| { | |
| "best_metric": 0.904707233065442, | |
| "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-woody_LeftGR_130epochs/checkpoint-6222", | |
| "epoch": 129.99591836734695, | |
| "global_step": 7930, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 6.305170239596469e-07, | |
| "loss": 0.7257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.2610340479192938e-06, | |
| "loss": 0.7195, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.8915510718789408e-06, | |
| "loss": 0.7001, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.5220680958385876e-06, | |
| "loss": 0.6915, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.152585119798235e-06, | |
| "loss": 0.6757, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.7831021437578815e-06, | |
| "loss": 0.6614, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6521239954075775, | |
| "eval_loss": 0.6404483914375305, | |
| "eval_runtime": 419.2583, | |
| "eval_samples_per_second": 2.077, | |
| "eval_steps_per_second": 0.067, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.4136191677175285e-06, | |
| "loss": 0.6571, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 5.044136191677175e-06, | |
| "loss": 0.6242, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 5.6746532156368225e-06, | |
| "loss": 0.6067, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 6.30517023959647e-06, | |
| "loss": 0.6059, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 6.9356872635561165e-06, | |
| "loss": 0.5905, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 7.566204287515763e-06, | |
| "loss": 0.5982, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7106773823191733, | |
| "eval_loss": 0.5548045039176941, | |
| "eval_runtime": 21.0238, | |
| "eval_samples_per_second": 41.429, | |
| "eval_steps_per_second": 1.332, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.196721311475409e-06, | |
| "loss": 0.6426, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 8.827238335435057e-06, | |
| "loss": 0.585, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 9.457755359394704e-06, | |
| "loss": 0.5886, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 1.008827238335435e-05, | |
| "loss": 0.5685, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.0718789407313998e-05, | |
| "loss": 0.5956, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 1.1349306431273645e-05, | |
| "loss": 0.579, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7141216991963261, | |
| "eval_loss": 0.538981020450592, | |
| "eval_runtime": 21.2907, | |
| "eval_samples_per_second": 40.91, | |
| "eval_steps_per_second": 1.315, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 1.1979823455233292e-05, | |
| "loss": 0.574, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 1.261034047919294e-05, | |
| "loss": 0.5782, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1.3240857503152585e-05, | |
| "loss": 0.5671, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.3871374527112233e-05, | |
| "loss": 0.5721, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 1.4501891551071881e-05, | |
| "loss": 0.5534, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 1.5132408575031526e-05, | |
| "loss": 0.5621, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7623421354764638, | |
| "eval_loss": 0.49202749133110046, | |
| "eval_runtime": 21.3554, | |
| "eval_samples_per_second": 40.786, | |
| "eval_steps_per_second": 1.311, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 1.5762925598991173e-05, | |
| "loss": 0.5591, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 1.6393442622950818e-05, | |
| "loss": 0.566, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 1.7023959646910466e-05, | |
| "loss": 0.537, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 1.7654476670870114e-05, | |
| "loss": 0.5478, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 1.828499369482976e-05, | |
| "loss": 0.5641, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "learning_rate": 1.8915510718789407e-05, | |
| "loss": 0.5567, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7313432835820896, | |
| "eval_loss": 0.5375362038612366, | |
| "eval_runtime": 21.6742, | |
| "eval_samples_per_second": 40.186, | |
| "eval_steps_per_second": 1.292, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 5.08, | |
| "learning_rate": 1.9546027742749056e-05, | |
| "loss": 0.5461, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 2.01765447667087e-05, | |
| "loss": 0.5376, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 2.080706179066835e-05, | |
| "loss": 0.5692, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 2.1437578814627997e-05, | |
| "loss": 0.5479, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 2.2068095838587642e-05, | |
| "loss": 0.5691, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 2.269861286254729e-05, | |
| "loss": 0.5271, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7405281285878301, | |
| "eval_loss": 0.5541573762893677, | |
| "eval_runtime": 22.2243, | |
| "eval_samples_per_second": 39.191, | |
| "eval_steps_per_second": 1.26, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 2.332912988650694e-05, | |
| "loss": 0.5585, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 2.3959646910466583e-05, | |
| "loss": 0.535, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 2.459016393442623e-05, | |
| "loss": 0.5334, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 2.522068095838588e-05, | |
| "loss": 0.5422, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 2.5851197982345528e-05, | |
| "loss": 0.5291, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 2.648171500630517e-05, | |
| "loss": 0.5312, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7876004592422503, | |
| "eval_loss": 0.45729219913482666, | |
| "eval_runtime": 22.2359, | |
| "eval_samples_per_second": 39.171, | |
| "eval_steps_per_second": 1.259, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 2.7112232030264818e-05, | |
| "loss": 0.5656, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 2.7742749054224466e-05, | |
| "loss": 0.5321, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.38, | |
| "learning_rate": 2.8373266078184114e-05, | |
| "loss": 0.554, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 2.9003783102143763e-05, | |
| "loss": 0.5192, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 2.9634300126103404e-05, | |
| "loss": 0.5342, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.87, | |
| "learning_rate": 3.0264817150063052e-05, | |
| "loss": 0.5477, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7784156142365097, | |
| "eval_loss": 0.453955739736557, | |
| "eval_runtime": 22.2779, | |
| "eval_samples_per_second": 39.097, | |
| "eval_steps_per_second": 1.257, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 3.08953341740227e-05, | |
| "loss": 0.5532, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 3.1525851197982345e-05, | |
| "loss": 0.5373, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 3.2156368221941994e-05, | |
| "loss": 0.5246, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 3.2786885245901635e-05, | |
| "loss": 0.5496, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.69, | |
| "learning_rate": 3.3417402269861284e-05, | |
| "loss": 0.5572, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 3.404791929382093e-05, | |
| "loss": 0.5554, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7634902411021814, | |
| "eval_loss": 0.4931538999080658, | |
| "eval_runtime": 22.408, | |
| "eval_samples_per_second": 38.87, | |
| "eval_steps_per_second": 1.25, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 3.467843631778058e-05, | |
| "loss": 0.5271, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 3.530895334174023e-05, | |
| "loss": 0.52, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 3.5939470365699877e-05, | |
| "loss": 0.5093, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 3.656998738965952e-05, | |
| "loss": 0.5228, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.67, | |
| "learning_rate": 3.7200504413619166e-05, | |
| "loss": 0.5501, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 3.7831021437578815e-05, | |
| "loss": 0.5311, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.5247, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7967853042479908, | |
| "eval_loss": 0.4407272934913635, | |
| "eval_runtime": 22.598, | |
| "eval_samples_per_second": 38.543, | |
| "eval_steps_per_second": 1.239, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 10.16, | |
| "learning_rate": 3.909205548549811e-05, | |
| "loss": 0.5183, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.33, | |
| "learning_rate": 3.972257250945776e-05, | |
| "loss": 0.5064, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 10.49, | |
| "learning_rate": 4.03530895334174e-05, | |
| "loss": 0.52, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.65, | |
| "learning_rate": 4.098360655737705e-05, | |
| "loss": 0.5195, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 4.16141235813367e-05, | |
| "loss": 0.5291, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.98, | |
| "learning_rate": 4.2244640605296346e-05, | |
| "loss": 0.5239, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.7841561423650976, | |
| "eval_loss": 0.4478810429573059, | |
| "eval_runtime": 22.2792, | |
| "eval_samples_per_second": 39.095, | |
| "eval_steps_per_second": 1.257, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 11.15, | |
| "learning_rate": 4.2875157629255994e-05, | |
| "loss": 0.5172, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 4.350567465321564e-05, | |
| "loss": 0.5075, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 11.47, | |
| "learning_rate": 4.4136191677175284e-05, | |
| "loss": 0.5629, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 4.476670870113493e-05, | |
| "loss": 0.4935, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 4.539722572509458e-05, | |
| "loss": 0.5106, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.96, | |
| "learning_rate": 4.602774274905423e-05, | |
| "loss": 0.5294, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7910447761194029, | |
| "eval_loss": 0.45090773701667786, | |
| "eval_runtime": 22.4724, | |
| "eval_samples_per_second": 38.759, | |
| "eval_steps_per_second": 1.246, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 12.13, | |
| "learning_rate": 4.665825977301388e-05, | |
| "loss": 0.53, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.29, | |
| "learning_rate": 4.7288776796973525e-05, | |
| "loss": 0.5052, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "learning_rate": 4.7919293820933167e-05, | |
| "loss": 0.5193, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.62, | |
| "learning_rate": 4.8549810844892815e-05, | |
| "loss": 0.5424, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 4.918032786885246e-05, | |
| "loss": 0.5481, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.95, | |
| "learning_rate": 4.981084489281211e-05, | |
| "loss": 0.531, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7933409873708381, | |
| "eval_loss": 0.4418846368789673, | |
| "eval_runtime": 21.9201, | |
| "eval_samples_per_second": 39.735, | |
| "eval_steps_per_second": 1.277, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 13.11, | |
| "learning_rate": 4.9950959787025363e-05, | |
| "loss": 0.5378, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 4.988090233991873e-05, | |
| "loss": 0.4999, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 4.981084489281211e-05, | |
| "loss": 0.5245, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 4.9740787445705485e-05, | |
| "loss": 0.5124, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 13.77, | |
| "learning_rate": 4.967072999859885e-05, | |
| "loss": 0.4897, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 13.93, | |
| "learning_rate": 4.9600672551492226e-05, | |
| "loss": 0.5493, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7784156142365097, | |
| "eval_loss": 0.4645788073539734, | |
| "eval_runtime": 21.6725, | |
| "eval_samples_per_second": 40.189, | |
| "eval_steps_per_second": 1.292, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 4.95306151043856e-05, | |
| "loss": 0.5204, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 14.26, | |
| "learning_rate": 4.9460557657278974e-05, | |
| "loss": 0.487, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 14.42, | |
| "learning_rate": 4.939050021017234e-05, | |
| "loss": 0.5226, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.59, | |
| "learning_rate": 4.9320442763065715e-05, | |
| "loss": 0.5097, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 4.925038531595909e-05, | |
| "loss": 0.5101, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.91, | |
| "learning_rate": 4.918032786885246e-05, | |
| "loss": 0.4934, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7967853042479908, | |
| "eval_loss": 0.43095123767852783, | |
| "eval_runtime": 21.7573, | |
| "eval_samples_per_second": 40.032, | |
| "eval_steps_per_second": 1.287, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 4.911027042174584e-05, | |
| "loss": 0.5233, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 15.24, | |
| "learning_rate": 4.9040212974639204e-05, | |
| "loss": 0.4925, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 15.41, | |
| "learning_rate": 4.897015552753258e-05, | |
| "loss": 0.5043, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 15.57, | |
| "learning_rate": 4.890009808042595e-05, | |
| "loss": 0.4891, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 15.73, | |
| "learning_rate": 4.8830040633319326e-05, | |
| "loss": 0.5045, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 4.87599831862127e-05, | |
| "loss": 0.4965, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7876004592422503, | |
| "eval_loss": 0.44487157464027405, | |
| "eval_runtime": 21.681, | |
| "eval_samples_per_second": 40.174, | |
| "eval_steps_per_second": 1.291, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 16.07, | |
| "learning_rate": 4.868992573910607e-05, | |
| "loss": 0.513, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 16.23, | |
| "learning_rate": 4.861986829199944e-05, | |
| "loss": 0.4868, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 4.8549810844892815e-05, | |
| "loss": 0.4985, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.56, | |
| "learning_rate": 4.847975339778619e-05, | |
| "loss": 0.4863, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 16.72, | |
| "learning_rate": 4.840969595067956e-05, | |
| "loss": 0.4931, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 16.88, | |
| "learning_rate": 4.833963850357293e-05, | |
| "loss": 0.4946, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8128587830080367, | |
| "eval_loss": 0.4341886043548584, | |
| "eval_runtime": 21.541, | |
| "eval_samples_per_second": 40.435, | |
| "eval_steps_per_second": 1.3, | |
| "step": 1037 | |
| }, | |
| { | |
| "epoch": 17.05, | |
| "learning_rate": 4.8269581056466304e-05, | |
| "loss": 0.4883, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 17.21, | |
| "learning_rate": 4.819952360935968e-05, | |
| "loss": 0.5016, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 17.38, | |
| "learning_rate": 4.812946616225305e-05, | |
| "loss": 0.4828, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 17.54, | |
| "learning_rate": 4.805940871514642e-05, | |
| "loss": 0.4914, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 4.798935126803979e-05, | |
| "loss": 0.4738, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 17.87, | |
| "learning_rate": 4.7919293820933167e-05, | |
| "loss": 0.4716, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8140068886337543, | |
| "eval_loss": 0.41291186213493347, | |
| "eval_runtime": 21.8801, | |
| "eval_samples_per_second": 39.808, | |
| "eval_steps_per_second": 1.28, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 18.03, | |
| "learning_rate": 4.784923637382654e-05, | |
| "loss": 0.4968, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 18.2, | |
| "learning_rate": 4.7779178926719914e-05, | |
| "loss": 0.4928, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 18.36, | |
| "learning_rate": 4.770912147961328e-05, | |
| "loss": 0.4813, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 18.52, | |
| "learning_rate": 4.7639064032506655e-05, | |
| "loss": 0.4804, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 18.69, | |
| "learning_rate": 4.756900658540003e-05, | |
| "loss": 0.4667, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "learning_rate": 4.74989491382934e-05, | |
| "loss": 0.4679, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8002296211251435, | |
| "eval_loss": 0.42902934551239014, | |
| "eval_runtime": 21.9135, | |
| "eval_samples_per_second": 39.747, | |
| "eval_steps_per_second": 1.278, | |
| "step": 1159 | |
| }, | |
| { | |
| "epoch": 19.02, | |
| "learning_rate": 4.742889169118678e-05, | |
| "loss": 0.4728, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 19.18, | |
| "learning_rate": 4.7358834244080144e-05, | |
| "loss": 0.483, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 19.34, | |
| "learning_rate": 4.7288776796973525e-05, | |
| "loss": 0.48, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 19.51, | |
| "learning_rate": 4.721871934986689e-05, | |
| "loss": 0.4828, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 19.67, | |
| "learning_rate": 4.7148661902760266e-05, | |
| "loss": 0.4826, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 19.83, | |
| "learning_rate": 4.707860445565364e-05, | |
| "loss": 0.4513, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 4.700854700854701e-05, | |
| "loss": 0.4799, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7841561423650976, | |
| "eval_loss": 0.4355582594871521, | |
| "eval_runtime": 21.8604, | |
| "eval_samples_per_second": 39.844, | |
| "eval_steps_per_second": 1.281, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 4.693848956144039e-05, | |
| "loss": 0.4786, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 20.33, | |
| "learning_rate": 4.6868432114333755e-05, | |
| "loss": 0.4694, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 20.49, | |
| "learning_rate": 4.679837466722713e-05, | |
| "loss": 0.4938, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.65, | |
| "learning_rate": 4.6728317220120496e-05, | |
| "loss": 0.484, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 20.82, | |
| "learning_rate": 4.665825977301388e-05, | |
| "loss": 0.4656, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 20.98, | |
| "learning_rate": 4.658820232590725e-05, | |
| "loss": 0.4744, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8094144661308841, | |
| "eval_loss": 0.40415847301483154, | |
| "eval_runtime": 21.7116, | |
| "eval_samples_per_second": 40.117, | |
| "eval_steps_per_second": 1.29, | |
| "step": 1281 | |
| }, | |
| { | |
| "epoch": 21.15, | |
| "learning_rate": 4.651814487880062e-05, | |
| "loss": 0.4637, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 21.31, | |
| "learning_rate": 4.644808743169399e-05, | |
| "loss": 0.4459, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 21.47, | |
| "learning_rate": 4.637802998458736e-05, | |
| "loss": 0.4449, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 21.64, | |
| "learning_rate": 4.630797253748074e-05, | |
| "loss": 0.4461, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 21.8, | |
| "learning_rate": 4.623791509037411e-05, | |
| "loss": 0.453, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 21.96, | |
| "learning_rate": 4.616785764326748e-05, | |
| "loss": 0.4512, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8117106773823192, | |
| "eval_loss": 0.3952537775039673, | |
| "eval_runtime": 21.3591, | |
| "eval_samples_per_second": 40.779, | |
| "eval_steps_per_second": 1.311, | |
| "step": 1342 | |
| }, | |
| { | |
| "epoch": 22.13, | |
| "learning_rate": 4.6097800196160855e-05, | |
| "loss": 0.4761, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 22.29, | |
| "learning_rate": 4.602774274905423e-05, | |
| "loss": 0.4314, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 22.46, | |
| "learning_rate": 4.59576853019476e-05, | |
| "loss": 0.4731, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 4.588762785484097e-05, | |
| "loss": 0.4318, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 4.5817570407734343e-05, | |
| "loss": 0.4714, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 22.95, | |
| "learning_rate": 4.574751296062772e-05, | |
| "loss": 0.4633, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.7956371986222732, | |
| "eval_loss": 0.41565003991127014, | |
| "eval_runtime": 21.3083, | |
| "eval_samples_per_second": 40.876, | |
| "eval_steps_per_second": 1.314, | |
| "step": 1403 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "learning_rate": 4.567745551352109e-05, | |
| "loss": 0.4322, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 23.28, | |
| "learning_rate": 4.5607398066414465e-05, | |
| "loss": 0.4488, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 23.44, | |
| "learning_rate": 4.553734061930783e-05, | |
| "loss": 0.4549, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 23.6, | |
| "learning_rate": 4.5467283172201206e-05, | |
| "loss": 0.4426, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 23.77, | |
| "learning_rate": 4.539722572509458e-05, | |
| "loss": 0.4465, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 23.93, | |
| "learning_rate": 4.5327168277987954e-05, | |
| "loss": 0.4528, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8094144661308841, | |
| "eval_loss": 0.3920004963874817, | |
| "eval_runtime": 21.251, | |
| "eval_samples_per_second": 40.986, | |
| "eval_steps_per_second": 1.318, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 24.1, | |
| "learning_rate": 4.525711083088133e-05, | |
| "loss": 0.4498, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 24.26, | |
| "learning_rate": 4.5187053383774695e-05, | |
| "loss": 0.4449, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 24.42, | |
| "learning_rate": 4.511699593666807e-05, | |
| "loss": 0.4571, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 24.59, | |
| "learning_rate": 4.504693848956144e-05, | |
| "loss": 0.4496, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "learning_rate": 4.497688104245482e-05, | |
| "loss": 0.4132, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 24.91, | |
| "learning_rate": 4.4906823595348184e-05, | |
| "loss": 0.4427, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8220436280137773, | |
| "eval_loss": 0.3929567039012909, | |
| "eval_runtime": 21.6868, | |
| "eval_samples_per_second": 40.163, | |
| "eval_steps_per_second": 1.291, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 25.08, | |
| "learning_rate": 4.483676614824156e-05, | |
| "loss": 0.4802, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 25.24, | |
| "learning_rate": 4.476670870113493e-05, | |
| "loss": 0.4328, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 25.41, | |
| "learning_rate": 4.4696651254028306e-05, | |
| "loss": 0.4355, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 25.57, | |
| "learning_rate": 4.462659380692168e-05, | |
| "loss": 0.418, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 25.73, | |
| "learning_rate": 4.455653635981505e-05, | |
| "loss": 0.4257, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 25.9, | |
| "learning_rate": 4.448647891270842e-05, | |
| "loss": 0.4238, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8140068886337543, | |
| "eval_loss": 0.38909533619880676, | |
| "eval_runtime": 22.1513, | |
| "eval_samples_per_second": 39.32, | |
| "eval_steps_per_second": 1.264, | |
| "step": 1586 | |
| }, | |
| { | |
| "epoch": 26.07, | |
| "learning_rate": 4.4416421465601795e-05, | |
| "loss": 0.4549, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 26.23, | |
| "learning_rate": 4.434636401849517e-05, | |
| "loss": 0.419, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 26.39, | |
| "learning_rate": 4.427630657138854e-05, | |
| "loss": 0.4175, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 4.420624912428191e-05, | |
| "loss": 0.4533, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 4.4136191677175284e-05, | |
| "loss": 0.4165, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 4.406613423006866e-05, | |
| "loss": 0.4257, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8254879448909299, | |
| "eval_loss": 0.36998629570007324, | |
| "eval_runtime": 23.1782, | |
| "eval_samples_per_second": 37.578, | |
| "eval_steps_per_second": 1.208, | |
| "step": 1647 | |
| }, | |
| { | |
| "epoch": 27.05, | |
| "learning_rate": 4.399607678296203e-05, | |
| "loss": 0.4606, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 27.21, | |
| "learning_rate": 4.3926019335855405e-05, | |
| "loss": 0.4206, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 27.38, | |
| "learning_rate": 4.385596188874877e-05, | |
| "loss": 0.4133, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 27.54, | |
| "learning_rate": 4.378590444164215e-05, | |
| "loss": 0.4321, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 27.7, | |
| "learning_rate": 4.371584699453552e-05, | |
| "loss": 0.4067, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 27.87, | |
| "learning_rate": 4.3645789547428894e-05, | |
| "loss": 0.4102, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7967853042479908, | |
| "eval_loss": 0.412211149930954, | |
| "eval_runtime": 22.5228, | |
| "eval_samples_per_second": 38.672, | |
| "eval_steps_per_second": 1.243, | |
| "step": 1708 | |
| }, | |
| { | |
| "epoch": 28.03, | |
| "learning_rate": 4.357573210032226e-05, | |
| "loss": 0.411, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 28.2, | |
| "learning_rate": 4.350567465321564e-05, | |
| "loss": 0.4324, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "learning_rate": 4.3435617206109016e-05, | |
| "loss": 0.4165, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 28.52, | |
| "learning_rate": 4.336555975900238e-05, | |
| "loss": 0.4183, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 28.69, | |
| "learning_rate": 4.329550231189576e-05, | |
| "loss": 0.4142, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.85, | |
| "learning_rate": 4.3225444864789124e-05, | |
| "loss": 0.4505, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.7944890929965557, | |
| "eval_loss": 0.42098405957221985, | |
| "eval_runtime": 22.5932, | |
| "eval_samples_per_second": 38.551, | |
| "eval_steps_per_second": 1.239, | |
| "step": 1769 | |
| }, | |
| { | |
| "epoch": 29.02, | |
| "learning_rate": 4.3155387417682505e-05, | |
| "loss": 0.4152, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 29.18, | |
| "learning_rate": 4.308532997057587e-05, | |
| "loss": 0.4152, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 29.34, | |
| "learning_rate": 4.3015272523469246e-05, | |
| "loss": 0.4153, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 29.51, | |
| "learning_rate": 4.294521507636262e-05, | |
| "loss": 0.4181, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 29.67, | |
| "learning_rate": 4.2875157629255994e-05, | |
| "loss": 0.4094, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 29.83, | |
| "learning_rate": 4.280510018214937e-05, | |
| "loss": 0.3891, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 4.2735042735042735e-05, | |
| "loss": 0.3973, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8197474167623421, | |
| "eval_loss": 0.3922854959964752, | |
| "eval_runtime": 22.6386, | |
| "eval_samples_per_second": 38.474, | |
| "eval_steps_per_second": 1.237, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 30.16, | |
| "learning_rate": 4.266498528793611e-05, | |
| "loss": 0.3995, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 30.33, | |
| "learning_rate": 4.259492784082948e-05, | |
| "loss": 0.3753, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 30.49, | |
| "learning_rate": 4.252487039372286e-05, | |
| "loss": 0.423, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 30.65, | |
| "learning_rate": 4.245481294661623e-05, | |
| "loss": 0.4107, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 30.82, | |
| "learning_rate": 4.23847554995096e-05, | |
| "loss": 0.3903, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 30.98, | |
| "learning_rate": 4.231469805240297e-05, | |
| "loss": 0.3824, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.8473019517795637, | |
| "eval_loss": 0.39075911045074463, | |
| "eval_runtime": 22.6362, | |
| "eval_samples_per_second": 38.478, | |
| "eval_steps_per_second": 1.237, | |
| "step": 1891 | |
| }, | |
| { | |
| "epoch": 31.15, | |
| "learning_rate": 4.2244640605296346e-05, | |
| "loss": 0.3827, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 31.31, | |
| "learning_rate": 4.217458315818972e-05, | |
| "loss": 0.392, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 31.47, | |
| "learning_rate": 4.2104525711083094e-05, | |
| "loss": 0.4118, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 31.64, | |
| "learning_rate": 4.203446826397646e-05, | |
| "loss": 0.3843, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 31.8, | |
| "learning_rate": 4.1964410816869835e-05, | |
| "loss": 0.3847, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 31.96, | |
| "learning_rate": 4.189435336976321e-05, | |
| "loss": 0.3887, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8312284730195177, | |
| "eval_loss": 0.38973063230514526, | |
| "eval_runtime": 22.347, | |
| "eval_samples_per_second": 38.976, | |
| "eval_steps_per_second": 1.253, | |
| "step": 1952 | |
| }, | |
| { | |
| "epoch": 32.13, | |
| "learning_rate": 4.182429592265658e-05, | |
| "loss": 0.413, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 32.29, | |
| "learning_rate": 4.175423847554995e-05, | |
| "loss": 0.4407, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 32.46, | |
| "learning_rate": 4.1684181028443323e-05, | |
| "loss": 0.3676, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 32.62, | |
| "learning_rate": 4.16141235813367e-05, | |
| "loss": 0.3921, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 32.78, | |
| "learning_rate": 4.154406613423007e-05, | |
| "loss": 0.4016, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 32.95, | |
| "learning_rate": 4.1474008687123445e-05, | |
| "loss": 0.3723, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8381171067738232, | |
| "eval_loss": 0.374667763710022, | |
| "eval_runtime": 22.583, | |
| "eval_samples_per_second": 38.569, | |
| "eval_steps_per_second": 1.24, | |
| "step": 2013 | |
| }, | |
| { | |
| "epoch": 33.11, | |
| "learning_rate": 4.140395124001681e-05, | |
| "loss": 0.3735, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 33.28, | |
| "learning_rate": 4.1333893792910186e-05, | |
| "loss": 0.3742, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 33.44, | |
| "learning_rate": 4.126383634580356e-05, | |
| "loss": 0.3997, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 33.6, | |
| "learning_rate": 4.1193778898696934e-05, | |
| "loss": 0.3632, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 33.77, | |
| "learning_rate": 4.112372145159031e-05, | |
| "loss": 0.3689, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 33.93, | |
| "learning_rate": 4.1053664004483675e-05, | |
| "loss": 0.3608, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.8300803673938002, | |
| "eval_loss": 0.3706473708152771, | |
| "eval_runtime": 22.6873, | |
| "eval_samples_per_second": 38.391, | |
| "eval_steps_per_second": 1.234, | |
| "step": 2074 | |
| }, | |
| { | |
| "epoch": 34.1, | |
| "learning_rate": 4.098360655737705e-05, | |
| "loss": 0.3363, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 34.26, | |
| "learning_rate": 4.091354911027042e-05, | |
| "loss": 0.3708, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 34.42, | |
| "learning_rate": 4.08434916631638e-05, | |
| "loss": 0.3921, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 34.59, | |
| "learning_rate": 4.077343421605717e-05, | |
| "loss": 0.3619, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 34.75, | |
| "learning_rate": 4.070337676895054e-05, | |
| "loss": 0.3796, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 34.91, | |
| "learning_rate": 4.063331932184392e-05, | |
| "loss": 0.3718, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.8254879448909299, | |
| "eval_loss": 0.39373716711997986, | |
| "eval_runtime": 22.7596, | |
| "eval_samples_per_second": 38.269, | |
| "eval_steps_per_second": 1.23, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 35.08, | |
| "learning_rate": 4.0563261874737286e-05, | |
| "loss": 0.3806, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 35.24, | |
| "learning_rate": 4.049320442763066e-05, | |
| "loss": 0.3772, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 35.41, | |
| "learning_rate": 4.042314698052403e-05, | |
| "loss": 0.401, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 35.57, | |
| "learning_rate": 4.03530895334174e-05, | |
| "loss": 0.37, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 35.73, | |
| "learning_rate": 4.028303208631078e-05, | |
| "loss": 0.3567, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 35.9, | |
| "learning_rate": 4.021297463920415e-05, | |
| "loss": 0.3692, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8036739380022963, | |
| "eval_loss": 0.39840611815452576, | |
| "eval_runtime": 22.4984, | |
| "eval_samples_per_second": 38.714, | |
| "eval_steps_per_second": 1.245, | |
| "step": 2196 | |
| }, | |
| { | |
| "epoch": 36.07, | |
| "learning_rate": 4.014291719209752e-05, | |
| "loss": 0.3794, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 36.23, | |
| "learning_rate": 4.007285974499089e-05, | |
| "loss": 0.3584, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 36.39, | |
| "learning_rate": 4.000280229788427e-05, | |
| "loss": 0.3895, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 36.56, | |
| "learning_rate": 3.993274485077764e-05, | |
| "loss": 0.3563, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 36.72, | |
| "learning_rate": 3.986268740367101e-05, | |
| "loss": 0.3646, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 36.88, | |
| "learning_rate": 3.9792629956564385e-05, | |
| "loss": 0.3533, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.8335246842709529, | |
| "eval_loss": 0.3791780471801758, | |
| "eval_runtime": 22.3647, | |
| "eval_samples_per_second": 38.945, | |
| "eval_steps_per_second": 1.252, | |
| "step": 2257 | |
| }, | |
| { | |
| "epoch": 37.05, | |
| "learning_rate": 3.972257250945776e-05, | |
| "loss": 0.3682, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 37.21, | |
| "learning_rate": 3.965251506235113e-05, | |
| "loss": 0.3295, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 37.38, | |
| "learning_rate": 3.95824576152445e-05, | |
| "loss": 0.3556, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 37.54, | |
| "learning_rate": 3.9512400168137874e-05, | |
| "loss": 0.343, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 37.7, | |
| "learning_rate": 3.944234272103125e-05, | |
| "loss": 0.3544, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 37.87, | |
| "learning_rate": 3.937228527392462e-05, | |
| "loss": 0.3625, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8163030998851895, | |
| "eval_loss": 0.40697064995765686, | |
| "eval_runtime": 22.7041, | |
| "eval_samples_per_second": 38.363, | |
| "eval_steps_per_second": 1.233, | |
| "step": 2318 | |
| }, | |
| { | |
| "epoch": 38.03, | |
| "learning_rate": 3.9302227826817996e-05, | |
| "loss": 0.3379, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 38.2, | |
| "learning_rate": 3.923217037971136e-05, | |
| "loss": 0.3373, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 38.36, | |
| "learning_rate": 3.916211293260474e-05, | |
| "loss": 0.3315, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 38.52, | |
| "learning_rate": 3.909205548549811e-05, | |
| "loss": 0.3477, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 38.69, | |
| "learning_rate": 3.9021998038391485e-05, | |
| "loss": 0.3568, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 38.85, | |
| "learning_rate": 3.895194059128486e-05, | |
| "loss": 0.3633, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.8231917336394948, | |
| "eval_loss": 0.41295844316482544, | |
| "eval_runtime": 22.1224, | |
| "eval_samples_per_second": 39.372, | |
| "eval_steps_per_second": 1.266, | |
| "step": 2379 | |
| }, | |
| { | |
| "epoch": 39.02, | |
| "learning_rate": 3.8881883144178226e-05, | |
| "loss": 0.346, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 39.18, | |
| "learning_rate": 3.88118256970716e-05, | |
| "loss": 0.3215, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 39.34, | |
| "learning_rate": 3.8741768249964974e-05, | |
| "loss": 0.3401, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 39.51, | |
| "learning_rate": 3.867171080285835e-05, | |
| "loss": 0.3445, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 39.67, | |
| "learning_rate": 3.8601653355751715e-05, | |
| "loss": 0.3421, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 39.83, | |
| "learning_rate": 3.853159590864509e-05, | |
| "loss": 0.3738, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.3602, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8185993111366245, | |
| "eval_loss": 0.39960527420043945, | |
| "eval_runtime": 22.0347, | |
| "eval_samples_per_second": 39.529, | |
| "eval_steps_per_second": 1.271, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 40.16, | |
| "learning_rate": 3.839148101443184e-05, | |
| "loss": 0.3417, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 40.33, | |
| "learning_rate": 3.832142356732521e-05, | |
| "loss": 0.3665, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 40.49, | |
| "learning_rate": 3.825136612021858e-05, | |
| "loss": 0.32, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 40.65, | |
| "learning_rate": 3.818130867311195e-05, | |
| "loss": 0.3254, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 40.82, | |
| "learning_rate": 3.8111251226005326e-05, | |
| "loss": 0.3344, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 40.98, | |
| "learning_rate": 3.80411937788987e-05, | |
| "loss": 0.3557, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.8335246842709529, | |
| "eval_loss": 0.37564805150032043, | |
| "eval_runtime": 21.6887, | |
| "eval_samples_per_second": 40.159, | |
| "eval_steps_per_second": 1.291, | |
| "step": 2501 | |
| }, | |
| { | |
| "epoch": 41.15, | |
| "learning_rate": 3.7971136331792074e-05, | |
| "loss": 0.3372, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 41.31, | |
| "learning_rate": 3.790107888468544e-05, | |
| "loss": 0.3287, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 41.47, | |
| "learning_rate": 3.7831021437578815e-05, | |
| "loss": 0.3525, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 41.64, | |
| "learning_rate": 3.776096399047219e-05, | |
| "loss": 0.3234, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 41.8, | |
| "learning_rate": 3.769090654336556e-05, | |
| "loss": 0.342, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 41.96, | |
| "learning_rate": 3.7620849096258936e-05, | |
| "loss": 0.3373, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.8220436280137773, | |
| "eval_loss": 0.3913869261741638, | |
| "eval_runtime": 21.664, | |
| "eval_samples_per_second": 40.205, | |
| "eval_steps_per_second": 1.292, | |
| "step": 2562 | |
| }, | |
| { | |
| "epoch": 42.13, | |
| "learning_rate": 3.7550791649152304e-05, | |
| "loss": 0.3555, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 42.29, | |
| "learning_rate": 3.7480734202045684e-05, | |
| "loss": 0.3257, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 42.46, | |
| "learning_rate": 3.741067675493905e-05, | |
| "loss": 0.3216, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 42.62, | |
| "learning_rate": 3.7340619307832425e-05, | |
| "loss": 0.323, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 42.78, | |
| "learning_rate": 3.727056186072579e-05, | |
| "loss": 0.3099, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 42.95, | |
| "learning_rate": 3.7200504413619166e-05, | |
| "loss": 0.3102, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.8507462686567164, | |
| "eval_loss": 0.41650915145874023, | |
| "eval_runtime": 21.9782, | |
| "eval_samples_per_second": 39.63, | |
| "eval_steps_per_second": 1.274, | |
| "step": 2623 | |
| }, | |
| { | |
| "epoch": 43.11, | |
| "learning_rate": 3.713044696651255e-05, | |
| "loss": 0.3268, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 43.28, | |
| "learning_rate": 3.7060389519405914e-05, | |
| "loss": 0.2725, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 43.44, | |
| "learning_rate": 3.699033207229929e-05, | |
| "loss": 0.3365, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 43.6, | |
| "learning_rate": 3.6920274625192655e-05, | |
| "loss": 0.3576, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 43.77, | |
| "learning_rate": 3.6850217178086036e-05, | |
| "loss": 0.3316, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 43.93, | |
| "learning_rate": 3.67801597309794e-05, | |
| "loss": 0.3135, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8277841561423651, | |
| "eval_loss": 0.38522833585739136, | |
| "eval_runtime": 22.1222, | |
| "eval_samples_per_second": 39.372, | |
| "eval_steps_per_second": 1.266, | |
| "step": 2684 | |
| }, | |
| { | |
| "epoch": 44.1, | |
| "learning_rate": 3.671010228387278e-05, | |
| "loss": 0.3152, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 44.26, | |
| "learning_rate": 3.664004483676615e-05, | |
| "loss": 0.3191, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 44.42, | |
| "learning_rate": 3.656998738965952e-05, | |
| "loss": 0.3135, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 44.59, | |
| "learning_rate": 3.64999299425529e-05, | |
| "loss": 0.3167, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 44.75, | |
| "learning_rate": 3.6429872495446266e-05, | |
| "loss": 0.3338, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 44.91, | |
| "learning_rate": 3.635981504833964e-05, | |
| "loss": 0.3286, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.8450057405281286, | |
| "eval_loss": 0.4163770079612732, | |
| "eval_runtime": 21.5791, | |
| "eval_samples_per_second": 40.363, | |
| "eval_steps_per_second": 1.298, | |
| "step": 2745 | |
| }, | |
| { | |
| "epoch": 45.08, | |
| "learning_rate": 3.6289757601233014e-05, | |
| "loss": 0.3109, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 45.24, | |
| "learning_rate": 3.621970015412639e-05, | |
| "loss": 0.2987, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 45.41, | |
| "learning_rate": 3.614964270701976e-05, | |
| "loss": 0.2925, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 45.57, | |
| "learning_rate": 3.607958525991313e-05, | |
| "loss": 0.2753, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 45.73, | |
| "learning_rate": 3.60095278128065e-05, | |
| "loss": 0.3047, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 45.9, | |
| "learning_rate": 3.5939470365699877e-05, | |
| "loss": 0.316, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.8495981630309989, | |
| "eval_loss": 0.34977445006370544, | |
| "eval_runtime": 22.6158, | |
| "eval_samples_per_second": 38.513, | |
| "eval_steps_per_second": 1.238, | |
| "step": 2806 | |
| }, | |
| { | |
| "epoch": 46.07, | |
| "learning_rate": 3.586941291859325e-05, | |
| "loss": 0.3171, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 46.23, | |
| "learning_rate": 3.5799355471486624e-05, | |
| "loss": 0.3198, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 46.39, | |
| "learning_rate": 3.572929802437999e-05, | |
| "loss": 0.2996, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 46.56, | |
| "learning_rate": 3.5659240577273365e-05, | |
| "loss": 0.2933, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 46.72, | |
| "learning_rate": 3.558918313016674e-05, | |
| "loss": 0.3506, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 46.88, | |
| "learning_rate": 3.551912568306011e-05, | |
| "loss": 0.2802, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.8461538461538461, | |
| "eval_loss": 0.38866329193115234, | |
| "eval_runtime": 22.8466, | |
| "eval_samples_per_second": 38.124, | |
| "eval_steps_per_second": 1.226, | |
| "step": 2867 | |
| }, | |
| { | |
| "epoch": 47.05, | |
| "learning_rate": 3.544906823595348e-05, | |
| "loss": 0.2925, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 47.21, | |
| "learning_rate": 3.5379010788846854e-05, | |
| "loss": 0.2719, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 47.38, | |
| "learning_rate": 3.530895334174023e-05, | |
| "loss": 0.2835, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 47.54, | |
| "learning_rate": 3.52388958946336e-05, | |
| "loss": 0.2803, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 47.7, | |
| "learning_rate": 3.5168838447526976e-05, | |
| "loss": 0.287, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 47.87, | |
| "learning_rate": 3.509878100042034e-05, | |
| "loss": 0.3184, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8576349024110218, | |
| "eval_loss": 0.382943332195282, | |
| "eval_runtime": 23.0554, | |
| "eval_samples_per_second": 37.779, | |
| "eval_steps_per_second": 1.214, | |
| "step": 2928 | |
| }, | |
| { | |
| "epoch": 48.03, | |
| "learning_rate": 3.502872355331372e-05, | |
| "loss": 0.3039, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 48.2, | |
| "learning_rate": 3.495866610620709e-05, | |
| "loss": 0.2713, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 48.36, | |
| "learning_rate": 3.4888608659100465e-05, | |
| "loss": 0.273, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 48.52, | |
| "learning_rate": 3.481855121199384e-05, | |
| "loss": 0.3149, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 48.69, | |
| "learning_rate": 3.4748493764887206e-05, | |
| "loss": 0.2671, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 48.85, | |
| "learning_rate": 3.467843631778058e-05, | |
| "loss": 0.2785, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.8484500574052812, | |
| "eval_loss": 0.36272233724594116, | |
| "eval_runtime": 22.7995, | |
| "eval_samples_per_second": 38.203, | |
| "eval_steps_per_second": 1.228, | |
| "step": 2989 | |
| }, | |
| { | |
| "epoch": 49.02, | |
| "learning_rate": 3.4608378870673954e-05, | |
| "loss": 0.2915, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 49.18, | |
| "learning_rate": 3.453832142356733e-05, | |
| "loss": 0.2845, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 49.34, | |
| "learning_rate": 3.44682639764607e-05, | |
| "loss": 0.2779, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 49.51, | |
| "learning_rate": 3.439820652935407e-05, | |
| "loss": 0.2676, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 49.67, | |
| "learning_rate": 3.432814908224744e-05, | |
| "loss": 0.2741, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 49.83, | |
| "learning_rate": 3.425809163514082e-05, | |
| "loss": 0.2592, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 3.418803418803419e-05, | |
| "loss": 0.2988, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.8369690011481056, | |
| "eval_loss": 0.3679194450378418, | |
| "eval_runtime": 23.1017, | |
| "eval_samples_per_second": 37.703, | |
| "eval_steps_per_second": 1.212, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 50.16, | |
| "learning_rate": 3.411797674092756e-05, | |
| "loss": 0.2759, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 50.33, | |
| "learning_rate": 3.404791929382093e-05, | |
| "loss": 0.2643, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 50.49, | |
| "learning_rate": 3.397786184671431e-05, | |
| "loss": 0.2894, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 50.65, | |
| "learning_rate": 3.390780439960768e-05, | |
| "loss": 0.2715, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 50.82, | |
| "learning_rate": 3.3837746952501054e-05, | |
| "loss": 0.2888, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 50.98, | |
| "learning_rate": 3.376768950539442e-05, | |
| "loss": 0.267, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.8645235361653272, | |
| "eval_loss": 0.3528089225292206, | |
| "eval_runtime": 22.8158, | |
| "eval_samples_per_second": 38.175, | |
| "eval_steps_per_second": 1.227, | |
| "step": 3111 | |
| }, | |
| { | |
| "epoch": 51.15, | |
| "learning_rate": 3.36976320582878e-05, | |
| "loss": 0.281, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 51.31, | |
| "learning_rate": 3.3627574611181175e-05, | |
| "loss": 0.2753, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 51.47, | |
| "learning_rate": 3.355751716407454e-05, | |
| "loss": 0.2697, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 51.64, | |
| "learning_rate": 3.3487459716967916e-05, | |
| "loss": 0.2695, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 51.8, | |
| "learning_rate": 3.3417402269861284e-05, | |
| "loss": 0.271, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 51.96, | |
| "learning_rate": 3.3347344822754664e-05, | |
| "loss": 0.2907, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.851894374282434, | |
| "eval_loss": 0.35381364822387695, | |
| "eval_runtime": 22.8225, | |
| "eval_samples_per_second": 38.164, | |
| "eval_steps_per_second": 1.227, | |
| "step": 3172 | |
| }, | |
| { | |
| "epoch": 52.13, | |
| "learning_rate": 3.327728737564803e-05, | |
| "loss": 0.2753, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 52.29, | |
| "learning_rate": 3.3207229928541405e-05, | |
| "loss": 0.2983, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 52.46, | |
| "learning_rate": 3.313717248143478e-05, | |
| "loss": 0.2643, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 52.62, | |
| "learning_rate": 3.306711503432815e-05, | |
| "loss": 0.2685, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 52.78, | |
| "learning_rate": 3.299705758722153e-05, | |
| "loss": 0.3086, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 52.95, | |
| "learning_rate": 3.2927000140114894e-05, | |
| "loss": 0.2857, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.8530424799081515, | |
| "eval_loss": 0.3593134880065918, | |
| "eval_runtime": 22.7937, | |
| "eval_samples_per_second": 38.212, | |
| "eval_steps_per_second": 1.228, | |
| "step": 3233 | |
| }, | |
| { | |
| "epoch": 53.11, | |
| "learning_rate": 3.285694269300827e-05, | |
| "loss": 0.2703, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 53.28, | |
| "learning_rate": 3.2786885245901635e-05, | |
| "loss": 0.2542, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 53.44, | |
| "learning_rate": 3.2716827798795016e-05, | |
| "loss": 0.2878, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 53.6, | |
| "learning_rate": 3.264677035168839e-05, | |
| "loss": 0.2681, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 53.77, | |
| "learning_rate": 3.257671290458176e-05, | |
| "loss": 0.2515, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 53.93, | |
| "learning_rate": 3.250665545747513e-05, | |
| "loss": 0.2651, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.8438576349024111, | |
| "eval_loss": 0.37323862314224243, | |
| "eval_runtime": 22.7472, | |
| "eval_samples_per_second": 38.29, | |
| "eval_steps_per_second": 1.231, | |
| "step": 3294 | |
| }, | |
| { | |
| "epoch": 54.1, | |
| "learning_rate": 3.2436598010368505e-05, | |
| "loss": 0.2772, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 54.26, | |
| "learning_rate": 3.236654056326188e-05, | |
| "loss": 0.27, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 54.42, | |
| "learning_rate": 3.2296483116155246e-05, | |
| "loss": 0.2604, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 54.59, | |
| "learning_rate": 3.222642566904862e-05, | |
| "loss": 0.2554, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 54.75, | |
| "learning_rate": 3.2156368221941994e-05, | |
| "loss": 0.2834, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 54.91, | |
| "learning_rate": 3.208631077483537e-05, | |
| "loss": 0.2447, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.8541905855338691, | |
| "eval_loss": 0.34408894181251526, | |
| "eval_runtime": 22.4871, | |
| "eval_samples_per_second": 38.733, | |
| "eval_steps_per_second": 1.245, | |
| "step": 3355 | |
| }, | |
| { | |
| "epoch": 55.08, | |
| "learning_rate": 3.201625332772874e-05, | |
| "loss": 0.2668, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 55.24, | |
| "learning_rate": 3.194619588062211e-05, | |
| "loss": 0.2264, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 55.41, | |
| "learning_rate": 3.187613843351548e-05, | |
| "loss": 0.2622, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 55.57, | |
| "learning_rate": 3.1806080986408857e-05, | |
| "loss": 0.2586, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 55.73, | |
| "learning_rate": 3.173602353930223e-05, | |
| "loss": 0.2834, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 55.9, | |
| "learning_rate": 3.1665966092195604e-05, | |
| "loss": 0.2542, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.8576349024110218, | |
| "eval_loss": 0.3897174000740051, | |
| "eval_runtime": 22.8896, | |
| "eval_samples_per_second": 38.052, | |
| "eval_steps_per_second": 1.223, | |
| "step": 3416 | |
| }, | |
| { | |
| "epoch": 56.07, | |
| "learning_rate": 3.159590864508897e-05, | |
| "loss": 0.2592, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 56.23, | |
| "learning_rate": 3.1525851197982345e-05, | |
| "loss": 0.2759, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 56.39, | |
| "learning_rate": 3.145579375087572e-05, | |
| "loss": 0.2382, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 56.56, | |
| "learning_rate": 3.138573630376909e-05, | |
| "loss": 0.2405, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 56.72, | |
| "learning_rate": 3.131567885666247e-05, | |
| "loss": 0.2594, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 56.88, | |
| "learning_rate": 3.1245621409555834e-05, | |
| "loss": 0.2634, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.8656716417910447, | |
| "eval_loss": 0.4082171320915222, | |
| "eval_runtime": 22.1657, | |
| "eval_samples_per_second": 39.295, | |
| "eval_steps_per_second": 1.263, | |
| "step": 3477 | |
| }, | |
| { | |
| "epoch": 57.05, | |
| "learning_rate": 3.117556396244921e-05, | |
| "loss": 0.2546, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 57.21, | |
| "learning_rate": 3.110550651534258e-05, | |
| "loss": 0.2337, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 57.38, | |
| "learning_rate": 3.1035449068235956e-05, | |
| "loss": 0.2402, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 57.54, | |
| "learning_rate": 3.096539162112932e-05, | |
| "loss": 0.2631, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 57.7, | |
| "learning_rate": 3.08953341740227e-05, | |
| "loss": 0.259, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 57.87, | |
| "learning_rate": 3.082527672691608e-05, | |
| "loss": 0.2505, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.8656716417910447, | |
| "eval_loss": 0.3416268825531006, | |
| "eval_runtime": 21.9732, | |
| "eval_samples_per_second": 39.639, | |
| "eval_steps_per_second": 1.274, | |
| "step": 3538 | |
| }, | |
| { | |
| "epoch": 58.03, | |
| "learning_rate": 3.0755219279809445e-05, | |
| "loss": 0.2645, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 58.2, | |
| "learning_rate": 3.068516183270282e-05, | |
| "loss": 0.2317, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 58.36, | |
| "learning_rate": 3.0615104385596186e-05, | |
| "loss": 0.2644, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 58.52, | |
| "learning_rate": 3.054504693848956e-05, | |
| "loss": 0.2555, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 58.69, | |
| "learning_rate": 3.0474989491382937e-05, | |
| "loss": 0.2489, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 58.85, | |
| "learning_rate": 3.0404932044276308e-05, | |
| "loss": 0.2555, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.8576349024110218, | |
| "eval_loss": 0.37253421545028687, | |
| "eval_runtime": 21.8571, | |
| "eval_samples_per_second": 39.85, | |
| "eval_steps_per_second": 1.281, | |
| "step": 3599 | |
| }, | |
| { | |
| "epoch": 59.02, | |
| "learning_rate": 3.0334874597169682e-05, | |
| "loss": 0.2501, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 59.18, | |
| "learning_rate": 3.0264817150063052e-05, | |
| "loss": 0.2371, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 59.34, | |
| "learning_rate": 3.0194759702956426e-05, | |
| "loss": 0.2449, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 59.51, | |
| "learning_rate": 3.0124702255849797e-05, | |
| "loss": 0.2393, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 59.67, | |
| "learning_rate": 3.005464480874317e-05, | |
| "loss": 0.2292, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 59.83, | |
| "learning_rate": 2.9984587361636545e-05, | |
| "loss": 0.2825, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 2.9914529914529915e-05, | |
| "loss": 0.2466, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8679678530424799, | |
| "eval_loss": 0.3495868146419525, | |
| "eval_runtime": 22.1136, | |
| "eval_samples_per_second": 39.388, | |
| "eval_steps_per_second": 1.266, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 60.16, | |
| "learning_rate": 2.984447246742329e-05, | |
| "loss": 0.2017, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 60.33, | |
| "learning_rate": 2.977441502031666e-05, | |
| "loss": 0.2389, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 60.49, | |
| "learning_rate": 2.9704357573210034e-05, | |
| "loss": 0.2708, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 60.65, | |
| "learning_rate": 2.9634300126103404e-05, | |
| "loss": 0.2466, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 60.82, | |
| "learning_rate": 2.9564242678996778e-05, | |
| "loss": 0.2471, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 60.98, | |
| "learning_rate": 2.9494185231890152e-05, | |
| "loss": 0.2585, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.878300803673938, | |
| "eval_loss": 0.32144051790237427, | |
| "eval_runtime": 21.838, | |
| "eval_samples_per_second": 39.885, | |
| "eval_steps_per_second": 1.282, | |
| "step": 3721 | |
| }, | |
| { | |
| "epoch": 61.15, | |
| "learning_rate": 2.9424127784783522e-05, | |
| "loss": 0.2537, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 61.31, | |
| "learning_rate": 2.9354070337676896e-05, | |
| "loss": 0.2497, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 61.47, | |
| "learning_rate": 2.9284012890570267e-05, | |
| "loss": 0.2312, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 61.64, | |
| "learning_rate": 2.921395544346364e-05, | |
| "loss": 0.2666, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 61.8, | |
| "learning_rate": 2.9143897996357018e-05, | |
| "loss": 0.2446, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 61.96, | |
| "learning_rate": 2.9073840549250385e-05, | |
| "loss": 0.235, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8737083811710677, | |
| "eval_loss": 0.35838621854782104, | |
| "eval_runtime": 21.8361, | |
| "eval_samples_per_second": 39.888, | |
| "eval_steps_per_second": 1.282, | |
| "step": 3782 | |
| }, | |
| { | |
| "epoch": 62.13, | |
| "learning_rate": 2.9003783102143763e-05, | |
| "loss": 0.2434, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 62.29, | |
| "learning_rate": 2.893372565503713e-05, | |
| "loss": 0.2149, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 62.46, | |
| "learning_rate": 2.8863668207930507e-05, | |
| "loss": 0.2407, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 62.62, | |
| "learning_rate": 2.8793610760823874e-05, | |
| "loss": 0.2245, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 62.78, | |
| "learning_rate": 2.8723553313717248e-05, | |
| "loss": 0.2424, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 62.95, | |
| "learning_rate": 2.8653495866610625e-05, | |
| "loss": 0.215, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.8656716417910447, | |
| "eval_loss": 0.3466746509075165, | |
| "eval_runtime": 21.88, | |
| "eval_samples_per_second": 39.808, | |
| "eval_steps_per_second": 1.28, | |
| "step": 3843 | |
| }, | |
| { | |
| "epoch": 63.11, | |
| "learning_rate": 2.8583438419503993e-05, | |
| "loss": 0.2552, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 63.28, | |
| "learning_rate": 2.851338097239737e-05, | |
| "loss": 0.2237, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 63.44, | |
| "learning_rate": 2.8443323525290737e-05, | |
| "loss": 0.2421, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 63.6, | |
| "learning_rate": 2.8373266078184114e-05, | |
| "loss": 0.2111, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 63.77, | |
| "learning_rate": 2.830320863107748e-05, | |
| "loss": 0.2264, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 63.93, | |
| "learning_rate": 2.823315118397086e-05, | |
| "loss": 0.236, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.8828932261768083, | |
| "eval_loss": 0.34709620475769043, | |
| "eval_runtime": 21.9169, | |
| "eval_samples_per_second": 39.741, | |
| "eval_steps_per_second": 1.278, | |
| "step": 3904 | |
| }, | |
| { | |
| "epoch": 64.1, | |
| "learning_rate": 2.8163093736864233e-05, | |
| "loss": 0.2475, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 64.26, | |
| "learning_rate": 2.8093036289757603e-05, | |
| "loss": 0.2339, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 64.42, | |
| "learning_rate": 2.8022978842650977e-05, | |
| "loss": 0.2388, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 64.59, | |
| "learning_rate": 2.7952921395544344e-05, | |
| "loss": 0.2466, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 64.75, | |
| "learning_rate": 2.788286394843772e-05, | |
| "loss": 0.2443, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 64.91, | |
| "learning_rate": 2.781280650133109e-05, | |
| "loss": 0.2211, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.886337543053961, | |
| "eval_loss": 0.3318321108818054, | |
| "eval_runtime": 22.0451, | |
| "eval_samples_per_second": 39.51, | |
| "eval_steps_per_second": 1.27, | |
| "step": 3965 | |
| }, | |
| { | |
| "epoch": 65.08, | |
| "learning_rate": 2.7742749054224466e-05, | |
| "loss": 0.2403, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 65.24, | |
| "learning_rate": 2.767269160711784e-05, | |
| "loss": 0.2187, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 65.41, | |
| "learning_rate": 2.760263416001121e-05, | |
| "loss": 0.2179, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 65.57, | |
| "learning_rate": 2.7532576712904584e-05, | |
| "loss": 0.216, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 65.73, | |
| "learning_rate": 2.7462519265797955e-05, | |
| "loss": 0.2021, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 65.9, | |
| "learning_rate": 2.739246181869133e-05, | |
| "loss": 0.1989, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.8851894374282434, | |
| "eval_loss": 0.3644832372665405, | |
| "eval_runtime": 21.8684, | |
| "eval_samples_per_second": 39.829, | |
| "eval_steps_per_second": 1.28, | |
| "step": 4026 | |
| }, | |
| { | |
| "epoch": 66.07, | |
| "learning_rate": 2.7322404371584703e-05, | |
| "loss": 0.2434, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 66.23, | |
| "learning_rate": 2.7252346924478073e-05, | |
| "loss": 0.2176, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 66.39, | |
| "learning_rate": 2.7182289477371447e-05, | |
| "loss": 0.2007, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 66.56, | |
| "learning_rate": 2.7112232030264818e-05, | |
| "loss": 0.2346, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 66.72, | |
| "learning_rate": 2.7042174583158192e-05, | |
| "loss": 0.2184, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 66.88, | |
| "learning_rate": 2.6972117136051562e-05, | |
| "loss": 0.2133, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.8897818599311137, | |
| "eval_loss": 0.34559473395347595, | |
| "eval_runtime": 22.3242, | |
| "eval_samples_per_second": 39.016, | |
| "eval_steps_per_second": 1.254, | |
| "step": 4087 | |
| }, | |
| { | |
| "epoch": 67.05, | |
| "learning_rate": 2.6902059688944936e-05, | |
| "loss": 0.2156, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 67.21, | |
| "learning_rate": 2.683200224183831e-05, | |
| "loss": 0.2248, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 67.38, | |
| "learning_rate": 2.676194479473168e-05, | |
| "loss": 0.19, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 67.54, | |
| "learning_rate": 2.6691887347625055e-05, | |
| "loss": 0.2148, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 67.7, | |
| "learning_rate": 2.6621829900518425e-05, | |
| "loss": 0.217, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 67.87, | |
| "learning_rate": 2.65517724534118e-05, | |
| "loss": 0.2169, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8851894374282434, | |
| "eval_loss": 0.3286873400211334, | |
| "eval_runtime": 23.6573, | |
| "eval_samples_per_second": 36.817, | |
| "eval_steps_per_second": 1.184, | |
| "step": 4148 | |
| }, | |
| { | |
| "epoch": 68.03, | |
| "learning_rate": 2.648171500630517e-05, | |
| "loss": 0.218, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 68.2, | |
| "learning_rate": 2.6411657559198543e-05, | |
| "loss": 0.2061, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 68.36, | |
| "learning_rate": 2.6341600112091917e-05, | |
| "loss": 0.2115, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 68.52, | |
| "learning_rate": 2.6271542664985288e-05, | |
| "loss": 0.236, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 68.69, | |
| "learning_rate": 2.6201485217878662e-05, | |
| "loss": 0.1899, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 68.85, | |
| "learning_rate": 2.6131427770772032e-05, | |
| "loss": 0.223, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.8920780711825488, | |
| "eval_loss": 0.31819307804107666, | |
| "eval_runtime": 22.0662, | |
| "eval_samples_per_second": 39.472, | |
| "eval_steps_per_second": 1.269, | |
| "step": 4209 | |
| }, | |
| { | |
| "epoch": 69.02, | |
| "learning_rate": 2.6061370323665406e-05, | |
| "loss": 0.2133, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 69.18, | |
| "learning_rate": 2.5991312876558784e-05, | |
| "loss": 0.2092, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 69.34, | |
| "learning_rate": 2.592125542945215e-05, | |
| "loss": 0.2222, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 69.51, | |
| "learning_rate": 2.5851197982345528e-05, | |
| "loss": 0.2058, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 69.67, | |
| "learning_rate": 2.5781140535238895e-05, | |
| "loss": 0.2295, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 69.83, | |
| "learning_rate": 2.571108308813227e-05, | |
| "loss": 0.1972, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "learning_rate": 2.564102564102564e-05, | |
| "loss": 0.2379, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.8840413318025259, | |
| "eval_loss": 0.32603782415390015, | |
| "eval_runtime": 23.23, | |
| "eval_samples_per_second": 37.495, | |
| "eval_steps_per_second": 1.205, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 70.16, | |
| "learning_rate": 2.5570968193919014e-05, | |
| "loss": 0.2109, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 70.33, | |
| "learning_rate": 2.550091074681239e-05, | |
| "loss": 0.2183, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 70.49, | |
| "learning_rate": 2.5430853299705758e-05, | |
| "loss": 0.2077, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 70.65, | |
| "learning_rate": 2.5360795852599135e-05, | |
| "loss": 0.1985, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 70.82, | |
| "learning_rate": 2.5290738405492502e-05, | |
| "loss": 0.2246, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 70.98, | |
| "learning_rate": 2.522068095838588e-05, | |
| "loss": 0.2149, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.8886337543053962, | |
| "eval_loss": 0.3229505717754364, | |
| "eval_runtime": 23.2738, | |
| "eval_samples_per_second": 37.424, | |
| "eval_steps_per_second": 1.203, | |
| "step": 4331 | |
| }, | |
| { | |
| "epoch": 71.15, | |
| "learning_rate": 2.5150623511279247e-05, | |
| "loss": 0.2261, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 71.31, | |
| "learning_rate": 2.5080566064172624e-05, | |
| "loss": 0.2142, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 71.47, | |
| "learning_rate": 2.5010508617065998e-05, | |
| "loss": 0.2261, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 71.64, | |
| "learning_rate": 2.4940451169959365e-05, | |
| "loss": 0.2156, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 71.8, | |
| "learning_rate": 2.4870393722852743e-05, | |
| "loss": 0.221, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 71.96, | |
| "learning_rate": 2.4800336275746113e-05, | |
| "loss": 0.2007, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.8760045924225028, | |
| "eval_loss": 0.39263173937797546, | |
| "eval_runtime": 22.287, | |
| "eval_samples_per_second": 39.081, | |
| "eval_steps_per_second": 1.256, | |
| "step": 4392 | |
| }, | |
| { | |
| "epoch": 72.13, | |
| "learning_rate": 2.4730278828639487e-05, | |
| "loss": 0.2062, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 72.29, | |
| "learning_rate": 2.4660221381532858e-05, | |
| "loss": 0.2015, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 72.46, | |
| "learning_rate": 2.459016393442623e-05, | |
| "loss": 0.2107, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 72.62, | |
| "learning_rate": 2.4520106487319602e-05, | |
| "loss": 0.2034, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 72.78, | |
| "learning_rate": 2.4450049040212976e-05, | |
| "loss": 0.1853, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 72.95, | |
| "learning_rate": 2.437999159310635e-05, | |
| "loss": 0.2091, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.878300803673938, | |
| "eval_loss": 0.41334080696105957, | |
| "eval_runtime": 23.7363, | |
| "eval_samples_per_second": 36.695, | |
| "eval_steps_per_second": 1.18, | |
| "step": 4453 | |
| }, | |
| { | |
| "epoch": 73.11, | |
| "learning_rate": 2.430993414599972e-05, | |
| "loss": 0.1954, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 73.28, | |
| "learning_rate": 2.4239876698893094e-05, | |
| "loss": 0.1911, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 73.44, | |
| "learning_rate": 2.4169819251786465e-05, | |
| "loss": 0.2238, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 73.6, | |
| "learning_rate": 2.409976180467984e-05, | |
| "loss": 0.2047, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 73.77, | |
| "learning_rate": 2.402970435757321e-05, | |
| "loss": 0.2063, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 73.93, | |
| "learning_rate": 2.3959646910466583e-05, | |
| "loss": 0.2229, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.8771526980482205, | |
| "eval_loss": 0.3867405354976654, | |
| "eval_runtime": 23.2782, | |
| "eval_samples_per_second": 37.417, | |
| "eval_steps_per_second": 1.203, | |
| "step": 4514 | |
| }, | |
| { | |
| "epoch": 74.1, | |
| "learning_rate": 2.3889589463359957e-05, | |
| "loss": 0.1814, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 74.26, | |
| "learning_rate": 2.3819532016253328e-05, | |
| "loss": 0.1991, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 74.42, | |
| "learning_rate": 2.37494745691467e-05, | |
| "loss": 0.1831, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 74.59, | |
| "learning_rate": 2.3679417122040072e-05, | |
| "loss": 0.1946, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 74.75, | |
| "learning_rate": 2.3609359674933446e-05, | |
| "loss": 0.2108, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 74.91, | |
| "learning_rate": 2.353930222782682e-05, | |
| "loss": 0.1903, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.8840413318025259, | |
| "eval_loss": 0.3594009578227997, | |
| "eval_runtime": 24.1408, | |
| "eval_samples_per_second": 36.08, | |
| "eval_steps_per_second": 1.16, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 75.08, | |
| "learning_rate": 2.3469244780720194e-05, | |
| "loss": 0.2022, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 75.24, | |
| "learning_rate": 2.3399187333613564e-05, | |
| "loss": 0.1818, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 75.41, | |
| "learning_rate": 2.332912988650694e-05, | |
| "loss": 0.2, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 75.57, | |
| "learning_rate": 2.325907243940031e-05, | |
| "loss": 0.1907, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 75.73, | |
| "learning_rate": 2.318901499229368e-05, | |
| "loss": 0.2053, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 75.9, | |
| "learning_rate": 2.3118957545187053e-05, | |
| "loss": 0.2124, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.8874856486796785, | |
| "eval_loss": 0.3387896716594696, | |
| "eval_runtime": 22.3276, | |
| "eval_samples_per_second": 39.01, | |
| "eval_steps_per_second": 1.254, | |
| "step": 4636 | |
| }, | |
| { | |
| "epoch": 76.07, | |
| "learning_rate": 2.3048900098080427e-05, | |
| "loss": 0.1721, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 76.23, | |
| "learning_rate": 2.29788426509738e-05, | |
| "loss": 0.2046, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 76.39, | |
| "learning_rate": 2.2908785203867172e-05, | |
| "loss": 0.2008, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 76.56, | |
| "learning_rate": 2.2838727756760546e-05, | |
| "loss": 0.2035, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 76.72, | |
| "learning_rate": 2.2768670309653916e-05, | |
| "loss": 0.1907, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 76.88, | |
| "learning_rate": 2.269861286254729e-05, | |
| "loss": 0.1999, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.8874856486796785, | |
| "eval_loss": 0.3304520547389984, | |
| "eval_runtime": 22.4433, | |
| "eval_samples_per_second": 38.809, | |
| "eval_steps_per_second": 1.248, | |
| "step": 4697 | |
| }, | |
| { | |
| "epoch": 77.05, | |
| "learning_rate": 2.2628555415440664e-05, | |
| "loss": 0.2072, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 77.21, | |
| "learning_rate": 2.2558497968334035e-05, | |
| "loss": 0.1988, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 77.38, | |
| "learning_rate": 2.248844052122741e-05, | |
| "loss": 0.1975, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 77.54, | |
| "learning_rate": 2.241838307412078e-05, | |
| "loss": 0.2019, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 77.7, | |
| "learning_rate": 2.2348325627014153e-05, | |
| "loss": 0.1801, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 77.87, | |
| "learning_rate": 2.2278268179907523e-05, | |
| "loss": 0.2053, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.8840413318025259, | |
| "eval_loss": 0.46702420711517334, | |
| "eval_runtime": 22.4416, | |
| "eval_samples_per_second": 38.812, | |
| "eval_steps_per_second": 1.248, | |
| "step": 4758 | |
| }, | |
| { | |
| "epoch": 78.03, | |
| "learning_rate": 2.2208210732800897e-05, | |
| "loss": 0.2157, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 78.2, | |
| "learning_rate": 2.213815328569427e-05, | |
| "loss": 0.2012, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 78.36, | |
| "learning_rate": 2.2068095838587642e-05, | |
| "loss": 0.184, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 78.52, | |
| "learning_rate": 2.1998038391481016e-05, | |
| "loss": 0.1903, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 78.69, | |
| "learning_rate": 2.1927980944374386e-05, | |
| "loss": 0.1983, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 78.85, | |
| "learning_rate": 2.185792349726776e-05, | |
| "loss": 0.1958, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.8909299655568312, | |
| "eval_loss": 0.3467552661895752, | |
| "eval_runtime": 22.3347, | |
| "eval_samples_per_second": 38.998, | |
| "eval_steps_per_second": 1.254, | |
| "step": 4819 | |
| }, | |
| { | |
| "epoch": 79.02, | |
| "learning_rate": 2.178786605016113e-05, | |
| "loss": 0.2, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 79.18, | |
| "learning_rate": 2.1717808603054508e-05, | |
| "loss": 0.181, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 79.34, | |
| "learning_rate": 2.164775115594788e-05, | |
| "loss": 0.1926, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 79.51, | |
| "learning_rate": 2.1577693708841253e-05, | |
| "loss": 0.1824, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 79.67, | |
| "learning_rate": 2.1507636261734623e-05, | |
| "loss": 0.2052, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 79.83, | |
| "learning_rate": 2.1437578814627997e-05, | |
| "loss": 0.1984, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "learning_rate": 2.1367521367521368e-05, | |
| "loss": 0.1839, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.8886337543053962, | |
| "eval_loss": 0.3901750147342682, | |
| "eval_runtime": 22.044, | |
| "eval_samples_per_second": 39.512, | |
| "eval_steps_per_second": 1.27, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 80.16, | |
| "learning_rate": 2.129746392041474e-05, | |
| "loss": 0.2062, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 80.33, | |
| "learning_rate": 2.1227406473308115e-05, | |
| "loss": 0.1959, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 80.49, | |
| "learning_rate": 2.1157349026201486e-05, | |
| "loss": 0.1819, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 80.65, | |
| "learning_rate": 2.108729157909486e-05, | |
| "loss": 0.188, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 80.82, | |
| "learning_rate": 2.101723413198823e-05, | |
| "loss": 0.1883, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 80.98, | |
| "learning_rate": 2.0947176684881604e-05, | |
| "loss": 0.1715, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.8874856486796785, | |
| "eval_loss": 0.3830375671386719, | |
| "eval_runtime": 22.1479, | |
| "eval_samples_per_second": 39.327, | |
| "eval_steps_per_second": 1.264, | |
| "step": 4941 | |
| }, | |
| { | |
| "epoch": 81.15, | |
| "learning_rate": 2.0877119237774975e-05, | |
| "loss": 0.1842, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 81.31, | |
| "learning_rate": 2.080706179066835e-05, | |
| "loss": 0.1833, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 81.47, | |
| "learning_rate": 2.0737004343561723e-05, | |
| "loss": 0.2009, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 81.64, | |
| "learning_rate": 2.0666946896455093e-05, | |
| "loss": 0.1966, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 81.8, | |
| "learning_rate": 2.0596889449348467e-05, | |
| "loss": 0.1986, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 81.96, | |
| "learning_rate": 2.0526832002241838e-05, | |
| "loss": 0.1803, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.8966704936854191, | |
| "eval_loss": 0.3133516311645508, | |
| "eval_runtime": 21.9352, | |
| "eval_samples_per_second": 39.708, | |
| "eval_steps_per_second": 1.276, | |
| "step": 5002 | |
| }, | |
| { | |
| "epoch": 82.13, | |
| "learning_rate": 2.045677455513521e-05, | |
| "loss": 0.174, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 82.29, | |
| "learning_rate": 2.0386717108028585e-05, | |
| "loss": 0.1689, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 82.46, | |
| "learning_rate": 2.031665966092196e-05, | |
| "loss": 0.1856, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 82.62, | |
| "learning_rate": 2.024660221381533e-05, | |
| "loss": 0.1916, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 82.78, | |
| "learning_rate": 2.01765447667087e-05, | |
| "loss": 0.1763, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 82.95, | |
| "learning_rate": 2.0106487319602074e-05, | |
| "loss": 0.1803, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.8909299655568312, | |
| "eval_loss": 0.3935208320617676, | |
| "eval_runtime": 22.1541, | |
| "eval_samples_per_second": 39.316, | |
| "eval_steps_per_second": 1.264, | |
| "step": 5063 | |
| }, | |
| { | |
| "epoch": 83.11, | |
| "learning_rate": 2.0036429872495445e-05, | |
| "loss": 0.169, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 83.28, | |
| "learning_rate": 1.996637242538882e-05, | |
| "loss": 0.1821, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 83.44, | |
| "learning_rate": 1.9896314978282193e-05, | |
| "loss": 0.1984, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 83.6, | |
| "learning_rate": 1.9826257531175567e-05, | |
| "loss": 0.1632, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 83.77, | |
| "learning_rate": 1.9756200084068937e-05, | |
| "loss": 0.1741, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 83.93, | |
| "learning_rate": 1.968614263696231e-05, | |
| "loss": 0.1865, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.886337543053961, | |
| "eval_loss": 0.3881831765174866, | |
| "eval_runtime": 21.9885, | |
| "eval_samples_per_second": 39.612, | |
| "eval_steps_per_second": 1.273, | |
| "step": 5124 | |
| }, | |
| { | |
| "epoch": 84.1, | |
| "learning_rate": 1.961608518985568e-05, | |
| "loss": 0.2022, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 84.26, | |
| "learning_rate": 1.9546027742749056e-05, | |
| "loss": 0.185, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 84.42, | |
| "learning_rate": 1.947597029564243e-05, | |
| "loss": 0.1989, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 84.59, | |
| "learning_rate": 1.94059128485358e-05, | |
| "loss": 0.1852, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 84.75, | |
| "learning_rate": 1.9335855401429174e-05, | |
| "loss": 0.163, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 84.91, | |
| "learning_rate": 1.9265797954322544e-05, | |
| "loss": 0.1884, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.8989667049368542, | |
| "eval_loss": 0.34847477078437805, | |
| "eval_runtime": 22.055, | |
| "eval_samples_per_second": 39.492, | |
| "eval_steps_per_second": 1.27, | |
| "step": 5185 | |
| }, | |
| { | |
| "epoch": 85.08, | |
| "learning_rate": 1.919574050721592e-05, | |
| "loss": 0.1861, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 85.24, | |
| "learning_rate": 1.912568306010929e-05, | |
| "loss": 0.1826, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 85.41, | |
| "learning_rate": 1.9055625613002663e-05, | |
| "loss": 0.1824, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 85.57, | |
| "learning_rate": 1.8985568165896037e-05, | |
| "loss": 0.1682, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 85.73, | |
| "learning_rate": 1.8915510718789407e-05, | |
| "loss": 0.1603, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 85.9, | |
| "learning_rate": 1.884545327168278e-05, | |
| "loss": 0.1663, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.894374282433984, | |
| "eval_loss": 0.36672815680503845, | |
| "eval_runtime": 22.0116, | |
| "eval_samples_per_second": 39.57, | |
| "eval_steps_per_second": 1.272, | |
| "step": 5246 | |
| }, | |
| { | |
| "epoch": 86.07, | |
| "learning_rate": 1.8775395824576152e-05, | |
| "loss": 0.1737, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 86.23, | |
| "learning_rate": 1.8705338377469526e-05, | |
| "loss": 0.1602, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 86.39, | |
| "learning_rate": 1.8635280930362896e-05, | |
| "loss": 0.1972, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 86.56, | |
| "learning_rate": 1.8565223483256274e-05, | |
| "loss": 0.1558, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 86.72, | |
| "learning_rate": 1.8495166036149644e-05, | |
| "loss": 0.1908, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 86.88, | |
| "learning_rate": 1.8425108589043018e-05, | |
| "loss": 0.1665, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.8932261768082663, | |
| "eval_loss": 0.35452085733413696, | |
| "eval_runtime": 23.5614, | |
| "eval_samples_per_second": 36.967, | |
| "eval_steps_per_second": 1.188, | |
| "step": 5307 | |
| }, | |
| { | |
| "epoch": 87.05, | |
| "learning_rate": 1.835505114193639e-05, | |
| "loss": 0.1724, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 87.21, | |
| "learning_rate": 1.828499369482976e-05, | |
| "loss": 0.1567, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 87.38, | |
| "learning_rate": 1.8214936247723133e-05, | |
| "loss": 0.1814, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 87.54, | |
| "learning_rate": 1.8144878800616507e-05, | |
| "loss": 0.1808, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 87.7, | |
| "learning_rate": 1.807482135350988e-05, | |
| "loss": 0.1575, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 87.87, | |
| "learning_rate": 1.800476390640325e-05, | |
| "loss": 0.1556, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.894374282433984, | |
| "eval_loss": 0.3881751000881195, | |
| "eval_runtime": 21.9972, | |
| "eval_samples_per_second": 39.596, | |
| "eval_steps_per_second": 1.273, | |
| "step": 5368 | |
| }, | |
| { | |
| "epoch": 88.03, | |
| "learning_rate": 1.7934706459296625e-05, | |
| "loss": 0.1599, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 88.2, | |
| "learning_rate": 1.7864649012189996e-05, | |
| "loss": 0.1823, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 88.36, | |
| "learning_rate": 1.779459156508337e-05, | |
| "loss": 0.1805, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 88.52, | |
| "learning_rate": 1.772453411797674e-05, | |
| "loss": 0.1683, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 88.69, | |
| "learning_rate": 1.7654476670870114e-05, | |
| "loss": 0.1845, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 88.85, | |
| "learning_rate": 1.7584419223763488e-05, | |
| "loss": 0.18, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.8897818599311137, | |
| "eval_loss": 0.375090628862381, | |
| "eval_runtime": 22.1144, | |
| "eval_samples_per_second": 39.386, | |
| "eval_steps_per_second": 1.266, | |
| "step": 5429 | |
| }, | |
| { | |
| "epoch": 89.02, | |
| "learning_rate": 1.751436177665686e-05, | |
| "loss": 0.1823, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 89.18, | |
| "learning_rate": 1.7444304329550233e-05, | |
| "loss": 0.1509, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 89.34, | |
| "learning_rate": 1.7374246882443603e-05, | |
| "loss": 0.1654, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 89.51, | |
| "learning_rate": 1.7304189435336977e-05, | |
| "loss": 0.2008, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 89.67, | |
| "learning_rate": 1.723413198823035e-05, | |
| "loss": 0.1676, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 89.83, | |
| "learning_rate": 1.716407454112372e-05, | |
| "loss": 0.193, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "learning_rate": 1.7094017094017095e-05, | |
| "loss": 0.1974, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.886337543053961, | |
| "eval_loss": 0.3979399800300598, | |
| "eval_runtime": 22.1015, | |
| "eval_samples_per_second": 39.409, | |
| "eval_steps_per_second": 1.267, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 90.16, | |
| "learning_rate": 1.7023959646910466e-05, | |
| "loss": 0.2104, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 90.33, | |
| "learning_rate": 1.695390219980384e-05, | |
| "loss": 0.1852, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 90.49, | |
| "learning_rate": 1.688384475269721e-05, | |
| "loss": 0.1611, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 90.65, | |
| "learning_rate": 1.6813787305590588e-05, | |
| "loss": 0.1649, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 90.82, | |
| "learning_rate": 1.6743729858483958e-05, | |
| "loss": 0.17, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 90.98, | |
| "learning_rate": 1.6673672411377332e-05, | |
| "loss": 0.1622, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.8966704936854191, | |
| "eval_loss": 0.36226746439933777, | |
| "eval_runtime": 23.282, | |
| "eval_samples_per_second": 37.411, | |
| "eval_steps_per_second": 1.203, | |
| "step": 5551 | |
| }, | |
| { | |
| "epoch": 91.15, | |
| "learning_rate": 1.6603614964270703e-05, | |
| "loss": 0.17, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 91.31, | |
| "learning_rate": 1.6533557517164077e-05, | |
| "loss": 0.1659, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 91.47, | |
| "learning_rate": 1.6463500070057447e-05, | |
| "loss": 0.1583, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 91.64, | |
| "learning_rate": 1.6393442622950818e-05, | |
| "loss": 0.1711, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 91.8, | |
| "learning_rate": 1.6323385175844195e-05, | |
| "loss": 0.1656, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 91.96, | |
| "learning_rate": 1.6253327728737565e-05, | |
| "loss": 0.1657, | |
| "step": 5610 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.8978185993111366, | |
| "eval_loss": 0.3854539394378662, | |
| "eval_runtime": 21.8358, | |
| "eval_samples_per_second": 39.889, | |
| "eval_steps_per_second": 1.282, | |
| "step": 5612 | |
| }, | |
| { | |
| "epoch": 92.13, | |
| "learning_rate": 1.618327028163094e-05, | |
| "loss": 0.1552, | |
| "step": 5620 | |
| }, | |
| { | |
| "epoch": 92.29, | |
| "learning_rate": 1.611321283452431e-05, | |
| "loss": 0.1468, | |
| "step": 5630 | |
| }, | |
| { | |
| "epoch": 92.46, | |
| "learning_rate": 1.6043155387417684e-05, | |
| "loss": 0.1773, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 92.62, | |
| "learning_rate": 1.5973097940311054e-05, | |
| "loss": 0.1656, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 92.78, | |
| "learning_rate": 1.5903040493204428e-05, | |
| "loss": 0.1503, | |
| "step": 5660 | |
| }, | |
| { | |
| "epoch": 92.95, | |
| "learning_rate": 1.5832983046097802e-05, | |
| "loss": 0.1672, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.894374282433984, | |
| "eval_loss": 0.37218040227890015, | |
| "eval_runtime": 22.1418, | |
| "eval_samples_per_second": 39.337, | |
| "eval_steps_per_second": 1.265, | |
| "step": 5673 | |
| }, | |
| { | |
| "epoch": 93.11, | |
| "learning_rate": 1.5762925598991173e-05, | |
| "loss": 0.168, | |
| "step": 5680 | |
| }, | |
| { | |
| "epoch": 93.28, | |
| "learning_rate": 1.5692868151884547e-05, | |
| "loss": 0.1626, | |
| "step": 5690 | |
| }, | |
| { | |
| "epoch": 93.44, | |
| "learning_rate": 1.5622810704777917e-05, | |
| "loss": 0.1659, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 93.6, | |
| "learning_rate": 1.555275325767129e-05, | |
| "loss": 0.1693, | |
| "step": 5710 | |
| }, | |
| { | |
| "epoch": 93.77, | |
| "learning_rate": 1.548269581056466e-05, | |
| "loss": 0.1595, | |
| "step": 5720 | |
| }, | |
| { | |
| "epoch": 93.93, | |
| "learning_rate": 1.541263836345804e-05, | |
| "loss": 0.1807, | |
| "step": 5730 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.8932261768082663, | |
| "eval_loss": 0.39940062165260315, | |
| "eval_runtime": 23.7713, | |
| "eval_samples_per_second": 36.641, | |
| "eval_steps_per_second": 1.178, | |
| "step": 5734 | |
| }, | |
| { | |
| "epoch": 94.1, | |
| "learning_rate": 1.534258091635141e-05, | |
| "loss": 0.1654, | |
| "step": 5740 | |
| }, | |
| { | |
| "epoch": 94.26, | |
| "learning_rate": 1.527252346924478e-05, | |
| "loss": 0.1556, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 94.42, | |
| "learning_rate": 1.5202466022138154e-05, | |
| "loss": 0.1644, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 94.59, | |
| "learning_rate": 1.5132408575031526e-05, | |
| "loss": 0.1747, | |
| "step": 5770 | |
| }, | |
| { | |
| "epoch": 94.75, | |
| "learning_rate": 1.5062351127924898e-05, | |
| "loss": 0.1711, | |
| "step": 5780 | |
| }, | |
| { | |
| "epoch": 94.91, | |
| "learning_rate": 1.4992293680818272e-05, | |
| "loss": 0.1419, | |
| "step": 5790 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.886337543053961, | |
| "eval_loss": 0.40166935324668884, | |
| "eval_runtime": 22.2236, | |
| "eval_samples_per_second": 39.192, | |
| "eval_steps_per_second": 1.26, | |
| "step": 5795 | |
| }, | |
| { | |
| "epoch": 95.08, | |
| "learning_rate": 1.4922236233711645e-05, | |
| "loss": 0.1748, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 95.24, | |
| "learning_rate": 1.4852178786605017e-05, | |
| "loss": 0.1521, | |
| "step": 5810 | |
| }, | |
| { | |
| "epoch": 95.41, | |
| "learning_rate": 1.4782121339498389e-05, | |
| "loss": 0.1582, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 95.57, | |
| "learning_rate": 1.4712063892391761e-05, | |
| "loss": 0.15, | |
| "step": 5830 | |
| }, | |
| { | |
| "epoch": 95.73, | |
| "learning_rate": 1.4642006445285133e-05, | |
| "loss": 0.1828, | |
| "step": 5840 | |
| }, | |
| { | |
| "epoch": 95.9, | |
| "learning_rate": 1.4571948998178509e-05, | |
| "loss": 0.178, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.8886337543053962, | |
| "eval_loss": 0.4167952537536621, | |
| "eval_runtime": 21.8164, | |
| "eval_samples_per_second": 39.924, | |
| "eval_steps_per_second": 1.283, | |
| "step": 5856 | |
| }, | |
| { | |
| "epoch": 96.07, | |
| "learning_rate": 1.4501891551071881e-05, | |
| "loss": 0.1464, | |
| "step": 5860 | |
| }, | |
| { | |
| "epoch": 96.23, | |
| "learning_rate": 1.4431834103965254e-05, | |
| "loss": 0.153, | |
| "step": 5870 | |
| }, | |
| { | |
| "epoch": 96.39, | |
| "learning_rate": 1.4361776656858624e-05, | |
| "loss": 0.1566, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 96.56, | |
| "learning_rate": 1.4291719209751996e-05, | |
| "loss": 0.1652, | |
| "step": 5890 | |
| }, | |
| { | |
| "epoch": 96.72, | |
| "learning_rate": 1.4221661762645369e-05, | |
| "loss": 0.1454, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 96.88, | |
| "learning_rate": 1.415160431553874e-05, | |
| "loss": 0.1402, | |
| "step": 5910 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.894374282433984, | |
| "eval_loss": 0.37266284227371216, | |
| "eval_runtime": 22.0238, | |
| "eval_samples_per_second": 39.548, | |
| "eval_steps_per_second": 1.271, | |
| "step": 5917 | |
| }, | |
| { | |
| "epoch": 97.05, | |
| "learning_rate": 1.4081546868432116e-05, | |
| "loss": 0.1698, | |
| "step": 5920 | |
| }, | |
| { | |
| "epoch": 97.21, | |
| "learning_rate": 1.4011489421325489e-05, | |
| "loss": 0.1572, | |
| "step": 5930 | |
| }, | |
| { | |
| "epoch": 97.38, | |
| "learning_rate": 1.394143197421886e-05, | |
| "loss": 0.1587, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 97.54, | |
| "learning_rate": 1.3871374527112233e-05, | |
| "loss": 0.1599, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 97.7, | |
| "learning_rate": 1.3801317080005605e-05, | |
| "loss": 0.1371, | |
| "step": 5960 | |
| }, | |
| { | |
| "epoch": 97.87, | |
| "learning_rate": 1.3731259632898977e-05, | |
| "loss": 0.1427, | |
| "step": 5970 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.8966704936854191, | |
| "eval_loss": 0.3918587863445282, | |
| "eval_runtime": 22.7379, | |
| "eval_samples_per_second": 38.306, | |
| "eval_steps_per_second": 1.231, | |
| "step": 5978 | |
| }, | |
| { | |
| "epoch": 98.03, | |
| "learning_rate": 1.3661202185792351e-05, | |
| "loss": 0.186, | |
| "step": 5980 | |
| }, | |
| { | |
| "epoch": 98.2, | |
| "learning_rate": 1.3591144738685724e-05, | |
| "loss": 0.1638, | |
| "step": 5990 | |
| }, | |
| { | |
| "epoch": 98.36, | |
| "learning_rate": 1.3521087291579096e-05, | |
| "loss": 0.1701, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 98.52, | |
| "learning_rate": 1.3451029844472468e-05, | |
| "loss": 0.1596, | |
| "step": 6010 | |
| }, | |
| { | |
| "epoch": 98.69, | |
| "learning_rate": 1.338097239736584e-05, | |
| "loss": 0.1388, | |
| "step": 6020 | |
| }, | |
| { | |
| "epoch": 98.85, | |
| "learning_rate": 1.3310914950259213e-05, | |
| "loss": 0.1318, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.8955223880597015, | |
| "eval_loss": 0.3843202292919159, | |
| "eval_runtime": 22.4002, | |
| "eval_samples_per_second": 38.884, | |
| "eval_steps_per_second": 1.25, | |
| "step": 6039 | |
| }, | |
| { | |
| "epoch": 99.02, | |
| "learning_rate": 1.3240857503152585e-05, | |
| "loss": 0.17, | |
| "step": 6040 | |
| }, | |
| { | |
| "epoch": 99.18, | |
| "learning_rate": 1.3170800056045959e-05, | |
| "loss": 0.1572, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 99.34, | |
| "learning_rate": 1.3100742608939331e-05, | |
| "loss": 0.163, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 99.51, | |
| "learning_rate": 1.3030685161832703e-05, | |
| "loss": 0.1461, | |
| "step": 6070 | |
| }, | |
| { | |
| "epoch": 99.67, | |
| "learning_rate": 1.2960627714726075e-05, | |
| "loss": 0.1571, | |
| "step": 6080 | |
| }, | |
| { | |
| "epoch": 99.83, | |
| "learning_rate": 1.2890570267619448e-05, | |
| "loss": 0.1735, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "learning_rate": 1.282051282051282e-05, | |
| "loss": 0.1417, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.8897818599311137, | |
| "eval_loss": 0.4016599655151367, | |
| "eval_runtime": 22.1786, | |
| "eval_samples_per_second": 39.272, | |
| "eval_steps_per_second": 1.262, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 100.16, | |
| "learning_rate": 1.2750455373406195e-05, | |
| "loss": 0.1551, | |
| "step": 6110 | |
| }, | |
| { | |
| "epoch": 100.33, | |
| "learning_rate": 1.2680397926299568e-05, | |
| "loss": 0.166, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 100.49, | |
| "learning_rate": 1.261034047919294e-05, | |
| "loss": 0.1446, | |
| "step": 6130 | |
| }, | |
| { | |
| "epoch": 100.65, | |
| "learning_rate": 1.2540283032086312e-05, | |
| "loss": 0.1572, | |
| "step": 6140 | |
| }, | |
| { | |
| "epoch": 100.82, | |
| "learning_rate": 1.2470225584979683e-05, | |
| "loss": 0.147, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 100.98, | |
| "learning_rate": 1.2400168137873057e-05, | |
| "loss": 0.1536, | |
| "step": 6160 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_accuracy": 0.8955223880597015, | |
| "eval_loss": 0.3612852096557617, | |
| "eval_runtime": 22.0285, | |
| "eval_samples_per_second": 39.54, | |
| "eval_steps_per_second": 1.271, | |
| "step": 6161 | |
| }, | |
| { | |
| "epoch": 101.15, | |
| "learning_rate": 1.2330110690766429e-05, | |
| "loss": 0.1518, | |
| "step": 6170 | |
| }, | |
| { | |
| "epoch": 101.31, | |
| "learning_rate": 1.2260053243659801e-05, | |
| "loss": 0.1627, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 101.47, | |
| "learning_rate": 1.2189995796553175e-05, | |
| "loss": 0.1663, | |
| "step": 6190 | |
| }, | |
| { | |
| "epoch": 101.64, | |
| "learning_rate": 1.2119938349446547e-05, | |
| "loss": 0.1575, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 101.8, | |
| "learning_rate": 1.204988090233992e-05, | |
| "loss": 0.1484, | |
| "step": 6210 | |
| }, | |
| { | |
| "epoch": 101.96, | |
| "learning_rate": 1.1979823455233292e-05, | |
| "loss": 0.1631, | |
| "step": 6220 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_accuracy": 0.904707233065442, | |
| "eval_loss": 0.3377176821231842, | |
| "eval_runtime": 23.7426, | |
| "eval_samples_per_second": 36.685, | |
| "eval_steps_per_second": 1.179, | |
| "step": 6222 | |
| }, | |
| { | |
| "epoch": 102.13, | |
| "learning_rate": 1.1909766008126664e-05, | |
| "loss": 0.16, | |
| "step": 6230 | |
| }, | |
| { | |
| "epoch": 102.29, | |
| "learning_rate": 1.1839708561020036e-05, | |
| "loss": 0.165, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 102.46, | |
| "learning_rate": 1.176965111391341e-05, | |
| "loss": 0.1702, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 102.62, | |
| "learning_rate": 1.1699593666806782e-05, | |
| "loss": 0.152, | |
| "step": 6260 | |
| }, | |
| { | |
| "epoch": 102.78, | |
| "learning_rate": 1.1629536219700154e-05, | |
| "loss": 0.1512, | |
| "step": 6270 | |
| }, | |
| { | |
| "epoch": 102.95, | |
| "learning_rate": 1.1559478772593527e-05, | |
| "loss": 0.1459, | |
| "step": 6280 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_accuracy": 0.8966704936854191, | |
| "eval_loss": 0.3723713457584381, | |
| "eval_runtime": 22.2769, | |
| "eval_samples_per_second": 39.099, | |
| "eval_steps_per_second": 1.257, | |
| "step": 6283 | |
| }, | |
| { | |
| "epoch": 103.11, | |
| "learning_rate": 1.14894213254869e-05, | |
| "loss": 0.1328, | |
| "step": 6290 | |
| }, | |
| { | |
| "epoch": 103.28, | |
| "learning_rate": 1.1419363878380273e-05, | |
| "loss": 0.1491, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 103.44, | |
| "learning_rate": 1.1349306431273645e-05, | |
| "loss": 0.1425, | |
| "step": 6310 | |
| }, | |
| { | |
| "epoch": 103.6, | |
| "learning_rate": 1.1279248984167017e-05, | |
| "loss": 0.1346, | |
| "step": 6320 | |
| }, | |
| { | |
| "epoch": 103.77, | |
| "learning_rate": 1.120919153706039e-05, | |
| "loss": 0.1667, | |
| "step": 6330 | |
| }, | |
| { | |
| "epoch": 103.93, | |
| "learning_rate": 1.1139134089953762e-05, | |
| "loss": 0.1499, | |
| "step": 6340 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_accuracy": 0.8955223880597015, | |
| "eval_loss": 0.3933733403682709, | |
| "eval_runtime": 24.3235, | |
| "eval_samples_per_second": 35.809, | |
| "eval_steps_per_second": 1.151, | |
| "step": 6344 | |
| }, | |
| { | |
| "epoch": 104.1, | |
| "learning_rate": 1.1069076642847136e-05, | |
| "loss": 0.1377, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 104.26, | |
| "learning_rate": 1.0999019195740508e-05, | |
| "loss": 0.1429, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 104.42, | |
| "learning_rate": 1.092896174863388e-05, | |
| "loss": 0.1565, | |
| "step": 6370 | |
| }, | |
| { | |
| "epoch": 104.59, | |
| "learning_rate": 1.0858904301527254e-05, | |
| "loss": 0.1532, | |
| "step": 6380 | |
| }, | |
| { | |
| "epoch": 104.75, | |
| "learning_rate": 1.0788846854420626e-05, | |
| "loss": 0.1677, | |
| "step": 6390 | |
| }, | |
| { | |
| "epoch": 104.91, | |
| "learning_rate": 1.0718789407313998e-05, | |
| "loss": 0.1572, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_accuracy": 0.8966704936854191, | |
| "eval_loss": 0.3368474245071411, | |
| "eval_runtime": 22.4129, | |
| "eval_samples_per_second": 38.862, | |
| "eval_steps_per_second": 1.249, | |
| "step": 6405 | |
| }, | |
| { | |
| "epoch": 105.08, | |
| "learning_rate": 1.064873196020737e-05, | |
| "loss": 0.1453, | |
| "step": 6410 | |
| }, | |
| { | |
| "epoch": 105.24, | |
| "learning_rate": 1.0578674513100743e-05, | |
| "loss": 0.1486, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 105.41, | |
| "learning_rate": 1.0508617065994115e-05, | |
| "loss": 0.1578, | |
| "step": 6430 | |
| }, | |
| { | |
| "epoch": 105.57, | |
| "learning_rate": 1.0438559618887487e-05, | |
| "loss": 0.1382, | |
| "step": 6440 | |
| }, | |
| { | |
| "epoch": 105.73, | |
| "learning_rate": 1.0368502171780861e-05, | |
| "loss": 0.1243, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 105.9, | |
| "learning_rate": 1.0298444724674234e-05, | |
| "loss": 0.1308, | |
| "step": 6460 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_accuracy": 0.8989667049368542, | |
| "eval_loss": 0.3782079517841339, | |
| "eval_runtime": 22.4333, | |
| "eval_samples_per_second": 38.826, | |
| "eval_steps_per_second": 1.248, | |
| "step": 6466 | |
| }, | |
| { | |
| "epoch": 106.07, | |
| "learning_rate": 1.0228387277567606e-05, | |
| "loss": 0.165, | |
| "step": 6470 | |
| }, | |
| { | |
| "epoch": 106.23, | |
| "learning_rate": 1.015832983046098e-05, | |
| "loss": 0.1689, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 106.39, | |
| "learning_rate": 1.008827238335435e-05, | |
| "loss": 0.121, | |
| "step": 6490 | |
| }, | |
| { | |
| "epoch": 106.56, | |
| "learning_rate": 1.0018214936247722e-05, | |
| "loss": 0.1287, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 106.72, | |
| "learning_rate": 9.948157489141096e-06, | |
| "loss": 0.1408, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 106.88, | |
| "learning_rate": 9.878100042034469e-06, | |
| "loss": 0.1535, | |
| "step": 6520 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_accuracy": 0.9024110218140069, | |
| "eval_loss": 0.33055686950683594, | |
| "eval_runtime": 22.1614, | |
| "eval_samples_per_second": 39.303, | |
| "eval_steps_per_second": 1.263, | |
| "step": 6527 | |
| }, | |
| { | |
| "epoch": 107.05, | |
| "learning_rate": 9.80804259492784e-06, | |
| "loss": 0.165, | |
| "step": 6530 | |
| }, | |
| { | |
| "epoch": 107.21, | |
| "learning_rate": 9.737985147821215e-06, | |
| "loss": 0.1605, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 107.38, | |
| "learning_rate": 9.667927700714587e-06, | |
| "loss": 0.1372, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 107.54, | |
| "learning_rate": 9.59787025360796e-06, | |
| "loss": 0.1332, | |
| "step": 6560 | |
| }, | |
| { | |
| "epoch": 107.7, | |
| "learning_rate": 9.527812806501331e-06, | |
| "loss": 0.148, | |
| "step": 6570 | |
| }, | |
| { | |
| "epoch": 107.87, | |
| "learning_rate": 9.457755359394704e-06, | |
| "loss": 0.125, | |
| "step": 6580 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_accuracy": 0.8897818599311137, | |
| "eval_loss": 0.40762317180633545, | |
| "eval_runtime": 23.7991, | |
| "eval_samples_per_second": 36.598, | |
| "eval_steps_per_second": 1.177, | |
| "step": 6588 | |
| }, | |
| { | |
| "epoch": 108.03, | |
| "learning_rate": 9.387697912288076e-06, | |
| "loss": 0.1506, | |
| "step": 6590 | |
| }, | |
| { | |
| "epoch": 108.2, | |
| "learning_rate": 9.317640465181448e-06, | |
| "loss": 0.129, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 108.36, | |
| "learning_rate": 9.247583018074822e-06, | |
| "loss": 0.1473, | |
| "step": 6610 | |
| }, | |
| { | |
| "epoch": 108.52, | |
| "learning_rate": 9.177525570968194e-06, | |
| "loss": 0.1467, | |
| "step": 6620 | |
| }, | |
| { | |
| "epoch": 108.69, | |
| "learning_rate": 9.107468123861566e-06, | |
| "loss": 0.1402, | |
| "step": 6630 | |
| }, | |
| { | |
| "epoch": 108.85, | |
| "learning_rate": 9.03741067675494e-06, | |
| "loss": 0.1339, | |
| "step": 6640 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_accuracy": 0.8989667049368542, | |
| "eval_loss": 0.3628109395503998, | |
| "eval_runtime": 22.1456, | |
| "eval_samples_per_second": 39.331, | |
| "eval_steps_per_second": 1.264, | |
| "step": 6649 | |
| }, | |
| { | |
| "epoch": 109.02, | |
| "learning_rate": 8.967353229648313e-06, | |
| "loss": 0.1544, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 109.18, | |
| "learning_rate": 8.897295782541685e-06, | |
| "loss": 0.149, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 109.34, | |
| "learning_rate": 8.827238335435057e-06, | |
| "loss": 0.1466, | |
| "step": 6670 | |
| }, | |
| { | |
| "epoch": 109.51, | |
| "learning_rate": 8.75718088832843e-06, | |
| "loss": 0.1296, | |
| "step": 6680 | |
| }, | |
| { | |
| "epoch": 109.67, | |
| "learning_rate": 8.687123441221802e-06, | |
| "loss": 0.1441, | |
| "step": 6690 | |
| }, | |
| { | |
| "epoch": 109.83, | |
| "learning_rate": 8.617065994115175e-06, | |
| "loss": 0.1568, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "learning_rate": 8.547008547008548e-06, | |
| "loss": 0.148, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_accuracy": 0.9012629161882894, | |
| "eval_loss": 0.36718717217445374, | |
| "eval_runtime": 22.5177, | |
| "eval_samples_per_second": 38.681, | |
| "eval_steps_per_second": 1.243, | |
| "step": 6710 | |
| }, | |
| { | |
| "epoch": 110.16, | |
| "learning_rate": 8.47695109990192e-06, | |
| "loss": 0.1394, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 110.33, | |
| "learning_rate": 8.406893652795294e-06, | |
| "loss": 0.1476, | |
| "step": 6730 | |
| }, | |
| { | |
| "epoch": 110.49, | |
| "learning_rate": 8.336836205688666e-06, | |
| "loss": 0.1415, | |
| "step": 6740 | |
| }, | |
| { | |
| "epoch": 110.65, | |
| "learning_rate": 8.266778758582038e-06, | |
| "loss": 0.1527, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 110.82, | |
| "learning_rate": 8.196721311475409e-06, | |
| "loss": 0.1605, | |
| "step": 6760 | |
| }, | |
| { | |
| "epoch": 110.98, | |
| "learning_rate": 8.126663864368783e-06, | |
| "loss": 0.1725, | |
| "step": 6770 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_accuracy": 0.8909299655568312, | |
| "eval_loss": 0.40064239501953125, | |
| "eval_runtime": 22.5208, | |
| "eval_samples_per_second": 38.675, | |
| "eval_steps_per_second": 1.243, | |
| "step": 6771 | |
| }, | |
| { | |
| "epoch": 111.15, | |
| "learning_rate": 8.056606417262155e-06, | |
| "loss": 0.1404, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 111.31, | |
| "learning_rate": 7.986548970155527e-06, | |
| "loss": 0.1538, | |
| "step": 6790 | |
| }, | |
| { | |
| "epoch": 111.47, | |
| "learning_rate": 7.916491523048901e-06, | |
| "loss": 0.1379, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 111.64, | |
| "learning_rate": 7.846434075942273e-06, | |
| "loss": 0.1331, | |
| "step": 6810 | |
| }, | |
| { | |
| "epoch": 111.8, | |
| "learning_rate": 7.776376628835646e-06, | |
| "loss": 0.1434, | |
| "step": 6820 | |
| }, | |
| { | |
| "epoch": 111.96, | |
| "learning_rate": 7.70631918172902e-06, | |
| "loss": 0.1326, | |
| "step": 6830 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_accuracy": 0.8920780711825488, | |
| "eval_loss": 0.4116767942905426, | |
| "eval_runtime": 22.3028, | |
| "eval_samples_per_second": 39.053, | |
| "eval_steps_per_second": 1.255, | |
| "step": 6832 | |
| }, | |
| { | |
| "epoch": 112.13, | |
| "learning_rate": 7.63626173462239e-06, | |
| "loss": 0.1455, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 112.29, | |
| "learning_rate": 7.566204287515763e-06, | |
| "loss": 0.1373, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 112.46, | |
| "learning_rate": 7.496146840409136e-06, | |
| "loss": 0.1399, | |
| "step": 6860 | |
| }, | |
| { | |
| "epoch": 112.62, | |
| "learning_rate": 7.426089393302508e-06, | |
| "loss": 0.1372, | |
| "step": 6870 | |
| }, | |
| { | |
| "epoch": 112.78, | |
| "learning_rate": 7.356031946195881e-06, | |
| "loss": 0.1395, | |
| "step": 6880 | |
| }, | |
| { | |
| "epoch": 112.95, | |
| "learning_rate": 7.2859744990892545e-06, | |
| "loss": 0.1438, | |
| "step": 6890 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_accuracy": 0.8978185993111366, | |
| "eval_loss": 0.39274829626083374, | |
| "eval_runtime": 22.447, | |
| "eval_samples_per_second": 38.802, | |
| "eval_steps_per_second": 1.247, | |
| "step": 6893 | |
| }, | |
| { | |
| "epoch": 113.11, | |
| "learning_rate": 7.215917051982627e-06, | |
| "loss": 0.157, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 113.28, | |
| "learning_rate": 7.145859604875998e-06, | |
| "loss": 0.1458, | |
| "step": 6910 | |
| }, | |
| { | |
| "epoch": 113.44, | |
| "learning_rate": 7.07580215776937e-06, | |
| "loss": 0.1359, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 113.6, | |
| "learning_rate": 7.005744710662744e-06, | |
| "loss": 0.1507, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 113.77, | |
| "learning_rate": 6.9356872635561165e-06, | |
| "loss": 0.143, | |
| "step": 6940 | |
| }, | |
| { | |
| "epoch": 113.93, | |
| "learning_rate": 6.865629816449489e-06, | |
| "loss": 0.1205, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_accuracy": 0.8989667049368542, | |
| "eval_loss": 0.3611946105957031, | |
| "eval_runtime": 22.3139, | |
| "eval_samples_per_second": 39.034, | |
| "eval_steps_per_second": 1.255, | |
| "step": 6954 | |
| }, | |
| { | |
| "epoch": 114.1, | |
| "learning_rate": 6.795572369342862e-06, | |
| "loss": 0.1496, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 114.26, | |
| "learning_rate": 6.725514922236234e-06, | |
| "loss": 0.1508, | |
| "step": 6970 | |
| }, | |
| { | |
| "epoch": 114.42, | |
| "learning_rate": 6.655457475129606e-06, | |
| "loss": 0.1421, | |
| "step": 6980 | |
| }, | |
| { | |
| "epoch": 114.59, | |
| "learning_rate": 6.585400028022979e-06, | |
| "loss": 0.1251, | |
| "step": 6990 | |
| }, | |
| { | |
| "epoch": 114.75, | |
| "learning_rate": 6.5153425809163516e-06, | |
| "loss": 0.1366, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 114.91, | |
| "learning_rate": 6.445285133809724e-06, | |
| "loss": 0.1531, | |
| "step": 7010 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_accuracy": 0.8932261768082663, | |
| "eval_loss": 0.35941407084465027, | |
| "eval_runtime": 24.2519, | |
| "eval_samples_per_second": 35.915, | |
| "eval_steps_per_second": 1.155, | |
| "step": 7015 | |
| }, | |
| { | |
| "epoch": 115.08, | |
| "learning_rate": 6.375227686703098e-06, | |
| "loss": 0.1752, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 115.24, | |
| "learning_rate": 6.30517023959647e-06, | |
| "loss": 0.1415, | |
| "step": 7030 | |
| }, | |
| { | |
| "epoch": 115.41, | |
| "learning_rate": 6.235112792489841e-06, | |
| "loss": 0.1277, | |
| "step": 7040 | |
| }, | |
| { | |
| "epoch": 115.57, | |
| "learning_rate": 6.165055345383214e-06, | |
| "loss": 0.1187, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 115.73, | |
| "learning_rate": 6.0949978982765875e-06, | |
| "loss": 0.1278, | |
| "step": 7060 | |
| }, | |
| { | |
| "epoch": 115.9, | |
| "learning_rate": 6.02494045116996e-06, | |
| "loss": 0.1473, | |
| "step": 7070 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_accuracy": 0.8874856486796785, | |
| "eval_loss": 0.44904759526252747, | |
| "eval_runtime": 22.5676, | |
| "eval_samples_per_second": 38.595, | |
| "eval_steps_per_second": 1.241, | |
| "step": 7076 | |
| }, | |
| { | |
| "epoch": 116.07, | |
| "learning_rate": 5.954883004063332e-06, | |
| "loss": 0.1505, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 116.23, | |
| "learning_rate": 5.884825556956705e-06, | |
| "loss": 0.1462, | |
| "step": 7090 | |
| }, | |
| { | |
| "epoch": 116.39, | |
| "learning_rate": 5.814768109850077e-06, | |
| "loss": 0.1568, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 116.56, | |
| "learning_rate": 5.74471066274345e-06, | |
| "loss": 0.1533, | |
| "step": 7110 | |
| }, | |
| { | |
| "epoch": 116.72, | |
| "learning_rate": 5.6746532156368225e-06, | |
| "loss": 0.1468, | |
| "step": 7120 | |
| }, | |
| { | |
| "epoch": 116.88, | |
| "learning_rate": 5.604595768530195e-06, | |
| "loss": 0.1388, | |
| "step": 7130 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_accuracy": 0.8920780711825488, | |
| "eval_loss": 0.39515480399131775, | |
| "eval_runtime": 22.408, | |
| "eval_samples_per_second": 38.87, | |
| "eval_steps_per_second": 1.25, | |
| "step": 7137 | |
| }, | |
| { | |
| "epoch": 117.05, | |
| "learning_rate": 5.534538321423568e-06, | |
| "loss": 0.1335, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 117.21, | |
| "learning_rate": 5.46448087431694e-06, | |
| "loss": 0.144, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 117.38, | |
| "learning_rate": 5.394423427210313e-06, | |
| "loss": 0.1303, | |
| "step": 7160 | |
| }, | |
| { | |
| "epoch": 117.54, | |
| "learning_rate": 5.324365980103685e-06, | |
| "loss": 0.1496, | |
| "step": 7170 | |
| }, | |
| { | |
| "epoch": 117.7, | |
| "learning_rate": 5.254308532997058e-06, | |
| "loss": 0.1247, | |
| "step": 7180 | |
| }, | |
| { | |
| "epoch": 117.87, | |
| "learning_rate": 5.184251085890431e-06, | |
| "loss": 0.136, | |
| "step": 7190 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_accuracy": 0.8920780711825488, | |
| "eval_loss": 0.40982648730278015, | |
| "eval_runtime": 23.9091, | |
| "eval_samples_per_second": 36.43, | |
| "eval_steps_per_second": 1.171, | |
| "step": 7198 | |
| }, | |
| { | |
| "epoch": 118.03, | |
| "learning_rate": 5.114193638783803e-06, | |
| "loss": 0.1348, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 118.2, | |
| "learning_rate": 5.044136191677175e-06, | |
| "loss": 0.1283, | |
| "step": 7210 | |
| }, | |
| { | |
| "epoch": 118.36, | |
| "learning_rate": 4.974078744570548e-06, | |
| "loss": 0.1505, | |
| "step": 7220 | |
| }, | |
| { | |
| "epoch": 118.52, | |
| "learning_rate": 4.90402129746392e-06, | |
| "loss": 0.14, | |
| "step": 7230 | |
| }, | |
| { | |
| "epoch": 118.69, | |
| "learning_rate": 4.8339638503572935e-06, | |
| "loss": 0.1299, | |
| "step": 7240 | |
| }, | |
| { | |
| "epoch": 118.85, | |
| "learning_rate": 4.763906403250666e-06, | |
| "loss": 0.1579, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_accuracy": 0.9012629161882894, | |
| "eval_loss": 0.359529972076416, | |
| "eval_runtime": 22.1968, | |
| "eval_samples_per_second": 39.24, | |
| "eval_steps_per_second": 1.261, | |
| "step": 7259 | |
| }, | |
| { | |
| "epoch": 119.02, | |
| "learning_rate": 4.693848956144038e-06, | |
| "loss": 0.1213, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 119.18, | |
| "learning_rate": 4.623791509037411e-06, | |
| "loss": 0.126, | |
| "step": 7270 | |
| }, | |
| { | |
| "epoch": 119.34, | |
| "learning_rate": 4.553734061930783e-06, | |
| "loss": 0.1356, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 119.51, | |
| "learning_rate": 4.483676614824156e-06, | |
| "loss": 0.1369, | |
| "step": 7290 | |
| }, | |
| { | |
| "epoch": 119.67, | |
| "learning_rate": 4.4136191677175285e-06, | |
| "loss": 0.1487, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 119.83, | |
| "learning_rate": 4.343561720610901e-06, | |
| "loss": 0.1296, | |
| "step": 7310 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "learning_rate": 4.273504273504274e-06, | |
| "loss": 0.1359, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_accuracy": 0.894374282433984, | |
| "eval_loss": 0.39699336886405945, | |
| "eval_runtime": 22.4895, | |
| "eval_samples_per_second": 38.729, | |
| "eval_steps_per_second": 1.245, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 120.16, | |
| "learning_rate": 4.203446826397647e-06, | |
| "loss": 0.1549, | |
| "step": 7330 | |
| }, | |
| { | |
| "epoch": 120.33, | |
| "learning_rate": 4.133389379291019e-06, | |
| "loss": 0.1411, | |
| "step": 7340 | |
| }, | |
| { | |
| "epoch": 120.49, | |
| "learning_rate": 4.063331932184391e-06, | |
| "loss": 0.1146, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 120.65, | |
| "learning_rate": 3.993274485077764e-06, | |
| "loss": 0.131, | |
| "step": 7360 | |
| }, | |
| { | |
| "epoch": 120.82, | |
| "learning_rate": 3.923217037971137e-06, | |
| "loss": 0.1166, | |
| "step": 7370 | |
| }, | |
| { | |
| "epoch": 120.98, | |
| "learning_rate": 3.85315959086451e-06, | |
| "loss": 0.1314, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 121.0, | |
| "eval_accuracy": 0.8932261768082663, | |
| "eval_loss": 0.4092465341091156, | |
| "eval_runtime": 23.8852, | |
| "eval_samples_per_second": 36.466, | |
| "eval_steps_per_second": 1.172, | |
| "step": 7381 | |
| }, | |
| { | |
| "epoch": 121.15, | |
| "learning_rate": 3.7831021437578815e-06, | |
| "loss": 0.1309, | |
| "step": 7390 | |
| }, | |
| { | |
| "epoch": 121.31, | |
| "learning_rate": 3.713044696651254e-06, | |
| "loss": 0.1477, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 121.47, | |
| "learning_rate": 3.6429872495446273e-06, | |
| "loss": 0.1412, | |
| "step": 7410 | |
| }, | |
| { | |
| "epoch": 121.64, | |
| "learning_rate": 3.572929802437999e-06, | |
| "loss": 0.1418, | |
| "step": 7420 | |
| }, | |
| { | |
| "epoch": 121.8, | |
| "learning_rate": 3.502872355331372e-06, | |
| "loss": 0.1331, | |
| "step": 7430 | |
| }, | |
| { | |
| "epoch": 121.96, | |
| "learning_rate": 3.4328149082247444e-06, | |
| "loss": 0.1337, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 122.0, | |
| "eval_accuracy": 0.8909299655568312, | |
| "eval_loss": 0.4191564619541168, | |
| "eval_runtime": 22.4509, | |
| "eval_samples_per_second": 38.796, | |
| "eval_steps_per_second": 1.247, | |
| "step": 7442 | |
| }, | |
| { | |
| "epoch": 122.13, | |
| "learning_rate": 3.362757461118117e-06, | |
| "loss": 0.1321, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 122.29, | |
| "learning_rate": 3.2927000140114897e-06, | |
| "loss": 0.1238, | |
| "step": 7460 | |
| }, | |
| { | |
| "epoch": 122.46, | |
| "learning_rate": 3.222642566904862e-06, | |
| "loss": 0.1199, | |
| "step": 7470 | |
| }, | |
| { | |
| "epoch": 122.62, | |
| "learning_rate": 3.152585119798235e-06, | |
| "loss": 0.1137, | |
| "step": 7480 | |
| }, | |
| { | |
| "epoch": 122.78, | |
| "learning_rate": 3.082527672691607e-06, | |
| "loss": 0.1331, | |
| "step": 7490 | |
| }, | |
| { | |
| "epoch": 122.95, | |
| "learning_rate": 3.01247022558498e-06, | |
| "loss": 0.1538, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 123.0, | |
| "eval_accuracy": 0.8897818599311137, | |
| "eval_loss": 0.4153917133808136, | |
| "eval_runtime": 22.5017, | |
| "eval_samples_per_second": 38.708, | |
| "eval_steps_per_second": 1.244, | |
| "step": 7503 | |
| }, | |
| { | |
| "epoch": 123.11, | |
| "learning_rate": 2.9424127784783525e-06, | |
| "loss": 0.1377, | |
| "step": 7510 | |
| }, | |
| { | |
| "epoch": 123.28, | |
| "learning_rate": 2.872355331371725e-06, | |
| "loss": 0.1372, | |
| "step": 7520 | |
| }, | |
| { | |
| "epoch": 123.44, | |
| "learning_rate": 2.8022978842650974e-06, | |
| "loss": 0.1445, | |
| "step": 7530 | |
| }, | |
| { | |
| "epoch": 123.6, | |
| "learning_rate": 2.73224043715847e-06, | |
| "loss": 0.1392, | |
| "step": 7540 | |
| }, | |
| { | |
| "epoch": 123.77, | |
| "learning_rate": 2.6621829900518427e-06, | |
| "loss": 0.1366, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 123.93, | |
| "learning_rate": 2.5921255429452153e-06, | |
| "loss": 0.119, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 124.0, | |
| "eval_accuracy": 0.8909299655568312, | |
| "eval_loss": 0.4120063781738281, | |
| "eval_runtime": 23.9427, | |
| "eval_samples_per_second": 36.379, | |
| "eval_steps_per_second": 1.169, | |
| "step": 7564 | |
| }, | |
| { | |
| "epoch": 124.1, | |
| "learning_rate": 2.5220680958385876e-06, | |
| "loss": 0.125, | |
| "step": 7570 | |
| }, | |
| { | |
| "epoch": 124.26, | |
| "learning_rate": 2.45201064873196e-06, | |
| "loss": 0.1434, | |
| "step": 7580 | |
| }, | |
| { | |
| "epoch": 124.42, | |
| "learning_rate": 2.381953201625333e-06, | |
| "loss": 0.1451, | |
| "step": 7590 | |
| }, | |
| { | |
| "epoch": 124.59, | |
| "learning_rate": 2.3118957545187055e-06, | |
| "loss": 0.1257, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 124.75, | |
| "learning_rate": 2.241838307412078e-06, | |
| "loss": 0.1385, | |
| "step": 7610 | |
| }, | |
| { | |
| "epoch": 124.91, | |
| "learning_rate": 2.1717808603054504e-06, | |
| "loss": 0.1353, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 125.0, | |
| "eval_accuracy": 0.8920780711825488, | |
| "eval_loss": 0.40598517656326294, | |
| "eval_runtime": 22.5018, | |
| "eval_samples_per_second": 38.708, | |
| "eval_steps_per_second": 1.244, | |
| "step": 7625 | |
| }, | |
| { | |
| "epoch": 125.08, | |
| "learning_rate": 2.1017234131988235e-06, | |
| "loss": 0.1385, | |
| "step": 7630 | |
| }, | |
| { | |
| "epoch": 125.24, | |
| "learning_rate": 2.0316659660921957e-06, | |
| "loss": 0.1456, | |
| "step": 7640 | |
| }, | |
| { | |
| "epoch": 125.41, | |
| "learning_rate": 1.9616085189855683e-06, | |
| "loss": 0.1318, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 125.57, | |
| "learning_rate": 1.8915510718789408e-06, | |
| "loss": 0.1139, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 125.73, | |
| "learning_rate": 1.8214936247723136e-06, | |
| "loss": 0.1406, | |
| "step": 7670 | |
| }, | |
| { | |
| "epoch": 125.9, | |
| "learning_rate": 1.751436177665686e-06, | |
| "loss": 0.1489, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 126.0, | |
| "eval_accuracy": 0.8909299655568312, | |
| "eval_loss": 0.4161646366119385, | |
| "eval_runtime": 22.4672, | |
| "eval_samples_per_second": 38.768, | |
| "eval_steps_per_second": 1.246, | |
| "step": 7686 | |
| }, | |
| { | |
| "epoch": 126.07, | |
| "learning_rate": 1.6813787305590585e-06, | |
| "loss": 0.1326, | |
| "step": 7690 | |
| }, | |
| { | |
| "epoch": 126.23, | |
| "learning_rate": 1.611321283452431e-06, | |
| "loss": 0.1145, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 126.39, | |
| "learning_rate": 1.5412638363458036e-06, | |
| "loss": 0.1276, | |
| "step": 7710 | |
| }, | |
| { | |
| "epoch": 126.56, | |
| "learning_rate": 1.4712063892391763e-06, | |
| "loss": 0.1264, | |
| "step": 7720 | |
| }, | |
| { | |
| "epoch": 126.72, | |
| "learning_rate": 1.4011489421325487e-06, | |
| "loss": 0.1437, | |
| "step": 7730 | |
| }, | |
| { | |
| "epoch": 126.88, | |
| "learning_rate": 1.3310914950259213e-06, | |
| "loss": 0.1554, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 127.0, | |
| "eval_accuracy": 0.894374282433984, | |
| "eval_loss": 0.414805144071579, | |
| "eval_runtime": 22.3399, | |
| "eval_samples_per_second": 38.989, | |
| "eval_steps_per_second": 1.253, | |
| "step": 7747 | |
| }, | |
| { | |
| "epoch": 127.05, | |
| "learning_rate": 1.2610340479192938e-06, | |
| "loss": 0.1236, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 127.21, | |
| "learning_rate": 1.1909766008126664e-06, | |
| "loss": 0.1428, | |
| "step": 7760 | |
| }, | |
| { | |
| "epoch": 127.38, | |
| "learning_rate": 1.120919153706039e-06, | |
| "loss": 0.1293, | |
| "step": 7770 | |
| }, | |
| { | |
| "epoch": 127.54, | |
| "learning_rate": 1.0508617065994117e-06, | |
| "loss": 0.1138, | |
| "step": 7780 | |
| }, | |
| { | |
| "epoch": 127.7, | |
| "learning_rate": 9.808042594927842e-07, | |
| "loss": 0.1323, | |
| "step": 7790 | |
| }, | |
| { | |
| "epoch": 127.87, | |
| "learning_rate": 9.107468123861568e-07, | |
| "loss": 0.1558, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 128.0, | |
| "eval_accuracy": 0.894374282433984, | |
| "eval_loss": 0.4168582856655121, | |
| "eval_runtime": 22.2971, | |
| "eval_samples_per_second": 39.063, | |
| "eval_steps_per_second": 1.256, | |
| "step": 7808 | |
| }, | |
| { | |
| "epoch": 128.03, | |
| "learning_rate": 8.406893652795293e-07, | |
| "loss": 0.1357, | |
| "step": 7810 | |
| }, | |
| { | |
| "epoch": 128.2, | |
| "learning_rate": 7.706319181729018e-07, | |
| "loss": 0.1423, | |
| "step": 7820 | |
| }, | |
| { | |
| "epoch": 128.36, | |
| "learning_rate": 7.005744710662743e-07, | |
| "loss": 0.1238, | |
| "step": 7830 | |
| }, | |
| { | |
| "epoch": 128.52, | |
| "learning_rate": 6.305170239596469e-07, | |
| "loss": 0.1342, | |
| "step": 7840 | |
| }, | |
| { | |
| "epoch": 128.69, | |
| "learning_rate": 5.604595768530195e-07, | |
| "loss": 0.1193, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 128.85, | |
| "learning_rate": 4.904021297463921e-07, | |
| "loss": 0.1268, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 129.0, | |
| "eval_accuracy": 0.8955223880597015, | |
| "eval_loss": 0.41104114055633545, | |
| "eval_runtime": 23.9571, | |
| "eval_samples_per_second": 36.357, | |
| "eval_steps_per_second": 1.169, | |
| "step": 7869 | |
| }, | |
| { | |
| "epoch": 129.02, | |
| "learning_rate": 4.2034468263976463e-07, | |
| "loss": 0.1287, | |
| "step": 7870 | |
| }, | |
| { | |
| "epoch": 129.18, | |
| "learning_rate": 3.5028723553313717e-07, | |
| "loss": 0.1353, | |
| "step": 7880 | |
| }, | |
| { | |
| "epoch": 129.34, | |
| "learning_rate": 2.8022978842650977e-07, | |
| "loss": 0.1331, | |
| "step": 7890 | |
| }, | |
| { | |
| "epoch": 129.51, | |
| "learning_rate": 2.1017234131988231e-07, | |
| "loss": 0.1279, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 129.67, | |
| "learning_rate": 1.4011489421325488e-07, | |
| "loss": 0.1272, | |
| "step": 7910 | |
| }, | |
| { | |
| "epoch": 129.83, | |
| "learning_rate": 7.005744710662744e-08, | |
| "loss": 0.1306, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1236, | |
| "step": 7930 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "eval_accuracy": 0.894374282433984, | |
| "eval_loss": 0.4196510314941406, | |
| "eval_runtime": 22.6712, | |
| "eval_samples_per_second": 38.419, | |
| "eval_steps_per_second": 1.235, | |
| "step": 7930 | |
| }, | |
| { | |
| "epoch": 130.0, | |
| "step": 7930, | |
| "total_flos": 2.531639646984101e+19, | |
| "train_loss": 0.28095060671112426, | |
| "train_runtime": 53110.9953, | |
| "train_samples_per_second": 19.178, | |
| "train_steps_per_second": 0.149 | |
| } | |
| ], | |
| "max_steps": 7930, | |
| "num_train_epochs": 130, | |
| "total_flos": 2.531639646984101e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |