| { | |
| "best_metric": 0.9918692001767565, | |
| "best_model_checkpoint": "electricidad-small-discriminator-finetuned-clasificacion-comentarios-suicidas/checkpoint-84154", | |
| "epoch": 15.0, | |
| "global_step": 90165, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.9889092219819223e-05, | |
| "loss": 0.3744, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.977818443963844e-05, | |
| "loss": 0.2448, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.9667276659457665e-05, | |
| "loss": 0.2103, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.9556368879276883e-05, | |
| "loss": 0.2037, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9445461099096104e-05, | |
| "loss": 0.1902, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.9334553318915322e-05, | |
| "loss": 0.1874, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.9223645538734543e-05, | |
| "loss": 0.1717, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.9112737758553765e-05, | |
| "loss": 0.1723, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.9001829978372986e-05, | |
| "loss": 0.1697, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.8890922198192204e-05, | |
| "loss": 0.1637, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.8780014418011425e-05, | |
| "loss": 0.1593, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.8669106637830646e-05, | |
| "loss": 0.1611, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9527176314626602, | |
| "eval_loss": 0.13305681943893433, | |
| "eval_runtime": 183.6617, | |
| "eval_samples_per_second": 123.216, | |
| "eval_steps_per_second": 3.855, | |
| "step": 6011 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 1.8558198857649864e-05, | |
| "loss": 0.1436, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 1.8447291077469085e-05, | |
| "loss": 0.1391, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 1.8336383297288306e-05, | |
| "loss": 0.1382, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.8225475517107528e-05, | |
| "loss": 0.1332, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 1.8114567736926746e-05, | |
| "loss": 0.1385, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 1.8003659956745967e-05, | |
| "loss": 0.136, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 1.7892752176565188e-05, | |
| "loss": 0.1426, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 1.7781844396384406e-05, | |
| "loss": 0.1308, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.767093661620363e-05, | |
| "loss": 0.1355, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.7560028836022848e-05, | |
| "loss": 0.1331, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 1.744912105584207e-05, | |
| "loss": 0.1272, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.7338213275661287e-05, | |
| "loss": 0.1345, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9608042421564296, | |
| "eval_loss": 0.11096587032079697, | |
| "eval_runtime": 183.8189, | |
| "eval_samples_per_second": 123.11, | |
| "eval_steps_per_second": 3.852, | |
| "step": 12022 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.722730549548051e-05, | |
| "loss": 0.1176, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.711639771529973e-05, | |
| "loss": 0.1138, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.700548993511895e-05, | |
| "loss": 0.1121, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.689458215493817e-05, | |
| "loss": 0.1163, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 1.678367437475739e-05, | |
| "loss": 0.1115, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 1.667276659457661e-05, | |
| "loss": 0.1201, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 1.656185881439583e-05, | |
| "loss": 0.1215, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 1.6450951034215054e-05, | |
| "loss": 0.112, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 1.634004325403427e-05, | |
| "loss": 0.122, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.6229135473853493e-05, | |
| "loss": 0.1084, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.611822769367271e-05, | |
| "loss": 0.1208, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 1.6007319913491932e-05, | |
| "loss": 0.1085, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9708351745470615, | |
| "eval_loss": 0.08641747385263443, | |
| "eval_runtime": 183.9354, | |
| "eval_samples_per_second": 123.032, | |
| "eval_steps_per_second": 3.849, | |
| "step": 18033 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.5896412133311153e-05, | |
| "loss": 0.1011, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 1.5785504353130374e-05, | |
| "loss": 0.1, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 1.5674596572949596e-05, | |
| "loss": 0.102, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 1.5563688792768813e-05, | |
| "loss": 0.0978, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.5452781012588035e-05, | |
| "loss": 0.1005, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 1.5341873232407252e-05, | |
| "loss": 0.1019, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.5230965452226474e-05, | |
| "loss": 0.0985, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 1.5120057672045697e-05, | |
| "loss": 0.0971, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 1.5009149891864916e-05, | |
| "loss": 0.107, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 1.4898242111684136e-05, | |
| "loss": 0.1001, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.4787334331503355e-05, | |
| "loss": 0.0988, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1.4676426551322576e-05, | |
| "loss": 0.0994, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.974856385329209, | |
| "eval_loss": 0.07361753284931183, | |
| "eval_runtime": 183.7502, | |
| "eval_samples_per_second": 123.156, | |
| "eval_steps_per_second": 3.853, | |
| "step": 24044 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 1.4565518771141798e-05, | |
| "loss": 0.0895, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 1.4454610990961017e-05, | |
| "loss": 0.0833, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 4.24, | |
| "learning_rate": 1.4343703210780238e-05, | |
| "loss": 0.0866, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1.4232795430599458e-05, | |
| "loss": 0.0892, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 1.4121887650418678e-05, | |
| "loss": 0.0837, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 1.4010979870237897e-05, | |
| "loss": 0.0903, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 1.390007209005712e-05, | |
| "loss": 0.0825, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 1.378916430987634e-05, | |
| "loss": 0.0905, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.3678256529695559e-05, | |
| "loss": 0.0822, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 1.3567348749514779e-05, | |
| "loss": 0.0904, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.3456440969334e-05, | |
| "loss": 0.0938, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 1.334553318915322e-05, | |
| "loss": 0.0905, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9796288113124172, | |
| "eval_loss": 0.06523095816373825, | |
| "eval_runtime": 184.074, | |
| "eval_samples_per_second": 122.94, | |
| "eval_steps_per_second": 3.846, | |
| "step": 30055 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.323462540897244e-05, | |
| "loss": 0.072, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 1.3123717628791662e-05, | |
| "loss": 0.0769, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 1.3012809848610881e-05, | |
| "loss": 0.0761, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 1.2901902068430101e-05, | |
| "loss": 0.0782, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 1.279099428824932e-05, | |
| "loss": 0.0682, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 5.49, | |
| "learning_rate": 1.2680086508068543e-05, | |
| "loss": 0.0799, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 1.2569178727887763e-05, | |
| "loss": 0.0766, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 1.2458270947706982e-05, | |
| "loss": 0.0762, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 5.74, | |
| "learning_rate": 1.2347363167526204e-05, | |
| "loss": 0.0775, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 1.2236455387345423e-05, | |
| "loss": 0.0756, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 1.2125547607164643e-05, | |
| "loss": 0.0784, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 1.2014639826983866e-05, | |
| "loss": 0.0807, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9823243482103402, | |
| "eval_loss": 0.0608493909239769, | |
| "eval_runtime": 183.9197, | |
| "eval_samples_per_second": 123.043, | |
| "eval_steps_per_second": 3.85, | |
| "step": 36066 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 1.1903732046803085e-05, | |
| "loss": 0.0664, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 1.1792824266622305e-05, | |
| "loss": 0.0656, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 1.1681916486441524e-05, | |
| "loss": 0.0669, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 1.1571008706260745e-05, | |
| "loss": 0.0646, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.1460100926079965e-05, | |
| "loss": 0.067, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 1.1349193145899186e-05, | |
| "loss": 0.0708, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 1.1238285365718407e-05, | |
| "loss": 0.0729, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 1.1127377585537627e-05, | |
| "loss": 0.0682, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 1.1016469805356846e-05, | |
| "loss": 0.0747, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 6.82, | |
| "learning_rate": 1.0905562025176066e-05, | |
| "loss": 0.0697, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 1.0794654244995286e-05, | |
| "loss": 0.0695, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "learning_rate": 1.0683746464814508e-05, | |
| "loss": 0.0692, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9861246133451171, | |
| "eval_loss": 0.05471781641244888, | |
| "eval_runtime": 184.0533, | |
| "eval_samples_per_second": 122.954, | |
| "eval_steps_per_second": 3.847, | |
| "step": 42077 | |
| }, | |
| { | |
| "epoch": 7.07, | |
| "learning_rate": 1.0572838684633728e-05, | |
| "loss": 0.062, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 1.0461930904452948e-05, | |
| "loss": 0.0573, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 1.0351023124272169e-05, | |
| "loss": 0.0599, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 1.0240115344091388e-05, | |
| "loss": 0.0577, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 1.012920756391061e-05, | |
| "loss": 0.0582, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 1.001829978372983e-05, | |
| "loss": 0.0637, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 9.90739200354905e-06, | |
| "loss": 0.0658, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 7.65, | |
| "learning_rate": 9.79648422336827e-06, | |
| "loss": 0.06, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 9.68557644318749e-06, | |
| "loss": 0.0575, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 7.82, | |
| "learning_rate": 9.57466866300671e-06, | |
| "loss": 0.0635, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 9.46376088282593e-06, | |
| "loss": 0.0623, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 9.352853102645151e-06, | |
| "loss": 0.0604, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9859478568272205, | |
| "eval_loss": 0.051153190433979034, | |
| "eval_runtime": 184.082, | |
| "eval_samples_per_second": 122.934, | |
| "eval_steps_per_second": 3.846, | |
| "step": 48088 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 9.241945322464373e-06, | |
| "loss": 0.0507, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 8.15, | |
| "learning_rate": 9.131037542283592e-06, | |
| "loss": 0.0538, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 9.020129762102813e-06, | |
| "loss": 0.0506, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.909221981922033e-06, | |
| "loss": 0.0526, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 8.798314201741252e-06, | |
| "loss": 0.0579, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 8.687406421560474e-06, | |
| "loss": 0.051, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 8.576498641379693e-06, | |
| "loss": 0.0508, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 8.465590861198913e-06, | |
| "loss": 0.0566, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 8.354683081018134e-06, | |
| "loss": 0.0582, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 8.243775300837355e-06, | |
| "loss": 0.0512, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 8.132867520656575e-06, | |
| "loss": 0.0544, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 8.98, | |
| "learning_rate": 8.021959740475796e-06, | |
| "loss": 0.0482, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9897481219619974, | |
| "eval_loss": 0.04574726149439812, | |
| "eval_runtime": 184.1495, | |
| "eval_samples_per_second": 122.889, | |
| "eval_steps_per_second": 3.845, | |
| "step": 54099 | |
| }, | |
| { | |
| "epoch": 9.07, | |
| "learning_rate": 7.911051960295015e-06, | |
| "loss": 0.0506, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 7.800144180114235e-06, | |
| "loss": 0.0423, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 7.689236399933456e-06, | |
| "loss": 0.0458, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 7.5783286197526765e-06, | |
| "loss": 0.0454, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 7.467420839571896e-06, | |
| "loss": 0.0434, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 7.356513059391117e-06, | |
| "loss": 0.0494, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 9.57, | |
| "learning_rate": 7.245605279210337e-06, | |
| "loss": 0.0477, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 7.134697499029557e-06, | |
| "loss": 0.0473, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 7.0237897188487784e-06, | |
| "loss": 0.0488, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "learning_rate": 6.912881938667998e-06, | |
| "loss": 0.0518, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 6.801974158487219e-06, | |
| "loss": 0.0482, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "learning_rate": 6.691066378306439e-06, | |
| "loss": 0.0455, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9880689350419797, | |
| "eval_loss": 0.049992308020591736, | |
| "eval_runtime": 183.6678, | |
| "eval_samples_per_second": 123.212, | |
| "eval_steps_per_second": 3.855, | |
| "step": 60110 | |
| }, | |
| { | |
| "epoch": 10.06, | |
| "learning_rate": 6.580158598125659e-06, | |
| "loss": 0.0419, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 6.4692508179448795e-06, | |
| "loss": 0.0401, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 10.23, | |
| "learning_rate": 6.3583430377641e-06, | |
| "loss": 0.0403, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "learning_rate": 6.247435257583319e-06, | |
| "loss": 0.0375, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 6.136527477402541e-06, | |
| "loss": 0.0461, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 10.48, | |
| "learning_rate": 6.025619697221761e-06, | |
| "loss": 0.0443, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 5.9147119170409805e-06, | |
| "loss": 0.0439, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 5.803804136860202e-06, | |
| "loss": 0.0374, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 5.692896356679421e-06, | |
| "loss": 0.0382, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 10.81, | |
| "learning_rate": 5.581988576498642e-06, | |
| "loss": 0.0428, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 5.471080796317863e-06, | |
| "loss": 0.0401, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 5.3601730161370824e-06, | |
| "loss": 0.0434, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.990234202386213, | |
| "eval_loss": 0.046325162053108215, | |
| "eval_runtime": 183.7954, | |
| "eval_samples_per_second": 123.126, | |
| "eval_steps_per_second": 3.852, | |
| "step": 66121 | |
| }, | |
| { | |
| "epoch": 11.06, | |
| "learning_rate": 5.249265235956302e-06, | |
| "loss": 0.044, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 5.138357455775523e-06, | |
| "loss": 0.0348, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 11.23, | |
| "learning_rate": 5.0274496755947436e-06, | |
| "loss": 0.0358, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 4.916541895413964e-06, | |
| "loss": 0.0356, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 4.805634115233184e-06, | |
| "loss": 0.0366, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 11.48, | |
| "learning_rate": 4.694726335052404e-06, | |
| "loss": 0.0361, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 4.583818554871624e-06, | |
| "loss": 0.038, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 11.65, | |
| "learning_rate": 4.4729107746908455e-06, | |
| "loss": 0.0383, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 11.73, | |
| "learning_rate": 4.362002994510065e-06, | |
| "loss": 0.0429, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 11.81, | |
| "learning_rate": 4.251095214329285e-06, | |
| "loss": 0.0341, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 11.89, | |
| "learning_rate": 4.140187434148506e-06, | |
| "loss": 0.0369, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 11.98, | |
| "learning_rate": 4.029279653967726e-06, | |
| "loss": 0.0343, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9897923110914715, | |
| "eval_loss": 0.050745535641908646, | |
| "eval_runtime": 183.7772, | |
| "eval_samples_per_second": 123.138, | |
| "eval_steps_per_second": 3.852, | |
| "step": 72132 | |
| }, | |
| { | |
| "epoch": 12.06, | |
| "learning_rate": 3.9183718737869465e-06, | |
| "loss": 0.0326, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 12.14, | |
| "learning_rate": 3.807464093606167e-06, | |
| "loss": 0.0315, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 12.23, | |
| "learning_rate": 3.6965563134253873e-06, | |
| "loss": 0.0338, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 3.5856485332446072e-06, | |
| "loss": 0.0326, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 12.39, | |
| "learning_rate": 3.4747407530638276e-06, | |
| "loss": 0.0365, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 3.3638329728830484e-06, | |
| "loss": 0.0312, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 12.56, | |
| "learning_rate": 3.252925192702268e-06, | |
| "loss": 0.0321, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 3.1420174125214888e-06, | |
| "loss": 0.0281, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 12.73, | |
| "learning_rate": 3.031109632340709e-06, | |
| "loss": 0.0399, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 12.81, | |
| "learning_rate": 2.920201852159929e-06, | |
| "loss": 0.0347, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "learning_rate": 2.8092940719791495e-06, | |
| "loss": 0.0296, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 12.98, | |
| "learning_rate": 2.69838629179837e-06, | |
| "loss": 0.0329, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.991736632788334, | |
| "eval_loss": 0.04343385621905327, | |
| "eval_runtime": 183.857, | |
| "eval_samples_per_second": 123.085, | |
| "eval_steps_per_second": 3.851, | |
| "step": 78143 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 2.5874785116175907e-06, | |
| "loss": 0.0345, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 13.14, | |
| "learning_rate": 2.47657073143681e-06, | |
| "loss": 0.0337, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 13.23, | |
| "learning_rate": 2.365662951256031e-06, | |
| "loss": 0.0269, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 13.31, | |
| "learning_rate": 2.254755171075251e-06, | |
| "loss": 0.0318, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 13.39, | |
| "learning_rate": 2.1438473908944713e-06, | |
| "loss": 0.033, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 13.48, | |
| "learning_rate": 2.0329396107136917e-06, | |
| "loss": 0.0325, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 13.56, | |
| "learning_rate": 1.922031830532912e-06, | |
| "loss": 0.0241, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 13.64, | |
| "learning_rate": 1.8111240503521325e-06, | |
| "loss": 0.0282, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 13.72, | |
| "learning_rate": 1.7002162701713526e-06, | |
| "loss": 0.027, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "learning_rate": 1.589308489990573e-06, | |
| "loss": 0.0348, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 1.4784007098097932e-06, | |
| "loss": 0.0267, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 13.97, | |
| "learning_rate": 1.3674929296290136e-06, | |
| "loss": 0.0284, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9918692001767565, | |
| "eval_loss": 0.04500320181250572, | |
| "eval_runtime": 183.85, | |
| "eval_samples_per_second": 123.089, | |
| "eval_steps_per_second": 3.851, | |
| "step": 84154 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "learning_rate": 1.256585149448234e-06, | |
| "loss": 0.0336, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 14.14, | |
| "learning_rate": 1.145677369267454e-06, | |
| "loss": 0.0285, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 1.0347695890866745e-06, | |
| "loss": 0.0265, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 9.238618089058949e-07, | |
| "loss": 0.0244, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 14.39, | |
| "learning_rate": 8.129540287251151e-07, | |
| "loss": 0.0288, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 14.47, | |
| "learning_rate": 7.020462485443355e-07, | |
| "loss": 0.0272, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 5.911384683635558e-07, | |
| "loss": 0.0293, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 14.64, | |
| "learning_rate": 4.802306881827761e-07, | |
| "loss": 0.0275, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 3.693229080019964e-07, | |
| "loss": 0.0246, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 14.81, | |
| "learning_rate": 2.5841512782121667e-07, | |
| "loss": 0.0301, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 14.89, | |
| "learning_rate": 1.47507347640437e-07, | |
| "loss": 0.0275, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "learning_rate": 3.65995674596573e-08, | |
| "loss": 0.0223, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9916482545293858, | |
| "eval_loss": 0.04581888020038605, | |
| "eval_runtime": 183.9121, | |
| "eval_samples_per_second": 123.048, | |
| "eval_steps_per_second": 3.85, | |
| "step": 90165 | |
| } | |
| ], | |
| "max_steps": 90165, | |
| "num_train_epochs": 15, | |
| "total_flos": 8.488169482669056e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |