no_pipeline_1k / trainer_log.jsonl
neginr's picture
Training in progress, epoch 6
da1afb5 verified
{"current_steps": 1, "total_steps": 70, "loss": 1.0969, "lr": 2.8571428571428573e-06, "epoch": 0.09375, "percentage": 1.43, "elapsed_time": "0:00:16", "remaining_time": "0:19:32"}
{"current_steps": 2, "total_steps": 70, "loss": 1.1622, "lr": 5.7142857142857145e-06, "epoch": 0.1875, "percentage": 2.86, "elapsed_time": "0:00:31", "remaining_time": "0:17:46"}
{"current_steps": 3, "total_steps": 70, "loss": 1.0888, "lr": 8.571428571428571e-06, "epoch": 0.28125, "percentage": 4.29, "elapsed_time": "0:00:43", "remaining_time": "0:16:19"}
{"current_steps": 4, "total_steps": 70, "loss": 0.9559, "lr": 1.1428571428571429e-05, "epoch": 0.375, "percentage": 5.71, "elapsed_time": "0:00:57", "remaining_time": "0:15:49"}
{"current_steps": 5, "total_steps": 70, "loss": 0.9652, "lr": 1.4285714285714287e-05, "epoch": 0.46875, "percentage": 7.14, "elapsed_time": "0:01:10", "remaining_time": "0:15:18"}
{"current_steps": 6, "total_steps": 70, "loss": 0.9197, "lr": 1.7142857142857142e-05, "epoch": 0.5625, "percentage": 8.57, "elapsed_time": "0:01:21", "remaining_time": "0:14:34"}
{"current_steps": 7, "total_steps": 70, "loss": 0.927, "lr": 2e-05, "epoch": 0.65625, "percentage": 10.0, "elapsed_time": "0:01:36", "remaining_time": "0:14:32"}
{"current_steps": 8, "total_steps": 70, "loss": 0.8941, "lr": 1.9987569212189224e-05, "epoch": 0.75, "percentage": 11.43, "elapsed_time": "0:01:51", "remaining_time": "0:14:23"}
{"current_steps": 9, "total_steps": 70, "loss": 0.85, "lr": 1.9950307753654016e-05, "epoch": 0.84375, "percentage": 12.86, "elapsed_time": "0:02:03", "remaining_time": "0:13:56"}
{"current_steps": 10, "total_steps": 70, "loss": 0.8695, "lr": 1.9888308262251286e-05, "epoch": 0.9375, "percentage": 14.29, "elapsed_time": "0:02:16", "remaining_time": "0:13:37"}
{"current_steps": 11, "total_steps": 70, "loss": 0.761, "lr": 1.9801724878485438e-05, "epoch": 1.0625, "percentage": 15.71, "elapsed_time": "0:04:14", "remaining_time": "0:22:42"}
{"current_steps": 12, "total_steps": 70, "loss": 0.7272, "lr": 1.969077286229078e-05, "epoch": 1.15625, "percentage": 17.14, "elapsed_time": "0:04:25", "remaining_time": "0:21:21"}
{"current_steps": 13, "total_steps": 70, "loss": 0.7332, "lr": 1.955572805786141e-05, "epoch": 1.25, "percentage": 18.57, "elapsed_time": "0:04:36", "remaining_time": "0:20:11"}
{"current_steps": 14, "total_steps": 70, "loss": 0.7255, "lr": 1.9396926207859085e-05, "epoch": 1.34375, "percentage": 20.0, "elapsed_time": "0:04:46", "remaining_time": "0:19:05"}
{"current_steps": 15, "total_steps": 70, "loss": 0.6784, "lr": 1.921476211870408e-05, "epoch": 1.4375, "percentage": 21.43, "elapsed_time": "0:04:59", "remaining_time": "0:18:18"}
{"current_steps": 16, "total_steps": 70, "loss": 0.6729, "lr": 1.900968867902419e-05, "epoch": 1.53125, "percentage": 22.86, "elapsed_time": "0:05:15", "remaining_time": "0:17:43"}
{"current_steps": 17, "total_steps": 70, "loss": 0.6509, "lr": 1.8782215733702286e-05, "epoch": 1.625, "percentage": 24.29, "elapsed_time": "0:05:29", "remaining_time": "0:17:06"}
{"current_steps": 18, "total_steps": 70, "loss": 0.636, "lr": 1.8532908816321557e-05, "epoch": 1.71875, "percentage": 25.71, "elapsed_time": "0:05:41", "remaining_time": "0:16:27"}
{"current_steps": 19, "total_steps": 70, "loss": 0.6498, "lr": 1.826238774315995e-05, "epoch": 1.8125, "percentage": 27.14, "elapsed_time": "0:05:53", "remaining_time": "0:15:48"}
{"current_steps": 20, "total_steps": 70, "loss": 0.6449, "lr": 1.7971325072229227e-05, "epoch": 1.90625, "percentage": 28.57, "elapsed_time": "0:06:08", "remaining_time": "0:15:20"}
{"current_steps": 21, "total_steps": 70, "loss": 0.6177, "lr": 1.766044443118978e-05, "epoch": 2.03125, "percentage": 30.0, "elapsed_time": "0:08:08", "remaining_time": "0:19:00"}
{"current_steps": 22, "total_steps": 70, "loss": 0.5356, "lr": 1.7330518718298263e-05, "epoch": 2.125, "percentage": 31.43, "elapsed_time": "0:08:23", "remaining_time": "0:18:18"}
{"current_steps": 23, "total_steps": 70, "loss": 0.4944, "lr": 1.698236818086073e-05, "epoch": 2.21875, "percentage": 32.86, "elapsed_time": "0:08:38", "remaining_time": "0:17:39"}
{"current_steps": 24, "total_steps": 70, "loss": 0.4853, "lr": 1.6616858375968596e-05, "epoch": 2.3125, "percentage": 34.29, "elapsed_time": "0:08:50", "remaining_time": "0:16:56"}
{"current_steps": 25, "total_steps": 70, "loss": 0.468, "lr": 1.6234898018587336e-05, "epoch": 2.40625, "percentage": 35.71, "elapsed_time": "0:09:03", "remaining_time": "0:16:17"}
{"current_steps": 26, "total_steps": 70, "loss": 0.5189, "lr": 1.5837436722347902e-05, "epoch": 2.5, "percentage": 37.14, "elapsed_time": "0:09:14", "remaining_time": "0:15:38"}
{"current_steps": 27, "total_steps": 70, "loss": 0.4353, "lr": 1.5425462638657597e-05, "epoch": 2.59375, "percentage": 38.57, "elapsed_time": "0:09:22", "remaining_time": "0:14:56"}
{"current_steps": 28, "total_steps": 70, "loss": 0.4513, "lr": 1.5000000000000002e-05, "epoch": 2.6875, "percentage": 40.0, "elapsed_time": "0:09:35", "remaining_time": "0:14:22"}
{"current_steps": 29, "total_steps": 70, "loss": 0.4769, "lr": 1.4562106573531632e-05, "epoch": 2.78125, "percentage": 41.43, "elapsed_time": "0:09:50", "remaining_time": "0:13:55"}
{"current_steps": 30, "total_steps": 70, "loss": 0.4683, "lr": 1.4112871031306118e-05, "epoch": 2.875, "percentage": 42.86, "elapsed_time": "0:10:02", "remaining_time": "0:13:23"}
{"current_steps": 31, "total_steps": 70, "loss": 0.4439, "lr": 1.3653410243663953e-05, "epoch": 2.96875, "percentage": 44.29, "elapsed_time": "0:10:12", "remaining_time": "0:12:50"}
{"current_steps": 32, "total_steps": 70, "loss": 0.4003, "lr": 1.3184866502516846e-05, "epoch": 3.09375, "percentage": 45.71, "elapsed_time": "0:12:11", "remaining_time": "0:14:28"}
{"current_steps": 33, "total_steps": 70, "loss": 0.375, "lr": 1.2708404681430054e-05, "epoch": 3.1875, "percentage": 47.14, "elapsed_time": "0:12:23", "remaining_time": "0:13:53"}
{"current_steps": 34, "total_steps": 70, "loss": 0.3495, "lr": 1.2225209339563144e-05, "epoch": 3.28125, "percentage": 48.57, "elapsed_time": "0:12:38", "remaining_time": "0:13:23"}
{"current_steps": 35, "total_steps": 70, "loss": 0.3432, "lr": 1.1736481776669307e-05, "epoch": 3.375, "percentage": 50.0, "elapsed_time": "0:12:51", "remaining_time": "0:12:51"}
{"current_steps": 36, "total_steps": 70, "loss": 0.3255, "lr": 1.1243437046474854e-05, "epoch": 3.46875, "percentage": 51.43, "elapsed_time": "0:13:05", "remaining_time": "0:12:21"}
{"current_steps": 37, "total_steps": 70, "loss": 0.3543, "lr": 1.0747300935864245e-05, "epoch": 3.5625, "percentage": 52.86, "elapsed_time": "0:13:18", "remaining_time": "0:11:52"}
{"current_steps": 38, "total_steps": 70, "loss": 0.3329, "lr": 1.0249306917380731e-05, "epoch": 3.65625, "percentage": 54.29, "elapsed_time": "0:13:30", "remaining_time": "0:11:22"}
{"current_steps": 39, "total_steps": 70, "loss": 0.3361, "lr": 9.750693082619274e-06, "epoch": 3.75, "percentage": 55.71, "elapsed_time": "0:13:41", "remaining_time": "0:10:53"}
{"current_steps": 40, "total_steps": 70, "loss": 0.32, "lr": 9.252699064135759e-06, "epoch": 3.84375, "percentage": 57.14, "elapsed_time": "0:13:54", "remaining_time": "0:10:25"}
{"current_steps": 41, "total_steps": 70, "loss": 0.3349, "lr": 8.756562953525151e-06, "epoch": 3.9375, "percentage": 58.57, "elapsed_time": "0:14:06", "remaining_time": "0:09:58"}
{"current_steps": 42, "total_steps": 70, "loss": 0.3181, "lr": 8.263518223330698e-06, "epoch": 4.0625, "percentage": 60.0, "elapsed_time": "0:16:04", "remaining_time": "0:10:43"}
{"current_steps": 43, "total_steps": 70, "loss": 0.2878, "lr": 7.774790660436857e-06, "epoch": 4.15625, "percentage": 61.43, "elapsed_time": "0:16:15", "remaining_time": "0:10:12"}
{"current_steps": 44, "total_steps": 70, "loss": 0.2664, "lr": 7.291595318569951e-06, "epoch": 4.25, "percentage": 62.86, "elapsed_time": "0:16:30", "remaining_time": "0:09:45"}
{"current_steps": 45, "total_steps": 70, "loss": 0.2519, "lr": 6.815133497483157e-06, "epoch": 4.34375, "percentage": 64.29, "elapsed_time": "0:16:45", "remaining_time": "0:09:18"}
{"current_steps": 46, "total_steps": 70, "loss": 0.2389, "lr": 6.34658975633605e-06, "epoch": 4.4375, "percentage": 65.71, "elapsed_time": "0:16:59", "remaining_time": "0:08:51"}
{"current_steps": 47, "total_steps": 70, "loss": 0.2535, "lr": 5.887128968693887e-06, "epoch": 4.53125, "percentage": 67.14, "elapsed_time": "0:17:11", "remaining_time": "0:08:24"}
{"current_steps": 48, "total_steps": 70, "loss": 0.2445, "lr": 5.43789342646837e-06, "epoch": 4.625, "percentage": 68.57, "elapsed_time": "0:17:20", "remaining_time": "0:07:57"}
{"current_steps": 49, "total_steps": 70, "loss": 0.2338, "lr": 5.000000000000003e-06, "epoch": 4.71875, "percentage": 70.0, "elapsed_time": "0:17:33", "remaining_time": "0:07:31"}
{"current_steps": 50, "total_steps": 70, "loss": 0.2713, "lr": 4.5745373613424075e-06, "epoch": 4.8125, "percentage": 71.43, "elapsed_time": "0:17:47", "remaining_time": "0:07:07"}
{"current_steps": 51, "total_steps": 70, "loss": 0.2671, "lr": 4.162563277652104e-06, "epoch": 4.90625, "percentage": 72.86, "elapsed_time": "0:18:00", "remaining_time": "0:06:42"}
{"current_steps": 52, "total_steps": 70, "loss": 0.2578, "lr": 3.7651019814126656e-06, "epoch": 5.03125, "percentage": 74.29, "elapsed_time": "0:19:49", "remaining_time": "0:06:51"}
{"current_steps": 53, "total_steps": 70, "loss": 0.2494, "lr": 3.3831416240314085e-06, "epoch": 5.125, "percentage": 75.71, "elapsed_time": "0:20:02", "remaining_time": "0:06:25"}
{"current_steps": 54, "total_steps": 70, "loss": 0.201, "lr": 3.017631819139273e-06, "epoch": 5.21875, "percentage": 77.14, "elapsed_time": "0:20:13", "remaining_time": "0:05:59"}
{"current_steps": 55, "total_steps": 70, "loss": 0.2311, "lr": 2.669481281701739e-06, "epoch": 5.3125, "percentage": 78.57, "elapsed_time": "0:20:27", "remaining_time": "0:05:34"}
{"current_steps": 56, "total_steps": 70, "loss": 0.2233, "lr": 2.339555568810221e-06, "epoch": 5.40625, "percentage": 80.0, "elapsed_time": "0:20:37", "remaining_time": "0:05:09"}
{"current_steps": 57, "total_steps": 70, "loss": 0.2184, "lr": 2.0286749277707783e-06, "epoch": 5.5, "percentage": 81.43, "elapsed_time": "0:20:48", "remaining_time": "0:04:44"}
{"current_steps": 58, "total_steps": 70, "loss": 0.2361, "lr": 1.7376122568400533e-06, "epoch": 5.59375, "percentage": 82.86, "elapsed_time": "0:21:04", "remaining_time": "0:04:21"}
{"current_steps": 59, "total_steps": 70, "loss": 0.195, "lr": 1.467091183678444e-06, "epoch": 5.6875, "percentage": 84.29, "elapsed_time": "0:21:12", "remaining_time": "0:03:57"}
{"current_steps": 60, "total_steps": 70, "loss": 0.2433, "lr": 1.2177842662977136e-06, "epoch": 5.78125, "percentage": 85.71, "elapsed_time": "0:21:24", "remaining_time": "0:03:34"}
{"current_steps": 61, "total_steps": 70, "loss": 0.2232, "lr": 9.903113209758098e-07, "epoch": 5.875, "percentage": 87.14, "elapsed_time": "0:21:38", "remaining_time": "0:03:11"}
{"current_steps": 62, "total_steps": 70, "loss": 0.1921, "lr": 7.852378812959227e-07, "epoch": 5.96875, "percentage": 88.57, "elapsed_time": "0:21:51", "remaining_time": "0:02:49"}
{"current_steps": 63, "total_steps": 70, "loss": 0.2026, "lr": 6.030737921409169e-07, "epoch": 6.09375, "percentage": 90.0, "elapsed_time": "0:23:47", "remaining_time": "0:02:38"}
{"current_steps": 64, "total_steps": 70, "loss": 0.1918, "lr": 4.4427194213859216e-07, "epoch": 6.1875, "percentage": 91.43, "elapsed_time": "0:23:57", "remaining_time": "0:02:14"}
{"current_steps": 65, "total_steps": 70, "loss": 0.2292, "lr": 3.0922713770922155e-07, "epoch": 6.28125, "percentage": 92.86, "elapsed_time": "0:24:09", "remaining_time": "0:01:51"}
{"current_steps": 66, "total_steps": 70, "loss": 0.2002, "lr": 1.9827512151456175e-07, "epoch": 6.375, "percentage": 94.29, "elapsed_time": "0:24:23", "remaining_time": "0:01:28"}
{"current_steps": 67, "total_steps": 70, "loss": 0.2056, "lr": 1.1169173774871478e-07, "epoch": 6.46875, "percentage": 95.71, "elapsed_time": "0:24:37", "remaining_time": "0:01:06"}
{"current_steps": 68, "total_steps": 70, "loss": 0.2116, "lr": 4.9692246345985905e-08, "epoch": 6.5625, "percentage": 97.14, "elapsed_time": "0:24:51", "remaining_time": "0:00:43"}
{"current_steps": 69, "total_steps": 70, "loss": 0.2591, "lr": 1.2430787810776556e-08, "epoch": 6.65625, "percentage": 98.57, "elapsed_time": "0:25:07", "remaining_time": "0:00:21"}
{"current_steps": 70, "total_steps": 70, "loss": 0.2233, "lr": 0.0, "epoch": 6.75, "percentage": 100.0, "elapsed_time": "0:25:19", "remaining_time": "0:00:00"}
{"current_steps": 70, "total_steps": 70, "epoch": 6.75, "percentage": 100.0, "elapsed_time": "0:27:50", "remaining_time": "0:00:00"}