| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.866113574595909, | |
| "eval_steps": 400, | |
| "global_step": 24000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014304105278214848, | |
| "grad_norm": 3.5871307485399613, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 4.2171, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028608210556429696, | |
| "grad_norm": 8.578020193760794, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 3.5086, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04291231583464454, | |
| "grad_norm": 3.453360153921811, | |
| "learning_rate": 5e-06, | |
| "loss": 2.7411, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05721642111285939, | |
| "grad_norm": 6.637419959801433, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.5587, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07152052639107424, | |
| "grad_norm": 5.39103050730964, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 2.4626, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08582463166928908, | |
| "grad_norm": 10.145361416938202, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3934, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10012873694750393, | |
| "grad_norm": 7.783722807777708, | |
| "learning_rate": 9.999953760295448e-06, | |
| "loss": 2.272, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.11443284222571878, | |
| "grad_norm": 3.65791345167478, | |
| "learning_rate": 9.999815042132062e-06, | |
| "loss": 2.2033, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11443284222571878, | |
| "eval_loss": 2.1356396675109863, | |
| "eval_runtime": 13.2089, | |
| "eval_samples_per_second": 75.707, | |
| "eval_steps_per_second": 2.423, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12873694750393364, | |
| "grad_norm": 8.621408307551274, | |
| "learning_rate": 9.999583848360633e-06, | |
| "loss": 2.1457, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1430410527821485, | |
| "grad_norm": 6.2605099034671, | |
| "learning_rate": 9.999260183732424e-06, | |
| "loss": 2.1022, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1573451580603633, | |
| "grad_norm": 7.684157630671387, | |
| "learning_rate": 9.998844054899058e-06, | |
| "loss": 2.0793, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.17164926333857816, | |
| "grad_norm": 1.7771086513044794, | |
| "learning_rate": 9.998335470412393e-06, | |
| "loss": 2.0783, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.185953368616793, | |
| "grad_norm": 4.839674439593447, | |
| "learning_rate": 9.997734440724333e-06, | |
| "loss": 2.0455, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.20025747389500786, | |
| "grad_norm": 1.7547598316419108, | |
| "learning_rate": 9.997040978186633e-06, | |
| "loss": 2.0206, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.21456157917322272, | |
| "grad_norm": 2.5514452897242035, | |
| "learning_rate": 9.996255097050624e-06, | |
| "loss": 2.003, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.22886568445143757, | |
| "grad_norm": 3.9407907366389976, | |
| "learning_rate": 9.995376813466934e-06, | |
| "loss": 1.9948, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.22886568445143757, | |
| "eval_loss": 1.9659738540649414, | |
| "eval_runtime": 13.202, | |
| "eval_samples_per_second": 75.746, | |
| "eval_steps_per_second": 2.424, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24316978972965242, | |
| "grad_norm": 1.7301759518540019, | |
| "learning_rate": 9.994406145485151e-06, | |
| "loss": 1.9861, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.25747389500786727, | |
| "grad_norm": 4.606477014527872, | |
| "learning_rate": 9.993343113053454e-06, | |
| "loss": 1.9713, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.2717780002860821, | |
| "grad_norm": 2.8102943343276183, | |
| "learning_rate": 9.992187738018203e-06, | |
| "loss": 1.9675, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.286082105564297, | |
| "grad_norm": 1.6938293305410583, | |
| "learning_rate": 9.99094004412348e-06, | |
| "loss": 1.9556, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3003862108425118, | |
| "grad_norm": 3.4489466081512044, | |
| "learning_rate": 9.989600057010625e-06, | |
| "loss": 1.9417, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.3146903161207266, | |
| "grad_norm": 1.454314969912362, | |
| "learning_rate": 9.988167804217682e-06, | |
| "loss": 1.9361, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.3289944213989415, | |
| "grad_norm": 1.168052123243911, | |
| "learning_rate": 9.986643315178848e-06, | |
| "loss": 1.9264, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.3432985266771563, | |
| "grad_norm": 1.7334339924315771, | |
| "learning_rate": 9.98502662122387e-06, | |
| "loss": 1.9308, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3432985266771563, | |
| "eval_loss": 1.8975478410720825, | |
| "eval_runtime": 13.3147, | |
| "eval_samples_per_second": 75.105, | |
| "eval_steps_per_second": 2.403, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3576026319553712, | |
| "grad_norm": 1.5051784354611382, | |
| "learning_rate": 9.983317755577392e-06, | |
| "loss": 1.9208, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.371906737233586, | |
| "grad_norm": 1.5926471600228091, | |
| "learning_rate": 9.981516753358274e-06, | |
| "loss": 1.9156, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.3862108425118009, | |
| "grad_norm": 1.4680846710500992, | |
| "learning_rate": 9.979623651578881e-06, | |
| "loss": 1.9003, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.40051494779001573, | |
| "grad_norm": 1.3763604778464051, | |
| "learning_rate": 9.977638489144308e-06, | |
| "loss": 1.9069, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.4148190530682306, | |
| "grad_norm": 1.524436140637499, | |
| "learning_rate": 9.975561306851585e-06, | |
| "loss": 1.8973, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.42912315834644543, | |
| "grad_norm": 1.6595586978206922, | |
| "learning_rate": 9.973392147388847e-06, | |
| "loss": 1.8994, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4434272636246603, | |
| "grad_norm": 1.5658370421245245, | |
| "learning_rate": 9.971131055334445e-06, | |
| "loss": 1.8875, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.45773136890287514, | |
| "grad_norm": 1.9874689334717497, | |
| "learning_rate": 9.968778077156035e-06, | |
| "loss": 1.8885, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.45773136890287514, | |
| "eval_loss": 1.8600050210952759, | |
| "eval_runtime": 13.4365, | |
| "eval_samples_per_second": 74.424, | |
| "eval_steps_per_second": 2.382, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.47203547418109, | |
| "grad_norm": 1.391686515937597, | |
| "learning_rate": 9.966333261209625e-06, | |
| "loss": 1.8825, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.48633957945930484, | |
| "grad_norm": 1.250031324432951, | |
| "learning_rate": 9.96379665773858e-06, | |
| "loss": 1.8812, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5006436847375196, | |
| "grad_norm": 0.937500185481468, | |
| "learning_rate": 9.961168318872583e-06, | |
| "loss": 1.873, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.5149477900157345, | |
| "grad_norm": 1.3831225145690145, | |
| "learning_rate": 9.958448298626576e-06, | |
| "loss": 1.8733, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5292518952939493, | |
| "grad_norm": 2.8853368812546845, | |
| "learning_rate": 9.95563665289964e-06, | |
| "loss": 1.8607, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.5435560005721642, | |
| "grad_norm": 1.8333114897013831, | |
| "learning_rate": 9.952733439473847e-06, | |
| "loss": 1.867, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.557860105850379, | |
| "grad_norm": 1.4955344425097794, | |
| "learning_rate": 9.94973871801308e-06, | |
| "loss": 1.8668, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.572164211128594, | |
| "grad_norm": 1.058766324989062, | |
| "learning_rate": 9.946652550061798e-06, | |
| "loss": 1.8468, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.572164211128594, | |
| "eval_loss": 1.8319525718688965, | |
| "eval_runtime": 13.2128, | |
| "eval_samples_per_second": 75.684, | |
| "eval_steps_per_second": 2.422, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5864683164068087, | |
| "grad_norm": 1.061225891590699, | |
| "learning_rate": 9.943474999043775e-06, | |
| "loss": 1.8513, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.6007724216850236, | |
| "grad_norm": 1.8307541279709998, | |
| "learning_rate": 9.9402061302608e-06, | |
| "loss": 1.8489, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.6150765269632384, | |
| "grad_norm": 1.3493002065305932, | |
| "learning_rate": 9.93684601089133e-06, | |
| "loss": 1.8428, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.6293806322414532, | |
| "grad_norm": 1.3269702867770274, | |
| "learning_rate": 9.933394709989109e-06, | |
| "loss": 1.8485, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6436847375196681, | |
| "grad_norm": 1.3587430620093466, | |
| "learning_rate": 9.92985229848175e-06, | |
| "loss": 1.8323, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.657988842797883, | |
| "grad_norm": 1.6220456911234815, | |
| "learning_rate": 9.926218849169284e-06, | |
| "loss": 1.8417, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6722929480760979, | |
| "grad_norm": 1.3306733931984986, | |
| "learning_rate": 9.922494436722653e-06, | |
| "loss": 1.8319, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.6865970533543126, | |
| "grad_norm": 1.841456096268586, | |
| "learning_rate": 9.91867913768218e-06, | |
| "loss": 1.8221, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.6865970533543126, | |
| "eval_loss": 1.8098633289337158, | |
| "eval_runtime": 13.2499, | |
| "eval_samples_per_second": 75.472, | |
| "eval_steps_per_second": 2.415, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.7009011586325276, | |
| "grad_norm": 1.0743552491621962, | |
| "learning_rate": 9.914773030456001e-06, | |
| "loss": 1.8264, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.7152052639107424, | |
| "grad_norm": 0.9817511549306134, | |
| "learning_rate": 9.910776195318448e-06, | |
| "loss": 1.8339, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7295093691889573, | |
| "grad_norm": 2.5586651091316166, | |
| "learning_rate": 9.906688714408396e-06, | |
| "loss": 1.8361, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.743813474467172, | |
| "grad_norm": 1.3521713422261818, | |
| "learning_rate": 9.902510671727583e-06, | |
| "loss": 1.8172, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.758117579745387, | |
| "grad_norm": 1.196264818533523, | |
| "learning_rate": 9.898242153138882e-06, | |
| "loss": 1.815, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.7724216850236018, | |
| "grad_norm": 1.1236416672692373, | |
| "learning_rate": 9.89388324636453e-06, | |
| "loss": 1.8217, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.7867257903018167, | |
| "grad_norm": 1.0482615125286014, | |
| "learning_rate": 9.889434040984333e-06, | |
| "loss": 1.8111, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.8010298955800315, | |
| "grad_norm": 1.2877895138097581, | |
| "learning_rate": 9.88489462843382e-06, | |
| "loss": 1.8139, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.8010298955800315, | |
| "eval_loss": 1.7917475700378418, | |
| "eval_runtime": 13.2172, | |
| "eval_samples_per_second": 75.659, | |
| "eval_steps_per_second": 2.421, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.8153340008582464, | |
| "grad_norm": 1.3263953998902482, | |
| "learning_rate": 9.880265102002369e-06, | |
| "loss": 1.7969, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.8296381061364612, | |
| "grad_norm": 0.8011721107369111, | |
| "learning_rate": 9.875545556831283e-06, | |
| "loss": 1.8123, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.843942211414676, | |
| "grad_norm": 1.452056398499391, | |
| "learning_rate": 9.870736089911836e-06, | |
| "loss": 1.8137, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.8582463166928909, | |
| "grad_norm": 1.1618490357992515, | |
| "learning_rate": 9.865836800083291e-06, | |
| "loss": 1.812, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8725504219711057, | |
| "grad_norm": 1.2693408191050113, | |
| "learning_rate": 9.860847788030852e-06, | |
| "loss": 1.7989, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.8868545272493206, | |
| "grad_norm": 1.1394593474503365, | |
| "learning_rate": 9.855769156283604e-06, | |
| "loss": 1.8068, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.9011586325275354, | |
| "grad_norm": 1.739305216161417, | |
| "learning_rate": 9.850601009212408e-06, | |
| "loss": 1.8026, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.9154627378057503, | |
| "grad_norm": 0.9509459350795362, | |
| "learning_rate": 9.845343453027747e-06, | |
| "loss": 1.8055, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.9154627378057503, | |
| "eval_loss": 1.7801611423492432, | |
| "eval_runtime": 13.218, | |
| "eval_samples_per_second": 75.654, | |
| "eval_steps_per_second": 2.421, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.9297668430839651, | |
| "grad_norm": 1.279124709454881, | |
| "learning_rate": 9.839996595777552e-06, | |
| "loss": 1.7968, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.94407094836218, | |
| "grad_norm": 1.092437156034456, | |
| "learning_rate": 9.83456054734498e-06, | |
| "loss": 1.7892, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9583750536403948, | |
| "grad_norm": 0.9619111877602855, | |
| "learning_rate": 9.829035419446156e-06, | |
| "loss": 1.7951, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.9726791589186097, | |
| "grad_norm": 0.9476479377652314, | |
| "learning_rate": 9.823421325627865e-06, | |
| "loss": 1.8003, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.9869832641968245, | |
| "grad_norm": 0.7761637732992411, | |
| "learning_rate": 9.81771838126524e-06, | |
| "loss": 1.7852, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.0012873694750393, | |
| "grad_norm": 1.6427439742947594, | |
| "learning_rate": 9.811926703559374e-06, | |
| "loss": 1.7813, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0155914747532542, | |
| "grad_norm": 1.1995527718721077, | |
| "learning_rate": 9.806046411534916e-06, | |
| "loss": 1.7693, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.029895580031469, | |
| "grad_norm": 0.6804399746581633, | |
| "learning_rate": 9.800077626037633e-06, | |
| "loss": 1.7779, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.029895580031469, | |
| "eval_loss": 1.770551323890686, | |
| "eval_runtime": 13.1907, | |
| "eval_samples_per_second": 75.811, | |
| "eval_steps_per_second": 2.426, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.044199685309684, | |
| "grad_norm": 0.9739432549705861, | |
| "learning_rate": 9.794020469731915e-06, | |
| "loss": 1.7844, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.0585037905878987, | |
| "grad_norm": 1.24072763349112, | |
| "learning_rate": 9.787875067098257e-06, | |
| "loss": 1.7826, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.0728078958661136, | |
| "grad_norm": 1.0497808533387654, | |
| "learning_rate": 9.781641544430703e-06, | |
| "loss": 1.7875, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.0871120011443285, | |
| "grad_norm": 1.608878092364201, | |
| "learning_rate": 9.775320029834255e-06, | |
| "loss": 1.7676, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.1014161064225432, | |
| "grad_norm": 0.8265375857322264, | |
| "learning_rate": 9.76891065322223e-06, | |
| "loss": 1.7758, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.115720211700758, | |
| "grad_norm": 0.8074509140095618, | |
| "learning_rate": 9.762413546313597e-06, | |
| "loss": 1.773, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.130024316978973, | |
| "grad_norm": 1.2955529307297018, | |
| "learning_rate": 9.755828842630269e-06, | |
| "loss": 1.7653, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.144328422257188, | |
| "grad_norm": 0.9723230317765355, | |
| "learning_rate": 9.749156677494357e-06, | |
| "loss": 1.7813, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.144328422257188, | |
| "eval_loss": 1.7602086067199707, | |
| "eval_runtime": 13.0715, | |
| "eval_samples_per_second": 76.502, | |
| "eval_steps_per_second": 2.448, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.1587755685881849, | |
| "grad_norm": 1.6203576789230651, | |
| "learning_rate": 9.742397188025394e-06, | |
| "loss": 1.7709, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.1730796738663996, | |
| "grad_norm": 1.1690135821413727, | |
| "learning_rate": 9.735550513137513e-06, | |
| "loss": 1.7583, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.1873837791446145, | |
| "grad_norm": 1.2584964373503669, | |
| "learning_rate": 9.728616793536588e-06, | |
| "loss": 1.7653, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.2016878844228294, | |
| "grad_norm": 1.022986798804273, | |
| "learning_rate": 9.721596171717352e-06, | |
| "loss": 1.7661, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.2159919897010443, | |
| "grad_norm": 0.9715095488392225, | |
| "learning_rate": 9.714488791960463e-06, | |
| "loss": 1.7745, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.230296094979259, | |
| "grad_norm": 1.1370122008173429, | |
| "learning_rate": 9.707294800329536e-06, | |
| "loss": 1.7684, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.2446002002574739, | |
| "grad_norm": 0.9536116406695613, | |
| "learning_rate": 9.700014344668152e-06, | |
| "loss": 1.7606, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.2589043055356888, | |
| "grad_norm": 0.7353885681465049, | |
| "learning_rate": 9.692647574596803e-06, | |
| "loss": 1.7633, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.2589043055356888, | |
| "eval_loss": 1.752835988998413, | |
| "eval_runtime": 13.2443, | |
| "eval_samples_per_second": 75.504, | |
| "eval_steps_per_second": 2.416, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.2732084108139037, | |
| "grad_norm": 1.1802783991524877, | |
| "learning_rate": 9.685194641509837e-06, | |
| "loss": 1.7686, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.2875125160921184, | |
| "grad_norm": 0.9318456023565893, | |
| "learning_rate": 9.677655698572326e-06, | |
| "loss": 1.7556, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.3018166213703333, | |
| "grad_norm": 1.0437155245378358, | |
| "learning_rate": 9.670030900716941e-06, | |
| "loss": 1.7571, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 1.3161207266485482, | |
| "grad_norm": 1.0912943460238356, | |
| "learning_rate": 9.662320404640743e-06, | |
| "loss": 1.7546, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.3304248319267629, | |
| "grad_norm": 1.0063174963239234, | |
| "learning_rate": 9.654524368801982e-06, | |
| "loss": 1.7644, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.3447289372049778, | |
| "grad_norm": 1.0417193249219145, | |
| "learning_rate": 9.646642953416835e-06, | |
| "loss": 1.7525, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.3590330424831927, | |
| "grad_norm": 0.698422675064761, | |
| "learning_rate": 9.638676320456109e-06, | |
| "loss": 1.7586, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 1.3733371477614076, | |
| "grad_norm": 1.1910335445073554, | |
| "learning_rate": 9.630624633641918e-06, | |
| "loss": 1.7528, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.3733371477614076, | |
| "eval_loss": 1.7467565536499023, | |
| "eval_runtime": 13.1696, | |
| "eval_samples_per_second": 75.932, | |
| "eval_steps_per_second": 2.43, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.3876412530396225, | |
| "grad_norm": 0.860266713830524, | |
| "learning_rate": 9.622488058444313e-06, | |
| "loss": 1.7526, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 1.4019453583178372, | |
| "grad_norm": 0.6381947527857678, | |
| "learning_rate": 9.614266762077891e-06, | |
| "loss": 1.7548, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.416249463596052, | |
| "grad_norm": 0.7554075411255639, | |
| "learning_rate": 9.605960913498342e-06, | |
| "loss": 1.7481, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.430553568874267, | |
| "grad_norm": 1.2154500150186984, | |
| "learning_rate": 9.597570683398996e-06, | |
| "loss": 1.7584, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.4448576741524817, | |
| "grad_norm": 0.6439874478006935, | |
| "learning_rate": 9.5890962442073e-06, | |
| "loss": 1.7445, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 1.4591617794306966, | |
| "grad_norm": 1.1984560510642397, | |
| "learning_rate": 9.580537770081285e-06, | |
| "loss": 1.7442, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.4734658847089115, | |
| "grad_norm": 1.1871050477497047, | |
| "learning_rate": 9.57189543690598e-06, | |
| "loss": 1.7498, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 1.4877699899871262, | |
| "grad_norm": 0.7133766609729304, | |
| "learning_rate": 9.563169422289798e-06, | |
| "loss": 1.7423, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.4877699899871262, | |
| "eval_loss": 1.7412633895874023, | |
| "eval_runtime": 13.1818, | |
| "eval_samples_per_second": 75.862, | |
| "eval_steps_per_second": 2.428, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.5020740952653413, | |
| "grad_norm": 0.7612313099084432, | |
| "learning_rate": 9.554359905560887e-06, | |
| "loss": 1.748, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 1.516378200543556, | |
| "grad_norm": 0.750224706069401, | |
| "learning_rate": 9.54546706776345e-06, | |
| "loss": 1.7435, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.530682305821771, | |
| "grad_norm": 0.9331760005679197, | |
| "learning_rate": 9.536491091654018e-06, | |
| "loss": 1.7324, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 1.5449864110999858, | |
| "grad_norm": 0.8613210624917503, | |
| "learning_rate": 9.527432161697696e-06, | |
| "loss": 1.751, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.5592905163782005, | |
| "grad_norm": 4.862833366342641, | |
| "learning_rate": 9.518290464064365e-06, | |
| "loss": 1.7365, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 1.5735946216564154, | |
| "grad_norm": 0.7838749485611254, | |
| "learning_rate": 9.509066186624872e-06, | |
| "loss": 1.7399, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.5878987269346303, | |
| "grad_norm": 0.798441318649249, | |
| "learning_rate": 9.499759518947156e-06, | |
| "loss": 1.737, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 1.602202832212845, | |
| "grad_norm": 0.7078515946606195, | |
| "learning_rate": 9.490370652292357e-06, | |
| "loss": 1.7412, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.602202832212845, | |
| "eval_loss": 1.7350177764892578, | |
| "eval_runtime": 13.1662, | |
| "eval_samples_per_second": 75.952, | |
| "eval_steps_per_second": 2.43, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.61650693749106, | |
| "grad_norm": 0.8939699763780663, | |
| "learning_rate": 9.480899779610883e-06, | |
| "loss": 1.7485, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 1.6308110427692748, | |
| "grad_norm": 0.7241948247907901, | |
| "learning_rate": 9.471347095538448e-06, | |
| "loss": 1.7338, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.6451151480474895, | |
| "grad_norm": 0.7753555958595959, | |
| "learning_rate": 9.461712796392067e-06, | |
| "loss": 1.7423, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 1.6594192533257046, | |
| "grad_norm": 0.9453545668822089, | |
| "learning_rate": 9.45199708016603e-06, | |
| "loss": 1.7411, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.6737233586039193, | |
| "grad_norm": 0.8069354542585767, | |
| "learning_rate": 9.442200146527824e-06, | |
| "loss": 1.7341, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 1.6880274638821342, | |
| "grad_norm": 0.9570095002200463, | |
| "learning_rate": 9.432322196814032e-06, | |
| "loss": 1.7309, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.7023315691603491, | |
| "grad_norm": 0.778079342980594, | |
| "learning_rate": 9.422363434026205e-06, | |
| "loss": 1.7331, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 1.7166356744385638, | |
| "grad_norm": 0.8582782820893037, | |
| "learning_rate": 9.41232406282667e-06, | |
| "loss": 1.7375, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.7166356744385638, | |
| "eval_loss": 1.7310324907302856, | |
| "eval_runtime": 13.1951, | |
| "eval_samples_per_second": 75.786, | |
| "eval_steps_per_second": 2.425, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.7309397797167787, | |
| "grad_norm": 0.657112371502439, | |
| "learning_rate": 9.402204289534344e-06, | |
| "loss": 1.725, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 1.7452438849949936, | |
| "grad_norm": 1.1123814501158173, | |
| "learning_rate": 9.392004322120484e-06, | |
| "loss": 1.7303, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.7595479902732083, | |
| "grad_norm": 0.9499171364049573, | |
| "learning_rate": 9.381724370204414e-06, | |
| "loss": 1.7203, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 1.7738520955514234, | |
| "grad_norm": 1.095712190889447, | |
| "learning_rate": 9.371364645049216e-06, | |
| "loss": 1.7291, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.788156200829638, | |
| "grad_norm": 1.0199371888229702, | |
| "learning_rate": 9.360925359557397e-06, | |
| "loss": 1.7155, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 1.8024603061078528, | |
| "grad_norm": 0.827904086276593, | |
| "learning_rate": 9.3504067282665e-06, | |
| "loss": 1.7404, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.816764411386068, | |
| "grad_norm": 0.8252103968718575, | |
| "learning_rate": 9.339808967344701e-06, | |
| "loss": 1.7275, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 1.8310685166642826, | |
| "grad_norm": 0.8608721928591242, | |
| "learning_rate": 9.329132294586374e-06, | |
| "loss": 1.7257, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.8310685166642826, | |
| "eval_loss": 1.7276860475540161, | |
| "eval_runtime": 13.1438, | |
| "eval_samples_per_second": 76.082, | |
| "eval_steps_per_second": 2.435, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.8453726219424975, | |
| "grad_norm": 1.0655198477534613, | |
| "learning_rate": 9.318376929407606e-06, | |
| "loss": 1.7219, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 1.8596767272207124, | |
| "grad_norm": 0.8202058864526146, | |
| "learning_rate": 9.307543092841688e-06, | |
| "loss": 1.7219, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.873980832498927, | |
| "grad_norm": 0.9119156406563158, | |
| "learning_rate": 9.296631007534576e-06, | |
| "loss": 1.7232, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 1.888284937777142, | |
| "grad_norm": 0.8561460550361113, | |
| "learning_rate": 9.285640897740316e-06, | |
| "loss": 1.718, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.902589043055357, | |
| "grad_norm": 0.9549020817113293, | |
| "learning_rate": 9.27457298931643e-06, | |
| "loss": 1.7348, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 1.9168931483335716, | |
| "grad_norm": 0.6729589207861246, | |
| "learning_rate": 9.263427509719287e-06, | |
| "loss": 1.7175, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.9311972536117867, | |
| "grad_norm": 0.709786130314777, | |
| "learning_rate": 9.252204687999401e-06, | |
| "loss": 1.7287, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 1.9455013588900014, | |
| "grad_norm": 0.9827727167496969, | |
| "learning_rate": 9.240904754796767e-06, | |
| "loss": 1.7241, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.9455013588900014, | |
| "eval_loss": 1.7200103998184204, | |
| "eval_runtime": 13.113, | |
| "eval_samples_per_second": 76.26, | |
| "eval_steps_per_second": 2.44, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.9598054641682163, | |
| "grad_norm": 0.8218927694104888, | |
| "learning_rate": 9.22952794233608e-06, | |
| "loss": 1.7334, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 1.9741095694464312, | |
| "grad_norm": 0.9202146449681148, | |
| "learning_rate": 9.218074484421977e-06, | |
| "loss": 1.7176, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 1.988413674724646, | |
| "grad_norm": 0.9757466555134802, | |
| "learning_rate": 9.206544616434249e-06, | |
| "loss": 1.716, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 2.0027177800028606, | |
| "grad_norm": 0.9665391581844135, | |
| "learning_rate": 9.194938575322973e-06, | |
| "loss": 1.7104, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.0170218852810757, | |
| "grad_norm": 0.747601621726994, | |
| "learning_rate": 9.183256599603672e-06, | |
| "loss": 1.7045, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 2.0313259905592904, | |
| "grad_norm": 0.590573479620199, | |
| "learning_rate": 9.171498929352388e-06, | |
| "loss": 1.7012, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 2.0456300958375055, | |
| "grad_norm": 0.7932008874801502, | |
| "learning_rate": 9.159665806200766e-06, | |
| "loss": 1.7017, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 2.0599342011157202, | |
| "grad_norm": 0.824718775314277, | |
| "learning_rate": 9.147757473331082e-06, | |
| "loss": 1.7019, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.0599342011157202, | |
| "eval_loss": 1.7177115678787231, | |
| "eval_runtime": 13.1014, | |
| "eval_samples_per_second": 76.328, | |
| "eval_steps_per_second": 2.442, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.074238306393935, | |
| "grad_norm": 1.080101464877567, | |
| "learning_rate": 9.135774175471244e-06, | |
| "loss": 1.7056, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 2.08854241167215, | |
| "grad_norm": 0.6161967559479131, | |
| "learning_rate": 9.123716158889765e-06, | |
| "loss": 1.6892, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 2.1028465169503647, | |
| "grad_norm": 0.6259364978680784, | |
| "learning_rate": 9.111583671390697e-06, | |
| "loss": 1.6876, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 2.1171506222285794, | |
| "grad_norm": 0.9054346826665011, | |
| "learning_rate": 9.09937696230855e-06, | |
| "loss": 1.7004, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 2.1314547275067945, | |
| "grad_norm": 0.8115910709185014, | |
| "learning_rate": 9.087096282503152e-06, | |
| "loss": 1.6951, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 2.1457588327850092, | |
| "grad_norm": 0.939188480700838, | |
| "learning_rate": 9.074741884354507e-06, | |
| "loss": 1.698, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.1600629380632244, | |
| "grad_norm": 0.5461813129993677, | |
| "learning_rate": 9.062314021757603e-06, | |
| "loss": 1.6953, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 2.174367043341439, | |
| "grad_norm": 0.8915398126133827, | |
| "learning_rate": 9.049812950117191e-06, | |
| "loss": 1.6838, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.174367043341439, | |
| "eval_loss": 1.7138569355010986, | |
| "eval_runtime": 13.1252, | |
| "eval_samples_per_second": 76.189, | |
| "eval_steps_per_second": 2.438, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.1886711486196537, | |
| "grad_norm": 0.8119718442892704, | |
| "learning_rate": 9.037238926342544e-06, | |
| "loss": 1.7012, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 2.202975253897869, | |
| "grad_norm": 0.6869354062120884, | |
| "learning_rate": 9.02459220884217e-06, | |
| "loss": 1.6918, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 2.2172793591760835, | |
| "grad_norm": 0.7341604750585072, | |
| "learning_rate": 9.011873057518503e-06, | |
| "loss": 1.699, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 2.2315834644542982, | |
| "grad_norm": 0.8261410417964352, | |
| "learning_rate": 8.999081733762568e-06, | |
| "loss": 1.6993, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 2.2458875697325134, | |
| "grad_norm": 0.7611803854476097, | |
| "learning_rate": 8.986218500448598e-06, | |
| "loss": 1.7069, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 2.260191675010728, | |
| "grad_norm": 0.771284372878959, | |
| "learning_rate": 8.973283621928644e-06, | |
| "loss": 1.7018, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 2.2744957802889427, | |
| "grad_norm": 0.6069248728630589, | |
| "learning_rate": 8.96027736402713e-06, | |
| "loss": 1.6894, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 2.288799885567158, | |
| "grad_norm": 0.6935253796751046, | |
| "learning_rate": 8.947199994035402e-06, | |
| "loss": 1.6857, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.288799885567158, | |
| "eval_loss": 1.709199070930481, | |
| "eval_runtime": 13.105, | |
| "eval_samples_per_second": 76.307, | |
| "eval_steps_per_second": 2.442, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.3031039908453725, | |
| "grad_norm": 0.6395079401863663, | |
| "learning_rate": 8.934051780706226e-06, | |
| "loss": 1.6867, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 2.3174080961235877, | |
| "grad_norm": 0.8808561738320105, | |
| "learning_rate": 8.920832994248268e-06, | |
| "loss": 1.6947, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 2.3317122014018024, | |
| "grad_norm": 0.6888071930360784, | |
| "learning_rate": 8.907543906320542e-06, | |
| "loss": 1.7005, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 2.346016306680017, | |
| "grad_norm": 0.6515296032830782, | |
| "learning_rate": 8.894184790026823e-06, | |
| "loss": 1.686, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.360320411958232, | |
| "grad_norm": 0.7401595322241383, | |
| "learning_rate": 8.880755919910048e-06, | |
| "loss": 1.6865, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 2.374624517236447, | |
| "grad_norm": 0.6000159117604718, | |
| "learning_rate": 8.867257571946646e-06, | |
| "loss": 1.6996, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 2.3889286225146615, | |
| "grad_norm": 0.6577366719572108, | |
| "learning_rate": 8.853690023540898e-06, | |
| "loss": 1.6929, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 2.4032327277928767, | |
| "grad_norm": 0.7392515614712054, | |
| "learning_rate": 8.840053553519216e-06, | |
| "loss": 1.6848, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.4032327277928767, | |
| "eval_loss": 1.7050341367721558, | |
| "eval_runtime": 13.1691, | |
| "eval_samples_per_second": 75.935, | |
| "eval_steps_per_second": 2.43, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.4175368330710914, | |
| "grad_norm": 0.9889920645015057, | |
| "learning_rate": 8.82634844212442e-06, | |
| "loss": 1.6893, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 2.431840938349306, | |
| "grad_norm": 0.9590160412926145, | |
| "learning_rate": 8.81257497100998e-06, | |
| "loss": 1.6846, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.446145043627521, | |
| "grad_norm": 0.8138219488107618, | |
| "learning_rate": 8.79873342323422e-06, | |
| "loss": 1.689, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 2.460449148905736, | |
| "grad_norm": 0.6771189511098283, | |
| "learning_rate": 8.78482408325451e-06, | |
| "loss": 1.684, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 2.474753254183951, | |
| "grad_norm": 0.637569459443737, | |
| "learning_rate": 8.770847236921412e-06, | |
| "loss": 1.6893, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 2.4890573594621657, | |
| "grad_norm": 0.8520093583138391, | |
| "learning_rate": 8.756803171472817e-06, | |
| "loss": 1.6858, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 2.5033614647403803, | |
| "grad_norm": 1.0853751747133211, | |
| "learning_rate": 8.742692175528027e-06, | |
| "loss": 1.6929, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 2.5176655700185955, | |
| "grad_norm": 0.5845518675223795, | |
| "learning_rate": 8.728514539081837e-06, | |
| "loss": 1.6795, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.5176655700185955, | |
| "eval_loss": 1.6996084451675415, | |
| "eval_runtime": 13.1313, | |
| "eval_samples_per_second": 76.154, | |
| "eval_steps_per_second": 2.437, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.53196967529681, | |
| "grad_norm": 0.6987736172220224, | |
| "learning_rate": 8.714270553498567e-06, | |
| "loss": 1.6786, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 2.5462737805750253, | |
| "grad_norm": 0.6845251902273746, | |
| "learning_rate": 8.699960511506077e-06, | |
| "loss": 1.6915, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 2.56057788585324, | |
| "grad_norm": 0.5813491957603439, | |
| "learning_rate": 8.685584707189749e-06, | |
| "loss": 1.6864, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 2.5748819911314547, | |
| "grad_norm": 0.7758297556506881, | |
| "learning_rate": 8.671143435986447e-06, | |
| "loss": 1.6853, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.5891860964096693, | |
| "grad_norm": 0.6480784306311093, | |
| "learning_rate": 8.656636994678447e-06, | |
| "loss": 1.6945, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 2.6034902016878845, | |
| "grad_norm": 0.752842227645809, | |
| "learning_rate": 8.642065681387329e-06, | |
| "loss": 1.6856, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 2.617794306966099, | |
| "grad_norm": 0.8563670508754716, | |
| "learning_rate": 8.627429795567858e-06, | |
| "loss": 1.6813, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 2.6320984122443143, | |
| "grad_norm": 0.649858543338678, | |
| "learning_rate": 8.61272963800183e-06, | |
| "loss": 1.6807, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.6320984122443143, | |
| "eval_loss": 1.6953411102294922, | |
| "eval_runtime": 13.1331, | |
| "eval_samples_per_second": 76.143, | |
| "eval_steps_per_second": 2.437, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.646402517522529, | |
| "grad_norm": 0.6485355884487186, | |
| "learning_rate": 8.597965510791883e-06, | |
| "loss": 1.691, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 2.6607066228007437, | |
| "grad_norm": 0.8331706908409144, | |
| "learning_rate": 8.5831377173553e-06, | |
| "loss": 1.6757, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 2.675010728078959, | |
| "grad_norm": 0.7237339174259747, | |
| "learning_rate": 8.568246562417762e-06, | |
| "loss": 1.6838, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 2.6893148333571735, | |
| "grad_norm": 0.6551466282285732, | |
| "learning_rate": 8.553292352007096e-06, | |
| "loss": 1.6815, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.7036189386353886, | |
| "grad_norm": 0.6601355008192104, | |
| "learning_rate": 8.538275393446976e-06, | |
| "loss": 1.6857, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 2.7179230439136033, | |
| "grad_norm": 0.6614316555641063, | |
| "learning_rate": 8.523195995350613e-06, | |
| "loss": 1.6823, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.732227149191818, | |
| "grad_norm": 0.9043872683705563, | |
| "learning_rate": 8.508054467614417e-06, | |
| "loss": 1.6807, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 2.7465312544700327, | |
| "grad_norm": 0.6024321505835114, | |
| "learning_rate": 8.492851121411614e-06, | |
| "loss": 1.6775, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.7465312544700327, | |
| "eval_loss": 1.6916736364364624, | |
| "eval_runtime": 13.1667, | |
| "eval_samples_per_second": 75.949, | |
| "eval_steps_per_second": 2.43, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.760835359748248, | |
| "grad_norm": 0.5885102755974863, | |
| "learning_rate": 8.477586269185868e-06, | |
| "loss": 1.6783, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 2.7751394650264625, | |
| "grad_norm": 0.5923048948697456, | |
| "learning_rate": 8.462260224644848e-06, | |
| "loss": 1.6754, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 2.7894435703046776, | |
| "grad_norm": 0.658689052183787, | |
| "learning_rate": 8.446873302753783e-06, | |
| "loss": 1.6879, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 2.8037476755828923, | |
| "grad_norm": 0.6839558742874721, | |
| "learning_rate": 8.431425819728998e-06, | |
| "loss": 1.6833, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.818051780861107, | |
| "grad_norm": 0.563076108100303, | |
| "learning_rate": 8.415918093031403e-06, | |
| "loss": 1.6746, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 2.832355886139322, | |
| "grad_norm": 0.6412513978425523, | |
| "learning_rate": 8.400350441359976e-06, | |
| "loss": 1.6673, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 2.846659991417537, | |
| "grad_norm": 0.6509884557319101, | |
| "learning_rate": 8.384723184645211e-06, | |
| "loss": 1.6736, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 2.860964096695752, | |
| "grad_norm": 0.6795285605676114, | |
| "learning_rate": 8.369036644042546e-06, | |
| "loss": 1.6602, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.860964096695752, | |
| "eval_loss": 1.6880682706832886, | |
| "eval_runtime": 13.1264, | |
| "eval_samples_per_second": 76.182, | |
| "eval_steps_per_second": 2.438, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.8752682019739666, | |
| "grad_norm": 0.6331270907140948, | |
| "learning_rate": 8.353291141925763e-06, | |
| "loss": 1.6678, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 2.8895723072521813, | |
| "grad_norm": 0.6165703754864105, | |
| "learning_rate": 8.337487001880353e-06, | |
| "loss": 1.6779, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 2.903876412530396, | |
| "grad_norm": 0.9180760124515276, | |
| "learning_rate": 8.32162454869688e-06, | |
| "loss": 1.6709, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 2.918180517808611, | |
| "grad_norm": 0.6067014553628142, | |
| "learning_rate": 8.305704108364301e-06, | |
| "loss": 1.6748, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 2.932484623086826, | |
| "grad_norm": 0.6822167283880958, | |
| "learning_rate": 8.289726008063265e-06, | |
| "loss": 1.6734, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 2.946788728365041, | |
| "grad_norm": 0.5414334397184379, | |
| "learning_rate": 8.273690576159383e-06, | |
| "loss": 1.674, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 2.9610928336432556, | |
| "grad_norm": 0.6960756922615432, | |
| "learning_rate": 8.257598142196496e-06, | |
| "loss": 1.6611, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 2.9753969389214703, | |
| "grad_norm": 0.6604617349648914, | |
| "learning_rate": 8.241449036889892e-06, | |
| "loss": 1.6676, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.9753969389214703, | |
| "eval_loss": 1.6850733757019043, | |
| "eval_runtime": 13.109, | |
| "eval_samples_per_second": 76.284, | |
| "eval_steps_per_second": 2.441, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 2.9897010441996854, | |
| "grad_norm": 0.803147857087257, | |
| "learning_rate": 8.225243592119501e-06, | |
| "loss": 1.6742, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 3.0040051494779, | |
| "grad_norm": 0.7661508794366779, | |
| "learning_rate": 8.208982140923095e-06, | |
| "loss": 1.6643, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.0183092547561152, | |
| "grad_norm": 0.9234438361457962, | |
| "learning_rate": 8.192665017489431e-06, | |
| "loss": 1.6358, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 3.03261336003433, | |
| "grad_norm": 0.6961614825939386, | |
| "learning_rate": 8.17629255715138e-06, | |
| "loss": 1.6545, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 3.0469174653125446, | |
| "grad_norm": 0.6895369107938377, | |
| "learning_rate": 8.159865096379046e-06, | |
| "loss": 1.6321, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 3.0612215705907597, | |
| "grad_norm": 0.7078335937537477, | |
| "learning_rate": 8.14338297277284e-06, | |
| "loss": 1.6349, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 3.0755256758689744, | |
| "grad_norm": 0.6076483839068002, | |
| "learning_rate": 8.126846525056555e-06, | |
| "loss": 1.6365, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 3.089829781147189, | |
| "grad_norm": 0.6898999480835771, | |
| "learning_rate": 8.110256093070393e-06, | |
| "loss": 1.6546, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 3.089829781147189, | |
| "eval_loss": 1.6832627058029175, | |
| "eval_runtime": 13.1347, | |
| "eval_samples_per_second": 76.134, | |
| "eval_steps_per_second": 2.436, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 3.104133886425404, | |
| "grad_norm": 0.7013516335683451, | |
| "learning_rate": 8.093612017763986e-06, | |
| "loss": 1.639, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 3.118437991703619, | |
| "grad_norm": 0.6585546257998172, | |
| "learning_rate": 8.076914641189388e-06, | |
| "loss": 1.649, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 3.1327420969818336, | |
| "grad_norm": 0.6634919864983012, | |
| "learning_rate": 8.060164306494052e-06, | |
| "loss": 1.6349, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 3.1470462022600487, | |
| "grad_norm": 0.6535125345700776, | |
| "learning_rate": 8.043361357913763e-06, | |
| "loss": 1.6354, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.1613503075382634, | |
| "grad_norm": 0.6365757392209358, | |
| "learning_rate": 8.026506140765581e-06, | |
| "loss": 1.6411, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 3.1756544128164785, | |
| "grad_norm": 0.7613496780923112, | |
| "learning_rate": 8.009599001440733e-06, | |
| "loss": 1.6443, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 3.189958518094693, | |
| "grad_norm": 0.6788371997973981, | |
| "learning_rate": 7.992640287397498e-06, | |
| "loss": 1.6406, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 3.204262623372908, | |
| "grad_norm": 0.7267161462233287, | |
| "learning_rate": 7.975630347154062e-06, | |
| "loss": 1.6416, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 3.204262623372908, | |
| "eval_loss": 1.6800661087036133, | |
| "eval_runtime": 13.1106, | |
| "eval_samples_per_second": 76.274, | |
| "eval_steps_per_second": 2.441, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 3.218566728651123, | |
| "grad_norm": 0.6610572852986926, | |
| "learning_rate": 7.958569530281369e-06, | |
| "loss": 1.637, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 3.2328708339293377, | |
| "grad_norm": 0.9622885989079347, | |
| "learning_rate": 7.941458187395918e-06, | |
| "loss": 1.6356, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 3.2471749392075524, | |
| "grad_norm": 0.6376730332996383, | |
| "learning_rate": 7.924296670152573e-06, | |
| "loss": 1.6353, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 3.2614790444857675, | |
| "grad_norm": 0.7223900847461898, | |
| "learning_rate": 7.907085331237328e-06, | |
| "loss": 1.6484, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 3.275783149763982, | |
| "grad_norm": 0.5989178515182939, | |
| "learning_rate": 7.889824524360058e-06, | |
| "loss": 1.6451, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 3.290087255042197, | |
| "grad_norm": 0.6779901779346886, | |
| "learning_rate": 7.872514604247261e-06, | |
| "loss": 1.6453, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.304391360320412, | |
| "grad_norm": 0.7005880085935425, | |
| "learning_rate": 7.855155926634755e-06, | |
| "loss": 1.6472, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 3.3186954655986267, | |
| "grad_norm": 0.7609081934908348, | |
| "learning_rate": 7.837748848260372e-06, | |
| "loss": 1.6465, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 3.3186954655986267, | |
| "eval_loss": 1.6766809225082397, | |
| "eval_runtime": 13.1249, | |
| "eval_samples_per_second": 76.191, | |
| "eval_steps_per_second": 2.438, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 3.332999570876842, | |
| "grad_norm": 0.6431999289309001, | |
| "learning_rate": 7.820293726856625e-06, | |
| "loss": 1.6363, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 3.3473036761550565, | |
| "grad_norm": 0.7971053094613834, | |
| "learning_rate": 7.802790921143367e-06, | |
| "loss": 1.642, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 3.361607781433271, | |
| "grad_norm": 0.8315194233152097, | |
| "learning_rate": 7.785240790820403e-06, | |
| "loss": 1.6356, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 3.3759118867114863, | |
| "grad_norm": 0.7233317425806471, | |
| "learning_rate": 7.767643696560103e-06, | |
| "loss": 1.625, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 3.390215991989701, | |
| "grad_norm": 0.7043201889466395, | |
| "learning_rate": 7.75e-06, | |
| "loss": 1.6454, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 3.4045200972679157, | |
| "grad_norm": 0.8514114238482182, | |
| "learning_rate": 7.732310063735346e-06, | |
| "loss": 1.6283, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 3.418824202546131, | |
| "grad_norm": 0.8115066197624821, | |
| "learning_rate": 7.71457425131166e-06, | |
| "loss": 1.6235, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 3.4331283078243455, | |
| "grad_norm": 0.6131161672110997, | |
| "learning_rate": 7.696792927217266e-06, | |
| "loss": 1.6332, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.4331283078243455, | |
| "eval_loss": 1.6723066568374634, | |
| "eval_runtime": 13.1167, | |
| "eval_samples_per_second": 76.238, | |
| "eval_steps_per_second": 2.44, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.44743241310256, | |
| "grad_norm": 0.5768237911834109, | |
| "learning_rate": 7.6789664568758e-06, | |
| "loss": 1.6232, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 3.4617365183807753, | |
| "grad_norm": 0.6357616712470612, | |
| "learning_rate": 7.661095206638688e-06, | |
| "loss": 1.6384, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 3.47604062365899, | |
| "grad_norm": 0.6064381660716113, | |
| "learning_rate": 7.643179543777636e-06, | |
| "loss": 1.6423, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 3.490344728937205, | |
| "grad_norm": 0.6129739275970794, | |
| "learning_rate": 7.625219836477073e-06, | |
| "loss": 1.6376, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 3.50464883421542, | |
| "grad_norm": 0.6413234223207633, | |
| "learning_rate": 7.607216453826575e-06, | |
| "loss": 1.6342, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 3.5189529394936345, | |
| "grad_norm": 0.649929569744414, | |
| "learning_rate": 7.589169765813298e-06, | |
| "loss": 1.6418, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 3.5332570447718497, | |
| "grad_norm": 0.5694768483225782, | |
| "learning_rate": 7.571080143314362e-06, | |
| "loss": 1.6242, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 3.5475611500500643, | |
| "grad_norm": 0.7350828307091747, | |
| "learning_rate": 7.552947958089234e-06, | |
| "loss": 1.6217, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 3.5475611500500643, | |
| "eval_loss": 1.6681584119796753, | |
| "eval_runtime": 13.1321, | |
| "eval_samples_per_second": 76.149, | |
| "eval_steps_per_second": 2.437, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 3.5618652553282795, | |
| "grad_norm": 0.8136490657582578, | |
| "learning_rate": 7.534773582772087e-06, | |
| "loss": 1.6303, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 3.576169360606494, | |
| "grad_norm": 0.7180717788221607, | |
| "learning_rate": 7.51655739086414e-06, | |
| "loss": 1.6361, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.590473465884709, | |
| "grad_norm": 0.7947804203928884, | |
| "learning_rate": 7.498299756725984e-06, | |
| "loss": 1.6387, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 3.6047775711629235, | |
| "grad_norm": 0.560362351616168, | |
| "learning_rate": 7.480001055569892e-06, | |
| "loss": 1.6309, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 3.6190816764411387, | |
| "grad_norm": 0.6426607371565076, | |
| "learning_rate": 7.4616616634521e-06, | |
| "loss": 1.633, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 3.6333857817193533, | |
| "grad_norm": 0.6171738461490535, | |
| "learning_rate": 7.443281957265086e-06, | |
| "loss": 1.6281, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 3.6476898869975685, | |
| "grad_norm": 0.6363040797185718, | |
| "learning_rate": 7.424862314729819e-06, | |
| "loss": 1.6311, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 3.661993992275783, | |
| "grad_norm": 0.7596986784676188, | |
| "learning_rate": 7.406403114388003e-06, | |
| "loss": 1.6292, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 3.661993992275783, | |
| "eval_loss": 1.6635466814041138, | |
| "eval_runtime": 13.15, | |
| "eval_samples_per_second": 76.046, | |
| "eval_steps_per_second": 2.433, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 3.676298097553998, | |
| "grad_norm": 0.7293094685670296, | |
| "learning_rate": 7.387904735594291e-06, | |
| "loss": 1.6287, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 3.690602202832213, | |
| "grad_norm": 0.6158921819942098, | |
| "learning_rate": 7.36936755850849e-06, | |
| "loss": 1.6385, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 3.7049063081104276, | |
| "grad_norm": 0.5784944167280377, | |
| "learning_rate": 7.3507919640877535e-06, | |
| "loss": 1.6328, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 3.7192104133886428, | |
| "grad_norm": 0.6275769116215365, | |
| "learning_rate": 7.332178334078746e-06, | |
| "loss": 1.6346, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.7335145186668575, | |
| "grad_norm": 0.7049335766852525, | |
| "learning_rate": 7.313527051009803e-06, | |
| "loss": 1.6314, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 3.747818623945072, | |
| "grad_norm": 0.5885503989540276, | |
| "learning_rate": 7.2948384981830655e-06, | |
| "loss": 1.6276, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 3.762122729223287, | |
| "grad_norm": 0.6144133824628834, | |
| "learning_rate": 7.2761130596666045e-06, | |
| "loss": 1.6194, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 3.776426834501502, | |
| "grad_norm": 0.6880469614329583, | |
| "learning_rate": 7.25735112028653e-06, | |
| "loss": 1.6263, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 3.776426834501502, | |
| "eval_loss": 1.6603440046310425, | |
| "eval_runtime": 13.1562, | |
| "eval_samples_per_second": 76.01, | |
| "eval_steps_per_second": 2.432, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 3.7907309397797166, | |
| "grad_norm": 0.6695854088226235, | |
| "learning_rate": 7.2385530656190785e-06, | |
| "loss": 1.6163, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 3.8050350450579318, | |
| "grad_norm": 0.7403722736764125, | |
| "learning_rate": 7.219719281982694e-06, | |
| "loss": 1.6223, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 3.8193391503361465, | |
| "grad_norm": 0.6035992360261074, | |
| "learning_rate": 7.20085015643008e-06, | |
| "loss": 1.6177, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 3.833643255614361, | |
| "grad_norm": 0.5706930216009009, | |
| "learning_rate": 7.181946076740257e-06, | |
| "loss": 1.6177, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 3.8479473608925763, | |
| "grad_norm": 0.6806370138912894, | |
| "learning_rate": 7.163007431410583e-06, | |
| "loss": 1.6262, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 3.862251466170791, | |
| "grad_norm": 0.6234185420830436, | |
| "learning_rate": 7.144034609648779e-06, | |
| "loss": 1.6331, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 3.876555571449006, | |
| "grad_norm": 0.7677470872346758, | |
| "learning_rate": 7.125028001364918e-06, | |
| "loss": 1.6197, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 3.8908596767272208, | |
| "grad_norm": 0.6034269149098646, | |
| "learning_rate": 7.105987997163424e-06, | |
| "loss": 1.6266, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 3.8908596767272208, | |
| "eval_loss": 1.6566662788391113, | |
| "eval_runtime": 13.1267, | |
| "eval_samples_per_second": 76.181, | |
| "eval_steps_per_second": 2.438, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 3.9051637820054355, | |
| "grad_norm": 0.8302705314191118, | |
| "learning_rate": 7.086914988335039e-06, | |
| "loss": 1.6269, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 3.91946788728365, | |
| "grad_norm": 0.6389864823326697, | |
| "learning_rate": 7.0678093668487836e-06, | |
| "loss": 1.6323, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 3.9337719925618653, | |
| "grad_norm": 0.7866068542682738, | |
| "learning_rate": 7.048671525343898e-06, | |
| "loss": 1.6106, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 3.94807609784008, | |
| "grad_norm": 0.7727876700796928, | |
| "learning_rate": 7.029501857121776e-06, | |
| "loss": 1.6173, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 3.962380203118295, | |
| "grad_norm": 0.6170837296024364, | |
| "learning_rate": 7.010300756137882e-06, | |
| "loss": 1.6109, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 3.9766843083965098, | |
| "grad_norm": 0.6847504318409611, | |
| "learning_rate": 6.991068616993655e-06, | |
| "loss": 1.6208, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 3.9909884136747245, | |
| "grad_norm": 0.7026084916595097, | |
| "learning_rate": 6.971805834928399e-06, | |
| "loss": 1.6147, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 4.005292518952939, | |
| "grad_norm": 0.5565822000879449, | |
| "learning_rate": 6.952512805811156e-06, | |
| "loss": 1.6238, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.005292518952939, | |
| "eval_loss": 1.6554406881332397, | |
| "eval_runtime": 13.1672, | |
| "eval_samples_per_second": 75.947, | |
| "eval_steps_per_second": 2.43, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.019596624231155, | |
| "grad_norm": 0.7906915205693054, | |
| "learning_rate": 6.933189926132581e-06, | |
| "loss": 1.5887, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 4.033900729509369, | |
| "grad_norm": 0.6014668104450175, | |
| "learning_rate": 6.913837592996783e-06, | |
| "loss": 1.5824, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 4.048204834787584, | |
| "grad_norm": 0.6349783814707618, | |
| "learning_rate": 6.894456204113167e-06, | |
| "loss": 1.5993, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 4.062508940065799, | |
| "grad_norm": 0.7004788731024523, | |
| "learning_rate": 6.875046157788267e-06, | |
| "loss": 1.5856, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 4.0768130453440135, | |
| "grad_norm": 0.5890601619700472, | |
| "learning_rate": 6.855607852917555e-06, | |
| "loss": 1.5992, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 4.091117150622228, | |
| "grad_norm": 0.7378157690547319, | |
| "learning_rate": 6.836141688977238e-06, | |
| "loss": 1.5933, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 4.105421255900444, | |
| "grad_norm": 0.5985785926592089, | |
| "learning_rate": 6.816648066016059e-06, | |
| "loss": 1.6059, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 4.119725361178658, | |
| "grad_norm": 0.7254510710383179, | |
| "learning_rate": 6.7971273846470696e-06, | |
| "loss": 1.5755, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 4.119725361178658, | |
| "eval_loss": 1.652251124382019, | |
| "eval_runtime": 13.1229, | |
| "eval_samples_per_second": 76.203, | |
| "eval_steps_per_second": 2.438, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 4.134029466456873, | |
| "grad_norm": 0.701638747657545, | |
| "learning_rate": 6.777580046039399e-06, | |
| "loss": 1.5878, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 4.148333571735088, | |
| "grad_norm": 0.6156043257629281, | |
| "learning_rate": 6.758006451910008e-06, | |
| "loss": 1.5888, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.1626376770133025, | |
| "grad_norm": 0.6311348402263556, | |
| "learning_rate": 6.738407004515434e-06, | |
| "loss": 1.5906, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 4.176941782291518, | |
| "grad_norm": 0.7457367222382035, | |
| "learning_rate": 6.718782106643524e-06, | |
| "loss": 1.5935, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 4.191245887569733, | |
| "grad_norm": 0.6497146588667823, | |
| "learning_rate": 6.699132161605158e-06, | |
| "loss": 1.5944, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 4.205549992847947, | |
| "grad_norm": 0.6021866479049087, | |
| "learning_rate": 6.679457573225961e-06, | |
| "loss": 1.5872, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 4.219854098126162, | |
| "grad_norm": 0.606706719077781, | |
| "learning_rate": 6.659758745837998e-06, | |
| "loss": 1.5892, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 4.234158203404377, | |
| "grad_norm": 0.796088041146077, | |
| "learning_rate": 6.640036084271477e-06, | |
| "loss": 1.5778, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 4.234158203404377, | |
| "eval_loss": 1.652685523033142, | |
| "eval_runtime": 13.11, | |
| "eval_samples_per_second": 76.278, | |
| "eval_steps_per_second": 2.441, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 4.248462308682592, | |
| "grad_norm": 0.5720799505387223, | |
| "learning_rate": 6.620289993846416e-06, | |
| "loss": 1.5853, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 4.262766413960807, | |
| "grad_norm": 0.638641651597387, | |
| "learning_rate": 6.600520880364318e-06, | |
| "loss": 1.5821, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 4.277070519239022, | |
| "grad_norm": 0.6826954900918857, | |
| "learning_rate": 6.5807291500998385e-06, | |
| "loss": 1.5926, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 4.291374624517236, | |
| "grad_norm": 0.7142773516133535, | |
| "learning_rate": 6.560915209792424e-06, | |
| "loss": 1.5756, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.305678729795451, | |
| "grad_norm": 0.6893665096075864, | |
| "learning_rate": 6.541079466637962e-06, | |
| "loss": 1.5898, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 4.319982835073666, | |
| "grad_norm": 0.6934025133503401, | |
| "learning_rate": 6.52122232828041e-06, | |
| "loss": 1.5906, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 4.334286940351881, | |
| "grad_norm": 0.5946314963781922, | |
| "learning_rate": 6.501344202803415e-06, | |
| "loss": 1.5876, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 4.348591045630096, | |
| "grad_norm": 0.6765765096436505, | |
| "learning_rate": 6.4814454987219355e-06, | |
| "loss": 1.5876, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 4.348591045630096, | |
| "eval_loss": 1.6479697227478027, | |
| "eval_runtime": 13.1313, | |
| "eval_samples_per_second": 76.154, | |
| "eval_steps_per_second": 2.437, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 4.362895150908311, | |
| "grad_norm": 0.6577195429173401, | |
| "learning_rate": 6.461526624973836e-06, | |
| "loss": 1.5899, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 4.377199256186525, | |
| "grad_norm": 0.8277675923235659, | |
| "learning_rate": 6.441587990911489e-06, | |
| "loss": 1.5887, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 4.39150336146474, | |
| "grad_norm": 0.7292088895911856, | |
| "learning_rate": 6.421630006293359e-06, | |
| "loss": 1.5728, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 4.405807466742955, | |
| "grad_norm": 0.7886180995867164, | |
| "learning_rate": 6.401653081275586e-06, | |
| "loss": 1.5765, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 4.42011157202117, | |
| "grad_norm": 0.6450755047638138, | |
| "learning_rate": 6.38165762640355e-06, | |
| "loss": 1.5831, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 4.434415677299385, | |
| "grad_norm": 0.6698809351304791, | |
| "learning_rate": 6.361644052603445e-06, | |
| "loss": 1.5795, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 4.4487197825776, | |
| "grad_norm": 0.7804327125701724, | |
| "learning_rate": 6.341612771173817e-06, | |
| "loss": 1.5896, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 4.463023887855814, | |
| "grad_norm": 0.5570965590960153, | |
| "learning_rate": 6.321564193777129e-06, | |
| "loss": 1.5778, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 4.463023887855814, | |
| "eval_loss": 1.6438684463500977, | |
| "eval_runtime": 13.1716, | |
| "eval_samples_per_second": 75.921, | |
| "eval_steps_per_second": 2.429, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 4.477327993134029, | |
| "grad_norm": 0.81125064044786, | |
| "learning_rate": 6.301498732431287e-06, | |
| "loss": 1.5898, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 4.491632098412245, | |
| "grad_norm": 0.7306624425115567, | |
| "learning_rate": 6.281416799501188e-06, | |
| "loss": 1.5775, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 4.505936203690459, | |
| "grad_norm": 0.7181992700870559, | |
| "learning_rate": 6.261318807690223e-06, | |
| "loss": 1.5844, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 4.520240308968674, | |
| "grad_norm": 0.7748503653032427, | |
| "learning_rate": 6.24120517003182e-06, | |
| "loss": 1.5807, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 4.534544414246889, | |
| "grad_norm": 0.692890389924739, | |
| "learning_rate": 6.221076299880939e-06, | |
| "loss": 1.5779, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 4.548848519525103, | |
| "grad_norm": 0.750802300795554, | |
| "learning_rate": 6.200932610905584e-06, | |
| "loss": 1.5914, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 4.563152624803319, | |
| "grad_norm": 0.6119826848690993, | |
| "learning_rate": 6.180774517078301e-06, | |
| "loss": 1.5745, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 4.577456730081534, | |
| "grad_norm": 0.6472801196876264, | |
| "learning_rate": 6.160602432667668e-06, | |
| "loss": 1.5737, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.577456730081534, | |
| "eval_loss": 1.6402463912963867, | |
| "eval_runtime": 13.0995, | |
| "eval_samples_per_second": 76.339, | |
| "eval_steps_per_second": 2.443, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.591760835359748, | |
| "grad_norm": 0.6082312742368647, | |
| "learning_rate": 6.140416772229785e-06, | |
| "loss": 1.5843, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 4.606064940637963, | |
| "grad_norm": 0.6109383078063736, | |
| "learning_rate": 6.12021795059975e-06, | |
| "loss": 1.5795, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 4.620369045916178, | |
| "grad_norm": 0.5808974596081403, | |
| "learning_rate": 6.10000638288314e-06, | |
| "loss": 1.5834, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 4.634673151194393, | |
| "grad_norm": 0.6471974483578133, | |
| "learning_rate": 6.079782484447475e-06, | |
| "loss": 1.5685, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 4.648977256472608, | |
| "grad_norm": 0.6706099898660832, | |
| "learning_rate": 6.059546670913684e-06, | |
| "loss": 1.582, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 4.663281361750823, | |
| "grad_norm": 0.634560651660765, | |
| "learning_rate": 6.03929935814756e-06, | |
| "loss": 1.572, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 4.677585467029037, | |
| "grad_norm": 0.6380102332948996, | |
| "learning_rate": 6.01904096225122e-06, | |
| "loss": 1.5715, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 4.691889572307252, | |
| "grad_norm": 0.6355595383367377, | |
| "learning_rate": 5.998771899554551e-06, | |
| "loss": 1.5724, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 4.691889572307252, | |
| "eval_loss": 1.6363039016723633, | |
| "eval_runtime": 13.141, | |
| "eval_samples_per_second": 76.098, | |
| "eval_steps_per_second": 2.435, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 4.706193677585467, | |
| "grad_norm": 0.6132759482920135, | |
| "learning_rate": 5.978492586606647e-06, | |
| "loss": 1.5769, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 4.720497782863681, | |
| "grad_norm": 0.6639573383492796, | |
| "learning_rate": 5.958203440167261e-06, | |
| "loss": 1.5671, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 4.734801888141897, | |
| "grad_norm": 0.5417322612862875, | |
| "learning_rate": 5.93790487719823e-06, | |
| "loss": 1.5755, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 4.749105993420112, | |
| "grad_norm": 0.6771963599708853, | |
| "learning_rate": 5.917597314854914e-06, | |
| "loss": 1.569, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 4.763410098698326, | |
| "grad_norm": 0.7200514277275499, | |
| "learning_rate": 5.897281170477614e-06, | |
| "loss": 1.577, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 4.777714203976541, | |
| "grad_norm": 0.5811950543492076, | |
| "learning_rate": 5.876956861583007e-06, | |
| "loss": 1.5622, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 4.792018309254756, | |
| "grad_norm": 0.7104533054634696, | |
| "learning_rate": 5.856624805855548e-06, | |
| "loss": 1.579, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 4.806322414532971, | |
| "grad_norm": 0.655887536338841, | |
| "learning_rate": 5.83628542113891e-06, | |
| "loss": 1.5857, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 4.806322414532971, | |
| "eval_loss": 1.633513331413269, | |
| "eval_runtime": 13.1532, | |
| "eval_samples_per_second": 76.027, | |
| "eval_steps_per_second": 2.433, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 4.820626519811186, | |
| "grad_norm": 0.6455948477676112, | |
| "learning_rate": 5.815939125427373e-06, | |
| "loss": 1.5707, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 4.834930625089401, | |
| "grad_norm": 0.6271361263073431, | |
| "learning_rate": 5.795586336857253e-06, | |
| "loss": 1.563, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 4.849234730367615, | |
| "grad_norm": 0.7674869603862556, | |
| "learning_rate": 5.775227473698294e-06, | |
| "loss": 1.5779, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 4.86353883564583, | |
| "grad_norm": 0.637190923985461, | |
| "learning_rate": 5.754862954345081e-06, | |
| "loss": 1.5713, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.877842940924046, | |
| "grad_norm": 0.6651093545639066, | |
| "learning_rate": 5.734493197308442e-06, | |
| "loss": 1.5752, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 4.89214704620226, | |
| "grad_norm": 0.7868806203083217, | |
| "learning_rate": 5.714118621206843e-06, | |
| "loss": 1.5692, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 4.906451151480475, | |
| "grad_norm": 0.8067206283766785, | |
| "learning_rate": 5.693739644757781e-06, | |
| "loss": 1.5824, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 4.92075525675869, | |
| "grad_norm": 0.6156907735488538, | |
| "learning_rate": 5.673356686769194e-06, | |
| "loss": 1.5582, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 4.92075525675869, | |
| "eval_loss": 1.6318423748016357, | |
| "eval_runtime": 13.1193, | |
| "eval_samples_per_second": 76.224, | |
| "eval_steps_per_second": 2.439, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 4.935059362036904, | |
| "grad_norm": 0.7876895181186726, | |
| "learning_rate": 5.6529701661308415e-06, | |
| "loss": 1.5689, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 4.94936346731512, | |
| "grad_norm": 0.6292685628972012, | |
| "learning_rate": 5.632580501805692e-06, | |
| "loss": 1.5739, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 4.963667572593335, | |
| "grad_norm": 0.7149239853712192, | |
| "learning_rate": 5.612188112821328e-06, | |
| "loss": 1.5797, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 4.977971677871549, | |
| "grad_norm": 0.834110019775529, | |
| "learning_rate": 5.591793418261326e-06, | |
| "loss": 1.5763, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 4.992275783149764, | |
| "grad_norm": 0.7309326453697327, | |
| "learning_rate": 5.571396837256637e-06, | |
| "loss": 1.5726, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 5.006579888427979, | |
| "grad_norm": 0.6697280370753163, | |
| "learning_rate": 5.550998788976988e-06, | |
| "loss": 1.5634, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 5.020883993706193, | |
| "grad_norm": 0.6174166960990144, | |
| "learning_rate": 5.530599692622257e-06, | |
| "loss": 1.5467, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 5.035188098984409, | |
| "grad_norm": 0.6241514857747369, | |
| "learning_rate": 5.510199967413862e-06, | |
| "loss": 1.5508, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 5.035188098984409, | |
| "eval_loss": 1.6312223672866821, | |
| "eval_runtime": 13.1239, | |
| "eval_samples_per_second": 76.197, | |
| "eval_steps_per_second": 2.438, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 5.049492204262624, | |
| "grad_norm": 0.607902431110512, | |
| "learning_rate": 5.489800032586141e-06, | |
| "loss": 1.5467, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 5.063796309540838, | |
| "grad_norm": 0.6361444457465594, | |
| "learning_rate": 5.4694003073777446e-06, | |
| "loss": 1.5323, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 5.078100414819053, | |
| "grad_norm": 0.7502195043466207, | |
| "learning_rate": 5.449001211023014e-06, | |
| "loss": 1.5372, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 5.092404520097268, | |
| "grad_norm": 0.6959223099372485, | |
| "learning_rate": 5.428603162743365e-06, | |
| "loss": 1.5507, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 5.106708625375482, | |
| "grad_norm": 0.8282524586776218, | |
| "learning_rate": 5.408206581738677e-06, | |
| "loss": 1.5511, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 5.121012730653698, | |
| "grad_norm": 0.6152478153542872, | |
| "learning_rate": 5.387811887178673e-06, | |
| "loss": 1.5454, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 5.135316835931913, | |
| "grad_norm": 0.7178652735808533, | |
| "learning_rate": 5.367419498194309e-06, | |
| "loss": 1.5328, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 5.149620941210127, | |
| "grad_norm": 0.6199866059077553, | |
| "learning_rate": 5.347029833869161e-06, | |
| "loss": 1.5323, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 5.149620941210127, | |
| "eval_loss": 1.6294597387313843, | |
| "eval_runtime": 13.0999, | |
| "eval_samples_per_second": 76.336, | |
| "eval_steps_per_second": 2.443, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 5.163925046488342, | |
| "grad_norm": 0.5994719638332001, | |
| "learning_rate": 5.326643313230806e-06, | |
| "loss": 1.544, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 5.178229151766557, | |
| "grad_norm": 0.6101948560685385, | |
| "learning_rate": 5.306260355242221e-06, | |
| "loss": 1.5393, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 5.192533257044772, | |
| "grad_norm": 0.6358629359192572, | |
| "learning_rate": 5.2858813787931605e-06, | |
| "loss": 1.5418, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 5.206837362322987, | |
| "grad_norm": 0.5992154701681206, | |
| "learning_rate": 5.26550680269156e-06, | |
| "loss": 1.5399, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 5.221141467601202, | |
| "grad_norm": 0.7386890859479155, | |
| "learning_rate": 5.24513704565492e-06, | |
| "loss": 1.5541, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 5.235445572879416, | |
| "grad_norm": 0.6887954344111628, | |
| "learning_rate": 5.224772526301709e-06, | |
| "loss": 1.5342, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 5.249749678157631, | |
| "grad_norm": 0.6961019703931222, | |
| "learning_rate": 5.20441366314275e-06, | |
| "loss": 1.5463, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 5.2640537834358465, | |
| "grad_norm": 0.7142803422247822, | |
| "learning_rate": 5.184060874572628e-06, | |
| "loss": 1.5415, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 5.2640537834358465, | |
| "eval_loss": 1.6250876188278198, | |
| "eval_runtime": 13.1209, | |
| "eval_samples_per_second": 76.214, | |
| "eval_steps_per_second": 2.439, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 5.278357888714061, | |
| "grad_norm": 0.7209586773593375, | |
| "learning_rate": 5.163714578861091e-06, | |
| "loss": 1.5432, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 5.292661993992276, | |
| "grad_norm": 0.8558312401002982, | |
| "learning_rate": 5.143375194144452e-06, | |
| "loss": 1.5396, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 5.306966099270491, | |
| "grad_norm": 0.6140496298664848, | |
| "learning_rate": 5.123043138416996e-06, | |
| "loss": 1.5347, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 5.321270204548705, | |
| "grad_norm": 0.584034537933172, | |
| "learning_rate": 5.102718829522387e-06, | |
| "loss": 1.5455, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 5.33557430982692, | |
| "grad_norm": 0.7567323256836789, | |
| "learning_rate": 5.082402685145088e-06, | |
| "loss": 1.5373, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 5.3498784151051355, | |
| "grad_norm": 0.6914309741643679, | |
| "learning_rate": 5.062095122801771e-06, | |
| "loss": 1.5353, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 5.36418252038335, | |
| "grad_norm": 0.5912773883840152, | |
| "learning_rate": 5.041796559832742e-06, | |
| "loss": 1.5339, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 5.378486625661565, | |
| "grad_norm": 0.6263016315822758, | |
| "learning_rate": 5.021507413393355e-06, | |
| "loss": 1.5409, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 5.378486625661565, | |
| "eval_loss": 1.6224277019500732, | |
| "eval_runtime": 13.1785, | |
| "eval_samples_per_second": 75.881, | |
| "eval_steps_per_second": 2.428, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 5.39279073093978, | |
| "grad_norm": 0.5697288065062571, | |
| "learning_rate": 5.001228100445451e-06, | |
| "loss": 1.5362, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 5.407094836217994, | |
| "grad_norm": 0.67253268999925, | |
| "learning_rate": 4.9809590377487795e-06, | |
| "loss": 1.5245, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 5.42139894149621, | |
| "grad_norm": 0.6736080205591396, | |
| "learning_rate": 4.960700641852442e-06, | |
| "loss": 1.5263, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 5.4357030467744245, | |
| "grad_norm": 0.7729780534104512, | |
| "learning_rate": 4.9404533290863186e-06, | |
| "loss": 1.5297, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 5.450007152052639, | |
| "grad_norm": 0.6214293118686126, | |
| "learning_rate": 4.920217515552526e-06, | |
| "loss": 1.5397, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 5.464311257330854, | |
| "grad_norm": 0.6343711973214149, | |
| "learning_rate": 4.8999936171168615e-06, | |
| "loss": 1.5439, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 5.478615362609069, | |
| "grad_norm": 0.7291330555122011, | |
| "learning_rate": 4.879782049400251e-06, | |
| "loss": 1.5336, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 5.492919467887283, | |
| "grad_norm": 0.6712685546736542, | |
| "learning_rate": 4.8595832277702175e-06, | |
| "loss": 1.5329, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 5.492919467887283, | |
| "eval_loss": 1.622052788734436, | |
| "eval_runtime": 13.144, | |
| "eval_samples_per_second": 76.08, | |
| "eval_steps_per_second": 2.435, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 5.507223573165499, | |
| "grad_norm": 0.5709944496814116, | |
| "learning_rate": 4.839397567332334e-06, | |
| "loss": 1.5404, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 5.5215276784437135, | |
| "grad_norm": 0.683232233789078, | |
| "learning_rate": 4.8192254829217e-06, | |
| "loss": 1.5422, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 5.535831783721928, | |
| "grad_norm": 0.6192373192804173, | |
| "learning_rate": 4.799067389094416e-06, | |
| "loss": 1.5443, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 5.550135889000143, | |
| "grad_norm": 0.7502591192271298, | |
| "learning_rate": 4.7789237001190624e-06, | |
| "loss": 1.5296, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 5.564439994278358, | |
| "grad_norm": 0.6351610614349129, | |
| "learning_rate": 4.758794829968181e-06, | |
| "loss": 1.5348, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 5.578744099556573, | |
| "grad_norm": 0.6108826056364483, | |
| "learning_rate": 4.738681192309778e-06, | |
| "loss": 1.5279, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 5.593048204834788, | |
| "grad_norm": 0.6437182525691378, | |
| "learning_rate": 4.718583200498814e-06, | |
| "loss": 1.5366, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 5.6073523101130025, | |
| "grad_norm": 0.639815861886649, | |
| "learning_rate": 4.698501267568713e-06, | |
| "loss": 1.5357, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 5.6073523101130025, | |
| "eval_loss": 1.6180142164230347, | |
| "eval_runtime": 13.085, | |
| "eval_samples_per_second": 76.423, | |
| "eval_steps_per_second": 2.446, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 5.621656415391217, | |
| "grad_norm": 0.7200835319066389, | |
| "learning_rate": 4.678435806222873e-06, | |
| "loss": 1.5321, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 5.635960520669432, | |
| "grad_norm": 0.783772141557461, | |
| "learning_rate": 4.658387228826185e-06, | |
| "loss": 1.5222, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 5.6502646259476474, | |
| "grad_norm": 0.6132596760513117, | |
| "learning_rate": 4.638355947396557e-06, | |
| "loss": 1.5297, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 5.664568731225862, | |
| "grad_norm": 0.6283378075518518, | |
| "learning_rate": 4.61834237359645e-06, | |
| "loss": 1.5295, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 5.678872836504077, | |
| "grad_norm": 0.6326692578607431, | |
| "learning_rate": 4.598346918724417e-06, | |
| "loss": 1.5351, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 5.6931769417822915, | |
| "grad_norm": 0.5940063235489941, | |
| "learning_rate": 4.578369993706643e-06, | |
| "loss": 1.5308, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 5.707481047060506, | |
| "grad_norm": 0.6349874592624309, | |
| "learning_rate": 4.5584120090885125e-06, | |
| "loss": 1.5214, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 5.721785152338721, | |
| "grad_norm": 0.7828872685863243, | |
| "learning_rate": 4.538473375026164e-06, | |
| "loss": 1.5428, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 5.721785152338721, | |
| "eval_loss": 1.6172399520874023, | |
| "eval_runtime": 13.1288, | |
| "eval_samples_per_second": 76.168, | |
| "eval_steps_per_second": 2.437, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 5.736089257616936, | |
| "grad_norm": 0.6299009394488376, | |
| "learning_rate": 4.518554501278064e-06, | |
| "loss": 1.5295, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 5.750393362895151, | |
| "grad_norm": 0.6258430789114957, | |
| "learning_rate": 4.498655797196586e-06, | |
| "loss": 1.5329, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 5.764697468173366, | |
| "grad_norm": 0.696293581732556, | |
| "learning_rate": 4.478777671719593e-06, | |
| "loss": 1.5413, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 5.7790015734515805, | |
| "grad_norm": 0.7124246186685519, | |
| "learning_rate": 4.458920533362039e-06, | |
| "loss": 1.5228, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 5.793305678729795, | |
| "grad_norm": 0.5760090289969003, | |
| "learning_rate": 4.439084790207577e-06, | |
| "loss": 1.5353, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 5.80760978400801, | |
| "grad_norm": 0.6449974415534122, | |
| "learning_rate": 4.419270849900164e-06, | |
| "loss": 1.5357, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 5.821913889286225, | |
| "grad_norm": 0.6282375399916217, | |
| "learning_rate": 4.399479119635683e-06, | |
| "loss": 1.5321, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 5.83621799456444, | |
| "grad_norm": 0.5919862101266721, | |
| "learning_rate": 4.3797100061535856e-06, | |
| "loss": 1.526, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 5.83621799456444, | |
| "eval_loss": 1.6131237745285034, | |
| "eval_runtime": 13.1139, | |
| "eval_samples_per_second": 76.255, | |
| "eval_steps_per_second": 2.44, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 5.850522099842655, | |
| "grad_norm": 0.6029658262074238, | |
| "learning_rate": 4.359963915728523e-06, | |
| "loss": 1.5247, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 5.8648262051208695, | |
| "grad_norm": 0.670869434044021, | |
| "learning_rate": 4.340241254162004e-06, | |
| "loss": 1.525, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 5.879130310399084, | |
| "grad_norm": 0.6367180654906258, | |
| "learning_rate": 4.320542426774042e-06, | |
| "loss": 1.5269, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 5.8934344156773, | |
| "grad_norm": 0.5920409715922154, | |
| "learning_rate": 4.300867838394843e-06, | |
| "loss": 1.5241, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 5.907738520955514, | |
| "grad_norm": 0.5951037902934461, | |
| "learning_rate": 4.281217893356478e-06, | |
| "loss": 1.5404, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 5.922042626233729, | |
| "grad_norm": 0.7114294289873735, | |
| "learning_rate": 4.261592995484567e-06, | |
| "loss": 1.5329, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 5.936346731511944, | |
| "grad_norm": 0.5783828576596121, | |
| "learning_rate": 4.241993548089994e-06, | |
| "loss": 1.533, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 5.9506508367901585, | |
| "grad_norm": 0.6407329854514554, | |
| "learning_rate": 4.2224199539606026e-06, | |
| "loss": 1.5145, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 5.9506508367901585, | |
| "eval_loss": 1.6121162176132202, | |
| "eval_runtime": 13.1147, | |
| "eval_samples_per_second": 76.25, | |
| "eval_steps_per_second": 2.44, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 5.964954942068374, | |
| "grad_norm": 0.634888254231562, | |
| "learning_rate": 4.202872615352932e-06, | |
| "loss": 1.5212, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 5.979259047346589, | |
| "grad_norm": 0.6229293024525429, | |
| "learning_rate": 4.183351933983942e-06, | |
| "loss": 1.5226, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 5.993563152624803, | |
| "grad_norm": 0.8314381666700691, | |
| "learning_rate": 4.163858311022765e-06, | |
| "loss": 1.5387, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 6.007867257903018, | |
| "grad_norm": 0.59693291322645, | |
| "learning_rate": 4.144392147082447e-06, | |
| "loss": 1.5043, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 6.022171363181233, | |
| "grad_norm": 0.665194604166561, | |
| "learning_rate": 4.124953842211733e-06, | |
| "loss": 1.5002, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 6.0364754684594475, | |
| "grad_norm": 0.6456678113415395, | |
| "learning_rate": 4.105543795886834e-06, | |
| "loss": 1.5004, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 6.050779573737663, | |
| "grad_norm": 0.642020830639423, | |
| "learning_rate": 4.086162407003219e-06, | |
| "loss": 1.499, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 6.065083679015878, | |
| "grad_norm": 0.6641186183494755, | |
| "learning_rate": 4.066810073867421e-06, | |
| "loss": 1.4973, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 6.065083679015878, | |
| "eval_loss": 1.6121020317077637, | |
| "eval_runtime": 13.0899, | |
| "eval_samples_per_second": 76.395, | |
| "eval_steps_per_second": 2.445, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 6.079387784294092, | |
| "grad_norm": 0.634272316306304, | |
| "learning_rate": 4.047487194188846e-06, | |
| "loss": 1.5132, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 6.093691889572307, | |
| "grad_norm": 0.6748754827417714, | |
| "learning_rate": 4.028194165071603e-06, | |
| "loss": 1.5064, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 6.107995994850522, | |
| "grad_norm": 0.7061607465519819, | |
| "learning_rate": 4.008931383006345e-06, | |
| "loss": 1.505, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 6.122300100128737, | |
| "grad_norm": 0.662154780004609, | |
| "learning_rate": 3.9896992438621195e-06, | |
| "loss": 1.5005, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 6.136604205406952, | |
| "grad_norm": 0.6380113889018068, | |
| "learning_rate": 3.9704981428782255e-06, | |
| "loss": 1.5061, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 6.150908310685167, | |
| "grad_norm": 0.6382768302952283, | |
| "learning_rate": 3.951328474656103e-06, | |
| "loss": 1.4931, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 6.165212415963381, | |
| "grad_norm": 0.6767629241771801, | |
| "learning_rate": 3.932190633151217e-06, | |
| "loss": 1.5037, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 6.179516521241596, | |
| "grad_norm": 0.6282216484213683, | |
| "learning_rate": 3.913085011664961e-06, | |
| "loss": 1.5036, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 6.179516521241596, | |
| "eval_loss": 1.6118288040161133, | |
| "eval_runtime": 13.1481, | |
| "eval_samples_per_second": 76.057, | |
| "eval_steps_per_second": 2.434, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 6.193820626519811, | |
| "grad_norm": 0.6004617238206564, | |
| "learning_rate": 3.894012002836578e-06, | |
| "loss": 1.5117, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 6.208124731798026, | |
| "grad_norm": 0.7154680728784966, | |
| "learning_rate": 3.874971998635083e-06, | |
| "loss": 1.5095, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 6.222428837076241, | |
| "grad_norm": 0.6725566004485558, | |
| "learning_rate": 3.855965390351222e-06, | |
| "loss": 1.4909, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 6.236732942354456, | |
| "grad_norm": 0.5965877047430266, | |
| "learning_rate": 3.836992568589417e-06, | |
| "loss": 1.4975, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 6.25103704763267, | |
| "grad_norm": 0.6027834656468215, | |
| "learning_rate": 3.818053923259745e-06, | |
| "loss": 1.5007, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 6.265341152910885, | |
| "grad_norm": 0.6663203163783424, | |
| "learning_rate": 3.7991498435699213e-06, | |
| "loss": 1.5051, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 6.279645258189101, | |
| "grad_norm": 0.7125353969852749, | |
| "learning_rate": 3.780280718017307e-06, | |
| "loss": 1.5012, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 6.293949363467315, | |
| "grad_norm": 0.6482680068197426, | |
| "learning_rate": 3.7614469343809208e-06, | |
| "loss": 1.5049, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 6.293949363467315, | |
| "eval_loss": 1.6089048385620117, | |
| "eval_runtime": 13.1237, | |
| "eval_samples_per_second": 76.198, | |
| "eval_steps_per_second": 2.438, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 6.30825346874553, | |
| "grad_norm": 0.7881816467240778, | |
| "learning_rate": 3.7426488797134706e-06, | |
| "loss": 1.5095, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 6.322557574023745, | |
| "grad_norm": 0.6541787463398775, | |
| "learning_rate": 3.7238869403333965e-06, | |
| "loss": 1.504, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 6.336861679301959, | |
| "grad_norm": 0.664079330402415, | |
| "learning_rate": 3.7051615018169363e-06, | |
| "loss": 1.5066, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 6.351165784580174, | |
| "grad_norm": 0.5916075057540389, | |
| "learning_rate": 3.686472948990198e-06, | |
| "loss": 1.5086, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 6.36546988985839, | |
| "grad_norm": 0.7325464747774915, | |
| "learning_rate": 3.6678216659212546e-06, | |
| "loss": 1.4992, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 6.379773995136604, | |
| "grad_norm": 0.7007083689793716, | |
| "learning_rate": 3.6492080359122487e-06, | |
| "loss": 1.5, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 6.394078100414819, | |
| "grad_norm": 0.6739401831383736, | |
| "learning_rate": 3.630632441491512e-06, | |
| "loss": 1.4995, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 6.408382205693034, | |
| "grad_norm": 0.6863089101260594, | |
| "learning_rate": 3.6120952644057104e-06, | |
| "loss": 1.5017, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 6.408382205693034, | |
| "eval_loss": 1.606228232383728, | |
| "eval_runtime": 13.1397, | |
| "eval_samples_per_second": 76.105, | |
| "eval_steps_per_second": 2.435, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 6.422686310971248, | |
| "grad_norm": 0.6147754073523626, | |
| "learning_rate": 3.593596885611997e-06, | |
| "loss": 1.4926, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 6.436990416249464, | |
| "grad_norm": 0.5871499975242569, | |
| "learning_rate": 3.575137685270182e-06, | |
| "loss": 1.4983, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 6.451294521527679, | |
| "grad_norm": 0.5786188568209956, | |
| "learning_rate": 3.556718042734915e-06, | |
| "loss": 1.4949, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 6.465598626805893, | |
| "grad_norm": 0.6071462043583132, | |
| "learning_rate": 3.538338336547902e-06, | |
| "loss": 1.4987, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 6.479902732084108, | |
| "grad_norm": 0.5785217797393283, | |
| "learning_rate": 3.5199989444301082e-06, | |
| "loss": 1.4931, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 6.494206837362323, | |
| "grad_norm": 0.623076022970078, | |
| "learning_rate": 3.5017002432740164e-06, | |
| "loss": 1.4981, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 6.508510942640537, | |
| "grad_norm": 0.73033655866744, | |
| "learning_rate": 3.483442609135862e-06, | |
| "loss": 1.5008, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 6.522815047918753, | |
| "grad_norm": 0.5934926417919788, | |
| "learning_rate": 3.4652264172279153e-06, | |
| "loss": 1.4881, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 6.522815047918753, | |
| "eval_loss": 1.604162335395813, | |
| "eval_runtime": 13.1475, | |
| "eval_samples_per_second": 76.06, | |
| "eval_steps_per_second": 2.434, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 6.537119153196968, | |
| "grad_norm": 0.6069986350354387, | |
| "learning_rate": 3.4470520419107667e-06, | |
| "loss": 1.4879, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 6.551423258475182, | |
| "grad_norm": 0.7399652835966712, | |
| "learning_rate": 3.4289198566856396e-06, | |
| "loss": 1.4942, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 6.565727363753397, | |
| "grad_norm": 0.6114058208337956, | |
| "learning_rate": 3.4108302341867045e-06, | |
| "loss": 1.4961, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 6.580031469031612, | |
| "grad_norm": 0.6007896515222266, | |
| "learning_rate": 3.392783546173426e-06, | |
| "loss": 1.4929, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 6.594335574309827, | |
| "grad_norm": 0.7491177037600624, | |
| "learning_rate": 3.374780163522929e-06, | |
| "loss": 1.4955, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 6.608639679588042, | |
| "grad_norm": 0.6917907740940776, | |
| "learning_rate": 3.356820456222362e-06, | |
| "loss": 1.5053, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 6.622943784866257, | |
| "grad_norm": 0.5797836988455244, | |
| "learning_rate": 3.338904793361314e-06, | |
| "loss": 1.4974, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 6.637247890144471, | |
| "grad_norm": 0.6589102327372058, | |
| "learning_rate": 3.321033543124202e-06, | |
| "loss": 1.4969, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 6.637247890144471, | |
| "eval_loss": 1.6024819612503052, | |
| "eval_runtime": 13.1262, | |
| "eval_samples_per_second": 76.183, | |
| "eval_steps_per_second": 2.438, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 6.651551995422686, | |
| "grad_norm": 0.67042895269073, | |
| "learning_rate": 3.3032070727827353e-06, | |
| "loss": 1.4931, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 6.665856100700902, | |
| "grad_norm": 0.6465762171859113, | |
| "learning_rate": 3.285425748688341e-06, | |
| "loss": 1.5047, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 6.680160205979116, | |
| "grad_norm": 0.5928906211207966, | |
| "learning_rate": 3.2676899362646563e-06, | |
| "loss": 1.5009, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 6.694464311257331, | |
| "grad_norm": 0.6204319354437976, | |
| "learning_rate": 3.2500000000000015e-06, | |
| "loss": 1.4904, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 6.708768416535546, | |
| "grad_norm": 0.6370248234668529, | |
| "learning_rate": 3.232356303439897e-06, | |
| "loss": 1.4962, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 6.72307252181376, | |
| "grad_norm": 0.5797494709987538, | |
| "learning_rate": 3.2147592091795992e-06, | |
| "loss": 1.4938, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 6.737376627091975, | |
| "grad_norm": 0.5800297263686035, | |
| "learning_rate": 3.1972090788566325e-06, | |
| "loss": 1.4852, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 6.751680732370191, | |
| "grad_norm": 0.6400211162161145, | |
| "learning_rate": 3.1797062731433764e-06, | |
| "loss": 1.4978, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 6.751680732370191, | |
| "eval_loss": 1.6009289026260376, | |
| "eval_runtime": 13.1205, | |
| "eval_samples_per_second": 76.216, | |
| "eval_steps_per_second": 2.439, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 6.765984837648405, | |
| "grad_norm": 0.6047950853143369, | |
| "learning_rate": 3.1622511517396297e-06, | |
| "loss": 1.4931, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 6.78028894292662, | |
| "grad_norm": 0.6976178519904986, | |
| "learning_rate": 3.144844073365247e-06, | |
| "loss": 1.4996, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 6.794593048204835, | |
| "grad_norm": 0.6200936341605483, | |
| "learning_rate": 3.127485395752739e-06, | |
| "loss": 1.4874, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 6.808897153483049, | |
| "grad_norm": 0.6678212868779091, | |
| "learning_rate": 3.1101754756399427e-06, | |
| "loss": 1.4951, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 6.823201258761264, | |
| "grad_norm": 0.6777775649765228, | |
| "learning_rate": 3.0929146687626756e-06, | |
| "loss": 1.4936, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 6.83750536403948, | |
| "grad_norm": 0.5932024233832688, | |
| "learning_rate": 3.0757033298474274e-06, | |
| "loss": 1.4908, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 6.851809469317694, | |
| "grad_norm": 0.6344747435348402, | |
| "learning_rate": 3.0585418126040832e-06, | |
| "loss": 1.5015, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 6.866113574595909, | |
| "grad_norm": 0.629407558903598, | |
| "learning_rate": 3.0414304697186313e-06, | |
| "loss": 1.4797, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 6.866113574595909, | |
| "eval_loss": 1.5976924896240234, | |
| "eval_runtime": 13.1566, | |
| "eval_samples_per_second": 76.008, | |
| "eval_steps_per_second": 2.432, | |
| "step": 24000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 34950, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 800, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1342699751735296e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |