| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 5243, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.009536524890329964, |
| "grad_norm": 1.3725634813308716, |
| "learning_rate": 3.7262357414448674e-05, |
| "loss": 1.5183903503417968, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.019073049780659927, |
| "grad_norm": 1.5630295276641846, |
| "learning_rate": 7.52851711026616e-05, |
| "loss": 1.0358538818359375, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.02860957467098989, |
| "grad_norm": 1.0457429885864258, |
| "learning_rate": 0.00011330798479087452, |
| "loss": 0.9928044128417969, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.038146099561319854, |
| "grad_norm": 1.1760847568511963, |
| "learning_rate": 0.00015133079847908746, |
| "loss": 0.9799901580810547, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.04768262445164982, |
| "grad_norm": 1.0198277235031128, |
| "learning_rate": 0.0001893536121673004, |
| "loss": 0.9692832946777343, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.05721914934197978, |
| "grad_norm": 4.2576141357421875, |
| "learning_rate": 0.00019997421320309795, |
| "loss": 0.9611747741699219, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.06675567423230974, |
| "grad_norm": 1.0672153234481812, |
| "learning_rate": 0.00019985286992997873, |
| "loss": 0.9739149475097656, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.07629219912263971, |
| "grad_norm": 1.015286922454834, |
| "learning_rate": 0.00019963219089815488, |
| "loss": 0.95861572265625, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.08582872401296968, |
| "grad_norm": 1.108496069908142, |
| "learning_rate": 0.00019931239564382073, |
| "loss": 0.9668975067138672, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.09536524890329964, |
| "grad_norm": 0.855691134929657, |
| "learning_rate": 0.0001988938023060968, |
| "loss": 0.9651553344726562, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.09536524890329964, |
| "eval_loss": 0.9762284159660339, |
| "eval_runtime": 680.8217, |
| "eval_samples_per_second": 12.536, |
| "eval_steps_per_second": 0.784, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.1049017737936296, |
| "grad_norm": 0.8507081866264343, |
| "learning_rate": 0.0001983768273105382, |
| "loss": 0.9656350708007813, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.11443829868395956, |
| "grad_norm": 0.8325157165527344, |
| "learning_rate": 0.00019776198495486565, |
| "loss": 0.9318672180175781, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.12397482357428953, |
| "grad_norm": 0.9234330654144287, |
| "learning_rate": 0.0001970498868973313, |
| "loss": 0.9393777465820312, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.13351134846461948, |
| "grad_norm": 0.8355016708374023, |
| "learning_rate": 0.0001962412415482278, |
| "loss": 0.9270508575439453, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.14304787335494945, |
| "grad_norm": 0.9328432083129883, |
| "learning_rate": 0.00019533685336514697, |
| "loss": 0.9209387969970703, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.15258439824527942, |
| "grad_norm": 1.194154977798462, |
| "learning_rate": 0.00019433762205268805, |
| "loss": 0.9753380584716796, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.16212092313560938, |
| "grad_norm": 0.9554775953292847, |
| "learning_rate": 0.0001932445416674127, |
| "loss": 0.9683086395263671, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.17165744802593935, |
| "grad_norm": 1.0252937078475952, |
| "learning_rate": 0.00019205869962893605, |
| "loss": 0.9329315948486329, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.18119397291626932, |
| "grad_norm": 1.2285805940628052, |
| "learning_rate": 0.00019078127563813883, |
| "loss": 0.9511469268798828, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.1907304978065993, |
| "grad_norm": 0.9454661011695862, |
| "learning_rate": 0.00018941354050357566, |
| "loss": 0.951951904296875, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.1907304978065993, |
| "eval_loss": 0.9598119258880615, |
| "eval_runtime": 680.8627, |
| "eval_samples_per_second": 12.536, |
| "eval_steps_per_second": 0.784, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.20026702269692923, |
| "grad_norm": 1.0210950374603271, |
| "learning_rate": 0.00018795685487724782, |
| "loss": 0.9263379669189453, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.2098035475872592, |
| "grad_norm": 1.0087344646453857, |
| "learning_rate": 0.0001864126679009975, |
| "loss": 0.9310942840576172, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.21934007247758916, |
| "grad_norm": 1.1398996114730835, |
| "learning_rate": 0.00018478251576487092, |
| "loss": 0.9465924072265625, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.22887659736791913, |
| "grad_norm": 0.9276406764984131, |
| "learning_rate": 0.0001830680201788836, |
| "loss": 0.9552659606933593, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.2384131222582491, |
| "grad_norm": 1.0002596378326416, |
| "learning_rate": 0.00018127088675970888, |
| "loss": 0.9471788024902343, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.24794964714857906, |
| "grad_norm": 1.0108773708343506, |
| "learning_rate": 0.000179392903333894, |
| "loss": 0.9245248413085938, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.257486172038909, |
| "grad_norm": 0.9765293002128601, |
| "learning_rate": 0.0001774359381592925, |
| "loss": 0.9204165649414062, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.26702269692923897, |
| "grad_norm": 1.0059659481048584, |
| "learning_rate": 0.00017540193806648134, |
| "loss": 0.9452506256103516, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.27655922181956893, |
| "grad_norm": 1.1858373880386353, |
| "learning_rate": 0.0001732929265220125, |
| "loss": 0.9286368560791015, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.2860957467098989, |
| "grad_norm": 1.0006766319274902, |
| "learning_rate": 0.00017111100161542545, |
| "loss": 0.9553109741210938, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.2860957467098989, |
| "eval_loss": 0.9582533836364746, |
| "eval_runtime": 680.822, |
| "eval_samples_per_second": 12.536, |
| "eval_steps_per_second": 0.784, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.29563227160022887, |
| "grad_norm": 0.9042516350746155, |
| "learning_rate": 0.00016885833397202308, |
| "loss": 0.93341796875, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.30516879649055884, |
| "grad_norm": 0.9387173652648926, |
| "learning_rate": 0.00016653716459348735, |
| "loss": 0.9339485168457031, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.3147053213808888, |
| "grad_norm": 0.9056106209754944, |
| "learning_rate": 0.00016414980262848333, |
| "loss": 0.9324442291259766, |
| "step": 1650 |
| }, |
| { |
| "epoch": 0.32424184627121877, |
| "grad_norm": 0.9407602548599243, |
| "learning_rate": 0.0001616986230754689, |
| "loss": 0.9319153594970703, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.33377837116154874, |
| "grad_norm": 0.9982315897941589, |
| "learning_rate": 0.0001591860644199957, |
| "loss": 0.9230084228515625, |
| "step": 1750 |
| }, |
| { |
| "epoch": 0.3433148960518787, |
| "grad_norm": 1.0833745002746582, |
| "learning_rate": 0.00015661462620885199, |
| "loss": 0.9161262512207031, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.35285142094220867, |
| "grad_norm": 0.9810793995857239, |
| "learning_rate": 0.00015398686656346028, |
| "loss": 0.9208243560791015, |
| "step": 1850 |
| }, |
| { |
| "epoch": 0.36238794583253864, |
| "grad_norm": 1.094853401184082, |
| "learning_rate": 0.00015130539963500376, |
| "loss": 0.9387385559082031, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.3719244707228686, |
| "grad_norm": 0.8733468055725098, |
| "learning_rate": 0.000148572893003813, |
| "loss": 0.9468997955322266, |
| "step": 1950 |
| }, |
| { |
| "epoch": 0.3814609956131986, |
| "grad_norm": 1.0074750185012817, |
| "learning_rate": 0.0001457920650256004, |
| "loss": 0.9178851318359375, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.3814609956131986, |
| "eval_loss": 0.9489485025405884, |
| "eval_runtime": 681.5678, |
| "eval_samples_per_second": 12.523, |
| "eval_steps_per_second": 0.783, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.39099752050352854, |
| "grad_norm": 1.0041425228118896, |
| "learning_rate": 0.00014296568212718213, |
| "loss": 0.9244281005859375, |
| "step": 2050 |
| }, |
| { |
| "epoch": 0.40053404539385845, |
| "grad_norm": 1.0447967052459717, |
| "learning_rate": 0.0001400965560543778, |
| "loss": 0.9248933410644531, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.4100705702841884, |
| "grad_norm": 0.968345046043396, |
| "learning_rate": 0.00013718754107482596, |
| "loss": 0.9109151458740234, |
| "step": 2150 |
| }, |
| { |
| "epoch": 0.4196070951745184, |
| "grad_norm": 0.9737382531166077, |
| "learning_rate": 0.0001342415311384981, |
| "loss": 0.9231878662109375, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.42914362006484835, |
| "grad_norm": 1.0494582653045654, |
| "learning_rate": 0.00013126145699873532, |
| "loss": 0.9193107604980468, |
| "step": 2250 |
| }, |
| { |
| "epoch": 0.4386801449551783, |
| "grad_norm": 0.925656259059906, |
| "learning_rate": 0.000128250283296673, |
| "loss": 0.9101874542236328, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.4482166698455083, |
| "grad_norm": 1.0119520425796509, |
| "learning_rate": 0.00012521100561195233, |
| "loss": 0.8976884460449219, |
| "step": 2350 |
| }, |
| { |
| "epoch": 0.45775319473583825, |
| "grad_norm": 0.9749938249588013, |
| "learning_rate": 0.0001221466474826543, |
| "loss": 0.9223648834228516, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.4672897196261682, |
| "grad_norm": 1.071219563484192, |
| "learning_rate": 0.00011906025739741956, |
| "loss": 0.9097858428955078, |
| "step": 2450 |
| }, |
| { |
| "epoch": 0.4768262445164982, |
| "grad_norm": 1.0023361444473267, |
| "learning_rate": 0.00011595490576274704, |
| "loss": 0.9021361541748046, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.4768262445164982, |
| "eval_loss": 0.9404354095458984, |
| "eval_runtime": 681.2848, |
| "eval_samples_per_second": 12.528, |
| "eval_steps_per_second": 0.784, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.48636276940682815, |
| "grad_norm": 0.7936119437217712, |
| "learning_rate": 0.00011283368184848842, |
| "loss": 0.9291069030761718, |
| "step": 2550 |
| }, |
| { |
| "epoch": 0.4958992942971581, |
| "grad_norm": 0.8363732695579529, |
| "learning_rate": 0.00010969969071457669, |
| "loss": 0.8912797546386719, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.505435819187488, |
| "grad_norm": 0.9047644734382629, |
| "learning_rate": 0.0001065560501220464, |
| "loss": 0.8831972503662109, |
| "step": 2650 |
| }, |
| { |
| "epoch": 0.514972344077818, |
| "grad_norm": 0.8407217264175415, |
| "learning_rate": 0.00010340588743141879, |
| "loss": 0.9096057891845704, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.524508868968148, |
| "grad_norm": 0.9929122924804688, |
| "learning_rate": 0.00010025233649153707, |
| "loss": 0.9299073028564453, |
| "step": 2750 |
| }, |
| { |
| "epoch": 0.5340453938584779, |
| "grad_norm": 1.0364736318588257, |
| "learning_rate": 9.70985345219468e-05, |
| "loss": 0.9169498443603515, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.5435819187488079, |
| "grad_norm": 0.9246217012405396, |
| "learning_rate": 9.394761899192327e-05, |
| "loss": 0.8965087127685547, |
| "step": 2850 |
| }, |
| { |
| "epoch": 0.5531184436391379, |
| "grad_norm": 0.9324344992637634, |
| "learning_rate": 9.08027244992503e-05, |
| "loss": 0.9102237701416016, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.5626549685294678, |
| "grad_norm": 0.998298704624176, |
| "learning_rate": 8.766697965185565e-05, |
| "loss": 0.9192097473144532, |
| "step": 2950 |
| }, |
| { |
| "epoch": 0.5721914934197978, |
| "grad_norm": 0.9278152585029602, |
| "learning_rate": 8.45435039554054e-05, |
| "loss": 0.9202249908447265, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.5721914934197978, |
| "eval_loss": 0.9327928423881531, |
| "eval_runtime": 680.7868, |
| "eval_samples_per_second": 12.537, |
| "eval_steps_per_second": 0.784, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.5817280183101278, |
| "grad_norm": 1.0032947063446045, |
| "learning_rate": 8.14354047099533e-05, |
| "loss": 0.9145193481445313, |
| "step": 3050 |
| }, |
| { |
| "epoch": 0.5912645432004577, |
| "grad_norm": 0.834137499332428, |
| "learning_rate": 7.834577391873266e-05, |
| "loss": 0.9149667358398438, |
| "step": 3100 |
| }, |
| { |
| "epoch": 0.6008010680907877, |
| "grad_norm": 0.9321780204772949, |
| "learning_rate": 7.527768521216568e-05, |
| "loss": 0.892784652709961, |
| "step": 3150 |
| }, |
| { |
| "epoch": 0.6103375929811177, |
| "grad_norm": 1.0074846744537354, |
| "learning_rate": 7.223419079015062e-05, |
| "loss": 0.9072589111328125, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.6198741178714476, |
| "grad_norm": 1.2590699195861816, |
| "learning_rate": 6.921831838566842e-05, |
| "loss": 0.9023927307128906, |
| "step": 3250 |
| }, |
| { |
| "epoch": 0.6294106427617776, |
| "grad_norm": 0.7596737742424011, |
| "learning_rate": 6.623306825272937e-05, |
| "loss": 0.896091079711914, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.6389471676521076, |
| "grad_norm": 0.9938393831253052, |
| "learning_rate": 6.328141018165693e-05, |
| "loss": 0.9024559783935547, |
| "step": 3350 |
| }, |
| { |
| "epoch": 0.6484836925424375, |
| "grad_norm": 0.8195408582687378, |
| "learning_rate": 6.036628054467682e-05, |
| "loss": 0.8873242950439453, |
| "step": 3400 |
| }, |
| { |
| "epoch": 0.6580202174327675, |
| "grad_norm": 0.9234633445739746, |
| "learning_rate": 5.7490579374751686e-05, |
| "loss": 0.8969253540039063, |
| "step": 3450 |
| }, |
| { |
| "epoch": 0.6675567423230975, |
| "grad_norm": 0.9521735906600952, |
| "learning_rate": 5.4657167480566594e-05, |
| "loss": 0.8936698913574219, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.6675567423230975, |
| "eval_loss": 0.9270365238189697, |
| "eval_runtime": 680.6766, |
| "eval_samples_per_second": 12.539, |
| "eval_steps_per_second": 0.785, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.6770932672134274, |
| "grad_norm": 0.9278208613395691, |
| "learning_rate": 5.1868863600535646e-05, |
| "loss": 0.8819551849365235, |
| "step": 3550 |
| }, |
| { |
| "epoch": 0.6866297921037574, |
| "grad_norm": 0.8966768383979797, |
| "learning_rate": 4.912844159866112e-05, |
| "loss": 0.905844955444336, |
| "step": 3600 |
| }, |
| { |
| "epoch": 0.6961663169940874, |
| "grad_norm": 0.886394202709198, |
| "learning_rate": 4.6438627705034535e-05, |
| "loss": 0.8963019561767578, |
| "step": 3650 |
| }, |
| { |
| "epoch": 0.7057028418844173, |
| "grad_norm": 1.0538233518600464, |
| "learning_rate": 4.380209780372496e-05, |
| "loss": 0.8904299926757813, |
| "step": 3700 |
| }, |
| { |
| "epoch": 0.7152393667747473, |
| "grad_norm": 1.0238487720489502, |
| "learning_rate": 4.12214747707527e-05, |
| "loss": 0.9049517822265625, |
| "step": 3750 |
| }, |
| { |
| "epoch": 0.7247758916650773, |
| "grad_norm": 0.913487434387207, |
| "learning_rate": 3.869932586479628e-05, |
| "loss": 0.8899057006835938, |
| "step": 3800 |
| }, |
| { |
| "epoch": 0.7343124165554072, |
| "grad_norm": 0.8777801990509033, |
| "learning_rate": 3.623816017322917e-05, |
| "loss": 0.8895880889892578, |
| "step": 3850 |
| }, |
| { |
| "epoch": 0.7438489414457372, |
| "grad_norm": 1.0374138355255127, |
| "learning_rate": 3.3840426116026044e-05, |
| "loss": 0.9089337921142578, |
| "step": 3900 |
| }, |
| { |
| "epoch": 0.7533854663360672, |
| "grad_norm": 1.0942944288253784, |
| "learning_rate": 3.150850901002268e-05, |
| "loss": 0.8874909210205079, |
| "step": 3950 |
| }, |
| { |
| "epoch": 0.7629219912263971, |
| "grad_norm": 0.8818588256835938, |
| "learning_rate": 2.9244728695951995e-05, |
| "loss": 0.8881364440917969, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.7629219912263971, |
| "eval_loss": 0.921961784362793, |
| "eval_runtime": 680.8471, |
| "eval_samples_per_second": 12.536, |
| "eval_steps_per_second": 0.784, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.7724585161167271, |
| "grad_norm": 0.8658433556556702, |
| "learning_rate": 2.7051337230617125e-05, |
| "loss": 0.887118148803711, |
| "step": 4050 |
| }, |
| { |
| "epoch": 0.7819950410070571, |
| "grad_norm": 1.0360819101333618, |
| "learning_rate": 2.4930516646497448e-05, |
| "loss": 0.9029306030273437, |
| "step": 4100 |
| }, |
| { |
| "epoch": 0.791531565897387, |
| "grad_norm": 0.9453035593032837, |
| "learning_rate": 2.2884376781016258e-05, |
| "loss": 0.874930419921875, |
| "step": 4150 |
| }, |
| { |
| "epoch": 0.8010680907877169, |
| "grad_norm": 0.9671445488929749, |
| "learning_rate": 2.0914953177629548e-05, |
| "loss": 0.8965608978271484, |
| "step": 4200 |
| }, |
| { |
| "epoch": 0.8106046156780469, |
| "grad_norm": 0.9346293210983276, |
| "learning_rate": 1.902420506082424e-05, |
| "loss": 0.8860881042480468, |
| "step": 4250 |
| }, |
| { |
| "epoch": 0.8201411405683768, |
| "grad_norm": 1.0210144519805908, |
| "learning_rate": 1.7214013387039884e-05, |
| "loss": 0.9090773773193359, |
| "step": 4300 |
| }, |
| { |
| "epoch": 0.8296776654587068, |
| "grad_norm": 0.7916406393051147, |
| "learning_rate": 1.54861789734532e-05, |
| "loss": 0.9077362060546875, |
| "step": 4350 |
| }, |
| { |
| "epoch": 0.8392141903490368, |
| "grad_norm": 0.849738597869873, |
| "learning_rate": 1.3842420706486903e-05, |
| "loss": 0.8971955871582031, |
| "step": 4400 |
| }, |
| { |
| "epoch": 0.8487507152393667, |
| "grad_norm": 0.8733137845993042, |
| "learning_rate": 1.2284373831824847e-05, |
| "loss": 0.8827657318115234, |
| "step": 4450 |
| }, |
| { |
| "epoch": 0.8582872401296967, |
| "grad_norm": 0.9427047967910767, |
| "learning_rate": 1.0813588327634961e-05, |
| "loss": 0.8771236419677735, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.8582872401296967, |
| "eval_loss": 0.9178871512413025, |
| "eval_runtime": 680.8349, |
| "eval_samples_per_second": 12.536, |
| "eval_steps_per_second": 0.784, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.8678237650200267, |
| "grad_norm": 0.8574934005737305, |
| "learning_rate": 9.431527362617832e-06, |
| "loss": 0.8978910827636719, |
| "step": 4550 |
| }, |
| { |
| "epoch": 0.8773602899103566, |
| "grad_norm": 0.986375629901886, |
| "learning_rate": 8.139565840415553e-06, |
| "loss": 0.8829045867919922, |
| "step": 4600 |
| }, |
| { |
| "epoch": 0.8868968148006866, |
| "grad_norm": 1.026666283607483, |
| "learning_rate": 6.938989031828158e-06, |
| "loss": 0.8786582183837891, |
| "step": 4650 |
| }, |
| { |
| "epoch": 0.8964333396910166, |
| "grad_norm": 0.9898380041122437, |
| "learning_rate": 5.8309912961990506e-06, |
| "loss": 0.8815351867675781, |
| "step": 4700 |
| }, |
| { |
| "epoch": 0.9059698645813465, |
| "grad_norm": 0.8167511224746704, |
| "learning_rate": 4.8166748932408355e-06, |
| "loss": 0.8737747192382812, |
| "step": 4750 |
| }, |
| { |
| "epoch": 0.9155063894716765, |
| "grad_norm": 0.9592494368553162, |
| "learning_rate": 3.8970488864839334e-06, |
| "loss": 0.886360092163086, |
| "step": 4800 |
| }, |
| { |
| "epoch": 0.9250429143620065, |
| "grad_norm": 1.1282484531402588, |
| "learning_rate": 3.0730281394387382e-06, |
| "loss": 0.9033355712890625, |
| "step": 4850 |
| }, |
| { |
| "epoch": 0.9345794392523364, |
| "grad_norm": 1.0762990713119507, |
| "learning_rate": 2.345432405469894e-06, |
| "loss": 0.9018070983886719, |
| "step": 4900 |
| }, |
| { |
| "epoch": 0.9441159641426664, |
| "grad_norm": 1.0391168594360352, |
| "learning_rate": 1.7149855122882697e-06, |
| "loss": 0.8773787689208984, |
| "step": 4950 |
| }, |
| { |
| "epoch": 0.9536524890329964, |
| "grad_norm": 1.160536527633667, |
| "learning_rate": 1.1823146418717068e-06, |
| "loss": 0.8903836822509765, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.9536524890329964, |
| "eval_loss": 0.9169394373893738, |
| "eval_runtime": 681.071, |
| "eval_samples_per_second": 12.532, |
| "eval_steps_per_second": 0.784, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.9631890139233263, |
| "grad_norm": 0.823947548866272, |
| "learning_rate": 7.479497065310925e-07, |
| "loss": 0.90203857421875, |
| "step": 5050 |
| }, |
| { |
| "epoch": 0.9727255388136563, |
| "grad_norm": 0.7839481830596924, |
| "learning_rate": 4.123228217422948e-07, |
| "loss": 0.8997705078125, |
| "step": 5100 |
| }, |
| { |
| "epoch": 0.9822620637039863, |
| "grad_norm": 0.9920501708984375, |
| "learning_rate": 1.7576787626851777e-07, |
| "loss": 0.8869709777832031, |
| "step": 5150 |
| }, |
| { |
| "epoch": 0.9917985885943162, |
| "grad_norm": 0.9276648759841919, |
| "learning_rate": 3.8520200000624615e-08, |
| "loss": 0.8911021423339843, |
| "step": 5200 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.9169082045555115, |
| "eval_runtime": 681.3749, |
| "eval_samples_per_second": 12.526, |
| "eval_steps_per_second": 0.784, |
| "step": 5243 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 5243, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.345861112836915e+18, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
