| { | |
| "best_metric": 1.3783499002456665, | |
| "best_model_checkpoint": "../checkpoints/sft/checkpoint-2000", | |
| "epoch": 1.8601767167880947, | |
| "eval_steps": 500, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01550147263990079, | |
| "grad_norm": 0.0904994085431099, | |
| "learning_rate": 4.9741602067183466e-05, | |
| "loss": 2.0913, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03100294527980158, | |
| "grad_norm": 0.09595159441232681, | |
| "learning_rate": 4.948320413436693e-05, | |
| "loss": 1.9736, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04650441791970237, | |
| "grad_norm": 0.09749136120080948, | |
| "learning_rate": 4.922480620155039e-05, | |
| "loss": 1.9502, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06200589055960316, | |
| "grad_norm": 0.08286518603563309, | |
| "learning_rate": 4.8966408268733855e-05, | |
| "loss": 1.9324, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07750736319950395, | |
| "grad_norm": 0.10390572249889374, | |
| "learning_rate": 4.870801033591731e-05, | |
| "loss": 1.9413, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.09300883583940474, | |
| "grad_norm": 0.08579128980636597, | |
| "learning_rate": 4.8449612403100775e-05, | |
| "loss": 1.9437, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10851030847930554, | |
| "grad_norm": 0.11584578454494476, | |
| "learning_rate": 4.819121447028424e-05, | |
| "loss": 1.939, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.12401178111920633, | |
| "grad_norm": 0.1426805555820465, | |
| "learning_rate": 4.79328165374677e-05, | |
| "loss": 1.9428, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.13951325375910711, | |
| "grad_norm": 0.08612250536680222, | |
| "learning_rate": 4.7674418604651164e-05, | |
| "loss": 1.9212, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1550147263990079, | |
| "grad_norm": 0.08324660360813141, | |
| "learning_rate": 4.741602067183463e-05, | |
| "loss": 1.9186, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1550147263990079, | |
| "eval_loss": 1.3784544467926025, | |
| "eval_runtime": 10.968, | |
| "eval_samples_per_second": 32.458, | |
| "eval_steps_per_second": 4.103, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1705161990389087, | |
| "grad_norm": 0.09479448199272156, | |
| "learning_rate": 4.715762273901809e-05, | |
| "loss": 1.9346, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.18601767167880948, | |
| "grad_norm": 0.10014442354440689, | |
| "learning_rate": 4.6899224806201553e-05, | |
| "loss": 1.9093, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.20151914431871026, | |
| "grad_norm": 0.08976327627897263, | |
| "learning_rate": 4.664082687338501e-05, | |
| "loss": 1.935, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.21702061695861108, | |
| "grad_norm": 0.10600723326206207, | |
| "learning_rate": 4.638242894056848e-05, | |
| "loss": 1.9172, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.23252208959851187, | |
| "grad_norm": 0.18757325410842896, | |
| "learning_rate": 4.6124031007751936e-05, | |
| "loss": 1.9177, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.24802356223841265, | |
| "grad_norm": 0.10721405595541, | |
| "learning_rate": 4.5865633074935406e-05, | |
| "loss": 1.9098, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.2635250348783134, | |
| "grad_norm": 0.09476891160011292, | |
| "learning_rate": 4.560723514211886e-05, | |
| "loss": 1.9307, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.27902650751821423, | |
| "grad_norm": 0.09466688334941864, | |
| "learning_rate": 4.5348837209302326e-05, | |
| "loss": 1.9178, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.29452798015811504, | |
| "grad_norm": 0.09889288246631622, | |
| "learning_rate": 4.509043927648579e-05, | |
| "loss": 1.9244, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.3100294527980158, | |
| "grad_norm": 0.14233581721782684, | |
| "learning_rate": 4.483204134366925e-05, | |
| "loss": 1.9153, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3100294527980158, | |
| "eval_loss": 1.411450982093811, | |
| "eval_runtime": 10.6228, | |
| "eval_samples_per_second": 33.513, | |
| "eval_steps_per_second": 4.236, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3255309254379166, | |
| "grad_norm": 0.08776664733886719, | |
| "learning_rate": 4.4573643410852715e-05, | |
| "loss": 1.9278, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.3410323980778174, | |
| "grad_norm": 0.09803825616836548, | |
| "learning_rate": 4.431524547803618e-05, | |
| "loss": 1.9199, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.3565338707177182, | |
| "grad_norm": 0.13931065797805786, | |
| "learning_rate": 4.405684754521964e-05, | |
| "loss": 1.9225, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.37203534335761895, | |
| "grad_norm": 0.09357253462076187, | |
| "learning_rate": 4.3798449612403104e-05, | |
| "loss": 1.9317, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.38753681599751977, | |
| "grad_norm": 0.10508549958467484, | |
| "learning_rate": 4.354005167958656e-05, | |
| "loss": 1.9255, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.4030382886374205, | |
| "grad_norm": 0.10250881314277649, | |
| "learning_rate": 4.328165374677003e-05, | |
| "loss": 1.9137, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.41853976127732134, | |
| "grad_norm": 0.10409200936555862, | |
| "learning_rate": 4.302325581395349e-05, | |
| "loss": 1.8974, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.43404123391722216, | |
| "grad_norm": 0.09141243994235992, | |
| "learning_rate": 4.276485788113696e-05, | |
| "loss": 1.9103, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.4495427065571229, | |
| "grad_norm": 0.09040896594524384, | |
| "learning_rate": 4.2506459948320413e-05, | |
| "loss": 1.9057, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.46504417919702373, | |
| "grad_norm": 0.09726119041442871, | |
| "learning_rate": 4.2248062015503877e-05, | |
| "loss": 1.9014, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.46504417919702373, | |
| "eval_loss": 1.3864915370941162, | |
| "eval_runtime": 10.6078, | |
| "eval_samples_per_second": 33.56, | |
| "eval_steps_per_second": 4.242, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4805456518369245, | |
| "grad_norm": 0.11088709533214569, | |
| "learning_rate": 4.198966408268734e-05, | |
| "loss": 1.9152, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.4960471244768253, | |
| "grad_norm": 0.11300063878297806, | |
| "learning_rate": 4.17312661498708e-05, | |
| "loss": 1.9168, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.5115485971167261, | |
| "grad_norm": 0.10414065420627594, | |
| "learning_rate": 4.1472868217054266e-05, | |
| "loss": 1.9172, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.5270500697566268, | |
| "grad_norm": 0.09191906452178955, | |
| "learning_rate": 4.121447028423773e-05, | |
| "loss": 1.8968, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5425515423965277, | |
| "grad_norm": 0.10366778820753098, | |
| "learning_rate": 4.095607235142119e-05, | |
| "loss": 1.8976, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.5580530150364285, | |
| "grad_norm": 0.09124482423067093, | |
| "learning_rate": 4.0697674418604655e-05, | |
| "loss": 1.8896, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5735544876763292, | |
| "grad_norm": 0.10119319707155228, | |
| "learning_rate": 4.043927648578811e-05, | |
| "loss": 1.8881, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.5890559603162301, | |
| "grad_norm": 0.1147024929523468, | |
| "learning_rate": 4.018087855297158e-05, | |
| "loss": 1.9097, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.6045574329561308, | |
| "grad_norm": 0.09813511371612549, | |
| "learning_rate": 3.992248062015504e-05, | |
| "loss": 1.908, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.6200589055960316, | |
| "grad_norm": 0.10509663820266724, | |
| "learning_rate": 3.966408268733851e-05, | |
| "loss": 1.9018, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.6200589055960316, | |
| "eval_loss": 1.3783499002456665, | |
| "eval_runtime": 10.6185, | |
| "eval_samples_per_second": 33.526, | |
| "eval_steps_per_second": 4.238, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.6355603782359324, | |
| "grad_norm": 0.1106325089931488, | |
| "learning_rate": 3.9405684754521964e-05, | |
| "loss": 1.8955, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.6510618508758332, | |
| "grad_norm": 0.09004335105419159, | |
| "learning_rate": 3.914728682170543e-05, | |
| "loss": 1.881, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.666563323515734, | |
| "grad_norm": 0.10601779073476791, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 1.8996, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.6820647961556348, | |
| "grad_norm": 0.09966927021741867, | |
| "learning_rate": 3.8630490956072354e-05, | |
| "loss": 1.8806, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6975662687955356, | |
| "grad_norm": 0.10469923913478851, | |
| "learning_rate": 3.837209302325582e-05, | |
| "loss": 1.8948, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.7130677414354364, | |
| "grad_norm": 0.10708159953355789, | |
| "learning_rate": 3.811369509043928e-05, | |
| "loss": 1.8917, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.7285692140753371, | |
| "grad_norm": 0.09772736579179764, | |
| "learning_rate": 3.785529715762274e-05, | |
| "loss": 1.9049, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.7440706867152379, | |
| "grad_norm": 0.10732176899909973, | |
| "learning_rate": 3.7596899224806207e-05, | |
| "loss": 1.911, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.7595721593551388, | |
| "grad_norm": 0.10482428967952728, | |
| "learning_rate": 3.733850129198966e-05, | |
| "loss": 1.8946, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.7750736319950395, | |
| "grad_norm": 0.10157684981822968, | |
| "learning_rate": 3.708010335917313e-05, | |
| "loss": 1.8859, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7750736319950395, | |
| "eval_loss": 1.3911091089248657, | |
| "eval_runtime": 10.6093, | |
| "eval_samples_per_second": 33.555, | |
| "eval_steps_per_second": 4.242, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7905751046349403, | |
| "grad_norm": 0.10432788729667664, | |
| "learning_rate": 3.682170542635659e-05, | |
| "loss": 1.894, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.806076577274841, | |
| "grad_norm": 0.10409342497587204, | |
| "learning_rate": 3.656330749354005e-05, | |
| "loss": 1.8882, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.8215780499147419, | |
| "grad_norm": 0.11120035499334335, | |
| "learning_rate": 3.6304909560723515e-05, | |
| "loss": 1.8827, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.8370795225546427, | |
| "grad_norm": 0.11159931123256683, | |
| "learning_rate": 3.604651162790698e-05, | |
| "loss": 1.8902, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.8525809951945434, | |
| "grad_norm": 0.09784770011901855, | |
| "learning_rate": 3.578811369509044e-05, | |
| "loss": 1.8881, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.8680824678344443, | |
| "grad_norm": 0.09907621890306473, | |
| "learning_rate": 3.5529715762273905e-05, | |
| "loss": 1.9006, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.8835839404743451, | |
| "grad_norm": 0.10387194156646729, | |
| "learning_rate": 3.527131782945737e-05, | |
| "loss": 1.9085, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.8990854131142458, | |
| "grad_norm": 0.09763891249895096, | |
| "learning_rate": 3.5012919896640824e-05, | |
| "loss": 1.8904, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.9145868857541466, | |
| "grad_norm": 0.10186181217432022, | |
| "learning_rate": 3.4754521963824294e-05, | |
| "loss": 1.8732, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.9300883583940475, | |
| "grad_norm": 0.11027953773736954, | |
| "learning_rate": 3.449612403100775e-05, | |
| "loss": 1.8886, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.9300883583940475, | |
| "eval_loss": 1.4133652448654175, | |
| "eval_runtime": 10.6201, | |
| "eval_samples_per_second": 33.521, | |
| "eval_steps_per_second": 4.237, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.9455898310339482, | |
| "grad_norm": 0.1076328456401825, | |
| "learning_rate": 3.4237726098191214e-05, | |
| "loss": 1.9007, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.961091303673849, | |
| "grad_norm": 0.10457822680473328, | |
| "learning_rate": 3.397932816537468e-05, | |
| "loss": 1.8894, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.9765927763137499, | |
| "grad_norm": 0.1240358054637909, | |
| "learning_rate": 3.372093023255814e-05, | |
| "loss": 1.8962, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.9920942489536506, | |
| "grad_norm": 0.1087583601474762, | |
| "learning_rate": 3.34625322997416e-05, | |
| "loss": 1.8849, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.0075957215935514, | |
| "grad_norm": 0.10473156720399857, | |
| "learning_rate": 3.3204134366925067e-05, | |
| "loss": 1.8825, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.0230971942334521, | |
| "grad_norm": 0.11174094676971436, | |
| "learning_rate": 3.294573643410852e-05, | |
| "loss": 1.8804, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.038598666873353, | |
| "grad_norm": 0.10820575803518295, | |
| "learning_rate": 3.268733850129199e-05, | |
| "loss": 1.874, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.0541001395132537, | |
| "grad_norm": 0.11375240236520767, | |
| "learning_rate": 3.242894056847545e-05, | |
| "loss": 1.892, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.0696016121531546, | |
| "grad_norm": 0.10983241349458694, | |
| "learning_rate": 3.217054263565892e-05, | |
| "loss": 1.8864, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.0851030847930554, | |
| "grad_norm": 0.11412903666496277, | |
| "learning_rate": 3.1912144702842375e-05, | |
| "loss": 1.8841, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0851030847930554, | |
| "eval_loss": 1.409255862236023, | |
| "eval_runtime": 10.6154, | |
| "eval_samples_per_second": 33.536, | |
| "eval_steps_per_second": 4.239, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.1006045574329562, | |
| "grad_norm": 0.11279023438692093, | |
| "learning_rate": 3.1653746770025845e-05, | |
| "loss": 1.8809, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.116106030072857, | |
| "grad_norm": 0.12842436134815216, | |
| "learning_rate": 3.13953488372093e-05, | |
| "loss": 1.8822, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.1316075027127577, | |
| "grad_norm": 0.11607849597930908, | |
| "learning_rate": 3.1136950904392765e-05, | |
| "loss": 1.8677, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.1471089753526584, | |
| "grad_norm": 0.11454817652702332, | |
| "learning_rate": 3.087855297157623e-05, | |
| "loss": 1.8785, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.1626104479925594, | |
| "grad_norm": 0.12619228661060333, | |
| "learning_rate": 3.062015503875969e-05, | |
| "loss": 1.8735, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.1781119206324602, | |
| "grad_norm": 0.12233872711658478, | |
| "learning_rate": 3.0361757105943154e-05, | |
| "loss": 1.8625, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.193613393272361, | |
| "grad_norm": 0.1316874474287033, | |
| "learning_rate": 3.0103359173126618e-05, | |
| "loss": 1.8775, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.2091148659122617, | |
| "grad_norm": 0.12887555360794067, | |
| "learning_rate": 2.9844961240310077e-05, | |
| "loss": 1.8868, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.2246163385521625, | |
| "grad_norm": 0.11875531822443008, | |
| "learning_rate": 2.9586563307493544e-05, | |
| "loss": 1.8645, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.2401178111920632, | |
| "grad_norm": 0.11634934693574905, | |
| "learning_rate": 2.9328165374677004e-05, | |
| "loss": 1.8803, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.2401178111920632, | |
| "eval_loss": 1.4193403720855713, | |
| "eval_runtime": 10.6141, | |
| "eval_samples_per_second": 33.54, | |
| "eval_steps_per_second": 4.24, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.255619283831964, | |
| "grad_norm": 0.12749060988426208, | |
| "learning_rate": 2.9069767441860467e-05, | |
| "loss": 1.8699, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.271120756471865, | |
| "grad_norm": 0.12758812308311462, | |
| "learning_rate": 2.881136950904393e-05, | |
| "loss": 1.8624, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.2866222291117655, | |
| "grad_norm": 0.11913730949163437, | |
| "learning_rate": 2.8552971576227393e-05, | |
| "loss": 1.8731, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.3021237017516665, | |
| "grad_norm": 0.11662113666534424, | |
| "learning_rate": 2.8294573643410853e-05, | |
| "loss": 1.8936, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.3176251743915672, | |
| "grad_norm": 0.13116636872291565, | |
| "learning_rate": 2.8036175710594316e-05, | |
| "loss": 1.8788, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.333126647031468, | |
| "grad_norm": 0.12884733080863953, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.8788, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.3486281196713688, | |
| "grad_norm": 0.12196724116802216, | |
| "learning_rate": 2.751937984496124e-05, | |
| "loss": 1.8689, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.3641295923112695, | |
| "grad_norm": 0.13119535148143768, | |
| "learning_rate": 2.7260981912144705e-05, | |
| "loss": 1.8702, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.3796310649511705, | |
| "grad_norm": 0.12181399017572403, | |
| "learning_rate": 2.7002583979328165e-05, | |
| "loss": 1.8708, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.395132537591071, | |
| "grad_norm": 0.1291220635175705, | |
| "learning_rate": 2.674418604651163e-05, | |
| "loss": 1.8509, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.395132537591071, | |
| "eval_loss": 1.4268625974655151, | |
| "eval_runtime": 10.6177, | |
| "eval_samples_per_second": 33.529, | |
| "eval_steps_per_second": 4.238, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.410634010230972, | |
| "grad_norm": 0.1215544119477272, | |
| "learning_rate": 2.648578811369509e-05, | |
| "loss": 1.868, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 1.4261354828708728, | |
| "grad_norm": 0.12441984564065933, | |
| "learning_rate": 2.622739018087855e-05, | |
| "loss": 1.8624, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.4416369555107735, | |
| "grad_norm": 0.12983018159866333, | |
| "learning_rate": 2.5968992248062018e-05, | |
| "loss": 1.875, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.4571384281506743, | |
| "grad_norm": 0.14041350781917572, | |
| "learning_rate": 2.5710594315245478e-05, | |
| "loss": 1.8634, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.472639900790575, | |
| "grad_norm": 0.1323089897632599, | |
| "learning_rate": 2.5452196382428944e-05, | |
| "loss": 1.8701, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 1.488141373430476, | |
| "grad_norm": 0.13671238720417023, | |
| "learning_rate": 2.5193798449612404e-05, | |
| "loss": 1.8722, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.5036428460703766, | |
| "grad_norm": 0.12991730868816376, | |
| "learning_rate": 2.4935400516795867e-05, | |
| "loss": 1.8548, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 1.5191443187102776, | |
| "grad_norm": 0.12073440849781036, | |
| "learning_rate": 2.467700258397933e-05, | |
| "loss": 1.8817, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.5346457913501783, | |
| "grad_norm": 0.1927834451198578, | |
| "learning_rate": 2.441860465116279e-05, | |
| "loss": 1.8624, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.550147263990079, | |
| "grad_norm": 0.1434555947780609, | |
| "learning_rate": 2.4160206718346253e-05, | |
| "loss": 1.8571, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.550147263990079, | |
| "eval_loss": 1.4204214811325073, | |
| "eval_runtime": 10.6279, | |
| "eval_samples_per_second": 33.497, | |
| "eval_steps_per_second": 4.234, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.5656487366299798, | |
| "grad_norm": 0.1407179832458496, | |
| "learning_rate": 2.3901808785529716e-05, | |
| "loss": 1.8693, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 1.5811502092698806, | |
| "grad_norm": 0.13802586495876312, | |
| "learning_rate": 2.364341085271318e-05, | |
| "loss": 1.8653, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.5966516819097816, | |
| "grad_norm": 0.13259877264499664, | |
| "learning_rate": 2.3385012919896642e-05, | |
| "loss": 1.85, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 1.612153154549682, | |
| "grad_norm": 0.14958499372005463, | |
| "learning_rate": 2.3131782945736435e-05, | |
| "loss": 1.8707, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.627654627189583, | |
| "grad_norm": 0.13671304285526276, | |
| "learning_rate": 2.2873385012919898e-05, | |
| "loss": 1.8642, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 1.6431560998294839, | |
| "grad_norm": 0.12920096516609192, | |
| "learning_rate": 2.261498708010336e-05, | |
| "loss": 1.856, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.6586575724693846, | |
| "grad_norm": 0.1263495683670044, | |
| "learning_rate": 2.235658914728682e-05, | |
| "loss": 1.8639, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 1.6741590451092854, | |
| "grad_norm": 0.1388077437877655, | |
| "learning_rate": 2.2098191214470284e-05, | |
| "loss": 1.8662, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.6896605177491861, | |
| "grad_norm": 0.13600564002990723, | |
| "learning_rate": 2.1839793281653747e-05, | |
| "loss": 1.8667, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 1.7051619903890871, | |
| "grad_norm": 0.1285238116979599, | |
| "learning_rate": 2.158139534883721e-05, | |
| "loss": 1.8691, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.7051619903890871, | |
| "eval_loss": 1.4164341688156128, | |
| "eval_runtime": 10.618, | |
| "eval_samples_per_second": 33.528, | |
| "eval_steps_per_second": 4.238, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.7206634630289876, | |
| "grad_norm": 0.14896276593208313, | |
| "learning_rate": 2.1322997416020673e-05, | |
| "loss": 1.8526, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 1.7361649356688886, | |
| "grad_norm": 0.13365153968334198, | |
| "learning_rate": 2.1064599483204136e-05, | |
| "loss": 1.8592, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.7516664083087892, | |
| "grad_norm": 0.1381397843360901, | |
| "learning_rate": 2.0806201550387596e-05, | |
| "loss": 1.8563, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 1.7671678809486902, | |
| "grad_norm": 0.14912950992584229, | |
| "learning_rate": 2.054780361757106e-05, | |
| "loss": 1.8562, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.782669353588591, | |
| "grad_norm": 0.13218577206134796, | |
| "learning_rate": 2.0289405684754523e-05, | |
| "loss": 1.8617, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 1.7981708262284917, | |
| "grad_norm": 0.13850583136081696, | |
| "learning_rate": 2.0031007751937986e-05, | |
| "loss": 1.8563, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.8136722988683927, | |
| "grad_norm": 0.13015194237232208, | |
| "learning_rate": 1.977260981912145e-05, | |
| "loss": 1.8473, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 1.8291737715082932, | |
| "grad_norm": 0.13473467528820038, | |
| "learning_rate": 1.9514211886304912e-05, | |
| "loss": 1.8549, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.8446752441481942, | |
| "grad_norm": 0.13621702790260315, | |
| "learning_rate": 1.9255813953488372e-05, | |
| "loss": 1.8565, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 1.8601767167880947, | |
| "grad_norm": 0.1430806815624237, | |
| "learning_rate": 1.8997416020671835e-05, | |
| "loss": 1.8533, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.8601767167880947, | |
| "eval_loss": 1.4264311790466309, | |
| "eval_runtime": 10.6098, | |
| "eval_samples_per_second": 33.554, | |
| "eval_steps_per_second": 4.241, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 9675, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.108324190905172e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |