| { | |
| "best_metric": 0.011031342670321465, | |
| "best_model_checkpoint": "autotrain-mb2mv-qdf75/checkpoint-3839", | |
| "epoch": 11.0, | |
| "eval_steps": 500, | |
| "global_step": 3839, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04871060171919771, | |
| "grad_norm": 12.027495384216309, | |
| "learning_rate": 2.028639618138425e-06, | |
| "loss": 4.4947, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09742120343839542, | |
| "grad_norm": 11.511441230773926, | |
| "learning_rate": 4.05727923627685e-06, | |
| "loss": 4.4912, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14613180515759314, | |
| "grad_norm": 12.500868797302246, | |
| "learning_rate": 5.966587112171838e-06, | |
| "loss": 4.4842, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.19484240687679083, | |
| "grad_norm": 11.219860076904297, | |
| "learning_rate": 7.995226730310263e-06, | |
| "loss": 4.4186, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.24355300859598855, | |
| "grad_norm": 11.510499000549316, | |
| "learning_rate": 1.0023866348448688e-05, | |
| "loss": 4.5182, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2922636103151863, | |
| "grad_norm": 12.528426170349121, | |
| "learning_rate": 1.2052505966587113e-05, | |
| "loss": 4.4535, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.34097421203438394, | |
| "grad_norm": 11.191871643066406, | |
| "learning_rate": 1.4081145584725539e-05, | |
| "loss": 4.4233, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.38968481375358166, | |
| "grad_norm": 13.019774436950684, | |
| "learning_rate": 1.6109785202863962e-05, | |
| "loss": 4.3845, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.4383954154727794, | |
| "grad_norm": 11.506011962890625, | |
| "learning_rate": 1.8138424821002386e-05, | |
| "loss": 4.3334, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.4871060171919771, | |
| "grad_norm": 11.238750457763672, | |
| "learning_rate": 2.0167064439140813e-05, | |
| "loss": 4.2554, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5358166189111748, | |
| "grad_norm": 11.771519660949707, | |
| "learning_rate": 2.2195704057279237e-05, | |
| "loss": 4.2028, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.5845272206303725, | |
| "grad_norm": 12.988870620727539, | |
| "learning_rate": 2.4224343675417664e-05, | |
| "loss": 4.0815, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.6332378223495702, | |
| "grad_norm": 12.157154083251953, | |
| "learning_rate": 2.6252983293556088e-05, | |
| "loss": 4.1055, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.6819484240687679, | |
| "grad_norm": 12.214086532592773, | |
| "learning_rate": 2.828162291169451e-05, | |
| "loss": 3.9383, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.7306590257879656, | |
| "grad_norm": 11.511253356933594, | |
| "learning_rate": 3.031026252983294e-05, | |
| "loss": 3.9894, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.7793696275071633, | |
| "grad_norm": 13.291036605834961, | |
| "learning_rate": 3.233890214797136e-05, | |
| "loss": 3.7944, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.828080229226361, | |
| "grad_norm": 13.204787254333496, | |
| "learning_rate": 3.424821002386635e-05, | |
| "loss": 3.7806, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.8767908309455588, | |
| "grad_norm": 13.473506927490234, | |
| "learning_rate": 3.627684964200477e-05, | |
| "loss": 3.6716, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.9255014326647565, | |
| "grad_norm": 12.780734062194824, | |
| "learning_rate": 3.83054892601432e-05, | |
| "loss": 3.4641, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.9742120343839542, | |
| "grad_norm": 20.36208724975586, | |
| "learning_rate": 4.0334128878281626e-05, | |
| "loss": 3.3018, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.43902439024390244, | |
| "eval_f1_macro": 0.3762682151157721, | |
| "eval_f1_micro": 0.43902439024390244, | |
| "eval_f1_weighted": 0.38500671624754507, | |
| "eval_loss": 2.9648730754852295, | |
| "eval_precision_macro": 0.5231114557498497, | |
| "eval_precision_micro": 0.43902439024390244, | |
| "eval_precision_weighted": 0.5343145132587477, | |
| "eval_recall_macro": 0.41928580121351205, | |
| "eval_recall_micro": 0.43902439024390244, | |
| "eval_recall_weighted": 0.43902439024390244, | |
| "eval_runtime": 3.4206, | |
| "eval_samples_per_second": 203.767, | |
| "eval_steps_per_second": 12.863, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 1.0229226361031518, | |
| "grad_norm": 11.021674156188965, | |
| "learning_rate": 4.236276849642005e-05, | |
| "loss": 3.1839, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 1.0716332378223496, | |
| "grad_norm": 12.111454963684082, | |
| "learning_rate": 4.4391408114558474e-05, | |
| "loss": 3.0222, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 1.1203438395415473, | |
| "grad_norm": 12.602492332458496, | |
| "learning_rate": 4.64200477326969e-05, | |
| "loss": 2.8135, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 1.1690544412607449, | |
| "grad_norm": 11.924349784851074, | |
| "learning_rate": 4.844868735083533e-05, | |
| "loss": 2.6733, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 1.2177650429799427, | |
| "grad_norm": 11.714224815368652, | |
| "learning_rate": 4.9946935526664904e-05, | |
| "loss": 2.4497, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.2664756446991405, | |
| "grad_norm": 13.355523109436035, | |
| "learning_rate": 4.972141151499072e-05, | |
| "loss": 2.3633, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.3151862464183381, | |
| "grad_norm": 11.773361206054688, | |
| "learning_rate": 4.949588750331653e-05, | |
| "loss": 2.2063, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 1.3638968481375358, | |
| "grad_norm": 12.601265907287598, | |
| "learning_rate": 4.9270363491642345e-05, | |
| "loss": 2.2622, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 1.4126074498567336, | |
| "grad_norm": 11.489968299865723, | |
| "learning_rate": 4.9044839479968165e-05, | |
| "loss": 2.0349, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 1.4613180515759312, | |
| "grad_norm": 11.553853034973145, | |
| "learning_rate": 4.881931546829398e-05, | |
| "loss": 1.8452, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.5100286532951288, | |
| "grad_norm": 13.461709976196289, | |
| "learning_rate": 4.85937914566198e-05, | |
| "loss": 1.7711, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.5587392550143266, | |
| "grad_norm": 11.289037704467773, | |
| "learning_rate": 4.8368267444945606e-05, | |
| "loss": 1.562, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 1.6074498567335245, | |
| "grad_norm": 9.85034465789795, | |
| "learning_rate": 4.814274343327143e-05, | |
| "loss": 1.4258, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 1.656160458452722, | |
| "grad_norm": 8.626704216003418, | |
| "learning_rate": 4.791721942159724e-05, | |
| "loss": 1.2561, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 1.7048710601719197, | |
| "grad_norm": 8.728435516357422, | |
| "learning_rate": 4.769169540992306e-05, | |
| "loss": 1.229, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 1.7535816618911175, | |
| "grad_norm": 11.541463851928711, | |
| "learning_rate": 4.7466171398248875e-05, | |
| "loss": 1.175, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 1.8022922636103151, | |
| "grad_norm": 11.69316291809082, | |
| "learning_rate": 4.724064738657469e-05, | |
| "loss": 1.2961, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 1.8510028653295127, | |
| "grad_norm": 7.8675737380981445, | |
| "learning_rate": 4.70151233749005e-05, | |
| "loss": 0.9699, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 1.8997134670487106, | |
| "grad_norm": 7.240268230438232, | |
| "learning_rate": 4.678959936322632e-05, | |
| "loss": 1.235, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 1.9484240687679084, | |
| "grad_norm": 6.3042426109313965, | |
| "learning_rate": 4.6564075351552136e-05, | |
| "loss": 1.1121, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.997134670487106, | |
| "grad_norm": 8.941567420959473, | |
| "learning_rate": 4.633855133987796e-05, | |
| "loss": 0.9363, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.945480631276901, | |
| "eval_f1_macro": 0.9425017115213628, | |
| "eval_f1_micro": 0.945480631276901, | |
| "eval_f1_weighted": 0.9445694655877982, | |
| "eval_loss": 0.5551677346229553, | |
| "eval_precision_macro": 0.9567204214794576, | |
| "eval_precision_micro": 0.945480631276901, | |
| "eval_precision_weighted": 0.9597403513113699, | |
| "eval_recall_macro": 0.94451833307255, | |
| "eval_recall_micro": 0.945480631276901, | |
| "eval_recall_weighted": 0.945480631276901, | |
| "eval_runtime": 3.3936, | |
| "eval_samples_per_second": 205.389, | |
| "eval_steps_per_second": 12.966, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 2.0458452722063036, | |
| "grad_norm": 4.50822114944458, | |
| "learning_rate": 4.611302732820377e-05, | |
| "loss": 1.0456, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 2.0945558739255015, | |
| "grad_norm": 5.0435686111450195, | |
| "learning_rate": 4.5887503316529584e-05, | |
| "loss": 0.5131, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 2.1432664756446993, | |
| "grad_norm": 5.728665351867676, | |
| "learning_rate": 4.5661979304855405e-05, | |
| "loss": 0.705, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 2.1919770773638967, | |
| "grad_norm": 4.446041584014893, | |
| "learning_rate": 4.543645529318122e-05, | |
| "loss": 0.6504, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 2.2406876790830945, | |
| "grad_norm": 5.601328372955322, | |
| "learning_rate": 4.521093128150703e-05, | |
| "loss": 0.6361, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 2.2893982808022924, | |
| "grad_norm": 6.830723285675049, | |
| "learning_rate": 4.4985407269832846e-05, | |
| "loss": 0.7554, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 2.3381088825214897, | |
| "grad_norm": 9.851592063903809, | |
| "learning_rate": 4.4759883258158666e-05, | |
| "loss": 0.6952, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 2.3868194842406876, | |
| "grad_norm": 12.239367485046387, | |
| "learning_rate": 4.453435924648448e-05, | |
| "loss": 0.7793, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 2.4355300859598854, | |
| "grad_norm": 4.4265360832214355, | |
| "learning_rate": 4.43088352348103e-05, | |
| "loss": 0.5841, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.4842406876790832, | |
| "grad_norm": 11.818037986755371, | |
| "learning_rate": 4.4083311223136114e-05, | |
| "loss": 0.6259, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 2.532951289398281, | |
| "grad_norm": 13.520539283752441, | |
| "learning_rate": 4.385778721146193e-05, | |
| "loss": 0.674, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 2.5816618911174785, | |
| "grad_norm": 12.981139183044434, | |
| "learning_rate": 4.363226319978774e-05, | |
| "loss": 0.7362, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 2.6303724928366763, | |
| "grad_norm": 12.412555694580078, | |
| "learning_rate": 4.340673918811356e-05, | |
| "loss": 0.557, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 2.6790830945558737, | |
| "grad_norm": 7.840790748596191, | |
| "learning_rate": 4.3181215176439375e-05, | |
| "loss": 0.6293, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 2.7277936962750715, | |
| "grad_norm": 4.981259822845459, | |
| "learning_rate": 4.2955691164765196e-05, | |
| "loss": 0.5793, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 2.7765042979942693, | |
| "grad_norm": 7.165767669677734, | |
| "learning_rate": 4.2730167153091e-05, | |
| "loss": 0.5705, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 2.825214899713467, | |
| "grad_norm": 6.7298736572265625, | |
| "learning_rate": 4.250464314141682e-05, | |
| "loss": 0.5446, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 2.873925501432665, | |
| "grad_norm": 7.268840789794922, | |
| "learning_rate": 4.227911912974264e-05, | |
| "loss": 0.4438, | |
| "step": 1003 | |
| }, | |
| { | |
| "epoch": 2.9226361031518624, | |
| "grad_norm": 1.802043080329895, | |
| "learning_rate": 4.205359511806846e-05, | |
| "loss": 0.4892, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.9713467048710602, | |
| "grad_norm": 10.247010231018066, | |
| "learning_rate": 4.182807110639427e-05, | |
| "loss": 0.4922, | |
| "step": 1037 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9727403156384505, | |
| "eval_f1_macro": 0.9705769072502259, | |
| "eval_f1_micro": 0.9727403156384505, | |
| "eval_f1_weighted": 0.9719785983620151, | |
| "eval_loss": 0.17863501608371735, | |
| "eval_precision_macro": 0.9795910916392845, | |
| "eval_precision_micro": 0.9727403156384505, | |
| "eval_precision_weighted": 0.9787328087184615, | |
| "eval_recall_macro": 0.969774335436986, | |
| "eval_recall_micro": 0.9727403156384505, | |
| "eval_recall_weighted": 0.9727403156384505, | |
| "eval_runtime": 3.4979, | |
| "eval_samples_per_second": 199.263, | |
| "eval_steps_per_second": 12.579, | |
| "step": 1047 | |
| }, | |
| { | |
| "epoch": 3.020057306590258, | |
| "grad_norm": 9.481998443603516, | |
| "learning_rate": 4.1602547094720085e-05, | |
| "loss": 0.5422, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 3.0687679083094554, | |
| "grad_norm": 9.671106338500977, | |
| "learning_rate": 4.13770230830459e-05, | |
| "loss": 0.408, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 3.1174785100286533, | |
| "grad_norm": 1.3068506717681885, | |
| "learning_rate": 4.115149907137172e-05, | |
| "loss": 0.404, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 3.166189111747851, | |
| "grad_norm": 8.020153045654297, | |
| "learning_rate": 4.092597505969753e-05, | |
| "loss": 0.4022, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 3.2148997134670485, | |
| "grad_norm": 9.03290843963623, | |
| "learning_rate": 4.070045104802335e-05, | |
| "loss": 0.4726, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 3.2636103151862463, | |
| "grad_norm": 8.347646713256836, | |
| "learning_rate": 4.047492703634917e-05, | |
| "loss": 0.4158, | |
| "step": 1139 | |
| }, | |
| { | |
| "epoch": 3.312320916905444, | |
| "grad_norm": 9.76726245880127, | |
| "learning_rate": 4.024940302467498e-05, | |
| "loss": 0.3523, | |
| "step": 1156 | |
| }, | |
| { | |
| "epoch": 3.361031518624642, | |
| "grad_norm": 8.464173316955566, | |
| "learning_rate": 4.00238790130008e-05, | |
| "loss": 0.5155, | |
| "step": 1173 | |
| }, | |
| { | |
| "epoch": 3.4097421203438394, | |
| "grad_norm": 4.331398963928223, | |
| "learning_rate": 3.9798355001326615e-05, | |
| "loss": 0.395, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.458452722063037, | |
| "grad_norm": 7.228985786437988, | |
| "learning_rate": 3.9572830989652435e-05, | |
| "loss": 0.3984, | |
| "step": 1207 | |
| }, | |
| { | |
| "epoch": 3.507163323782235, | |
| "grad_norm": 10.442928314208984, | |
| "learning_rate": 3.934730697797824e-05, | |
| "loss": 0.4143, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 3.555873925501433, | |
| "grad_norm": 8.429516792297363, | |
| "learning_rate": 3.912178296630406e-05, | |
| "loss": 0.3767, | |
| "step": 1241 | |
| }, | |
| { | |
| "epoch": 3.6045845272206303, | |
| "grad_norm": 12.501051902770996, | |
| "learning_rate": 3.8896258954629876e-05, | |
| "loss": 0.3507, | |
| "step": 1258 | |
| }, | |
| { | |
| "epoch": 3.653295128939828, | |
| "grad_norm": 7.7675652503967285, | |
| "learning_rate": 3.86707349429557e-05, | |
| "loss": 0.395, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 3.702005730659026, | |
| "grad_norm": 4.184613227844238, | |
| "learning_rate": 3.844521093128151e-05, | |
| "loss": 0.2874, | |
| "step": 1292 | |
| }, | |
| { | |
| "epoch": 3.7507163323782233, | |
| "grad_norm": 10.189749717712402, | |
| "learning_rate": 3.8219686919607324e-05, | |
| "loss": 0.3396, | |
| "step": 1309 | |
| }, | |
| { | |
| "epoch": 3.799426934097421, | |
| "grad_norm": 2.022300958633423, | |
| "learning_rate": 3.799416290793314e-05, | |
| "loss": 0.2436, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 3.848137535816619, | |
| "grad_norm": 8.71822452545166, | |
| "learning_rate": 3.776863889625896e-05, | |
| "loss": 0.3773, | |
| "step": 1343 | |
| }, | |
| { | |
| "epoch": 3.896848137535817, | |
| "grad_norm": 7.879873752593994, | |
| "learning_rate": 3.754311488458477e-05, | |
| "loss": 0.4686, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.945558739255014, | |
| "grad_norm": 1.0487672090530396, | |
| "learning_rate": 3.731759087291059e-05, | |
| "loss": 0.3921, | |
| "step": 1377 | |
| }, | |
| { | |
| "epoch": 3.994269340974212, | |
| "grad_norm": 8.260384559631348, | |
| "learning_rate": 3.70920668612364e-05, | |
| "loss": 0.2956, | |
| "step": 1394 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9885222381635581, | |
| "eval_f1_macro": 0.9872476382417075, | |
| "eval_f1_micro": 0.9885222381635581, | |
| "eval_f1_weighted": 0.9882948425801252, | |
| "eval_loss": 0.09004738181829453, | |
| "eval_precision_macro": 0.9903644882560545, | |
| "eval_precision_micro": 0.9885222381635581, | |
| "eval_precision_weighted": 0.9902174543135807, | |
| "eval_recall_macro": 0.9865557467967108, | |
| "eval_recall_micro": 0.9885222381635581, | |
| "eval_recall_weighted": 0.9885222381635581, | |
| "eval_runtime": 3.3411, | |
| "eval_samples_per_second": 208.616, | |
| "eval_steps_per_second": 13.169, | |
| "step": 1396 | |
| }, | |
| { | |
| "epoch": 4.042979942693409, | |
| "grad_norm": 6.5528106689453125, | |
| "learning_rate": 3.686654284956222e-05, | |
| "loss": 0.4403, | |
| "step": 1411 | |
| }, | |
| { | |
| "epoch": 4.091690544412607, | |
| "grad_norm": 3.8414504528045654, | |
| "learning_rate": 3.6641018837888034e-05, | |
| "loss": 0.2637, | |
| "step": 1428 | |
| }, | |
| { | |
| "epoch": 4.140401146131805, | |
| "grad_norm": 16.609180450439453, | |
| "learning_rate": 3.6415494826213854e-05, | |
| "loss": 0.3618, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 4.189111747851003, | |
| "grad_norm": 2.179348945617676, | |
| "learning_rate": 3.618997081453967e-05, | |
| "loss": 0.4447, | |
| "step": 1462 | |
| }, | |
| { | |
| "epoch": 4.237822349570201, | |
| "grad_norm": 3.5908546447753906, | |
| "learning_rate": 3.596444680286548e-05, | |
| "loss": 0.2905, | |
| "step": 1479 | |
| }, | |
| { | |
| "epoch": 4.286532951289399, | |
| "grad_norm": 7.550769805908203, | |
| "learning_rate": 3.5738922791191295e-05, | |
| "loss": 0.2448, | |
| "step": 1496 | |
| }, | |
| { | |
| "epoch": 4.3352435530085955, | |
| "grad_norm": 0.7109397649765015, | |
| "learning_rate": 3.5513398779517116e-05, | |
| "loss": 0.2127, | |
| "step": 1513 | |
| }, | |
| { | |
| "epoch": 4.383954154727793, | |
| "grad_norm": 1.54320228099823, | |
| "learning_rate": 3.528787476784293e-05, | |
| "loss": 0.2202, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 4.432664756446991, | |
| "grad_norm": 10.156286239624023, | |
| "learning_rate": 3.506235075616875e-05, | |
| "loss": 0.3263, | |
| "step": 1547 | |
| }, | |
| { | |
| "epoch": 4.481375358166189, | |
| "grad_norm": 11.149276733398438, | |
| "learning_rate": 3.4836826744494563e-05, | |
| "loss": 0.213, | |
| "step": 1564 | |
| }, | |
| { | |
| "epoch": 4.530085959885387, | |
| "grad_norm": 14.087788581848145, | |
| "learning_rate": 3.461130273282038e-05, | |
| "loss": 0.3907, | |
| "step": 1581 | |
| }, | |
| { | |
| "epoch": 4.578796561604585, | |
| "grad_norm": 6.006841659545898, | |
| "learning_rate": 3.43857787211462e-05, | |
| "loss": 0.4959, | |
| "step": 1598 | |
| }, | |
| { | |
| "epoch": 4.6275071633237825, | |
| "grad_norm": 6.818835258483887, | |
| "learning_rate": 3.416025470947201e-05, | |
| "loss": 0.3309, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 4.6762177650429795, | |
| "grad_norm": 1.0696688890457153, | |
| "learning_rate": 3.393473069779783e-05, | |
| "loss": 0.2245, | |
| "step": 1632 | |
| }, | |
| { | |
| "epoch": 4.724928366762177, | |
| "grad_norm": 11.383952140808105, | |
| "learning_rate": 3.370920668612364e-05, | |
| "loss": 0.3473, | |
| "step": 1649 | |
| }, | |
| { | |
| "epoch": 4.773638968481375, | |
| "grad_norm": 7.438843727111816, | |
| "learning_rate": 3.348368267444946e-05, | |
| "loss": 0.2508, | |
| "step": 1666 | |
| }, | |
| { | |
| "epoch": 4.822349570200573, | |
| "grad_norm": 1.553702473640442, | |
| "learning_rate": 3.325815866277527e-05, | |
| "loss": 0.2669, | |
| "step": 1683 | |
| }, | |
| { | |
| "epoch": 4.871060171919771, | |
| "grad_norm": 5.968568325042725, | |
| "learning_rate": 3.303263465110109e-05, | |
| "loss": 0.1219, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.919770773638969, | |
| "grad_norm": 0.3757087290287018, | |
| "learning_rate": 3.280711063942691e-05, | |
| "loss": 0.2749, | |
| "step": 1717 | |
| }, | |
| { | |
| "epoch": 4.9684813753581665, | |
| "grad_norm": 7.143729209899902, | |
| "learning_rate": 3.258158662775272e-05, | |
| "loss": 0.1591, | |
| "step": 1734 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9885222381635581, | |
| "eval_f1_macro": 0.9880046003912989, | |
| "eval_f1_micro": 0.9885222381635581, | |
| "eval_f1_weighted": 0.9883902987879117, | |
| "eval_loss": 0.05691728740930557, | |
| "eval_precision_macro": 0.9900693683826214, | |
| "eval_precision_micro": 0.9885222381635581, | |
| "eval_precision_weighted": 0.9900236221613553, | |
| "eval_recall_macro": 0.9879231210556513, | |
| "eval_recall_micro": 0.9885222381635581, | |
| "eval_recall_weighted": 0.9885222381635581, | |
| "eval_runtime": 3.3973, | |
| "eval_samples_per_second": 205.165, | |
| "eval_steps_per_second": 12.952, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 5.017191977077364, | |
| "grad_norm": 1.9127634763717651, | |
| "learning_rate": 3.2356062616078534e-05, | |
| "loss": 0.397, | |
| "step": 1751 | |
| }, | |
| { | |
| "epoch": 5.065902578796561, | |
| "grad_norm": 8.336675643920898, | |
| "learning_rate": 3.2130538604404355e-05, | |
| "loss": 0.2355, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 5.114613180515759, | |
| "grad_norm": 7.159496307373047, | |
| "learning_rate": 3.190501459273017e-05, | |
| "loss": 0.2086, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 5.163323782234957, | |
| "grad_norm": 6.03056526184082, | |
| "learning_rate": 3.167949058105599e-05, | |
| "loss": 0.2212, | |
| "step": 1802 | |
| }, | |
| { | |
| "epoch": 5.212034383954155, | |
| "grad_norm": 7.681415557861328, | |
| "learning_rate": 3.1453966569381796e-05, | |
| "loss": 0.2721, | |
| "step": 1819 | |
| }, | |
| { | |
| "epoch": 5.260744985673353, | |
| "grad_norm": 1.4911251068115234, | |
| "learning_rate": 3.1228442557707616e-05, | |
| "loss": 0.1994, | |
| "step": 1836 | |
| }, | |
| { | |
| "epoch": 5.30945558739255, | |
| "grad_norm": 7.99345588684082, | |
| "learning_rate": 3.100291854603343e-05, | |
| "loss": 0.312, | |
| "step": 1853 | |
| }, | |
| { | |
| "epoch": 5.358166189111748, | |
| "grad_norm": 3.288712978363037, | |
| "learning_rate": 3.077739453435925e-05, | |
| "loss": 0.3002, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 5.406876790830945, | |
| "grad_norm": 0.1384359449148178, | |
| "learning_rate": 3.0551870522685064e-05, | |
| "loss": 0.1875, | |
| "step": 1887 | |
| }, | |
| { | |
| "epoch": 5.455587392550143, | |
| "grad_norm": 2.912055730819702, | |
| "learning_rate": 3.0326346511010878e-05, | |
| "loss": 0.1617, | |
| "step": 1904 | |
| }, | |
| { | |
| "epoch": 5.504297994269341, | |
| "grad_norm": 9.510294914245605, | |
| "learning_rate": 3.0100822499336695e-05, | |
| "loss": 0.1553, | |
| "step": 1921 | |
| }, | |
| { | |
| "epoch": 5.553008595988539, | |
| "grad_norm": 5.520040988922119, | |
| "learning_rate": 2.9875298487662512e-05, | |
| "loss": 0.1949, | |
| "step": 1938 | |
| }, | |
| { | |
| "epoch": 5.6017191977077365, | |
| "grad_norm": 0.39325079321861267, | |
| "learning_rate": 2.964977447598833e-05, | |
| "loss": 0.2814, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 5.650429799426934, | |
| "grad_norm": 0.1934385895729065, | |
| "learning_rate": 2.942425046431414e-05, | |
| "loss": 0.3251, | |
| "step": 1972 | |
| }, | |
| { | |
| "epoch": 5.699140401146132, | |
| "grad_norm": 5.8890533447265625, | |
| "learning_rate": 2.9198726452639957e-05, | |
| "loss": 0.1652, | |
| "step": 1989 | |
| }, | |
| { | |
| "epoch": 5.747851002865329, | |
| "grad_norm": 5.028823375701904, | |
| "learning_rate": 2.8973202440965774e-05, | |
| "loss": 0.305, | |
| "step": 2006 | |
| }, | |
| { | |
| "epoch": 5.796561604584527, | |
| "grad_norm": 0.35111504793167114, | |
| "learning_rate": 2.874767842929159e-05, | |
| "loss": 0.1684, | |
| "step": 2023 | |
| }, | |
| { | |
| "epoch": 5.845272206303725, | |
| "grad_norm": 1.910530686378479, | |
| "learning_rate": 2.8522154417617408e-05, | |
| "loss": 0.2535, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 5.893982808022923, | |
| "grad_norm": 5.5074334144592285, | |
| "learning_rate": 2.8296630405943218e-05, | |
| "loss": 0.2924, | |
| "step": 2057 | |
| }, | |
| { | |
| "epoch": 5.9426934097421205, | |
| "grad_norm": 6.081971645355225, | |
| "learning_rate": 2.8071106394269035e-05, | |
| "loss": 0.1663, | |
| "step": 2074 | |
| }, | |
| { | |
| "epoch": 5.991404011461318, | |
| "grad_norm": 1.7783217430114746, | |
| "learning_rate": 2.7845582382594852e-05, | |
| "loss": 0.1912, | |
| "step": 2091 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9971305595408895, | |
| "eval_f1_macro": 0.997156659844563, | |
| "eval_f1_micro": 0.9971305595408895, | |
| "eval_f1_weighted": 0.9971139798573604, | |
| "eval_loss": 0.031095275655388832, | |
| "eval_precision_macro": 0.9975660216624072, | |
| "eval_precision_micro": 0.9971305595408895, | |
| "eval_precision_weighted": 0.9974204020115067, | |
| "eval_recall_macro": 0.9970740103270225, | |
| "eval_recall_micro": 0.9971305595408895, | |
| "eval_recall_weighted": 0.9971305595408895, | |
| "eval_runtime": 3.3447, | |
| "eval_samples_per_second": 208.387, | |
| "eval_steps_per_second": 13.155, | |
| "step": 2094 | |
| }, | |
| { | |
| "epoch": 6.040114613180516, | |
| "grad_norm": 12.544295310974121, | |
| "learning_rate": 2.762005837092067e-05, | |
| "loss": 0.2401, | |
| "step": 2108 | |
| }, | |
| { | |
| "epoch": 6.088825214899713, | |
| "grad_norm": 0.36089888215065, | |
| "learning_rate": 2.7394534359246486e-05, | |
| "loss": 0.1197, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 6.137535816618911, | |
| "grad_norm": 3.824916124343872, | |
| "learning_rate": 2.71690103475723e-05, | |
| "loss": 0.2304, | |
| "step": 2142 | |
| }, | |
| { | |
| "epoch": 6.186246418338109, | |
| "grad_norm": 7.010196685791016, | |
| "learning_rate": 2.6943486335898117e-05, | |
| "loss": 0.2393, | |
| "step": 2159 | |
| }, | |
| { | |
| "epoch": 6.234957020057307, | |
| "grad_norm": 0.23738817870616913, | |
| "learning_rate": 2.6717962324223934e-05, | |
| "loss": 0.2878, | |
| "step": 2176 | |
| }, | |
| { | |
| "epoch": 6.283667621776504, | |
| "grad_norm": 6.685153961181641, | |
| "learning_rate": 2.649243831254975e-05, | |
| "loss": 0.23, | |
| "step": 2193 | |
| }, | |
| { | |
| "epoch": 6.332378223495702, | |
| "grad_norm": 9.155635833740234, | |
| "learning_rate": 2.626691430087557e-05, | |
| "loss": 0.127, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 6.3810888252149, | |
| "grad_norm": 1.8248714208602905, | |
| "learning_rate": 2.604139028920138e-05, | |
| "loss": 0.264, | |
| "step": 2227 | |
| }, | |
| { | |
| "epoch": 6.429799426934097, | |
| "grad_norm": 3.287179946899414, | |
| "learning_rate": 2.5815866277527196e-05, | |
| "loss": 0.2568, | |
| "step": 2244 | |
| }, | |
| { | |
| "epoch": 6.478510028653295, | |
| "grad_norm": 0.12249535322189331, | |
| "learning_rate": 2.5590342265853013e-05, | |
| "loss": 0.1211, | |
| "step": 2261 | |
| }, | |
| { | |
| "epoch": 6.527220630372493, | |
| "grad_norm": 9.649252891540527, | |
| "learning_rate": 2.536481825417883e-05, | |
| "loss": 0.2599, | |
| "step": 2278 | |
| }, | |
| { | |
| "epoch": 6.5759312320916905, | |
| "grad_norm": 8.501516342163086, | |
| "learning_rate": 2.5139294242504647e-05, | |
| "loss": 0.1997, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 6.624641833810888, | |
| "grad_norm": 6.785931587219238, | |
| "learning_rate": 2.491377023083046e-05, | |
| "loss": 0.1947, | |
| "step": 2312 | |
| }, | |
| { | |
| "epoch": 6.673352435530086, | |
| "grad_norm": 1.3328988552093506, | |
| "learning_rate": 2.4688246219156274e-05, | |
| "loss": 0.2236, | |
| "step": 2329 | |
| }, | |
| { | |
| "epoch": 6.722063037249284, | |
| "grad_norm": 9.384140014648438, | |
| "learning_rate": 2.446272220748209e-05, | |
| "loss": 0.2394, | |
| "step": 2346 | |
| }, | |
| { | |
| "epoch": 6.770773638968482, | |
| "grad_norm": 1.0058611631393433, | |
| "learning_rate": 2.423719819580791e-05, | |
| "loss": 0.1288, | |
| "step": 2363 | |
| }, | |
| { | |
| "epoch": 6.819484240687679, | |
| "grad_norm": 0.7905517816543579, | |
| "learning_rate": 2.4011674184133722e-05, | |
| "loss": 0.1528, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 6.868194842406877, | |
| "grad_norm": 10.827178955078125, | |
| "learning_rate": 2.378615017245954e-05, | |
| "loss": 0.1767, | |
| "step": 2397 | |
| }, | |
| { | |
| "epoch": 6.916905444126074, | |
| "grad_norm": 7.897141933441162, | |
| "learning_rate": 2.3560626160785353e-05, | |
| "loss": 0.1411, | |
| "step": 2414 | |
| }, | |
| { | |
| "epoch": 6.965616045845272, | |
| "grad_norm": 4.635827541351318, | |
| "learning_rate": 2.333510214911117e-05, | |
| "loss": 0.1712, | |
| "step": 2431 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9956958393113343, | |
| "eval_f1_macro": 0.9951431111442676, | |
| "eval_f1_micro": 0.9956958393113343, | |
| "eval_f1_weighted": 0.9956405011600654, | |
| "eval_loss": 0.024958999827504158, | |
| "eval_precision_macro": 0.995983935742972, | |
| "eval_precision_micro": 0.9956958393113343, | |
| "eval_precision_weighted": 0.9964929061055317, | |
| "eval_recall_macro": 0.9953528399311532, | |
| "eval_recall_micro": 0.9956958393113343, | |
| "eval_recall_weighted": 0.9956958393113343, | |
| "eval_runtime": 3.4628, | |
| "eval_samples_per_second": 201.281, | |
| "eval_steps_per_second": 12.706, | |
| "step": 2443 | |
| }, | |
| { | |
| "epoch": 7.01432664756447, | |
| "grad_norm": 0.12232652306556702, | |
| "learning_rate": 2.3109578137436987e-05, | |
| "loss": 0.2055, | |
| "step": 2448 | |
| }, | |
| { | |
| "epoch": 7.063037249283668, | |
| "grad_norm": 0.07312128692865372, | |
| "learning_rate": 2.28840541257628e-05, | |
| "loss": 0.1848, | |
| "step": 2465 | |
| }, | |
| { | |
| "epoch": 7.111747851002866, | |
| "grad_norm": 0.32181409001350403, | |
| "learning_rate": 2.2658530114088618e-05, | |
| "loss": 0.1364, | |
| "step": 2482 | |
| }, | |
| { | |
| "epoch": 7.160458452722063, | |
| "grad_norm": 0.7672788500785828, | |
| "learning_rate": 2.2433006102414432e-05, | |
| "loss": 0.072, | |
| "step": 2499 | |
| }, | |
| { | |
| "epoch": 7.2091690544412605, | |
| "grad_norm": 8.377331733703613, | |
| "learning_rate": 2.220748209074025e-05, | |
| "loss": 0.2638, | |
| "step": 2516 | |
| }, | |
| { | |
| "epoch": 7.257879656160458, | |
| "grad_norm": 9.670488357543945, | |
| "learning_rate": 2.1981958079066066e-05, | |
| "loss": 0.2495, | |
| "step": 2533 | |
| }, | |
| { | |
| "epoch": 7.306590257879656, | |
| "grad_norm": 0.24363534152507782, | |
| "learning_rate": 2.1756434067391883e-05, | |
| "loss": 0.2038, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 7.355300859598854, | |
| "grad_norm": 2.2357654571533203, | |
| "learning_rate": 2.15309100557177e-05, | |
| "loss": 0.2934, | |
| "step": 2567 | |
| }, | |
| { | |
| "epoch": 7.404011461318052, | |
| "grad_norm": 0.20546384155750275, | |
| "learning_rate": 2.1305386044043514e-05, | |
| "loss": 0.1834, | |
| "step": 2584 | |
| }, | |
| { | |
| "epoch": 7.45272206303725, | |
| "grad_norm": 0.32598844170570374, | |
| "learning_rate": 2.107986203236933e-05, | |
| "loss": 0.0821, | |
| "step": 2601 | |
| }, | |
| { | |
| "epoch": 7.501432664756447, | |
| "grad_norm": 8.553650856018066, | |
| "learning_rate": 2.0854338020695148e-05, | |
| "loss": 0.0992, | |
| "step": 2618 | |
| }, | |
| { | |
| "epoch": 7.5501432664756445, | |
| "grad_norm": 0.3119734525680542, | |
| "learning_rate": 2.062881400902096e-05, | |
| "loss": 0.2344, | |
| "step": 2635 | |
| }, | |
| { | |
| "epoch": 7.598853868194842, | |
| "grad_norm": 6.1670002937316895, | |
| "learning_rate": 2.040328999734678e-05, | |
| "loss": 0.1058, | |
| "step": 2652 | |
| }, | |
| { | |
| "epoch": 7.64756446991404, | |
| "grad_norm": 2.705218553543091, | |
| "learning_rate": 2.0177765985672592e-05, | |
| "loss": 0.1608, | |
| "step": 2669 | |
| }, | |
| { | |
| "epoch": 7.696275071633238, | |
| "grad_norm": 5.938003063201904, | |
| "learning_rate": 1.995224197399841e-05, | |
| "loss": 0.1554, | |
| "step": 2686 | |
| }, | |
| { | |
| "epoch": 7.744985673352436, | |
| "grad_norm": 0.41698479652404785, | |
| "learning_rate": 1.9726717962324227e-05, | |
| "loss": 0.0979, | |
| "step": 2703 | |
| }, | |
| { | |
| "epoch": 7.793696275071634, | |
| "grad_norm": 0.4503624141216278, | |
| "learning_rate": 1.950119395065004e-05, | |
| "loss": 0.1353, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 7.842406876790831, | |
| "grad_norm": 4.662674427032471, | |
| "learning_rate": 1.9275669938975857e-05, | |
| "loss": 0.1295, | |
| "step": 2737 | |
| }, | |
| { | |
| "epoch": 7.891117478510028, | |
| "grad_norm": 5.666357517242432, | |
| "learning_rate": 1.905014592730167e-05, | |
| "loss": 0.2144, | |
| "step": 2754 | |
| }, | |
| { | |
| "epoch": 7.939828080229226, | |
| "grad_norm": 0.6394052505493164, | |
| "learning_rate": 1.8824621915627488e-05, | |
| "loss": 0.178, | |
| "step": 2771 | |
| }, | |
| { | |
| "epoch": 7.988538681948424, | |
| "grad_norm": 9.961098670959473, | |
| "learning_rate": 1.8599097903953305e-05, | |
| "loss": 0.2561, | |
| "step": 2788 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9956958393113343, | |
| "eval_f1_macro": 0.9951431111442676, | |
| "eval_f1_micro": 0.9956958393113343, | |
| "eval_f1_weighted": 0.9956405011600654, | |
| "eval_loss": 0.023447172716259956, | |
| "eval_precision_macro": 0.995983935742972, | |
| "eval_precision_micro": 0.9956958393113343, | |
| "eval_precision_weighted": 0.9964929061055317, | |
| "eval_recall_macro": 0.9953528399311532, | |
| "eval_recall_micro": 0.9956958393113343, | |
| "eval_recall_weighted": 0.9956958393113343, | |
| "eval_runtime": 3.3596, | |
| "eval_samples_per_second": 207.466, | |
| "eval_steps_per_second": 13.097, | |
| "step": 2792 | |
| }, | |
| { | |
| "epoch": 8.037249283667622, | |
| "grad_norm": 10.93313217163086, | |
| "learning_rate": 1.837357389227912e-05, | |
| "loss": 0.11, | |
| "step": 2805 | |
| }, | |
| { | |
| "epoch": 8.085959885386819, | |
| "grad_norm": 0.05085707828402519, | |
| "learning_rate": 1.8148049880604936e-05, | |
| "loss": 0.0616, | |
| "step": 2822 | |
| }, | |
| { | |
| "epoch": 8.134670487106018, | |
| "grad_norm": 10.42803955078125, | |
| "learning_rate": 1.792252586893075e-05, | |
| "loss": 0.0648, | |
| "step": 2839 | |
| }, | |
| { | |
| "epoch": 8.183381088825215, | |
| "grad_norm": 1.379164457321167, | |
| "learning_rate": 1.7697001857256567e-05, | |
| "loss": 0.1706, | |
| "step": 2856 | |
| }, | |
| { | |
| "epoch": 8.232091690544413, | |
| "grad_norm": 8.783364295959473, | |
| "learning_rate": 1.7471477845582384e-05, | |
| "loss": 0.1954, | |
| "step": 2873 | |
| }, | |
| { | |
| "epoch": 8.28080229226361, | |
| "grad_norm": 1.5522698163986206, | |
| "learning_rate": 1.7245953833908197e-05, | |
| "loss": 0.2134, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 8.329512893982809, | |
| "grad_norm": 6.784268379211426, | |
| "learning_rate": 1.7020429822234015e-05, | |
| "loss": 0.1928, | |
| "step": 2907 | |
| }, | |
| { | |
| "epoch": 8.378223495702006, | |
| "grad_norm": 3.0361063480377197, | |
| "learning_rate": 1.679490581055983e-05, | |
| "loss": 0.3187, | |
| "step": 2924 | |
| }, | |
| { | |
| "epoch": 8.426934097421203, | |
| "grad_norm": 1.8513216972351074, | |
| "learning_rate": 1.6569381798885645e-05, | |
| "loss": 0.1319, | |
| "step": 2941 | |
| }, | |
| { | |
| "epoch": 8.475644699140402, | |
| "grad_norm": 0.5567758083343506, | |
| "learning_rate": 1.6343857787211462e-05, | |
| "loss": 0.136, | |
| "step": 2958 | |
| }, | |
| { | |
| "epoch": 8.524355300859598, | |
| "grad_norm": 2.810915231704712, | |
| "learning_rate": 1.611833377553728e-05, | |
| "loss": 0.0858, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 8.573065902578797, | |
| "grad_norm": 1.9855493307113647, | |
| "learning_rate": 1.5892809763863097e-05, | |
| "loss": 0.1732, | |
| "step": 2992 | |
| }, | |
| { | |
| "epoch": 8.621776504297994, | |
| "grad_norm": 0.1735798567533493, | |
| "learning_rate": 1.566728575218891e-05, | |
| "loss": 0.0911, | |
| "step": 3009 | |
| }, | |
| { | |
| "epoch": 8.670487106017191, | |
| "grad_norm": 0.19329993426799774, | |
| "learning_rate": 1.5441761740514727e-05, | |
| "loss": 0.1024, | |
| "step": 3026 | |
| }, | |
| { | |
| "epoch": 8.71919770773639, | |
| "grad_norm": 4.43624210357666, | |
| "learning_rate": 1.5216237728840543e-05, | |
| "loss": 0.1408, | |
| "step": 3043 | |
| }, | |
| { | |
| "epoch": 8.767908309455587, | |
| "grad_norm": 9.911310195922852, | |
| "learning_rate": 1.4990713717166358e-05, | |
| "loss": 0.1626, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 8.816618911174785, | |
| "grad_norm": 1.323052167892456, | |
| "learning_rate": 1.4765189705492175e-05, | |
| "loss": 0.1222, | |
| "step": 3077 | |
| }, | |
| { | |
| "epoch": 8.865329512893982, | |
| "grad_norm": 11.561975479125977, | |
| "learning_rate": 1.4539665693817989e-05, | |
| "loss": 0.1769, | |
| "step": 3094 | |
| }, | |
| { | |
| "epoch": 8.914040114613181, | |
| "grad_norm": 0.08104487508535385, | |
| "learning_rate": 1.4314141682143806e-05, | |
| "loss": 0.0953, | |
| "step": 3111 | |
| }, | |
| { | |
| "epoch": 8.962750716332378, | |
| "grad_norm": 0.04927730932831764, | |
| "learning_rate": 1.408861767046962e-05, | |
| "loss": 0.0574, | |
| "step": 3128 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9956958393113343, | |
| "eval_f1_macro": 0.9948504424939576, | |
| "eval_f1_micro": 0.9956958393113343, | |
| "eval_f1_weighted": 0.9956230754082893, | |
| "eval_loss": 0.017519734799861908, | |
| "eval_precision_macro": 0.995983935742972, | |
| "eval_precision_micro": 0.9956958393113343, | |
| "eval_precision_weighted": 0.9964929061055317, | |
| "eval_recall_macro": 0.9948364888123926, | |
| "eval_recall_micro": 0.9956958393113343, | |
| "eval_recall_weighted": 0.9956958393113343, | |
| "eval_runtime": 3.4072, | |
| "eval_samples_per_second": 204.565, | |
| "eval_steps_per_second": 12.914, | |
| "step": 3141 | |
| }, | |
| { | |
| "epoch": 9.011461318051577, | |
| "grad_norm": 0.3880198001861572, | |
| "learning_rate": 1.3863093658795437e-05, | |
| "loss": 0.1954, | |
| "step": 3145 | |
| }, | |
| { | |
| "epoch": 9.060171919770774, | |
| "grad_norm": 0.05076654255390167, | |
| "learning_rate": 1.3637569647121254e-05, | |
| "loss": 0.0797, | |
| "step": 3162 | |
| }, | |
| { | |
| "epoch": 9.10888252148997, | |
| "grad_norm": 6.032546043395996, | |
| "learning_rate": 1.3412045635447068e-05, | |
| "loss": 0.2393, | |
| "step": 3179 | |
| }, | |
| { | |
| "epoch": 9.15759312320917, | |
| "grad_norm": 11.056164741516113, | |
| "learning_rate": 1.3186521623772885e-05, | |
| "loss": 0.1001, | |
| "step": 3196 | |
| }, | |
| { | |
| "epoch": 9.206303724928366, | |
| "grad_norm": 0.19840994477272034, | |
| "learning_rate": 1.29609976120987e-05, | |
| "loss": 0.0743, | |
| "step": 3213 | |
| }, | |
| { | |
| "epoch": 9.255014326647565, | |
| "grad_norm": 4.645060062408447, | |
| "learning_rate": 1.2735473600424515e-05, | |
| "loss": 0.1446, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 9.303724928366762, | |
| "grad_norm": 9.013117790222168, | |
| "learning_rate": 1.2509949588750332e-05, | |
| "loss": 0.1288, | |
| "step": 3247 | |
| }, | |
| { | |
| "epoch": 9.35243553008596, | |
| "grad_norm": 1.7711181640625, | |
| "learning_rate": 1.228442557707615e-05, | |
| "loss": 0.0835, | |
| "step": 3264 | |
| }, | |
| { | |
| "epoch": 9.401146131805158, | |
| "grad_norm": 5.3366379737854, | |
| "learning_rate": 1.2058901565401965e-05, | |
| "loss": 0.1201, | |
| "step": 3281 | |
| }, | |
| { | |
| "epoch": 9.449856733524355, | |
| "grad_norm": 3.4900286197662354, | |
| "learning_rate": 1.183337755372778e-05, | |
| "loss": 0.1026, | |
| "step": 3298 | |
| }, | |
| { | |
| "epoch": 9.498567335243553, | |
| "grad_norm": 0.059569913893938065, | |
| "learning_rate": 1.1607853542053596e-05, | |
| "loss": 0.1123, | |
| "step": 3315 | |
| }, | |
| { | |
| "epoch": 9.54727793696275, | |
| "grad_norm": 8.251703262329102, | |
| "learning_rate": 1.1382329530379411e-05, | |
| "loss": 0.1441, | |
| "step": 3332 | |
| }, | |
| { | |
| "epoch": 9.595988538681949, | |
| "grad_norm": 1.078260064125061, | |
| "learning_rate": 1.1156805518705226e-05, | |
| "loss": 0.1191, | |
| "step": 3349 | |
| }, | |
| { | |
| "epoch": 9.644699140401146, | |
| "grad_norm": 7.364470958709717, | |
| "learning_rate": 1.0931281507031044e-05, | |
| "loss": 0.1539, | |
| "step": 3366 | |
| }, | |
| { | |
| "epoch": 9.693409742120345, | |
| "grad_norm": 2.354499101638794, | |
| "learning_rate": 1.0705757495356859e-05, | |
| "loss": 0.1502, | |
| "step": 3383 | |
| }, | |
| { | |
| "epoch": 9.742120343839542, | |
| "grad_norm": 10.193525314331055, | |
| "learning_rate": 1.0480233483682674e-05, | |
| "loss": 0.1199, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 9.790830945558739, | |
| "grad_norm": 2.536367893218994, | |
| "learning_rate": 1.025470947200849e-05, | |
| "loss": 0.2098, | |
| "step": 3417 | |
| }, | |
| { | |
| "epoch": 9.839541547277937, | |
| "grad_norm": 5.09243631362915, | |
| "learning_rate": 1.0029185460334307e-05, | |
| "loss": 0.2896, | |
| "step": 3434 | |
| }, | |
| { | |
| "epoch": 9.888252148997134, | |
| "grad_norm": 1.098929762840271, | |
| "learning_rate": 9.803661448660124e-06, | |
| "loss": 0.1017, | |
| "step": 3451 | |
| }, | |
| { | |
| "epoch": 9.936962750716333, | |
| "grad_norm": 0.1535651981830597, | |
| "learning_rate": 9.57813743698594e-06, | |
| "loss": 0.1077, | |
| "step": 3468 | |
| }, | |
| { | |
| "epoch": 9.98567335243553, | |
| "grad_norm": 0.5236210227012634, | |
| "learning_rate": 9.352613425311755e-06, | |
| "loss": 0.084, | |
| "step": 3485 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9956958393113343, | |
| "eval_f1_macro": 0.9949831411206324, | |
| "eval_f1_micro": 0.9956958393113343, | |
| "eval_f1_weighted": 0.9955771743939521, | |
| "eval_loss": 0.015395666472613811, | |
| "eval_precision_macro": 0.9964707314104905, | |
| "eval_precision_micro": 0.9956958393113343, | |
| "eval_precision_weighted": 0.9963769691172847, | |
| "eval_recall_macro": 0.9945496270797476, | |
| "eval_recall_micro": 0.9956958393113343, | |
| "eval_recall_weighted": 0.9956958393113343, | |
| "eval_runtime": 3.4096, | |
| "eval_samples_per_second": 204.424, | |
| "eval_steps_per_second": 12.905, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 10.034383954154729, | |
| "grad_norm": 0.10064805299043655, | |
| "learning_rate": 9.12708941363757e-06, | |
| "loss": 0.129, | |
| "step": 3502 | |
| }, | |
| { | |
| "epoch": 10.083094555873926, | |
| "grad_norm": 0.9957130551338196, | |
| "learning_rate": 8.901565401963385e-06, | |
| "loss": 0.0652, | |
| "step": 3519 | |
| }, | |
| { | |
| "epoch": 10.131805157593123, | |
| "grad_norm": 4.763299465179443, | |
| "learning_rate": 8.676041390289202e-06, | |
| "loss": 0.1531, | |
| "step": 3536 | |
| }, | |
| { | |
| "epoch": 10.180515759312321, | |
| "grad_norm": 0.9550924897193909, | |
| "learning_rate": 8.450517378615018e-06, | |
| "loss": 0.0548, | |
| "step": 3553 | |
| }, | |
| { | |
| "epoch": 10.229226361031518, | |
| "grad_norm": 0.5510568022727966, | |
| "learning_rate": 8.224993366940833e-06, | |
| "loss": 0.171, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 10.277936962750717, | |
| "grad_norm": 1.120082139968872, | |
| "learning_rate": 7.999469355266649e-06, | |
| "loss": 0.1506, | |
| "step": 3587 | |
| }, | |
| { | |
| "epoch": 10.326647564469914, | |
| "grad_norm": 8.000428199768066, | |
| "learning_rate": 7.773945343592464e-06, | |
| "loss": 0.0791, | |
| "step": 3604 | |
| }, | |
| { | |
| "epoch": 10.375358166189113, | |
| "grad_norm": 0.08897445350885391, | |
| "learning_rate": 7.548421331918282e-06, | |
| "loss": 0.1006, | |
| "step": 3621 | |
| }, | |
| { | |
| "epoch": 10.42406876790831, | |
| "grad_norm": 1.5076502561569214, | |
| "learning_rate": 7.322897320244097e-06, | |
| "loss": 0.1085, | |
| "step": 3638 | |
| }, | |
| { | |
| "epoch": 10.472779369627506, | |
| "grad_norm": 0.3444303870201111, | |
| "learning_rate": 7.097373308569913e-06, | |
| "loss": 0.0881, | |
| "step": 3655 | |
| }, | |
| { | |
| "epoch": 10.521489971346705, | |
| "grad_norm": 5.353268146514893, | |
| "learning_rate": 6.871849296895728e-06, | |
| "loss": 0.1233, | |
| "step": 3672 | |
| }, | |
| { | |
| "epoch": 10.570200573065902, | |
| "grad_norm": 6.925529479980469, | |
| "learning_rate": 6.646325285221544e-06, | |
| "loss": 0.1726, | |
| "step": 3689 | |
| }, | |
| { | |
| "epoch": 10.6189111747851, | |
| "grad_norm": 1.2398282289505005, | |
| "learning_rate": 6.42080127354736e-06, | |
| "loss": 0.1607, | |
| "step": 3706 | |
| }, | |
| { | |
| "epoch": 10.667621776504298, | |
| "grad_norm": 0.17667262256145477, | |
| "learning_rate": 6.195277261873176e-06, | |
| "loss": 0.1065, | |
| "step": 3723 | |
| }, | |
| { | |
| "epoch": 10.716332378223496, | |
| "grad_norm": 8.593550682067871, | |
| "learning_rate": 5.969753250198992e-06, | |
| "loss": 0.1598, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 10.765042979942693, | |
| "grad_norm": 6.634376049041748, | |
| "learning_rate": 5.744229238524808e-06, | |
| "loss": 0.214, | |
| "step": 3757 | |
| }, | |
| { | |
| "epoch": 10.81375358166189, | |
| "grad_norm": 0.12865765392780304, | |
| "learning_rate": 5.518705226850624e-06, | |
| "loss": 0.1079, | |
| "step": 3774 | |
| }, | |
| { | |
| "epoch": 10.862464183381089, | |
| "grad_norm": 0.4588039815425873, | |
| "learning_rate": 5.29318121517644e-06, | |
| "loss": 0.1218, | |
| "step": 3791 | |
| }, | |
| { | |
| "epoch": 10.911174785100286, | |
| "grad_norm": 8.046585083007812, | |
| "learning_rate": 5.0676572035022555e-06, | |
| "loss": 0.1618, | |
| "step": 3808 | |
| }, | |
| { | |
| "epoch": 10.959885386819485, | |
| "grad_norm": 0.34073105454444885, | |
| "learning_rate": 4.842133191828072e-06, | |
| "loss": 0.0788, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 1.0, | |
| "eval_f1_macro": 1.0, | |
| "eval_f1_micro": 1.0, | |
| "eval_f1_weighted": 1.0, | |
| "eval_loss": 0.011031342670321465, | |
| "eval_precision_macro": 1.0, | |
| "eval_precision_micro": 1.0, | |
| "eval_precision_weighted": 1.0, | |
| "eval_recall_macro": 1.0, | |
| "eval_recall_micro": 1.0, | |
| "eval_recall_weighted": 1.0, | |
| "eval_runtime": 3.4121, | |
| "eval_samples_per_second": 204.275, | |
| "eval_steps_per_second": 12.895, | |
| "step": 3839 | |
| } | |
| ], | |
| "logging_steps": 17, | |
| "max_steps": 4188, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3756905482586214e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |