| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 100, | |
| "global_step": 850, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.029411764705882353, | |
| "grad_norm": 7.394163236707443, | |
| "learning_rate": 1.1764705882352942e-06, | |
| "loss": 1.4868, | |
| "mean_token_accuracy": 0.670187404697577, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 4.989051492464897, | |
| "learning_rate": 2.3529411764705885e-06, | |
| "loss": 1.4548, | |
| "mean_token_accuracy": 0.6696601003430951, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08823529411764706, | |
| "grad_norm": 1.718958499756161, | |
| "learning_rate": 3.529411764705883e-06, | |
| "loss": 1.2494, | |
| "mean_token_accuracy": 0.6895946883758232, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 1.7334017715973813, | |
| "learning_rate": 4.705882352941177e-06, | |
| "loss": 1.1266, | |
| "mean_token_accuracy": 0.7048006769329966, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14705882352941177, | |
| "grad_norm": 0.764379154080371, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 1.0738, | |
| "mean_token_accuracy": 0.7112541876090825, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17647058823529413, | |
| "grad_norm": 0.5574786594203679, | |
| "learning_rate": 7.058823529411766e-06, | |
| "loss": 0.9891, | |
| "mean_token_accuracy": 0.7278180810901669, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20588235294117646, | |
| "grad_norm": 0.43685454872404356, | |
| "learning_rate": 8.23529411764706e-06, | |
| "loss": 0.9706, | |
| "mean_token_accuracy": 0.7296801992148935, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.3720554551518854, | |
| "learning_rate": 9.411764705882354e-06, | |
| "loss": 0.933, | |
| "mean_token_accuracy": 0.738009820036878, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2647058823529412, | |
| "grad_norm": 0.32483974488667805, | |
| "learning_rate": 1.0588235294117648e-05, | |
| "loss": 0.9158, | |
| "mean_token_accuracy": 0.7409755301059546, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 0.3218526340694397, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 0.9203, | |
| "mean_token_accuracy": 0.7389487349847822, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3235294117647059, | |
| "grad_norm": 0.3002154739759154, | |
| "learning_rate": 1.2941176470588238e-05, | |
| "loss": 0.8935, | |
| "mean_token_accuracy": 0.7449524112208951, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.30954774782779204, | |
| "learning_rate": 1.4117647058823532e-05, | |
| "loss": 0.8859, | |
| "mean_token_accuracy": 0.7456974429587235, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38235294117647056, | |
| "grad_norm": 0.31990114149137194, | |
| "learning_rate": 1.5294117647058822e-05, | |
| "loss": 0.8857, | |
| "mean_token_accuracy": 0.7454657299610173, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4117647058823529, | |
| "grad_norm": 0.29621110088082725, | |
| "learning_rate": 1.647058823529412e-05, | |
| "loss": 0.863, | |
| "mean_token_accuracy": 0.751065675239264, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4411764705882353, | |
| "grad_norm": 0.31927741229254775, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.8662, | |
| "mean_token_accuracy": 0.7495714356533111, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.3005392170981355, | |
| "learning_rate": 1.8823529411764708e-05, | |
| "loss": 0.8481, | |
| "mean_token_accuracy": 0.753874134893318, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.29730380637608206, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8395, | |
| "mean_token_accuracy": 0.755573912125712, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5294117647058824, | |
| "grad_norm": 0.3669506861420523, | |
| "learning_rate": 1.9997891995035914e-05, | |
| "loss": 0.8465, | |
| "mean_token_accuracy": 0.7536556086477052, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5588235294117647, | |
| "grad_norm": 0.29666794474782, | |
| "learning_rate": 1.999156886888064e-05, | |
| "loss": 0.8272, | |
| "mean_token_accuracy": 0.7588607737716251, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.30382605735837637, | |
| "learning_rate": 1.9981033287370443e-05, | |
| "loss": 0.8219, | |
| "mean_token_accuracy": 0.760143495941066, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6176470588235294, | |
| "grad_norm": 0.29012444795471226, | |
| "learning_rate": 1.9966289692316944e-05, | |
| "loss": 0.8311, | |
| "mean_token_accuracy": 0.7565005350426584, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6470588235294118, | |
| "grad_norm": 0.2912583936011533, | |
| "learning_rate": 1.9947344299634464e-05, | |
| "loss": 0.8222, | |
| "mean_token_accuracy": 0.7590272071446524, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6764705882352942, | |
| "grad_norm": 0.30772503851162025, | |
| "learning_rate": 1.992420509671936e-05, | |
| "loss": 0.82, | |
| "mean_token_accuracy": 0.7592413729046079, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.37056353510208045, | |
| "learning_rate": 1.9896881839082554e-05, | |
| "loss": 0.8212, | |
| "mean_token_accuracy": 0.759279812103064, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7352941176470589, | |
| "grad_norm": 0.29893908828157484, | |
| "learning_rate": 1.9865386046236597e-05, | |
| "loss": 0.8256, | |
| "mean_token_accuracy": 0.7575601720590184, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7647058823529411, | |
| "grad_norm": 0.3074055212225788, | |
| "learning_rate": 1.982973099683902e-05, | |
| "loss": 0.8155, | |
| "mean_token_accuracy": 0.75987807875422, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7941176470588235, | |
| "grad_norm": 0.3054700413716101, | |
| "learning_rate": 1.9789931723094046e-05, | |
| "loss": 0.8145, | |
| "mean_token_accuracy": 0.7605635562676385, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.31001811075570757, | |
| "learning_rate": 1.9746005004415004e-05, | |
| "loss": 0.8039, | |
| "mean_token_accuracy": 0.7631607094065346, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8529411764705882, | |
| "grad_norm": 0.3136963713557885, | |
| "learning_rate": 1.9697969360350098e-05, | |
| "loss": 0.8049, | |
| "mean_token_accuracy": 0.7624575022466116, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 0.3191880097370058, | |
| "learning_rate": 1.9645845042774555e-05, | |
| "loss": 0.802, | |
| "mean_token_accuracy": 0.7633903493459862, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9117647058823529, | |
| "grad_norm": 0.31057235371298675, | |
| "learning_rate": 1.9589654027352412e-05, | |
| "loss": 0.7986, | |
| "mean_token_accuracy": 0.7643766169115257, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.29582364900334857, | |
| "learning_rate": 1.9529420004271568e-05, | |
| "loss": 0.7914, | |
| "mean_token_accuracy": 0.7649156224508902, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9705882352941176, | |
| "grad_norm": 0.3193491594935024, | |
| "learning_rate": 1.9465168368255946e-05, | |
| "loss": 0.8003, | |
| "mean_token_accuracy": 0.762817530530919, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.3110939132941867, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 0.79, | |
| "mean_token_accuracy": 0.7647602598149285, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0294117647058822, | |
| "grad_norm": 0.3633335573513833, | |
| "learning_rate": 1.932472229404356e-05, | |
| "loss": 0.7299, | |
| "mean_token_accuracy": 0.7798239661883426, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.0588235294117647, | |
| "grad_norm": 0.3285229069104878, | |
| "learning_rate": 1.924858706805112e-05, | |
| "loss": 0.7229, | |
| "mean_token_accuracy": 0.7820958235079569, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.088235294117647, | |
| "grad_norm": 0.3128912088038598, | |
| "learning_rate": 1.9168552628568632e-05, | |
| "loss": 0.7271, | |
| "mean_token_accuracy": 0.7804769391368682, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.1176470588235294, | |
| "grad_norm": 0.3081304554701627, | |
| "learning_rate": 1.9084652718195237e-05, | |
| "loss": 0.7312, | |
| "mean_token_accuracy": 0.7789700891513861, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.1470588235294117, | |
| "grad_norm": 0.3276014451232185, | |
| "learning_rate": 1.8996922709216456e-05, | |
| "loss": 0.7198, | |
| "mean_token_accuracy": 0.7823098470986267, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.30110481549521834, | |
| "learning_rate": 1.8905399588691165e-05, | |
| "loss": 0.7243, | |
| "mean_token_accuracy": 0.7809635103462556, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.2058823529411764, | |
| "grad_norm": 0.30156642595064437, | |
| "learning_rate": 1.8810121942857848e-05, | |
| "loss": 0.7087, | |
| "mean_token_accuracy": 0.7859269243460426, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.2352941176470589, | |
| "grad_norm": 0.34077822382920914, | |
| "learning_rate": 1.8711129940866577e-05, | |
| "loss": 0.7248, | |
| "mean_token_accuracy": 0.7809192289978137, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.2647058823529411, | |
| "grad_norm": 0.32911315395038965, | |
| "learning_rate": 1.860846531784368e-05, | |
| "loss": 0.7093, | |
| "mean_token_accuracy": 0.785446429758738, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 0.3157810716541353, | |
| "learning_rate": 1.8502171357296144e-05, | |
| "loss": 0.7278, | |
| "mean_token_accuracy": 0.7799419555666971, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.3235294117647058, | |
| "grad_norm": 0.30424816114084574, | |
| "learning_rate": 1.839229287286327e-05, | |
| "loss": 0.7275, | |
| "mean_token_accuracy": 0.7794343137623393, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.3529411764705883, | |
| "grad_norm": 0.2984011834982273, | |
| "learning_rate": 1.827887618942318e-05, | |
| "loss": 0.7175, | |
| "mean_token_accuracy": 0.7828088672818859, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.3823529411764706, | |
| "grad_norm": 0.33971195458260056, | |
| "learning_rate": 1.816196912356222e-05, | |
| "loss": 0.7172, | |
| "mean_token_accuracy": 0.7824906691918898, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.32633469157456657, | |
| "learning_rate": 1.8041620963415418e-05, | |
| "loss": 0.7208, | |
| "mean_token_accuracy": 0.7814289254041461, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.4411764705882353, | |
| "grad_norm": 0.31489767315655054, | |
| "learning_rate": 1.7917882447886585e-05, | |
| "loss": 0.7365, | |
| "mean_token_accuracy": 0.7766203149595159, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.4705882352941178, | |
| "grad_norm": 0.32277097391893517, | |
| "learning_rate": 1.7790805745256703e-05, | |
| "loss": 0.7177, | |
| "mean_token_accuracy": 0.782642169037961, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.30987881280212765, | |
| "learning_rate": 1.766044443118978e-05, | |
| "loss": 0.727, | |
| "mean_token_accuracy": 0.779525294630621, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.5294117647058822, | |
| "grad_norm": 0.31448685091412465, | |
| "learning_rate": 1.7526853466145248e-05, | |
| "loss": 0.721, | |
| "mean_token_accuracy": 0.7812619303947332, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.5588235294117647, | |
| "grad_norm": 0.32175478306501826, | |
| "learning_rate": 1.7390089172206594e-05, | |
| "loss": 0.7241, | |
| "mean_token_accuracy": 0.780364964868133, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.5882352941176472, | |
| "grad_norm": 0.2981306127426255, | |
| "learning_rate": 1.725020920933593e-05, | |
| "loss": 0.7267, | |
| "mean_token_accuracy": 0.7790934213702954, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.6176470588235294, | |
| "grad_norm": 0.3033949440928067, | |
| "learning_rate": 1.710727255106447e-05, | |
| "loss": 0.7257, | |
| "mean_token_accuracy": 0.7797863888193627, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.30974296262432216, | |
| "learning_rate": 1.696133945962927e-05, | |
| "loss": 0.7235, | |
| "mean_token_accuracy": 0.7804705115541349, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.6764705882352942, | |
| "grad_norm": 0.31142423335839425, | |
| "learning_rate": 1.681247146056654e-05, | |
| "loss": 0.7086, | |
| "mean_token_accuracy": 0.7846730427727773, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.7058823529411766, | |
| "grad_norm": 0.3071934896661938, | |
| "learning_rate": 1.6660731316772503e-05, | |
| "loss": 0.7174, | |
| "mean_token_accuracy": 0.7824091019225257, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.7352941176470589, | |
| "grad_norm": 0.3386291051319253, | |
| "learning_rate": 1.650618300204242e-05, | |
| "loss": 0.7232, | |
| "mean_token_accuracy": 0.7803308030095385, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.3140186357800053, | |
| "learning_rate": 1.634889167409923e-05, | |
| "loss": 0.7129, | |
| "mean_token_accuracy": 0.782982412331459, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.7941176470588234, | |
| "grad_norm": 0.3021409601720461, | |
| "learning_rate": 1.6188923647122946e-05, | |
| "loss": 0.7107, | |
| "mean_token_accuracy": 0.7836278096533718, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.8235294117647058, | |
| "grad_norm": 0.314246176884694, | |
| "learning_rate": 1.6026346363792565e-05, | |
| "loss": 0.7049, | |
| "mean_token_accuracy": 0.7850809024928556, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.8529411764705883, | |
| "grad_norm": 0.30224040461662033, | |
| "learning_rate": 1.5861228366852148e-05, | |
| "loss": 0.7007, | |
| "mean_token_accuracy": 0.7861974119207782, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.3247059160222777, | |
| "learning_rate": 1.5693639270213138e-05, | |
| "loss": 0.7185, | |
| "mean_token_accuracy": 0.7818327782869858, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.9117647058823528, | |
| "grad_norm": 0.2990975208169173, | |
| "learning_rate": 1.552364972960506e-05, | |
| "loss": 0.7105, | |
| "mean_token_accuracy": 0.7837350647310662, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.9411764705882353, | |
| "grad_norm": 0.292315327238204, | |
| "learning_rate": 1.5351331412787004e-05, | |
| "loss": 0.7062, | |
| "mean_token_accuracy": 0.7850761466894601, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.9705882352941178, | |
| "grad_norm": 0.34311073870983216, | |
| "learning_rate": 1.5176756969332428e-05, | |
| "loss": 0.7103, | |
| "mean_token_accuracy": 0.7839965589810655, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.29664361496826974, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.7133, | |
| "mean_token_accuracy": 0.7825006235163733, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.0294117647058822, | |
| "grad_norm": 0.3924789864040961, | |
| "learning_rate": 1.4821135025703491e-05, | |
| "loss": 0.6271, | |
| "mean_token_accuracy": 0.8049891882579882, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 2.0588235294117645, | |
| "grad_norm": 0.37701624048661836, | |
| "learning_rate": 1.4640237456093636e-05, | |
| "loss": 0.6164, | |
| "mean_token_accuracy": 0.8081895456693632, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.088235294117647, | |
| "grad_norm": 0.33511734135583915, | |
| "learning_rate": 1.4457383557765385e-05, | |
| "loss": 0.6166, | |
| "mean_token_accuracy": 0.8076739145094626, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 2.1176470588235294, | |
| "grad_norm": 0.33243930178538456, | |
| "learning_rate": 1.427265042210381e-05, | |
| "loss": 0.6243, | |
| "mean_token_accuracy": 0.8049194097878407, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.1470588235294117, | |
| "grad_norm": 0.33350676253837797, | |
| "learning_rate": 1.4086115932782316e-05, | |
| "loss": 0.6084, | |
| "mean_token_accuracy": 0.810022229810283, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.176470588235294, | |
| "grad_norm": 0.3634421833067062, | |
| "learning_rate": 1.3897858732926794e-05, | |
| "loss": 0.6214, | |
| "mean_token_accuracy": 0.8059747023198034, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.2058823529411766, | |
| "grad_norm": 0.32882544775622274, | |
| "learning_rate": 1.3707958191959609e-05, | |
| "loss": 0.6226, | |
| "mean_token_accuracy": 0.8054682041286021, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.3305436002182192, | |
| "learning_rate": 1.3516494372137368e-05, | |
| "loss": 0.6112, | |
| "mean_token_accuracy": 0.8089070977046144, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.264705882352941, | |
| "grad_norm": 0.33722751621182623, | |
| "learning_rate": 1.3323547994796597e-05, | |
| "loss": 0.628, | |
| "mean_token_accuracy": 0.8039877302887909, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 2.2941176470588234, | |
| "grad_norm": 0.33248407945905123, | |
| "learning_rate": 1.3129200406321545e-05, | |
| "loss": 0.617, | |
| "mean_token_accuracy": 0.8073568639992759, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.323529411764706, | |
| "grad_norm": 0.32142510146932524, | |
| "learning_rate": 1.2933533543848462e-05, | |
| "loss": 0.6215, | |
| "mean_token_accuracy": 0.8055732590173094, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": 0.33654477807126704, | |
| "learning_rate": 1.2736629900720832e-05, | |
| "loss": 0.6157, | |
| "mean_token_accuracy": 0.8077722830589826, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.3823529411764706, | |
| "grad_norm": 0.3235396120568174, | |
| "learning_rate": 1.2538572491710079e-05, | |
| "loss": 0.6175, | |
| "mean_token_accuracy": 0.8072083426089869, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 2.411764705882353, | |
| "grad_norm": 0.32834778791268815, | |
| "learning_rate": 1.2339444818016488e-05, | |
| "loss": 0.609, | |
| "mean_token_accuracy": 0.8097089774864203, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.4411764705882355, | |
| "grad_norm": 0.3256651992427977, | |
| "learning_rate": 1.2139330832064975e-05, | |
| "loss": 0.6093, | |
| "mean_token_accuracy": 0.809542989158514, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 2.4705882352941178, | |
| "grad_norm": 0.32713429702744246, | |
| "learning_rate": 1.1938314902110701e-05, | |
| "loss": 0.6221, | |
| "mean_token_accuracy": 0.80594164904137, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.32892077647415724, | |
| "learning_rate": 1.1736481776669307e-05, | |
| "loss": 0.623, | |
| "mean_token_accuracy": 0.8050380371141161, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.5294117647058822, | |
| "grad_norm": 0.3351510239392618, | |
| "learning_rate": 1.1533916548786856e-05, | |
| "loss": 0.6221, | |
| "mean_token_accuracy": 0.8059383027153586, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.5588235294117645, | |
| "grad_norm": 0.32376353924923923, | |
| "learning_rate": 1.133070462016454e-05, | |
| "loss": 0.6296, | |
| "mean_token_accuracy": 0.8035830262709686, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 0.33352315854264303, | |
| "learning_rate": 1.1126931665153213e-05, | |
| "loss": 0.6303, | |
| "mean_token_accuracy": 0.8032632915017253, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.6176470588235294, | |
| "grad_norm": 0.33504031536917384, | |
| "learning_rate": 1.092268359463302e-05, | |
| "loss": 0.6162, | |
| "mean_token_accuracy": 0.8078497177646451, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 2.6470588235294117, | |
| "grad_norm": 0.32470133593647843, | |
| "learning_rate": 1.0718046519793276e-05, | |
| "loss": 0.6199, | |
| "mean_token_accuracy": 0.8059828691740311, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.6764705882352944, | |
| "grad_norm": 0.3311817254874853, | |
| "learning_rate": 1.0513106715827897e-05, | |
| "loss": 0.6157, | |
| "mean_token_accuracy": 0.8077946153778027, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "grad_norm": 0.32993180062270316, | |
| "learning_rate": 1.0307950585561705e-05, | |
| "loss": 0.6132, | |
| "mean_token_accuracy": 0.8084912132776563, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.735294117647059, | |
| "grad_norm": 0.325542621113992, | |
| "learning_rate": 1.01026646230229e-05, | |
| "loss": 0.6227, | |
| "mean_token_accuracy": 0.805343767865405, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 2.764705882352941, | |
| "grad_norm": 0.3173303746756242, | |
| "learning_rate": 9.897335376977104e-06, | |
| "loss": 0.6234, | |
| "mean_token_accuracy": 0.8049582474536037, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.7941176470588234, | |
| "grad_norm": 0.31358035777765325, | |
| "learning_rate": 9.692049414438298e-06, | |
| "loss": 0.6189, | |
| "mean_token_accuracy": 0.806300440606665, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.8235294117647056, | |
| "grad_norm": 0.3115874102200609, | |
| "learning_rate": 9.486893284172103e-06, | |
| "loss": 0.611, | |
| "mean_token_accuracy": 0.8087930759771561, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.8529411764705883, | |
| "grad_norm": 0.32045359513311766, | |
| "learning_rate": 9.281953480206725e-06, | |
| "loss": 0.617, | |
| "mean_token_accuracy": 0.806921570390956, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 2.8823529411764706, | |
| "grad_norm": 0.31864642830498724, | |
| "learning_rate": 9.07731640536698e-06, | |
| "loss": 0.6174, | |
| "mean_token_accuracy": 0.8067054562694989, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.911764705882353, | |
| "grad_norm": 0.321661470925901, | |
| "learning_rate": 8.87306833484679e-06, | |
| "loss": 0.6177, | |
| "mean_token_accuracy": 0.8073543308517797, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.9411764705882355, | |
| "grad_norm": 0.31775074388030633, | |
| "learning_rate": 8.669295379835467e-06, | |
| "loss": 0.6104, | |
| "mean_token_accuracy": 0.8088693944661568, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.9705882352941178, | |
| "grad_norm": 0.31639792662745364, | |
| "learning_rate": 8.466083451213145e-06, | |
| "loss": 0.6137, | |
| "mean_token_accuracy": 0.8079348085921285, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.3133845393789324, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 0.6199, | |
| "mean_token_accuracy": 0.8058531411884824, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.0294117647058822, | |
| "grad_norm": 0.4515133376678954, | |
| "learning_rate": 8.0616850978893e-06, | |
| "loss": 0.5429, | |
| "mean_token_accuracy": 0.8280749968215273, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 3.0588235294117645, | |
| "grad_norm": 0.43255149163083684, | |
| "learning_rate": 7.860669167935028e-06, | |
| "loss": 0.5424, | |
| "mean_token_accuracy": 0.8279721150148507, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.088235294117647, | |
| "grad_norm": 0.3814367503664446, | |
| "learning_rate": 7.660555181983517e-06, | |
| "loss": 0.5369, | |
| "mean_token_accuracy": 0.8295389031535093, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.1176470588235294, | |
| "grad_norm": 0.3585734376658857, | |
| "learning_rate": 7.461427508289922e-06, | |
| "loss": 0.5324, | |
| "mean_token_accuracy": 0.8305589141009605, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 3.1470588235294117, | |
| "grad_norm": 0.3516058935793569, | |
| "learning_rate": 7.263370099279173e-06, | |
| "loss": 0.5295, | |
| "mean_token_accuracy": 0.8319955163114205, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 3.176470588235294, | |
| "grad_norm": 0.3515670124714757, | |
| "learning_rate": 7.066466456151541e-06, | |
| "loss": 0.5409, | |
| "mean_token_accuracy": 0.827999215139253, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.2058823529411766, | |
| "grad_norm": 0.3425326731760254, | |
| "learning_rate": 6.870799593678459e-06, | |
| "loss": 0.5343, | |
| "mean_token_accuracy": 0.8301978132314783, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 3.235294117647059, | |
| "grad_norm": 0.4045712289767328, | |
| "learning_rate": 6.6764520052034054e-06, | |
| "loss": 0.5265, | |
| "mean_token_accuracy": 0.8329135799939124, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.264705882352941, | |
| "grad_norm": 0.3466050915406474, | |
| "learning_rate": 6.483505627862632e-06, | |
| "loss": 0.5305, | |
| "mean_token_accuracy": 0.8308944335567917, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 3.2941176470588234, | |
| "grad_norm": 0.3480592845097812, | |
| "learning_rate": 6.292041808040393e-06, | |
| "loss": 0.5312, | |
| "mean_token_accuracy": 0.8311541824181544, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.323529411764706, | |
| "grad_norm": 0.3476466845454666, | |
| "learning_rate": 6.102141267073207e-06, | |
| "loss": 0.5294, | |
| "mean_token_accuracy": 0.8318951179091675, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 3.3529411764705883, | |
| "grad_norm": 0.5241508868023107, | |
| "learning_rate": 5.913884067217686e-06, | |
| "loss": 0.5528, | |
| "mean_token_accuracy": 0.824183505569461, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.3823529411764706, | |
| "grad_norm": 0.35062363129549806, | |
| "learning_rate": 5.727349577896194e-06, | |
| "loss": 0.5397, | |
| "mean_token_accuracy": 0.8283691203284675, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 3.411764705882353, | |
| "grad_norm": 0.3347143755417769, | |
| "learning_rate": 5.542616442234618e-06, | |
| "loss": 0.5346, | |
| "mean_token_accuracy": 0.8302798791058473, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.4411764705882355, | |
| "grad_norm": 0.35274599242118565, | |
| "learning_rate": 5.3597625439063685e-06, | |
| "loss": 0.5367, | |
| "mean_token_accuracy": 0.8289645071509449, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 3.4705882352941178, | |
| "grad_norm": 0.3420158033073416, | |
| "learning_rate": 5.178864974296511e-06, | |
| "loss": 0.5337, | |
| "mean_token_accuracy": 0.8301539169568171, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 0.3454361511498841, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.5221, | |
| "mean_token_accuracy": 0.8342361720674832, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 3.5294117647058822, | |
| "grad_norm": 0.33581256443628404, | |
| "learning_rate": 4.823243030667576e-06, | |
| "loss": 0.5441, | |
| "mean_token_accuracy": 0.8269164229088842, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.5588235294117645, | |
| "grad_norm": 0.34226274444007343, | |
| "learning_rate": 4.648668587212998e-06, | |
| "loss": 0.54, | |
| "mean_token_accuracy": 0.8282965213330156, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 3.588235294117647, | |
| "grad_norm": 0.3500745490149332, | |
| "learning_rate": 4.476350270394942e-06, | |
| "loss": 0.5365, | |
| "mean_token_accuracy": 0.8292353029731997, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.6176470588235294, | |
| "grad_norm": 0.3397747170148032, | |
| "learning_rate": 4.306360729786867e-06, | |
| "loss": 0.531, | |
| "mean_token_accuracy": 0.8312139710361102, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 3.6470588235294117, | |
| "grad_norm": 0.3441348350064406, | |
| "learning_rate": 4.138771633147856e-06, | |
| "loss": 0.5401, | |
| "mean_token_accuracy": 0.8284560238696452, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.6764705882352944, | |
| "grad_norm": 0.34066437903851693, | |
| "learning_rate": 3.973653636207437e-06, | |
| "loss": 0.5389, | |
| "mean_token_accuracy": 0.8286709573008434, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 3.7058823529411766, | |
| "grad_norm": 0.3435442485915975, | |
| "learning_rate": 3.8110763528770543e-06, | |
| "loss": 0.5328, | |
| "mean_token_accuracy": 0.8307493440913218, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.735294117647059, | |
| "grad_norm": 0.33871491756685385, | |
| "learning_rate": 3.651108325900773e-06, | |
| "loss": 0.5396, | |
| "mean_token_accuracy": 0.8285779483750313, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 3.764705882352941, | |
| "grad_norm": 0.3322716149770833, | |
| "learning_rate": 3.493816997957582e-06, | |
| "loss": 0.5281, | |
| "mean_token_accuracy": 0.8320226506861953, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.7941176470588234, | |
| "grad_norm": 0.3408913341899395, | |
| "learning_rate": 3.339268683227499e-06, | |
| "loss": 0.5276, | |
| "mean_token_accuracy": 0.8323494901801878, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 3.8235294117647056, | |
| "grad_norm": 0.33820541461548986, | |
| "learning_rate": 3.1875285394334575e-06, | |
| "loss": 0.5382, | |
| "mean_token_accuracy": 0.8290421087951524, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.8529411764705883, | |
| "grad_norm": 0.3274191844325364, | |
| "learning_rate": 3.0386605403707347e-06, | |
| "loss": 0.5314, | |
| "mean_token_accuracy": 0.8310860589974585, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 3.8823529411764706, | |
| "grad_norm": 0.3290584011649337, | |
| "learning_rate": 2.8927274489355296e-06, | |
| "loss": 0.5423, | |
| "mean_token_accuracy": 0.8274875320572039, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.911764705882353, | |
| "grad_norm": 0.331251976751198, | |
| "learning_rate": 2.749790790664074e-06, | |
| "loss": 0.5321, | |
| "mean_token_accuracy": 0.8305707371259743, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 3.9411764705882355, | |
| "grad_norm": 0.3357781073651013, | |
| "learning_rate": 2.6099108277934105e-06, | |
| "loss": 0.53, | |
| "mean_token_accuracy": 0.8316958534732434, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.9705882352941178, | |
| "grad_norm": 0.36159917760376725, | |
| "learning_rate": 2.4731465338547556e-06, | |
| "loss": 0.5347, | |
| "mean_token_accuracy": 0.8300342318417423, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.3308064618286195, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 0.5379, | |
| "mean_token_accuracy": 0.8293708444456257, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 4.029411764705882, | |
| "grad_norm": 0.40943584673721745, | |
| "learning_rate": 2.209194254743295e-06, | |
| "loss": 0.4867, | |
| "mean_token_accuracy": 0.8454998608013117, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 4.0588235294117645, | |
| "grad_norm": 0.45370431209989043, | |
| "learning_rate": 2.0821175521134208e-06, | |
| "loss": 0.4913, | |
| "mean_token_accuracy": 0.8430829216918625, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 4.088235294117647, | |
| "grad_norm": 0.37717302254595253, | |
| "learning_rate": 1.9583790365845823e-06, | |
| "loss": 0.4873, | |
| "mean_token_accuracy": 0.8438923476557101, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 4.117647058823529, | |
| "grad_norm": 0.37698941484112286, | |
| "learning_rate": 1.8380308764377841e-06, | |
| "loss": 0.4836, | |
| "mean_token_accuracy": 0.8452770314043809, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.147058823529412, | |
| "grad_norm": 0.34607890458991425, | |
| "learning_rate": 1.7211238105768213e-06, | |
| "loss": 0.4981, | |
| "mean_token_accuracy": 0.8410555546918426, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 4.176470588235294, | |
| "grad_norm": 0.35787679802722067, | |
| "learning_rate": 1.607707127136734e-06, | |
| "loss": 0.4906, | |
| "mean_token_accuracy": 0.8431163617148336, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 4.205882352941177, | |
| "grad_norm": 0.34960387882531924, | |
| "learning_rate": 1.4978286427038602e-06, | |
| "loss": 0.4842, | |
| "mean_token_accuracy": 0.8452673287333395, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 4.235294117647059, | |
| "grad_norm": 0.3499750570371467, | |
| "learning_rate": 1.3915346821563235e-06, | |
| "loss": 0.4905, | |
| "mean_token_accuracy": 0.8434864507543587, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 4.264705882352941, | |
| "grad_norm": 0.3491087040345698, | |
| "learning_rate": 1.2888700591334225e-06, | |
| "loss": 0.4853, | |
| "mean_token_accuracy": 0.8449809552096237, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 4.294117647058823, | |
| "grad_norm": 0.34592474384102057, | |
| "learning_rate": 1.1898780571421554e-06, | |
| "loss": 0.4959, | |
| "mean_token_accuracy": 0.8415862048252866, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.323529411764706, | |
| "grad_norm": 0.35193064175626443, | |
| "learning_rate": 1.0946004113088381e-06, | |
| "loss": 0.4779, | |
| "mean_token_accuracy": 0.8476395134466322, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 4.352941176470588, | |
| "grad_norm": 0.3494094701083019, | |
| "learning_rate": 1.0030772907835484e-06, | |
| "loss": 0.4811, | |
| "mean_token_accuracy": 0.8462678766991031, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.382352941176471, | |
| "grad_norm": 0.3418341304288849, | |
| "learning_rate": 9.153472818047627e-07, | |
| "loss": 0.4784, | |
| "mean_token_accuracy": 0.8473868594161684, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 4.411764705882353, | |
| "grad_norm": 0.46400060241908164, | |
| "learning_rate": 8.31447371431372e-07, | |
| "loss": 0.4902, | |
| "mean_token_accuracy": 0.8432360408003623, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.4411764705882355, | |
| "grad_norm": 0.34372164358517193, | |
| "learning_rate": 7.514129319488839e-07, | |
| "loss": 0.4901, | |
| "mean_token_accuracy": 0.8436843577092926, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 4.470588235294118, | |
| "grad_norm": 0.3433127486725145, | |
| "learning_rate": 6.752777059564431e-07, | |
| "loss": 0.4876, | |
| "mean_token_accuracy": 0.8438663347463565, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 0.3512358511844125, | |
| "learning_rate": 6.030737921409169e-07, | |
| "loss": 0.4761, | |
| "mean_token_accuracy": 0.8475494992121411, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 4.529411764705882, | |
| "grad_norm": 0.47038019186648355, | |
| "learning_rate": 5.348316317440549e-07, | |
| "loss": 0.4856, | |
| "mean_token_accuracy": 0.8448994452927483, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.5588235294117645, | |
| "grad_norm": 1.9678500078373677, | |
| "learning_rate": 4.7057999572843516e-07, | |
| "loss": 0.4939, | |
| "mean_token_accuracy": 0.8421438229981003, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 4.588235294117647, | |
| "grad_norm": 0.3407337138700973, | |
| "learning_rate": 4.103459726475889e-07, | |
| "loss": 0.4827, | |
| "mean_token_accuracy": 0.845469943467501, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.617647058823529, | |
| "grad_norm": 0.3414928705541955, | |
| "learning_rate": 3.541549572254488e-07, | |
| "loss": 0.4888, | |
| "mean_token_accuracy": 0.8437554763885953, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 4.647058823529412, | |
| "grad_norm": 0.34079162834625754, | |
| "learning_rate": 3.020306396499062e-07, | |
| "loss": 0.4824, | |
| "mean_token_accuracy": 0.8457629333628377, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.676470588235294, | |
| "grad_norm": 0.3367904168904605, | |
| "learning_rate": 2.539949955849985e-07, | |
| "loss": 0.4891, | |
| "mean_token_accuracy": 0.8440021811993889, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": 0.3439387496930163, | |
| "learning_rate": 2.1006827690595478e-07, | |
| "loss": 0.4829, | |
| "mean_token_accuracy": 0.8455398197222916, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.735294117647059, | |
| "grad_norm": 0.348751695583376, | |
| "learning_rate": 1.7026900316098217e-07, | |
| "loss": 0.4905, | |
| "mean_token_accuracy": 0.8436304876776248, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 4.764705882352941, | |
| "grad_norm": 0.34277352712561143, | |
| "learning_rate": 1.3461395376340502e-07, | |
| "loss": 0.4795, | |
| "mean_token_accuracy": 0.8471346559845427, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.794117647058823, | |
| "grad_norm": 0.34865285423056336, | |
| "learning_rate": 1.0311816091744698e-07, | |
| "loss": 0.4887, | |
| "mean_token_accuracy": 0.8439427585239713, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 4.823529411764706, | |
| "grad_norm": 0.3510593438971943, | |
| "learning_rate": 7.579490328064265e-08, | |
| "loss": 0.4833, | |
| "mean_token_accuracy": 0.8458809389490854, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.852941176470588, | |
| "grad_norm": 0.3463646553260396, | |
| "learning_rate": 5.265570036553813e-08, | |
| "loss": 0.4891, | |
| "mean_token_accuracy": 0.8441209681319158, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 4.882352941176471, | |
| "grad_norm": 0.3425423146063826, | |
| "learning_rate": 3.371030768305583e-08, | |
| "loss": 0.4918, | |
| "mean_token_accuracy": 0.8428475797274417, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.911764705882353, | |
| "grad_norm": 0.3417126353423841, | |
| "learning_rate": 1.896671262955896e-08, | |
| "loss": 0.4892, | |
| "mean_token_accuracy": 0.8436010165370922, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 4.9411764705882355, | |
| "grad_norm": 0.3578021424188356, | |
| "learning_rate": 8.431131119361891e-09, | |
| "loss": 0.4852, | |
| "mean_token_accuracy": 0.8451092251253867, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.970588235294118, | |
| "grad_norm": 0.3424641211768565, | |
| "learning_rate": 2.108004964086474e-09, | |
| "loss": 0.4894, | |
| "mean_token_accuracy": 0.8437161999232033, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.3466047787737126, | |
| "learning_rate": 0.0, | |
| "loss": 0.4888, | |
| "mean_token_accuracy": 0.8429997643925609, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 850, | |
| "total_flos": 355893069742080.0, | |
| "train_loss": 0.6545549502092249, | |
| "train_runtime": 47744.7612, | |
| "train_samples_per_second": 2.278, | |
| "train_steps_per_second": 0.018 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 850, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 355893069742080.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |