| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 934, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.010718113612004287, |
| "grad_norm": 1.3203599452972412, |
| "learning_rate": 1.0256410256410257e-06, |
| "loss": 1.3095, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.021436227224008574, |
| "grad_norm": 1.005972981452942, |
| "learning_rate": 2.307692307692308e-06, |
| "loss": 1.3756, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03215434083601286, |
| "grad_norm": 0.8182684183120728, |
| "learning_rate": 3.58974358974359e-06, |
| "loss": 1.3238, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.04287245444801715, |
| "grad_norm": 0.791577160358429, |
| "learning_rate": 4.871794871794872e-06, |
| "loss": 1.2938, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.05359056806002144, |
| "grad_norm": 0.6379374861717224, |
| "learning_rate": 6.153846153846154e-06, |
| "loss": 1.2856, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.06430868167202572, |
| "grad_norm": 0.6668587327003479, |
| "learning_rate": 7.435897435897436e-06, |
| "loss": 1.2841, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.07502679528403002, |
| "grad_norm": 0.716699481010437, |
| "learning_rate": 8.717948717948719e-06, |
| "loss": 1.2718, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0857449088960343, |
| "grad_norm": 0.5486516952514648, |
| "learning_rate": 9.999999999999999e-06, |
| "loss": 1.273, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.09646302250803858, |
| "grad_norm": 0.46251392364501953, |
| "learning_rate": 1.1282051282051283e-05, |
| "loss": 1.312, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.10718113612004287, |
| "grad_norm": 0.4610588848590851, |
| "learning_rate": 1.2564102564102565e-05, |
| "loss": 1.2015, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.11789924973204716, |
| "grad_norm": 0.4434472918510437, |
| "learning_rate": 1.3846153846153847e-05, |
| "loss": 1.2457, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.12861736334405144, |
| "grad_norm": 0.43525955080986023, |
| "learning_rate": 1.5128205128205129e-05, |
| "loss": 1.2111, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.13933547695605572, |
| "grad_norm": 0.45412635803222656, |
| "learning_rate": 1.641025641025641e-05, |
| "loss": 1.2055, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.15005359056806003, |
| "grad_norm": 0.47974953055381775, |
| "learning_rate": 1.7692307692307694e-05, |
| "loss": 1.1836, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.1607717041800643, |
| "grad_norm": 0.5585247278213501, |
| "learning_rate": 1.8974358974358975e-05, |
| "loss": 1.1456, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.1714898177920686, |
| "grad_norm": 0.4740090072154999, |
| "learning_rate": 2.025641025641026e-05, |
| "loss": 1.1697, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.18220793140407288, |
| "grad_norm": 0.49104949831962585, |
| "learning_rate": 2.153846153846154e-05, |
| "loss": 1.1723, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.19292604501607716, |
| "grad_norm": 0.47726204991340637, |
| "learning_rate": 2.282051282051282e-05, |
| "loss": 1.1729, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.20364415862808147, |
| "grad_norm": 0.5089394450187683, |
| "learning_rate": 2.4102564102564103e-05, |
| "loss": 1.1313, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.21436227224008575, |
| "grad_norm": 0.4856749475002289, |
| "learning_rate": 2.5384615384615386e-05, |
| "loss": 1.1221, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.22508038585209003, |
| "grad_norm": 0.4452688992023468, |
| "learning_rate": 2.6666666666666667e-05, |
| "loss": 1.1334, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.2357984994640943, |
| "grad_norm": 0.5895005464553833, |
| "learning_rate": 2.794871794871795e-05, |
| "loss": 1.1453, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.2465166130760986, |
| "grad_norm": 0.5326249003410339, |
| "learning_rate": 2.923076923076923e-05, |
| "loss": 1.0856, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.2572347266881029, |
| "grad_norm": 0.588718056678772, |
| "learning_rate": 2.9999939813702703e-05, |
| "loss": 1.0957, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.2679528403001072, |
| "grad_norm": 0.4917924106121063, |
| "learning_rate": 2.9999262723404875e-05, |
| "loss": 1.0265, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.27867095391211144, |
| "grad_norm": 0.624920666217804, |
| "learning_rate": 2.9997833344010312e-05, |
| "loss": 1.0845, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.28938906752411575, |
| "grad_norm": 0.627967119216919, |
| "learning_rate": 2.9995651747209637e-05, |
| "loss": 1.1037, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.30010718113612006, |
| "grad_norm": 0.5074423551559448, |
| "learning_rate": 2.9992718042420993e-05, |
| "loss": 1.0788, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.3108252947481243, |
| "grad_norm": 0.5567290186882019, |
| "learning_rate": 2.9989032376784556e-05, |
| "loss": 1.1003, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.3215434083601286, |
| "grad_norm": 0.5891143083572388, |
| "learning_rate": 2.998459493515515e-05, |
| "loss": 1.0162, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.3322615219721329, |
| "grad_norm": 0.6841644048690796, |
| "learning_rate": 2.9979405940092978e-05, |
| "loss": 1.0204, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.3429796355841372, |
| "grad_norm": 0.6039224863052368, |
| "learning_rate": 2.997346565185246e-05, |
| "loss": 1.0219, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.3536977491961415, |
| "grad_norm": 0.5960545539855957, |
| "learning_rate": 2.9966774368369175e-05, |
| "loss": 1.0065, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.36441586280814575, |
| "grad_norm": 0.6452131867408752, |
| "learning_rate": 2.995933242524493e-05, |
| "loss": 0.9917, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.37513397642015006, |
| "grad_norm": 0.5966811776161194, |
| "learning_rate": 2.995114019573091e-05, |
| "loss": 0.9868, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.3858520900321543, |
| "grad_norm": 0.6129615306854248, |
| "learning_rate": 2.9942198090708976e-05, |
| "loss": 1.034, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.3965702036441586, |
| "grad_norm": 0.6630488038063049, |
| "learning_rate": 2.993250655867105e-05, |
| "loss": 1.0303, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.40728831725616294, |
| "grad_norm": 0.6165331602096558, |
| "learning_rate": 2.9922066085696613e-05, |
| "loss": 0.987, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.4180064308681672, |
| "grad_norm": 0.7296874523162842, |
| "learning_rate": 2.9910877195428335e-05, |
| "loss": 0.9805, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.4287245444801715, |
| "grad_norm": 0.6991822123527527, |
| "learning_rate": 2.989894044904581e-05, |
| "loss": 0.9377, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.43944265809217575, |
| "grad_norm": 0.7727455496788025, |
| "learning_rate": 2.9886256445237405e-05, |
| "loss": 0.9726, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.45016077170418006, |
| "grad_norm": 0.7376512289047241, |
| "learning_rate": 2.987282582017024e-05, |
| "loss": 0.946, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.4608788853161844, |
| "grad_norm": 0.819678544998169, |
| "learning_rate": 2.9858649247458287e-05, |
| "loss": 0.9861, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.4715969989281886, |
| "grad_norm": 0.7300285696983337, |
| "learning_rate": 2.984372743812855e-05, |
| "loss": 1.0026, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.48231511254019294, |
| "grad_norm": 0.7369091510772705, |
| "learning_rate": 2.9828061140585463e-05, |
| "loss": 0.9064, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.4930332261521972, |
| "grad_norm": 0.6813873052597046, |
| "learning_rate": 2.9811651140573287e-05, |
| "loss": 0.8859, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.5037513397642015, |
| "grad_norm": 0.7347345352172852, |
| "learning_rate": 2.979449826113676e-05, |
| "loss": 0.8983, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.5144694533762058, |
| "grad_norm": 0.8283259272575378, |
| "learning_rate": 2.9776603362579775e-05, |
| "loss": 0.8876, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.5251875669882101, |
| "grad_norm": 0.7388147711753845, |
| "learning_rate": 2.9757967342422246e-05, |
| "loss": 0.899, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.5359056806002144, |
| "grad_norm": 0.7657457590103149, |
| "learning_rate": 2.9738591135355108e-05, |
| "loss": 0.9412, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.5466237942122186, |
| "grad_norm": 0.8804264664649963, |
| "learning_rate": 2.971847571319341e-05, |
| "loss": 0.8838, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.5573419078242229, |
| "grad_norm": 0.771865963935852, |
| "learning_rate": 2.969762208482759e-05, |
| "loss": 0.8697, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.5680600214362272, |
| "grad_norm": 0.7006550431251526, |
| "learning_rate": 2.967603129617288e-05, |
| "loss": 0.8801, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.5787781350482315, |
| "grad_norm": 0.7909011244773865, |
| "learning_rate": 2.9653704430116827e-05, |
| "loss": 0.9199, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.5894962486602358, |
| "grad_norm": 0.9315905570983887, |
| "learning_rate": 2.9630642606464998e-05, |
| "loss": 0.8249, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.6002143622722401, |
| "grad_norm": 0.7528437376022339, |
| "learning_rate": 2.9606846981884812e-05, |
| "loss": 0.8656, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.6109324758842444, |
| "grad_norm": 0.7914732098579407, |
| "learning_rate": 2.958231874984753e-05, |
| "loss": 0.8618, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.6216505894962486, |
| "grad_norm": 0.7694675922393799, |
| "learning_rate": 2.955705914056838e-05, |
| "loss": 0.8546, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.632368703108253, |
| "grad_norm": 0.8651600480079651, |
| "learning_rate": 2.9531069420944876e-05, |
| "loss": 0.8654, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.6430868167202572, |
| "grad_norm": 0.7878230214118958, |
| "learning_rate": 2.9504350894493272e-05, |
| "loss": 0.8624, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6538049303322615, |
| "grad_norm": 0.9521771669387817, |
| "learning_rate": 2.9476904901283175e-05, |
| "loss": 0.8175, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.6645230439442658, |
| "grad_norm": 0.8132469058036804, |
| "learning_rate": 2.944873281787034e-05, |
| "loss": 0.8087, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.6752411575562701, |
| "grad_norm": 0.8626110553741455, |
| "learning_rate": 2.9419836057227634e-05, |
| "loss": 0.8033, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.6859592711682744, |
| "grad_norm": 0.858932614326477, |
| "learning_rate": 2.9390216068674154e-05, |
| "loss": 0.7535, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.6966773847802786, |
| "grad_norm": 1.0335079431533813, |
| "learning_rate": 2.9359874337802542e-05, |
| "loss": 0.8272, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.707395498392283, |
| "grad_norm": 0.819476842880249, |
| "learning_rate": 2.9328812386404503e-05, |
| "loss": 0.8184, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.7181136120042872, |
| "grad_norm": 0.9225292205810547, |
| "learning_rate": 2.9297031772394412e-05, |
| "loss": 0.8009, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.7288317256162915, |
| "grad_norm": 0.9197941422462463, |
| "learning_rate": 2.9264534089731262e-05, |
| "loss": 0.7841, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.7395498392282959, |
| "grad_norm": 0.8611735701560974, |
| "learning_rate": 2.9231320968338644e-05, |
| "loss": 0.7975, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.7502679528403001, |
| "grad_norm": 0.8244771361351013, |
| "learning_rate": 2.9197394074023042e-05, |
| "loss": 0.7895, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.7609860664523044, |
| "grad_norm": 0.8496798872947693, |
| "learning_rate": 2.9162755108390278e-05, |
| "loss": 0.7931, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.7717041800643086, |
| "grad_norm": 0.9810552000999451, |
| "learning_rate": 2.9127405808760152e-05, |
| "loss": 0.7507, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.782422293676313, |
| "grad_norm": 0.9915773272514343, |
| "learning_rate": 2.9091347948079318e-05, |
| "loss": 0.8251, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.7931404072883173, |
| "grad_norm": 1.0386714935302734, |
| "learning_rate": 2.9054583334832366e-05, |
| "loss": 0.8063, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.8038585209003215, |
| "grad_norm": 0.9649940729141235, |
| "learning_rate": 2.9017113812951105e-05, |
| "loss": 0.7797, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.8145766345123259, |
| "grad_norm": 1.0805562734603882, |
| "learning_rate": 2.897894126172209e-05, |
| "loss": 0.7873, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.8252947481243301, |
| "grad_norm": 0.9175759553909302, |
| "learning_rate": 2.8940067595692367e-05, |
| "loss": 0.7306, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.8360128617363344, |
| "grad_norm": 1.0049532651901245, |
| "learning_rate": 2.890049476457344e-05, |
| "loss": 0.7357, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.8467309753483387, |
| "grad_norm": 0.8982154726982117, |
| "learning_rate": 2.8860224753143486e-05, |
| "loss": 0.7478, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.857449088960343, |
| "grad_norm": 0.898063600063324, |
| "learning_rate": 2.881925958114782e-05, |
| "loss": 0.7576, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8681672025723473, |
| "grad_norm": 0.9208119511604309, |
| "learning_rate": 2.877760130319757e-05, |
| "loss": 0.7413, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.8788853161843515, |
| "grad_norm": 0.9576625823974609, |
| "learning_rate": 2.8735252008666663e-05, |
| "loss": 0.6863, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.8896034297963559, |
| "grad_norm": 0.9474856853485107, |
| "learning_rate": 2.8692213821586988e-05, |
| "loss": 0.7466, |
| "step": 415 |
| }, |
| { |
| "epoch": 0.9003215434083601, |
| "grad_norm": 1.0231027603149414, |
| "learning_rate": 2.8648488900541915e-05, |
| "loss": 0.7399, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.9110396570203644, |
| "grad_norm": 0.9832124710083008, |
| "learning_rate": 2.8604079438557985e-05, |
| "loss": 0.7037, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.9217577706323687, |
| "grad_norm": 1.0980058908462524, |
| "learning_rate": 2.8558987662994948e-05, |
| "loss": 0.7189, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.932475884244373, |
| "grad_norm": 1.1283589601516724, |
| "learning_rate": 2.851321583543404e-05, |
| "loss": 0.6951, |
| "step": 435 |
| }, |
| { |
| "epoch": 0.9431939978563773, |
| "grad_norm": 0.9087287187576294, |
| "learning_rate": 2.8466766251564554e-05, |
| "loss": 0.6932, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.9539121114683816, |
| "grad_norm": 1.0392457246780396, |
| "learning_rate": 2.8419641241068687e-05, |
| "loss": 0.7065, |
| "step": 445 |
| }, |
| { |
| "epoch": 0.9646302250803859, |
| "grad_norm": 0.9226632118225098, |
| "learning_rate": 2.837184316750473e-05, |
| "loss": 0.7066, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.9753483386923901, |
| "grad_norm": 0.9685462713241577, |
| "learning_rate": 2.832337442818848e-05, |
| "loss": 0.6805, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.9860664523043944, |
| "grad_norm": 0.9703472852706909, |
| "learning_rate": 2.8274237454073034e-05, |
| "loss": 0.668, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.9967845659163987, |
| "grad_norm": 0.902520477771759, |
| "learning_rate": 2.822443470962685e-05, |
| "loss": 0.6379, |
| "step": 465 |
| }, |
| { |
| "epoch": 1.0064308681672025, |
| "grad_norm": 1.2527391910552979, |
| "learning_rate": 2.8173968692710142e-05, |
| "loss": 0.6063, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.0171489817792068, |
| "grad_norm": 1.0625535249710083, |
| "learning_rate": 2.8122841934449607e-05, |
| "loss": 0.5916, |
| "step": 475 |
| }, |
| { |
| "epoch": 1.0278670953912112, |
| "grad_norm": 1.1103384494781494, |
| "learning_rate": 2.807105699911147e-05, |
| "loss": 0.6323, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.0385852090032155, |
| "grad_norm": 1.0214422941207886, |
| "learning_rate": 2.8018616483972874e-05, |
| "loss": 0.573, |
| "step": 485 |
| }, |
| { |
| "epoch": 1.0493033226152197, |
| "grad_norm": 0.9643238186836243, |
| "learning_rate": 2.7965523019191606e-05, |
| "loss": 0.5675, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.060021436227224, |
| "grad_norm": 0.9685465097427368, |
| "learning_rate": 2.7911779267674207e-05, |
| "loss": 0.5708, |
| "step": 495 |
| }, |
| { |
| "epoch": 1.0707395498392283, |
| "grad_norm": 1.0887079238891602, |
| "learning_rate": 2.7857387924942387e-05, |
| "loss": 0.5954, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0814576634512325, |
| "grad_norm": 0.9755250811576843, |
| "learning_rate": 2.7802351718997825e-05, |
| "loss": 0.5384, |
| "step": 505 |
| }, |
| { |
| "epoch": 1.092175777063237, |
| "grad_norm": 0.9574642181396484, |
| "learning_rate": 2.7746673410185387e-05, |
| "loss": 0.5627, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.1028938906752412, |
| "grad_norm": 1.0391875505447388, |
| "learning_rate": 2.7690355791054632e-05, |
| "loss": 0.5621, |
| "step": 515 |
| }, |
| { |
| "epoch": 1.1136120042872455, |
| "grad_norm": 0.9786142706871033, |
| "learning_rate": 2.7633401686219793e-05, |
| "loss": 0.5991, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.1243301178992497, |
| "grad_norm": 1.0193188190460205, |
| "learning_rate": 2.7575813952218075e-05, |
| "loss": 0.5723, |
| "step": 525 |
| }, |
| { |
| "epoch": 1.135048231511254, |
| "grad_norm": 1.0080389976501465, |
| "learning_rate": 2.75175954773664e-05, |
| "loss": 0.5206, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.1457663451232583, |
| "grad_norm": 0.9439852833747864, |
| "learning_rate": 2.7458749181616545e-05, |
| "loss": 0.571, |
| "step": 535 |
| }, |
| { |
| "epoch": 1.1564844587352625, |
| "grad_norm": 0.9455674290657043, |
| "learning_rate": 2.7399278016408695e-05, |
| "loss": 0.547, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.167202572347267, |
| "grad_norm": 1.138099193572998, |
| "learning_rate": 2.7339184964523404e-05, |
| "loss": 0.5942, |
| "step": 545 |
| }, |
| { |
| "epoch": 1.1779206859592712, |
| "grad_norm": 1.1031590700149536, |
| "learning_rate": 2.7278473039931992e-05, |
| "loss": 0.5378, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.1886387995712755, |
| "grad_norm": 1.1105057001113892, |
| "learning_rate": 2.7217145287645393e-05, |
| "loss": 0.5186, |
| "step": 555 |
| }, |
| { |
| "epoch": 1.1993569131832797, |
| "grad_norm": 1.2202413082122803, |
| "learning_rate": 2.715520478356141e-05, |
| "loss": 0.5721, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.210075026795284, |
| "grad_norm": 0.9721954464912415, |
| "learning_rate": 2.7092654634310468e-05, |
| "loss": 0.5433, |
| "step": 565 |
| }, |
| { |
| "epoch": 1.2207931404072883, |
| "grad_norm": 1.2260032892227173, |
| "learning_rate": 2.7029497977099784e-05, |
| "loss": 0.543, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.2315112540192925, |
| "grad_norm": 0.9644677639007568, |
| "learning_rate": 2.6965737979556025e-05, |
| "loss": 0.552, |
| "step": 575 |
| }, |
| { |
| "epoch": 1.242229367631297, |
| "grad_norm": 0.9937833547592163, |
| "learning_rate": 2.6901377839566443e-05, |
| "loss": 0.535, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.2529474812433012, |
| "grad_norm": 1.031482219696045, |
| "learning_rate": 2.683642078511846e-05, |
| "loss": 0.5322, |
| "step": 585 |
| }, |
| { |
| "epoch": 1.2636655948553055, |
| "grad_norm": 0.9676262140274048, |
| "learning_rate": 2.6770870074137808e-05, |
| "loss": 0.5006, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.2743837084673098, |
| "grad_norm": 1.3593294620513916, |
| "learning_rate": 2.670472899432509e-05, |
| "loss": 0.5064, |
| "step": 595 |
| }, |
| { |
| "epoch": 1.285101822079314, |
| "grad_norm": 1.0694024562835693, |
| "learning_rate": 2.66380008629909e-05, |
| "loss": 0.5848, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.2958199356913183, |
| "grad_norm": 1.0443016290664673, |
| "learning_rate": 2.657068902688945e-05, |
| "loss": 0.538, |
| "step": 605 |
| }, |
| { |
| "epoch": 1.3065380493033225, |
| "grad_norm": 1.023464560508728, |
| "learning_rate": 2.65027968620507e-05, |
| "loss": 0.5587, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.317256162915327, |
| "grad_norm": 0.9948901534080505, |
| "learning_rate": 2.643432777361105e-05, |
| "loss": 0.534, |
| "step": 615 |
| }, |
| { |
| "epoch": 1.3279742765273312, |
| "grad_norm": 1.0392403602600098, |
| "learning_rate": 2.636528519564253e-05, |
| "loss": 0.5365, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.3386923901393355, |
| "grad_norm": 1.0413520336151123, |
| "learning_rate": 2.6295672590980586e-05, |
| "loss": 0.4708, |
| "step": 625 |
| }, |
| { |
| "epoch": 1.3494105037513398, |
| "grad_norm": 1.1629996299743652, |
| "learning_rate": 2.6225493451050397e-05, |
| "loss": 0.5554, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.360128617363344, |
| "grad_norm": 1.023750901222229, |
| "learning_rate": 2.6154751295691756e-05, |
| "loss": 0.4827, |
| "step": 635 |
| }, |
| { |
| "epoch": 1.3708467309753483, |
| "grad_norm": 1.13310706615448, |
| "learning_rate": 2.608344967298253e-05, |
| "loss": 0.4657, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.3815648445873525, |
| "grad_norm": 1.083983063697815, |
| "learning_rate": 2.6011592159060717e-05, |
| "loss": 0.5213, |
| "step": 645 |
| }, |
| { |
| "epoch": 1.392282958199357, |
| "grad_norm": 1.048169493675232, |
| "learning_rate": 2.593918235794508e-05, |
| "loss": 0.4819, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.4030010718113612, |
| "grad_norm": 0.9783421158790588, |
| "learning_rate": 2.5866223901354372e-05, |
| "loss": 0.5378, |
| "step": 655 |
| }, |
| { |
| "epoch": 1.4137191854233655, |
| "grad_norm": 1.2764405012130737, |
| "learning_rate": 2.579272044852523e-05, |
| "loss": 0.4782, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.4244372990353698, |
| "grad_norm": 1.0567833185195923, |
| "learning_rate": 2.5718675686028582e-05, |
| "loss": 0.5, |
| "step": 665 |
| }, |
| { |
| "epoch": 1.435155412647374, |
| "grad_norm": 1.150490164756775, |
| "learning_rate": 2.56440933275848e-05, |
| "loss": 0.4415, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.4458735262593785, |
| "grad_norm": 1.0718622207641602, |
| "learning_rate": 2.5568977113877426e-05, |
| "loss": 0.5022, |
| "step": 675 |
| }, |
| { |
| "epoch": 1.4565916398713825, |
| "grad_norm": 1.0396467447280884, |
| "learning_rate": 2.549333081236553e-05, |
| "loss": 0.4582, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.467309753483387, |
| "grad_norm": 1.0076903104782104, |
| "learning_rate": 2.5417158217094788e-05, |
| "loss": 0.4865, |
| "step": 685 |
| }, |
| { |
| "epoch": 1.4780278670953912, |
| "grad_norm": 1.1110858917236328, |
| "learning_rate": 2.5340463148507178e-05, |
| "loss": 0.4707, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.4887459807073955, |
| "grad_norm": 1.0835309028625488, |
| "learning_rate": 2.5263249453249356e-05, |
| "loss": 0.4569, |
| "step": 695 |
| }, |
| { |
| "epoch": 1.4994640943193998, |
| "grad_norm": 1.1380281448364258, |
| "learning_rate": 2.5185521003979746e-05, |
| "loss": 0.4699, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.510182207931404, |
| "grad_norm": 1.2212399244308472, |
| "learning_rate": 2.5107281699174287e-05, |
| "loss": 0.4579, |
| "step": 705 |
| }, |
| { |
| "epoch": 1.5209003215434085, |
| "grad_norm": 1.080427646636963, |
| "learning_rate": 2.5028535462930924e-05, |
| "loss": 0.4509, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.5316184351554125, |
| "grad_norm": 1.0146664381027222, |
| "learning_rate": 2.494928624477277e-05, |
| "loss": 0.5209, |
| "step": 715 |
| }, |
| { |
| "epoch": 1.542336548767417, |
| "grad_norm": 1.023618221282959, |
| "learning_rate": 2.4869538019450045e-05, |
| "loss": 0.459, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.5530546623794212, |
| "grad_norm": 1.0760775804519653, |
| "learning_rate": 2.4789294786740705e-05, |
| "loss": 0.4522, |
| "step": 725 |
| }, |
| { |
| "epoch": 1.5637727759914255, |
| "grad_norm": 1.0976240634918213, |
| "learning_rate": 2.4708560571249845e-05, |
| "loss": 0.4853, |
| "step": 730 |
| }, |
| { |
| "epoch": 1.5744908896034298, |
| "grad_norm": 1.2561285495758057, |
| "learning_rate": 2.4627339422207805e-05, |
| "loss": 0.4584, |
| "step": 735 |
| }, |
| { |
| "epoch": 1.585209003215434, |
| "grad_norm": 1.1148028373718262, |
| "learning_rate": 2.454563541326716e-05, |
| "loss": 0.4492, |
| "step": 740 |
| }, |
| { |
| "epoch": 1.5959271168274385, |
| "grad_norm": 1.085665225982666, |
| "learning_rate": 2.4463452642298324e-05, |
| "loss": 0.4545, |
| "step": 745 |
| }, |
| { |
| "epoch": 1.6066452304394425, |
| "grad_norm": 0.9975435137748718, |
| "learning_rate": 2.438079523118406e-05, |
| "loss": 0.4392, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.617363344051447, |
| "grad_norm": 1.1030360460281372, |
| "learning_rate": 2.4297667325612756e-05, |
| "loss": 0.4255, |
| "step": 755 |
| }, |
| { |
| "epoch": 1.6280814576634512, |
| "grad_norm": 1.02976655960083, |
| "learning_rate": 2.421407309487046e-05, |
| "loss": 0.4452, |
| "step": 760 |
| }, |
| { |
| "epoch": 1.6387995712754555, |
| "grad_norm": 1.0580244064331055, |
| "learning_rate": 2.4130016731631815e-05, |
| "loss": 0.4275, |
| "step": 765 |
| }, |
| { |
| "epoch": 1.6495176848874598, |
| "grad_norm": 1.1036502122879028, |
| "learning_rate": 2.4045502451749736e-05, |
| "loss": 0.4672, |
| "step": 770 |
| }, |
| { |
| "epoch": 1.660235798499464, |
| "grad_norm": 1.1784788370132446, |
| "learning_rate": 2.3960534494043993e-05, |
| "loss": 0.4036, |
| "step": 775 |
| }, |
| { |
| "epoch": 1.6709539121114685, |
| "grad_norm": 1.1079624891281128, |
| "learning_rate": 2.387511712008859e-05, |
| "loss": 0.4294, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.6816720257234725, |
| "grad_norm": 1.0606523752212524, |
| "learning_rate": 2.3789254613998043e-05, |
| "loss": 0.449, |
| "step": 785 |
| }, |
| { |
| "epoch": 1.692390139335477, |
| "grad_norm": 0.9858099818229675, |
| "learning_rate": 2.3702951282212492e-05, |
| "loss": 0.3832, |
| "step": 790 |
| }, |
| { |
| "epoch": 1.7031082529474812, |
| "grad_norm": 1.1735355854034424, |
| "learning_rate": 2.3616211453281726e-05, |
| "loss": 0.445, |
| "step": 795 |
| }, |
| { |
| "epoch": 1.7138263665594855, |
| "grad_norm": 1.083713412284851, |
| "learning_rate": 2.3529039477648087e-05, |
| "loss": 0.4306, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.72454448017149, |
| "grad_norm": 1.1281569004058838, |
| "learning_rate": 2.344143972742826e-05, |
| "loss": 0.3807, |
| "step": 805 |
| }, |
| { |
| "epoch": 1.735262593783494, |
| "grad_norm": 1.0552798509597778, |
| "learning_rate": 2.3353416596193985e-05, |
| "loss": 0.4013, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.7459807073954985, |
| "grad_norm": 1.0200108289718628, |
| "learning_rate": 2.326497449875173e-05, |
| "loss": 0.369, |
| "step": 815 |
| }, |
| { |
| "epoch": 1.7566988210075025, |
| "grad_norm": 1.0658568143844604, |
| "learning_rate": 2.3176117870921218e-05, |
| "loss": 0.3814, |
| "step": 820 |
| }, |
| { |
| "epoch": 1.767416934619507, |
| "grad_norm": 1.164661169052124, |
| "learning_rate": 2.3086851169312992e-05, |
| "loss": 0.4044, |
| "step": 825 |
| }, |
| { |
| "epoch": 1.7781350482315113, |
| "grad_norm": 1.178032636642456, |
| "learning_rate": 2.299717887110487e-05, |
| "loss": 0.3985, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.7888531618435155, |
| "grad_norm": 1.1956833600997925, |
| "learning_rate": 2.290710547381739e-05, |
| "loss": 0.3905, |
| "step": 835 |
| }, |
| { |
| "epoch": 1.79957127545552, |
| "grad_norm": 1.205641269683838, |
| "learning_rate": 2.2816635495088244e-05, |
| "loss": 0.3915, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.810289389067524, |
| "grad_norm": 1.208314299583435, |
| "learning_rate": 2.272577347244571e-05, |
| "loss": 0.403, |
| "step": 845 |
| }, |
| { |
| "epoch": 1.8210075026795285, |
| "grad_norm": 1.1529418230056763, |
| "learning_rate": 2.2634523963081033e-05, |
| "loss": 0.3932, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.8317256162915327, |
| "grad_norm": 1.1101915836334229, |
| "learning_rate": 2.25428915436199e-05, |
| "loss": 0.3763, |
| "step": 855 |
| }, |
| { |
| "epoch": 1.842443729903537, |
| "grad_norm": 1.071894884109497, |
| "learning_rate": 2.245088080989287e-05, |
| "loss": 0.3824, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.8531618435155413, |
| "grad_norm": 1.1817514896392822, |
| "learning_rate": 2.2358496376704898e-05, |
| "loss": 0.4261, |
| "step": 865 |
| }, |
| { |
| "epoch": 1.8638799571275455, |
| "grad_norm": 1.1303304433822632, |
| "learning_rate": 2.2265742877603838e-05, |
| "loss": 0.3604, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.87459807073955, |
| "grad_norm": 1.0623246431350708, |
| "learning_rate": 2.2172624964648094e-05, |
| "loss": 0.4049, |
| "step": 875 |
| }, |
| { |
| "epoch": 1.885316184351554, |
| "grad_norm": 1.171410322189331, |
| "learning_rate": 2.2079147308173258e-05, |
| "loss": 0.3633, |
| "step": 880 |
| }, |
| { |
| "epoch": 1.8960342979635585, |
| "grad_norm": 1.20453941822052, |
| "learning_rate": 2.1985314596557887e-05, |
| "loss": 0.4022, |
| "step": 885 |
| }, |
| { |
| "epoch": 1.9067524115755627, |
| "grad_norm": 1.171126365661621, |
| "learning_rate": 2.1891131535988364e-05, |
| "loss": 0.3967, |
| "step": 890 |
| }, |
| { |
| "epoch": 1.917470525187567, |
| "grad_norm": 1.1599109172821045, |
| "learning_rate": 2.1796602850222832e-05, |
| "loss": 0.349, |
| "step": 895 |
| }, |
| { |
| "epoch": 1.9281886387995713, |
| "grad_norm": 1.056682825088501, |
| "learning_rate": 2.170173328035431e-05, |
| "loss": 0.3705, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.9389067524115755, |
| "grad_norm": 1.1990083456039429, |
| "learning_rate": 2.1606527584572854e-05, |
| "loss": 0.367, |
| "step": 905 |
| }, |
| { |
| "epoch": 1.94962486602358, |
| "grad_norm": 1.1245200634002686, |
| "learning_rate": 2.1510990537926983e-05, |
| "loss": 0.3734, |
| "step": 910 |
| }, |
| { |
| "epoch": 1.960342979635584, |
| "grad_norm": 1.2177960872650146, |
| "learning_rate": 2.1415126932084104e-05, |
| "loss": 0.4062, |
| "step": 915 |
| }, |
| { |
| "epoch": 1.9710610932475885, |
| "grad_norm": 1.1364030838012695, |
| "learning_rate": 2.1318941575090233e-05, |
| "loss": 0.3492, |
| "step": 920 |
| }, |
| { |
| "epoch": 1.9817792068595927, |
| "grad_norm": 1.1492586135864258, |
| "learning_rate": 2.1222439291128855e-05, |
| "loss": 0.3597, |
| "step": 925 |
| }, |
| { |
| "epoch": 1.992497320471597, |
| "grad_norm": 1.0529663562774658, |
| "learning_rate": 2.112562492027893e-05, |
| "loss": 0.3996, |
| "step": 930 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 2335, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 2000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.394156316393472e+18, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
