| { | |
| "best_metric": 70.793, | |
| "best_model_checkpoint": "flan-t5-xl-spider-dict_qpl-20240304-v3/checkpoint-91770", | |
| "epoch": 14.0, | |
| "eval_steps": 500, | |
| "global_step": 91770, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 2.1395843029022217, | |
| "learning_rate": 0.0001989829646580219, | |
| "loss": 1.1111, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 1.5051442384719849, | |
| "learning_rate": 0.00019796592931604375, | |
| "loss": 0.2196, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 1.0700268745422363, | |
| "learning_rate": 0.00019694889397406563, | |
| "loss": 0.1653, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.6627328395843506, | |
| "learning_rate": 0.00019593185863208746, | |
| "loss": 0.1313, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.8090806603431702, | |
| "learning_rate": 0.00019491482329010934, | |
| "loss": 0.1141, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.5775860548019409, | |
| "learning_rate": 0.0001938977879481312, | |
| "loss": 0.1071, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.548545777797699, | |
| "learning_rate": 0.00019288075260615308, | |
| "loss": 0.0963, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.8567075729370117, | |
| "learning_rate": 0.00019186371726417494, | |
| "loss": 0.0852, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.2921431064605713, | |
| "learning_rate": 0.00019084668192219682, | |
| "loss": 0.0787, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.1600842922925949, | |
| "learning_rate": 0.00018982964658021868, | |
| "loss": 0.0789, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.48446208238601685, | |
| "learning_rate": 0.00018881261123824053, | |
| "loss": 0.0732, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.5679713487625122, | |
| "learning_rate": 0.0001877955758962624, | |
| "loss": 0.0699, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 1.3154789209365845, | |
| "learning_rate": 0.00018677854055428427, | |
| "loss": 0.068, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_execution_accuracy": 39.4584, | |
| "eval_loss": 0.0767175704240799, | |
| "eval_runtime": 1448.6397, | |
| "eval_samples_per_second": 0.714, | |
| "eval_steps_per_second": 0.09, | |
| "step": 6555 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 0.3169132173061371, | |
| "learning_rate": 0.00018576150521230613, | |
| "loss": 0.0608, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 0.5822262763977051, | |
| "learning_rate": 0.000184744469870328, | |
| "loss": 0.0594, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 0.39004069566726685, | |
| "learning_rate": 0.00018372743452834986, | |
| "loss": 0.0601, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 0.48953133821487427, | |
| "learning_rate": 0.00018271039918637175, | |
| "loss": 0.0563, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 0.24563811719417572, | |
| "learning_rate": 0.0001816933638443936, | |
| "loss": 0.0547, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 0.028272481635212898, | |
| "learning_rate": 0.00018067632850241546, | |
| "loss": 0.0513, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 0.5085881948471069, | |
| "learning_rate": 0.00017965929316043731, | |
| "loss": 0.054, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.3579294681549072, | |
| "learning_rate": 0.0001786422578184592, | |
| "loss": 0.0523, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 0.717029869556427, | |
| "learning_rate": 0.00017762522247648105, | |
| "loss": 0.048, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.5166067481040955, | |
| "learning_rate": 0.00017660818713450294, | |
| "loss": 0.0494, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 0.7487884759902954, | |
| "learning_rate": 0.0001755911517925248, | |
| "loss": 0.0444, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 0.24778613448143005, | |
| "learning_rate": 0.00017457411645054667, | |
| "loss": 0.0427, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 0.3205878436565399, | |
| "learning_rate": 0.00017355708110856853, | |
| "loss": 0.0432, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_execution_accuracy": 52.9981, | |
| "eval_loss": 0.06084170565009117, | |
| "eval_runtime": 1830.3328, | |
| "eval_samples_per_second": 0.565, | |
| "eval_steps_per_second": 0.071, | |
| "step": 13110 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 0.424517959356308, | |
| "learning_rate": 0.00017254004576659039, | |
| "loss": 0.0422, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 0.5932648777961731, | |
| "learning_rate": 0.00017152301042461227, | |
| "loss": 0.0447, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "grad_norm": 0.1377120316028595, | |
| "learning_rate": 0.00017050597508263412, | |
| "loss": 0.0399, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "grad_norm": 0.257429301738739, | |
| "learning_rate": 0.000169488939740656, | |
| "loss": 0.0361, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 0.18395432829856873, | |
| "learning_rate": 0.00016847190439867786, | |
| "loss": 0.038, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 0.526056706905365, | |
| "learning_rate": 0.00016745486905669975, | |
| "loss": 0.0343, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 0.17391307651996613, | |
| "learning_rate": 0.0001664378337147216, | |
| "loss": 0.0357, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "grad_norm": 0.2732052505016327, | |
| "learning_rate": 0.00016542079837274346, | |
| "loss": 0.0366, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "grad_norm": 0.3006477355957031, | |
| "learning_rate": 0.0001644037630307653, | |
| "loss": 0.033, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 0.011468607001006603, | |
| "learning_rate": 0.0001633867276887872, | |
| "loss": 0.0335, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "grad_norm": 0.5990091562271118, | |
| "learning_rate": 0.00016236969234680905, | |
| "loss": 0.0355, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 0.29567310214042664, | |
| "learning_rate": 0.00016135265700483093, | |
| "loss": 0.0337, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "grad_norm": 0.006056224461644888, | |
| "learning_rate": 0.0001603356216628528, | |
| "loss": 0.033, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_execution_accuracy": 60.3482, | |
| "eval_loss": 0.06122712045907974, | |
| "eval_runtime": 1764.8897, | |
| "eval_samples_per_second": 0.586, | |
| "eval_steps_per_second": 0.074, | |
| "step": 19665 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "grad_norm": 0.30340930819511414, | |
| "learning_rate": 0.00015931858632087467, | |
| "loss": 0.0297, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "grad_norm": 0.017457757145166397, | |
| "learning_rate": 0.00015830155097889653, | |
| "loss": 0.0305, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.254963755607605, | |
| "learning_rate": 0.00015728451563691838, | |
| "loss": 0.028, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "grad_norm": 0.8444741368293762, | |
| "learning_rate": 0.00015626748029494024, | |
| "loss": 0.027, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "grad_norm": 0.47470298409461975, | |
| "learning_rate": 0.00015525044495296212, | |
| "loss": 0.0297, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "grad_norm": 0.08465476334095001, | |
| "learning_rate": 0.00015423340961098398, | |
| "loss": 0.0288, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "grad_norm": 0.32479336857795715, | |
| "learning_rate": 0.00015321637426900586, | |
| "loss": 0.0302, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "grad_norm": 3.906116008758545, | |
| "learning_rate": 0.00015219933892702772, | |
| "loss": 0.0297, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "grad_norm": 0.821506917476654, | |
| "learning_rate": 0.0001511823035850496, | |
| "loss": 0.0266, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "grad_norm": 0.36568546295166016, | |
| "learning_rate": 0.00015016526824307146, | |
| "loss": 0.0296, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "grad_norm": 0.6190164089202881, | |
| "learning_rate": 0.0001491482329010933, | |
| "loss": 0.0287, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "grad_norm": 0.2852056920528412, | |
| "learning_rate": 0.00014813119755911517, | |
| "loss": 0.0271, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "grad_norm": 0.10050356388092041, | |
| "learning_rate": 0.00014711416221713705, | |
| "loss": 0.0297, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_execution_accuracy": 62.8627, | |
| "eval_loss": 0.0589316301047802, | |
| "eval_runtime": 1802.5956, | |
| "eval_samples_per_second": 0.574, | |
| "eval_steps_per_second": 0.072, | |
| "step": 26220 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "grad_norm": 0.4248579740524292, | |
| "learning_rate": 0.00014609712687515893, | |
| "loss": 0.027, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "grad_norm": 0.5822145342826843, | |
| "learning_rate": 0.0001450800915331808, | |
| "loss": 0.0234, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "grad_norm": 0.028582902625203133, | |
| "learning_rate": 0.00014406305619120267, | |
| "loss": 0.0256, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "grad_norm": 0.026179086416959763, | |
| "learning_rate": 0.00014304602084922453, | |
| "loss": 0.0248, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "grad_norm": 0.24167686700820923, | |
| "learning_rate": 0.00014202898550724638, | |
| "loss": 0.024, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "grad_norm": 0.21196796000003815, | |
| "learning_rate": 0.00014101195016526824, | |
| "loss": 0.0232, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 0.1384715437889099, | |
| "learning_rate": 0.00013999491482329012, | |
| "loss": 0.0231, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "grad_norm": 0.25323405861854553, | |
| "learning_rate": 0.00013897787948131198, | |
| "loss": 0.0227, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "grad_norm": 0.17340293526649475, | |
| "learning_rate": 0.00013796084413933386, | |
| "loss": 0.0232, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "grad_norm": 0.01007129717618227, | |
| "learning_rate": 0.00013694380879735572, | |
| "loss": 0.0212, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "grad_norm": 0.5236365795135498, | |
| "learning_rate": 0.0001359267734553776, | |
| "loss": 0.0233, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "grad_norm": 0.49340179562568665, | |
| "learning_rate": 0.00013490973811339945, | |
| "loss": 0.0258, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "grad_norm": 0.7839340567588806, | |
| "learning_rate": 0.0001338927027714213, | |
| "loss": 0.0213, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_execution_accuracy": 64.1199, | |
| "eval_loss": 0.06054983288049698, | |
| "eval_runtime": 1797.3766, | |
| "eval_samples_per_second": 0.575, | |
| "eval_steps_per_second": 0.072, | |
| "step": 32775 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "grad_norm": 0.47601643204689026, | |
| "learning_rate": 0.00013287566742944317, | |
| "loss": 0.0198, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "grad_norm": 0.3969705402851105, | |
| "learning_rate": 0.00013185863208746505, | |
| "loss": 0.0201, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "grad_norm": 0.06148134917020798, | |
| "learning_rate": 0.0001308415967454869, | |
| "loss": 0.021, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "grad_norm": 0.0021157702431082726, | |
| "learning_rate": 0.0001298245614035088, | |
| "loss": 0.0189, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "grad_norm": 0.09957286715507507, | |
| "learning_rate": 0.00012880752606153064, | |
| "loss": 0.0214, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "grad_norm": 0.0950658768415451, | |
| "learning_rate": 0.00012779049071955253, | |
| "loss": 0.0206, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "grad_norm": 0.5534018874168396, | |
| "learning_rate": 0.00012677345537757438, | |
| "loss": 0.0182, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "grad_norm": 0.21119213104248047, | |
| "learning_rate": 0.00012575642003559624, | |
| "loss": 0.0195, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "grad_norm": 0.10089027881622314, | |
| "learning_rate": 0.0001247393846936181, | |
| "loss": 0.0196, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "grad_norm": 0.36528435349464417, | |
| "learning_rate": 0.00012372234935163998, | |
| "loss": 0.0187, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "grad_norm": 0.13980288803577423, | |
| "learning_rate": 0.00012270531400966183, | |
| "loss": 0.0177, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "grad_norm": 0.03852877765893936, | |
| "learning_rate": 0.00012168827866768371, | |
| "loss": 0.0219, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "grad_norm": 0.23849190771579742, | |
| "learning_rate": 0.00012067124332570557, | |
| "loss": 0.0188, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_execution_accuracy": 64.3133, | |
| "eval_loss": 0.061897873878479004, | |
| "eval_runtime": 1866.1394, | |
| "eval_samples_per_second": 0.554, | |
| "eval_steps_per_second": 0.07, | |
| "step": 39330 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "grad_norm": 0.6830750703811646, | |
| "learning_rate": 0.00011965420798372744, | |
| "loss": 0.0175, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "grad_norm": 0.013556591235101223, | |
| "learning_rate": 0.00011863717264174932, | |
| "loss": 0.0166, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "grad_norm": 0.06067229434847832, | |
| "learning_rate": 0.00011762013729977118, | |
| "loss": 0.0167, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "grad_norm": 0.815282940864563, | |
| "learning_rate": 0.00011660310195779305, | |
| "loss": 0.0179, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "grad_norm": 0.09995106607675552, | |
| "learning_rate": 0.0001155860666158149, | |
| "loss": 0.0164, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 6.41, | |
| "grad_norm": 0.07753593474626541, | |
| "learning_rate": 0.00011456903127383679, | |
| "loss": 0.0162, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "grad_norm": 0.16108450293540955, | |
| "learning_rate": 0.00011355199593185864, | |
| "loss": 0.0176, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "grad_norm": 0.1027306616306305, | |
| "learning_rate": 0.00011253496058988051, | |
| "loss": 0.0176, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "grad_norm": 0.527164876461029, | |
| "learning_rate": 0.00011151792524790237, | |
| "loss": 0.0148, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 6.71, | |
| "grad_norm": 0.12876121699810028, | |
| "learning_rate": 0.00011050088990592425, | |
| "loss": 0.016, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "grad_norm": 0.07147472351789474, | |
| "learning_rate": 0.00010948385456394609, | |
| "loss": 0.0166, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "grad_norm": 0.11269113421440125, | |
| "learning_rate": 0.00010846681922196797, | |
| "loss": 0.0159, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "grad_norm": 0.0018060138681903481, | |
| "learning_rate": 0.00010744978387998983, | |
| "loss": 0.0166, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_execution_accuracy": 66.441, | |
| "eval_loss": 0.06106872484087944, | |
| "eval_runtime": 1845.4627, | |
| "eval_samples_per_second": 0.56, | |
| "eval_steps_per_second": 0.07, | |
| "step": 45885 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "grad_norm": 0.010804968886077404, | |
| "learning_rate": 0.00010643274853801171, | |
| "loss": 0.0148, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "grad_norm": 0.014622188173234463, | |
| "learning_rate": 0.00010541571319603355, | |
| "loss": 0.0147, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "grad_norm": 0.13804876804351807, | |
| "learning_rate": 0.00010439867785405544, | |
| "loss": 0.015, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "grad_norm": 0.0409139022231102, | |
| "learning_rate": 0.00010338164251207729, | |
| "loss": 0.0126, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "grad_norm": 0.11225342750549316, | |
| "learning_rate": 0.00010236460717009918, | |
| "loss": 0.014, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "grad_norm": 0.021166274324059486, | |
| "learning_rate": 0.00010134757182812102, | |
| "loss": 0.0146, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "grad_norm": 0.2523152828216553, | |
| "learning_rate": 0.0001003305364861429, | |
| "loss": 0.014, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 7.55, | |
| "grad_norm": 0.014010763727128506, | |
| "learning_rate": 9.931350114416477e-05, | |
| "loss": 0.0142, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "grad_norm": 0.3102033734321594, | |
| "learning_rate": 9.829646580218663e-05, | |
| "loss": 0.0131, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "grad_norm": 0.00048806238919496536, | |
| "learning_rate": 9.72794304602085e-05, | |
| "loss": 0.014, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 7.78, | |
| "grad_norm": 1.1056194305419922, | |
| "learning_rate": 9.626239511823036e-05, | |
| "loss": 0.0122, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "grad_norm": 0.07580041885375977, | |
| "learning_rate": 9.524535977625223e-05, | |
| "loss": 0.0118, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 7.93, | |
| "grad_norm": 0.06150615215301514, | |
| "learning_rate": 9.422832443427409e-05, | |
| "loss": 0.0162, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_execution_accuracy": 65.8607, | |
| "eval_loss": 0.0669085830450058, | |
| "eval_runtime": 1870.6797, | |
| "eval_samples_per_second": 0.553, | |
| "eval_steps_per_second": 0.069, | |
| "step": 52440 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "grad_norm": 0.3560275733470917, | |
| "learning_rate": 9.321128909229596e-05, | |
| "loss": 0.0137, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "grad_norm": 0.0782669186592102, | |
| "learning_rate": 9.219425375031783e-05, | |
| "loss": 0.0114, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "grad_norm": 0.008491788990795612, | |
| "learning_rate": 9.11772184083397e-05, | |
| "loss": 0.0124, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "grad_norm": 0.1824067234992981, | |
| "learning_rate": 9.016018306636155e-05, | |
| "loss": 0.0122, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "grad_norm": 0.1216733381152153, | |
| "learning_rate": 8.914314772438342e-05, | |
| "loss": 0.0124, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "grad_norm": 0.4382436275482178, | |
| "learning_rate": 8.812611238240529e-05, | |
| "loss": 0.0115, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 8.47, | |
| "grad_norm": 0.35070136189460754, | |
| "learning_rate": 8.710907704042716e-05, | |
| "loss": 0.0111, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "grad_norm": 0.03633696213364601, | |
| "learning_rate": 8.609204169844902e-05, | |
| "loss": 0.0111, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "grad_norm": 0.05109800025820732, | |
| "learning_rate": 8.507500635647089e-05, | |
| "loss": 0.0129, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "grad_norm": 0.02394057996571064, | |
| "learning_rate": 8.405797101449276e-05, | |
| "loss": 0.012, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "grad_norm": 0.5572072863578796, | |
| "learning_rate": 8.304093567251462e-05, | |
| "loss": 0.0121, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "grad_norm": 0.10420696437358856, | |
| "learning_rate": 8.202390033053648e-05, | |
| "loss": 0.0113, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 8.92, | |
| "grad_norm": 0.14662973582744598, | |
| "learning_rate": 8.100686498855835e-05, | |
| "loss": 0.0109, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_execution_accuracy": 68.9555, | |
| "eval_loss": 0.06655910611152649, | |
| "eval_runtime": 1868.1909, | |
| "eval_samples_per_second": 0.553, | |
| "eval_steps_per_second": 0.07, | |
| "step": 58995 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.44341155886650085, | |
| "learning_rate": 7.998982964658023e-05, | |
| "loss": 0.0117, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "grad_norm": 0.07052640616893768, | |
| "learning_rate": 7.897279430460209e-05, | |
| "loss": 0.0109, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "grad_norm": 0.22480645775794983, | |
| "learning_rate": 7.795575896262396e-05, | |
| "loss": 0.0095, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "grad_norm": 0.3521146774291992, | |
| "learning_rate": 7.693872362064583e-05, | |
| "loss": 0.0105, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "grad_norm": 0.17205676436424255, | |
| "learning_rate": 7.59216882786677e-05, | |
| "loss": 0.0099, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "grad_norm": 0.018218664452433586, | |
| "learning_rate": 7.490465293668955e-05, | |
| "loss": 0.01, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 9.46, | |
| "grad_norm": 0.0007620451506227255, | |
| "learning_rate": 7.388761759471142e-05, | |
| "loss": 0.0097, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "grad_norm": 0.12471388280391693, | |
| "learning_rate": 7.287058225273329e-05, | |
| "loss": 0.0102, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 9.61, | |
| "grad_norm": 0.0011848780559375882, | |
| "learning_rate": 7.185354691075516e-05, | |
| "loss": 0.0093, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 9.69, | |
| "grad_norm": 0.32076504826545715, | |
| "learning_rate": 7.083651156877702e-05, | |
| "loss": 0.0096, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "grad_norm": 1.0963212251663208, | |
| "learning_rate": 6.981947622679888e-05, | |
| "loss": 0.0103, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 9.84, | |
| "grad_norm": 0.2559475004673004, | |
| "learning_rate": 6.880244088482075e-05, | |
| "loss": 0.011, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "grad_norm": 0.1217416375875473, | |
| "learning_rate": 6.778540554284262e-05, | |
| "loss": 0.0092, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "grad_norm": 0.004103431012481451, | |
| "learning_rate": 6.676837020086448e-05, | |
| "loss": 0.0101, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_execution_accuracy": 68.1818, | |
| "eval_loss": 0.07360666990280151, | |
| "eval_runtime": 1900.7634, | |
| "eval_samples_per_second": 0.544, | |
| "eval_steps_per_second": 0.068, | |
| "step": 65550 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "grad_norm": 0.13344629108905792, | |
| "learning_rate": 6.575133485888635e-05, | |
| "loss": 0.0092, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 10.14, | |
| "grad_norm": 0.0032061520032584667, | |
| "learning_rate": 6.473429951690822e-05, | |
| "loss": 0.0081, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "grad_norm": 0.21120476722717285, | |
| "learning_rate": 6.371726417493009e-05, | |
| "loss": 0.0086, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "grad_norm": 0.00848371535539627, | |
| "learning_rate": 6.270022883295194e-05, | |
| "loss": 0.0081, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "grad_norm": 0.0012110616080462933, | |
| "learning_rate": 6.168319349097381e-05, | |
| "loss": 0.0085, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "grad_norm": 0.05799203738570213, | |
| "learning_rate": 6.066615814899568e-05, | |
| "loss": 0.0078, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 10.53, | |
| "grad_norm": 0.03763442113995552, | |
| "learning_rate": 5.9649122807017544e-05, | |
| "loss": 0.008, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "grad_norm": 0.01833200454711914, | |
| "learning_rate": 5.8632087465039406e-05, | |
| "loss": 0.0089, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 10.68, | |
| "grad_norm": 0.27255308628082275, | |
| "learning_rate": 5.7615052123061275e-05, | |
| "loss": 0.0085, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 10.76, | |
| "grad_norm": 0.049906667321920395, | |
| "learning_rate": 5.659801678108314e-05, | |
| "loss": 0.0093, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "grad_norm": 0.49261561036109924, | |
| "learning_rate": 5.558098143910501e-05, | |
| "loss": 0.0099, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 10.91, | |
| "grad_norm": 0.010688086971640587, | |
| "learning_rate": 5.456394609712687e-05, | |
| "loss": 0.0092, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "grad_norm": 0.015557405538856983, | |
| "learning_rate": 5.354691075514875e-05, | |
| "loss": 0.0085, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_execution_accuracy": 68.0851, | |
| "eval_loss": 0.07639693468809128, | |
| "eval_runtime": 1996.6932, | |
| "eval_samples_per_second": 0.518, | |
| "eval_steps_per_second": 0.065, | |
| "step": 72105 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "grad_norm": 0.1298118531703949, | |
| "learning_rate": 5.2529875413170615e-05, | |
| "loss": 0.0078, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 11.14, | |
| "grad_norm": 0.08524327725172043, | |
| "learning_rate": 5.151284007119248e-05, | |
| "loss": 0.0085, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 11.21, | |
| "grad_norm": 0.1634071171283722, | |
| "learning_rate": 5.049580472921435e-05, | |
| "loss": 0.0071, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 11.29, | |
| "grad_norm": 0.0011399647919461131, | |
| "learning_rate": 4.947876938723621e-05, | |
| "loss": 0.0069, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "grad_norm": 0.010579722002148628, | |
| "learning_rate": 4.846173404525807e-05, | |
| "loss": 0.0072, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 11.44, | |
| "grad_norm": 0.014801290817558765, | |
| "learning_rate": 4.744469870327994e-05, | |
| "loss": 0.0067, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "grad_norm": 0.0037248600274324417, | |
| "learning_rate": 4.642766336130181e-05, | |
| "loss": 0.0075, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 11.59, | |
| "grad_norm": 0.00024146214127540588, | |
| "learning_rate": 4.541062801932367e-05, | |
| "loss": 0.0065, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 11.67, | |
| "grad_norm": 0.013673787005245686, | |
| "learning_rate": 4.439359267734554e-05, | |
| "loss": 0.0071, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "grad_norm": 0.4386146366596222, | |
| "learning_rate": 4.3376557335367405e-05, | |
| "loss": 0.0073, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 11.82, | |
| "grad_norm": 0.011454693973064423, | |
| "learning_rate": 4.2359521993389274e-05, | |
| "loss": 0.0071, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "grad_norm": 0.2784646451473236, | |
| "learning_rate": 4.1342486651411136e-05, | |
| "loss": 0.0084, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "grad_norm": 0.1163712665438652, | |
| "learning_rate": 4.0325451309433006e-05, | |
| "loss": 0.0069, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_execution_accuracy": 69.0522, | |
| "eval_loss": 0.08005601912736893, | |
| "eval_runtime": 1886.3805, | |
| "eval_samples_per_second": 0.548, | |
| "eval_steps_per_second": 0.069, | |
| "step": 78660 | |
| }, | |
| { | |
| "epoch": 12.05, | |
| "grad_norm": 0.41248416900634766, | |
| "learning_rate": 3.930841596745487e-05, | |
| "loss": 0.007, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "grad_norm": 0.38738590478897095, | |
| "learning_rate": 3.829138062547674e-05, | |
| "loss": 0.0069, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "grad_norm": 0.24087974429130554, | |
| "learning_rate": 3.72743452834986e-05, | |
| "loss": 0.0057, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 12.28, | |
| "grad_norm": 0.18917705118656158, | |
| "learning_rate": 3.625730994152047e-05, | |
| "loss": 0.0065, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 12.36, | |
| "grad_norm": 0.05060713738203049, | |
| "learning_rate": 3.524027459954233e-05, | |
| "loss": 0.0054, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 12.43, | |
| "grad_norm": 0.07384895533323288, | |
| "learning_rate": 3.422323925756421e-05, | |
| "loss": 0.0063, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 12.51, | |
| "grad_norm": 0.22887946665287018, | |
| "learning_rate": 3.320620391558607e-05, | |
| "loss": 0.0057, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 12.59, | |
| "grad_norm": 0.2123759686946869, | |
| "learning_rate": 3.218916857360794e-05, | |
| "loss": 0.0074, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 12.66, | |
| "grad_norm": 0.09510879218578339, | |
| "learning_rate": 3.11721332316298e-05, | |
| "loss": 0.0056, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 12.74, | |
| "grad_norm": 0.00010326172196073458, | |
| "learning_rate": 3.0155097889651668e-05, | |
| "loss": 0.0058, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "grad_norm": 0.37206101417541504, | |
| "learning_rate": 2.9138062547673534e-05, | |
| "loss": 0.0059, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "grad_norm": 0.10882502794265747, | |
| "learning_rate": 2.81210272056954e-05, | |
| "loss": 0.0053, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "grad_norm": 0.010751358233392239, | |
| "learning_rate": 2.7103991863717266e-05, | |
| "loss": 0.0068, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_execution_accuracy": 69.2456, | |
| "eval_loss": 0.0884392261505127, | |
| "eval_runtime": 1938.7518, | |
| "eval_samples_per_second": 0.533, | |
| "eval_steps_per_second": 0.067, | |
| "step": 85215 | |
| }, | |
| { | |
| "epoch": 13.04, | |
| "grad_norm": 0.10975372046232224, | |
| "learning_rate": 2.608695652173913e-05, | |
| "loss": 0.0057, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "grad_norm": 0.0004275761893950403, | |
| "learning_rate": 2.5069921179760997e-05, | |
| "loss": 0.0048, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "grad_norm": 0.3996267020702362, | |
| "learning_rate": 2.4052885837782867e-05, | |
| "loss": 0.0051, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "grad_norm": 0.00662227114662528, | |
| "learning_rate": 2.3035850495804733e-05, | |
| "loss": 0.0062, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 13.35, | |
| "grad_norm": 0.09702113270759583, | |
| "learning_rate": 2.20188151538266e-05, | |
| "loss": 0.0051, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "grad_norm": 0.0026878053322434425, | |
| "learning_rate": 2.100177981184846e-05, | |
| "loss": 0.0063, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "grad_norm": 0.05382531136274338, | |
| "learning_rate": 1.9984744469870327e-05, | |
| "loss": 0.0042, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 13.58, | |
| "grad_norm": 0.770341157913208, | |
| "learning_rate": 1.8967709127892193e-05, | |
| "loss": 0.0052, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 13.65, | |
| "grad_norm": 0.00518847955390811, | |
| "learning_rate": 1.795067378591406e-05, | |
| "loss": 0.0052, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "grad_norm": 0.0707794651389122, | |
| "learning_rate": 1.6933638443935928e-05, | |
| "loss": 0.0053, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "grad_norm": 0.5020930767059326, | |
| "learning_rate": 1.5916603101957794e-05, | |
| "loss": 0.0057, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "grad_norm": 0.11777380853891373, | |
| "learning_rate": 1.489956775997966e-05, | |
| "loss": 0.0056, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "grad_norm": 0.0008695057476870716, | |
| "learning_rate": 1.3882532418001526e-05, | |
| "loss": 0.0052, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_execution_accuracy": 70.793, | |
| "eval_loss": 0.08826606720685959, | |
| "eval_runtime": 1858.3154, | |
| "eval_samples_per_second": 0.556, | |
| "eval_steps_per_second": 0.07, | |
| "step": 91770 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 98325, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "total_flos": 8.553259153863475e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |