{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.10040388455255037, "eval_steps": 500, "global_step": 88500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005672535850426574, "grad_norm": 3.387953996658325, "learning_rate": 1.9994327464149576e-05, "loss": 0.4217, "step": 500 }, { "epoch": 0.0011345071700853148, "grad_norm": 7.831711769104004, "learning_rate": 1.998865492829915e-05, "loss": 0.3872, "step": 1000 }, { "epoch": 0.0017017607551279724, "grad_norm": 0.5793220400810242, "learning_rate": 1.998298239244872e-05, "loss": 0.3817, "step": 1500 }, { "epoch": 0.0022690143401706297, "grad_norm": 1.234447956085205, "learning_rate": 1.9977309856598294e-05, "loss": 0.3843, "step": 2000 }, { "epoch": 0.0028362679252132874, "grad_norm": 1.1251826286315918, "learning_rate": 1.997163732074787e-05, "loss": 0.3823, "step": 2500 }, { "epoch": 0.0034035215102559448, "grad_norm": 5.509366512298584, "learning_rate": 1.9965964784897443e-05, "loss": 0.3689, "step": 3000 }, { "epoch": 0.0039707750952986025, "grad_norm": 1.2918850183486938, "learning_rate": 1.9960292249047017e-05, "loss": 0.368, "step": 3500 }, { "epoch": 0.004538028680341259, "grad_norm": 0.7386884689331055, "learning_rate": 1.9954619713196587e-05, "loss": 0.3588, "step": 4000 }, { "epoch": 0.005105282265383917, "grad_norm": 0.40995702147483826, "learning_rate": 1.994894717734616e-05, "loss": 0.3648, "step": 4500 }, { "epoch": 0.005672535850426575, "grad_norm": 1.1950393915176392, "learning_rate": 1.9943274641495735e-05, "loss": 0.3636, "step": 5000 }, { "epoch": 0.006239789435469232, "grad_norm": 0.33484068512916565, "learning_rate": 1.993760210564531e-05, "loss": 0.3727, "step": 5500 }, { "epoch": 0.0068070430205118895, "grad_norm": 0.6621952056884766, "learning_rate": 1.9931929569794883e-05, "loss": 0.3645, "step": 6000 }, { "epoch": 0.007374296605554547, "grad_norm": 0.3775445222854614, "learning_rate": 1.9926257033944457e-05, "loss": 0.3463, "step": 6500 }, { "epoch": 0.007941550190597205, "grad_norm": 3.5549304485321045, "learning_rate": 1.9920584498094028e-05, "loss": 0.3486, "step": 7000 }, { "epoch": 0.008508803775639862, "grad_norm": 0.8449244499206543, "learning_rate": 1.9914911962243602e-05, "loss": 0.3516, "step": 7500 }, { "epoch": 0.009076057360682519, "grad_norm": 0.4936882257461548, "learning_rate": 1.9909239426393176e-05, "loss": 0.3726, "step": 8000 }, { "epoch": 0.009643310945725177, "grad_norm": 0.3846686780452728, "learning_rate": 1.990356689054275e-05, "loss": 0.3559, "step": 8500 }, { "epoch": 0.010210564530767834, "grad_norm": 1.0206539630889893, "learning_rate": 1.9897894354692324e-05, "loss": 0.3465, "step": 9000 }, { "epoch": 0.010777818115810491, "grad_norm": 0.32130077481269836, "learning_rate": 1.9892221818841898e-05, "loss": 0.356, "step": 9500 }, { "epoch": 0.01134507170085315, "grad_norm": 1.2418744564056396, "learning_rate": 1.988654928299147e-05, "loss": 0.3536, "step": 10000 }, { "epoch": 0.011912325285895807, "grad_norm": 3.4250869750976562, "learning_rate": 1.9880876747141043e-05, "loss": 0.34, "step": 10500 }, { "epoch": 0.012479578870938464, "grad_norm": 0.8089951872825623, "learning_rate": 1.9875204211290617e-05, "loss": 0.3542, "step": 11000 }, { "epoch": 0.013046832455981122, "grad_norm": 2.089003562927246, "learning_rate": 1.986953167544019e-05, "loss": 0.3639, "step": 11500 }, { "epoch": 0.013614086041023779, "grad_norm": 0.32313957810401917, "learning_rate": 1.9863859139589762e-05, "loss": 0.3437, "step": 12000 }, { "epoch": 0.014181339626066436, "grad_norm": 0.3242214620113373, "learning_rate": 1.985818660373934e-05, "loss": 0.3498, "step": 12500 }, { "epoch": 0.014748593211109095, "grad_norm": 0.5132392644882202, "learning_rate": 1.985251406788891e-05, "loss": 0.3476, "step": 13000 }, { "epoch": 0.015315846796151751, "grad_norm": 1.0964300632476807, "learning_rate": 1.9846841532038484e-05, "loss": 0.3345, "step": 13500 }, { "epoch": 0.01588310038119441, "grad_norm": 0.9808000326156616, "learning_rate": 1.9841168996188058e-05, "loss": 0.3337, "step": 14000 }, { "epoch": 0.016450353966237067, "grad_norm": 21.7490291595459, "learning_rate": 1.9835496460337632e-05, "loss": 0.3562, "step": 14500 }, { "epoch": 0.017017607551279724, "grad_norm": 0.37766537070274353, "learning_rate": 1.9829823924487203e-05, "loss": 0.3343, "step": 15000 }, { "epoch": 0.01758486113632238, "grad_norm": 1.8476216793060303, "learning_rate": 1.982415138863678e-05, "loss": 0.3381, "step": 15500 }, { "epoch": 0.018152114721365038, "grad_norm": 0.5553542971611023, "learning_rate": 1.981847885278635e-05, "loss": 0.3497, "step": 16000 }, { "epoch": 0.018719368306407698, "grad_norm": 0.21085184812545776, "learning_rate": 1.9812806316935925e-05, "loss": 0.3472, "step": 16500 }, { "epoch": 0.019286621891450355, "grad_norm": 9.589337348937988, "learning_rate": 1.98071337810855e-05, "loss": 0.3449, "step": 17000 }, { "epoch": 0.01985387547649301, "grad_norm": 0.9183555245399475, "learning_rate": 1.9801461245235073e-05, "loss": 0.3339, "step": 17500 }, { "epoch": 0.02042112906153567, "grad_norm": 23.96393585205078, "learning_rate": 1.9795788709384643e-05, "loss": 0.3385, "step": 18000 }, { "epoch": 0.020988382646578325, "grad_norm": 1.359579086303711, "learning_rate": 1.9790116173534217e-05, "loss": 0.3428, "step": 18500 }, { "epoch": 0.021555636231620982, "grad_norm": 0.5926823019981384, "learning_rate": 1.978444363768379e-05, "loss": 0.3444, "step": 19000 }, { "epoch": 0.022122889816663643, "grad_norm": 0.7892150282859802, "learning_rate": 1.9778771101833366e-05, "loss": 0.3321, "step": 19500 }, { "epoch": 0.0226901434017063, "grad_norm": 0.3750669062137604, "learning_rate": 1.9773098565982936e-05, "loss": 0.3548, "step": 20000 }, { "epoch": 0.023257396986748956, "grad_norm": 4.070109844207764, "learning_rate": 1.9767426030132514e-05, "loss": 0.3522, "step": 20500 }, { "epoch": 0.023824650571791613, "grad_norm": 0.38032421469688416, "learning_rate": 1.9761753494282084e-05, "loss": 0.3474, "step": 21000 }, { "epoch": 0.02439190415683427, "grad_norm": 21.677780151367188, "learning_rate": 1.975608095843166e-05, "loss": 0.3453, "step": 21500 }, { "epoch": 0.024959157741876927, "grad_norm": 5.641119480133057, "learning_rate": 1.9750408422581232e-05, "loss": 0.3449, "step": 22000 }, { "epoch": 0.025526411326919587, "grad_norm": 25.08061981201172, "learning_rate": 1.9744735886730806e-05, "loss": 0.345, "step": 22500 }, { "epoch": 0.026093664911962244, "grad_norm": 0.43347591161727905, "learning_rate": 1.9739063350880377e-05, "loss": 0.3366, "step": 23000 }, { "epoch": 0.0266609184970049, "grad_norm": 0.31947267055511475, "learning_rate": 1.9733390815029955e-05, "loss": 0.3358, "step": 23500 }, { "epoch": 0.027228172082047558, "grad_norm": 1.0318926572799683, "learning_rate": 1.9727718279179525e-05, "loss": 0.3322, "step": 24000 }, { "epoch": 0.027795425667090215, "grad_norm": 1.8301944732666016, "learning_rate": 1.97220457433291e-05, "loss": 0.3396, "step": 24500 }, { "epoch": 0.028362679252132872, "grad_norm": 0.3236497640609741, "learning_rate": 1.9716373207478673e-05, "loss": 0.3516, "step": 25000 }, { "epoch": 0.028929932837175532, "grad_norm": 2.550765037536621, "learning_rate": 1.9710700671628247e-05, "loss": 0.3478, "step": 25500 }, { "epoch": 0.02949718642221819, "grad_norm": 0.537734866142273, "learning_rate": 1.9705028135777818e-05, "loss": 0.3263, "step": 26000 }, { "epoch": 0.030064440007260846, "grad_norm": 0.5279741883277893, "learning_rate": 1.9699355599927392e-05, "loss": 0.3268, "step": 26500 }, { "epoch": 0.030631693592303503, "grad_norm": 4.043364524841309, "learning_rate": 1.9693683064076966e-05, "loss": 0.3476, "step": 27000 }, { "epoch": 0.03119894717734616, "grad_norm": 0.4588943421840668, "learning_rate": 1.968801052822654e-05, "loss": 0.335, "step": 27500 }, { "epoch": 0.03176620076238882, "grad_norm": 0.31232479214668274, "learning_rate": 1.9682337992376114e-05, "loss": 0.327, "step": 28000 }, { "epoch": 0.03233345434743148, "grad_norm": 0.3791950047016144, "learning_rate": 1.9676665456525688e-05, "loss": 0.3347, "step": 28500 }, { "epoch": 0.032900707932474134, "grad_norm": 0.11353936791419983, "learning_rate": 1.967099292067526e-05, "loss": 0.332, "step": 29000 }, { "epoch": 0.03346796151751679, "grad_norm": 0.5194895267486572, "learning_rate": 1.9665320384824833e-05, "loss": 0.3322, "step": 29500 }, { "epoch": 0.03403521510255945, "grad_norm": 0.7947537302970886, "learning_rate": 1.9659647848974407e-05, "loss": 0.3307, "step": 30000 }, { "epoch": 0.034602468687602105, "grad_norm": 0.3675363063812256, "learning_rate": 1.965397531312398e-05, "loss": 0.3482, "step": 30500 }, { "epoch": 0.03516972227264476, "grad_norm": 0.27730804681777954, "learning_rate": 1.9648302777273555e-05, "loss": 0.3409, "step": 31000 }, { "epoch": 0.03573697585768742, "grad_norm": 0.44526398181915283, "learning_rate": 1.964263024142313e-05, "loss": 0.3315, "step": 31500 }, { "epoch": 0.036304229442730075, "grad_norm": 0.28707778453826904, "learning_rate": 1.96369577055727e-05, "loss": 0.3236, "step": 32000 }, { "epoch": 0.03687148302777273, "grad_norm": 0.7148706912994385, "learning_rate": 1.9631285169722274e-05, "loss": 0.332, "step": 32500 }, { "epoch": 0.037438736612815396, "grad_norm": 132.02745056152344, "learning_rate": 1.9625612633871848e-05, "loss": 0.3325, "step": 33000 }, { "epoch": 0.03800599019785805, "grad_norm": 0.3043186366558075, "learning_rate": 1.9619940098021422e-05, "loss": 0.3292, "step": 33500 }, { "epoch": 0.03857324378290071, "grad_norm": 13.414630889892578, "learning_rate": 1.9614267562170996e-05, "loss": 0.3338, "step": 34000 }, { "epoch": 0.03914049736794337, "grad_norm": 0.20249101519584656, "learning_rate": 1.9608595026320567e-05, "loss": 0.3362, "step": 34500 }, { "epoch": 0.03970775095298602, "grad_norm": 0.8548006415367126, "learning_rate": 1.960292249047014e-05, "loss": 0.3499, "step": 35000 }, { "epoch": 0.04027500453802868, "grad_norm": 0.12220838665962219, "learning_rate": 1.9597249954619715e-05, "loss": 0.3285, "step": 35500 }, { "epoch": 0.04084225812307134, "grad_norm": 0.29653048515319824, "learning_rate": 1.959157741876929e-05, "loss": 0.3454, "step": 36000 }, { "epoch": 0.041409511708113994, "grad_norm": 0.09974247217178345, "learning_rate": 1.9585904882918863e-05, "loss": 0.3448, "step": 36500 }, { "epoch": 0.04197676529315665, "grad_norm": 0.23804782330989838, "learning_rate": 1.9580232347068437e-05, "loss": 0.3224, "step": 37000 }, { "epoch": 0.04254401887819931, "grad_norm": 0.26832830905914307, "learning_rate": 1.9574559811218007e-05, "loss": 0.3163, "step": 37500 }, { "epoch": 0.043111272463241965, "grad_norm": 3.487936019897461, "learning_rate": 1.956888727536758e-05, "loss": 0.3343, "step": 38000 }, { "epoch": 0.04367852604828463, "grad_norm": 0.18137934803962708, "learning_rate": 1.9563214739517155e-05, "loss": 0.3375, "step": 38500 }, { "epoch": 0.044245779633327285, "grad_norm": 0.42142942547798157, "learning_rate": 1.955754220366673e-05, "loss": 0.338, "step": 39000 }, { "epoch": 0.04481303321836994, "grad_norm": 0.21193692088127136, "learning_rate": 1.95518696678163e-05, "loss": 0.3336, "step": 39500 }, { "epoch": 0.0453802868034126, "grad_norm": 0.33044755458831787, "learning_rate": 1.9546197131965878e-05, "loss": 0.3238, "step": 40000 }, { "epoch": 0.045947540388455256, "grad_norm": 0.25394052267074585, "learning_rate": 1.9540524596115448e-05, "loss": 0.3311, "step": 40500 }, { "epoch": 0.04651479397349791, "grad_norm": 0.24994152784347534, "learning_rate": 1.9534852060265022e-05, "loss": 0.3173, "step": 41000 }, { "epoch": 0.04708204755854057, "grad_norm": 4.048117637634277, "learning_rate": 1.9529179524414596e-05, "loss": 0.3449, "step": 41500 }, { "epoch": 0.04764930114358323, "grad_norm": 0.7400296330451965, "learning_rate": 1.952350698856417e-05, "loss": 0.3474, "step": 42000 }, { "epoch": 0.048216554728625884, "grad_norm": 0.26707279682159424, "learning_rate": 1.951783445271374e-05, "loss": 0.3386, "step": 42500 }, { "epoch": 0.04878380831366854, "grad_norm": 13.8534517288208, "learning_rate": 1.951216191686332e-05, "loss": 0.3232, "step": 43000 }, { "epoch": 0.0493510618987112, "grad_norm": 9.848762512207031, "learning_rate": 1.950648938101289e-05, "loss": 0.3431, "step": 43500 }, { "epoch": 0.049918315483753854, "grad_norm": 0.6303707361221313, "learning_rate": 1.9500816845162463e-05, "loss": 0.3266, "step": 44000 }, { "epoch": 0.05048556906879652, "grad_norm": 12.861529350280762, "learning_rate": 1.9495144309312037e-05, "loss": 0.3239, "step": 44500 }, { "epoch": 0.051052822653839175, "grad_norm": 9.070085525512695, "learning_rate": 1.948947177346161e-05, "loss": 0.3319, "step": 45000 }, { "epoch": 0.05162007623888183, "grad_norm": 14.648274421691895, "learning_rate": 1.9483799237611182e-05, "loss": 0.331, "step": 45500 }, { "epoch": 0.05218732982392449, "grad_norm": 34.75390625, "learning_rate": 1.947812670176076e-05, "loss": 0.3295, "step": 46000 }, { "epoch": 0.052754583408967146, "grad_norm": 1.1457617282867432, "learning_rate": 1.947245416591033e-05, "loss": 0.3236, "step": 46500 }, { "epoch": 0.0533218369940098, "grad_norm": 1.6054667234420776, "learning_rate": 1.9466781630059904e-05, "loss": 0.3236, "step": 47000 }, { "epoch": 0.05388909057905246, "grad_norm": 1.246711254119873, "learning_rate": 1.9461109094209475e-05, "loss": 0.332, "step": 47500 }, { "epoch": 0.054456344164095116, "grad_norm": 0.5977410674095154, "learning_rate": 1.9455436558359052e-05, "loss": 0.3393, "step": 48000 }, { "epoch": 0.05502359774913777, "grad_norm": 5.520767688751221, "learning_rate": 1.9449764022508623e-05, "loss": 0.3327, "step": 48500 }, { "epoch": 0.05559085133418043, "grad_norm": 1.9742405414581299, "learning_rate": 1.9444091486658197e-05, "loss": 0.3444, "step": 49000 }, { "epoch": 0.05615810491922309, "grad_norm": 0.8282870650291443, "learning_rate": 1.943841895080777e-05, "loss": 0.3394, "step": 49500 }, { "epoch": 0.056725358504265744, "grad_norm": 2.033897638320923, "learning_rate": 1.9432746414957345e-05, "loss": 0.3363, "step": 50000 }, { "epoch": 0.05729261208930841, "grad_norm": 1.0143098831176758, "learning_rate": 1.9427073879106916e-05, "loss": 0.3196, "step": 50500 }, { "epoch": 0.057859865674351064, "grad_norm": 1.6727173328399658, "learning_rate": 1.9421401343256493e-05, "loss": 0.3294, "step": 51000 }, { "epoch": 0.05842711925939372, "grad_norm": 34.665252685546875, "learning_rate": 1.9415728807406064e-05, "loss": 0.3282, "step": 51500 }, { "epoch": 0.05899437284443638, "grad_norm": 0.5767442584037781, "learning_rate": 1.9410056271555638e-05, "loss": 0.3327, "step": 52000 }, { "epoch": 0.059561626429479035, "grad_norm": 0.6436382532119751, "learning_rate": 1.9404383735705212e-05, "loss": 0.3137, "step": 52500 }, { "epoch": 0.06012888001452169, "grad_norm": 0.4447130858898163, "learning_rate": 1.9398711199854786e-05, "loss": 0.328, "step": 53000 }, { "epoch": 0.06069613359956435, "grad_norm": 1.7067936658859253, "learning_rate": 1.9393038664004356e-05, "loss": 0.3268, "step": 53500 }, { "epoch": 0.061263387184607006, "grad_norm": 97.85061645507812, "learning_rate": 1.938736612815393e-05, "loss": 0.3195, "step": 54000 }, { "epoch": 0.06183064076964966, "grad_norm": 0.6765246391296387, "learning_rate": 1.9381693592303505e-05, "loss": 0.3233, "step": 54500 }, { "epoch": 0.06239789435469232, "grad_norm": 71.85704803466797, "learning_rate": 1.937602105645308e-05, "loss": 0.3317, "step": 55000 }, { "epoch": 0.06296514793973498, "grad_norm": 1.1403242349624634, "learning_rate": 1.9370348520602653e-05, "loss": 0.3349, "step": 55500 }, { "epoch": 0.06353240152477764, "grad_norm": 22.765140533447266, "learning_rate": 1.9364675984752227e-05, "loss": 0.3192, "step": 56000 }, { "epoch": 0.0640996551098203, "grad_norm": 0.7139065861701965, "learning_rate": 1.9359003448901797e-05, "loss": 0.3162, "step": 56500 }, { "epoch": 0.06466690869486295, "grad_norm": 0.6095991134643555, "learning_rate": 1.935333091305137e-05, "loss": 0.3173, "step": 57000 }, { "epoch": 0.06523416227990561, "grad_norm": 0.4620860815048218, "learning_rate": 1.9347658377200945e-05, "loss": 0.3405, "step": 57500 }, { "epoch": 0.06580141586494827, "grad_norm": 2.4695820808410645, "learning_rate": 1.934198584135052e-05, "loss": 0.3263, "step": 58000 }, { "epoch": 0.06636866944999092, "grad_norm": 0.49013492465019226, "learning_rate": 1.933631330550009e-05, "loss": 0.327, "step": 58500 }, { "epoch": 0.06693592303503358, "grad_norm": 0.8440238237380981, "learning_rate": 1.9330640769649668e-05, "loss": 0.3326, "step": 59000 }, { "epoch": 0.06750317662007624, "grad_norm": 5.433935165405273, "learning_rate": 1.9324968233799238e-05, "loss": 0.3242, "step": 59500 }, { "epoch": 0.0680704302051189, "grad_norm": 1.157573938369751, "learning_rate": 1.9319295697948812e-05, "loss": 0.3268, "step": 60000 }, { "epoch": 0.06863768379016155, "grad_norm": 1.0837581157684326, "learning_rate": 1.9313623162098386e-05, "loss": 0.3228, "step": 60500 }, { "epoch": 0.06920493737520421, "grad_norm": 1.0040887594223022, "learning_rate": 1.930795062624796e-05, "loss": 0.3115, "step": 61000 }, { "epoch": 0.06977219096024687, "grad_norm": 1.13579523563385, "learning_rate": 1.930227809039753e-05, "loss": 0.3155, "step": 61500 }, { "epoch": 0.07033944454528952, "grad_norm": 3.2068631649017334, "learning_rate": 1.9296605554547105e-05, "loss": 0.3132, "step": 62000 }, { "epoch": 0.07090669813033218, "grad_norm": 0.586251974105835, "learning_rate": 1.929093301869668e-05, "loss": 0.3153, "step": 62500 }, { "epoch": 0.07147395171537484, "grad_norm": 0.7550469636917114, "learning_rate": 1.9285260482846253e-05, "loss": 0.3283, "step": 63000 }, { "epoch": 0.0720412053004175, "grad_norm": 1.0829483270645142, "learning_rate": 1.9279587946995827e-05, "loss": 0.3304, "step": 63500 }, { "epoch": 0.07260845888546015, "grad_norm": 0.7655236124992371, "learning_rate": 1.92739154111454e-05, "loss": 0.326, "step": 64000 }, { "epoch": 0.07317571247050281, "grad_norm": 0.857245922088623, "learning_rate": 1.9268242875294972e-05, "loss": 0.3212, "step": 64500 }, { "epoch": 0.07374296605554546, "grad_norm": 0.4056306779384613, "learning_rate": 1.9262570339444546e-05, "loss": 0.32, "step": 65000 }, { "epoch": 0.07431021964058813, "grad_norm": 10.08352279663086, "learning_rate": 1.925689780359412e-05, "loss": 0.3229, "step": 65500 }, { "epoch": 0.07487747322563079, "grad_norm": 15.482842445373535, "learning_rate": 1.9251225267743694e-05, "loss": 0.3236, "step": 66000 }, { "epoch": 0.07544472681067345, "grad_norm": 0.32501137256622314, "learning_rate": 1.9245552731893268e-05, "loss": 0.3212, "step": 66500 }, { "epoch": 0.0760119803957161, "grad_norm": 0.5554530620574951, "learning_rate": 1.9239880196042842e-05, "loss": 0.3373, "step": 67000 }, { "epoch": 0.07657923398075876, "grad_norm": 0.27948904037475586, "learning_rate": 1.9234207660192413e-05, "loss": 0.3305, "step": 67500 }, { "epoch": 0.07714648756580142, "grad_norm": 1.6499723196029663, "learning_rate": 1.9228535124341987e-05, "loss": 0.3404, "step": 68000 }, { "epoch": 0.07771374115084408, "grad_norm": 8.564773559570312, "learning_rate": 1.922286258849156e-05, "loss": 0.3298, "step": 68500 }, { "epoch": 0.07828099473588673, "grad_norm": 7.0219573974609375, "learning_rate": 1.9217190052641135e-05, "loss": 0.3343, "step": 69000 }, { "epoch": 0.07884824832092939, "grad_norm": 0.3555821180343628, "learning_rate": 1.921151751679071e-05, "loss": 0.3291, "step": 69500 }, { "epoch": 0.07941550190597205, "grad_norm": 0.2007092386484146, "learning_rate": 1.920584498094028e-05, "loss": 0.3188, "step": 70000 }, { "epoch": 0.0799827554910147, "grad_norm": 0.5300312638282776, "learning_rate": 1.9200172445089854e-05, "loss": 0.3126, "step": 70500 }, { "epoch": 0.08055000907605736, "grad_norm": 0.5101011991500854, "learning_rate": 1.9194499909239428e-05, "loss": 0.3205, "step": 71000 }, { "epoch": 0.08111726266110002, "grad_norm": 1.1713281869888306, "learning_rate": 1.9188827373389e-05, "loss": 0.3466, "step": 71500 }, { "epoch": 0.08168451624614267, "grad_norm": 3.439805269241333, "learning_rate": 1.9183154837538576e-05, "loss": 0.3124, "step": 72000 }, { "epoch": 0.08225176983118533, "grad_norm": 0.778472363948822, "learning_rate": 1.917748230168815e-05, "loss": 0.3308, "step": 72500 }, { "epoch": 0.08281902341622799, "grad_norm": 0.433795303106308, "learning_rate": 1.917180976583772e-05, "loss": 0.3271, "step": 73000 }, { "epoch": 0.08338627700127065, "grad_norm": 15.664637565612793, "learning_rate": 1.9166137229987294e-05, "loss": 0.3219, "step": 73500 }, { "epoch": 0.0839535305863133, "grad_norm": 0.6989821195602417, "learning_rate": 1.916046469413687e-05, "loss": 0.3095, "step": 74000 }, { "epoch": 0.08452078417135596, "grad_norm": 19.356645584106445, "learning_rate": 1.9154792158286443e-05, "loss": 0.3266, "step": 74500 }, { "epoch": 0.08508803775639862, "grad_norm": 0.32333022356033325, "learning_rate": 1.9149119622436013e-05, "loss": 0.3219, "step": 75000 }, { "epoch": 0.08565529134144127, "grad_norm": 0.29713454842567444, "learning_rate": 1.914344708658559e-05, "loss": 0.3364, "step": 75500 }, { "epoch": 0.08622254492648393, "grad_norm": 1.616568684577942, "learning_rate": 1.913777455073516e-05, "loss": 0.3326, "step": 76000 }, { "epoch": 0.08678979851152659, "grad_norm": 0.38876867294311523, "learning_rate": 1.9132102014884735e-05, "loss": 0.3363, "step": 76500 }, { "epoch": 0.08735705209656926, "grad_norm": 0.2728395164012909, "learning_rate": 1.912642947903431e-05, "loss": 0.3174, "step": 77000 }, { "epoch": 0.08792430568161191, "grad_norm": 0.38797077536582947, "learning_rate": 1.9120756943183883e-05, "loss": 0.3341, "step": 77500 }, { "epoch": 0.08849155926665457, "grad_norm": 0.9708689451217651, "learning_rate": 1.9115084407333454e-05, "loss": 0.3258, "step": 78000 }, { "epoch": 0.08905881285169723, "grad_norm": 0.5084453821182251, "learning_rate": 1.910941187148303e-05, "loss": 0.318, "step": 78500 }, { "epoch": 0.08962606643673988, "grad_norm": 10.395822525024414, "learning_rate": 1.9103739335632602e-05, "loss": 0.3267, "step": 79000 }, { "epoch": 0.09019332002178254, "grad_norm": 56.53432846069336, "learning_rate": 1.9098066799782176e-05, "loss": 0.3206, "step": 79500 }, { "epoch": 0.0907605736068252, "grad_norm": 0.5847833752632141, "learning_rate": 1.909239426393175e-05, "loss": 0.3289, "step": 80000 }, { "epoch": 0.09132782719186786, "grad_norm": 0.6055426597595215, "learning_rate": 1.9086721728081324e-05, "loss": 0.3099, "step": 80500 }, { "epoch": 0.09189508077691051, "grad_norm": 0.13933761417865753, "learning_rate": 1.9081049192230895e-05, "loss": 0.3094, "step": 81000 }, { "epoch": 0.09246233436195317, "grad_norm": 3.231118679046631, "learning_rate": 1.9075376656380472e-05, "loss": 0.3292, "step": 81500 }, { "epoch": 0.09302958794699583, "grad_norm": 11.789403915405273, "learning_rate": 1.9069704120530043e-05, "loss": 0.3284, "step": 82000 }, { "epoch": 0.09359684153203848, "grad_norm": 0.47824761271476746, "learning_rate": 1.9064031584679617e-05, "loss": 0.316, "step": 82500 }, { "epoch": 0.09416409511708114, "grad_norm": 0.5431397557258606, "learning_rate": 1.9058359048829188e-05, "loss": 0.3316, "step": 83000 }, { "epoch": 0.0947313487021238, "grad_norm": 0.027491087093949318, "learning_rate": 1.9052686512978765e-05, "loss": 0.3226, "step": 83500 }, { "epoch": 0.09529860228716645, "grad_norm": 0.167594775557518, "learning_rate": 1.9047013977128336e-05, "loss": 0.3265, "step": 84000 }, { "epoch": 0.09586585587220911, "grad_norm": 25.423133850097656, "learning_rate": 1.904134144127791e-05, "loss": 0.3212, "step": 84500 }, { "epoch": 0.09643310945725177, "grad_norm": 8.196709632873535, "learning_rate": 1.9035668905427484e-05, "loss": 0.3355, "step": 85000 }, { "epoch": 0.09700036304229442, "grad_norm": 0.22309711575508118, "learning_rate": 1.9029996369577058e-05, "loss": 0.3287, "step": 85500 }, { "epoch": 0.09756761662733708, "grad_norm": 4.482788562774658, "learning_rate": 1.902432383372663e-05, "loss": 0.3315, "step": 86000 }, { "epoch": 0.09813487021237974, "grad_norm": 5.861471652984619, "learning_rate": 1.9018651297876206e-05, "loss": 0.3193, "step": 86500 }, { "epoch": 0.0987021237974224, "grad_norm": 2.7159125804901123, "learning_rate": 1.9012978762025777e-05, "loss": 0.3163, "step": 87000 }, { "epoch": 0.09926937738246505, "grad_norm": 0.4765207767486572, "learning_rate": 1.900730622617535e-05, "loss": 0.3125, "step": 87500 }, { "epoch": 0.09983663096750771, "grad_norm": 0.6516081094741821, "learning_rate": 1.9001633690324925e-05, "loss": 0.3231, "step": 88000 }, { "epoch": 0.10040388455255037, "grad_norm": 6.820018291473389, "learning_rate": 1.89959611544745e-05, "loss": 0.3099, "step": 88500 } ], "logging_steps": 500, "max_steps": 1762880, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 9.3786918248448e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }