| { | |
| "best_metric": 1.3453013896942139, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.3032600454890068, | |
| "eval_steps": 25, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003032600454890068, | |
| "grad_norm": 0.5732214450836182, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 1.2366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003032600454890068, | |
| "eval_loss": 2.233814001083374, | |
| "eval_runtime": 2.1263, | |
| "eval_samples_per_second": 23.515, | |
| "eval_steps_per_second": 3.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006065200909780136, | |
| "grad_norm": 0.5826615691184998, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 1.2069, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009097801364670205, | |
| "grad_norm": 0.8060511946678162, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.4296, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012130401819560273, | |
| "grad_norm": 0.7838976979255676, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.8031, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015163002274450341, | |
| "grad_norm": 0.9152936935424805, | |
| "learning_rate": 0.00015, | |
| "loss": 2.8825, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01819560272934041, | |
| "grad_norm": 0.9083536863327026, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.8714, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02122820318423048, | |
| "grad_norm": 0.7592295408248901, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.6227, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.024260803639120546, | |
| "grad_norm": 0.8848680257797241, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.3879, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.027293404094010616, | |
| "grad_norm": 1.1162092685699463, | |
| "learning_rate": 0.00027, | |
| "loss": 1.9078, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.030326004548900682, | |
| "grad_norm": 1.1469495296478271, | |
| "learning_rate": 0.0003, | |
| "loss": 2.3304, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03335860500379075, | |
| "grad_norm": 1.7421014308929443, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 2.6528, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03639120545868082, | |
| "grad_norm": 2.160493850708008, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 1.7365, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.039423805913570885, | |
| "grad_norm": 1.6525168418884277, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 1.3977, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04245640636846096, | |
| "grad_norm": 1.732264757156372, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.9095, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.045489006823351025, | |
| "grad_norm": 1.9203606843948364, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.8081, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04852160727824109, | |
| "grad_norm": 1.9768295288085938, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.5633, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05155420773313116, | |
| "grad_norm": 1.7694615125656128, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.8582, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05458680818802123, | |
| "grad_norm": 5.227871417999268, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 2.0478, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0576194086429113, | |
| "grad_norm": 5.613846302032471, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 2.628, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.060652009097801364, | |
| "grad_norm": 3.1168196201324463, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 2.2502, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06368460955269144, | |
| "grad_norm": 2.028256893157959, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 1.9875, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0667172100075815, | |
| "grad_norm": 2.2501745223999023, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 1.3561, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06974981046247157, | |
| "grad_norm": 2.091094970703125, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 1.4375, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07278241091736164, | |
| "grad_norm": 1.8560627698898315, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.8881, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0758150113722517, | |
| "grad_norm": 1.5652915239334106, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 1.1072, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0758150113722517, | |
| "eval_loss": 1.6969295740127563, | |
| "eval_runtime": 1.6362, | |
| "eval_samples_per_second": 30.559, | |
| "eval_steps_per_second": 4.278, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07884761182714177, | |
| "grad_norm": 2.593773126602173, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 2.3669, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08188021228203184, | |
| "grad_norm": 3.031888961791992, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 2.1705, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08491281273692192, | |
| "grad_norm": 5.483036994934082, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 2.0639, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08794541319181198, | |
| "grad_norm": 2.578169584274292, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 2.2763, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09097801364670205, | |
| "grad_norm": 2.708948850631714, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 2.6701, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09401061410159212, | |
| "grad_norm": 2.3376152515411377, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 2.552, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09704321455648218, | |
| "grad_norm": 4.5717453956604, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 2.5146, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10007581501137225, | |
| "grad_norm": 3.326918601989746, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 2.7361, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10310841546626232, | |
| "grad_norm": 3.0180697441101074, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 2.1276, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10614101592115238, | |
| "grad_norm": 3.3345470428466797, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 3.5262, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10917361637604246, | |
| "grad_norm": 4.028136730194092, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 1.3238, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11220621683093253, | |
| "grad_norm": 2.7964673042297363, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 1.9645, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1152388172858226, | |
| "grad_norm": 2.7283153533935547, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 1.6322, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11827141774071266, | |
| "grad_norm": 3.139758586883545, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 1.3747, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12130401819560273, | |
| "grad_norm": 3.401658535003662, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 1.0433, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1243366186504928, | |
| "grad_norm": 3.2721481323242188, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.9206, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12736921910538287, | |
| "grad_norm": 2.2043514251708984, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.6399, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13040181956027294, | |
| "grad_norm": 2.3156049251556396, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.8682, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.133434420015163, | |
| "grad_norm": 4.419061660766602, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.5265, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.13646702047005307, | |
| "grad_norm": 2.9401931762695312, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.4974, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13949962092494314, | |
| "grad_norm": 2.4342000484466553, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.4075, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1425322213798332, | |
| "grad_norm": 1.5229568481445312, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.2443, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.14556482183472327, | |
| "grad_norm": 0.7514405846595764, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.032, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14859742228961334, | |
| "grad_norm": 3.046010732650757, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.6208, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1516300227445034, | |
| "grad_norm": 3.323383331298828, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.4257, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1516300227445034, | |
| "eval_loss": 2.1368014812469482, | |
| "eval_runtime": 1.6375, | |
| "eval_samples_per_second": 30.534, | |
| "eval_steps_per_second": 4.275, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15466262319939347, | |
| "grad_norm": 4.283215522766113, | |
| "learning_rate": 0.0002668315918143169, | |
| "loss": 1.3323, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.15769522365428354, | |
| "grad_norm": 3.335487127304077, | |
| "learning_rate": 0.00026526016662852886, | |
| "loss": 1.1937, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1607278241091736, | |
| "grad_norm": 2.471447706222534, | |
| "learning_rate": 0.00026365723046405023, | |
| "loss": 0.9932, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.16376042456406367, | |
| "grad_norm": 1.7774912118911743, | |
| "learning_rate": 0.0002620232215476231, | |
| "loss": 0.7889, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.16679302501895377, | |
| "grad_norm": 3.3943495750427246, | |
| "learning_rate": 0.0002603585866009697, | |
| "loss": 2.2703, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.16982562547384383, | |
| "grad_norm": 2.009979724884033, | |
| "learning_rate": 0.00025866378071866334, | |
| "loss": 2.3109, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1728582259287339, | |
| "grad_norm": 2.5208301544189453, | |
| "learning_rate": 0.00025693926724370956, | |
| "loss": 2.1646, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.17589082638362397, | |
| "grad_norm": 1.7100300788879395, | |
| "learning_rate": 0.00025518551764087326, | |
| "loss": 1.8255, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.17892342683851403, | |
| "grad_norm": 1.4710556268692017, | |
| "learning_rate": 0.00025340301136778483, | |
| "loss": 1.0757, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1819560272934041, | |
| "grad_norm": 1.435238003730774, | |
| "learning_rate": 0.00025159223574386114, | |
| "loss": 1.3513, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18498862774829417, | |
| "grad_norm": 1.8190333843231201, | |
| "learning_rate": 0.0002497536858170772, | |
| "loss": 1.6192, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.18802122820318423, | |
| "grad_norm": 1.4935904741287231, | |
| "learning_rate": 0.00024788786422862526, | |
| "loss": 1.3938, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1910538286580743, | |
| "grad_norm": 1.5081324577331543, | |
| "learning_rate": 0.00024599528107549745, | |
| "loss": 1.0642, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.19408642911296436, | |
| "grad_norm": 1.1953938007354736, | |
| "learning_rate": 0.00024407645377103054, | |
| "loss": 0.5319, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.19711902956785443, | |
| "grad_norm": 1.042183756828308, | |
| "learning_rate": 0.00024213190690345018, | |
| "loss": 0.2488, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2001516300227445, | |
| "grad_norm": 0.7810710072517395, | |
| "learning_rate": 0.00024016217209245374, | |
| "loss": 0.2012, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.20318423047763456, | |
| "grad_norm": 0.7428088188171387, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.2595, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.20621683093252463, | |
| "grad_norm": 1.495041012763977, | |
| "learning_rate": 0.0002361492994024415, | |
| "loss": 1.0473, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2092494313874147, | |
| "grad_norm": 3.027667284011841, | |
| "learning_rate": 0.0002341072586027509, | |
| "loss": 1.2385, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.21228203184230476, | |
| "grad_norm": 2.402413845062256, | |
| "learning_rate": 0.00023204222371836405, | |
| "loss": 1.1585, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.21531463229719486, | |
| "grad_norm": 2.1353776454925537, | |
| "learning_rate": 0.00022995475930919905, | |
| "loss": 0.8443, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.21834723275208492, | |
| "grad_norm": 1.6501647233963013, | |
| "learning_rate": 0.00022784543606718227, | |
| "loss": 1.0337, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.221379833206975, | |
| "grad_norm": 4.340311527252197, | |
| "learning_rate": 0.00022571483066022657, | |
| "loss": 1.1674, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.22441243366186506, | |
| "grad_norm": 2.6187245845794678, | |
| "learning_rate": 0.0002235635255745762, | |
| "loss": 0.8261, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.22744503411675512, | |
| "grad_norm": 1.8873292207717896, | |
| "learning_rate": 0.00022139210895556104, | |
| "loss": 0.6276, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.22744503411675512, | |
| "eval_loss": 1.2340877056121826, | |
| "eval_runtime": 1.6504, | |
| "eval_samples_per_second": 30.296, | |
| "eval_steps_per_second": 4.242, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2304776345716452, | |
| "grad_norm": 1.3795561790466309, | |
| "learning_rate": 0.00021920117444680317, | |
| "loss": 1.1671, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.23351023502653526, | |
| "grad_norm": 2.4479212760925293, | |
| "learning_rate": 0.00021699132102792097, | |
| "loss": 1.5214, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.23654283548142532, | |
| "grad_norm": 2.233268976211548, | |
| "learning_rate": 0.0002147631528507739, | |
| "loss": 1.3013, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.2395754359363154, | |
| "grad_norm": 1.663133144378662, | |
| "learning_rate": 0.00021251727907429355, | |
| "loss": 1.0497, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.24260803639120546, | |
| "grad_norm": 1.6820964813232422, | |
| "learning_rate": 0.0002102543136979454, | |
| "loss": 1.8455, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24564063684609552, | |
| "grad_norm": 1.9858072996139526, | |
| "learning_rate": 0.0002079748753938678, | |
| "loss": 1.2171, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.2486732373009856, | |
| "grad_norm": 1.5699634552001953, | |
| "learning_rate": 0.0002056795873377331, | |
| "loss": 1.2286, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.2517058377558757, | |
| "grad_norm": 1.4695563316345215, | |
| "learning_rate": 0.00020336907703837748, | |
| "loss": 1.815, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.25473843821076575, | |
| "grad_norm": 1.7311599254608154, | |
| "learning_rate": 0.00020104397616624645, | |
| "loss": 2.3227, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.2577710386656558, | |
| "grad_norm": 1.2741672992706299, | |
| "learning_rate": 0.00019870492038070252, | |
| "loss": 1.8355, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2608036391205459, | |
| "grad_norm": 1.5505032539367676, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 1.4854, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.26383623957543595, | |
| "grad_norm": 1.86395263671875, | |
| "learning_rate": 0.0001939875056076697, | |
| "loss": 1.8457, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.266868840030326, | |
| "grad_norm": 1.2954498529434204, | |
| "learning_rate": 0.00019161043631427666, | |
| "loss": 2.1125, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.2699014404852161, | |
| "grad_norm": 1.0831388235092163, | |
| "learning_rate": 0.00018922199114307294, | |
| "loss": 1.1493, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.27293404094010615, | |
| "grad_norm": 1.4645804166793823, | |
| "learning_rate": 0.00018682282307111987, | |
| "loss": 1.0175, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2759666413949962, | |
| "grad_norm": 1.5428311824798584, | |
| "learning_rate": 0.00018441358800701273, | |
| "loss": 0.9792, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.2789992418498863, | |
| "grad_norm": 1.3811968564987183, | |
| "learning_rate": 0.00018199494461156203, | |
| "loss": 0.4531, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.28203184230477635, | |
| "grad_norm": 1.3926177024841309, | |
| "learning_rate": 0.000179567554117722, | |
| "loss": 0.4052, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.2850644427596664, | |
| "grad_norm": 1.544171929359436, | |
| "learning_rate": 0.00017713208014981648, | |
| "loss": 0.5097, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.2880970432145565, | |
| "grad_norm": 1.181302547454834, | |
| "learning_rate": 0.00017468918854211007, | |
| "loss": 0.327, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.29112964366944655, | |
| "grad_norm": 1.7300562858581543, | |
| "learning_rate": 0.00017223954715677627, | |
| "loss": 0.3545, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2941622441243366, | |
| "grad_norm": 1.378700852394104, | |
| "learning_rate": 0.00016978382570131034, | |
| "loss": 0.2552, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.2971948445792267, | |
| "grad_norm": 1.5631200075149536, | |
| "learning_rate": 0.00016732269554543794, | |
| "loss": 0.2897, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.30022744503411675, | |
| "grad_norm": 0.8782522678375244, | |
| "learning_rate": 0.00016485682953756942, | |
| "loss": 0.1431, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.3032600454890068, | |
| "grad_norm": 2.4966511726379395, | |
| "learning_rate": 0.00016238690182084986, | |
| "loss": 0.5109, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3032600454890068, | |
| "eval_loss": 1.3453013896942139, | |
| "eval_runtime": 1.6367, | |
| "eval_samples_per_second": 30.55, | |
| "eval_steps_per_second": 4.277, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.066692512625459e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |