| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9997970367363507, | |
| "eval_steps": 80, | |
| "global_step": 821, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006088897909478384, | |
| "grad_norm": 3.566783556339775, | |
| "learning_rate": 5.5e-07, | |
| "loss": 1.1009, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012177795818956769, | |
| "grad_norm": 3.472124035548172, | |
| "learning_rate": 1.1e-06, | |
| "loss": 1.0381, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018266693728435153, | |
| "grad_norm": 2.9811017753128577, | |
| "learning_rate": 1.6499999999999999e-06, | |
| "loss": 0.9465, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024355591637913537, | |
| "grad_norm": 2.922160623410553, | |
| "learning_rate": 2.2e-06, | |
| "loss": 1.2107, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03044448954739192, | |
| "grad_norm": 2.4899147411553546, | |
| "learning_rate": 2.75e-06, | |
| "loss": 1.1834, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.036533387456870306, | |
| "grad_norm": 2.4171440435334826, | |
| "learning_rate": 3.2999999999999997e-06, | |
| "loss": 1.0345, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04262228536634869, | |
| "grad_norm": 2.3631050864525105, | |
| "learning_rate": 3.8499999999999996e-06, | |
| "loss": 0.8937, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.048711183275827075, | |
| "grad_norm": 2.367215460791824, | |
| "learning_rate": 4.4e-06, | |
| "loss": 1.0384, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05480008118530546, | |
| "grad_norm": 2.3735664390744695, | |
| "learning_rate": 4.95e-06, | |
| "loss": 0.8559, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06088897909478384, | |
| "grad_norm": 2.1106128418644574, | |
| "learning_rate": 5.5e-06, | |
| "loss": 1.0974, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06697787700426223, | |
| "grad_norm": 2.4447079098341042, | |
| "learning_rate": 5.416103509565232e-06, | |
| "loss": 1.0212, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.07306677491374061, | |
| "grad_norm": 2.4511103681763307, | |
| "learning_rate": 5.333024453086441e-06, | |
| "loss": 0.9416, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.079155672823219, | |
| "grad_norm": 2.2384105642036918, | |
| "learning_rate": 5.250760158320862e-06, | |
| "loss": 1.2031, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.08524457073269738, | |
| "grad_norm": 3.119602266469178, | |
| "learning_rate": 5.16930794423241e-06, | |
| "loss": 0.8486, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09133346864217577, | |
| "grad_norm": 2.5881641097806862, | |
| "learning_rate": 5.088665120904279e-06, | |
| "loss": 1.1537, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09742236655165415, | |
| "grad_norm": 2.2055002770457657, | |
| "learning_rate": 5.008828989450109e-06, | |
| "loss": 1.0313, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09742236655165415, | |
| "eval_loss": 0.9289844036102295, | |
| "eval_runtime": 10.8703, | |
| "eval_samples_per_second": 18.399, | |
| "eval_steps_per_second": 4.6, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.10351126446113254, | |
| "grad_norm": 2.415544688492964, | |
| "learning_rate": 4.92979684192366e-06, | |
| "loss": 0.9282, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.10960016237061092, | |
| "grad_norm": 1.7793675433556284, | |
| "learning_rate": 4.851565961226947e-06, | |
| "loss": 0.8977, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11568906028008931, | |
| "grad_norm": 2.8859944584710293, | |
| "learning_rate": 4.774133621016826e-06, | |
| "loss": 0.9419, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.12177795818956769, | |
| "grad_norm": 2.469055183117004, | |
| "learning_rate": 4.69749708560997e-06, | |
| "loss": 0.9848, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12786685609904608, | |
| "grad_norm": 2.2447776512327544, | |
| "learning_rate": 4.621653609886213e-06, | |
| "loss": 1.215, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.13395575400852447, | |
| "grad_norm": 2.531579161423441, | |
| "learning_rate": 4.5466004391902066e-06, | |
| "loss": 1.1061, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.14004465191800283, | |
| "grad_norm": 1.9522000168289182, | |
| "learning_rate": 4.472334809231365e-06, | |
| "loss": 0.9953, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.14613354982748122, | |
| "grad_norm": 2.5590272228727136, | |
| "learning_rate": 4.398853945982053e-06, | |
| "loss": 0.6939, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.15222244773695962, | |
| "grad_norm": 2.801526994914379, | |
| "learning_rate": 4.326155065573944e-06, | |
| "loss": 0.9363, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.158311345646438, | |
| "grad_norm": 1.8373874255277394, | |
| "learning_rate": 4.254235374192553e-06, | |
| "loss": 1.195, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.16440024355591637, | |
| "grad_norm": 2.236882560839364, | |
| "learning_rate": 4.183092067969859e-06, | |
| "loss": 0.9793, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.17048914146539476, | |
| "grad_norm": 3.3065776583087643, | |
| "learning_rate": 4.112722332874986e-06, | |
| "loss": 0.9404, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.17657803937487315, | |
| "grad_norm": 2.5409656409615695, | |
| "learning_rate": 4.043123344602879e-06, | |
| "loss": 0.7751, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.18266693728435154, | |
| "grad_norm": 2.6275401841731814, | |
| "learning_rate": 3.974292268460949e-06, | |
| "loss": 0.874, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1887558351938299, | |
| "grad_norm": 2.8046791101602007, | |
| "learning_rate": 3.906226259253599e-06, | |
| "loss": 0.9028, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.1948447331033083, | |
| "grad_norm": 2.1392572989093006, | |
| "learning_rate": 3.838922461164612e-06, | |
| "loss": 0.985, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.1948447331033083, | |
| "eval_loss": 0.9194434881210327, | |
| "eval_runtime": 10.0404, | |
| "eval_samples_per_second": 19.919, | |
| "eval_steps_per_second": 4.98, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2009336310127867, | |
| "grad_norm": 1.937352853882511, | |
| "learning_rate": 3.772378007637317e-06, | |
| "loss": 1.2669, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.20702252892226508, | |
| "grad_norm": 2.31447918391138, | |
| "learning_rate": 3.7065900212524865e-06, | |
| "loss": 0.8301, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.21311142683174344, | |
| "grad_norm": 1.9170456106220028, | |
| "learning_rate": 3.6415556136039017e-06, | |
| "loss": 0.9021, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.21920032474122184, | |
| "grad_norm": 2.2610666535764716, | |
| "learning_rate": 3.57727188517153e-06, | |
| "loss": 0.925, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.22528922265070023, | |
| "grad_norm": 2.4930543513110566, | |
| "learning_rate": 3.513735925192236e-06, | |
| "loss": 0.861, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.23137812056017862, | |
| "grad_norm": 2.1552816913331334, | |
| "learning_rate": 3.4509448115279674e-06, | |
| "loss": 1.1969, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.23746701846965698, | |
| "grad_norm": 1.8621642100291538, | |
| "learning_rate": 3.388895610531349e-06, | |
| "loss": 0.8704, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.24355591637913537, | |
| "grad_norm": 2.1209832615085285, | |
| "learning_rate": 3.3275853769086063e-06, | |
| "loss": 0.9503, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.24964481428861376, | |
| "grad_norm": 2.237393861143882, | |
| "learning_rate": 3.267011153579745e-06, | |
| "loss": 0.9347, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.25573371219809216, | |
| "grad_norm": 2.2028682955334964, | |
| "learning_rate": 3.2071699715359122e-06, | |
| "loss": 0.8733, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2618226101075705, | |
| "grad_norm": 2.1266652440547475, | |
| "learning_rate": 3.148058849693859e-06, | |
| "loss": 1.065, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.26791150801704894, | |
| "grad_norm": 2.285707011170251, | |
| "learning_rate": 3.0896747947474105e-06, | |
| "loss": 0.9307, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.2740004059265273, | |
| "grad_norm": 2.5710181491838737, | |
| "learning_rate": 3.0320148010158774e-06, | |
| "loss": 1.0314, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.28008930383600567, | |
| "grad_norm": 2.292322109336443, | |
| "learning_rate": 2.975075850289298e-06, | |
| "loss": 0.9115, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2861782017454841, | |
| "grad_norm": 2.1450080532027025, | |
| "learning_rate": 2.9188549116704386e-06, | |
| "loss": 1.0111, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.29226709965496245, | |
| "grad_norm": 2.1135370162342717, | |
| "learning_rate": 2.8633489414134293e-06, | |
| "loss": 1.091, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.29226709965496245, | |
| "eval_loss": 0.9108514189720154, | |
| "eval_runtime": 10.044, | |
| "eval_samples_per_second": 19.912, | |
| "eval_steps_per_second": 4.978, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2983559975644408, | |
| "grad_norm": 1.8496992962121142, | |
| "learning_rate": 2.8085548827589632e-06, | |
| "loss": 0.9449, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.30444489547391923, | |
| "grad_norm": 2.2350891035464615, | |
| "learning_rate": 2.7544696657659385e-06, | |
| "loss": 1.0587, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3105337933833976, | |
| "grad_norm": 2.6722037220078767, | |
| "learning_rate": 2.7010902071394348e-06, | |
| "loss": 0.7525, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.316622691292876, | |
| "grad_norm": 2.277080303923668, | |
| "learning_rate": 2.6484134100549204e-06, | |
| "loss": 0.8815, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3227115892023544, | |
| "grad_norm": 2.0493281130802616, | |
| "learning_rate": 2.5964361639785647e-06, | |
| "loss": 1.1089, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.32880048711183274, | |
| "grad_norm": 2.042407938817224, | |
| "learning_rate": 2.5451553444835415e-06, | |
| "loss": 1.0962, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.33488938502131116, | |
| "grad_norm": 2.4634190870687287, | |
| "learning_rate": 2.4945678130621847e-06, | |
| "loss": 0.981, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3409782829307895, | |
| "grad_norm": 2.260346564740007, | |
| "learning_rate": 2.4446704169338846e-06, | |
| "loss": 0.8348, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3470671808402679, | |
| "grad_norm": 2.1046411435401806, | |
| "learning_rate": 2.3954599888485643e-06, | |
| "loss": 0.7611, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.3531560787497463, | |
| "grad_norm": 2.192608175141679, | |
| "learning_rate": 2.3469333468856106e-06, | |
| "loss": 1.1149, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.35924497665922467, | |
| "grad_norm": 1.9896811996512633, | |
| "learning_rate": 2.299087294248103e-06, | |
| "loss": 0.8705, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.3653338745687031, | |
| "grad_norm": 2.342371852699277, | |
| "learning_rate": 2.25191861905219e-06, | |
| "loss": 0.7842, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.37142277247818145, | |
| "grad_norm": 2.7056358054268945, | |
| "learning_rate": 2.205424094111439e-06, | |
| "loss": 0.9357, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.3775116703876598, | |
| "grad_norm": 1.827000174010884, | |
| "learning_rate": 2.1596004767160085e-06, | |
| "loss": 1.088, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.38360056829713823, | |
| "grad_norm": 2.11667666402572, | |
| "learning_rate": 2.1144445084064565e-06, | |
| "loss": 1.0323, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3896894662066166, | |
| "grad_norm": 1.9194964413075437, | |
| "learning_rate": 2.069952914741992e-06, | |
| "loss": 0.9087, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3896894662066166, | |
| "eval_loss": 0.9030415415763855, | |
| "eval_runtime": 10.0588, | |
| "eval_samples_per_second": 19.883, | |
| "eval_steps_per_second": 4.971, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.39577836411609496, | |
| "grad_norm": 2.379416328048356, | |
| "learning_rate": 2.026122405062999e-06, | |
| "loss": 0.9356, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.4018672620255734, | |
| "grad_norm": 2.3051629049862967, | |
| "learning_rate": 1.982949672247615e-06, | |
| "loss": 0.9179, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.40795615993505174, | |
| "grad_norm": 2.2745740533676724, | |
| "learning_rate": 1.940431392462155e-06, | |
| "loss": 0.9632, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.41404505784453016, | |
| "grad_norm": 2.2794095449818252, | |
| "learning_rate": 1.8985642249051713e-06, | |
| "loss": 0.8374, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.4201339557540085, | |
| "grad_norm": 1.9892966603109936, | |
| "learning_rate": 1.8573448115449084e-06, | |
| "loss": 0.8853, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.4262228536634869, | |
| "grad_norm": 1.9076114123449572, | |
| "learning_rate": 1.8167697768499194e-06, | |
| "loss": 1.006, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.4323117515729653, | |
| "grad_norm": 2.4400224099994183, | |
| "learning_rate": 1.7768357275125856e-06, | |
| "loss": 0.7937, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.43840064948244367, | |
| "grad_norm": 1.9229232682741382, | |
| "learning_rate": 1.737539252165281e-06, | |
| "loss": 0.937, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.44448954739192204, | |
| "grad_norm": 2.482169188918342, | |
| "learning_rate": 1.6988769210889033e-06, | |
| "loss": 0.8412, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.45057844530140045, | |
| "grad_norm": 2.0823727911627117, | |
| "learning_rate": 1.6608452859134694e-06, | |
| "loss": 1.0682, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.4566673432108788, | |
| "grad_norm": 2.1349739191332624, | |
| "learning_rate": 1.6234408793104964e-06, | |
| "loss": 0.9272, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.46275624112035724, | |
| "grad_norm": 2.30837580526881, | |
| "learning_rate": 1.5866602146768156e-06, | |
| "loss": 0.8386, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4688451390298356, | |
| "grad_norm": 1.998746509174225, | |
| "learning_rate": 1.55049978580951e-06, | |
| "loss": 1.0616, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.47493403693931396, | |
| "grad_norm": 1.7126649948610602, | |
| "learning_rate": 1.5149560665716053e-06, | |
| "loss": 0.9667, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.4810229348487924, | |
| "grad_norm": 5.6311081714105935, | |
| "learning_rate": 1.4800255105481483e-06, | |
| "loss": 0.876, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.48711183275827075, | |
| "grad_norm": 2.3657992350084545, | |
| "learning_rate": 1.445704550692281e-06, | |
| "loss": 1.0107, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.48711183275827075, | |
| "eval_loss": 0.8974834680557251, | |
| "eval_runtime": 10.0412, | |
| "eval_samples_per_second": 19.918, | |
| "eval_steps_per_second": 4.979, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4932007306677491, | |
| "grad_norm": 1.7698636674115102, | |
| "learning_rate": 1.4119895989608974e-06, | |
| "loss": 0.9153, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.49928962857722753, | |
| "grad_norm": 2.054779528570307, | |
| "learning_rate": 1.3788770459394496e-06, | |
| "loss": 0.8891, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.5053785264867059, | |
| "grad_norm": 1.9369644275849407, | |
| "learning_rate": 1.3463632604554425e-06, | |
| "loss": 0.9571, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.5114674243961843, | |
| "grad_norm": 1.8987765645217645, | |
| "learning_rate": 1.3144445891801363e-06, | |
| "loss": 0.963, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5175563223056627, | |
| "grad_norm": 2.403051805328199, | |
| "learning_rate": 1.28311735621795e-06, | |
| "loss": 1.1635, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.523645220215141, | |
| "grad_norm": 2.109077522246386, | |
| "learning_rate": 1.252377862683016e-06, | |
| "loss": 1.0585, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.5297341181246195, | |
| "grad_norm": 1.874133422791628, | |
| "learning_rate": 1.222222386262332e-06, | |
| "loss": 0.9143, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.5358230160340979, | |
| "grad_norm": 2.1929101428736177, | |
| "learning_rate": 1.1926471807648967e-06, | |
| "loss": 0.9188, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5419119139435762, | |
| "grad_norm": 1.6260373540934423, | |
| "learning_rate": 1.1636484756561917e-06, | |
| "loss": 0.8914, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.5480008118530546, | |
| "grad_norm": 1.9739709292895855, | |
| "learning_rate": 1.1352224755773445e-06, | |
| "loss": 1.0831, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.554089709762533, | |
| "grad_norm": 2.023310630964453, | |
| "learning_rate": 1.107365359848245e-06, | |
| "loss": 1.0402, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.5601786076720113, | |
| "grad_norm": 2.466428732846668, | |
| "learning_rate": 1.0800732819538616e-06, | |
| "loss": 0.9395, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5662675055814897, | |
| "grad_norm": 1.9030259115900607, | |
| "learning_rate": 1.0533423690129516e-06, | |
| "loss": 0.8586, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.5723564034909682, | |
| "grad_norm": 2.1592861330197946, | |
| "learning_rate": 1.0271687212283061e-06, | |
| "loss": 0.9337, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5784453014004465, | |
| "grad_norm": 2.356602817957484, | |
| "learning_rate": 1.0015484113176207e-06, | |
| "loss": 0.8562, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5845341993099249, | |
| "grad_norm": 1.9750104030522446, | |
| "learning_rate": 9.764774839240228e-07, | |
| "loss": 0.9108, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5845341993099249, | |
| "eval_loss": 0.8940006494522095, | |
| "eval_runtime": 10.0627, | |
| "eval_samples_per_second": 19.875, | |
| "eval_steps_per_second": 4.969, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5906230972194033, | |
| "grad_norm": 2.294181751504768, | |
| "learning_rate": 9.519519550052165e-07, | |
| "loss": 0.9483, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.5967119951288816, | |
| "grad_norm": 2.390172284421488, | |
| "learning_rate": 9.27967811200154e-07, | |
| "loss": 0.9252, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.60280089303836, | |
| "grad_norm": 1.9195131453200192, | |
| "learning_rate": 9.045210091720488e-07, | |
| "loss": 1.045, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.6088897909478385, | |
| "grad_norm": 2.3087652972941957, | |
| "learning_rate": 8.816074749264782e-07, | |
| "loss": 0.8324, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6149786888573169, | |
| "grad_norm": 1.887331233479458, | |
| "learning_rate": 8.592231031032369e-07, | |
| "loss": 0.9797, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.6210675867667952, | |
| "grad_norm": 2.546311216104545, | |
| "learning_rate": 8.37363756240493e-07, | |
| "loss": 0.9758, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.6271564846762736, | |
| "grad_norm": 2.052324183223674, | |
| "learning_rate": 8.160252640097203e-07, | |
| "loss": 0.9379, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.633245382585752, | |
| "grad_norm": 1.8162505508545923, | |
| "learning_rate": 7.952034224197429e-07, | |
| "loss": 1.0445, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6393342804952303, | |
| "grad_norm": 1.9039113307487847, | |
| "learning_rate": 7.748939929881281e-07, | |
| "loss": 0.9693, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.6454231784047088, | |
| "grad_norm": 1.7791797404105452, | |
| "learning_rate": 7.5509270187801e-07, | |
| "loss": 1.1654, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6515120763141872, | |
| "grad_norm": 2.2713665666241023, | |
| "learning_rate": 7.357952389983003e-07, | |
| "loss": 1.0812, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.6576009742236655, | |
| "grad_norm": 2.7771426272207926, | |
| "learning_rate": 7.169972570650695e-07, | |
| "loss": 1.0663, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6636898721331439, | |
| "grad_norm": 2.1095605296190794, | |
| "learning_rate": 6.986943706217093e-07, | |
| "loss": 1.2464, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.6697787700426223, | |
| "grad_norm": 2.165590845905102, | |
| "learning_rate": 6.808821550153036e-07, | |
| "loss": 1.1615, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6758676679521006, | |
| "grad_norm": 2.098201375795868, | |
| "learning_rate": 6.635561453264081e-07, | |
| "loss": 1.2256, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.681956565861579, | |
| "grad_norm": 1.597477657082927, | |
| "learning_rate": 6.467118352492235e-07, | |
| "loss": 1.1531, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.681956565861579, | |
| "eval_loss": 0.9038890600204468, | |
| "eval_runtime": 10.0714, | |
| "eval_samples_per_second": 19.858, | |
| "eval_steps_per_second": 4.965, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6880454637710575, | |
| "grad_norm": 1.9610561566970353, | |
| "learning_rate": 6.303446759188759e-07, | |
| "loss": 1.1032, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.6941343616805358, | |
| "grad_norm": 1.8771579285205593, | |
| "learning_rate": 6.14450074682243e-07, | |
| "loss": 1.0247, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.7002232595900142, | |
| "grad_norm": 1.9428546209099045, | |
| "learning_rate": 5.990233938084431e-07, | |
| "loss": 0.9957, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.7063121574994926, | |
| "grad_norm": 2.0685369493893453, | |
| "learning_rate": 5.840599491347582e-07, | |
| "loss": 1.073, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.712401055408971, | |
| "grad_norm": 1.4232455246953637, | |
| "learning_rate": 5.695550086433726e-07, | |
| "loss": 1.17, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.7184899533184493, | |
| "grad_norm": 1.9953305653364002, | |
| "learning_rate": 5.555037909638744e-07, | |
| "loss": 1.0394, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.7245788512279278, | |
| "grad_norm": 2.234757544147466, | |
| "learning_rate": 5.419014637959808e-07, | |
| "loss": 1.1472, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.7306677491374062, | |
| "grad_norm": 2.2367049852297876, | |
| "learning_rate": 5.287431422464098e-07, | |
| "loss": 1.0496, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7367566470468845, | |
| "grad_norm": 2.2212989204910367, | |
| "learning_rate": 5.160238870732056e-07, | |
| "loss": 0.9907, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.7428455449563629, | |
| "grad_norm": 1.8355911585139566, | |
| "learning_rate": 5.037387028301462e-07, | |
| "loss": 1.3347, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.7489344428658413, | |
| "grad_norm": 2.172477947251129, | |
| "learning_rate": 4.918825359030837e-07, | |
| "loss": 1.1386, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.7550233407753196, | |
| "grad_norm": 1.8047316252716201, | |
| "learning_rate": 4.804502724291952e-07, | |
| "loss": 1.1201, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.761112238684798, | |
| "grad_norm": 1.8666031715794023, | |
| "learning_rate": 4.6943673608912795e-07, | |
| "loss": 1.0354, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.7672011365942765, | |
| "grad_norm": 1.948049167249183, | |
| "learning_rate": 4.588366857608947e-07, | |
| "loss": 0.9314, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.7732900345037548, | |
| "grad_norm": 1.9360471601880767, | |
| "learning_rate": 4.4864481302308764e-07, | |
| "loss": 1.3016, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.7793789324132332, | |
| "grad_norm": 1.7603394486420607, | |
| "learning_rate": 4.388557394934996e-07, | |
| "loss": 1.2698, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7793789324132332, | |
| "eval_loss": 0.9068670868873596, | |
| "eval_runtime": 10.0454, | |
| "eval_samples_per_second": 19.91, | |
| "eval_steps_per_second": 4.977, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7854678303227116, | |
| "grad_norm": 1.8121869716312213, | |
| "learning_rate": 4.2946401398754887e-07, | |
| "loss": 1.0936, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.7915567282321899, | |
| "grad_norm": 2.2784724809217116, | |
| "learning_rate": 4.20464109478947e-07, | |
| "loss": 1.0688, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7976456261416683, | |
| "grad_norm": 1.9511498628400707, | |
| "learning_rate": 4.118504198427839e-07, | |
| "loss": 1.2066, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.8037345240511468, | |
| "grad_norm": 1.6886651269860387, | |
| "learning_rate": 4.036172563585779e-07, | |
| "loss": 1.0209, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.8098234219606252, | |
| "grad_norm": 1.770877392703053, | |
| "learning_rate": 3.957588439477604e-07, | |
| "loss": 1.1583, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.8159123198701035, | |
| "grad_norm": 2.1758718521360385, | |
| "learning_rate": 3.8826931711647146e-07, | |
| "loss": 1.0352, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.8220012177795819, | |
| "grad_norm": 2.003054070991938, | |
| "learning_rate": 3.8114271557029493e-07, | |
| "loss": 1.1568, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.8280901156890603, | |
| "grad_norm": 2.167247263874176, | |
| "learning_rate": 3.74372979462545e-07, | |
| "loss": 1.0868, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8341790135985386, | |
| "grad_norm": 1.8384381989648775, | |
| "learning_rate": 3.679539442317327e-07, | |
| "loss": 1.1053, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.840267911508017, | |
| "grad_norm": 2.1673707360409877, | |
| "learning_rate": 3.6187933497668937e-07, | |
| "loss": 1.1503, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.8463568094174955, | |
| "grad_norm": 1.9246135785489056, | |
| "learning_rate": 3.5614276030919706e-07, | |
| "loss": 1.0148, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.8524457073269738, | |
| "grad_norm": 1.675592035681543, | |
| "learning_rate": 3.507377056135281e-07, | |
| "loss": 1.0533, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8585346052364522, | |
| "grad_norm": 1.58433949898804, | |
| "learning_rate": 3.456575256295274e-07, | |
| "loss": 0.9223, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.8646235031459306, | |
| "grad_norm": 1.5089882230199272, | |
| "learning_rate": 3.408954362601715e-07, | |
| "loss": 1.1612, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.8707124010554089, | |
| "grad_norm": 1.8812149702939354, | |
| "learning_rate": 3.364445054850564e-07, | |
| "loss": 1.1011, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.8768012989648873, | |
| "grad_norm": 1.8009898237225854, | |
| "learning_rate": 3.322976432368887e-07, | |
| "loss": 1.1988, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.8768012989648873, | |
| "eval_loss": 0.9062988758087158, | |
| "eval_runtime": 10.0522, | |
| "eval_samples_per_second": 19.896, | |
| "eval_steps_per_second": 4.974, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.8828901968743658, | |
| "grad_norm": 2.0516728550272494, | |
| "learning_rate": 3.284475900672534e-07, | |
| "loss": 1.217, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.8889790947838441, | |
| "grad_norm": 1.8636754853646536, | |
| "learning_rate": 3.2488690438860155e-07, | |
| "loss": 1.05, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.8950679926933225, | |
| "grad_norm": 2.0197164306265973, | |
| "learning_rate": 3.216079480286014e-07, | |
| "loss": 1.083, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.9011568906028009, | |
| "grad_norm": 1.7192487834075223, | |
| "learning_rate": 3.186028697665536e-07, | |
| "loss": 0.9577, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.9072457885122793, | |
| "grad_norm": 1.9547679875155324, | |
| "learning_rate": 3.1586358643344154e-07, | |
| "loss": 1.0405, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.9133346864217576, | |
| "grad_norm": 2.0062949300387847, | |
| "learning_rate": 3.1338176103847303e-07, | |
| "loss": 1.1779, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.919423584331236, | |
| "grad_norm": 1.5531676528239142, | |
| "learning_rate": 3.111487772222592e-07, | |
| "loss": 1.1676, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.9255124822407145, | |
| "grad_norm": 1.5372578345670411, | |
| "learning_rate": 3.0915570910938297e-07, | |
| "loss": 1.0719, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9316013801501928, | |
| "grad_norm": 2.1454113233082706, | |
| "learning_rate": 3.07393285308207e-07, | |
| "loss": 1.0105, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.9376902780596712, | |
| "grad_norm": 1.5547170974986044, | |
| "learning_rate": 3.0585184532967033e-07, | |
| "loss": 1.0721, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.9437791759691496, | |
| "grad_norm": 1.852645012921805, | |
| "learning_rate": 3.045212859784411e-07, | |
| "loss": 1.0933, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.9498680738786279, | |
| "grad_norm": 1.8094221288522232, | |
| "learning_rate": 3.033909941480833e-07, | |
| "loss": 0.9671, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.9559569717881063, | |
| "grad_norm": 1.5561960733621902, | |
| "learning_rate": 3.024497606276943e-07, | |
| "loss": 1.1151, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.9620458696975848, | |
| "grad_norm": 1.84094988169291, | |
| "learning_rate": 3.016856664111943e-07, | |
| "loss": 0.9727, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.9681347676070631, | |
| "grad_norm": 1.8600686188407434, | |
| "learning_rate": 3.0108592734273526e-07, | |
| "loss": 1.1713, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.9742236655165415, | |
| "grad_norm": 1.9971464440071154, | |
| "learning_rate": 3.006366718310598e-07, | |
| "loss": 1.1649, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9742236655165415, | |
| "eval_loss": 0.9046012759208679, | |
| "eval_runtime": 10.0656, | |
| "eval_samples_per_second": 19.87, | |
| "eval_steps_per_second": 4.967, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9803125634260199, | |
| "grad_norm": 1.801943230059916, | |
| "learning_rate": 3.00322602222577e-07, | |
| "loss": 1.0695, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.9864014613354982, | |
| "grad_norm": 1.839016967735732, | |
| "learning_rate": 3.001264297011597e-07, | |
| "loss": 0.9731, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.9924903592449766, | |
| "grad_norm": 1.9692055921355986, | |
| "learning_rate": 3.00027780849675e-07, | |
| "loss": 0.9058, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.9985792571544551, | |
| "grad_norm": 2.8720134735995413, | |
| "learning_rate": 3.0000031504123295e-07, | |
| "loss": 1.2194, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.9997970367363507, | |
| "step": 821, | |
| "total_flos": 1.4841304991137792e+17, | |
| "train_loss": 1.0157385155576737, | |
| "train_runtime": 6062.254, | |
| "train_samples_per_second": 4.876, | |
| "train_steps_per_second": 0.135 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 821, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 821, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4841304991137792e+17, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |