nemo_nano_code_0.3k / trainer_log.jsonl
ryanmarten's picture
Training in progress, epoch 5
ada7ed3 verified
raw
history blame
12.4 kB
{"current_steps": 1, "total_steps": 117, "loss": 0.9457, "lr": 8.333333333333333e-07, "epoch": 0.10126582278481013, "percentage": 0.85, "elapsed_time": "0:00:23", "remaining_time": "0:44:47"}
{"current_steps": 2, "total_steps": 117, "loss": 1.0165, "lr": 1.6666666666666667e-06, "epoch": 0.20253164556962025, "percentage": 1.71, "elapsed_time": "0:00:52", "remaining_time": "0:50:25"}
{"current_steps": 3, "total_steps": 117, "loss": 1.0366, "lr": 2.5e-06, "epoch": 0.3037974683544304, "percentage": 2.56, "elapsed_time": "0:01:25", "remaining_time": "0:54:26"}
{"current_steps": 4, "total_steps": 117, "loss": 1.0122, "lr": 3.3333333333333333e-06, "epoch": 0.4050632911392405, "percentage": 3.42, "elapsed_time": "0:01:48", "remaining_time": "0:51:18"}
{"current_steps": 5, "total_steps": 117, "loss": 0.9254, "lr": 4.166666666666667e-06, "epoch": 0.5063291139240507, "percentage": 4.27, "elapsed_time": "0:02:08", "remaining_time": "0:48:01"}
{"current_steps": 6, "total_steps": 117, "loss": 0.9647, "lr": 5e-06, "epoch": 0.6075949367088608, "percentage": 5.13, "elapsed_time": "0:02:24", "remaining_time": "0:44:32"}
{"current_steps": 7, "total_steps": 117, "loss": 0.914, "lr": 5.833333333333334e-06, "epoch": 0.7088607594936709, "percentage": 5.98, "elapsed_time": "0:02:55", "remaining_time": "0:45:54"}
{"current_steps": 8, "total_steps": 117, "loss": 0.8691, "lr": 6.666666666666667e-06, "epoch": 0.810126582278481, "percentage": 6.84, "elapsed_time": "0:03:20", "remaining_time": "0:45:25"}
{"current_steps": 9, "total_steps": 117, "loss": 0.8462, "lr": 7.500000000000001e-06, "epoch": 0.9113924050632911, "percentage": 7.69, "elapsed_time": "0:03:43", "remaining_time": "0:44:37"}
{"current_steps": 10, "total_steps": 117, "loss": 0.7583, "lr": 8.333333333333334e-06, "epoch": 1.0506329113924051, "percentage": 8.55, "elapsed_time": "0:04:47", "remaining_time": "0:51:12"}
{"current_steps": 11, "total_steps": 117, "loss": 0.7174, "lr": 9.166666666666666e-06, "epoch": 1.1518987341772151, "percentage": 9.4, "elapsed_time": "0:05:12", "remaining_time": "0:50:06"}
{"current_steps": 12, "total_steps": 117, "loss": 0.8281, "lr": 1e-05, "epoch": 1.2531645569620253, "percentage": 10.26, "elapsed_time": "0:05:31", "remaining_time": "0:48:22"}
{"current_steps": 13, "total_steps": 117, "loss": 0.7152, "lr": 9.997762161417517e-06, "epoch": 1.3544303797468356, "percentage": 11.11, "elapsed_time": "0:05:49", "remaining_time": "0:46:39"}
{"current_steps": 14, "total_steps": 117, "loss": 0.6728, "lr": 9.991050648838676e-06, "epoch": 1.4556962025316456, "percentage": 11.97, "elapsed_time": "0:06:10", "remaining_time": "0:45:23"}
{"current_steps": 15, "total_steps": 117, "loss": 0.7307, "lr": 9.979871469976197e-06, "epoch": 1.5569620253164556, "percentage": 12.82, "elapsed_time": "0:06:39", "remaining_time": "0:45:18"}
{"current_steps": 16, "total_steps": 117, "loss": 0.6258, "lr": 9.964234631709188e-06, "epoch": 1.6582278481012658, "percentage": 13.68, "elapsed_time": "0:07:00", "remaining_time": "0:44:12"}
{"current_steps": 17, "total_steps": 117, "loss": 0.6115, "lr": 9.944154131125643e-06, "epoch": 1.759493670886076, "percentage": 14.53, "elapsed_time": "0:07:20", "remaining_time": "0:43:13"}
{"current_steps": 18, "total_steps": 117, "loss": 0.6621, "lr": 9.91964794299315e-06, "epoch": 1.8607594936708862, "percentage": 15.38, "elapsed_time": "0:07:54", "remaining_time": "0:43:30"}
{"current_steps": 19, "total_steps": 117, "loss": 0.6426, "lr": 9.890738003669029e-06, "epoch": 1.9620253164556962, "percentage": 16.24, "elapsed_time": "0:08:25", "remaining_time": "0:43:29"}
{"current_steps": 20, "total_steps": 117, "loss": 0.5377, "lr": 9.857450191464337e-06, "epoch": 2.1012658227848102, "percentage": 17.09, "elapsed_time": "0:09:39", "remaining_time": "0:46:51"}
{"current_steps": 21, "total_steps": 117, "loss": 0.6157, "lr": 9.819814303479268e-06, "epoch": 2.2025316455696204, "percentage": 17.95, "elapsed_time": "0:10:03", "remaining_time": "0:45:59"}
{"current_steps": 22, "total_steps": 117, "loss": 0.5267, "lr": 9.777864028930705e-06, "epoch": 2.3037974683544302, "percentage": 18.8, "elapsed_time": "0:10:30", "remaining_time": "0:45:22"}
{"current_steps": 23, "total_steps": 117, "loss": 0.5002, "lr": 9.731636918995821e-06, "epoch": 2.4050632911392404, "percentage": 19.66, "elapsed_time": "0:10:50", "remaining_time": "0:44:19"}
{"current_steps": 24, "total_steps": 117, "loss": 0.4973, "lr": 9.681174353198687e-06, "epoch": 2.5063291139240507, "percentage": 20.51, "elapsed_time": "0:11:13", "remaining_time": "0:43:30"}
{"current_steps": 25, "total_steps": 117, "loss": 0.5686, "lr": 9.626521502369984e-06, "epoch": 2.607594936708861, "percentage": 21.37, "elapsed_time": "0:11:44", "remaining_time": "0:43:13"}
{"current_steps": 26, "total_steps": 117, "loss": 0.453, "lr": 9.567727288213005e-06, "epoch": 2.708860759493671, "percentage": 22.22, "elapsed_time": "0:12:14", "remaining_time": "0:42:52"}
{"current_steps": 27, "total_steps": 117, "loss": 0.5362, "lr": 9.504844339512096e-06, "epoch": 2.810126582278481, "percentage": 23.08, "elapsed_time": "0:12:38", "remaining_time": "0:42:09"}
{"current_steps": 28, "total_steps": 117, "loss": 0.4751, "lr": 9.437928945022772e-06, "epoch": 2.911392405063291, "percentage": 23.93, "elapsed_time": "0:12:57", "remaining_time": "0:41:12"}
{"current_steps": 29, "total_steps": 117, "loss": 0.4695, "lr": 9.36704100308565e-06, "epoch": 3.050632911392405, "percentage": 24.79, "elapsed_time": "0:14:37", "remaining_time": "0:44:23"}
{"current_steps": 30, "total_steps": 117, "loss": 0.4252, "lr": 9.292243968009332e-06, "epoch": 3.151898734177215, "percentage": 25.64, "elapsed_time": "0:15:08", "remaining_time": "0:43:54"}
{"current_steps": 31, "total_steps": 117, "loss": 0.397, "lr": 9.213604793270196e-06, "epoch": 3.2531645569620253, "percentage": 26.5, "elapsed_time": "0:15:35", "remaining_time": "0:43:16"}
{"current_steps": 32, "total_steps": 117, "loss": 0.3685, "lr": 9.131193871579975e-06, "epoch": 3.3544303797468356, "percentage": 27.35, "elapsed_time": "0:16:00", "remaining_time": "0:42:31"}
{"current_steps": 33, "total_steps": 117, "loss": 0.3762, "lr": 9.045084971874738e-06, "epoch": 3.4556962025316453, "percentage": 28.21, "elapsed_time": "0:16:21", "remaining_time": "0:41:39"}
{"current_steps": 34, "total_steps": 117, "loss": 0.4226, "lr": 8.955355173281709e-06, "epoch": 3.5569620253164556, "percentage": 29.06, "elapsed_time": "0:16:44", "remaining_time": "0:40:52"}
{"current_steps": 35, "total_steps": 117, "loss": 0.3912, "lr": 8.862084796122998e-06, "epoch": 3.6582278481012658, "percentage": 29.91, "elapsed_time": "0:17:07", "remaining_time": "0:40:06"}
{"current_steps": 36, "total_steps": 117, "loss": 0.3695, "lr": 8.765357330018056e-06, "epoch": 3.759493670886076, "percentage": 30.77, "elapsed_time": "0:17:28", "remaining_time": "0:39:19"}
{"current_steps": 37, "total_steps": 117, "loss": 0.3987, "lr": 8.665259359149132e-06, "epoch": 3.8607594936708862, "percentage": 31.62, "elapsed_time": "0:17:54", "remaining_time": "0:38:42"}
{"current_steps": 38, "total_steps": 117, "loss": 0.3722, "lr": 8.561880484756726e-06, "epoch": 3.962025316455696, "percentage": 32.48, "elapsed_time": "0:18:14", "remaining_time": "0:37:54"}
{"current_steps": 39, "total_steps": 117, "loss": 0.3469, "lr": 8.455313244934324e-06, "epoch": 4.10126582278481, "percentage": 33.33, "elapsed_time": "0:19:41", "remaining_time": "0:39:23"}
{"current_steps": 40, "total_steps": 117, "loss": 0.3401, "lr": 8.345653031794292e-06, "epoch": 4.2025316455696204, "percentage": 34.19, "elapsed_time": "0:20:15", "remaining_time": "0:39:00"}
{"current_steps": 41, "total_steps": 117, "loss": 0.367, "lr": 8.232998006078998e-06, "epoch": 4.30379746835443, "percentage": 35.04, "elapsed_time": "0:20:43", "remaining_time": "0:38:24"}
{"current_steps": 42, "total_steps": 117, "loss": 0.2696, "lr": 8.117449009293668e-06, "epoch": 4.405063291139241, "percentage": 35.9, "elapsed_time": "0:21:05", "remaining_time": "0:37:40"}
{"current_steps": 43, "total_steps": 117, "loss": 0.3087, "lr": 7.99910947343957e-06, "epoch": 4.506329113924051, "percentage": 36.75, "elapsed_time": "0:21:40", "remaining_time": "0:37:17"}
{"current_steps": 44, "total_steps": 117, "loss": 0.3239, "lr": 7.87808532842837e-06, "epoch": 4.6075949367088604, "percentage": 37.61, "elapsed_time": "0:22:08", "remaining_time": "0:36:44"}
{"current_steps": 45, "total_steps": 117, "loss": 0.2656, "lr": 7.754484907260513e-06, "epoch": 4.708860759493671, "percentage": 38.46, "elapsed_time": "0:22:25", "remaining_time": "0:35:52"}
{"current_steps": 46, "total_steps": 117, "loss": 0.2963, "lr": 7.628418849052523e-06, "epoch": 4.810126582278481, "percentage": 39.32, "elapsed_time": "0:22:48", "remaining_time": "0:35:11"}
{"current_steps": 47, "total_steps": 117, "loss": 0.3296, "lr": 7.500000000000001e-06, "epoch": 4.911392405063291, "percentage": 40.17, "elapsed_time": "0:23:19", "remaining_time": "0:34:44"}
{"current_steps": 48, "total_steps": 117, "loss": 0.2582, "lr": 7.369343312364994e-06, "epoch": 5.050632911392405, "percentage": 41.03, "elapsed_time": "0:24:49", "remaining_time": "0:35:41"}
{"current_steps": 49, "total_steps": 117, "loss": 0.3102, "lr": 7.236565741578163e-06, "epoch": 5.151898734177215, "percentage": 41.88, "elapsed_time": "0:25:15", "remaining_time": "0:35:03"}
{"current_steps": 50, "total_steps": 117, "loss": 0.2222, "lr": 7.101786141547829e-06, "epoch": 5.253164556962025, "percentage": 42.74, "elapsed_time": "0:25:39", "remaining_time": "0:34:23"}
{"current_steps": 51, "total_steps": 117, "loss": 0.2291, "lr": 6.965125158269619e-06, "epoch": 5.3544303797468356, "percentage": 43.59, "elapsed_time": "0:26:05", "remaining_time": "0:33:46"}
{"current_steps": 52, "total_steps": 117, "loss": 0.2867, "lr": 6.8267051218319766e-06, "epoch": 5.455696202531645, "percentage": 44.44, "elapsed_time": "0:26:37", "remaining_time": "0:33:17"}
{"current_steps": 53, "total_steps": 117, "loss": 0.1868, "lr": 6.686649936914151e-06, "epoch": 5.556962025316456, "percentage": 45.3, "elapsed_time": "0:26:52", "remaining_time": "0:32:26"}
{"current_steps": 54, "total_steps": 117, "loss": 0.1927, "lr": 6.545084971874738e-06, "epoch": 5.658227848101266, "percentage": 46.15, "elapsed_time": "0:27:12", "remaining_time": "0:31:44"}
{"current_steps": 55, "total_steps": 117, "loss": 0.3279, "lr": 6.402136946530014e-06, "epoch": 5.759493670886076, "percentage": 47.01, "elapsed_time": "0:27:47", "remaining_time": "0:31:19"}
{"current_steps": 56, "total_steps": 117, "loss": 0.209, "lr": 6.257933818722544e-06, "epoch": 5.860759493670886, "percentage": 47.86, "elapsed_time": "0:28:08", "remaining_time": "0:30:38"}
{"current_steps": 57, "total_steps": 117, "loss": 0.2742, "lr": 6.112604669781572e-06, "epoch": 5.962025316455696, "percentage": 48.72, "elapsed_time": "0:28:35", "remaining_time": "0:30:05"}
{"current_steps": 58, "total_steps": 117, "loss": 0.2199, "lr": 5.9662795889777666e-06, "epoch": 6.10126582278481, "percentage": 49.57, "elapsed_time": "0:30:10", "remaining_time": "0:30:41"}
{"current_steps": 59, "total_steps": 117, "loss": 0.1918, "lr": 5.819089557075689e-06, "epoch": 6.2025316455696204, "percentage": 50.43, "elapsed_time": "0:30:27", "remaining_time": "0:29:56"}
{"current_steps": 60, "total_steps": 117, "loss": 0.197, "lr": 5.671166329088278e-06, "epoch": 6.30379746835443, "percentage": 51.28, "elapsed_time": "0:30:53", "remaining_time": "0:29:21"}
{"current_steps": 61, "total_steps": 117, "loss": 0.1614, "lr": 5.522642316338268e-06, "epoch": 6.405063291139241, "percentage": 52.14, "elapsed_time": "0:31:14", "remaining_time": "0:28:40"}
{"current_steps": 62, "total_steps": 117, "loss": 0.2126, "lr": 5.373650467932122e-06, "epoch": 6.506329113924051, "percentage": 52.99, "elapsed_time": "0:31:37", "remaining_time": "0:28:02"}
{"current_steps": 63, "total_steps": 117, "loss": 0.1935, "lr": 5.224324151752575e-06, "epoch": 6.6075949367088604, "percentage": 53.85, "elapsed_time": "0:32:01", "remaining_time": "0:27:26"}
{"current_steps": 64, "total_steps": 117, "loss": 0.1897, "lr": 5.074797035076319e-06, "epoch": 6.708860759493671, "percentage": 54.7, "elapsed_time": "0:32:19", "remaining_time": "0:26:46"}
{"current_steps": 65, "total_steps": 117, "loss": 0.2797, "lr": 4.9252029649236835e-06, "epoch": 6.810126582278481, "percentage": 55.56, "elapsed_time": "0:32:52", "remaining_time": "0:26:18"}