| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03932698421021584, | |
| "eval_steps": 500, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018352592631434058, | |
| "grad_norm": 6.3117218017578125, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 1.3791, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00036705185262868117, | |
| "grad_norm": 2.600785255432129, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.2643, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005505777789430217, | |
| "grad_norm": 0.2835376560688019, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0565, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007341037052573623, | |
| "grad_norm": 0.10635749995708466, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.0706, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0009176296315717029, | |
| "grad_norm": 1.4374091625213623, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0657, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0011011555578860435, | |
| "grad_norm": 2.8197357654571533, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.0532, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0012846814842003842, | |
| "grad_norm": 3.916447877883911, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.0308, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0014682074105147247, | |
| "grad_norm": 6.559009552001953, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0369, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0016517333368290654, | |
| "grad_norm": 1.6039685010910034, | |
| "learning_rate": 6.3e-05, | |
| "loss": 0.0236, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0018352592631434058, | |
| "grad_norm": 10.057470321655273, | |
| "learning_rate": 7e-05, | |
| "loss": 0.064, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0020187851894577463, | |
| "grad_norm": 26.96637535095215, | |
| "learning_rate": 7.7e-05, | |
| "loss": 0.0906, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.002202311115772087, | |
| "grad_norm": 1.050362467765808, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0707, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0023858370420864277, | |
| "grad_norm": 4.492347240447998, | |
| "learning_rate": 9.1e-05, | |
| "loss": 0.0583, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.0025693629684007684, | |
| "grad_norm": 6.358117580413818, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.067, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.0027528888947151086, | |
| "grad_norm": 5.182433605194092, | |
| "learning_rate": 9.999685283773504e-05, | |
| "loss": 0.2084, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.0029364148210294493, | |
| "grad_norm": 5.367171764373779, | |
| "learning_rate": 9.998187325055106e-05, | |
| "loss": 0.1108, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.00311994074734379, | |
| "grad_norm": 1.7939116954803467, | |
| "learning_rate": 9.995456138403733e-05, | |
| "loss": 0.0369, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.0033034666736581307, | |
| "grad_norm": 0.6074697375297546, | |
| "learning_rate": 9.991492397698826e-05, | |
| "loss": 0.064, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.003486992599972471, | |
| "grad_norm": 2.814542770385742, | |
| "learning_rate": 9.986297080934089e-05, | |
| "loss": 0.1008, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.0036705185262868117, | |
| "grad_norm": 5.787035942077637, | |
| "learning_rate": 9.979871469976196e-05, | |
| "loss": 0.0465, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0038540444526011523, | |
| "grad_norm": 7.020626068115234, | |
| "learning_rate": 9.972217150248503e-05, | |
| "loss": 0.1523, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.004037570378915493, | |
| "grad_norm": 27.655929565429688, | |
| "learning_rate": 9.963336010339868e-05, | |
| "loss": 0.0449, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.004221096305229833, | |
| "grad_norm": 43.63124465942383, | |
| "learning_rate": 9.953230241538674e-05, | |
| "loss": 0.0855, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.004404622231544174, | |
| "grad_norm": 7.2519211769104, | |
| "learning_rate": 9.941902337292155e-05, | |
| "loss": 0.0665, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.004588148157858515, | |
| "grad_norm": 4.373692512512207, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1223, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.004771674084172855, | |
| "grad_norm": 3.619549512863159, | |
| "learning_rate": 9.915591603280631e-05, | |
| "loss": 0.0416, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.004955200010487196, | |
| "grad_norm": 2.198378324508667, | |
| "learning_rate": 9.900615265295552e-05, | |
| "loss": 0.1072, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.005138725936801537, | |
| "grad_norm": 8.324142456054688, | |
| "learning_rate": 9.884429773823239e-05, | |
| "loss": 0.0479, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.005322251863115877, | |
| "grad_norm": 8.378353118896484, | |
| "learning_rate": 9.867039122391527e-05, | |
| "loss": 0.0778, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.005505777789430217, | |
| "grad_norm": 1.1520366668701172, | |
| "learning_rate": 9.848447601883435e-05, | |
| "loss": 0.0138, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.005689303715744558, | |
| "grad_norm": 11.729530334472656, | |
| "learning_rate": 9.828659799478456e-05, | |
| "loss": 0.0723, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.005872829642058899, | |
| "grad_norm": 42.59210205078125, | |
| "learning_rate": 9.807680597520746e-05, | |
| "loss": 0.2053, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.006056355568373239, | |
| "grad_norm": 5.65015172958374, | |
| "learning_rate": 9.785515172314463e-05, | |
| "loss": 0.0846, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.00623988149468758, | |
| "grad_norm": 5.274237155914307, | |
| "learning_rate": 9.762168992846614e-05, | |
| "loss": 0.0548, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.006423407421001921, | |
| "grad_norm": 4.7061333656311035, | |
| "learning_rate": 9.737647819437645e-05, | |
| "loss": 0.021, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.006606933347316261, | |
| "grad_norm": 0.0789986327290535, | |
| "learning_rate": 9.711957702320175e-05, | |
| "loss": 0.0621, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.006790459273630601, | |
| "grad_norm": 26.16635513305664, | |
| "learning_rate": 9.685104980146193e-05, | |
| "loss": 0.07, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.006973985199944942, | |
| "grad_norm": 9.659036636352539, | |
| "learning_rate": 9.657096278423093e-05, | |
| "loss": 0.0952, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.007157511126259283, | |
| "grad_norm": 8.012511253356934, | |
| "learning_rate": 9.627938507878917e-05, | |
| "loss": 0.0412, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.007341037052573623, | |
| "grad_norm": 1.9756983518600464, | |
| "learning_rate": 9.597638862757255e-05, | |
| "loss": 0.0387, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.007524562978887964, | |
| "grad_norm": 13.931029319763184, | |
| "learning_rate": 9.566204819042152e-05, | |
| "loss": 0.2204, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.007708088905202305, | |
| "grad_norm": 9.124067306518555, | |
| "learning_rate": 9.533644132613541e-05, | |
| "loss": 0.0479, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.007891614831516645, | |
| "grad_norm": 8.203433990478516, | |
| "learning_rate": 9.49996483733358e-05, | |
| "loss": 0.038, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.008075140757830985, | |
| "grad_norm": 14.49701976776123, | |
| "learning_rate": 9.465175243064428e-05, | |
| "loss": 0.1173, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.008258666684145327, | |
| "grad_norm": 12.1497163772583, | |
| "learning_rate": 9.4292839336179e-05, | |
| "loss": 0.5881, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.008442192610459667, | |
| "grad_norm": 1.9857338666915894, | |
| "learning_rate": 9.39229976463755e-05, | |
| "loss": 0.0714, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.008625718536774008, | |
| "grad_norm": 6.0610151290893555, | |
| "learning_rate": 9.354231861413668e-05, | |
| "loss": 0.0567, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.008809244463088348, | |
| "grad_norm": 9.057708740234375, | |
| "learning_rate": 9.315089616631752e-05, | |
| "loss": 0.073, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.008992770389402688, | |
| "grad_norm": 3.3271257877349854, | |
| "learning_rate": 9.274882688055005e-05, | |
| "loss": 0.034, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.00917629631571703, | |
| "grad_norm": 3.928396701812744, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0393, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.00935982224203137, | |
| "grad_norm": 15.419633865356445, | |
| "learning_rate": 9.191314721596072e-05, | |
| "loss": 0.1113, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.00954334816834571, | |
| "grad_norm": 13.88370418548584, | |
| "learning_rate": 9.147974302859157e-05, | |
| "loss": 0.1967, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.00972687409466005, | |
| "grad_norm": 52.43412780761719, | |
| "learning_rate": 9.103610433530483e-05, | |
| "loss": 0.412, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.009910400020974392, | |
| "grad_norm": 17.925010681152344, | |
| "learning_rate": 9.058234059730976e-05, | |
| "loss": 0.0833, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.010093925947288732, | |
| "grad_norm": 11.497563362121582, | |
| "learning_rate": 9.01185637740189e-05, | |
| "loss": 0.1545, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.010277451873603074, | |
| "grad_norm": 1.4290711879730225, | |
| "learning_rate": 8.964488829542377e-05, | |
| "loss": 0.0297, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.010460977799917413, | |
| "grad_norm": 0.6557618975639343, | |
| "learning_rate": 8.916143103386093e-05, | |
| "loss": 0.0612, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.010644503726231753, | |
| "grad_norm": 15.241708755493164, | |
| "learning_rate": 8.866831127517557e-05, | |
| "loss": 0.0615, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.010828029652546095, | |
| "grad_norm": 0.8321524858474731, | |
| "learning_rate": 8.81656506892894e-05, | |
| "loss": 0.0363, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.011011555578860435, | |
| "grad_norm": 7.561135292053223, | |
| "learning_rate": 8.765357330018056e-05, | |
| "loss": 0.0542, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.011195081505174776, | |
| "grad_norm": 0.6955423355102539, | |
| "learning_rate": 8.71322054552824e-05, | |
| "loss": 0.0222, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.011378607431489116, | |
| "grad_norm": 3.8866684436798096, | |
| "learning_rate": 8.660167579430927e-05, | |
| "loss": 0.0324, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.011562133357803457, | |
| "grad_norm": 13.728404998779297, | |
| "learning_rate": 8.606211521751652e-05, | |
| "loss": 0.0835, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.011745659284117797, | |
| "grad_norm": 18.460779190063477, | |
| "learning_rate": 8.551365685340285e-05, | |
| "loss": 0.0668, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.011929185210432139, | |
| "grad_norm": 11.145697593688965, | |
| "learning_rate": 8.495643602586287e-05, | |
| "loss": 0.2785, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.012112711136746479, | |
| "grad_norm": 5.782137870788574, | |
| "learning_rate": 8.439059022079789e-05, | |
| "loss": 0.0965, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.012296237063060819, | |
| "grad_norm": 4.491423606872559, | |
| "learning_rate": 8.381625905219339e-05, | |
| "loss": 0.0161, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.01247976298937516, | |
| "grad_norm": 2.3955559730529785, | |
| "learning_rate": 8.32335842276713e-05, | |
| "loss": 0.0453, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.0126632889156895, | |
| "grad_norm": 5.535737991333008, | |
| "learning_rate": 8.264270951352581e-05, | |
| "loss": 0.0626, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.012846814842003841, | |
| "grad_norm": 16.16122817993164, | |
| "learning_rate": 8.20437806992512e-05, | |
| "loss": 0.0823, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.013030340768318181, | |
| "grad_norm": 7.036065101623535, | |
| "learning_rate": 8.143694556157046e-05, | |
| "loss": 0.0595, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.013213866694632523, | |
| "grad_norm": 12.481003761291504, | |
| "learning_rate": 8.082235382797349e-05, | |
| "loss": 0.046, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.013397392620946863, | |
| "grad_norm": 12.709206581115723, | |
| "learning_rate": 8.020015713977427e-05, | |
| "loss": 0.0443, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.013580918547261202, | |
| "grad_norm": 8.762887001037598, | |
| "learning_rate": 7.957050901469545e-05, | |
| "loss": 0.0859, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.013764444473575544, | |
| "grad_norm": 4.909962177276611, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.0304, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.013947970399889884, | |
| "grad_norm": 53.53133773803711, | |
| "learning_rate": 7.828948167911074e-05, | |
| "loss": 0.0384, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.014131496326204225, | |
| "grad_norm": 7.125665664672852, | |
| "learning_rate": 7.763841854293145e-05, | |
| "loss": 0.0371, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.014315022252518565, | |
| "grad_norm": 5.672843933105469, | |
| "learning_rate": 7.698053604053922e-05, | |
| "loss": 0.073, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.014498548178832907, | |
| "grad_norm": 4.972446918487549, | |
| "learning_rate": 7.631599649459744e-05, | |
| "loss": 0.0681, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.014682074105147247, | |
| "grad_norm": 40.443214416503906, | |
| "learning_rate": 7.564496387029532e-05, | |
| "loss": 0.0528, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.014865600031461588, | |
| "grad_norm": 5.652285099029541, | |
| "learning_rate": 7.496760373489202e-05, | |
| "loss": 0.0849, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.015049125957775928, | |
| "grad_norm": 4.100184917449951, | |
| "learning_rate": 7.428408321686541e-05, | |
| "loss": 0.0595, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.015232651884090268, | |
| "grad_norm": 5.924082279205322, | |
| "learning_rate": 7.35945709646756e-05, | |
| "loss": 0.0402, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.01541617781040461, | |
| "grad_norm": 3.973080635070801, | |
| "learning_rate": 7.289923710515339e-05, | |
| "loss": 0.0631, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.01559970373671895, | |
| "grad_norm": 6.043672561645508, | |
| "learning_rate": 7.219825320152411e-05, | |
| "loss": 0.0612, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.01578322966303329, | |
| "grad_norm": 23.230714797973633, | |
| "learning_rate": 7.149179221107694e-05, | |
| "loss": 0.0552, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.015966755589347632, | |
| "grad_norm": 11.104944229125977, | |
| "learning_rate": 7.078002844249032e-05, | |
| "loss": 0.0252, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.01615028151566197, | |
| "grad_norm": 31.511911392211914, | |
| "learning_rate": 7.006313751282372e-05, | |
| "loss": 0.0974, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.016333807441976312, | |
| "grad_norm": 1.653994083404541, | |
| "learning_rate": 6.934129630418701e-05, | |
| "loss": 0.034, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.016517333368290654, | |
| "grad_norm": 5.44677209854126, | |
| "learning_rate": 6.861468292009727e-05, | |
| "loss": 0.1175, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.01670085929460499, | |
| "grad_norm": 17.435009002685547, | |
| "learning_rate": 6.788347664153447e-05, | |
| "loss": 0.0717, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.016884385220919333, | |
| "grad_norm": 25.111541748046875, | |
| "learning_rate": 6.714785788270658e-05, | |
| "loss": 0.0931, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.017067911147233675, | |
| "grad_norm": 16.484365463256836, | |
| "learning_rate": 6.640800814653503e-05, | |
| "loss": 0.0241, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.017251437073548016, | |
| "grad_norm": 4.067661285400391, | |
| "learning_rate": 6.566410997987163e-05, | |
| "loss": 0.0516, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.017434962999862354, | |
| "grad_norm": 1.4263770580291748, | |
| "learning_rate": 6.49163469284578e-05, | |
| "loss": 0.0188, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.017618488926176696, | |
| "grad_norm": 0.4355856478214264, | |
| "learning_rate": 6.416490349163748e-05, | |
| "loss": 0.0704, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.017802014852491038, | |
| "grad_norm": 3.417959213256836, | |
| "learning_rate": 6.340996507683458e-05, | |
| "loss": 0.0902, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.017985540778805376, | |
| "grad_norm": 0.19045788049697876, | |
| "learning_rate": 6.265171795380659e-05, | |
| "loss": 0.0745, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.018169066705119717, | |
| "grad_norm": 52.73567199707031, | |
| "learning_rate": 6.189034920868522e-05, | |
| "loss": 0.0481, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.01835259263143406, | |
| "grad_norm": 10.482780456542969, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0798, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.0185361185577484, | |
| "grad_norm": 0.6400662660598755, | |
| "learning_rate": 6.0358999001406156e-05, | |
| "loss": 0.0277, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 0.01871964448406274, | |
| "grad_norm": 16.048450469970703, | |
| "learning_rate": 5.9589395376998e-05, | |
| "loss": 0.0459, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.01890317041037708, | |
| "grad_norm": 7.567919731140137, | |
| "learning_rate": 5.8817425712769794e-05, | |
| "loss": 0.0304, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 0.01908669633669142, | |
| "grad_norm": 2.94071626663208, | |
| "learning_rate": 5.804328048068492e-05, | |
| "loss": 0.0598, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.019270222263005763, | |
| "grad_norm": 1.3117618560791016, | |
| "learning_rate": 5.7267150689495644e-05, | |
| "loss": 0.0166, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.0194537481893201, | |
| "grad_norm": 16.543682098388672, | |
| "learning_rate": 5.648922783761443e-05, | |
| "loss": 0.0087, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.019637274115634443, | |
| "grad_norm": 21.542856216430664, | |
| "learning_rate": 5.570970386586469e-05, | |
| "loss": 0.0414, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 0.019820800041948784, | |
| "grad_norm": 4.565967082977295, | |
| "learning_rate": 5.492877111012218e-05, | |
| "loss": 0.023, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.020004325968263122, | |
| "grad_norm": 17.27544593811035, | |
| "learning_rate": 5.414662225385903e-05, | |
| "loss": 0.0472, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 0.020187851894577464, | |
| "grad_norm": 7.022396087646484, | |
| "learning_rate": 5.336345028060199e-05, | |
| "loss": 0.0379, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.020371377820891805, | |
| "grad_norm": 10.918366432189941, | |
| "learning_rate": 5.257944842631658e-05, | |
| "loss": 0.0228, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.020554903747206147, | |
| "grad_norm": 10.15198802947998, | |
| "learning_rate": 5.179481013172912e-05, | |
| "loss": 0.0631, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.020738429673520485, | |
| "grad_norm": 1.512853741645813, | |
| "learning_rate": 5.100972899459796e-05, | |
| "loss": 0.0047, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 0.020921955599834827, | |
| "grad_norm": 5.792972564697266, | |
| "learning_rate": 5.022439872194629e-05, | |
| "loss": 0.024, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.021105481526149168, | |
| "grad_norm": 1.3428311347961426, | |
| "learning_rate": 4.943901308226771e-05, | |
| "loss": 0.0241, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.021289007452463506, | |
| "grad_norm": 0.24871955811977386, | |
| "learning_rate": 4.865376585771687e-05, | |
| "loss": 0.0408, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.021472533378777848, | |
| "grad_norm": 1.912901759147644, | |
| "learning_rate": 4.7868850796296495e-05, | |
| "loss": 0.0273, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 0.02165605930509219, | |
| "grad_norm": 2.7074570655822754, | |
| "learning_rate": 4.708446156405307e-05, | |
| "loss": 0.043, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.02183958523140653, | |
| "grad_norm": 2.9339606761932373, | |
| "learning_rate": 4.630079169729257e-05, | |
| "loss": 0.0389, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 0.02202311115772087, | |
| "grad_norm": 9.8698091506958, | |
| "learning_rate": 4.551803455482833e-05, | |
| "loss": 0.0166, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.02220663708403521, | |
| "grad_norm": 1.908019781112671, | |
| "learning_rate": 4.473638327027259e-05, | |
| "loss": 0.0115, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 0.022390163010349552, | |
| "grad_norm": 4.707207679748535, | |
| "learning_rate": 4.395603070438373e-05, | |
| "loss": 0.0185, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.02257368893666389, | |
| "grad_norm": 6.587421417236328, | |
| "learning_rate": 4.31771693974807e-05, | |
| "loss": 0.0469, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 0.022757214862978232, | |
| "grad_norm": 2.0711984634399414, | |
| "learning_rate": 4.239999152193664e-05, | |
| "loss": 0.0543, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.022940740789292573, | |
| "grad_norm": 275.3908996582031, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.1184, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.023124266715606915, | |
| "grad_norm": 0.8165872693061829, | |
| "learning_rate": 4.085145263029726e-05, | |
| "loss": 0.0206, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.023307792641921253, | |
| "grad_norm": 0.032993383705616, | |
| "learning_rate": 4.008047369300218e-05, | |
| "loss": 0.0115, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 0.023491318568235595, | |
| "grad_norm": 1.4026904106140137, | |
| "learning_rate": 3.9311942250394276e-05, | |
| "loss": 0.0053, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.023674844494549936, | |
| "grad_norm": 1.8072174787521362, | |
| "learning_rate": 3.8546047926107256e-05, | |
| "loss": 0.0033, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.023858370420864278, | |
| "grad_norm": 0.23341313004493713, | |
| "learning_rate": 3.778297969310529e-05, | |
| "loss": 0.0495, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.024041896347178616, | |
| "grad_norm": 0.19453687965869904, | |
| "learning_rate": 3.7022925827056884e-05, | |
| "loss": 0.0435, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 0.024225422273492957, | |
| "grad_norm": 12.686004638671875, | |
| "learning_rate": 3.62660738598805e-05, | |
| "loss": 0.0385, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.0244089481998073, | |
| "grad_norm": 0.022196639329195023, | |
| "learning_rate": 3.551261053347404e-05, | |
| "loss": 0.0305, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 0.024592474126121637, | |
| "grad_norm": 2.3748865127563477, | |
| "learning_rate": 3.4762721753638995e-05, | |
| "loss": 0.0169, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.02477600005243598, | |
| "grad_norm": 3.813014268875122, | |
| "learning_rate": 3.401659254421094e-05, | |
| "loss": 0.0054, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.02495952597875032, | |
| "grad_norm": 1.4644575119018555, | |
| "learning_rate": 3.3274407001407735e-05, | |
| "loss": 0.0152, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 0.02514305190506466, | |
| "grad_norm": 16.26466941833496, | |
| "learning_rate": 3.2536348248406534e-05, | |
| "loss": 0.0186, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 0.025326577831379, | |
| "grad_norm": 1.4943578243255615, | |
| "learning_rate": 3.1802598390160784e-05, | |
| "loss": 0.0614, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.02551010375769334, | |
| "grad_norm": 0.06556755304336548, | |
| "learning_rate": 3.107333846846872e-05, | |
| "loss": 0.0132, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 0.025693629684007683, | |
| "grad_norm": 0.04227546602487564, | |
| "learning_rate": 3.0348748417303823e-05, | |
| "loss": 0.0114, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.02587715561032202, | |
| "grad_norm": 7.547623157501221, | |
| "learning_rate": 2.9629007018418985e-05, | |
| "loss": 0.0064, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 0.026060681536636363, | |
| "grad_norm": 0.793245255947113, | |
| "learning_rate": 2.8914291857234636e-05, | |
| "loss": 0.0206, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 0.026244207462950704, | |
| "grad_norm": 0.18259727954864502, | |
| "learning_rate": 2.8204779279022276e-05, | |
| "loss": 0.0022, | |
| "step": 1001 | |
| }, | |
| { | |
| "epoch": 0.026427733389265046, | |
| "grad_norm": 11.862234115600586, | |
| "learning_rate": 2.7500644345393943e-05, | |
| "loss": 0.0177, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 0.026611259315579384, | |
| "grad_norm": 2.59283185005188, | |
| "learning_rate": 2.68020607911083e-05, | |
| "loss": 0.0278, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.026794785241893725, | |
| "grad_norm": 0.04772788658738136, | |
| "learning_rate": 2.610920098120424e-05, | |
| "loss": 0.0181, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 0.026978311168208067, | |
| "grad_norm": 0.016560537740588188, | |
| "learning_rate": 2.5422235868472345e-05, | |
| "loss": 0.0098, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 0.027161837094522405, | |
| "grad_norm": 0.38349756598472595, | |
| "learning_rate": 2.4741334951274947e-05, | |
| "loss": 0.0251, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 0.027345363020836747, | |
| "grad_norm": 0.31784552335739136, | |
| "learning_rate": 2.40666662317248e-05, | |
| "loss": 0.08, | |
| "step": 1043 | |
| }, | |
| { | |
| "epoch": 0.027528888947151088, | |
| "grad_norm": 0.3511944115161896, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0017, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.02771241487346543, | |
| "grad_norm": 0.11994984745979309, | |
| "learning_rate": 2.2736689664437217e-05, | |
| "loss": 0.0158, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 0.027895940799779768, | |
| "grad_norm": 0.1353398561477661, | |
| "learning_rate": 2.2081709968516866e-05, | |
| "loss": 0.0318, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 0.02807946672609411, | |
| "grad_norm": 0.10267901420593262, | |
| "learning_rate": 2.1433618692911467e-05, | |
| "loss": 0.03, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 0.02826299265240845, | |
| "grad_norm": 0.787115216255188, | |
| "learning_rate": 2.0792575744445653e-05, | |
| "loss": 0.009, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 0.02844651857872279, | |
| "grad_norm": 6.143826484680176, | |
| "learning_rate": 2.015873929087482e-05, | |
| "loss": 0.0432, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.02863004450503713, | |
| "grad_norm": 0.05623776093125343, | |
| "learning_rate": 1.95322657218596e-05, | |
| "loss": 0.0229, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 0.028813570431351472, | |
| "grad_norm": 1.2254972457885742, | |
| "learning_rate": 1.8913309610379015e-05, | |
| "loss": 0.0572, | |
| "step": 1099 | |
| }, | |
| { | |
| "epoch": 0.028997096357665814, | |
| "grad_norm": 0.01922564022243023, | |
| "learning_rate": 1.8302023674591935e-05, | |
| "loss": 0.0145, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 0.02918062228398015, | |
| "grad_norm": 0.03139118850231171, | |
| "learning_rate": 1.7698558740156135e-05, | |
| "loss": 0.0281, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 0.029364148210294493, | |
| "grad_norm": 8.748254776000977, | |
| "learning_rate": 1.7103063703014372e-05, | |
| "loss": 0.0191, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.029547674136608835, | |
| "grad_norm": 2.5039148330688477, | |
| "learning_rate": 1.6515685492656467e-05, | |
| "loss": 0.0017, | |
| "step": 1127 | |
| }, | |
| { | |
| "epoch": 0.029731200062923176, | |
| "grad_norm": 10.268917083740234, | |
| "learning_rate": 1.59365690358667e-05, | |
| "loss": 0.0144, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 0.029914725989237514, | |
| "grad_norm": 3.4766223430633545, | |
| "learning_rate": 1.5365857220965275e-05, | |
| "loss": 0.0035, | |
| "step": 1141 | |
| }, | |
| { | |
| "epoch": 0.030098251915551856, | |
| "grad_norm": 0.5243438482284546, | |
| "learning_rate": 1.4803690862552755e-05, | |
| "loss": 0.0042, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 0.030281777841866198, | |
| "grad_norm": 0.26499995589256287, | |
| "learning_rate": 1.4250208666766235e-05, | |
| "loss": 0.0028, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.030465303768180536, | |
| "grad_norm": 4.1601338386535645, | |
| "learning_rate": 1.3705547197055584e-05, | |
| "loss": 0.0495, | |
| "step": 1162 | |
| }, | |
| { | |
| "epoch": 0.030648829694494877, | |
| "grad_norm": 0.10166924446821213, | |
| "learning_rate": 1.3169840840488501e-05, | |
| "loss": 0.0124, | |
| "step": 1169 | |
| }, | |
| { | |
| "epoch": 0.03083235562080922, | |
| "grad_norm": 0.010529532097280025, | |
| "learning_rate": 1.2643221774592518e-05, | |
| "loss": 0.023, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 0.03101588154712356, | |
| "grad_norm": 8.22623062133789, | |
| "learning_rate": 1.2125819934742188e-05, | |
| "loss": 0.0436, | |
| "step": 1183 | |
| }, | |
| { | |
| "epoch": 0.0311994074734379, | |
| "grad_norm": 1.1787302494049072, | |
| "learning_rate": 1.1617762982099446e-05, | |
| "loss": 0.0118, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.03138293339975224, | |
| "grad_norm": 0.2951812744140625, | |
| "learning_rate": 1.1119176272115128e-05, | |
| "loss": 0.0233, | |
| "step": 1197 | |
| }, | |
| { | |
| "epoch": 0.03156645932606658, | |
| "grad_norm": 0.042958952486515045, | |
| "learning_rate": 1.0630182823599399e-05, | |
| "loss": 0.0024, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 0.03174998525238092, | |
| "grad_norm": 0.051287971436977386, | |
| "learning_rate": 1.0150903288368741e-05, | |
| "loss": 0.0034, | |
| "step": 1211 | |
| }, | |
| { | |
| "epoch": 0.031933511178695265, | |
| "grad_norm": 0.15109604597091675, | |
| "learning_rate": 9.681455921476839e-06, | |
| "loss": 0.0016, | |
| "step": 1218 | |
| }, | |
| { | |
| "epoch": 0.0321170371050096, | |
| "grad_norm": 4.658985137939453, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0049, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.03230056303132394, | |
| "grad_norm": 5.163771629333496, | |
| "learning_rate": 8.772518554642973e-06, | |
| "loss": 0.0078, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 0.03248408895763828, | |
| "grad_norm": 0.658769428730011, | |
| "learning_rate": 8.333252821395526e-06, | |
| "loss": 0.001, | |
| "step": 1239 | |
| }, | |
| { | |
| "epoch": 0.032667614883952624, | |
| "grad_norm": 0.03406643494963646, | |
| "learning_rate": 7.904267734541498e-06, | |
| "loss": 0.0025, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 0.032851140810266966, | |
| "grad_norm": 0.048391830176115036, | |
| "learning_rate": 7.485669139732004e-06, | |
| "loss": 0.0075, | |
| "step": 1253 | |
| }, | |
| { | |
| "epoch": 0.03303466673658131, | |
| "grad_norm": 0.02164422534406185, | |
| "learning_rate": 7.077560319906695e-06, | |
| "loss": 0.0101, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.03321819266289565, | |
| "grad_norm": 0.0323006734251976, | |
| "learning_rate": 6.680041969810203e-06, | |
| "loss": 0.0212, | |
| "step": 1267 | |
| }, | |
| { | |
| "epoch": 0.03340171858920998, | |
| "grad_norm": 0.01731325499713421, | |
| "learning_rate": 6.293212171147206e-06, | |
| "loss": 0.0005, | |
| "step": 1274 | |
| }, | |
| { | |
| "epoch": 0.033585244515524325, | |
| "grad_norm": 0.0469672717154026, | |
| "learning_rate": 5.917166368382277e-06, | |
| "loss": 0.0113, | |
| "step": 1281 | |
| }, | |
| { | |
| "epoch": 0.033768770441838666, | |
| "grad_norm": 0.5670210719108582, | |
| "learning_rate": 5.5519973451903405e-06, | |
| "loss": 0.0065, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 0.03395229636815301, | |
| "grad_norm": 0.6679732799530029, | |
| "learning_rate": 5.197795201563743e-06, | |
| "loss": 0.0009, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.03413582229446735, | |
| "grad_norm": 0.7266259789466858, | |
| "learning_rate": 4.8546473315813856e-06, | |
| "loss": 0.0004, | |
| "step": 1302 | |
| }, | |
| { | |
| "epoch": 0.03431934822078169, | |
| "grad_norm": 0.007858018390834332, | |
| "learning_rate": 4.522638401845547e-06, | |
| "loss": 0.0277, | |
| "step": 1309 | |
| }, | |
| { | |
| "epoch": 0.03450287414709603, | |
| "grad_norm": 4.2354326248168945, | |
| "learning_rate": 4.2018503305916775e-06, | |
| "loss": 0.0052, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 0.03468640007341037, | |
| "grad_norm": 36.58195495605469, | |
| "learning_rate": 3.892362267476313e-06, | |
| "loss": 0.0192, | |
| "step": 1323 | |
| }, | |
| { | |
| "epoch": 0.03486992599972471, | |
| "grad_norm": 0.05499963089823723, | |
| "learning_rate": 3.5942505740480582e-06, | |
| "loss": 0.0264, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.03505345192603905, | |
| "grad_norm": 0.2299686074256897, | |
| "learning_rate": 3.3075888049065196e-06, | |
| "loss": 0.0099, | |
| "step": 1337 | |
| }, | |
| { | |
| "epoch": 0.03523697785235339, | |
| "grad_norm": 0.014163389801979065, | |
| "learning_rate": 3.03244768955383e-06, | |
| "loss": 0.0014, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 0.035420503778667733, | |
| "grad_norm": 0.02343047223985195, | |
| "learning_rate": 2.7688951149431595e-06, | |
| "loss": 0.0061, | |
| "step": 1351 | |
| }, | |
| { | |
| "epoch": 0.035604029704982075, | |
| "grad_norm": 0.3476681709289551, | |
| "learning_rate": 2.5169961087286974e-06, | |
| "loss": 0.002, | |
| "step": 1358 | |
| }, | |
| { | |
| "epoch": 0.03578755563129642, | |
| "grad_norm": 0.07447517663240433, | |
| "learning_rate": 2.276812823220964e-06, | |
| "loss": 0.0029, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.03597108155761075, | |
| "grad_norm": 0.008758554235100746, | |
| "learning_rate": 2.048404520051722e-06, | |
| "loss": 0.0067, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 0.03615460748392509, | |
| "grad_norm": 0.46787765622138977, | |
| "learning_rate": 1.8318275555520237e-06, | |
| "loss": 0.0005, | |
| "step": 1379 | |
| }, | |
| { | |
| "epoch": 0.036338133410239434, | |
| "grad_norm": 0.024509649723768234, | |
| "learning_rate": 1.6271353668471655e-06, | |
| "loss": 0.0015, | |
| "step": 1386 | |
| }, | |
| { | |
| "epoch": 0.036521659336553776, | |
| "grad_norm": 0.01940271630883217, | |
| "learning_rate": 1.4343784586718311e-06, | |
| "loss": 0.0006, | |
| "step": 1393 | |
| }, | |
| { | |
| "epoch": 0.03670518526286812, | |
| "grad_norm": 0.1267419457435608, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0031, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.03688871118918246, | |
| "grad_norm": 1.5990060567855835, | |
| "learning_rate": 1.0848577668543802e-06, | |
| "loss": 0.0277, | |
| "step": 1407 | |
| }, | |
| { | |
| "epoch": 0.0370722371154968, | |
| "grad_norm": 7.815530300140381, | |
| "learning_rate": 9.281802222129765e-07, | |
| "loss": 0.0045, | |
| "step": 1414 | |
| }, | |
| { | |
| "epoch": 0.03725576304181114, | |
| "grad_norm": 0.020791860297322273, | |
| "learning_rate": 7.836104148243484e-07, | |
| "loss": 0.0009, | |
| "step": 1421 | |
| }, | |
| { | |
| "epoch": 0.03743928896812548, | |
| "grad_norm": 0.010349948890507221, | |
| "learning_rate": 6.511840151252169e-07, | |
| "loss": 0.002, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 0.03762281489443982, | |
| "grad_norm": 0.030976630747318268, | |
| "learning_rate": 5.309336973481683e-07, | |
| "loss": 0.0002, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.03780634082075416, | |
| "grad_norm": 0.06936094164848328, | |
| "learning_rate": 4.228891314597694e-07, | |
| "loss": 0.0003, | |
| "step": 1442 | |
| }, | |
| { | |
| "epoch": 0.0379898667470685, | |
| "grad_norm": 0.06425853073596954, | |
| "learning_rate": 3.2707697583995167e-07, | |
| "loss": 0.0004, | |
| "step": 1449 | |
| }, | |
| { | |
| "epoch": 0.03817339267338284, | |
| "grad_norm": 0.005400571506470442, | |
| "learning_rate": 2.4352087070443895e-07, | |
| "loss": 0.0066, | |
| "step": 1456 | |
| }, | |
| { | |
| "epoch": 0.038356918599697185, | |
| "grad_norm": 0.039011601358652115, | |
| "learning_rate": 1.7224143227190236e-07, | |
| "loss": 0.0081, | |
| "step": 1463 | |
| }, | |
| { | |
| "epoch": 0.038540444526011526, | |
| "grad_norm": 0.20835164189338684, | |
| "learning_rate": 1.132562476771959e-07, | |
| "loss": 0.0003, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.03872397045232586, | |
| "grad_norm": 1.4877870082855225, | |
| "learning_rate": 6.657987063200533e-08, | |
| "loss": 0.1775, | |
| "step": 1477 | |
| }, | |
| { | |
| "epoch": 0.0389074963786402, | |
| "grad_norm": 0.1349838227033615, | |
| "learning_rate": 3.2223817833931805e-08, | |
| "loss": 0.0009, | |
| "step": 1484 | |
| }, | |
| { | |
| "epoch": 0.039091022304954544, | |
| "grad_norm": 4.346598148345947, | |
| "learning_rate": 1.019656612492592e-08, | |
| "loss": 0.0038, | |
| "step": 1491 | |
| }, | |
| { | |
| "epoch": 0.039274548231268885, | |
| "grad_norm": 0.2060699611902237, | |
| "learning_rate": 5.035503997385949e-10, | |
| "loss": 0.0016, | |
| "step": 1498 | |
| } | |
| ], | |
| "logging_steps": 7, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.546484091060224e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |