| { | |
| "best_metric": 10.526249885559082, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 1.5285171102661597, | |
| "eval_steps": 25, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015209125475285171, | |
| "grad_norm": 7.798121452331543, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 44.4974, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015209125475285171, | |
| "eval_loss": 11.139165878295898, | |
| "eval_runtime": 0.5313, | |
| "eval_samples_per_second": 94.102, | |
| "eval_steps_per_second": 13.174, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030418250950570342, | |
| "grad_norm": 7.954409599304199, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 44.5234, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.045627376425855515, | |
| "grad_norm": 7.833451747894287, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 44.5026, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.060836501901140684, | |
| "grad_norm": 7.779505729675293, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 44.4479, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07604562737642585, | |
| "grad_norm": 7.852802753448486, | |
| "learning_rate": 0.00015, | |
| "loss": 44.4609, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09125475285171103, | |
| "grad_norm": 7.819211006164551, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 44.3568, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10646387832699619, | |
| "grad_norm": 7.94288969039917, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 44.3203, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12167300380228137, | |
| "grad_norm": 7.820436000823975, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 44.2292, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13688212927756654, | |
| "grad_norm": 7.844394207000732, | |
| "learning_rate": 0.00027, | |
| "loss": 44.1641, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1520912547528517, | |
| "grad_norm": 7.6544904708862305, | |
| "learning_rate": 0.0003, | |
| "loss": 44.0807, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16730038022813687, | |
| "grad_norm": 7.4691572189331055, | |
| "learning_rate": 0.00029995027012714694, | |
| "loss": 43.9766, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18250950570342206, | |
| "grad_norm": 7.065072059631348, | |
| "learning_rate": 0.00029980111348272456, | |
| "loss": 43.8542, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19771863117870722, | |
| "grad_norm": 6.962889671325684, | |
| "learning_rate": 0.00029955262896727894, | |
| "loss": 43.7083, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.21292775665399238, | |
| "grad_norm": 6.819710731506348, | |
| "learning_rate": 0.00029920498134218835, | |
| "loss": 43.612, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.22813688212927757, | |
| "grad_norm": 6.688031196594238, | |
| "learning_rate": 0.0002987584011204152, | |
| "loss": 43.474, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.24334600760456274, | |
| "grad_norm": 5.722296714782715, | |
| "learning_rate": 0.0002982131844136615, | |
| "loss": 43.4219, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2585551330798479, | |
| "grad_norm": 5.815008163452148, | |
| "learning_rate": 0.0002975696927360274, | |
| "loss": 43.3333, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2737642585551331, | |
| "grad_norm": 5.559881687164307, | |
| "learning_rate": 0.0002968283527643036, | |
| "loss": 43.1901, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2889733840304182, | |
| "grad_norm": 5.232143878936768, | |
| "learning_rate": 0.00029598965605505737, | |
| "loss": 43.1224, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3041825095057034, | |
| "grad_norm": 5.151193618774414, | |
| "learning_rate": 0.000295054158718698, | |
| "loss": 43.0365, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3193916349809886, | |
| "grad_norm": 4.557214260101318, | |
| "learning_rate": 0.0002940224810507402, | |
| "loss": 43.0156, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.33460076045627374, | |
| "grad_norm": 4.298803329467773, | |
| "learning_rate": 0.00029289530712050735, | |
| "loss": 42.8672, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.34980988593155893, | |
| "grad_norm": 3.9553070068359375, | |
| "learning_rate": 0.0002916733843175492, | |
| "loss": 42.8229, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3650190114068441, | |
| "grad_norm": 3.7043850421905518, | |
| "learning_rate": 0.000290357522856074, | |
| "loss": 42.75, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.38022813688212925, | |
| "grad_norm": 3.5806026458740234, | |
| "learning_rate": 0.0002889485952377242, | |
| "loss": 42.6536, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.38022813688212925, | |
| "eval_loss": 10.657498359680176, | |
| "eval_runtime": 0.1066, | |
| "eval_samples_per_second": 469.222, | |
| "eval_steps_per_second": 65.691, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39543726235741444, | |
| "grad_norm": 3.0404555797576904, | |
| "learning_rate": 0.0002874475356730507, | |
| "loss": 42.724, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.41064638783269963, | |
| "grad_norm": 3.1695425510406494, | |
| "learning_rate": 0.0002858553394620707, | |
| "loss": 42.6042, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.42585551330798477, | |
| "grad_norm": 2.890155076980591, | |
| "learning_rate": 0.0002841730623343193, | |
| "loss": 42.6042, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.44106463878326996, | |
| "grad_norm": 2.8616456985473633, | |
| "learning_rate": 0.00028240181974883207, | |
| "loss": 42.5703, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.45627376425855515, | |
| "grad_norm": 2.712928056716919, | |
| "learning_rate": 0.00028054278615452326, | |
| "loss": 42.5104, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4714828897338403, | |
| "grad_norm": 2.436995267868042, | |
| "learning_rate": 0.0002785971942114498, | |
| "loss": 42.5052, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4866920152091255, | |
| "grad_norm": 2.1528892517089844, | |
| "learning_rate": 0.0002765663339734778, | |
| "loss": 42.5156, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5019011406844106, | |
| "grad_norm": 1.9085866212844849, | |
| "learning_rate": 0.0002744515520328928, | |
| "loss": 42.4583, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5171102661596958, | |
| "grad_norm": 2.139317274093628, | |
| "learning_rate": 0.00027225425062752165, | |
| "loss": 42.388, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.532319391634981, | |
| "grad_norm": 1.8673893213272095, | |
| "learning_rate": 0.0002699758867109579, | |
| "loss": 42.3281, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5475285171102662, | |
| "grad_norm": 1.6618345975875854, | |
| "learning_rate": 0.0002676179709865066, | |
| "loss": 42.3125, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5627376425855514, | |
| "grad_norm": 1.54766047000885, | |
| "learning_rate": 0.00026518206690549, | |
| "loss": 42.2943, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5779467680608364, | |
| "grad_norm": 1.4217829704284668, | |
| "learning_rate": 0.0002626697896305779, | |
| "loss": 42.2943, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5931558935361216, | |
| "grad_norm": 1.5864824056625366, | |
| "learning_rate": 0.00026008280496482984, | |
| "loss": 42.3333, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6083650190114068, | |
| "grad_norm": 1.3134839534759521, | |
| "learning_rate": 0.000257422828247159, | |
| "loss": 42.25, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.623574144486692, | |
| "grad_norm": 1.3444600105285645, | |
| "learning_rate": 0.00025469162321495147, | |
| "loss": 42.3021, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6387832699619772, | |
| "grad_norm": 1.1616184711456299, | |
| "learning_rate": 0.00025189100083459397, | |
| "loss": 42.2057, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6539923954372624, | |
| "grad_norm": 1.3812938928604126, | |
| "learning_rate": 0.00024902281810068475, | |
| "loss": 42.263, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6692015209125475, | |
| "grad_norm": 1.0146691799163818, | |
| "learning_rate": 0.0002460889768047263, | |
| "loss": 42.1901, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6844106463878327, | |
| "grad_norm": 1.0053883790969849, | |
| "learning_rate": 0.0002430914222741134, | |
| "loss": 42.2161, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6996197718631179, | |
| "grad_norm": 0.9144092202186584, | |
| "learning_rate": 0.00024003214208225522, | |
| "loss": 42.2161, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.714828897338403, | |
| "grad_norm": 0.8486371636390686, | |
| "learning_rate": 0.00023691316473068452, | |
| "loss": 42.2214, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7300380228136882, | |
| "grad_norm": 1.0502363443374634, | |
| "learning_rate": 0.00023373655830402968, | |
| "loss": 42.3255, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7452471482889734, | |
| "grad_norm": 1.3109233379364014, | |
| "learning_rate": 0.00023050442909874007, | |
| "loss": 42.3125, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7604562737642585, | |
| "grad_norm": 0.9757567644119263, | |
| "learning_rate": 0.00022721892022647462, | |
| "loss": 42.1979, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7604562737642585, | |
| "eval_loss": 10.535416603088379, | |
| "eval_runtime": 0.1079, | |
| "eval_samples_per_second": 463.538, | |
| "eval_steps_per_second": 64.895, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7756653992395437, | |
| "grad_norm": 0.7378947138786316, | |
| "learning_rate": 0.00022388221019307967, | |
| "loss": 42.1719, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.7908745247148289, | |
| "grad_norm": 0.8719134330749512, | |
| "learning_rate": 0.000220496511454098, | |
| "loss": 42.1641, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.8060836501901141, | |
| "grad_norm": 0.7421266436576843, | |
| "learning_rate": 0.00021706406894776709, | |
| "loss": 42.2005, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.8212927756653993, | |
| "grad_norm": 0.8768603205680847, | |
| "learning_rate": 0.0002135871586064791, | |
| "loss": 42.1771, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.8365019011406845, | |
| "grad_norm": 0.6931475400924683, | |
| "learning_rate": 0.00021006808584768998, | |
| "loss": 42.1979, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.8517110266159695, | |
| "grad_norm": 0.5837717652320862, | |
| "learning_rate": 0.00020650918404527775, | |
| "loss": 42.1406, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.8669201520912547, | |
| "grad_norm": 0.712273895740509, | |
| "learning_rate": 0.00020291281298236423, | |
| "loss": 42.1328, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.8821292775665399, | |
| "grad_norm": 0.8226441740989685, | |
| "learning_rate": 0.00019928135728662522, | |
| "loss": 42.1745, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.8973384030418251, | |
| "grad_norm": 0.617861270904541, | |
| "learning_rate": 0.0001956172248491277, | |
| "loss": 42.1719, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.9125475285171103, | |
| "grad_norm": 0.6812199950218201, | |
| "learning_rate": 0.00019192284522774142, | |
| "loss": 42.1484, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9277566539923955, | |
| "grad_norm": 0.6634241342544556, | |
| "learning_rate": 0.00018820066803618428, | |
| "loss": 42.1615, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.9429657794676806, | |
| "grad_norm": 0.5809543132781982, | |
| "learning_rate": 0.00018445316131976934, | |
| "loss": 42.1432, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.9581749049429658, | |
| "grad_norm": 0.8210413455963135, | |
| "learning_rate": 0.00018068280991893014, | |
| "loss": 42.1901, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.973384030418251, | |
| "grad_norm": 1.388875961303711, | |
| "learning_rate": 0.00017689211382161034, | |
| "loss": 42.2708, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.9885931558935361, | |
| "grad_norm": 0.802690327167511, | |
| "learning_rate": 0.00017308358650560928, | |
| "loss": 42.1328, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.0114068441064639, | |
| "grad_norm": 0.6896817088127136, | |
| "learning_rate": 0.00016925975327198266, | |
| "loss": 42.1927, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.026615969581749, | |
| "grad_norm": 0.818332850933075, | |
| "learning_rate": 0.00016542314957060405, | |
| "loss": 42.1562, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.0418250950570342, | |
| "grad_norm": 0.49196258187294006, | |
| "learning_rate": 0.00016157631931899697, | |
| "loss": 42.125, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.0570342205323193, | |
| "grad_norm": 0.43189793825149536, | |
| "learning_rate": 0.00015772181321555196, | |
| "loss": 42.1172, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.0722433460076046, | |
| "grad_norm": 0.3118878901004791, | |
| "learning_rate": 0.0001538621870482483, | |
| "loss": 42.1068, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0874524714828897, | |
| "grad_norm": 0.5249186158180237, | |
| "learning_rate": 0.00015, | |
| "loss": 42.151, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.102661596958175, | |
| "grad_norm": 0.6453397274017334, | |
| "learning_rate": 0.00014613781295175172, | |
| "loss": 42.1589, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.11787072243346, | |
| "grad_norm": 0.34862664341926575, | |
| "learning_rate": 0.000142278186784448, | |
| "loss": 42.125, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.1330798479087452, | |
| "grad_norm": 0.37730568647384644, | |
| "learning_rate": 0.00013842368068100303, | |
| "loss": 42.1198, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.1482889733840305, | |
| "grad_norm": 0.39992350339889526, | |
| "learning_rate": 0.00013457685042939592, | |
| "loss": 42.138, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.1482889733840305, | |
| "eval_loss": 10.527915954589844, | |
| "eval_runtime": 0.106, | |
| "eval_samples_per_second": 471.538, | |
| "eval_steps_per_second": 66.015, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.1634980988593155, | |
| "grad_norm": 0.9189149141311646, | |
| "learning_rate": 0.00013074024672801731, | |
| "loss": 42.1536, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.1787072243346008, | |
| "grad_norm": 0.5288547873497009, | |
| "learning_rate": 0.0001269164134943907, | |
| "loss": 42.1667, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.193916349809886, | |
| "grad_norm": 0.5245852470397949, | |
| "learning_rate": 0.00012310788617838966, | |
| "loss": 42.1432, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.209125475285171, | |
| "grad_norm": 0.670550525188446, | |
| "learning_rate": 0.0001193171900810699, | |
| "loss": 42.1536, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.2243346007604563, | |
| "grad_norm": 0.6620810031890869, | |
| "learning_rate": 0.00011554683868023067, | |
| "loss": 42.1406, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2395437262357414, | |
| "grad_norm": 0.7172536253929138, | |
| "learning_rate": 0.0001117993319638157, | |
| "loss": 42.1667, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.2547528517110267, | |
| "grad_norm": 0.6294752359390259, | |
| "learning_rate": 0.00010807715477225858, | |
| "loss": 42.1797, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.2699619771863118, | |
| "grad_norm": 0.5978144407272339, | |
| "learning_rate": 0.00010438277515087233, | |
| "loss": 42.1667, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.285171102661597, | |
| "grad_norm": 0.5058898329734802, | |
| "learning_rate": 0.00010071864271337478, | |
| "loss": 42.125, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.3003802281368821, | |
| "grad_norm": 0.5284583568572998, | |
| "learning_rate": 9.708718701763577e-05, | |
| "loss": 42.112, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.3155893536121672, | |
| "grad_norm": 0.5570880770683289, | |
| "learning_rate": 9.34908159547222e-05, | |
| "loss": 42.1302, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.3307984790874525, | |
| "grad_norm": 0.44924110174179077, | |
| "learning_rate": 8.993191415231e-05, | |
| "loss": 42.1536, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.3460076045627376, | |
| "grad_norm": 0.5590141415596008, | |
| "learning_rate": 8.641284139352091e-05, | |
| "loss": 42.1406, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.3612167300380227, | |
| "grad_norm": 0.3548166751861572, | |
| "learning_rate": 8.293593105223287e-05, | |
| "loss": 42.1042, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.376425855513308, | |
| "grad_norm": 0.46111956238746643, | |
| "learning_rate": 7.950348854590204e-05, | |
| "loss": 42.112, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.3916349809885933, | |
| "grad_norm": 0.2855987846851349, | |
| "learning_rate": 7.611778980692035e-05, | |
| "loss": 42.1094, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.4068441064638784, | |
| "grad_norm": 0.3709195852279663, | |
| "learning_rate": 7.278107977352543e-05, | |
| "loss": 42.138, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.4220532319391634, | |
| "grad_norm": 0.8047066330909729, | |
| "learning_rate": 6.949557090125994e-05, | |
| "loss": 42.1667, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.4372623574144487, | |
| "grad_norm": 0.5303740501403809, | |
| "learning_rate": 6.626344169597031e-05, | |
| "loss": 42.125, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.4524714828897338, | |
| "grad_norm": 0.41722556948661804, | |
| "learning_rate": 6.308683526931545e-05, | |
| "loss": 42.125, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.467680608365019, | |
| "grad_norm": 1.1801074743270874, | |
| "learning_rate": 5.996785791774478e-05, | |
| "loss": 42.2188, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.4828897338403042, | |
| "grad_norm": 0.8621243238449097, | |
| "learning_rate": 5.690857772588657e-05, | |
| "loss": 42.1849, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.4980988593155893, | |
| "grad_norm": 1.1932792663574219, | |
| "learning_rate": 5.391102319527373e-05, | |
| "loss": 42.2187, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.5133079847908744, | |
| "grad_norm": 0.38025224208831787, | |
| "learning_rate": 5.0977181899315214e-05, | |
| "loss": 42.1276, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.5285171102661597, | |
| "grad_norm": 0.39083558320999146, | |
| "learning_rate": 4.8108999165406026e-05, | |
| "loss": 42.1458, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5285171102661597, | |
| "eval_loss": 10.526249885559082, | |
| "eval_runtime": 0.1068, | |
| "eval_samples_per_second": 467.988, | |
| "eval_steps_per_second": 65.518, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 132, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 795475968000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |