| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9751552795031055, | |
| "eval_steps": 41, | |
| "global_step": 322, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006211180124223602, | |
| "grad_norm": 0.3814874589443207, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.538, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006211180124223602, | |
| "eval_loss": 1.570106863975525, | |
| "eval_runtime": 26.7523, | |
| "eval_samples_per_second": 2.953, | |
| "eval_steps_per_second": 0.374, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012422360248447204, | |
| "grad_norm": 0.34790050983428955, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.5515, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018633540372670808, | |
| "grad_norm": 0.315510630607605, | |
| "learning_rate": 3e-06, | |
| "loss": 1.6394, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.024844720496894408, | |
| "grad_norm": 0.333831787109375, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.5686, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.031055900621118012, | |
| "grad_norm": 0.3356265723705292, | |
| "learning_rate": 5e-06, | |
| "loss": 1.6442, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.037267080745341616, | |
| "grad_norm": 0.3302271366119385, | |
| "learning_rate": 6e-06, | |
| "loss": 1.6543, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.043478260869565216, | |
| "grad_norm": 0.3428245484828949, | |
| "learning_rate": 7e-06, | |
| "loss": 1.583, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.049689440993788817, | |
| "grad_norm": 0.3571615517139435, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.5863, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.055900621118012424, | |
| "grad_norm": 0.3609354496002197, | |
| "learning_rate": 9e-06, | |
| "loss": 1.5861, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.062111801242236024, | |
| "grad_norm": 0.38313618302345276, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6357, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06832298136645963, | |
| "grad_norm": 0.3678596317768097, | |
| "learning_rate": 9.99974652980635e-06, | |
| "loss": 1.6452, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07453416149068323, | |
| "grad_norm": 0.36209872364997864, | |
| "learning_rate": 9.998986144924253e-06, | |
| "loss": 1.6364, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08074534161490683, | |
| "grad_norm": 0.3838407099246979, | |
| "learning_rate": 9.997718922447669e-06, | |
| "loss": 1.6456, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 0.3796548545360565, | |
| "learning_rate": 9.995944990857848e-06, | |
| "loss": 1.5417, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09316770186335403, | |
| "grad_norm": 0.393232524394989, | |
| "learning_rate": 9.993664530010308e-06, | |
| "loss": 1.5553, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09937888198757763, | |
| "grad_norm": 0.40382516384124756, | |
| "learning_rate": 9.990877771116588e-06, | |
| "loss": 1.4974, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10559006211180125, | |
| "grad_norm": 0.410980224609375, | |
| "learning_rate": 9.987584996720813e-06, | |
| "loss": 1.5143, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11180124223602485, | |
| "grad_norm": 0.43435031175613403, | |
| "learning_rate": 9.983786540671052e-06, | |
| "loss": 1.7078, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11801242236024845, | |
| "grad_norm": 0.46852847933769226, | |
| "learning_rate": 9.979482788085455e-06, | |
| "loss": 1.5725, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12422360248447205, | |
| "grad_norm": 0.44078120589256287, | |
| "learning_rate": 9.974674175313228e-06, | |
| "loss": 1.5146, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13043478260869565, | |
| "grad_norm": 0.4520568251609802, | |
| "learning_rate": 9.969361189890373e-06, | |
| "loss": 1.551, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13664596273291926, | |
| "grad_norm": 0.44940102100372314, | |
| "learning_rate": 9.96354437049027e-06, | |
| "loss": 1.5154, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.42880144715309143, | |
| "learning_rate": 9.957224306869053e-06, | |
| "loss": 1.5664, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14906832298136646, | |
| "grad_norm": 0.4296427071094513, | |
| "learning_rate": 9.950401639805822e-06, | |
| "loss": 1.5391, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15527950310559005, | |
| "grad_norm": 0.4148462116718292, | |
| "learning_rate": 9.943077061037672e-06, | |
| "loss": 1.559, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16149068322981366, | |
| "grad_norm": 0.45027458667755127, | |
| "learning_rate": 9.935251313189564e-06, | |
| "loss": 1.5797, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16770186335403728, | |
| "grad_norm": 0.43325772881507874, | |
| "learning_rate": 9.92692518969903e-06, | |
| "loss": 1.5651, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 0.4363733232021332, | |
| "learning_rate": 9.91809953473572e-06, | |
| "loss": 1.4171, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18012422360248448, | |
| "grad_norm": 0.4001283347606659, | |
| "learning_rate": 9.908775243115822e-06, | |
| "loss": 1.5172, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.18633540372670807, | |
| "grad_norm": 0.42918145656585693, | |
| "learning_rate": 9.89895326021134e-06, | |
| "loss": 1.4501, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19254658385093168, | |
| "grad_norm": 0.3902086019515991, | |
| "learning_rate": 9.888634581854235e-06, | |
| "loss": 1.4396, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.19875776397515527, | |
| "grad_norm": 0.4069195091724396, | |
| "learning_rate": 9.87782025423547e-06, | |
| "loss": 1.4399, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20496894409937888, | |
| "grad_norm": 0.40982964634895325, | |
| "learning_rate": 9.86651137379893e-06, | |
| "loss": 1.4445, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2111801242236025, | |
| "grad_norm": 0.4249035716056824, | |
| "learning_rate": 9.854709087130261e-06, | |
| "loss": 1.4402, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.21739130434782608, | |
| "grad_norm": 0.4334266781806946, | |
| "learning_rate": 9.842414590840618e-06, | |
| "loss": 1.4633, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2236024844720497, | |
| "grad_norm": 0.4241773188114166, | |
| "learning_rate": 9.829629131445342e-06, | |
| "loss": 1.5354, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.22981366459627328, | |
| "grad_norm": 0.45813798904418945, | |
| "learning_rate": 9.816354005237583e-06, | |
| "loss": 1.4568, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2360248447204969, | |
| "grad_norm": 0.4499090909957886, | |
| "learning_rate": 9.802590558156863e-06, | |
| "loss": 1.4483, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2422360248447205, | |
| "grad_norm": 0.44764548540115356, | |
| "learning_rate": 9.78834018565262e-06, | |
| "loss": 1.4769, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2484472049689441, | |
| "grad_norm": 0.4358612298965454, | |
| "learning_rate": 9.77360433254273e-06, | |
| "loss": 1.5545, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2546583850931677, | |
| "grad_norm": 0.44274434447288513, | |
| "learning_rate": 9.758384492867004e-06, | |
| "loss": 1.3615, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2546583850931677, | |
| "eval_loss": 1.3996479511260986, | |
| "eval_runtime": 27.0472, | |
| "eval_samples_per_second": 2.921, | |
| "eval_steps_per_second": 0.37, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": 0.42516258358955383, | |
| "learning_rate": 9.742682209735727e-06, | |
| "loss": 1.4802, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2670807453416149, | |
| "grad_norm": 0.40934988856315613, | |
| "learning_rate": 9.726499075173201e-06, | |
| "loss": 1.3283, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2732919254658385, | |
| "grad_norm": 0.40728411078453064, | |
| "learning_rate": 9.709836729956326e-06, | |
| "loss": 1.4724, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2795031055900621, | |
| "grad_norm": 0.405512273311615, | |
| "learning_rate": 9.692696863448246e-06, | |
| "loss": 1.3943, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.4585839807987213, | |
| "learning_rate": 9.675081213427076e-06, | |
| "loss": 1.4038, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2919254658385093, | |
| "grad_norm": 0.40490880608558655, | |
| "learning_rate": 9.656991565909703e-06, | |
| "loss": 1.3807, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2981366459627329, | |
| "grad_norm": 0.4017808735370636, | |
| "learning_rate": 9.638429754970715e-06, | |
| "loss": 1.3532, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.30434782608695654, | |
| "grad_norm": 0.41484227776527405, | |
| "learning_rate": 9.619397662556434e-06, | |
| "loss": 1.3379, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3105590062111801, | |
| "grad_norm": 0.36943531036376953, | |
| "learning_rate": 9.599897218294122e-06, | |
| "loss": 1.393, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3167701863354037, | |
| "grad_norm": 0.39943498373031616, | |
| "learning_rate": 9.57993039929633e-06, | |
| "loss": 1.3039, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.32298136645962733, | |
| "grad_norm": 0.374943345785141, | |
| "learning_rate": 9.55949922996045e-06, | |
| "loss": 1.355, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.32919254658385094, | |
| "grad_norm": 0.4175715446472168, | |
| "learning_rate": 9.538605781763464e-06, | |
| "loss": 1.3716, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.33540372670807456, | |
| "grad_norm": 0.37441951036453247, | |
| "learning_rate": 9.517252173051912e-06, | |
| "loss": 1.3081, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3416149068322981, | |
| "grad_norm": 0.39863765239715576, | |
| "learning_rate": 9.49544056882713e-06, | |
| "loss": 1.3942, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 0.3854600787162781, | |
| "learning_rate": 9.473173180525737e-06, | |
| "loss": 1.2902, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.35403726708074534, | |
| "grad_norm": 0.42524421215057373, | |
| "learning_rate": 9.450452265795423e-06, | |
| "loss": 1.2544, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.36024844720496896, | |
| "grad_norm": 0.41367658972740173, | |
| "learning_rate": 9.427280128266049e-06, | |
| "loss": 1.3194, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.36645962732919257, | |
| "grad_norm": 0.3787434697151184, | |
| "learning_rate": 9.403659117316093e-06, | |
| "loss": 1.3077, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.37267080745341613, | |
| "grad_norm": 0.4197174608707428, | |
| "learning_rate": 9.37959162783444e-06, | |
| "loss": 1.2356, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.37888198757763975, | |
| "grad_norm": 0.39209407567977905, | |
| "learning_rate": 9.355080099977579e-06, | |
| "loss": 1.2168, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.38509316770186336, | |
| "grad_norm": 0.41228196024894714, | |
| "learning_rate": 9.330127018922195e-06, | |
| "loss": 1.2237, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.391304347826087, | |
| "grad_norm": 0.4241032302379608, | |
| "learning_rate": 9.3047349146132e-06, | |
| "loss": 1.3146, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.39751552795031053, | |
| "grad_norm": 0.4294179677963257, | |
| "learning_rate": 9.278906361507238e-06, | |
| "loss": 1.2716, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.40372670807453415, | |
| "grad_norm": 0.4411190450191498, | |
| "learning_rate": 9.252643978311649e-06, | |
| "loss": 1.2735, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.40993788819875776, | |
| "grad_norm": 0.46513664722442627, | |
| "learning_rate": 9.225950427718974e-06, | |
| "loss": 1.2337, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4161490683229814, | |
| "grad_norm": 0.36713191866874695, | |
| "learning_rate": 9.198828416136991e-06, | |
| "loss": 1.3339, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.422360248447205, | |
| "grad_norm": 0.351909875869751, | |
| "learning_rate": 9.171280693414307e-06, | |
| "loss": 1.358, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.3643895983695984, | |
| "learning_rate": 9.14331005256157e-06, | |
| "loss": 1.2482, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.43478260869565216, | |
| "grad_norm": 0.4360922873020172, | |
| "learning_rate": 9.114919329468283e-06, | |
| "loss": 1.3115, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4409937888198758, | |
| "grad_norm": 0.4254709482192993, | |
| "learning_rate": 9.086111402615274e-06, | |
| "loss": 1.2351, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4472049689440994, | |
| "grad_norm": 0.3786623179912567, | |
| "learning_rate": 9.056889192782865e-06, | |
| "loss": 1.3746, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.453416149068323, | |
| "grad_norm": 0.4647882878780365, | |
| "learning_rate": 9.02725566275473e-06, | |
| "loss": 1.2395, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.45962732919254656, | |
| "grad_norm": 0.4040616452693939, | |
| "learning_rate": 8.997213817017508e-06, | |
| "loss": 1.2998, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.4658385093167702, | |
| "grad_norm": 0.41700279712677, | |
| "learning_rate": 8.966766701456177e-06, | |
| "loss": 1.2105, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4720496894409938, | |
| "grad_norm": 0.3908318877220154, | |
| "learning_rate": 8.935917403045251e-06, | |
| "loss": 1.2011, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.4782608695652174, | |
| "grad_norm": 0.38885021209716797, | |
| "learning_rate": 8.90466904953579e-06, | |
| "loss": 1.2471, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.484472049689441, | |
| "grad_norm": 0.42335832118988037, | |
| "learning_rate": 8.873024809138272e-06, | |
| "loss": 1.2683, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.4906832298136646, | |
| "grad_norm": 0.39654576778411865, | |
| "learning_rate": 8.840987890201404e-06, | |
| "loss": 1.2587, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.4968944099378882, | |
| "grad_norm": 0.4123787581920624, | |
| "learning_rate": 8.808561540886796e-06, | |
| "loss": 1.1794, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5031055900621118, | |
| "grad_norm": 0.42227044701576233, | |
| "learning_rate": 8.77574904883967e-06, | |
| "loss": 1.2339, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5093167701863354, | |
| "grad_norm": 0.4471132159233093, | |
| "learning_rate": 8.742553740855507e-06, | |
| "loss": 1.1954, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5093167701863354, | |
| "eval_loss": 1.2136852741241455, | |
| "eval_runtime": 26.7767, | |
| "eval_samples_per_second": 2.95, | |
| "eval_steps_per_second": 0.373, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.515527950310559, | |
| "grad_norm": 0.42590177059173584, | |
| "learning_rate": 8.708978982542766e-06, | |
| "loss": 1.2426, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 0.39879706501960754, | |
| "learning_rate": 8.675028177981643e-06, | |
| "loss": 1.2618, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5279503105590062, | |
| "grad_norm": 0.4137211740016937, | |
| "learning_rate": 8.640704769378943e-06, | |
| "loss": 1.1735, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5341614906832298, | |
| "grad_norm": 0.42463183403015137, | |
| "learning_rate": 8.606012236719073e-06, | |
| "loss": 1.1433, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.5403726708074534, | |
| "grad_norm": 0.42853713035583496, | |
| "learning_rate": 8.570954097411224e-06, | |
| "loss": 1.2307, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.546583850931677, | |
| "grad_norm": 0.408589243888855, | |
| "learning_rate": 8.535533905932739e-06, | |
| "loss": 1.1523, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.5527950310559007, | |
| "grad_norm": 0.42884618043899536, | |
| "learning_rate": 8.499755253468732e-06, | |
| "loss": 1.2494, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.5590062111801242, | |
| "grad_norm": 0.4813741445541382, | |
| "learning_rate": 8.463621767547998e-06, | |
| "loss": 1.2417, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5652173913043478, | |
| "grad_norm": 0.4021080732345581, | |
| "learning_rate": 8.4271371116752e-06, | |
| "loss": 1.2715, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.3832411468029022, | |
| "learning_rate": 8.390304984959455e-06, | |
| "loss": 1.1586, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.577639751552795, | |
| "grad_norm": 0.4360566735267639, | |
| "learning_rate": 8.35312912173928e-06, | |
| "loss": 1.217, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.5838509316770186, | |
| "grad_norm": 0.44515809416770935, | |
| "learning_rate": 8.315613291203977e-06, | |
| "loss": 1.264, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.5900621118012422, | |
| "grad_norm": 0.41051459312438965, | |
| "learning_rate": 8.277761297011475e-06, | |
| "loss": 1.1578, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5962732919254659, | |
| "grad_norm": 0.45815277099609375, | |
| "learning_rate": 8.239576976902694e-06, | |
| "loss": 1.2084, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6024844720496895, | |
| "grad_norm": 0.4373926520347595, | |
| "learning_rate": 8.20106420231244e-06, | |
| "loss": 1.1925, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6086956521739131, | |
| "grad_norm": 0.444323867559433, | |
| "learning_rate": 8.162226877976886e-06, | |
| "loss": 1.2183, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6149068322981367, | |
| "grad_norm": 0.4503950774669647, | |
| "learning_rate": 8.123068941537681e-06, | |
| "loss": 1.1156, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6211180124223602, | |
| "grad_norm": 0.4149700105190277, | |
| "learning_rate": 8.083594363142717e-06, | |
| "loss": 1.2379, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6273291925465838, | |
| "grad_norm": 0.472960501909256, | |
| "learning_rate": 8.043807145043604e-06, | |
| "loss": 1.14, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.6335403726708074, | |
| "grad_norm": 0.40744665265083313, | |
| "learning_rate": 8.003711321189895e-06, | |
| "loss": 1.2446, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.639751552795031, | |
| "grad_norm": 0.3995897173881531, | |
| "learning_rate": 7.963310956820085e-06, | |
| "loss": 1.179, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.6459627329192547, | |
| "grad_norm": 0.4376934766769409, | |
| "learning_rate": 7.922610148049445e-06, | |
| "loss": 1.2818, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.6521739130434783, | |
| "grad_norm": 0.4294185936450958, | |
| "learning_rate": 7.881613021454728e-06, | |
| "loss": 1.1463, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6583850931677019, | |
| "grad_norm": 0.46748086810112, | |
| "learning_rate": 7.84032373365578e-06, | |
| "loss": 1.1702, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.6645962732919255, | |
| "grad_norm": 0.47421255707740784, | |
| "learning_rate": 7.798746470894113e-06, | |
| "loss": 1.2922, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.6708074534161491, | |
| "grad_norm": 0.37985584139823914, | |
| "learning_rate": 7.75688544860846e-06, | |
| "loss": 1.1581, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.6770186335403726, | |
| "grad_norm": 0.4336451590061188, | |
| "learning_rate": 7.714744911007395e-06, | |
| "loss": 1.1532, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.6832298136645962, | |
| "grad_norm": 0.4210762679576874, | |
| "learning_rate": 7.672329130639007e-06, | |
| "loss": 1.2047, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6894409937888198, | |
| "grad_norm": 0.42413201928138733, | |
| "learning_rate": 7.62964240795772e-06, | |
| "loss": 1.125, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 0.47521328926086426, | |
| "learning_rate": 7.586689070888284e-06, | |
| "loss": 1.2143, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7018633540372671, | |
| "grad_norm": 0.41499438881874084, | |
| "learning_rate": 7.543473474386962e-06, | |
| "loss": 1.07, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.7080745341614907, | |
| "grad_norm": 0.4027252495288849, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.262, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.4009539484977722, | |
| "learning_rate": 7.4562730554193875e-06, | |
| "loss": 1.1742, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7204968944099379, | |
| "grad_norm": 0.46428173780441284, | |
| "learning_rate": 7.412297074035968e-06, | |
| "loss": 1.1629, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.7267080745341615, | |
| "grad_norm": 0.4374319016933441, | |
| "learning_rate": 7.368076514489947e-06, | |
| "loss": 1.1065, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.7329192546583851, | |
| "grad_norm": 0.42879152297973633, | |
| "learning_rate": 7.323615860218844e-06, | |
| "loss": 1.193, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.7391304347826086, | |
| "grad_norm": 0.4889649748802185, | |
| "learning_rate": 7.2789196190029155e-06, | |
| "loss": 1.2618, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.7453416149068323, | |
| "grad_norm": 0.4490755796432495, | |
| "learning_rate": 7.2339923225081296e-06, | |
| "loss": 1.1857, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7515527950310559, | |
| "grad_norm": 0.4516308009624481, | |
| "learning_rate": 7.188838525826702e-06, | |
| "loss": 1.1076, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.7577639751552795, | |
| "grad_norm": 0.5366808176040649, | |
| "learning_rate": 7.143462807015271e-06, | |
| "loss": 1.1523, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.7639751552795031, | |
| "grad_norm": 0.4146997332572937, | |
| "learning_rate": 7.09786976663073e-06, | |
| "loss": 1.1766, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.7639751552795031, | |
| "eval_loss": 1.1551172733306885, | |
| "eval_runtime": 26.7368, | |
| "eval_samples_per_second": 2.955, | |
| "eval_steps_per_second": 0.374, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.7701863354037267, | |
| "grad_norm": 0.4490116536617279, | |
| "learning_rate": 7.052064027263785e-06, | |
| "loss": 1.1971, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.7763975155279503, | |
| "grad_norm": 0.48434358835220337, | |
| "learning_rate": 7.006050233070289e-06, | |
| "loss": 1.239, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.782608695652174, | |
| "grad_norm": 0.4746357798576355, | |
| "learning_rate": 6.959833049300376e-06, | |
| "loss": 1.1586, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.7888198757763976, | |
| "grad_norm": 0.39503100514411926, | |
| "learning_rate": 6.913417161825449e-06, | |
| "loss": 1.0894, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.7950310559006211, | |
| "grad_norm": 0.43696898221969604, | |
| "learning_rate": 6.8668072766631054e-06, | |
| "loss": 1.0384, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8012422360248447, | |
| "grad_norm": 0.4739917814731598, | |
| "learning_rate": 6.820008119499992e-06, | |
| "loss": 1.1741, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.8074534161490683, | |
| "grad_norm": 0.4144044518470764, | |
| "learning_rate": 6.773024435212678e-06, | |
| "loss": 1.1911, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8136645962732919, | |
| "grad_norm": 0.4699600636959076, | |
| "learning_rate": 6.7258609873865895e-06, | |
| "loss": 1.2041, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.8198757763975155, | |
| "grad_norm": 0.40221303701400757, | |
| "learning_rate": 6.678522557833025e-06, | |
| "loss": 1.1077, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.8260869565217391, | |
| "grad_norm": 0.4720539152622223, | |
| "learning_rate": 6.631013946104348e-06, | |
| "loss": 1.0987, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.8322981366459627, | |
| "grad_norm": 0.4860423505306244, | |
| "learning_rate": 6.583339969007364e-06, | |
| "loss": 1.1455, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.8385093167701864, | |
| "grad_norm": 0.5083861947059631, | |
| "learning_rate": 6.5355054601149545e-06, | |
| "loss": 1.1314, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.84472049689441, | |
| "grad_norm": 0.5092173218727112, | |
| "learning_rate": 6.487515269276015e-06, | |
| "loss": 1.2228, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.8509316770186336, | |
| "grad_norm": 0.4544651508331299, | |
| "learning_rate": 6.439374262123731e-06, | |
| "loss": 1.1177, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.45371013879776, | |
| "learning_rate": 6.391087319582264e-06, | |
| "loss": 1.1782, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.8633540372670807, | |
| "grad_norm": 0.5025550723075867, | |
| "learning_rate": 6.342659337371884e-06, | |
| "loss": 1.1594, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 0.48699814081192017, | |
| "learning_rate": 6.294095225512604e-06, | |
| "loss": 1.1246, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8757763975155279, | |
| "grad_norm": 0.442331999540329, | |
| "learning_rate": 6.2453999078263596e-06, | |
| "loss": 1.1265, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.8819875776397516, | |
| "grad_norm": 0.4538658857345581, | |
| "learning_rate": 6.1965783214377895e-06, | |
| "loss": 1.2054, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.8881987577639752, | |
| "grad_norm": 0.4796921908855438, | |
| "learning_rate": 6.147635416273679e-06, | |
| "loss": 1.1621, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.8944099378881988, | |
| "grad_norm": 0.4758358895778656, | |
| "learning_rate": 6.0985761545610865e-06, | |
| "loss": 1.117, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9006211180124224, | |
| "grad_norm": 0.44177138805389404, | |
| "learning_rate": 6.049405510324237e-06, | |
| "loss": 1.1016, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.906832298136646, | |
| "grad_norm": 0.48750707507133484, | |
| "learning_rate": 6.000128468880223e-06, | |
| "loss": 1.2238, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.9130434782608695, | |
| "grad_norm": 0.53321373462677, | |
| "learning_rate": 5.950750026333534e-06, | |
| "loss": 1.0768, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.9192546583850931, | |
| "grad_norm": 0.4829699993133545, | |
| "learning_rate": 5.90127518906953e-06, | |
| "loss": 1.1229, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.9254658385093167, | |
| "grad_norm": 0.5378725528717041, | |
| "learning_rate": 5.851708973246841e-06, | |
| "loss": 1.076, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.9316770186335404, | |
| "grad_norm": 0.44234123826026917, | |
| "learning_rate": 5.8020564042888015e-06, | |
| "loss": 1.1543, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.937888198757764, | |
| "grad_norm": 0.41885337233543396, | |
| "learning_rate": 5.752322516373916e-06, | |
| "loss": 1.1918, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.9440993788819876, | |
| "grad_norm": 0.4357737600803375, | |
| "learning_rate": 5.7025123519254644e-06, | |
| "loss": 1.1822, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.9503105590062112, | |
| "grad_norm": 0.48525384068489075, | |
| "learning_rate": 5.65263096110026e-06, | |
| "loss": 1.1569, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.9565217391304348, | |
| "grad_norm": 0.4788309335708618, | |
| "learning_rate": 5.6026834012766155e-06, | |
| "loss": 1.1826, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.9627329192546584, | |
| "grad_norm": 0.4695623815059662, | |
| "learning_rate": 5.5526747365416e-06, | |
| "loss": 1.196, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.968944099378882, | |
| "grad_norm": 0.38793641328811646, | |
| "learning_rate": 5.502610037177586e-06, | |
| "loss": 1.0959, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.9751552795031055, | |
| "grad_norm": 0.4816080629825592, | |
| "learning_rate": 5.45249437914819e-06, | |
| "loss": 1.1359, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.9813664596273292, | |
| "grad_norm": 0.4505300223827362, | |
| "learning_rate": 5.402332843583631e-06, | |
| "loss": 1.0793, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.9875776397515528, | |
| "grad_norm": 0.5171789526939392, | |
| "learning_rate": 5.35213051626556e-06, | |
| "loss": 1.1582, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.9937888198757764, | |
| "grad_norm": 0.4746135473251343, | |
| "learning_rate": 5.301892487111431e-06, | |
| "loss": 1.13, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.5038459897041321, | |
| "learning_rate": 5.251623849658434e-06, | |
| "loss": 1.2033, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 1.0062111801242235, | |
| "grad_norm": 0.4865545332431793, | |
| "learning_rate": 5.201329700547077e-06, | |
| "loss": 1.2215, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.0124223602484472, | |
| "grad_norm": 0.44650915265083313, | |
| "learning_rate": 5.151015139004445e-06, | |
| "loss": 1.1592, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 1.0186335403726707, | |
| "grad_norm": 0.4772714376449585, | |
| "learning_rate": 5.100685266327202e-06, | |
| "loss": 1.1361, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.0186335403726707, | |
| "eval_loss": 1.1316967010498047, | |
| "eval_runtime": 26.8815, | |
| "eval_samples_per_second": 2.939, | |
| "eval_steps_per_second": 0.372, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 1.0248447204968945, | |
| "grad_norm": 0.4834270179271698, | |
| "learning_rate": 5.050345185364378e-06, | |
| "loss": 1.1859, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.0062111801242235, | |
| "grad_norm": 0.48713916540145874, | |
| "learning_rate": 5e-06, | |
| "loss": 1.0621, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 1.0124223602484472, | |
| "grad_norm": 0.4767020642757416, | |
| "learning_rate": 4.949654814635623e-06, | |
| "loss": 1.0793, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 1.0186335403726707, | |
| "grad_norm": 0.4696958065032959, | |
| "learning_rate": 4.8993147336728e-06, | |
| "loss": 1.2284, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 1.0248447204968945, | |
| "grad_norm": 0.47341403365135193, | |
| "learning_rate": 4.848984860995557e-06, | |
| "loss": 1.1235, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 1.031055900621118, | |
| "grad_norm": 0.5151461958885193, | |
| "learning_rate": 4.798670299452926e-06, | |
| "loss": 1.1104, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0372670807453417, | |
| "grad_norm": 0.4465959668159485, | |
| "learning_rate": 4.748376150341566e-06, | |
| "loss": 1.106, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 1.0434782608695652, | |
| "grad_norm": 0.4610389769077301, | |
| "learning_rate": 4.69810751288857e-06, | |
| "loss": 1.2657, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.049689440993789, | |
| "grad_norm": 0.4607885479927063, | |
| "learning_rate": 4.647869483734441e-06, | |
| "loss": 1.1618, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 1.0559006211180124, | |
| "grad_norm": 0.4866524934768677, | |
| "learning_rate": 4.597667156416371e-06, | |
| "loss": 1.1848, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 1.062111801242236, | |
| "grad_norm": 0.4338420033454895, | |
| "learning_rate": 4.547505620851812e-06, | |
| "loss": 1.1223, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.0683229813664596, | |
| "grad_norm": 0.5134140849113464, | |
| "learning_rate": 4.497389962822416e-06, | |
| "loss": 1.1493, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 1.0745341614906831, | |
| "grad_norm": 0.5529913902282715, | |
| "learning_rate": 4.447325263458401e-06, | |
| "loss": 1.1222, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 1.0807453416149069, | |
| "grad_norm": 0.48266178369522095, | |
| "learning_rate": 4.397316598723385e-06, | |
| "loss": 1.2108, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 1.0869565217391304, | |
| "grad_norm": 0.42973291873931885, | |
| "learning_rate": 4.347369038899744e-06, | |
| "loss": 1.1305, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 1.093167701863354, | |
| "grad_norm": 0.4676703214645386, | |
| "learning_rate": 4.297487648074538e-06, | |
| "loss": 1.2059, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0993788819875776, | |
| "grad_norm": 0.4928361773490906, | |
| "learning_rate": 4.247677483626085e-06, | |
| "loss": 1.1674, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 1.1055900621118013, | |
| "grad_norm": 0.526463508605957, | |
| "learning_rate": 4.1979435957111984e-06, | |
| "loss": 1.0983, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 1.1118012422360248, | |
| "grad_norm": 0.44327542185783386, | |
| "learning_rate": 4.148291026753159e-06, | |
| "loss": 1.1574, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.1180124223602483, | |
| "grad_norm": 0.4704626798629761, | |
| "learning_rate": 4.098724810930472e-06, | |
| "loss": 1.1953, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.124223602484472, | |
| "grad_norm": 0.43922385573387146, | |
| "learning_rate": 4.049249973666468e-06, | |
| "loss": 1.1376, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.1304347826086956, | |
| "grad_norm": 0.462429404258728, | |
| "learning_rate": 3.999871531119779e-06, | |
| "loss": 1.0687, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.1366459627329193, | |
| "grad_norm": 0.47191864252090454, | |
| "learning_rate": 3.9505944896757635e-06, | |
| "loss": 1.139, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.46805888414382935, | |
| "learning_rate": 3.901423845438916e-06, | |
| "loss": 1.1135, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.1490683229813665, | |
| "grad_norm": 0.4984455704689026, | |
| "learning_rate": 3.852364583726324e-06, | |
| "loss": 1.0954, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 1.15527950310559, | |
| "grad_norm": 0.5003888010978699, | |
| "learning_rate": 3.803421678562213e-06, | |
| "loss": 1.1432, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.1614906832298137, | |
| "grad_norm": 0.5040602087974548, | |
| "learning_rate": 3.7546000921736413e-06, | |
| "loss": 1.1675, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 1.1677018633540373, | |
| "grad_norm": 0.45909303426742554, | |
| "learning_rate": 3.705904774487396e-06, | |
| "loss": 1.1865, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 1.1739130434782608, | |
| "grad_norm": 0.4990633428096771, | |
| "learning_rate": 3.657340662628116e-06, | |
| "loss": 1.1393, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 1.1801242236024845, | |
| "grad_norm": 0.4696108400821686, | |
| "learning_rate": 3.6089126804177373e-06, | |
| "loss": 1.1307, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 1.186335403726708, | |
| "grad_norm": 0.5014775395393372, | |
| "learning_rate": 3.56062573787627e-06, | |
| "loss": 1.137, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.1925465838509317, | |
| "grad_norm": 0.46463677287101746, | |
| "learning_rate": 3.5124847307239863e-06, | |
| "loss": 1.1561, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 1.1987577639751552, | |
| "grad_norm": 0.43704545497894287, | |
| "learning_rate": 3.464494539885047e-06, | |
| "loss": 1.1201, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 1.204968944099379, | |
| "grad_norm": 0.445740669965744, | |
| "learning_rate": 3.416660030992639e-06, | |
| "loss": 1.1516, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 1.2111801242236024, | |
| "grad_norm": 0.5268468856811523, | |
| "learning_rate": 3.3689860538956547e-06, | |
| "loss": 1.1288, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 1.2173913043478262, | |
| "grad_norm": 0.4934462606906891, | |
| "learning_rate": 3.3214774421669777e-06, | |
| "loss": 1.1642, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2236024844720497, | |
| "grad_norm": 0.5016915202140808, | |
| "learning_rate": 3.274139012613411e-06, | |
| "loss": 1.0885, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 1.2298136645962732, | |
| "grad_norm": 0.4747258722782135, | |
| "learning_rate": 3.226975564787322e-06, | |
| "loss": 1.1381, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 1.236024844720497, | |
| "grad_norm": 0.522182285785675, | |
| "learning_rate": 3.1799918805000097e-06, | |
| "loss": 1.0668, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 1.2422360248447206, | |
| "grad_norm": 0.5038187503814697, | |
| "learning_rate": 3.1331927233368954e-06, | |
| "loss": 1.0818, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 1.2484472049689441, | |
| "grad_norm": 0.46231281757354736, | |
| "learning_rate": 3.0865828381745515e-06, | |
| "loss": 1.0431, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.2484472049689441, | |
| "eval_loss": 1.1210699081420898, | |
| "eval_runtime": 26.9725, | |
| "eval_samples_per_second": 2.929, | |
| "eval_steps_per_second": 0.371, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.2546583850931676, | |
| "grad_norm": 0.5070775747299194, | |
| "learning_rate": 3.040166950699626e-06, | |
| "loss": 1.1643, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 1.2608695652173914, | |
| "grad_norm": 0.5011193752288818, | |
| "learning_rate": 2.993949766929711e-06, | |
| "loss": 1.0472, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 1.2670807453416149, | |
| "grad_norm": 0.4393374025821686, | |
| "learning_rate": 2.947935972736217e-06, | |
| "loss": 1.0875, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 1.2732919254658386, | |
| "grad_norm": 0.46959808468818665, | |
| "learning_rate": 2.9021302333692738e-06, | |
| "loss": 1.1078, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 1.279503105590062, | |
| "grad_norm": 0.4769798219203949, | |
| "learning_rate": 2.8565371929847286e-06, | |
| "loss": 1.16, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.4200010895729065, | |
| "learning_rate": 2.8111614741732975e-06, | |
| "loss": 1.1258, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 1.2919254658385093, | |
| "grad_norm": 0.502759575843811, | |
| "learning_rate": 2.766007677491871e-06, | |
| "loss": 1.1263, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 1.298136645962733, | |
| "grad_norm": 0.48976272344589233, | |
| "learning_rate": 2.7210803809970853e-06, | |
| "loss": 1.174, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 1.3043478260869565, | |
| "grad_norm": 0.582251787185669, | |
| "learning_rate": 2.6763841397811576e-06, | |
| "loss": 1.1542, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 1.31055900621118, | |
| "grad_norm": 0.525684654712677, | |
| "learning_rate": 2.631923485510054e-06, | |
| "loss": 1.1594, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.3167701863354038, | |
| "grad_norm": 0.5200883150100708, | |
| "learning_rate": 2.587702925964034e-06, | |
| "loss": 1.1374, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.3229813664596273, | |
| "grad_norm": 0.4962819218635559, | |
| "learning_rate": 2.5437269445806146e-06, | |
| "loss": 1.0839, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 1.329192546583851, | |
| "grad_norm": 0.5223807692527771, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 1.0708, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.3354037267080745, | |
| "grad_norm": 0.434766560792923, | |
| "learning_rate": 2.4565265256130393e-06, | |
| "loss": 1.1387, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 1.341614906832298, | |
| "grad_norm": 0.4618338346481323, | |
| "learning_rate": 2.4133109291117156e-06, | |
| "loss": 1.0728, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.3478260869565217, | |
| "grad_norm": 0.5078674554824829, | |
| "learning_rate": 2.3703575920422793e-06, | |
| "loss": 1.1649, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 1.3540372670807455, | |
| "grad_norm": 0.5160240530967712, | |
| "learning_rate": 2.3276708693609947e-06, | |
| "loss": 1.1226, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 1.360248447204969, | |
| "grad_norm": 0.44181424379348755, | |
| "learning_rate": 2.2852550889926067e-06, | |
| "loss": 1.0961, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 1.3664596273291925, | |
| "grad_norm": 0.4639110863208771, | |
| "learning_rate": 2.243114551391542e-06, | |
| "loss": 1.0937, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 1.3726708074534162, | |
| "grad_norm": 0.44535526633262634, | |
| "learning_rate": 2.20125352910589e-06, | |
| "loss": 1.1514, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.3788819875776397, | |
| "grad_norm": 0.463021844625473, | |
| "learning_rate": 2.159676266344222e-06, | |
| "loss": 1.1019, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 1.3850931677018634, | |
| "grad_norm": 0.494054913520813, | |
| "learning_rate": 2.1183869785452744e-06, | |
| "loss": 1.1175, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 1.391304347826087, | |
| "grad_norm": 0.5025504231452942, | |
| "learning_rate": 2.077389851950557e-06, | |
| "loss": 1.0575, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 1.3975155279503104, | |
| "grad_norm": 0.46806544065475464, | |
| "learning_rate": 2.036689043179917e-06, | |
| "loss": 1.1058, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 1.4037267080745341, | |
| "grad_norm": 0.4613620638847351, | |
| "learning_rate": 1.996288678810105e-06, | |
| "loss": 1.1508, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.4099378881987579, | |
| "grad_norm": 0.5427222847938538, | |
| "learning_rate": 1.956192854956397e-06, | |
| "loss": 1.2126, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 1.4161490683229814, | |
| "grad_norm": 0.4144895374774933, | |
| "learning_rate": 1.9164056368572847e-06, | |
| "loss": 1.0932, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 1.4223602484472049, | |
| "grad_norm": 0.47324222326278687, | |
| "learning_rate": 1.87693105846232e-06, | |
| "loss": 1.075, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.4890088737010956, | |
| "learning_rate": 1.8377731220231144e-06, | |
| "loss": 1.1909, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 1.434782608695652, | |
| "grad_norm": 0.5050180554389954, | |
| "learning_rate": 1.7989357976875603e-06, | |
| "loss": 1.0406, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.4409937888198758, | |
| "grad_norm": 0.5166496634483337, | |
| "learning_rate": 1.7604230230973068e-06, | |
| "loss": 1.1579, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 1.4472049689440993, | |
| "grad_norm": 0.5063875913619995, | |
| "learning_rate": 1.7222387029885268e-06, | |
| "loss": 1.0532, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 1.453416149068323, | |
| "grad_norm": 0.43411558866500854, | |
| "learning_rate": 1.6843867087960252e-06, | |
| "loss": 1.1798, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 1.4596273291925466, | |
| "grad_norm": 0.5085105895996094, | |
| "learning_rate": 1.6468708782607213e-06, | |
| "loss": 1.0451, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 1.4658385093167703, | |
| "grad_norm": 0.5479459166526794, | |
| "learning_rate": 1.6096950150405454e-06, | |
| "loss": 1.1467, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.4720496894409938, | |
| "grad_norm": 0.5029129981994629, | |
| "learning_rate": 1.572862888324801e-06, | |
| "loss": 1.1512, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 1.4782608695652173, | |
| "grad_norm": 0.4606218934059143, | |
| "learning_rate": 1.5363782324520033e-06, | |
| "loss": 1.1006, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 1.484472049689441, | |
| "grad_norm": 0.4794401526451111, | |
| "learning_rate": 1.5002447465312675e-06, | |
| "loss": 1.0808, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 1.4906832298136645, | |
| "grad_norm": 0.49627459049224854, | |
| "learning_rate": 1.4644660940672628e-06, | |
| "loss": 1.1399, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 1.4968944099378882, | |
| "grad_norm": 0.5150241851806641, | |
| "learning_rate": 1.4290459025887771e-06, | |
| "loss": 1.1315, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.5031055900621118, | |
| "grad_norm": 0.5009984374046326, | |
| "learning_rate": 1.3939877632809279e-06, | |
| "loss": 1.1501, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.5031055900621118, | |
| "eval_loss": 1.1153790950775146, | |
| "eval_runtime": 26.9095, | |
| "eval_samples_per_second": 2.936, | |
| "eval_steps_per_second": 0.372, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 1.5093167701863353, | |
| "grad_norm": 0.5049424767494202, | |
| "learning_rate": 1.3592952306210589e-06, | |
| "loss": 1.1243, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 1.515527950310559, | |
| "grad_norm": 0.5412471890449524, | |
| "learning_rate": 1.3249718220183583e-06, | |
| "loss": 1.1214, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 1.5217391304347827, | |
| "grad_norm": 0.5261203050613403, | |
| "learning_rate": 1.2910210174572346e-06, | |
| "loss": 1.0369, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 1.5279503105590062, | |
| "grad_norm": 0.47771474719047546, | |
| "learning_rate": 1.257446259144494e-06, | |
| "loss": 1.0598, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.5341614906832297, | |
| "grad_norm": 0.4789620339870453, | |
| "learning_rate": 1.2242509511603318e-06, | |
| "loss": 1.0653, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 1.5403726708074534, | |
| "grad_norm": 0.5012646317481995, | |
| "learning_rate": 1.1914384591132045e-06, | |
| "loss": 1.0909, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 1.5465838509316772, | |
| "grad_norm": 0.49552974104881287, | |
| "learning_rate": 1.159012109798598e-06, | |
| "loss": 1.1051, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 1.5527950310559007, | |
| "grad_norm": 0.48969194293022156, | |
| "learning_rate": 1.1269751908617277e-06, | |
| "loss": 1.2151, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.5590062111801242, | |
| "grad_norm": 0.5141896605491638, | |
| "learning_rate": 1.095330950464213e-06, | |
| "loss": 1.1452, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.5652173913043477, | |
| "grad_norm": 0.5273729562759399, | |
| "learning_rate": 1.0640825969547498e-06, | |
| "loss": 1.1325, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 0.5029155015945435, | |
| "learning_rate": 1.0332332985438248e-06, | |
| "loss": 1.0992, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 1.5776397515527951, | |
| "grad_norm": 0.47117024660110474, | |
| "learning_rate": 1.0027861829824953e-06, | |
| "loss": 1.1461, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 1.5838509316770186, | |
| "grad_norm": 0.4335295855998993, | |
| "learning_rate": 9.7274433724527e-07, | |
| "loss": 1.0592, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 1.5900621118012421, | |
| "grad_norm": 0.49043720960617065, | |
| "learning_rate": 9.431108072171346e-07, | |
| "loss": 1.1516, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.5962732919254659, | |
| "grad_norm": 0.5176280736923218, | |
| "learning_rate": 9.138885973847262e-07, | |
| "loss": 1.168, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 1.6024844720496896, | |
| "grad_norm": 0.4628904461860657, | |
| "learning_rate": 8.850806705317183e-07, | |
| "loss": 1.0914, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 1.608695652173913, | |
| "grad_norm": 0.4468037784099579, | |
| "learning_rate": 8.566899474384299e-07, | |
| "loss": 1.0685, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 1.6149068322981366, | |
| "grad_norm": 0.5194827318191528, | |
| "learning_rate": 8.287193065856936e-07, | |
| "loss": 1.1787, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.62111801242236, | |
| "grad_norm": 0.48394885659217834, | |
| "learning_rate": 8.011715838630107e-07, | |
| "loss": 1.2196, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.6273291925465838, | |
| "grad_norm": 0.486788809299469, | |
| "learning_rate": 7.740495722810271e-07, | |
| "loss": 1.1354, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 1.6335403726708075, | |
| "grad_norm": 0.5033959150314331, | |
| "learning_rate": 7.473560216883524e-07, | |
| "loss": 1.13, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 1.639751552795031, | |
| "grad_norm": 0.4517529606819153, | |
| "learning_rate": 7.210936384927631e-07, | |
| "loss": 1.1115, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 1.6459627329192545, | |
| "grad_norm": 0.5163289904594421, | |
| "learning_rate": 6.952650853867993e-07, | |
| "loss": 1.1724, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 1.6521739130434783, | |
| "grad_norm": 0.5138719081878662, | |
| "learning_rate": 6.698729810778065e-07, | |
| "loss": 1.1498, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.658385093167702, | |
| "grad_norm": 0.5368619561195374, | |
| "learning_rate": 6.449199000224221e-07, | |
| "loss": 1.1271, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 1.6645962732919255, | |
| "grad_norm": 0.46004772186279297, | |
| "learning_rate": 6.204083721655607e-07, | |
| "loss": 1.0344, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 1.670807453416149, | |
| "grad_norm": 0.4616802930831909, | |
| "learning_rate": 5.963408826839079e-07, | |
| "loss": 1.1346, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.6770186335403725, | |
| "grad_norm": 0.514466404914856, | |
| "learning_rate": 5.727198717339511e-07, | |
| "loss": 1.1606, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 1.6832298136645962, | |
| "grad_norm": 0.4969620406627655, | |
| "learning_rate": 5.49547734204578e-07, | |
| "loss": 1.0281, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.68944099378882, | |
| "grad_norm": 0.5189189314842224, | |
| "learning_rate": 5.268268194742638e-07, | |
| "loss": 1.1554, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 1.6956521739130435, | |
| "grad_norm": 0.49855127930641174, | |
| "learning_rate": 5.045594311728708e-07, | |
| "loss": 1.1224, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 1.701863354037267, | |
| "grad_norm": 0.4984905421733856, | |
| "learning_rate": 4.827478269480895e-07, | |
| "loss": 1.0951, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 1.7080745341614907, | |
| "grad_norm": 0.5486929416656494, | |
| "learning_rate": 4.6139421823653716e-07, | |
| "loss": 1.1237, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.4911029636859894, | |
| "learning_rate": 4.405007700395497e-07, | |
| "loss": 1.0601, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.720496894409938, | |
| "grad_norm": 0.4640960991382599, | |
| "learning_rate": 4.200696007036703e-07, | |
| "loss": 1.059, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 1.7267080745341614, | |
| "grad_norm": 0.48524951934814453, | |
| "learning_rate": 4.001027817058789e-07, | |
| "loss": 1.1238, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 1.7329192546583851, | |
| "grad_norm": 0.46812015771865845, | |
| "learning_rate": 3.8060233744356634e-07, | |
| "loss": 1.2098, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 1.7391304347826086, | |
| "grad_norm": 0.4788132309913635, | |
| "learning_rate": 3.615702450292857e-07, | |
| "loss": 1.1629, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 1.7453416149068324, | |
| "grad_norm": 0.47269925475120544, | |
| "learning_rate": 3.430084340902973e-07, | |
| "loss": 1.1628, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.7515527950310559, | |
| "grad_norm": 0.5449272394180298, | |
| "learning_rate": 3.2491878657292643e-07, | |
| "loss": 1.1587, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 1.7577639751552794, | |
| "grad_norm": 0.46690839529037476, | |
| "learning_rate": 3.0730313655175647e-07, | |
| "loss": 1.2015, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.7577639751552794, | |
| "eval_loss": 1.1139311790466309, | |
| "eval_runtime": 27.0876, | |
| "eval_samples_per_second": 2.916, | |
| "eval_steps_per_second": 0.369, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 1.763975155279503, | |
| "grad_norm": 0.570745050907135, | |
| "learning_rate": 2.901632700436757e-07, | |
| "loss": 1.1747, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 1.7701863354037268, | |
| "grad_norm": 0.5287693738937378, | |
| "learning_rate": 2.7350092482679836e-07, | |
| "loss": 1.0633, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 1.7763975155279503, | |
| "grad_norm": 0.4709635376930237, | |
| "learning_rate": 2.573177902642726e-07, | |
| "loss": 1.1393, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.7826086956521738, | |
| "grad_norm": 0.49392980337142944, | |
| "learning_rate": 2.416155071329973e-07, | |
| "loss": 1.0933, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 1.7888198757763976, | |
| "grad_norm": 0.5224959850311279, | |
| "learning_rate": 2.2639566745727203e-07, | |
| "loss": 1.1316, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 1.795031055900621, | |
| "grad_norm": 0.4887482821941376, | |
| "learning_rate": 2.1165981434738025e-07, | |
| "loss": 1.1066, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 1.8012422360248448, | |
| "grad_norm": 0.4881725013256073, | |
| "learning_rate": 1.9740944184313882e-07, | |
| "loss": 1.032, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 1.8074534161490683, | |
| "grad_norm": 0.47561758756637573, | |
| "learning_rate": 1.8364599476241862e-07, | |
| "loss": 1.1154, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.8136645962732918, | |
| "grad_norm": 0.4982871413230896, | |
| "learning_rate": 1.7037086855465902e-07, | |
| "loss": 1.1942, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 1.8198757763975155, | |
| "grad_norm": 0.7219922542572021, | |
| "learning_rate": 1.575854091593837e-07, | |
| "loss": 1.0776, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 1.8260869565217392, | |
| "grad_norm": 0.5696266293525696, | |
| "learning_rate": 1.4529091286973994e-07, | |
| "loss": 1.1663, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 1.8322981366459627, | |
| "grad_norm": 0.45875245332717896, | |
| "learning_rate": 1.3348862620107038e-07, | |
| "loss": 1.1009, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 1.8385093167701863, | |
| "grad_norm": 0.4918197989463806, | |
| "learning_rate": 1.2217974576453072e-07, | |
| "loss": 1.1357, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.84472049689441, | |
| "grad_norm": 0.5131499171257019, | |
| "learning_rate": 1.1136541814576574e-07, | |
| "loss": 1.1376, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 1.8509316770186337, | |
| "grad_norm": 0.49699532985687256, | |
| "learning_rate": 1.0104673978866164e-07, | |
| "loss": 1.231, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 0.5739893913269043, | |
| "learning_rate": 9.122475688417954e-08, | |
| "loss": 1.1645, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 1.8633540372670807, | |
| "grad_norm": 0.4959266781806946, | |
| "learning_rate": 8.190046526428241e-08, | |
| "loss": 1.1419, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 1.8695652173913042, | |
| "grad_norm": 0.5045937299728394, | |
| "learning_rate": 7.307481030097152e-08, | |
| "loss": 1.1859, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.875776397515528, | |
| "grad_norm": 0.47639361023902893, | |
| "learning_rate": 6.474868681043578e-08, | |
| "loss": 1.1026, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 1.8819875776397517, | |
| "grad_norm": 0.5153087973594666, | |
| "learning_rate": 5.6922938962329364e-08, | |
| "loss": 1.1612, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 1.8881987577639752, | |
| "grad_norm": 0.4941299855709076, | |
| "learning_rate": 4.959836019417963e-08, | |
| "loss": 1.0876, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 1.8944099378881987, | |
| "grad_norm": 0.4527961015701294, | |
| "learning_rate": 4.2775693130948094e-08, | |
| "loss": 1.1657, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 1.9006211180124224, | |
| "grad_norm": 0.49893486499786377, | |
| "learning_rate": 3.645562950973014e-08, | |
| "loss": 1.1261, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.9068322981366461, | |
| "grad_norm": 0.498981773853302, | |
| "learning_rate": 3.063881010962611e-08, | |
| "loss": 1.1179, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 1.9130434782608696, | |
| "grad_norm": 0.5112736225128174, | |
| "learning_rate": 2.5325824686772138e-08, | |
| "loss": 1.1863, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.9192546583850931, | |
| "grad_norm": 0.539107620716095, | |
| "learning_rate": 2.0517211914545254e-08, | |
| "loss": 1.0501, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 1.9254658385093166, | |
| "grad_norm": 0.514134407043457, | |
| "learning_rate": 1.6213459328950355e-08, | |
| "loss": 1.1264, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 1.9316770186335404, | |
| "grad_norm": 0.5193644165992737, | |
| "learning_rate": 1.2415003279186988e-08, | |
| "loss": 1.1484, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.937888198757764, | |
| "grad_norm": 0.4869459867477417, | |
| "learning_rate": 9.12222888341252e-09, | |
| "loss": 1.1454, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 1.9440993788819876, | |
| "grad_norm": 0.4767916798591614, | |
| "learning_rate": 6.335469989692255e-09, | |
| "loss": 1.2203, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 1.950310559006211, | |
| "grad_norm": 0.5365714430809021, | |
| "learning_rate": 4.055009142152066e-09, | |
| "loss": 1.252, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 1.9565217391304348, | |
| "grad_norm": 0.4672715961933136, | |
| "learning_rate": 2.2810775523329775e-09, | |
| "loss": 1.134, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 1.9627329192546585, | |
| "grad_norm": 0.45685145258903503, | |
| "learning_rate": 1.0138550757493592e-09, | |
| "loss": 1.1381, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.968944099378882, | |
| "grad_norm": 0.49931174516677856, | |
| "learning_rate": 2.534701936512951e-10, | |
| "loss": 1.1142, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 1.9751552795031055, | |
| "grad_norm": 0.4903966188430786, | |
| "learning_rate": 0.0, | |
| "loss": 1.0961, | |
| "step": 322 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 322, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 81, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7811992452614062e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |