nemotron-sft_100000 / trainer_log.jsonl
ryanmarten's picture
Upload folder using huggingface_hub
9d8889f verified
{"current_steps": 1, "total_steps": 72, "loss": 1.2112, "lr": 1e-05, "epoch": 0.04113110539845758, "percentage": 1.39, "elapsed_time": "0:04:17", "remaining_time": "5:04:36"}
{"current_steps": 2, "total_steps": 72, "loss": 1.2033, "lr": 2e-05, "epoch": 0.08226221079691516, "percentage": 2.78, "elapsed_time": "0:07:53", "remaining_time": "4:36:26"}
{"current_steps": 3, "total_steps": 72, "loss": 1.0955, "lr": 3.0000000000000004e-05, "epoch": 0.12339331619537275, "percentage": 4.17, "elapsed_time": "0:11:30", "remaining_time": "4:24:38"}
{"current_steps": 4, "total_steps": 72, "loss": 1.1047, "lr": 4e-05, "epoch": 0.16452442159383032, "percentage": 5.56, "elapsed_time": "0:15:04", "remaining_time": "4:16:15"}
{"current_steps": 5, "total_steps": 72, "loss": 1.1423, "lr": 5e-05, "epoch": 0.20565552699228792, "percentage": 6.94, "elapsed_time": "0:18:37", "remaining_time": "4:09:28"}
{"current_steps": 6, "total_steps": 72, "loss": 1.0961, "lr": 6.000000000000001e-05, "epoch": 0.2467866323907455, "percentage": 8.33, "elapsed_time": "0:22:09", "remaining_time": "4:03:43"}
{"current_steps": 7, "total_steps": 72, "loss": 1.0179, "lr": 7.000000000000001e-05, "epoch": 0.2879177377892031, "percentage": 9.72, "elapsed_time": "0:25:43", "remaining_time": "3:58:48"}
{"current_steps": 8, "total_steps": 72, "loss": 1.001, "lr": 8e-05, "epoch": 0.32904884318766064, "percentage": 11.11, "elapsed_time": "0:29:17", "remaining_time": "3:54:20"}
{"current_steps": 9, "total_steps": 72, "loss": 0.9559, "lr": 7.99518182482069e-05, "epoch": 0.37017994858611825, "percentage": 12.5, "elapsed_time": "0:32:52", "remaining_time": "3:50:04"}
{"current_steps": 10, "total_steps": 72, "loss": 0.9333, "lr": 7.980738906688788e-05, "epoch": 0.41131105398457585, "percentage": 13.89, "elapsed_time": "0:36:26", "remaining_time": "3:45:54"}
{"current_steps": 11, "total_steps": 72, "loss": 0.8816, "lr": 7.956706039859124e-05, "epoch": 0.4524421593830334, "percentage": 15.28, "elapsed_time": "0:39:59", "remaining_time": "3:41:47"}
{"current_steps": 12, "total_steps": 72, "loss": 0.8995, "lr": 7.923141121612922e-05, "epoch": 0.493573264781491, "percentage": 16.67, "elapsed_time": "0:43:28", "remaining_time": "3:37:20"}
{"current_steps": 13, "total_steps": 72, "loss": 1.3647, "lr": 7.880125012778177e-05, "epoch": 0.5347043701799485, "percentage": 18.06, "elapsed_time": "0:46:50", "remaining_time": "3:32:34"}
{"current_steps": 14, "total_steps": 72, "loss": 1.1214, "lr": 7.827761342928836e-05, "epoch": 0.5758354755784062, "percentage": 19.44, "elapsed_time": "0:50:23", "remaining_time": "3:28:47"}
{"current_steps": 15, "total_steps": 72, "loss": 1.115, "lr": 7.766176260732084e-05, "epoch": 0.6169665809768637, "percentage": 20.83, "elapsed_time": "0:53:57", "remaining_time": "3:25:04"}
{"current_steps": 16, "total_steps": 72, "loss": 0.9562, "lr": 7.695518130045147e-05, "epoch": 0.6580976863753213, "percentage": 22.22, "elapsed_time": "0:57:30", "remaining_time": "3:21:15"}
{"current_steps": 17, "total_steps": 72, "loss": 0.9133, "lr": 7.615957172493774e-05, "epoch": 0.699228791773779, "percentage": 23.61, "elapsed_time": "1:01:04", "remaining_time": "3:17:35"}
{"current_steps": 18, "total_steps": 72, "loss": 0.8791, "lr": 7.52768505739342e-05, "epoch": 0.7403598971722365, "percentage": 25.0, "elapsed_time": "1:04:37", "remaining_time": "3:13:51"}
{"current_steps": 19, "total_steps": 72, "loss": 0.8744, "lr": 7.430914440001089e-05, "epoch": 0.781491002570694, "percentage": 26.39, "elapsed_time": "1:08:32", "remaining_time": "3:11:11"}
{"current_steps": 20, "total_steps": 72, "loss": 0.8437, "lr": 7.325878449210182e-05, "epoch": 0.8226221079691517, "percentage": 27.78, "elapsed_time": "1:13:10", "remaining_time": "3:10:15"}
{"current_steps": 21, "total_steps": 72, "loss": 0.8163, "lr": 7.21283012592258e-05, "epoch": 0.8637532133676092, "percentage": 29.17, "elapsed_time": "1:17:06", "remaining_time": "3:07:16"}
{"current_steps": 22, "total_steps": 72, "loss": 0.8066, "lr": 7.092041813450948e-05, "epoch": 0.9048843187660668, "percentage": 30.56, "elapsed_time": "1:20:52", "remaining_time": "3:03:49"}
{"current_steps": 23, "total_steps": 72, "loss": 0.8061, "lr": 6.963804501419837e-05, "epoch": 0.9460154241645244, "percentage": 31.94, "elapsed_time": "1:24:29", "remaining_time": "2:59:59"}
{"current_steps": 24, "total_steps": 72, "loss": 0.7991, "lr": 6.828427124746191e-05, "epoch": 0.987146529562982, "percentage": 33.33, "elapsed_time": "1:28:08", "remaining_time": "2:56:17"}
{"current_steps": 25, "total_steps": 72, "loss": 0.8015, "lr": 6.686235819388075e-05, "epoch": 1.0282776349614395, "percentage": 34.72, "elapsed_time": "1:32:54", "remaining_time": "2:54:39"}
{"current_steps": 26, "total_steps": 72, "loss": 0.7812, "lr": 6.537573136654582e-05, "epoch": 1.069408740359897, "percentage": 36.11, "elapsed_time": "1:36:29", "remaining_time": "2:50:42"}
{"current_steps": 27, "total_steps": 72, "loss": 0.7926, "lr": 6.382797217969734e-05, "epoch": 1.1105398457583548, "percentage": 37.5, "elapsed_time": "1:40:04", "remaining_time": "2:46:47"}
{"current_steps": 28, "total_steps": 72, "loss": 0.7228, "lr": 6.22228093207841e-05, "epoch": 1.1516709511568124, "percentage": 38.89, "elapsed_time": "1:43:38", "remaining_time": "2:42:51"}
{"current_steps": 29, "total_steps": 72, "loss": 0.7668, "lr": 6.056410976772887e-05, "epoch": 1.19280205655527, "percentage": 40.28, "elapsed_time": "1:47:13", "remaining_time": "2:38:59"}
{"current_steps": 30, "total_steps": 72, "loss": 0.7555, "lr": 5.8855869473039924e-05, "epoch": 1.2339331619537275, "percentage": 41.67, "elapsed_time": "1:50:47", "remaining_time": "2:35:07"}
{"current_steps": 31, "total_steps": 72, "loss": 0.725, "lr": 5.710220373721129e-05, "epoch": 1.275064267352185, "percentage": 43.06, "elapsed_time": "1:54:22", "remaining_time": "2:31:16"}
{"current_steps": 32, "total_steps": 72, "loss": 0.755, "lr": 5.5307337294603595e-05, "epoch": 1.3161953727506428, "percentage": 44.44, "elapsed_time": "1:57:56", "remaining_time": "2:27:25"}
{"current_steps": 33, "total_steps": 72, "loss": 0.734, "lr": 5.347559413568881e-05, "epoch": 1.3573264781491003, "percentage": 45.83, "elapsed_time": "2:01:29", "remaining_time": "2:23:34"}
{"current_steps": 34, "total_steps": 72, "loss": 0.7788, "lr": 5.16113870901785e-05, "epoch": 1.398457583547558, "percentage": 47.22, "elapsed_time": "2:05:02", "remaining_time": "2:19:45"}
{"current_steps": 35, "total_steps": 72, "loss": 0.7554, "lr": 4.971920719613056e-05, "epoch": 1.4395886889460154, "percentage": 48.61, "elapsed_time": "2:08:38", "remaining_time": "2:15:59"}
{"current_steps": 36, "total_steps": 72, "loss": 0.7256, "lr": 4.780361288064514e-05, "epoch": 1.480719794344473, "percentage": 50.0, "elapsed_time": "2:12:11", "remaining_time": "2:12:11"}
{"current_steps": 37, "total_steps": 72, "loss": 0.7338, "lr": 4.586921897821447e-05, "epoch": 1.5218508997429305, "percentage": 51.39, "elapsed_time": "2:15:38", "remaining_time": "2:08:18"}
{"current_steps": 38, "total_steps": 72, "loss": 0.7109, "lr": 4.392068561318244e-05, "epoch": 1.562982005141388, "percentage": 52.78, "elapsed_time": "2:19:03", "remaining_time": "2:04:25"}
{"current_steps": 39, "total_steps": 72, "loss": 0.7282, "lr": 4.1962706973096726e-05, "epoch": 1.6041131105398456, "percentage": 54.17, "elapsed_time": "2:22:37", "remaining_time": "2:00:40"}
{"current_steps": 40, "total_steps": 72, "loss": 0.7073, "lr": 4e-05, "epoch": 1.6452442159383034, "percentage": 55.56, "elapsed_time": "2:26:10", "remaining_time": "1:56:56"}
{"current_steps": 41, "total_steps": 72, "loss": 0.7067, "lr": 3.803729302690328e-05, "epoch": 1.686375321336761, "percentage": 56.94, "elapsed_time": "2:29:43", "remaining_time": "1:53:12"}
{"current_steps": 42, "total_steps": 72, "loss": 0.6925, "lr": 3.6079314386817575e-05, "epoch": 1.7275064267352185, "percentage": 58.33, "elapsed_time": "2:33:17", "remaining_time": "1:49:29"}
{"current_steps": 43, "total_steps": 72, "loss": 0.6938, "lr": 3.4130781021785535e-05, "epoch": 1.7686375321336762, "percentage": 59.72, "elapsed_time": "2:36:51", "remaining_time": "1:45:47"}
{"current_steps": 44, "total_steps": 72, "loss": 0.7192, "lr": 3.219638711935488e-05, "epoch": 1.8097686375321338, "percentage": 61.11, "elapsed_time": "2:40:24", "remaining_time": "1:42:04"}
{"current_steps": 45, "total_steps": 72, "loss": 0.733, "lr": 3.028079280386945e-05, "epoch": 1.8508997429305913, "percentage": 62.5, "elapsed_time": "2:43:57", "remaining_time": "1:38:22"}
{"current_steps": 46, "total_steps": 72, "loss": 0.7089, "lr": 2.8388612909821515e-05, "epoch": 1.8920308483290489, "percentage": 63.89, "elapsed_time": "2:47:31", "remaining_time": "1:34:41"}
{"current_steps": 47, "total_steps": 72, "loss": 0.6901, "lr": 2.6524405864311203e-05, "epoch": 1.9331619537275064, "percentage": 65.28, "elapsed_time": "2:51:04", "remaining_time": "1:30:59"}
{"current_steps": 48, "total_steps": 72, "loss": 0.6814, "lr": 2.4692662705396412e-05, "epoch": 1.974293059125964, "percentage": 66.67, "elapsed_time": "2:54:37", "remaining_time": "1:27:18"}
{"current_steps": 49, "total_steps": 72, "loss": 0.6945, "lr": 2.2897796262788728e-05, "epoch": 2.0154241645244215, "percentage": 68.06, "elapsed_time": "2:59:11", "remaining_time": "1:24:06"}
{"current_steps": 50, "total_steps": 72, "loss": 0.6808, "lr": 2.1144130526960093e-05, "epoch": 2.056555269922879, "percentage": 69.44, "elapsed_time": "3:02:41", "remaining_time": "1:20:23"}
{"current_steps": 51, "total_steps": 72, "loss": 0.6365, "lr": 1.9435890232271136e-05, "epoch": 2.0976863753213366, "percentage": 70.83, "elapsed_time": "3:06:14", "remaining_time": "1:16:41"}
{"current_steps": 52, "total_steps": 72, "loss": 0.6733, "lr": 1.7777190679215923e-05, "epoch": 2.138817480719794, "percentage": 72.22, "elapsed_time": "3:09:48", "remaining_time": "1:13:00"}
{"current_steps": 53, "total_steps": 72, "loss": 0.6676, "lr": 1.617202782030267e-05, "epoch": 2.179948586118252, "percentage": 73.61, "elapsed_time": "3:13:22", "remaining_time": "1:09:19"}
{"current_steps": 54, "total_steps": 72, "loss": 0.6436, "lr": 1.4624268633454187e-05, "epoch": 2.2210796915167097, "percentage": 75.0, "elapsed_time": "3:16:55", "remaining_time": "1:05:38"}
{"current_steps": 55, "total_steps": 72, "loss": 0.6417, "lr": 1.3137641806119264e-05, "epoch": 2.2622107969151672, "percentage": 76.39, "elapsed_time": "3:20:29", "remaining_time": "1:01:58"}
{"current_steps": 56, "total_steps": 72, "loss": 0.6674, "lr": 1.1715728752538103e-05, "epoch": 2.303341902313625, "percentage": 77.78, "elapsed_time": "3:24:02", "remaining_time": "0:58:17"}
{"current_steps": 57, "total_steps": 72, "loss": 0.6733, "lr": 1.0361954985801646e-05, "epoch": 2.3444730077120823, "percentage": 79.17, "elapsed_time": "3:27:37", "remaining_time": "0:54:38"}
{"current_steps": 58, "total_steps": 72, "loss": 0.6748, "lr": 9.07958186549052e-06, "epoch": 2.38560411311054, "percentage": 80.56, "elapsed_time": "3:31:11", "remaining_time": "0:50:58"}
{"current_steps": 59, "total_steps": 72, "loss": 0.6552, "lr": 7.871698740774208e-06, "epoch": 2.4267352185089974, "percentage": 81.94, "elapsed_time": "3:34:45", "remaining_time": "0:47:19"}
{"current_steps": 60, "total_steps": 72, "loss": 0.6551, "lr": 6.7412155078981865e-06, "epoch": 2.467866323907455, "percentage": 83.33, "elapsed_time": "3:38:17", "remaining_time": "0:43:39"}
{"current_steps": 61, "total_steps": 72, "loss": 0.6501, "lr": 5.690855599989121e-06, "epoch": 2.5089974293059125, "percentage": 84.72, "elapsed_time": "3:41:43", "remaining_time": "0:39:59"}
{"current_steps": 62, "total_steps": 72, "loss": 0.6848, "lr": 4.723149426065803e-06, "epoch": 2.55012853470437, "percentage": 86.11, "elapsed_time": "3:45:17", "remaining_time": "0:36:20"}
{"current_steps": 63, "total_steps": 72, "loss": 0.6778, "lr": 3.840428275062267e-06, "epoch": 2.5912596401028276, "percentage": 87.5, "elapsed_time": "3:48:51", "remaining_time": "0:32:41"}
{"current_steps": 64, "total_steps": 72, "loss": 0.6546, "lr": 3.0448186995485307e-06, "epoch": 2.6323907455012856, "percentage": 88.89, "elapsed_time": "3:52:27", "remaining_time": "0:29:03"}
{"current_steps": 65, "total_steps": 72, "loss": 0.6539, "lr": 2.3382373926791722e-06, "epoch": 2.6735218508997427, "percentage": 90.28, "elapsed_time": "3:56:01", "remaining_time": "0:25:25"}
{"current_steps": 66, "total_steps": 72, "loss": 0.6565, "lr": 1.7223865707116472e-06, "epoch": 2.7146529562982007, "percentage": 91.67, "elapsed_time": "3:59:35", "remaining_time": "0:21:46"}
{"current_steps": 67, "total_steps": 72, "loss": 0.661, "lr": 1.1987498722182411e-06, "epoch": 2.7557840616966582, "percentage": 93.06, "elapsed_time": "4:03:09", "remaining_time": "0:18:08"}
{"current_steps": 68, "total_steps": 72, "loss": 0.6437, "lr": 7.685887838707828e-07, "epoch": 2.796915167095116, "percentage": 94.44, "elapsed_time": "4:06:44", "remaining_time": "0:14:30"}
{"current_steps": 69, "total_steps": 72, "loss": 0.6573, "lr": 4.3293960140875946e-07, "epoch": 2.8380462724935733, "percentage": 95.83, "elapsed_time": "4:10:16", "remaining_time": "0:10:52"}
{"current_steps": 70, "total_steps": 72, "loss": 0.6578, "lr": 1.926109331121273e-07, "epoch": 2.879177377892031, "percentage": 97.22, "elapsed_time": "4:13:51", "remaining_time": "0:07:15"}
{"current_steps": 71, "total_steps": 72, "loss": 0.6636, "lr": 4.8181751793103806e-08, "epoch": 2.9203084832904884, "percentage": 98.61, "elapsed_time": "4:17:25", "remaining_time": "0:03:37"}
{"current_steps": 72, "total_steps": 72, "loss": 0.6851, "lr": 0.0, "epoch": 2.961439588688946, "percentage": 100.0, "elapsed_time": "4:20:51", "remaining_time": "0:00:00"}
{"current_steps": 72, "total_steps": 72, "epoch": 2.961439588688946, "percentage": 100.0, "elapsed_time": "4:21:59", "remaining_time": "0:00:00"}