| "learning_rate": 2.5114398511505734e-05, | |
| "loss": 0.0729, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 2.3258937388899863, | |
| "grad_norm": 0.10546875, | |
| "learning_rate": 2.4667403673665623e-05, | |
| "loss": 0.0704, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 2.3258937388899863, | |
| "eval_loss": 0.11980412155389786, | |
| "eval_runtime": 58.0487, | |
| "eval_samples_per_second": 18.364, | |
| "eval_steps_per_second": 18.364, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 2.332214102310883, | |
| "grad_norm": 0.09326171875, | |
| "learning_rate": 2.4223862221322424e-05, | |
| "loss": 0.0616, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 2.3385344657317795, | |
| "grad_norm": 0.111328125, | |
| "learning_rate": 2.3783794487236365e-05, | |
| "loss": 0.0584, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.344854829152676, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 2.3347220644926028e-05, | |
| "loss": 0.0618, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 2.351175192573573, | |
| "grad_norm": 0.10986328125, | |
| "learning_rate": 2.2914160707743538e-05, | |
| "loss": 0.0775, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 2.3574955559944697, | |
| "grad_norm": 0.09375, | |
| "learning_rate": 2.248463452795705e-05, | |
| "loss": 0.0481, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 2.3638159194153663, | |
| "grad_norm": 0.11376953125, | |
| "learning_rate": 2.205866179584084e-05, | |
| "loss": 0.0654, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 2.3701362828362633, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 2.1636262038772504e-05, | |
| "loss": 0.0733, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.37645664625716, | |
| "grad_norm": 0.103515625, | |
| "learning_rate": 2.121745462033784e-05, | |
| "loss": 0.0737, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 2.3827770096780565, | |
| "grad_norm": 0.10888671875, | |
| "learning_rate": 2.080225873944328e-05, | |
| "loss": 0.0506, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 2.389097373098953, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 2.0390693429435627e-05, | |
| "loss": 0.0737, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.3954177365198497, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 1.998277755722965e-05, | |
| "loss": 0.0542, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 2.4017380999407467, | |
| "grad_norm": 0.0966796875, | |
| "learning_rate": 1.957852982244309e-05, | |
| "loss": 0.0603, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.4080584633616433, | |
| "grad_norm": 0.10546875, | |
| "learning_rate": 1.9177968756539567e-05, | |
| "loss": 0.0624, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 2.41437882678254, | |
| "grad_norm": 0.13671875, | |
| "learning_rate": 1.87811127219789e-05, | |
| "loss": 0.0809, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 2.420699190203437, | |
| "grad_norm": 0.10693359375, | |
| "learning_rate": 1.838797991137543e-05, | |
| "loss": 0.068, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 2.4270195536243335, | |
| "grad_norm": 0.109375, | |
| "learning_rate": 1.7998588346664115e-05, | |
| "loss": 0.0787, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 2.4270195536243335, | |
| "eval_loss": 0.11915146559476852, | |
| "eval_runtime": 58.9409, | |
| "eval_samples_per_second": 18.086, | |
| "eval_steps_per_second": 18.086, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 2.43333991704523, | |
| "grad_norm": 0.109375, | |
| "learning_rate": 1.761295587827416e-05, | |
| "loss": 0.064, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.4396602804661267, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 1.7231100184310956e-05, | |
| "loss": 0.067, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 2.4459806438870233, | |
| "grad_norm": 0.09814453125, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.0582, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 2.4523010073079203, | |
| "grad_norm": 0.099609375, | |
| "learning_rate": 1.6478788965611993e-05, | |
| "loss": 0.0672, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 2.458621370728817, | |
| "grad_norm": 0.0986328125, | |
| "learning_rate": 1.6108367928213476e-05, | |
| "loss": 0.0514, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 2.4649417341497135, | |
| "grad_norm": 0.09375, | |
| "learning_rate": 1.5741792638335095e-05, | |
| "loss": 0.0551, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.4712620975706105, | |
| "grad_norm": 0.09619140625, | |
| "learning_rate": 1.5379079900465953e-05, | |
| "loss": 0.0482, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 2.477582460991507, | |
| "grad_norm": 0.1083984375, | |
| "learning_rate": 1.502024634202851e-05, | |
| "loss": 0.0622, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 2.4839028244124037, | |
| "grad_norm": 0.0947265625, | |
| "learning_rate": 1.4665308412616596e-05, | |
| "loss": 0.0605, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 2.4902231878333003, | |
| "grad_norm": 0.1005859375, | |
| "learning_rate": 1.4314282383241096e-05, | |
| "loss": 0.0622, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 2.496543551254197, | |
| "grad_norm": 0.10107421875, | |
| "learning_rate": 1.3967184345584173e-05, | |
| "loss": 0.0605, | |
| "step": 395 | |
| } | |
| ], | |
| "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": 6.92788670068949e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |