| { | |
| "best_metric": 0.8652849740932642, | |
| "best_model_checkpoint": "./vit-base-skin/checkpoint-3500", | |
| "epoch": 6.0, | |
| "global_step": 3756, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001994675186368477, | |
| "loss": 1.3237, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019893503727369543, | |
| "loss": 1.0905, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019840255591054313, | |
| "loss": 0.8815, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019787007454739086, | |
| "loss": 1.037, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019733759318423856, | |
| "loss": 0.8188, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019680511182108628, | |
| "loss": 0.8761, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019627263045793398, | |
| "loss": 0.8691, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019574014909478168, | |
| "loss": 0.8463, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001952076677316294, | |
| "loss": 0.9363, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001946751863684771, | |
| "loss": 0.7904, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.7772020725388601, | |
| "eval_f1": 0.737244188762286, | |
| "eval_loss": 0.7231084704399109, | |
| "eval_precision": 0.7396732872769142, | |
| "eval_recall": 0.7772020725388601, | |
| "eval_runtime": 1.3029, | |
| "eval_samples_per_second": 148.135, | |
| "eval_steps_per_second": 19.188, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00019414270500532483, | |
| "loss": 0.8837, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00019361022364217253, | |
| "loss": 0.7978, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00019307774227902025, | |
| "loss": 0.6996, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00019254526091586795, | |
| "loss": 0.6961, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00019201277955271565, | |
| "loss": 0.867, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00019148029818956338, | |
| "loss": 0.8337, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00019094781682641108, | |
| "loss": 0.7045, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0001904153354632588, | |
| "loss": 0.8221, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001898828541001065, | |
| "loss": 0.6349, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00018935037273695422, | |
| "loss": 0.7746, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.7668393782383419, | |
| "eval_f1": 0.7146777529746666, | |
| "eval_loss": 0.6371975541114807, | |
| "eval_precision": 0.7457832653511188, | |
| "eval_recall": 0.7668393782383419, | |
| "eval_runtime": 1.3304, | |
| "eval_samples_per_second": 145.065, | |
| "eval_steps_per_second": 18.791, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00018881789137380192, | |
| "loss": 0.7965, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00018828541001064962, | |
| "loss": 0.7181, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00018775292864749735, | |
| "loss": 0.6919, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00018722044728434505, | |
| "loss": 0.7025, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018668796592119277, | |
| "loss": 0.6229, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00018615548455804047, | |
| "loss": 0.7728, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001856230031948882, | |
| "loss": 0.761, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001850905218317359, | |
| "loss": 0.8128, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001845580404685836, | |
| "loss": 0.7274, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00018402555910543132, | |
| "loss": 0.611, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.7409326424870466, | |
| "eval_f1": 0.6929874697608479, | |
| "eval_loss": 0.6454838514328003, | |
| "eval_precision": 0.7664604070267819, | |
| "eval_recall": 0.7409326424870466, | |
| "eval_runtime": 1.4204, | |
| "eval_samples_per_second": 135.879, | |
| "eval_steps_per_second": 17.601, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00018349307774227902, | |
| "loss": 0.6157, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00018296059637912674, | |
| "loss": 0.5813, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00018242811501597444, | |
| "loss": 0.6457, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00018189563365282217, | |
| "loss": 0.7674, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00018136315228966987, | |
| "loss": 0.6878, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00018083067092651756, | |
| "loss": 0.6402, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0001802981895633653, | |
| "loss": 0.5979, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00017976570820021302, | |
| "loss": 0.6453, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00017923322683706071, | |
| "loss": 0.5258, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0001787007454739084, | |
| "loss": 0.8406, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_accuracy": 0.8031088082901554, | |
| "eval_f1": 0.809840159673701, | |
| "eval_loss": 0.6233395338058472, | |
| "eval_precision": 0.8432674450459283, | |
| "eval_recall": 0.8031088082901554, | |
| "eval_runtime": 1.4932, | |
| "eval_samples_per_second": 129.253, | |
| "eval_steps_per_second": 16.743, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00017816826411075614, | |
| "loss": 0.6445, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00017763578274760384, | |
| "loss": 0.6499, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00017710330138445154, | |
| "loss": 0.797, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00017657082002129926, | |
| "loss": 0.6823, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.000176038338658147, | |
| "loss": 0.6078, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.00017550585729499469, | |
| "loss": 0.5897, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0001749733759318424, | |
| "loss": 0.619, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0001744408945686901, | |
| "loss": 0.5443, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0001739084132055378, | |
| "loss": 0.7851, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0001733759318423855, | |
| "loss": 0.587, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_accuracy": 0.7512953367875648, | |
| "eval_f1": 0.7163091147160436, | |
| "eval_loss": 0.6027703285217285, | |
| "eval_precision": 0.7659052043186402, | |
| "eval_recall": 0.7512953367875648, | |
| "eval_runtime": 1.4769, | |
| "eval_samples_per_second": 130.678, | |
| "eval_steps_per_second": 16.927, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.00017284345047923323, | |
| "loss": 0.6187, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.00017231096911608096, | |
| "loss": 0.5544, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00017177848775292866, | |
| "loss": 0.5216, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.00017124600638977638, | |
| "loss": 0.6979, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00017071352502662408, | |
| "loss": 0.6383, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00017018104366347178, | |
| "loss": 0.5769, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.00016964856230031948, | |
| "loss": 0.5587, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0001691160809371672, | |
| "loss": 0.47, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00016858359957401493, | |
| "loss": 0.5475, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00016805111821086263, | |
| "loss": 0.5532, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_accuracy": 0.8290155440414507, | |
| "eval_f1": 0.8089895755126505, | |
| "eval_loss": 0.46891143918037415, | |
| "eval_precision": 0.8376552906269454, | |
| "eval_recall": 0.8290155440414507, | |
| "eval_runtime": 1.408, | |
| "eval_samples_per_second": 137.071, | |
| "eval_steps_per_second": 17.755, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.00016751863684771035, | |
| "loss": 0.6815, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00016698615548455805, | |
| "loss": 0.547, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00016645367412140575, | |
| "loss": 0.543, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 0.00016592119275825345, | |
| "loss": 0.3827, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00016538871139510118, | |
| "loss": 0.471, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0001648562300319489, | |
| "loss": 0.5505, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0001643237486687966, | |
| "loss": 0.5783, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00016379126730564433, | |
| "loss": 0.4842, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00016325878594249202, | |
| "loss": 0.4051, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00016272630457933972, | |
| "loss": 0.4326, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_accuracy": 0.8290155440414507, | |
| "eval_f1": 0.8199745547073791, | |
| "eval_loss": 0.49676093459129333, | |
| "eval_precision": 0.8368314970525431, | |
| "eval_recall": 0.8290155440414507, | |
| "eval_runtime": 1.5106, | |
| "eval_samples_per_second": 127.764, | |
| "eval_steps_per_second": 16.55, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.00016219382321618745, | |
| "loss": 0.5959, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00016166134185303515, | |
| "loss": 0.4156, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.00016112886048988287, | |
| "loss": 0.4439, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00016059637912673057, | |
| "loss": 0.425, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0001600638977635783, | |
| "loss": 0.4345, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.000159531416400426, | |
| "loss": 0.5209, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.0001589989350372737, | |
| "loss": 0.3988, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00015846645367412142, | |
| "loss": 0.5338, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00015793397231096912, | |
| "loss": 0.4767, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00015740149094781684, | |
| "loss": 0.4713, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_accuracy": 0.8186528497409327, | |
| "eval_f1": 0.8222086183111903, | |
| "eval_loss": 0.49726101756095886, | |
| "eval_precision": 0.8435568089332187, | |
| "eval_recall": 0.8186528497409327, | |
| "eval_runtime": 1.4952, | |
| "eval_samples_per_second": 129.081, | |
| "eval_steps_per_second": 16.72, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00015686900958466454, | |
| "loss": 0.48, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.00015633652822151227, | |
| "loss": 0.5152, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00015580404685835997, | |
| "loss": 0.3305, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00015527156549520767, | |
| "loss": 0.4994, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0001547390841320554, | |
| "loss": 0.4158, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.0001542066027689031, | |
| "loss": 0.6436, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.00015367412140575082, | |
| "loss": 0.619, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 0.00015314164004259851, | |
| "loss": 0.3574, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00015260915867944624, | |
| "loss": 0.4911, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.00015207667731629394, | |
| "loss": 0.4333, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_accuracy": 0.772020725388601, | |
| "eval_f1": 0.7614727244003432, | |
| "eval_loss": 0.5500032901763916, | |
| "eval_precision": 0.770546254326385, | |
| "eval_recall": 0.772020725388601, | |
| "eval_runtime": 1.4669, | |
| "eval_samples_per_second": 131.571, | |
| "eval_steps_per_second": 17.043, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00015154419595314164, | |
| "loss": 0.4749, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.00015101171458998936, | |
| "loss": 0.5035, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 0.00015047923322683706, | |
| "loss": 0.4334, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0001499467518636848, | |
| "loss": 0.6071, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.00014941427050053249, | |
| "loss": 0.5453, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.0001488817891373802, | |
| "loss": 0.456, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.0001483493077742279, | |
| "loss": 0.4823, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.0001478168264110756, | |
| "loss": 0.4462, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00014728434504792333, | |
| "loss": 0.5317, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00014675186368477103, | |
| "loss": 0.441, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.8238341968911918, | |
| "eval_f1": 0.8397524744696683, | |
| "eval_loss": 0.5518435835838318, | |
| "eval_precision": 0.8773677045709595, | |
| "eval_recall": 0.8238341968911918, | |
| "eval_runtime": 1.389, | |
| "eval_samples_per_second": 138.947, | |
| "eval_steps_per_second": 17.998, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00014621938232161876, | |
| "loss": 0.4289, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00014568690095846646, | |
| "loss": 0.4198, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00014515441959531418, | |
| "loss": 0.4176, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00014462193823216188, | |
| "loss": 0.5608, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00014408945686900958, | |
| "loss": 0.4953, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.0001435569755058573, | |
| "loss": 0.4704, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.000143024494142705, | |
| "loss": 0.4316, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00014249201277955273, | |
| "loss": 0.4783, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00014195953141640043, | |
| "loss": 0.469, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00014142705005324815, | |
| "loss": 0.4172, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_accuracy": 0.8031088082901554, | |
| "eval_f1": 0.7801725165008492, | |
| "eval_loss": 0.5608089566230774, | |
| "eval_precision": 0.8260356195955431, | |
| "eval_recall": 0.8031088082901554, | |
| "eval_runtime": 1.4534, | |
| "eval_samples_per_second": 132.794, | |
| "eval_steps_per_second": 17.201, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 0.00014089456869009585, | |
| "loss": 0.6351, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00014036208732694355, | |
| "loss": 0.4055, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00013982960596379128, | |
| "loss": 0.2751, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.000139297124600639, | |
| "loss": 0.3695, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.0001387646432374867, | |
| "loss": 0.5388, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.0001382321618743344, | |
| "loss": 0.4343, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00013769968051118212, | |
| "loss": 0.3776, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00013716719914802982, | |
| "loss": 0.614, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00013663471778487752, | |
| "loss": 0.3002, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00013610223642172525, | |
| "loss": 0.4062, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_accuracy": 0.8290155440414507, | |
| "eval_f1": 0.8311939888539486, | |
| "eval_loss": 0.4730203151702881, | |
| "eval_precision": 0.8704151262352084, | |
| "eval_recall": 0.8290155440414507, | |
| "eval_runtime": 1.3874, | |
| "eval_samples_per_second": 139.113, | |
| "eval_steps_per_second": 18.02, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00013556975505857297, | |
| "loss": 0.4636, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00013503727369542067, | |
| "loss": 0.2477, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00013450479233226837, | |
| "loss": 0.3576, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0001339723109691161, | |
| "loss": 0.4479, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001334398296059638, | |
| "loss": 0.5046, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.0001329073482428115, | |
| "loss": 0.3975, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00013237486687965922, | |
| "loss": 0.2875, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00013184238551650694, | |
| "loss": 0.2943, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00013130990415335464, | |
| "loss": 0.2591, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.00013077742279020234, | |
| "loss": 0.271, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_accuracy": 0.8031088082901554, | |
| "eval_f1": 0.8018000867897372, | |
| "eval_loss": 0.48927029967308044, | |
| "eval_precision": 0.8164087291615287, | |
| "eval_recall": 0.8031088082901554, | |
| "eval_runtime": 1.4641, | |
| "eval_samples_per_second": 131.825, | |
| "eval_steps_per_second": 17.076, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.00013024494142705007, | |
| "loss": 0.2387, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00012971246006389777, | |
| "loss": 0.2448, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "learning_rate": 0.00012917997870074546, | |
| "loss": 0.2278, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.0001286474973375932, | |
| "loss": 0.346, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 0.00012811501597444092, | |
| "loss": 0.3535, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.00012758253461128861, | |
| "loss": 0.3082, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.0001270500532481363, | |
| "loss": 0.228, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.00012651757188498404, | |
| "loss": 0.3094, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 0.00012598509052183174, | |
| "loss": 0.3428, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.00012545260915867944, | |
| "loss": 0.2294, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.8341968911917098, | |
| "eval_f1": 0.8368989393943828, | |
| "eval_loss": 0.4859079420566559, | |
| "eval_precision": 0.8441898712034582, | |
| "eval_recall": 0.8341968911917098, | |
| "eval_runtime": 1.4937, | |
| "eval_samples_per_second": 129.212, | |
| "eval_steps_per_second": 16.737, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00012492012779552716, | |
| "loss": 0.2736, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0001243876464323749, | |
| "loss": 0.3359, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.00012385516506922259, | |
| "loss": 0.2467, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00012332268370607028, | |
| "loss": 0.2545, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.000122790202342918, | |
| "loss": 0.3198, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0001222577209797657, | |
| "loss": 0.2881, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.00012172523961661342, | |
| "loss": 0.2112, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00012119275825346112, | |
| "loss": 0.3612, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00012066027689030886, | |
| "loss": 0.2148, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00012012779552715656, | |
| "loss": 0.2687, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_accuracy": 0.8393782383419689, | |
| "eval_f1": 0.8391251786538111, | |
| "eval_loss": 0.48051658272743225, | |
| "eval_precision": 0.8424139753886638, | |
| "eval_recall": 0.8393782383419689, | |
| "eval_runtime": 1.502, | |
| "eval_samples_per_second": 128.491, | |
| "eval_steps_per_second": 16.644, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.00011959531416400427, | |
| "loss": 0.2028, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.00011906283280085198, | |
| "loss": 0.2303, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 0.00011853035143769968, | |
| "loss": 0.2188, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.00011799787007454739, | |
| "loss": 0.2845, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.00011746538871139509, | |
| "loss": 0.2516, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00011693290734824283, | |
| "loss": 0.1845, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.00011640042598509053, | |
| "loss": 0.2353, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 0.00011586794462193824, | |
| "loss": 0.2546, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 0.00011533546325878595, | |
| "loss": 0.2683, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.00011480298189563365, | |
| "loss": 0.2348, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_accuracy": 0.8497409326424871, | |
| "eval_f1": 0.8522240003469944, | |
| "eval_loss": 0.4667459726333618, | |
| "eval_precision": 0.856714706608032, | |
| "eval_recall": 0.8497409326424871, | |
| "eval_runtime": 1.5349, | |
| "eval_samples_per_second": 125.744, | |
| "eval_steps_per_second": 16.288, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 0.00011427050053248136, | |
| "loss": 0.1582, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 0.00011373801916932908, | |
| "loss": 0.3019, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.0001132055378061768, | |
| "loss": 0.3721, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.0001126730564430245, | |
| "loss": 0.1819, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.00011214057507987221, | |
| "loss": 0.3548, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 0.00011160809371671992, | |
| "loss": 0.2736, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.00011107561235356762, | |
| "loss": 0.4458, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.00011054313099041533, | |
| "loss": 0.2138, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 0.00011001064962726305, | |
| "loss": 0.3914, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 0.00010947816826411077, | |
| "loss": 0.2038, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.8134715025906736, | |
| "eval_f1": 0.8148427277960955, | |
| "eval_loss": 0.5050258636474609, | |
| "eval_precision": 0.8221690802001682, | |
| "eval_recall": 0.8134715025906736, | |
| "eval_runtime": 1.4958, | |
| "eval_samples_per_second": 129.031, | |
| "eval_steps_per_second": 16.714, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.00010894568690095847, | |
| "loss": 0.3304, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.00010841320553780618, | |
| "loss": 0.1844, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 0.0001078807241746539, | |
| "loss": 0.188, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.0001073482428115016, | |
| "loss": 0.2894, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0001068157614483493, | |
| "loss": 0.2851, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.00010628328008519702, | |
| "loss": 0.247, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.00010575079872204474, | |
| "loss": 0.1691, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 0.00010521831735889244, | |
| "loss": 0.2618, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00010468583599574015, | |
| "loss": 0.2194, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.00010415335463258787, | |
| "loss": 0.2102, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "eval_accuracy": 0.8497409326424871, | |
| "eval_f1": 0.8527187480941545, | |
| "eval_loss": 0.4730379283428192, | |
| "eval_precision": 0.8695213624394802, | |
| "eval_recall": 0.8497409326424871, | |
| "eval_runtime": 1.4423, | |
| "eval_samples_per_second": 133.818, | |
| "eval_steps_per_second": 17.334, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 0.00010362087326943557, | |
| "loss": 0.2967, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.00010308839190628328, | |
| "loss": 0.3537, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.000102555910543131, | |
| "loss": 0.1035, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00010202342917997871, | |
| "loss": 0.1721, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.00010149094781682643, | |
| "loss": 0.1508, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 0.00010095846645367413, | |
| "loss": 0.3197, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 0.00010042598509052184, | |
| "loss": 0.325, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.989350372736954e-05, | |
| "loss": 0.1793, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.936102236421726e-05, | |
| "loss": 0.1501, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 9.882854100106496e-05, | |
| "loss": 0.0978, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_accuracy": 0.844559585492228, | |
| "eval_f1": 0.8449770937974714, | |
| "eval_loss": 0.46732112765312195, | |
| "eval_precision": 0.8508216136195411, | |
| "eval_recall": 0.844559585492228, | |
| "eval_runtime": 1.5128, | |
| "eval_samples_per_second": 127.581, | |
| "eval_steps_per_second": 16.526, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 9.829605963791267e-05, | |
| "loss": 0.0876, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 9.77635782747604e-05, | |
| "loss": 0.1038, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 9.72310969116081e-05, | |
| "loss": 0.1503, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 9.669861554845581e-05, | |
| "loss": 0.0927, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 9.616613418530351e-05, | |
| "loss": 0.1496, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 9.563365282215123e-05, | |
| "loss": 0.1248, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 9.510117145899895e-05, | |
| "loss": 0.1006, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 9.456869009584664e-05, | |
| "loss": 0.0928, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 9.403620873269437e-05, | |
| "loss": 0.0704, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 9.350372736954207e-05, | |
| "loss": 0.104, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.19, | |
| "eval_accuracy": 0.8341968911917098, | |
| "eval_f1": 0.8273862635503388, | |
| "eval_loss": 0.5348378419876099, | |
| "eval_precision": 0.8312724354624778, | |
| "eval_recall": 0.8341968911917098, | |
| "eval_runtime": 1.4975, | |
| "eval_samples_per_second": 128.885, | |
| "eval_steps_per_second": 16.695, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 9.297124600638978e-05, | |
| "loss": 0.0438, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 9.243876464323749e-05, | |
| "loss": 0.0651, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 9.19062832800852e-05, | |
| "loss": 0.1215, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 9.137380191693292e-05, | |
| "loss": 0.1289, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 9.084132055378062e-05, | |
| "loss": 0.0977, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 9.030883919062834e-05, | |
| "loss": 0.1273, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 8.977635782747604e-05, | |
| "loss": 0.0985, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 8.924387646432375e-05, | |
| "loss": 0.1005, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 3.34, | |
| "learning_rate": 8.871139510117146e-05, | |
| "loss": 0.1272, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 8.817891373801918e-05, | |
| "loss": 0.0562, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "eval_accuracy": 0.8341968911917098, | |
| "eval_f1": 0.8264024083229033, | |
| "eval_loss": 0.5747538208961487, | |
| "eval_precision": 0.8298787608638384, | |
| "eval_recall": 0.8341968911917098, | |
| "eval_runtime": 1.7111, | |
| "eval_samples_per_second": 112.791, | |
| "eval_steps_per_second": 14.61, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 8.764643237486689e-05, | |
| "loss": 0.1713, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 8.711395101171459e-05, | |
| "loss": 0.1078, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 8.658146964856231e-05, | |
| "loss": 0.079, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 8.610223642172525e-05, | |
| "loss": 0.1117, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 8.556975505857295e-05, | |
| "loss": 0.1554, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 8.503727369542066e-05, | |
| "loss": 0.0705, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 8.450479233226837e-05, | |
| "loss": 0.0611, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 8.397231096911609e-05, | |
| "loss": 0.0309, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 8.34398296059638e-05, | |
| "loss": 0.0446, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 8.29073482428115e-05, | |
| "loss": 0.1443, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "eval_accuracy": 0.844559585492228, | |
| "eval_f1": 0.8432447144276622, | |
| "eval_loss": 0.5903483033180237, | |
| "eval_precision": 0.8448140460575695, | |
| "eval_recall": 0.844559585492228, | |
| "eval_runtime": 1.4004, | |
| "eval_samples_per_second": 137.819, | |
| "eval_steps_per_second": 17.852, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 8.237486687965922e-05, | |
| "loss": 0.1415, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 8.184238551650692e-05, | |
| "loss": 0.0694, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 8.130990415335463e-05, | |
| "loss": 0.0885, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 8.077742279020235e-05, | |
| "loss": 0.1913, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 8.024494142705006e-05, | |
| "loss": 0.1442, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 7.971246006389777e-05, | |
| "loss": 0.0892, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 7.917997870074548e-05, | |
| "loss": 0.0599, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 7.86474973375932e-05, | |
| "loss": 0.1186, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 7.811501597444089e-05, | |
| "loss": 0.0893, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 7.75825346112886e-05, | |
| "loss": 0.1245, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "eval_accuracy": 0.8601036269430051, | |
| "eval_f1": 0.8627294402139966, | |
| "eval_loss": 0.5772939920425415, | |
| "eval_precision": 0.8778706068043401, | |
| "eval_recall": 0.8601036269430051, | |
| "eval_runtime": 1.4549, | |
| "eval_samples_per_second": 132.651, | |
| "eval_steps_per_second": 17.183, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 7.705005324813632e-05, | |
| "loss": 0.0712, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 7.651757188498403e-05, | |
| "loss": 0.1629, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "learning_rate": 7.598509052183174e-05, | |
| "loss": 0.0709, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 7.545260915867945e-05, | |
| "loss": 0.0228, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 7.492012779552717e-05, | |
| "loss": 0.051, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 7.438764643237486e-05, | |
| "loss": 0.0481, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 7.385516506922258e-05, | |
| "loss": 0.1078, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 7.332268370607029e-05, | |
| "loss": 0.085, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 7.2790202342918e-05, | |
| "loss": 0.2343, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 7.225772097976571e-05, | |
| "loss": 0.081, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_accuracy": 0.8393782383419689, | |
| "eval_f1": 0.8423708824581471, | |
| "eval_loss": 0.6190107464790344, | |
| "eval_precision": 0.8486741846997866, | |
| "eval_recall": 0.8393782383419689, | |
| "eval_runtime": 1.4536, | |
| "eval_samples_per_second": 132.77, | |
| "eval_steps_per_second": 17.198, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 7.172523961661343e-05, | |
| "loss": 0.0631, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 7.119275825346114e-05, | |
| "loss": 0.0902, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 7.066027689030884e-05, | |
| "loss": 0.1689, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 7.012779552715655e-05, | |
| "loss": 0.0719, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 6.959531416400426e-05, | |
| "loss": 0.0705, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 6.906283280085197e-05, | |
| "loss": 0.0773, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 6.853035143769968e-05, | |
| "loss": 0.12, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 6.79978700745474e-05, | |
| "loss": 0.0519, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 6.746538871139511e-05, | |
| "loss": 0.0805, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 6.693290734824281e-05, | |
| "loss": 0.1314, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_accuracy": 0.8549222797927462, | |
| "eval_f1": 0.8508924450616168, | |
| "eval_loss": 0.6077536940574646, | |
| "eval_precision": 0.8506327275706129, | |
| "eval_recall": 0.8549222797927462, | |
| "eval_runtime": 1.4717, | |
| "eval_samples_per_second": 131.139, | |
| "eval_steps_per_second": 16.987, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 6.640042598509052e-05, | |
| "loss": 0.1132, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 6.586794462193823e-05, | |
| "loss": 0.0444, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 6.533546325878594e-05, | |
| "loss": 0.0609, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 6.480298189563366e-05, | |
| "loss": 0.0168, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 6.427050053248137e-05, | |
| "loss": 0.1162, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 6.379126730564431e-05, | |
| "loss": 0.0565, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 6.325878594249202e-05, | |
| "loss": 0.0131, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 6.272630457933972e-05, | |
| "loss": 0.0406, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 6.219382321618744e-05, | |
| "loss": 0.0069, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 6.166134185303514e-05, | |
| "loss": 0.0415, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_accuracy": 0.8290155440414507, | |
| "eval_f1": 0.8312353272443574, | |
| "eval_loss": 0.7038956880569458, | |
| "eval_precision": 0.8357539130317297, | |
| "eval_recall": 0.8290155440414507, | |
| "eval_runtime": 1.5062, | |
| "eval_samples_per_second": 128.136, | |
| "eval_steps_per_second": 16.598, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 6.112886048988285e-05, | |
| "loss": 0.0425, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 6.059637912673056e-05, | |
| "loss": 0.0387, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 6.006389776357828e-05, | |
| "loss": 0.0077, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 5.953141640042599e-05, | |
| "loss": 0.013, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 5.8998935037273696e-05, | |
| "loss": 0.0061, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 5.8466453674121415e-05, | |
| "loss": 0.0082, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 5.793397231096912e-05, | |
| "loss": 0.0076, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 5.7401490947816826e-05, | |
| "loss": 0.0089, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 5.686900958466454e-05, | |
| "loss": 0.0176, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 5.633652822151225e-05, | |
| "loss": 0.0402, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "eval_accuracy": 0.8238341968911918, | |
| "eval_f1": 0.8166115071246114, | |
| "eval_loss": 0.7476995587348938, | |
| "eval_precision": 0.8179313661993294, | |
| "eval_recall": 0.8238341968911918, | |
| "eval_runtime": 1.3974, | |
| "eval_samples_per_second": 138.114, | |
| "eval_steps_per_second": 17.89, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 5.580404685835996e-05, | |
| "loss": 0.0084, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 5.527156549520767e-05, | |
| "loss": 0.0111, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 5.4739084132055386e-05, | |
| "loss": 0.0706, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 5.420660276890309e-05, | |
| "loss": 0.0167, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 4.39, | |
| "learning_rate": 5.36741214057508e-05, | |
| "loss": 0.0196, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 5.314164004259851e-05, | |
| "loss": 0.0153, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 5.260915867944622e-05, | |
| "loss": 0.016, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 5.207667731629393e-05, | |
| "loss": 0.0669, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 5.154419595314164e-05, | |
| "loss": 0.0054, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 5.101171458998936e-05, | |
| "loss": 0.0045, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_accuracy": 0.8497409326424871, | |
| "eval_f1": 0.8493288007968494, | |
| "eval_loss": 0.7207270860671997, | |
| "eval_precision": 0.8538791928006545, | |
| "eval_recall": 0.8497409326424871, | |
| "eval_runtime": 1.4883, | |
| "eval_samples_per_second": 129.674, | |
| "eval_steps_per_second": 16.797, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 5.047923322683706e-05, | |
| "loss": 0.061, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 4.994675186368477e-05, | |
| "loss": 0.0181, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 4.941427050053248e-05, | |
| "loss": 0.0474, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "learning_rate": 4.88817891373802e-05, | |
| "loss": 0.0767, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 4.8349307774227905e-05, | |
| "loss": 0.0269, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 4.781682641107562e-05, | |
| "loss": 0.0267, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 4.728434504792332e-05, | |
| "loss": 0.0074, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 4.6751863684771034e-05, | |
| "loss": 0.0488, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 4.6219382321618746e-05, | |
| "loss": 0.051, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 4.568690095846646e-05, | |
| "loss": 0.0608, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "eval_accuracy": 0.8341968911917098, | |
| "eval_f1": 0.8369927904619928, | |
| "eval_loss": 0.7339458465576172, | |
| "eval_precision": 0.8468513424743631, | |
| "eval_recall": 0.8341968911917098, | |
| "eval_runtime": 1.4899, | |
| "eval_samples_per_second": 129.54, | |
| "eval_steps_per_second": 16.78, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.65, | |
| "learning_rate": 4.515441959531417e-05, | |
| "loss": 0.0154, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 4.4621938232161876e-05, | |
| "loss": 0.0081, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 4.408945686900959e-05, | |
| "loss": 0.0814, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 4.355697550585729e-05, | |
| "loss": 0.0141, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 4.71, | |
| "learning_rate": 4.3024494142705005e-05, | |
| "loss": 0.078, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 4.73, | |
| "learning_rate": 4.249201277955272e-05, | |
| "loss": 0.0039, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 4.195953141640043e-05, | |
| "loss": 0.0707, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 4.76, | |
| "learning_rate": 4.142705005324814e-05, | |
| "loss": 0.0602, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 4.089456869009585e-05, | |
| "loss": 0.0489, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 4.036208732694356e-05, | |
| "loss": 0.0168, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "eval_accuracy": 0.8290155440414507, | |
| "eval_f1": 0.8387750582593335, | |
| "eval_loss": 0.7893615961074829, | |
| "eval_precision": 0.853923494467536, | |
| "eval_recall": 0.8290155440414507, | |
| "eval_runtime": 1.3998, | |
| "eval_samples_per_second": 137.877, | |
| "eval_steps_per_second": 17.86, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 3.9829605963791265e-05, | |
| "loss": 0.0101, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "learning_rate": 3.929712460063898e-05, | |
| "loss": 0.0077, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 3.876464323748669e-05, | |
| "loss": 0.0081, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "learning_rate": 3.82321618743344e-05, | |
| "loss": 0.007, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 3.769968051118211e-05, | |
| "loss": 0.0036, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 3.716719914802982e-05, | |
| "loss": 0.0039, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 3.663471778487753e-05, | |
| "loss": 0.0169, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 3.610223642172524e-05, | |
| "loss": 0.0239, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 3.556975505857295e-05, | |
| "loss": 0.0081, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 3.503727369542067e-05, | |
| "loss": 0.0042, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_accuracy": 0.8601036269430051, | |
| "eval_f1": 0.8628268915025089, | |
| "eval_loss": 0.7267940044403076, | |
| "eval_precision": 0.8680958173098623, | |
| "eval_recall": 0.8601036269430051, | |
| "eval_runtime": 1.5061, | |
| "eval_samples_per_second": 128.144, | |
| "eval_steps_per_second": 16.599, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 3.450479233226837e-05, | |
| "loss": 0.0249, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 3.3972310969116084e-05, | |
| "loss": 0.0038, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.343982960596379e-05, | |
| "loss": 0.0081, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 3.29073482428115e-05, | |
| "loss": 0.0367, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 3.2374866879659214e-05, | |
| "loss": 0.0074, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 3.1842385516506926e-05, | |
| "loss": 0.0031, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 5.06, | |
| "learning_rate": 3.130990415335464e-05, | |
| "loss": 0.0032, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 3.0777422790202344e-05, | |
| "loss": 0.004, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 3.0244941427050056e-05, | |
| "loss": 0.003, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 2.971246006389776e-05, | |
| "loss": 0.0149, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "eval_accuracy": 0.8601036269430051, | |
| "eval_f1": 0.8577106091539843, | |
| "eval_loss": 0.7144800424575806, | |
| "eval_precision": 0.8599681272322061, | |
| "eval_recall": 0.8601036269430051, | |
| "eval_runtime": 1.4043, | |
| "eval_samples_per_second": 137.44, | |
| "eval_steps_per_second": 17.803, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 2.9179978700745477e-05, | |
| "loss": 0.0029, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 2.864749733759319e-05, | |
| "loss": 0.0029, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 2.8115015974440894e-05, | |
| "loss": 0.0046, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 2.7582534611288606e-05, | |
| "loss": 0.028, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 5.19, | |
| "learning_rate": 2.7050053248136315e-05, | |
| "loss": 0.0033, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 5.21, | |
| "learning_rate": 2.6517571884984027e-05, | |
| "loss": 0.0029, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 2.598509052183174e-05, | |
| "loss": 0.0099, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 2.5452609158679448e-05, | |
| "loss": 0.0058, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 2.4920127795527157e-05, | |
| "loss": 0.0027, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 2.438764643237487e-05, | |
| "loss": 0.0074, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "eval_accuracy": 0.8341968911917098, | |
| "eval_f1": 0.8354284290653713, | |
| "eval_loss": 0.7423849105834961, | |
| "eval_precision": 0.8380347744168425, | |
| "eval_recall": 0.8341968911917098, | |
| "eval_runtime": 1.4364, | |
| "eval_samples_per_second": 134.36, | |
| "eval_steps_per_second": 17.404, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 2.3855165069222578e-05, | |
| "loss": 0.0032, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 2.332268370607029e-05, | |
| "loss": 0.0051, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 2.2790202342918e-05, | |
| "loss": 0.0027, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 2.2257720979765707e-05, | |
| "loss": 0.0031, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 2.172523961661342e-05, | |
| "loss": 0.0034, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 2.1192758253461128e-05, | |
| "loss": 0.0026, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 2.066027689030884e-05, | |
| "loss": 0.0031, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 2.0127795527156552e-05, | |
| "loss": 0.0099, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 5.42, | |
| "learning_rate": 1.959531416400426e-05, | |
| "loss": 0.0031, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 1.906283280085197e-05, | |
| "loss": 0.0029, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "eval_accuracy": 0.8652849740932642, | |
| "eval_f1": 0.8648698461235622, | |
| "eval_loss": 0.7122710943222046, | |
| "eval_precision": 0.8686330674606623, | |
| "eval_recall": 0.8652849740932642, | |
| "eval_runtime": 1.4134, | |
| "eval_samples_per_second": 136.551, | |
| "eval_steps_per_second": 17.688, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 1.8530351437699682e-05, | |
| "loss": 0.0031, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "learning_rate": 1.799787007454739e-05, | |
| "loss": 0.0028, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 1.7465388711395103e-05, | |
| "loss": 0.0031, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 1.693290734824281e-05, | |
| "loss": 0.0028, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 5.51, | |
| "learning_rate": 1.6400425985090524e-05, | |
| "loss": 0.0033, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 1.5867944621938232e-05, | |
| "loss": 0.0026, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 1.533546325878594e-05, | |
| "loss": 0.0026, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 1.4802981895633653e-05, | |
| "loss": 0.0031, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 1.4270500532481365e-05, | |
| "loss": 0.0038, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "learning_rate": 1.3738019169329076e-05, | |
| "loss": 0.0123, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.59, | |
| "eval_accuracy": 0.8652849740932642, | |
| "eval_f1": 0.8632695552980046, | |
| "eval_loss": 0.7052408456802368, | |
| "eval_precision": 0.8632473160306697, | |
| "eval_recall": 0.8652849740932642, | |
| "eval_runtime": 1.5567, | |
| "eval_samples_per_second": 123.983, | |
| "eval_steps_per_second": 16.06, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 1.3205537806176784e-05, | |
| "loss": 0.0026, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 1.2673056443024495e-05, | |
| "loss": 0.0065, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "learning_rate": 1.2140575079872205e-05, | |
| "loss": 0.0023, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 1.1608093716719916e-05, | |
| "loss": 0.0025, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 1.1075612353567626e-05, | |
| "loss": 0.0133, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 1.0543130990415335e-05, | |
| "loss": 0.0025, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 1.0010649627263047e-05, | |
| "loss": 0.0025, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 9.478168264110757e-06, | |
| "loss": 0.0237, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 8.945686900958466e-06, | |
| "loss": 0.0026, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 8.413205537806178e-06, | |
| "loss": 0.0028, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "eval_accuracy": 0.8601036269430051, | |
| "eval_f1": 0.8589898846254087, | |
| "eval_loss": 0.7026710510253906, | |
| "eval_precision": 0.8600505798174194, | |
| "eval_recall": 0.8601036269430051, | |
| "eval_runtime": 1.4657, | |
| "eval_samples_per_second": 131.676, | |
| "eval_steps_per_second": 17.057, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 7.880724174653887e-06, | |
| "loss": 0.0026, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 7.3482428115015974e-06, | |
| "loss": 0.0022, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 6.815761448349309e-06, | |
| "loss": 0.0047, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 5.81, | |
| "learning_rate": 6.283280085197018e-06, | |
| "loss": 0.0024, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 5.750798722044729e-06, | |
| "loss": 0.0023, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 5.85, | |
| "learning_rate": 5.218317358892439e-06, | |
| "loss": 0.0028, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 4.68583599574015e-06, | |
| "loss": 0.0023, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 4.153354632587859e-06, | |
| "loss": 0.0042, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 3.62087326943557e-06, | |
| "loss": 0.0025, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "learning_rate": 3.08839190628328e-06, | |
| "loss": 0.0029, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.91, | |
| "eval_accuracy": 0.8549222797927462, | |
| "eval_f1": 0.8533972524433742, | |
| "eval_loss": 0.7037147879600525, | |
| "eval_precision": 0.8535709697744556, | |
| "eval_recall": 0.8549222797927462, | |
| "eval_runtime": 1.4719, | |
| "eval_samples_per_second": 131.121, | |
| "eval_steps_per_second": 16.985, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 2.5559105431309904e-06, | |
| "loss": 0.0032, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 2.023429179978701e-06, | |
| "loss": 0.0024, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 1.490947816826411e-06, | |
| "loss": 0.0527, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 9.584664536741213e-07, | |
| "loss": 0.0026, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 4.259850905218318e-07, | |
| "loss": 0.0024, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 3756, | |
| "total_flos": 4.65670232933972e+18, | |
| "train_loss": 0.26311645210404205, | |
| "train_runtime": 1312.8124, | |
| "train_samples_per_second": 45.772, | |
| "train_steps_per_second": 2.861 | |
| } | |
| ], | |
| "max_steps": 3756, | |
| "num_train_epochs": 6, | |
| "total_flos": 4.65670232933972e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |