| { | |
| "best_metric": 0.8613303269447576, | |
| "best_model_checkpoint": "vit-base-patch16-384-finetuned-galaxy10-decals/checkpoint-781", | |
| "epoch": 29.76, | |
| "eval_steps": 500, | |
| "global_step": 930, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 2.2974, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 2.0265, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 1.5894, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.5744081172491544, | |
| "eval_f1": 0.5480702796340504, | |
| "eval_loss": 1.2731903791427612, | |
| "eval_precision": 0.5408951469363718, | |
| "eval_recall": 0.5744081172491544, | |
| "eval_runtime": 21.8126, | |
| "eval_samples_per_second": 81.329, | |
| "eval_steps_per_second": 0.642, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 1.2296, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.9378, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.8001, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_accuracy": 0.7976324689966178, | |
| "eval_f1": 0.7879640575454192, | |
| "eval_loss": 0.618441641330719, | |
| "eval_precision": 0.7933566799249927, | |
| "eval_recall": 0.7976324689966178, | |
| "eval_runtime": 22.1643, | |
| "eval_samples_per_second": 80.039, | |
| "eval_steps_per_second": 0.632, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.742, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.6869, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.6895, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "eval_accuracy": 0.8066516347237881, | |
| "eval_f1": 0.7955335694474486, | |
| "eval_loss": 0.5823069214820862, | |
| "eval_precision": 0.7990571311786572, | |
| "eval_recall": 0.8066516347237881, | |
| "eval_runtime": 22.3324, | |
| "eval_samples_per_second": 79.436, | |
| "eval_steps_per_second": 0.627, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.916367980884111e-05, | |
| "loss": 0.6689, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 9.79689366786141e-05, | |
| "loss": 0.6449, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 9.677419354838711e-05, | |
| "loss": 0.6259, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8432919954904171, | |
| "eval_f1": 0.8367752646524916, | |
| "eval_loss": 0.49104946851730347, | |
| "eval_precision": 0.8426702265640142, | |
| "eval_recall": 0.8432919954904171, | |
| "eval_runtime": 22.0094, | |
| "eval_samples_per_second": 80.602, | |
| "eval_steps_per_second": 0.636, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 9.55794504181601e-05, | |
| "loss": 0.5898, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 9.438470728793309e-05, | |
| "loss": 0.5565, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 9.31899641577061e-05, | |
| "loss": 0.556, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.846674182638106, | |
| "eval_f1": 0.8464510661392919, | |
| "eval_loss": 0.48742011189460754, | |
| "eval_precision": 0.8465088132210393, | |
| "eval_recall": 0.846674182638106, | |
| "eval_runtime": 22.0562, | |
| "eval_samples_per_second": 80.431, | |
| "eval_steps_per_second": 0.635, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 9.199522102747909e-05, | |
| "loss": 0.5251, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 9.080047789725208e-05, | |
| "loss": 0.5217, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 8.960573476702509e-05, | |
| "loss": 0.5116, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.98, | |
| "eval_accuracy": 0.85456595264938, | |
| "eval_f1": 0.8517657628179492, | |
| "eval_loss": 0.47338515520095825, | |
| "eval_precision": 0.8568577324587641, | |
| "eval_recall": 0.85456595264938, | |
| "eval_runtime": 22.2468, | |
| "eval_samples_per_second": 79.742, | |
| "eval_steps_per_second": 0.629, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 8.84109916367981e-05, | |
| "loss": 0.5088, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 8.72162485065711e-05, | |
| "loss": 0.4811, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 8.60215053763441e-05, | |
| "loss": 0.4877, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "eval_accuracy": 0.8461104847801578, | |
| "eval_f1": 0.8428422926421464, | |
| "eval_loss": 0.4538511335849762, | |
| "eval_precision": 0.8428871947589589, | |
| "eval_recall": 0.8461104847801578, | |
| "eval_runtime": 22.0712, | |
| "eval_samples_per_second": 80.376, | |
| "eval_steps_per_second": 0.634, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 8.482676224611709e-05, | |
| "loss": 0.4978, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 8.363201911589009e-05, | |
| "loss": 0.4539, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 8.243727598566309e-05, | |
| "loss": 0.4677, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 8.124253285543608e-05, | |
| "loss": 0.4383, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8376550169109357, | |
| "eval_f1": 0.8344803158108158, | |
| "eval_loss": 0.4715927839279175, | |
| "eval_precision": 0.8399037217806676, | |
| "eval_recall": 0.8376550169109357, | |
| "eval_runtime": 21.9794, | |
| "eval_samples_per_second": 80.712, | |
| "eval_steps_per_second": 0.637, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 8.004778972520908e-05, | |
| "loss": 0.4267, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 7.885304659498209e-05, | |
| "loss": 0.4439, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 7.765830346475508e-05, | |
| "loss": 0.4267, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8602029312288614, | |
| "eval_f1": 0.8558609549343756, | |
| "eval_loss": 0.43548089265823364, | |
| "eval_precision": 0.8576044168006902, | |
| "eval_recall": 0.8602029312288614, | |
| "eval_runtime": 22.1787, | |
| "eval_samples_per_second": 79.987, | |
| "eval_steps_per_second": 0.631, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 7.646356033452809e-05, | |
| "loss": 0.3988, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 7.526881720430108e-05, | |
| "loss": 0.4008, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.4022, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 9.98, | |
| "eval_accuracy": 0.8376550169109357, | |
| "eval_f1": 0.8355648091511257, | |
| "eval_loss": 0.47575539350509644, | |
| "eval_precision": 0.8377044905358585, | |
| "eval_recall": 0.8376550169109357, | |
| "eval_runtime": 22.2342, | |
| "eval_samples_per_second": 79.787, | |
| "eval_steps_per_second": 0.63, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 7.287933094384708e-05, | |
| "loss": 0.3884, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 7.168458781362007e-05, | |
| "loss": 0.3949, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 7.048984468339306e-05, | |
| "loss": 0.3811, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "eval_accuracy": 0.8494926719278467, | |
| "eval_f1": 0.8474377896340821, | |
| "eval_loss": 0.4537804424762726, | |
| "eval_precision": 0.8471164348108314, | |
| "eval_recall": 0.8494926719278467, | |
| "eval_runtime": 21.9928, | |
| "eval_samples_per_second": 80.663, | |
| "eval_steps_per_second": 0.637, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 6.929510155316607e-05, | |
| "loss": 0.3545, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 6.810035842293908e-05, | |
| "loss": 0.3437, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 6.690561529271207e-05, | |
| "loss": 0.3612, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8438556933483653, | |
| "eval_f1": 0.83986286467956, | |
| "eval_loss": 0.4807531237602234, | |
| "eval_precision": 0.8412077042410786, | |
| "eval_recall": 0.8438556933483653, | |
| "eval_runtime": 21.9365, | |
| "eval_samples_per_second": 80.87, | |
| "eval_steps_per_second": 0.638, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 6.571087216248507e-05, | |
| "loss": 0.3442, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 6.451612903225807e-05, | |
| "loss": 0.3353, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 6.332138590203107e-05, | |
| "loss": 0.363, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.846674182638106, | |
| "eval_f1": 0.8458450902771538, | |
| "eval_loss": 0.4751308262348175, | |
| "eval_precision": 0.8502119134878978, | |
| "eval_recall": 0.846674182638106, | |
| "eval_runtime": 22.1071, | |
| "eval_samples_per_second": 80.246, | |
| "eval_steps_per_second": 0.633, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 6.212664277180407e-05, | |
| "loss": 0.3409, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 6.093189964157706e-05, | |
| "loss": 0.3311, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 5.9737156511350064e-05, | |
| "loss": 0.3198, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 13.98, | |
| "eval_accuracy": 0.8489289740698985, | |
| "eval_f1": 0.8450237290199628, | |
| "eval_loss": 0.47995442152023315, | |
| "eval_precision": 0.8497216931511434, | |
| "eval_recall": 0.8489289740698985, | |
| "eval_runtime": 22.3525, | |
| "eval_samples_per_second": 79.365, | |
| "eval_steps_per_second": 0.626, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 5.8542413381123063e-05, | |
| "loss": 0.3169, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 5.7347670250896056e-05, | |
| "loss": 0.3034, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 5.615292712066906e-05, | |
| "loss": 0.3192, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 14.98, | |
| "eval_accuracy": 0.8573844419391207, | |
| "eval_f1": 0.857032095022158, | |
| "eval_loss": 0.48344284296035767, | |
| "eval_precision": 0.8580034765886128, | |
| "eval_recall": 0.8573844419391207, | |
| "eval_runtime": 22.221, | |
| "eval_samples_per_second": 79.834, | |
| "eval_steps_per_second": 0.63, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 5.495818399044206e-05, | |
| "loss": 0.2982, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 5.3763440860215054e-05, | |
| "loss": 0.2866, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 5.256869772998806e-05, | |
| "loss": 0.2877, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 5.137395459976105e-05, | |
| "loss": 0.3041, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8494926719278467, | |
| "eval_f1": 0.8443027737508426, | |
| "eval_loss": 0.4879484176635742, | |
| "eval_precision": 0.8500026597900313, | |
| "eval_recall": 0.8494926719278467, | |
| "eval_runtime": 22.0401, | |
| "eval_samples_per_second": 80.49, | |
| "eval_steps_per_second": 0.635, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 5.017921146953405e-05, | |
| "loss": 0.2706, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.2924, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.2607, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8540022547914318, | |
| "eval_f1": 0.8523463281841663, | |
| "eval_loss": 0.49578550457954407, | |
| "eval_precision": 0.8528831157271395, | |
| "eval_recall": 0.8540022547914318, | |
| "eval_runtime": 22.033, | |
| "eval_samples_per_second": 80.515, | |
| "eval_steps_per_second": 0.635, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.2715, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.2834, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.2649, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 17.98, | |
| "eval_accuracy": 0.8579481397970687, | |
| "eval_f1": 0.8562326829930054, | |
| "eval_loss": 0.49265938997268677, | |
| "eval_precision": 0.8570005813023908, | |
| "eval_recall": 0.8579481397970687, | |
| "eval_runtime": 22.3417, | |
| "eval_samples_per_second": 79.403, | |
| "eval_steps_per_second": 0.627, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.2624, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.2423, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.2553, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 18.98, | |
| "eval_accuracy": 0.8494926719278467, | |
| "eval_f1": 0.8473638848040509, | |
| "eval_loss": 0.5094860196113586, | |
| "eval_precision": 0.847257566255885, | |
| "eval_recall": 0.8494926719278467, | |
| "eval_runtime": 21.8356, | |
| "eval_samples_per_second": 81.244, | |
| "eval_steps_per_second": 0.641, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.2515, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.2526, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2453, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8494926719278467, | |
| "eval_f1": 0.8467359900263874, | |
| "eval_loss": 0.5161798000335693, | |
| "eval_precision": 0.8467382302648213, | |
| "eval_recall": 0.8494926719278467, | |
| "eval_runtime": 22.0357, | |
| "eval_samples_per_second": 80.506, | |
| "eval_steps_per_second": 0.635, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.2427, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.2364, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.2417, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8579481397970687, | |
| "eval_f1": 0.8542523881152531, | |
| "eval_loss": 0.5374500751495361, | |
| "eval_precision": 0.8572760382500455, | |
| "eval_recall": 0.8579481397970687, | |
| "eval_runtime": 22.3872, | |
| "eval_samples_per_second": 79.242, | |
| "eval_steps_per_second": 0.625, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.229, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.2359, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.241, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 21.98, | |
| "eval_accuracy": 0.8568207440811725, | |
| "eval_f1": 0.8547169886868239, | |
| "eval_loss": 0.512915313243866, | |
| "eval_precision": 0.8545685444650545, | |
| "eval_recall": 0.8568207440811725, | |
| "eval_runtime": 22.1438, | |
| "eval_samples_per_second": 80.113, | |
| "eval_steps_per_second": 0.632, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.2366, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.2258, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.2257, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 22.98, | |
| "eval_accuracy": 0.8596392333709132, | |
| "eval_f1": 0.8570784965746712, | |
| "eval_loss": 0.5315744280815125, | |
| "eval_precision": 0.8583802070333396, | |
| "eval_recall": 0.8596392333709132, | |
| "eval_runtime": 22.2978, | |
| "eval_samples_per_second": 79.559, | |
| "eval_steps_per_second": 0.628, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.2263, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.2182, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.2297, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.2087, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8511837655016911, | |
| "eval_f1": 0.848921831106386, | |
| "eval_loss": 0.5529980659484863, | |
| "eval_precision": 0.849654051064782, | |
| "eval_recall": 0.8511837655016911, | |
| "eval_runtime": 22.0692, | |
| "eval_samples_per_second": 80.383, | |
| "eval_steps_per_second": 0.634, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.2279, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.2103, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.2196, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8613303269447576, | |
| "eval_f1": 0.8596444828561277, | |
| "eval_loss": 0.5422354936599731, | |
| "eval_precision": 0.8600050951653831, | |
| "eval_recall": 0.8613303269447576, | |
| "eval_runtime": 22.3792, | |
| "eval_samples_per_second": 79.27, | |
| "eval_steps_per_second": 0.626, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.1947, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.2016, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.1975, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 25.98, | |
| "eval_accuracy": 0.8528748590755355, | |
| "eval_f1": 0.850826122514615, | |
| "eval_loss": 0.5671515464782715, | |
| "eval_precision": 0.8533722924188255, | |
| "eval_recall": 0.8528748590755355, | |
| "eval_runtime": 22.1344, | |
| "eval_samples_per_second": 80.147, | |
| "eval_steps_per_second": 0.632, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.2206, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.2007, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.2135, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 26.98, | |
| "eval_accuracy": 0.8523111612175873, | |
| "eval_f1": 0.8508686765834379, | |
| "eval_loss": 0.5697333216667175, | |
| "eval_precision": 0.8512784330826557, | |
| "eval_recall": 0.8523111612175873, | |
| "eval_runtime": 21.9964, | |
| "eval_samples_per_second": 80.65, | |
| "eval_steps_per_second": 0.636, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.2134, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.2157, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.1946, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8556933483652762, | |
| "eval_f1": 0.8536344252156703, | |
| "eval_loss": 0.5598114728927612, | |
| "eval_precision": 0.854160182325068, | |
| "eval_recall": 0.8556933483652762, | |
| "eval_runtime": 22.2731, | |
| "eval_samples_per_second": 79.648, | |
| "eval_steps_per_second": 0.629, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.2131, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.1988, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.2006, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.859075535512965, | |
| "eval_f1": 0.8559520451985321, | |
| "eval_loss": 0.5581933259963989, | |
| "eval_precision": 0.8565751475892288, | |
| "eval_recall": 0.859075535512965, | |
| "eval_runtime": 22.1527, | |
| "eval_samples_per_second": 80.081, | |
| "eval_steps_per_second": 0.632, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.2068, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.188, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.1968, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.859075535512965, | |
| "eval_f1": 0.8563712215450049, | |
| "eval_loss": 0.5570882558822632, | |
| "eval_precision": 0.8570535356400701, | |
| "eval_recall": 0.859075535512965, | |
| "eval_runtime": 22.3987, | |
| "eval_samples_per_second": 79.201, | |
| "eval_steps_per_second": 0.625, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 930, | |
| "total_flos": 1.0856143898633267e+20, | |
| "train_loss": 0.41153401379944177, | |
| "train_runtime": 9651.1603, | |
| "train_samples_per_second": 49.617, | |
| "train_steps_per_second": 0.096 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 930, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.0856143898633267e+20, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |