| { | |
| "best_metric": 0.8652762119503946, | |
| "best_model_checkpoint": "swinv2-base-patch4-window12to16-192to256-22kto1k-ft-finetuned-galaxy10-decals/checkpoint-1860", | |
| "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": 2.3651, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 2.1743, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 1.9776, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 1.649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 1.395, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 1.1028, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.681510710259301, | |
| "eval_f1": 0.672512022193357, | |
| "eval_loss": 0.8747186064720154, | |
| "eval_precision": 0.7018930248872796, | |
| "eval_recall": 0.681510710259301, | |
| "eval_runtime": 14.1151, | |
| "eval_samples_per_second": 125.681, | |
| "eval_steps_per_second": 1.984, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 1.055, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.9293, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 0.8562, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.8071, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 0.7745, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.7637, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7993235625704622, | |
| "eval_f1": 0.7944067828700224, | |
| "eval_loss": 0.6109892725944519, | |
| "eval_precision": 0.8031775592187559, | |
| "eval_recall": 0.7993235625704622, | |
| "eval_runtime": 14.1177, | |
| "eval_samples_per_second": 125.658, | |
| "eval_steps_per_second": 1.983, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 0.7277, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.7271, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.7572, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.7533, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.7165, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.702, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.8179255918827508, | |
| "eval_f1": 0.8201239577996661, | |
| "eval_loss": 0.5406890511512756, | |
| "eval_precision": 0.8281612148942736, | |
| "eval_recall": 0.8179255918827508, | |
| "eval_runtime": 14.1176, | |
| "eval_samples_per_second": 125.659, | |
| "eval_steps_per_second": 1.983, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.98805256869773e-05, | |
| "loss": 0.7166, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.638, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 4.92831541218638e-05, | |
| "loss": 0.6491, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.6923, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 4.86857825567503e-05, | |
| "loss": 0.6255, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.6451, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.80884109916368e-05, | |
| "loss": 0.6131, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8325817361894025, | |
| "eval_f1": 0.8275638067001595, | |
| "eval_loss": 0.5038104057312012, | |
| "eval_precision": 0.8356035737117677, | |
| "eval_recall": 0.8325817361894025, | |
| "eval_runtime": 14.5578, | |
| "eval_samples_per_second": 121.859, | |
| "eval_steps_per_second": 1.923, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.6418, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 4.74910394265233e-05, | |
| "loss": 0.6274, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.6195, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.6893667861409805e-05, | |
| "loss": 0.5954, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.618, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.5453, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.8534385569334837, | |
| "eval_f1": 0.8527927506642161, | |
| "eval_loss": 0.45234787464141846, | |
| "eval_precision": 0.8546761827456698, | |
| "eval_recall": 0.8534385569334837, | |
| "eval_runtime": 14.5429, | |
| "eval_samples_per_second": 121.984, | |
| "eval_steps_per_second": 1.925, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.5557, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.5798, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.5752, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.51015531660693e-05, | |
| "loss": 0.5381, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.5378, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 4.4504181600955796e-05, | |
| "loss": 0.5409, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8376550169109357, | |
| "eval_f1": 0.8339264194949979, | |
| "eval_loss": 0.4908079206943512, | |
| "eval_precision": 0.8388782287526354, | |
| "eval_recall": 0.8376550169109357, | |
| "eval_runtime": 14.4197, | |
| "eval_samples_per_second": 123.026, | |
| "eval_steps_per_second": 1.942, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.5204, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 4.390681003584229e-05, | |
| "loss": 0.5286, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.4931, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 4.3309438470728796e-05, | |
| "loss": 0.5234, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.506, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 4.271206690561529e-05, | |
| "loss": 0.5246, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.8478015783540023, | |
| "eval_f1": 0.8486346456948685, | |
| "eval_loss": 0.45832160115242004, | |
| "eval_precision": 0.850947402065825, | |
| "eval_recall": 0.8478015783540023, | |
| "eval_runtime": 14.2181, | |
| "eval_samples_per_second": 124.771, | |
| "eval_steps_per_second": 1.969, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.5465, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 4.2114695340501795e-05, | |
| "loss": 0.5222, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.4876, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 4.15173237753883e-05, | |
| "loss": 0.5294, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.4807, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 4.0919952210274794e-05, | |
| "loss": 0.4803, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.478, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.850620067643743, | |
| "eval_f1": 0.8485657166034476, | |
| "eval_loss": 0.44167110323905945, | |
| "eval_precision": 0.8529461252603475, | |
| "eval_recall": 0.850620067643743, | |
| "eval_runtime": 13.8991, | |
| "eval_samples_per_second": 127.635, | |
| "eval_steps_per_second": 2.015, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.454, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.4513, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 3.972520908004779e-05, | |
| "loss": 0.5252, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.4681, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 3.912783751493429e-05, | |
| "loss": 0.5123, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.4845, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8596392333709132, | |
| "eval_f1": 0.8564708694320489, | |
| "eval_loss": 0.43437659740448, | |
| "eval_precision": 0.8591086675357801, | |
| "eval_recall": 0.8596392333709132, | |
| "eval_runtime": 14.1057, | |
| "eval_samples_per_second": 125.765, | |
| "eval_steps_per_second": 1.985, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 3.8530465949820786e-05, | |
| "loss": 0.4484, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.4322, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 3.793309438470729e-05, | |
| "loss": 0.4429, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.4539, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 3.7335722819593785e-05, | |
| "loss": 0.4226, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.4228, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8478015783540023, | |
| "eval_f1": 0.8461862766258204, | |
| "eval_loss": 0.4579648971557617, | |
| "eval_precision": 0.8488436694275387, | |
| "eval_recall": 0.8478015783540023, | |
| "eval_runtime": 14.7128, | |
| "eval_samples_per_second": 120.575, | |
| "eval_steps_per_second": 1.903, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 3.673835125448029e-05, | |
| "loss": 0.4498, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.4457, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 3.614097968936679e-05, | |
| "loss": 0.4657, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.4244, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 3.554360812425329e-05, | |
| "loss": 0.425, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.4414, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.8534385569334837, | |
| "eval_f1": 0.852456675591609, | |
| "eval_loss": 0.4519624710083008, | |
| "eval_precision": 0.8538889984443793, | |
| "eval_recall": 0.8534385569334837, | |
| "eval_runtime": 14.2726, | |
| "eval_samples_per_second": 124.294, | |
| "eval_steps_per_second": 1.962, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 0.4056, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.4106, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 3.4348864994026287e-05, | |
| "loss": 0.3995, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.4023, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 3.375149342891278e-05, | |
| "loss": 0.4231, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.4246, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.3154121863799286e-05, | |
| "loss": 0.3783, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8517474633596392, | |
| "eval_f1": 0.8501250467403075, | |
| "eval_loss": 0.477611243724823, | |
| "eval_precision": 0.8504472633109906, | |
| "eval_recall": 0.8517474633596392, | |
| "eval_runtime": 13.6733, | |
| "eval_samples_per_second": 129.742, | |
| "eval_steps_per_second": 2.048, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.3967, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 3.255675029868578e-05, | |
| "loss": 0.3899, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.3962, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 3.195937873357228e-05, | |
| "loss": 0.4381, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.4057, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 3.136200716845878e-05, | |
| "loss": 0.407, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.8478015783540023, | |
| "eval_f1": 0.844438354456064, | |
| "eval_loss": 0.4799591600894928, | |
| "eval_precision": 0.8482189599988375, | |
| "eval_recall": 0.8478015783540023, | |
| "eval_runtime": 14.1722, | |
| "eval_samples_per_second": 125.174, | |
| "eval_steps_per_second": 1.976, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.3965, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 3.0764635603345284e-05, | |
| "loss": 0.3707, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.421, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 3.016726403823178e-05, | |
| "loss": 0.3667, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.3947, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 0.3944, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.863021420518602, | |
| "eval_f1": 0.8617711783380199, | |
| "eval_loss": 0.4540901780128479, | |
| "eval_precision": 0.8638633750676442, | |
| "eval_recall": 0.863021420518602, | |
| "eval_runtime": 14.1277, | |
| "eval_samples_per_second": 125.569, | |
| "eval_steps_per_second": 1.982, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.3674, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 2.897252090800478e-05, | |
| "loss": 0.3416, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.3759, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 2.8375149342891276e-05, | |
| "loss": 0.396, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.3759, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.3563, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.8534385569334837, | |
| "eval_f1": 0.8522908798796575, | |
| "eval_loss": 0.48484402894973755, | |
| "eval_precision": 0.8531087562319168, | |
| "eval_recall": 0.8534385569334837, | |
| "eval_runtime": 14.2958, | |
| "eval_samples_per_second": 124.092, | |
| "eval_steps_per_second": 1.959, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.369, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 2.718040621266428e-05, | |
| "loss": 0.3488, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.3539, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 2.6583034647550775e-05, | |
| "loss": 0.3688, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.3463, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 2.5985663082437278e-05, | |
| "loss": 0.3625, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.3576, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8540022547914318, | |
| "eval_f1": 0.8522159716730663, | |
| "eval_loss": 0.48768532276153564, | |
| "eval_precision": 0.852621671526639, | |
| "eval_recall": 0.8540022547914318, | |
| "eval_runtime": 14.3097, | |
| "eval_samples_per_second": 123.972, | |
| "eval_steps_per_second": 1.957, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 2.5388291517323774e-05, | |
| "loss": 0.3458, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.3255, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 2.4790919952210277e-05, | |
| "loss": 0.357, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.3725, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 0.3446, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.317, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.855129650507328, | |
| "eval_f1": 0.8545780255661041, | |
| "eval_loss": 0.5122403502464294, | |
| "eval_precision": 0.857156130400553, | |
| "eval_recall": 0.855129650507328, | |
| "eval_runtime": 14.0492, | |
| "eval_samples_per_second": 126.27, | |
| "eval_steps_per_second": 1.993, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 2.3596176821983273e-05, | |
| "loss": 0.3401, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.3292, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 2.2998805256869773e-05, | |
| "loss": 0.3402, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.3366, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 2.2401433691756272e-05, | |
| "loss": 0.3098, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.3439, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8483652762119503, | |
| "eval_f1": 0.8466022768436097, | |
| "eval_loss": 0.5073115825653076, | |
| "eval_precision": 0.8509035234884134, | |
| "eval_recall": 0.8483652762119503, | |
| "eval_runtime": 14.4506, | |
| "eval_samples_per_second": 122.763, | |
| "eval_steps_per_second": 1.938, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 2.1804062126642775e-05, | |
| "loss": 0.3328, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.3063, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 2.120669056152927e-05, | |
| "loss": 0.3032, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.3094, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 2.060931899641577e-05, | |
| "loss": 0.3134, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.3199, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.8573844419391207, | |
| "eval_f1": 0.8555039631706255, | |
| "eval_loss": 0.5183351039886475, | |
| "eval_precision": 0.8551865105651447, | |
| "eval_recall": 0.8573844419391207, | |
| "eval_runtime": 14.5137, | |
| "eval_samples_per_second": 122.229, | |
| "eval_steps_per_second": 1.929, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 2.001194743130227e-05, | |
| "loss": 0.3168, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.3045, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 1.941457586618877e-05, | |
| "loss": 0.3049, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.3048, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 0.3024, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3184, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.821983273596177e-05, | |
| "loss": 0.3121, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8483652762119503, | |
| "eval_f1": 0.8450844355791876, | |
| "eval_loss": 0.5367450714111328, | |
| "eval_precision": 0.8470706613860829, | |
| "eval_recall": 0.8483652762119503, | |
| "eval_runtime": 14.2447, | |
| "eval_samples_per_second": 124.537, | |
| "eval_steps_per_second": 1.966, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.2913, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 1.7622461170848266e-05, | |
| "loss": 0.315, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.2827, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 1.702508960573477e-05, | |
| "loss": 0.2971, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.3058, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 1.642771804062127e-05, | |
| "loss": 0.2942, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8534385569334837, | |
| "eval_f1": 0.8508753046672477, | |
| "eval_loss": 0.5904532074928284, | |
| "eval_precision": 0.8505842460299928, | |
| "eval_recall": 0.8534385569334837, | |
| "eval_runtime": 14.2262, | |
| "eval_samples_per_second": 124.699, | |
| "eval_steps_per_second": 1.968, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.2834, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 1.5830346475507768e-05, | |
| "loss": 0.289, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.2906, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 1.5232974910394265e-05, | |
| "loss": 0.2842, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.3055, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 1.4635603345280766e-05, | |
| "loss": 0.3253, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8494926719278467, | |
| "eval_f1": 0.8478431779401735, | |
| "eval_loss": 0.5762498378753662, | |
| "eval_precision": 0.8497810429424291, | |
| "eval_recall": 0.8494926719278467, | |
| "eval_runtime": 14.2293, | |
| "eval_samples_per_second": 124.673, | |
| "eval_steps_per_second": 1.968, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.2685, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 1.4038231780167265e-05, | |
| "loss": 0.2826, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.2935, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 0.2809, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.2813, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 1.2843488649940263e-05, | |
| "loss": 0.2917, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.8432919954904171, | |
| "eval_f1": 0.8428373736681363, | |
| "eval_loss": 0.5865141153335571, | |
| "eval_precision": 0.8452005885204262, | |
| "eval_recall": 0.8432919954904171, | |
| "eval_runtime": 14.5151, | |
| "eval_samples_per_second": 122.218, | |
| "eval_steps_per_second": 1.929, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.2815, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 1.2246117084826763e-05, | |
| "loss": 0.2658, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.2769, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 1.1648745519713262e-05, | |
| "loss": 0.2815, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.3163, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 1.1051373954599762e-05, | |
| "loss": 0.2537, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.2708, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8568207440811725, | |
| "eval_f1": 0.853945237325703, | |
| "eval_loss": 0.5801535248756409, | |
| "eval_precision": 0.853236436250704, | |
| "eval_recall": 0.8568207440811725, | |
| "eval_runtime": 14.1567, | |
| "eval_samples_per_second": 125.312, | |
| "eval_steps_per_second": 1.978, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "learning_rate": 1.0454002389486262e-05, | |
| "loss": 0.2757, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.2963, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 9.856630824372761e-06, | |
| "loss": 0.2812, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.2625, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.2579, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.2801, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8556933483652762, | |
| "eval_f1": 0.8525433071972798, | |
| "eval_loss": 0.6005085706710815, | |
| "eval_precision": 0.8520647352840229, | |
| "eval_recall": 0.8556933483652762, | |
| "eval_runtime": 14.1004, | |
| "eval_samples_per_second": 125.812, | |
| "eval_steps_per_second": 1.986, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 8.661887694145759e-06, | |
| "loss": 0.2567, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.2517, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 25.44, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 0.2545, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.2799, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 7.467144563918758e-06, | |
| "loss": 0.2477, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.2608, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8635851183765502, | |
| "eval_f1": 0.8612168475515003, | |
| "eval_loss": 0.5915827751159668, | |
| "eval_precision": 0.8606118358536786, | |
| "eval_recall": 0.8635851183765502, | |
| "eval_runtime": 13.8009, | |
| "eval_samples_per_second": 128.542, | |
| "eval_steps_per_second": 2.029, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 26.08, | |
| "learning_rate": 6.869772998805258e-06, | |
| "loss": 0.2683, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.2764, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 6.2724014336917564e-06, | |
| "loss": 0.262, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.2467, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 5.675029868578255e-06, | |
| "loss": 0.2685, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.2625, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.8568207440811725, | |
| "eval_f1": 0.855163477321066, | |
| "eval_loss": 0.5932098627090454, | |
| "eval_precision": 0.8551452974235462, | |
| "eval_recall": 0.8568207440811725, | |
| "eval_runtime": 14.3602, | |
| "eval_samples_per_second": 123.536, | |
| "eval_steps_per_second": 1.95, | |
| "step": 1687 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 5.077658303464755e-06, | |
| "loss": 0.2518, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.2436, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 4.4802867383512545e-06, | |
| "loss": 0.2776, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.2489, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 3.882915173237754e-06, | |
| "loss": 0.226, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.2488, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 3.2855436081242537e-06, | |
| "loss": 0.2759, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8568207440811725, | |
| "eval_f1": 0.8545559848199051, | |
| "eval_loss": 0.6276565194129944, | |
| "eval_precision": 0.8556634541090311, | |
| "eval_recall": 0.8568207440811725, | |
| "eval_runtime": 14.228, | |
| "eval_samples_per_second": 124.684, | |
| "eval_steps_per_second": 1.968, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.2582, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 0.2613, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.2427, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 2.090800477897252e-06, | |
| "loss": 0.2345, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.2459, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 1.4934289127837516e-06, | |
| "loss": 0.2483, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.863021420518602, | |
| "eval_f1": 0.8608362481532486, | |
| "eval_loss": 0.6054866909980774, | |
| "eval_precision": 0.8606794902736699, | |
| "eval_recall": 0.863021420518602, | |
| "eval_runtime": 14.537, | |
| "eval_samples_per_second": 122.034, | |
| "eval_steps_per_second": 1.926, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.2519, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 8.960573476702509e-07, | |
| "loss": 0.2392, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.23, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 2.9868578255675034e-07, | |
| "loss": 0.2427, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.2554, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.8652762119503946, | |
| "eval_f1": 0.863267769226329, | |
| "eval_loss": 0.6137780547142029, | |
| "eval_precision": 0.8633338077075188, | |
| "eval_recall": 0.8652762119503946, | |
| "eval_runtime": 14.2881, | |
| "eval_samples_per_second": 124.159, | |
| "eval_steps_per_second": 1.96, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 1860, | |
| "total_flos": 4.870114457320843e+19, | |
| "train_loss": 0.4489922520934895, | |
| "train_runtime": 8242.9199, | |
| "train_samples_per_second": 58.093, | |
| "train_steps_per_second": 0.226 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 4.870114457320843e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |