| { | |
| "best_metric": 0.7472190257000384, | |
| "best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-crop-classification/checkpoint-1468", | |
| "epoch": 9.97275204359673, | |
| "eval_steps": 500, | |
| "global_step": 1830, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.73224043715847e-06, | |
| "loss": 1.6369, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5.46448087431694e-06, | |
| "loss": 1.6111, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 8.196721311475409e-06, | |
| "loss": 1.5398, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.092896174863388e-05, | |
| "loss": 1.4457, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.3661202185792351e-05, | |
| "loss": 1.3015, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 1.6393442622950818e-05, | |
| "loss": 1.1684, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 1.912568306010929e-05, | |
| "loss": 1.0962, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.185792349726776e-05, | |
| "loss": 1.0177, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.459016393442623e-05, | |
| "loss": 0.9627, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.7322404371584703e-05, | |
| "loss": 0.8997, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.005464480874317e-05, | |
| "loss": 0.8822, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.2786885245901635e-05, | |
| "loss": 0.8726, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 3.551912568306011e-05, | |
| "loss": 0.8288, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 3.825136612021858e-05, | |
| "loss": 0.8337, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.098360655737705e-05, | |
| "loss": 0.829, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.371584699453552e-05, | |
| "loss": 0.7949, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 4.644808743169399e-05, | |
| "loss": 0.7856, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 4.918032786885246e-05, | |
| "loss": 0.8031, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7050249328730341, | |
| "eval_loss": 0.7602581977844238, | |
| "eval_runtime": 93.216, | |
| "eval_samples_per_second": 27.967, | |
| "eval_steps_per_second": 0.88, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.9787492410443234e-05, | |
| "loss": 0.78, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 4.948391013964785e-05, | |
| "loss": 0.7994, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 4.918032786885246e-05, | |
| "loss": 0.7665, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.8876745598057074e-05, | |
| "loss": 0.7866, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.857316332726169e-05, | |
| "loss": 0.7733, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 4.8269581056466304e-05, | |
| "loss": 0.7504, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 4.7965998785670915e-05, | |
| "loss": 0.7805, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 4.766241651487553e-05, | |
| "loss": 0.7671, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 4.7358834244080144e-05, | |
| "loss": 0.7012, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 4.705525197328476e-05, | |
| "loss": 0.7305, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 4.6751669702489374e-05, | |
| "loss": 0.7441, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 4.644808743169399e-05, | |
| "loss": 0.7758, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 4.61445051608986e-05, | |
| "loss": 0.731, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 4.584092289010322e-05, | |
| "loss": 0.7303, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 4.553734061930783e-05, | |
| "loss": 0.7265, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 4.523375834851245e-05, | |
| "loss": 0.7385, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 4.493017607771706e-05, | |
| "loss": 0.7396, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 4.462659380692168e-05, | |
| "loss": 0.7311, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7249712313003452, | |
| "eval_loss": 0.7046979069709778, | |
| "eval_runtime": 93.2263, | |
| "eval_samples_per_second": 27.964, | |
| "eval_steps_per_second": 0.88, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 4.432301153612629e-05, | |
| "loss": 0.7129, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 4.401942926533091e-05, | |
| "loss": 0.7103, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 4.371584699453552e-05, | |
| "loss": 0.6994, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 4.341226472374014e-05, | |
| "loss": 0.6637, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 4.310868245294475e-05, | |
| "loss": 0.7107, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 4.280510018214937e-05, | |
| "loss": 0.7326, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.250151791135398e-05, | |
| "loss": 0.7229, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.21979356405586e-05, | |
| "loss": 0.7064, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 4.189435336976321e-05, | |
| "loss": 0.6781, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 4.1590771098967827e-05, | |
| "loss": 0.7207, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.128718882817244e-05, | |
| "loss": 0.7244, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 4.098360655737705e-05, | |
| "loss": 0.6972, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 4.068002428658167e-05, | |
| "loss": 0.7148, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.037644201578628e-05, | |
| "loss": 0.7168, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.007285974499089e-05, | |
| "loss": 0.7146, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.976927747419551e-05, | |
| "loss": 0.6583, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 3.946569520340012e-05, | |
| "loss": 0.7119, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 3.916211293260474e-05, | |
| "loss": 0.6891, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.885853066180935e-05, | |
| "loss": 0.7144, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7211354046797085, | |
| "eval_loss": 0.6968041062355042, | |
| "eval_runtime": 91.8623, | |
| "eval_samples_per_second": 28.379, | |
| "eval_steps_per_second": 0.893, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 3.8554948391013967e-05, | |
| "loss": 0.7037, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.825136612021858e-05, | |
| "loss": 0.6613, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 3.7947783849423196e-05, | |
| "loss": 0.6462, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 3.764420157862781e-05, | |
| "loss": 0.6484, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 3.27, | |
| "learning_rate": 3.7340619307832425e-05, | |
| "loss": 0.6747, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.7036, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 3.6733454766241655e-05, | |
| "loss": 0.6444, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 3.6429872495446266e-05, | |
| "loss": 0.6337, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "learning_rate": 3.6126290224650884e-05, | |
| "loss": 0.6715, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 3.5822707953855495e-05, | |
| "loss": 0.6583, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 3.551912568306011e-05, | |
| "loss": 0.663, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 3.5215543412264725e-05, | |
| "loss": 0.6901, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 3.491196114146934e-05, | |
| "loss": 0.6582, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 3.4608378870673954e-05, | |
| "loss": 0.6868, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 3.430479659987857e-05, | |
| "loss": 0.7168, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 3.400121432908318e-05, | |
| "loss": 0.6522, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 3.36976320582878e-05, | |
| "loss": 0.6337, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 3.339404978749241e-05, | |
| "loss": 0.6516, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7376294591484465, | |
| "eval_loss": 0.6568663716316223, | |
| "eval_runtime": 93.5303, | |
| "eval_samples_per_second": 27.873, | |
| "eval_steps_per_second": 0.877, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 3.3090467516697024e-05, | |
| "loss": 0.6547, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 3.2786885245901635e-05, | |
| "loss": 0.6444, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 3.248330297510625e-05, | |
| "loss": 0.6687, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 3.2179720704310865e-05, | |
| "loss": 0.6634, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 3.187613843351548e-05, | |
| "loss": 0.6334, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 3.1572556162720094e-05, | |
| "loss": 0.6095, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 3.126897389192471e-05, | |
| "loss": 0.6467, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.41, | |
| "learning_rate": 3.096539162112932e-05, | |
| "loss": 0.6532, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 3.066180935033394e-05, | |
| "loss": 0.6544, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 3.0358227079538553e-05, | |
| "loss": 0.6161, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 3.005464480874317e-05, | |
| "loss": 0.6092, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 2.9751062537947782e-05, | |
| "loss": 0.6323, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 2.94474802671524e-05, | |
| "loss": 0.6593, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 2.9143897996357018e-05, | |
| "loss": 0.6493, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 2.884031572556163e-05, | |
| "loss": 0.6475, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 2.8536733454766244e-05, | |
| "loss": 0.6196, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 2.823315118397086e-05, | |
| "loss": 0.6257, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 2.7929568913175473e-05, | |
| "loss": 0.6371, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7376294591484465, | |
| "eval_loss": 0.6482810974121094, | |
| "eval_runtime": 93.1536, | |
| "eval_samples_per_second": 27.986, | |
| "eval_steps_per_second": 0.88, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 2.7625986642380085e-05, | |
| "loss": 0.6049, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 2.7322404371584703e-05, | |
| "loss": 0.6072, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 2.7018822100789314e-05, | |
| "loss": 0.5548, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 2.6715239829993932e-05, | |
| "loss": 0.5689, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "learning_rate": 2.6411657559198543e-05, | |
| "loss": 0.6459, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 2.610807528840316e-05, | |
| "loss": 0.6033, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 2.5804493017607773e-05, | |
| "loss": 0.5981, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 2.550091074681239e-05, | |
| "loss": 0.6201, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 2.5197328476017002e-05, | |
| "loss": 0.6121, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 2.4893746205221617e-05, | |
| "loss": 0.6147, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 2.459016393442623e-05, | |
| "loss": 0.6007, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 5.61, | |
| "learning_rate": 2.4286581663630846e-05, | |
| "loss": 0.6087, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 2.3982999392835457e-05, | |
| "loss": 0.6195, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 5.72, | |
| "learning_rate": 2.3679417122040072e-05, | |
| "loss": 0.5848, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 2.3375834851244687e-05, | |
| "loss": 0.6066, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 2.30722525804493e-05, | |
| "loss": 0.6386, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 2.2768670309653916e-05, | |
| "loss": 0.6196, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "learning_rate": 2.246508803885853e-05, | |
| "loss": 0.6127, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 2.2161505768063146e-05, | |
| "loss": 0.6246, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7364787111622555, | |
| "eval_loss": 0.6492410898208618, | |
| "eval_runtime": 92.6582, | |
| "eval_samples_per_second": 28.136, | |
| "eval_steps_per_second": 0.885, | |
| "step": 1101 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 2.185792349726776e-05, | |
| "loss": 0.5467, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 2.1554341226472375e-05, | |
| "loss": 0.577, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 2.125075895567699e-05, | |
| "loss": 0.6047, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 6.21, | |
| "learning_rate": 2.0947176684881604e-05, | |
| "loss": 0.5822, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 2.064359441408622e-05, | |
| "loss": 0.605, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "learning_rate": 2.0340012143290834e-05, | |
| "loss": 0.5743, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 2.0036429872495445e-05, | |
| "loss": 0.5658, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 6.43, | |
| "learning_rate": 1.973284760170006e-05, | |
| "loss": 0.5686, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 1.9429265330904674e-05, | |
| "loss": 0.5884, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 1.912568306010929e-05, | |
| "loss": 0.544, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 1.8822100789313904e-05, | |
| "loss": 0.5888, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.5377, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 1.8214936247723133e-05, | |
| "loss": 0.5665, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 1.7911353976927748e-05, | |
| "loss": 0.6032, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 1.7607771706132362e-05, | |
| "loss": 0.5905, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 1.7304189435336977e-05, | |
| "loss": 0.5831, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 1.700060716454159e-05, | |
| "loss": 0.5762, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 1.6697024893746206e-05, | |
| "loss": 0.5659, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7410817031070196, | |
| "eval_loss": 0.6481292843818665, | |
| "eval_runtime": 93.3242, | |
| "eval_samples_per_second": 27.935, | |
| "eval_steps_per_second": 0.879, | |
| "step": 1284 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 1.6393442622950818e-05, | |
| "loss": 0.5738, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.6089860352155432e-05, | |
| "loss": 0.5339, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 1.5786278081360047e-05, | |
| "loss": 0.5405, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 1.548269581056466e-05, | |
| "loss": 0.5792, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 1.5179113539769276e-05, | |
| "loss": 0.5677, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 1.4875531268973891e-05, | |
| "loss": 0.5319, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 1.4571948998178509e-05, | |
| "loss": 0.5693, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 1.4268366727383122e-05, | |
| "loss": 0.5532, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 1.3964784456587737e-05, | |
| "loss": 0.565, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 1.3661202185792351e-05, | |
| "loss": 0.536, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 1.3357619914996966e-05, | |
| "loss": 0.5408, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 7.63, | |
| "learning_rate": 1.305403764420158e-05, | |
| "loss": 0.5835, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 1.2750455373406195e-05, | |
| "loss": 0.5353, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 1.2446873102610808e-05, | |
| "loss": 0.5568, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 1.2143290831815423e-05, | |
| "loss": 0.5531, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 7.85, | |
| "learning_rate": 1.1839708561020036e-05, | |
| "loss": 0.555, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 1.153612629022465e-05, | |
| "loss": 0.5478, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "learning_rate": 1.1232544019429265e-05, | |
| "loss": 0.533, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.7472190257000384, | |
| "eval_loss": 0.6449919939041138, | |
| "eval_runtime": 93.8292, | |
| "eval_samples_per_second": 27.785, | |
| "eval_steps_per_second": 0.874, | |
| "step": 1468 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 1.092896174863388e-05, | |
| "loss": 0.5692, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 1.0625379477838495e-05, | |
| "loss": 0.5422, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 1.032179720704311e-05, | |
| "loss": 0.5154, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "learning_rate": 1.0018214936247722e-05, | |
| "loss": 0.5471, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 9.714632665452337e-06, | |
| "loss": 0.5253, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 9.411050394656952e-06, | |
| "loss": 0.526, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 8.34, | |
| "learning_rate": 9.107468123861566e-06, | |
| "loss": 0.5038, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 8.803885853066181e-06, | |
| "loss": 0.5109, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 8.500303582270796e-06, | |
| "loss": 0.4941, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 8.196721311475409e-06, | |
| "loss": 0.5616, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 8.56, | |
| "learning_rate": 7.893139040680023e-06, | |
| "loss": 0.5514, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 7.589556769884638e-06, | |
| "loss": 0.5203, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 7.2859744990892545e-06, | |
| "loss": 0.5351, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 6.982392228293868e-06, | |
| "loss": 0.5334, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 8.77, | |
| "learning_rate": 6.678809957498483e-06, | |
| "loss": 0.5162, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 8.83, | |
| "learning_rate": 6.375227686703098e-06, | |
| "loss": 0.5482, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 6.0716454159077115e-06, | |
| "loss": 0.5077, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "learning_rate": 5.768063145112325e-06, | |
| "loss": 0.5392, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "learning_rate": 5.46448087431694e-06, | |
| "loss": 0.5416, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.74530111238972, | |
| "eval_loss": 0.638206422328949, | |
| "eval_runtime": 94.5986, | |
| "eval_samples_per_second": 27.559, | |
| "eval_steps_per_second": 0.867, | |
| "step": 1651 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 5.160898603521555e-06, | |
| "loss": 0.541, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 4.8573163327261686e-06, | |
| "loss": 0.5393, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 9.16, | |
| "learning_rate": 4.553734061930783e-06, | |
| "loss": 0.488, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 4.250151791135398e-06, | |
| "loss": 0.5104, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 3.946569520340012e-06, | |
| "loss": 0.5151, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 3.6429872495446273e-06, | |
| "loss": 0.5165, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 9.37, | |
| "learning_rate": 3.3394049787492415e-06, | |
| "loss": 0.5116, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 9.43, | |
| "learning_rate": 3.0358227079538558e-06, | |
| "loss": 0.5174, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 2.73224043715847e-06, | |
| "loss": 0.5321, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "learning_rate": 2.4286581663630843e-06, | |
| "loss": 0.4799, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "learning_rate": 2.125075895567699e-06, | |
| "loss": 0.4766, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 1.8214936247723136e-06, | |
| "loss": 0.5425, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 1.5179113539769279e-06, | |
| "loss": 0.4936, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 1.2143290831815421e-06, | |
| "loss": 0.5408, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 9.107468123861568e-07, | |
| "loss": 0.5223, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "learning_rate": 6.071645415907711e-07, | |
| "loss": 0.5074, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.0358227079538554e-07, | |
| "loss": 0.5151, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "learning_rate": 0.0, | |
| "loss": 0.5062, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "eval_accuracy": 0.7460682777138473, | |
| "eval_loss": 0.6395400166511536, | |
| "eval_runtime": 94.039, | |
| "eval_samples_per_second": 27.723, | |
| "eval_steps_per_second": 0.872, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 9.97, | |
| "step": 1830, | |
| "total_flos": 1.8133380652001642e+19, | |
| "train_loss": 0.6611971782204883, | |
| "train_runtime": 13354.5549, | |
| "train_samples_per_second": 17.568, | |
| "train_steps_per_second": 0.137 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1830, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1.8133380652001642e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |