| { |
| "best_global_step": 900, |
| "best_metric": 1.4535424709320068, |
| "best_model_checkpoint": "outputs/Qwen3.5-9B-cpt/checkpoint-900", |
| "epoch": 0.5689450809956539, |
| "eval_steps": 50, |
| "global_step": 900, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006321612011062821, |
| "grad_norm": 2.2357523441314697, |
| "learning_rate": 1.8947368421052634e-06, |
| "loss": 1.8448415756225587, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.012643224022125641, |
| "grad_norm": 1.1725322008132935, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 1.728614044189453, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.018964836033188465, |
| "grad_norm": 1.0519399642944336, |
| "learning_rate": 6.105263157894738e-06, |
| "loss": 1.6825117111206054, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.025286448044251283, |
| "grad_norm": 0.9476595520973206, |
| "learning_rate": 8.210526315789475e-06, |
| "loss": 1.627689743041992, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.03160806005531411, |
| "grad_norm": 1.026922345161438, |
| "learning_rate": 1.0315789473684213e-05, |
| "loss": 1.625675582885742, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03160806005531411, |
| "eval_loss": 1.6307754516601562, |
| "eval_runtime": 1436.5207, |
| "eval_samples_per_second": 3.71, |
| "eval_steps_per_second": 1.855, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03792967206637693, |
| "grad_norm": 0.9994499683380127, |
| "learning_rate": 1.2421052631578949e-05, |
| "loss": 1.6042352676391602, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.044251284077439744, |
| "grad_norm": 1.2228177785873413, |
| "learning_rate": 1.4526315789473687e-05, |
| "loss": 1.60198917388916, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.050572896088502566, |
| "grad_norm": 0.9573417901992798, |
| "learning_rate": 1.6631578947368423e-05, |
| "loss": 1.6050102233886718, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.05689450809956539, |
| "grad_norm": 0.9371166825294495, |
| "learning_rate": 1.873684210526316e-05, |
| "loss": 1.5779685020446776, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.06321612011062822, |
| "grad_norm": 0.9192007780075073, |
| "learning_rate": 1.9999916170794767e-05, |
| "loss": 1.5790796279907227, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.06321612011062822, |
| "eval_loss": 1.5887949466705322, |
| "eval_runtime": 1428.4275, |
| "eval_samples_per_second": 3.731, |
| "eval_steps_per_second": 1.866, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.06953773212169104, |
| "grad_norm": 0.9729642271995544, |
| "learning_rate": 1.99989731083767e-05, |
| "loss": 1.54850435256958, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.07585934413275386, |
| "grad_norm": 0.9361611008644104, |
| "learning_rate": 1.9996982296182915e-05, |
| "loss": 1.5509929656982422, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.08218095614381667, |
| "grad_norm": 1.1141622066497803, |
| "learning_rate": 1.999394394282214e-05, |
| "loss": 1.5608986854553222, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.08850256815487949, |
| "grad_norm": 1.1783406734466553, |
| "learning_rate": 1.9989858366670475e-05, |
| "loss": 1.5713417053222656, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.09482418016594231, |
| "grad_norm": 0.8572059273719788, |
| "learning_rate": 1.9984725995838032e-05, |
| "loss": 1.5512660026550293, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.09482418016594231, |
| "eval_loss": 1.5633909702301025, |
| "eval_runtime": 1434.0069, |
| "eval_samples_per_second": 3.716, |
| "eval_steps_per_second": 1.858, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.10114579217700513, |
| "grad_norm": 1.1298227310180664, |
| "learning_rate": 1.9978547368124073e-05, |
| "loss": 1.5835878372192382, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.10746740418806795, |
| "grad_norm": 0.85079425573349, |
| "learning_rate": 1.997132313096066e-05, |
| "loss": 1.5457270622253418, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.11378901619913077, |
| "grad_norm": 0.7577758431434631, |
| "learning_rate": 1.9963054041344826e-05, |
| "loss": 1.5363761901855468, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.1201106282101936, |
| "grad_norm": 0.9953492879867554, |
| "learning_rate": 1.9953740965759222e-05, |
| "loss": 1.5482823371887207, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.12643224022125643, |
| "grad_norm": 1.0341110229492188, |
| "learning_rate": 1.994338488008134e-05, |
| "loss": 1.533665084838867, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.12643224022125643, |
| "eval_loss": 1.5468075275421143, |
| "eval_runtime": 1432.7951, |
| "eval_samples_per_second": 3.719, |
| "eval_steps_per_second": 1.86, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.13275385223231925, |
| "grad_norm": 1.2680150270462036, |
| "learning_rate": 1.993198686948127e-05, |
| "loss": 1.5316329956054688, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.13907546424338207, |
| "grad_norm": 0.7387447953224182, |
| "learning_rate": 1.9919548128307954e-05, |
| "loss": 1.5236242294311524, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.1453970762544449, |
| "grad_norm": 1.4287664890289307, |
| "learning_rate": 1.9906069959964073e-05, |
| "loss": 1.5394685745239258, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.15171868826550772, |
| "grad_norm": 1.0277458429336548, |
| "learning_rate": 1.989155377676944e-05, |
| "loss": 1.52191104888916, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.15804030027657054, |
| "grad_norm": 0.7789772152900696, |
| "learning_rate": 1.9876001099813018e-05, |
| "loss": 1.546618366241455, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.15804030027657054, |
| "eval_loss": 1.533789873123169, |
| "eval_runtime": 1436.9068, |
| "eval_samples_per_second": 3.709, |
| "eval_steps_per_second": 1.855, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.16436191228763333, |
| "grad_norm": 1.4293335676193237, |
| "learning_rate": 1.9859413558793545e-05, |
| "loss": 1.540808868408203, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.17068352429869615, |
| "grad_norm": 0.757379949092865, |
| "learning_rate": 1.9841792891848744e-05, |
| "loss": 1.521357822418213, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.17700513630975898, |
| "grad_norm": 1.5915902853012085, |
| "learning_rate": 1.982314094537321e-05, |
| "loss": 1.5167811393737793, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.1833267483208218, |
| "grad_norm": 0.8537394404411316, |
| "learning_rate": 1.980345967382491e-05, |
| "loss": 1.5079852104187013, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.18964836033188462, |
| "grad_norm": 0.7207210063934326, |
| "learning_rate": 1.978275113952041e-05, |
| "loss": 1.504821491241455, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.18964836033188462, |
| "eval_loss": 1.5223760604858398, |
| "eval_runtime": 1434.9006, |
| "eval_samples_per_second": 3.714, |
| "eval_steps_per_second": 1.857, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.19596997234294744, |
| "grad_norm": 0.761333167552948, |
| "learning_rate": 1.9761017512418757e-05, |
| "loss": 1.511648941040039, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.20229158435401026, |
| "grad_norm": 1.4120904207229614, |
| "learning_rate": 1.973826106989411e-05, |
| "loss": 1.4993165016174317, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.20861319636507308, |
| "grad_norm": 1.1191859245300293, |
| "learning_rate": 1.9714484196497087e-05, |
| "loss": 1.5109681129455566, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.2149348083761359, |
| "grad_norm": 0.7707664370536804, |
| "learning_rate": 1.9689689383704907e-05, |
| "loss": 1.5163365364074708, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.22125642038719873, |
| "grad_norm": 1.249089241027832, |
| "learning_rate": 1.9663879229660338e-05, |
| "loss": 1.5154297828674317, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.22125642038719873, |
| "eval_loss": 1.5136882066726685, |
| "eval_runtime": 1434.1581, |
| "eval_samples_per_second": 3.716, |
| "eval_steps_per_second": 1.858, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.22757803239826155, |
| "grad_norm": 0.8356915712356567, |
| "learning_rate": 1.963705643889941e-05, |
| "loss": 1.500742244720459, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.23389964440932437, |
| "grad_norm": 0.9244163036346436, |
| "learning_rate": 1.9609223822068045e-05, |
| "loss": 1.5091425895690918, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.2402212564203872, |
| "grad_norm": 2.6756114959716797, |
| "learning_rate": 1.9580384295627546e-05, |
| "loss": 1.5230279922485352, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.24654286843145, |
| "grad_norm": 0.8224273324012756, |
| "learning_rate": 1.9550540881548962e-05, |
| "loss": 1.4959823608398437, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.25286448044251286, |
| "grad_norm": 2.7606499195098877, |
| "learning_rate": 1.9519696706996457e-05, |
| "loss": 1.504225730895996, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.25286448044251286, |
| "eval_loss": 1.5063496828079224, |
| "eval_runtime": 1442.4518, |
| "eval_samples_per_second": 3.694, |
| "eval_steps_per_second": 1.848, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.25918609245357566, |
| "grad_norm": 1.9451311826705933, |
| "learning_rate": 1.9487855003999632e-05, |
| "loss": 1.5024944305419923, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.2655077044646385, |
| "grad_norm": 0.7222695350646973, |
| "learning_rate": 1.9455019109114833e-05, |
| "loss": 1.5029170036315918, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.2718293164757013, |
| "grad_norm": 1.9110443592071533, |
| "learning_rate": 1.9421192463075532e-05, |
| "loss": 1.511544895172119, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.27815092848676415, |
| "grad_norm": 0.8087928295135498, |
| "learning_rate": 1.938637861043179e-05, |
| "loss": 1.4900238037109375, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.28447254049782694, |
| "grad_norm": 1.2225767374038696, |
| "learning_rate": 1.9350581199178858e-05, |
| "loss": 1.479935646057129, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.28447254049782694, |
| "eval_loss": 1.4983773231506348, |
| "eval_runtime": 1432.1372, |
| "eval_samples_per_second": 3.721, |
| "eval_steps_per_second": 1.861, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.2907941525088898, |
| "grad_norm": 0.7390967011451721, |
| "learning_rate": 1.9313803980374882e-05, |
| "loss": 1.507608699798584, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.2971157645199526, |
| "grad_norm": 1.7765216827392578, |
| "learning_rate": 1.9276050807747878e-05, |
| "loss": 1.486252784729004, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.30343737653101543, |
| "grad_norm": 1.1083087921142578, |
| "learning_rate": 1.9237325637291897e-05, |
| "loss": 1.4911764144897461, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.30975898854207823, |
| "grad_norm": 1.495973825454712, |
| "learning_rate": 1.9197632526852502e-05, |
| "loss": 1.4877856254577637, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.3160806005531411, |
| "grad_norm": 0.844947338104248, |
| "learning_rate": 1.915697563570156e-05, |
| "loss": 1.479910182952881, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3160806005531411, |
| "eval_loss": 1.4914230108261108, |
| "eval_runtime": 1432.4776, |
| "eval_samples_per_second": 3.72, |
| "eval_steps_per_second": 1.86, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.32240221256420387, |
| "grad_norm": 1.77666437625885, |
| "learning_rate": 1.9115359224101416e-05, |
| "loss": 1.490778350830078, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.32872382457526667, |
| "grad_norm": 2.99625301361084, |
| "learning_rate": 1.9072787652858463e-05, |
| "loss": 1.494775390625, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.3350454365863295, |
| "grad_norm": 1.031172752380371, |
| "learning_rate": 1.9029265382866216e-05, |
| "loss": 1.4774039268493653, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.3413670485973923, |
| "grad_norm": 0.9397842288017273, |
| "learning_rate": 1.8984796974637845e-05, |
| "loss": 1.4831487655639648, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.34768866060845516, |
| "grad_norm": 0.822282075881958, |
| "learning_rate": 1.8939387087828326e-05, |
| "loss": 1.4724056243896484, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.34768866060845516, |
| "eval_loss": 1.4864764213562012, |
| "eval_runtime": 1435.983, |
| "eval_samples_per_second": 3.711, |
| "eval_steps_per_second": 1.856, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.35401027261951795, |
| "grad_norm": 1.08564293384552, |
| "learning_rate": 1.889304048074616e-05, |
| "loss": 1.4828974723815918, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.3603318846305808, |
| "grad_norm": 1.6417145729064941, |
| "learning_rate": 1.8845762009854765e-05, |
| "loss": 1.4577611923217773, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.3666534966416436, |
| "grad_norm": 1.2441695928573608, |
| "learning_rate": 1.8797556629263603e-05, |
| "loss": 1.4795442581176759, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.37297510865270644, |
| "grad_norm": 0.7002350687980652, |
| "learning_rate": 1.8748429390209052e-05, |
| "loss": 1.4860575675964356, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.37929672066376924, |
| "grad_norm": 0.7346900701522827, |
| "learning_rate": 1.869838544052511e-05, |
| "loss": 1.4883034706115723, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.37929672066376924, |
| "eval_loss": 1.4805960655212402, |
| "eval_runtime": 1434.6251, |
| "eval_samples_per_second": 3.715, |
| "eval_steps_per_second": 1.858, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3856183326748321, |
| "grad_norm": 1.2719956636428833, |
| "learning_rate": 1.8647430024103975e-05, |
| "loss": 1.4628222465515137, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.3919399446858949, |
| "grad_norm": 3.929159641265869, |
| "learning_rate": 1.8595568480346555e-05, |
| "loss": 1.4697487831115723, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.39826155669695773, |
| "grad_norm": 1.7072134017944336, |
| "learning_rate": 1.8542806243602984e-05, |
| "loss": 1.466939926147461, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.4045831687080205, |
| "grad_norm": 0.8139464855194092, |
| "learning_rate": 1.8489148842603172e-05, |
| "loss": 1.47437744140625, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.4109047807190834, |
| "grad_norm": 0.8353721499443054, |
| "learning_rate": 1.8434601899877484e-05, |
| "loss": 1.4795381546020507, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.4109047807190834, |
| "eval_loss": 1.4759365320205688, |
| "eval_runtime": 1440.6676, |
| "eval_samples_per_second": 3.699, |
| "eval_steps_per_second": 1.85, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.41722639273014617, |
| "grad_norm": 1.203122854232788, |
| "learning_rate": 1.8379171131167557e-05, |
| "loss": 1.4443695068359375, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.423548004741209, |
| "grad_norm": 0.7811446785926819, |
| "learning_rate": 1.8322862344827404e-05, |
| "loss": 1.453621006011963, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.4298696167522718, |
| "grad_norm": 0.7570304274559021, |
| "learning_rate": 1.8265681441214744e-05, |
| "loss": 1.4751152992248535, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.43619122876333466, |
| "grad_norm": 1.1196154356002808, |
| "learning_rate": 1.8207634412072765e-05, |
| "loss": 1.4665375709533692, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.44251284077439745, |
| "grad_norm": 1.452694296836853, |
| "learning_rate": 1.8148727339902245e-05, |
| "loss": 1.4367003440856934, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.44251284077439745, |
| "eval_loss": 1.4716598987579346, |
| "eval_runtime": 1433.735, |
| "eval_samples_per_second": 3.717, |
| "eval_steps_per_second": 1.859, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.4488344527854603, |
| "grad_norm": 0.9854422807693481, |
| "learning_rate": 1.8088966397324215e-05, |
| "loss": 1.4711213111877441, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.4551560647965231, |
| "grad_norm": 0.8611396551132202, |
| "learning_rate": 1.8028357846433144e-05, |
| "loss": 1.447887134552002, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.46147767680758595, |
| "grad_norm": 0.9595324397087097, |
| "learning_rate": 1.796690803814076e-05, |
| "loss": 1.4460906982421875, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.46779928881864874, |
| "grad_norm": 0.995147705078125, |
| "learning_rate": 1.7904623411510565e-05, |
| "loss": 1.4776107788085937, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.4741209008297116, |
| "grad_norm": 1.3566371202468872, |
| "learning_rate": 1.7841510493083126e-05, |
| "loss": 1.4614599227905274, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.4741209008297116, |
| "eval_loss": 1.4664231538772583, |
| "eval_runtime": 1435.7161, |
| "eval_samples_per_second": 3.712, |
| "eval_steps_per_second": 1.856, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.4804425128407744, |
| "grad_norm": 1.0786532163619995, |
| "learning_rate": 1.7777575896192177e-05, |
| "loss": 1.4631671905517578, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.48676412485183723, |
| "grad_norm": 1.5780668258666992, |
| "learning_rate": 1.7712826320271633e-05, |
| "loss": 1.4548497200012207, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.4930857368629, |
| "grad_norm": 1.075210690498352, |
| "learning_rate": 1.7647268550153583e-05, |
| "loss": 1.4418771743774415, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.4994073488739629, |
| "grad_norm": 0.7408574819564819, |
| "learning_rate": 1.7580909455357344e-05, |
| "loss": 1.4451427459716797, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.5057289608850257, |
| "grad_norm": 0.9548968076705933, |
| "learning_rate": 1.7513755989369636e-05, |
| "loss": 1.4488779067993165, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5057289608850257, |
| "eval_loss": 1.461513876914978, |
| "eval_runtime": 1439.1351, |
| "eval_samples_per_second": 3.703, |
| "eval_steps_per_second": 1.852, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5120505728960885, |
| "grad_norm": 0.8898774981498718, |
| "learning_rate": 1.744581518891595e-05, |
| "loss": 1.4661118507385253, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.5183721849071513, |
| "grad_norm": 2.370990514755249, |
| "learning_rate": 1.737709417322319e-05, |
| "loss": 1.4475753784179688, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.5246937969182142, |
| "grad_norm": 0.7134878039360046, |
| "learning_rate": 1.730760014327371e-05, |
| "loss": 1.4453336715698242, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.531015408929277, |
| "grad_norm": 0.7120240330696106, |
| "learning_rate": 1.72373403810507e-05, |
| "loss": 1.4352140426635742, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.5373370209403397, |
| "grad_norm": 1.5345282554626465, |
| "learning_rate": 1.7166322248775212e-05, |
| "loss": 1.434824275970459, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.5373370209403397, |
| "eval_loss": 1.4574466943740845, |
| "eval_runtime": 1435.0764, |
| "eval_samples_per_second": 3.713, |
| "eval_steps_per_second": 1.857, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.5436586329514026, |
| "grad_norm": 0.7333837151527405, |
| "learning_rate": 1.709455318813463e-05, |
| "loss": 1.4499679565429688, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.5499802449624654, |
| "grad_norm": 1.3881059885025024, |
| "learning_rate": 1.7022040719502935e-05, |
| "loss": 1.4426145553588867, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.5563018569735283, |
| "grad_norm": 2.6665091514587402, |
| "learning_rate": 1.6948792441152666e-05, |
| "loss": 1.4703943252563476, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.562623468984591, |
| "grad_norm": 0.7150371074676514, |
| "learning_rate": 1.687481602845872e-05, |
| "loss": 1.441333293914795, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.5689450809956539, |
| "grad_norm": 3.045902729034424, |
| "learning_rate": 1.6800119233094093e-05, |
| "loss": 1.4491585731506347, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5689450809956539, |
| "eval_loss": 1.4535424709320068, |
| "eval_runtime": 1434.0825, |
| "eval_samples_per_second": 3.716, |
| "eval_steps_per_second": 1.858, |
| "step": 900 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 3164, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.005 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 3 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.183432293135155e+18, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
