| { | |
| "best_metric": 0.8680947012401353, | |
| "best_model_checkpoint": "convnextv2-large-1k-224-finetuned-galaxy10-decals/checkpoint-1187", | |
| "epoch": 29.76, | |
| "eval_steps": 500, | |
| "global_step": 1860, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 2.298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 2.2732, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 2.2401, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 2.1798, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 2.0775, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 1.9261, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.4695603156708005, | |
| "eval_f1": 0.38749521098083667, | |
| "eval_loss": 1.8152951002120972, | |
| "eval_precision": 0.5069539754761746, | |
| "eval_recall": 0.4695603156708005, | |
| "eval_runtime": 17.1509, | |
| "eval_samples_per_second": 103.435, | |
| "eval_steps_per_second": 1.633, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 1.8014, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 1.6732, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 1.5599, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 1.4412, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 1.3364, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 1.2684, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6792559188275085, | |
| "eval_f1": 0.6478368948883783, | |
| "eval_loss": 1.1432373523712158, | |
| "eval_precision": 0.639509102504084, | |
| "eval_recall": 0.6792559188275085, | |
| "eval_runtime": 17.0738, | |
| "eval_samples_per_second": 103.902, | |
| "eval_steps_per_second": 1.64, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 1.1896, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 1.112, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 1.0529, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.9981, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.9443, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.9177, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.7846674182638106, | |
| "eval_f1": 0.7719507406127416, | |
| "eval_loss": 0.7477334141731262, | |
| "eval_precision": 0.783202377661933, | |
| "eval_recall": 0.7846674182638106, | |
| "eval_runtime": 17.1603, | |
| "eval_samples_per_second": 103.378, | |
| "eval_steps_per_second": 1.632, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.98805256869773e-05, | |
| "loss": 0.8937, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.815, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 4.92831541218638e-05, | |
| "loss": 0.7862, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.7953, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 4.86857825567503e-05, | |
| "loss": 0.7408, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.7581, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.80884109916368e-05, | |
| "loss": 0.6937, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8167981961668546, | |
| "eval_f1": 0.8104358000741603, | |
| "eval_loss": 0.5962362885475159, | |
| "eval_precision": 0.8145130593254478, | |
| "eval_recall": 0.8167981961668546, | |
| "eval_runtime": 17.3887, | |
| "eval_samples_per_second": 102.02, | |
| "eval_steps_per_second": 1.61, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.6875, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 4.74910394265233e-05, | |
| "loss": 0.69, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.6487, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.6893667861409805e-05, | |
| "loss": 0.6504, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.6709, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.5937, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8190529875986471, | |
| "eval_f1": 0.8166765744397984, | |
| "eval_loss": 0.5861955285072327, | |
| "eval_precision": 0.8233656134473737, | |
| "eval_recall": 0.8190529875986471, | |
| "eval_runtime": 17.0959, | |
| "eval_samples_per_second": 103.767, | |
| "eval_steps_per_second": 1.638, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.6144, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.6261, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.5918, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.51015531660693e-05, | |
| "loss": 0.6202, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.584, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 4.4504181600955796e-05, | |
| "loss": 0.5921, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8365276211950394, | |
| "eval_f1": 0.830022034898174, | |
| "eval_loss": 0.5389049649238586, | |
| "eval_precision": 0.8454361878294624, | |
| "eval_recall": 0.8365276211950394, | |
| "eval_runtime": 17.0935, | |
| "eval_samples_per_second": 103.782, | |
| "eval_steps_per_second": 1.638, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.5679, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 4.390681003584229e-05, | |
| "loss": 0.5647, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.5531, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 4.3309438470728796e-05, | |
| "loss": 0.6546, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.5635, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 4.271206690561529e-05, | |
| "loss": 0.557, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.8432919954904171, | |
| "eval_f1": 0.8409668149289347, | |
| "eval_loss": 0.494432270526886, | |
| "eval_precision": 0.8478289920908162, | |
| "eval_recall": 0.8432919954904171, | |
| "eval_runtime": 17.0843, | |
| "eval_samples_per_second": 103.838, | |
| "eval_steps_per_second": 1.639, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.5892, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 4.2114695340501795e-05, | |
| "loss": 0.561, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.5226, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 4.15173237753883e-05, | |
| "loss": 0.5311, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.513, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 4.0919952210274794e-05, | |
| "loss": 0.549, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.5522, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.842728297632469, | |
| "eval_f1": 0.8416197575288515, | |
| "eval_loss": 0.5021829009056091, | |
| "eval_precision": 0.8507791899926822, | |
| "eval_recall": 0.842728297632469, | |
| "eval_runtime": 17.0715, | |
| "eval_samples_per_second": 103.916, | |
| "eval_steps_per_second": 1.64, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.5013, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.4951, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 3.972520908004779e-05, | |
| "loss": 0.5181, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.4967, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 3.912783751493429e-05, | |
| "loss": 0.5242, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.5028, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8579481397970687, | |
| "eval_f1": 0.8580315629125352, | |
| "eval_loss": 0.4480929970741272, | |
| "eval_precision": 0.8609723534744894, | |
| "eval_recall": 0.8579481397970687, | |
| "eval_runtime": 17.0304, | |
| "eval_samples_per_second": 104.167, | |
| "eval_steps_per_second": 1.644, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 3.8530465949820786e-05, | |
| "loss": 0.488, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.4706, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 3.793309438470729e-05, | |
| "loss": 0.4698, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.4637, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 3.7335722819593785e-05, | |
| "loss": 0.4563, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.4801, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.855129650507328, | |
| "eval_f1": 0.8526707321633308, | |
| "eval_loss": 0.43604525923728943, | |
| "eval_precision": 0.8536456004266395, | |
| "eval_recall": 0.855129650507328, | |
| "eval_runtime": 17.3842, | |
| "eval_samples_per_second": 102.047, | |
| "eval_steps_per_second": 1.611, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 3.673835125448029e-05, | |
| "loss": 0.4672, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.4488, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 3.614097968936679e-05, | |
| "loss": 0.4708, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.442, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 3.554360812425329e-05, | |
| "loss": 0.4253, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.4475, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.8410372040586246, | |
| "eval_f1": 0.8407274997055765, | |
| "eval_loss": 0.4662620723247528, | |
| "eval_precision": 0.8423142107926088, | |
| "eval_recall": 0.8410372040586246, | |
| "eval_runtime": 17.1177, | |
| "eval_samples_per_second": 103.635, | |
| "eval_steps_per_second": 1.636, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 0.4372, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.4267, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 3.4348864994026287e-05, | |
| "loss": 0.4018, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.4159, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 3.375149342891278e-05, | |
| "loss": 0.4323, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.4121, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.3154121863799286e-05, | |
| "loss": 0.411, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.85456595264938, | |
| "eval_f1": 0.8538121824167246, | |
| "eval_loss": 0.4444187879562378, | |
| "eval_precision": 0.8551537379479608, | |
| "eval_recall": 0.85456595264938, | |
| "eval_runtime": 17.0678, | |
| "eval_samples_per_second": 103.939, | |
| "eval_steps_per_second": 1.641, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.3988, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 3.255675029868578e-05, | |
| "loss": 0.3883, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.402, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 3.195937873357228e-05, | |
| "loss": 0.422, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.4007, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 3.136200716845878e-05, | |
| "loss": 0.4173, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8613303269447576, | |
| "eval_f1": 0.859450538578204, | |
| "eval_loss": 0.4341481328010559, | |
| "eval_precision": 0.8627143963245729, | |
| "eval_recall": 0.8613303269447576, | |
| "eval_runtime": 17.0381, | |
| "eval_samples_per_second": 104.12, | |
| "eval_steps_per_second": 1.643, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.3618, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 3.0764635603345284e-05, | |
| "loss": 0.3843, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.4019, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 3.016726403823178e-05, | |
| "loss": 0.3693, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.3792, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 0.3995, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8652762119503946, | |
| "eval_f1": 0.8637234831322527, | |
| "eval_loss": 0.43799063563346863, | |
| "eval_precision": 0.8655306696908023, | |
| "eval_recall": 0.8652762119503946, | |
| "eval_runtime": 17.0187, | |
| "eval_samples_per_second": 104.238, | |
| "eval_steps_per_second": 1.645, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.3702, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 2.897252090800478e-05, | |
| "loss": 0.3422, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.3605, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 2.8375149342891276e-05, | |
| "loss": 0.3888, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.3662, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3657, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.8624577226606539, | |
| "eval_f1": 0.8615334998239615, | |
| "eval_loss": 0.46589186787605286, | |
| "eval_precision": 0.8632715811406524, | |
| "eval_recall": 0.8624577226606539, | |
| "eval_runtime": 17.0621, | |
| "eval_samples_per_second": 103.973, | |
| "eval_steps_per_second": 1.641, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.3712, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 2.718040621266428e-05, | |
| "loss": 0.3406, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.3376, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 2.6583034647550775e-05, | |
| "loss": 0.3482, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.3325, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 2.5985663082437278e-05, | |
| "loss": 0.3486, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.3533, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8602029312288614, | |
| "eval_f1": 0.8585116528654431, | |
| "eval_loss": 0.4600202143192291, | |
| "eval_precision": 0.8591976610260634, | |
| "eval_recall": 0.8602029312288614, | |
| "eval_runtime": 17.1139, | |
| "eval_samples_per_second": 103.658, | |
| "eval_steps_per_second": 1.636, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 2.5388291517323774e-05, | |
| "loss": 0.3453, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.3117, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 2.4790919952210277e-05, | |
| "loss": 0.3457, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.3811, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 0.3561, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.3001, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.8478015783540023, | |
| "eval_f1": 0.845016612946031, | |
| "eval_loss": 0.5068523287773132, | |
| "eval_precision": 0.8454922791310482, | |
| "eval_recall": 0.8478015783540023, | |
| "eval_runtime": 17.0863, | |
| "eval_samples_per_second": 103.826, | |
| "eval_steps_per_second": 1.639, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 2.3596176821983273e-05, | |
| "loss": 0.3239, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.3262, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 2.2998805256869773e-05, | |
| "loss": 0.3493, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.3245, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 2.2401433691756272e-05, | |
| "loss": 0.3195, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.318, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8573844419391207, | |
| "eval_f1": 0.8552065772532064, | |
| "eval_loss": 0.4647408723831177, | |
| "eval_precision": 0.8576165196015635, | |
| "eval_recall": 0.8573844419391207, | |
| "eval_runtime": 17.0481, | |
| "eval_samples_per_second": 104.059, | |
| "eval_steps_per_second": 1.642, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 2.1804062126642775e-05, | |
| "loss": 0.3215, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.2927, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 2.120669056152927e-05, | |
| "loss": 0.3065, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.3043, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 2.060931899641577e-05, | |
| "loss": 0.3062, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.3029, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.8680947012401353, | |
| "eval_f1": 0.866760619510197, | |
| "eval_loss": 0.44794121384620667, | |
| "eval_precision": 0.8669754761441882, | |
| "eval_recall": 0.8680947012401353, | |
| "eval_runtime": 17.2079, | |
| "eval_samples_per_second": 103.092, | |
| "eval_steps_per_second": 1.627, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 2.001194743130227e-05, | |
| "loss": 0.3169, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.2836, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 1.941457586618877e-05, | |
| "loss": 0.3017, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.3075, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 0.3022, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3132, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.821983273596177e-05, | |
| "loss": 0.2915, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8624577226606539, | |
| "eval_f1": 0.858577583185894, | |
| "eval_loss": 0.47721442580223083, | |
| "eval_precision": 0.859765869888627, | |
| "eval_recall": 0.8624577226606539, | |
| "eval_runtime": 17.1009, | |
| "eval_samples_per_second": 103.737, | |
| "eval_steps_per_second": 1.637, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.2922, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 1.7622461170848266e-05, | |
| "loss": 0.2905, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.2701, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 1.702508960573477e-05, | |
| "loss": 0.2801, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.3102, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 1.642771804062127e-05, | |
| "loss": 0.2742, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8556933483652762, | |
| "eval_f1": 0.8521257250797397, | |
| "eval_loss": 0.4797609746456146, | |
| "eval_precision": 0.853766976661393, | |
| "eval_recall": 0.8556933483652762, | |
| "eval_runtime": 17.0558, | |
| "eval_samples_per_second": 104.012, | |
| "eval_steps_per_second": 1.642, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.2644, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 1.5830346475507768e-05, | |
| "loss": 0.2918, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.2726, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 1.5232974910394265e-05, | |
| "loss": 0.2733, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.2835, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 1.4635603345280766e-05, | |
| "loss": 0.3067, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8602029312288614, | |
| "eval_f1": 0.8575173946999252, | |
| "eval_loss": 0.47669386863708496, | |
| "eval_precision": 0.8573242103773507, | |
| "eval_recall": 0.8602029312288614, | |
| "eval_runtime": 17.0823, | |
| "eval_samples_per_second": 103.85, | |
| "eval_steps_per_second": 1.639, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.2772, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 1.4038231780167265e-05, | |
| "loss": 0.2577, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.2707, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 0.2641, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.2761, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 1.2843488649940263e-05, | |
| "loss": 0.2758, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.850620067643743, | |
| "eval_f1": 0.851561054015019, | |
| "eval_loss": 0.5098563432693481, | |
| "eval_precision": 0.8547403877090707, | |
| "eval_recall": 0.850620067643743, | |
| "eval_runtime": 17.0511, | |
| "eval_samples_per_second": 104.04, | |
| "eval_steps_per_second": 1.642, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.2594, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 1.2246117084826763e-05, | |
| "loss": 0.2519, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.2727, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 1.1648745519713262e-05, | |
| "loss": 0.2526, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.2862, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 1.1051373954599762e-05, | |
| "loss": 0.246, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.2527, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8585118376550169, | |
| "eval_f1": 0.8565325600683443, | |
| "eval_loss": 0.5016410946846008, | |
| "eval_precision": 0.856278727634548, | |
| "eval_recall": 0.8585118376550169, | |
| "eval_runtime": 17.0984, | |
| "eval_samples_per_second": 103.752, | |
| "eval_steps_per_second": 1.638, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "learning_rate": 1.0454002389486262e-05, | |
| "loss": 0.2627, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.2853, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 9.856630824372761e-06, | |
| "loss": 0.2605, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.2298, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.2605, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.253, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8624577226606539, | |
| "eval_f1": 0.86039097705839, | |
| "eval_loss": 0.49895402789115906, | |
| "eval_precision": 0.8604966932048342, | |
| "eval_recall": 0.8624577226606539, | |
| "eval_runtime": 17.083, | |
| "eval_samples_per_second": 103.846, | |
| "eval_steps_per_second": 1.639, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 8.661887694145759e-06, | |
| "loss": 0.2468, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.2281, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 25.44, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 0.2358, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.2522, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 7.467144563918758e-06, | |
| "loss": 0.2375, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.2361, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8602029312288614, | |
| "eval_f1": 0.8591410041543185, | |
| "eval_loss": 0.49027714133262634, | |
| "eval_precision": 0.8590385226216685, | |
| "eval_recall": 0.8602029312288614, | |
| "eval_runtime": 17.1152, | |
| "eval_samples_per_second": 103.65, | |
| "eval_steps_per_second": 1.636, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 26.08, | |
| "learning_rate": 6.869772998805258e-06, | |
| "loss": 0.2481, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.2627, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 6.2724014336917564e-06, | |
| "loss": 0.237, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.2405, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 5.675029868578255e-06, | |
| "loss": 0.2468, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.2325, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.8602029312288614, | |
| "eval_f1": 0.8599887862312972, | |
| "eval_loss": 0.5062335133552551, | |
| "eval_precision": 0.8612276366692254, | |
| "eval_recall": 0.8602029312288614, | |
| "eval_runtime": 17.0703, | |
| "eval_samples_per_second": 103.923, | |
| "eval_steps_per_second": 1.64, | |
| "step": 1687 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 5.077658303464755e-06, | |
| "loss": 0.2452, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.2356, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 4.4802867383512545e-06, | |
| "loss": 0.2547, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.2338, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 3.882915173237754e-06, | |
| "loss": 0.2142, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.2298, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 3.2855436081242537e-06, | |
| "loss": 0.2448, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8669673055242391, | |
| "eval_f1": 0.8645620822519051, | |
| "eval_loss": 0.4996810853481293, | |
| "eval_precision": 0.864790123792046, | |
| "eval_recall": 0.8669673055242391, | |
| "eval_runtime": 17.0564, | |
| "eval_samples_per_second": 104.008, | |
| "eval_steps_per_second": 1.642, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.2239, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 0.2414, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.2242, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 2.090800477897252e-06, | |
| "loss": 0.2307, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.2443, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 1.4934289127837516e-06, | |
| "loss": 0.2354, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.8607666290868095, | |
| "eval_f1": 0.8590271066528125, | |
| "eval_loss": 0.4956284463405609, | |
| "eval_precision": 0.8585975350561472, | |
| "eval_recall": 0.8607666290868095, | |
| "eval_runtime": 17.0518, | |
| "eval_samples_per_second": 104.036, | |
| "eval_steps_per_second": 1.642, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.2414, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 8.960573476702509e-07, | |
| "loss": 0.2122, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.2244, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 2.9868578255675034e-07, | |
| "loss": 0.2267, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.2156, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.863021420518602, | |
| "eval_f1": 0.8617403218532078, | |
| "eval_loss": 0.49696364998817444, | |
| "eval_precision": 0.8614817373597583, | |
| "eval_recall": 0.863021420518602, | |
| "eval_runtime": 17.0759, | |
| "eval_samples_per_second": 103.889, | |
| "eval_steps_per_second": 1.64, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 1860, | |
| "total_flos": 8.428193799076122e+19, | |
| "train_loss": 0.49954657362353416, | |
| "train_runtime": 10215.0719, | |
| "train_samples_per_second": 46.878, | |
| "train_steps_per_second": 0.182 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 8.428193799076122e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |