gsmyrnis's picture
Training in progress, epoch 3
0c3975f verified
{"current_steps": 10, "total_steps": 834, "loss": 1.0175, "lr": 5e-06, "epoch": 0.03597122302158273, "percentage": 1.2, "elapsed_time": "0:01:00", "remaining_time": "1:23:34"}
{"current_steps": 20, "total_steps": 834, "loss": 0.9337, "lr": 5e-06, "epoch": 0.07194244604316546, "percentage": 2.4, "elapsed_time": "0:02:02", "remaining_time": "1:23:05"}
{"current_steps": 30, "total_steps": 834, "loss": 0.8923, "lr": 5e-06, "epoch": 0.1079136690647482, "percentage": 3.6, "elapsed_time": "0:03:03", "remaining_time": "1:22:11"}
{"current_steps": 40, "total_steps": 834, "loss": 0.8673, "lr": 5e-06, "epoch": 0.14388489208633093, "percentage": 4.8, "elapsed_time": "0:04:05", "remaining_time": "1:21:05"}
{"current_steps": 50, "total_steps": 834, "loss": 0.8553, "lr": 5e-06, "epoch": 0.17985611510791366, "percentage": 6.0, "elapsed_time": "0:05:06", "remaining_time": "1:20:06"}
{"current_steps": 60, "total_steps": 834, "loss": 0.8492, "lr": 5e-06, "epoch": 0.2158273381294964, "percentage": 7.19, "elapsed_time": "0:06:08", "remaining_time": "1:19:07"}
{"current_steps": 70, "total_steps": 834, "loss": 0.8382, "lr": 5e-06, "epoch": 0.2517985611510791, "percentage": 8.39, "elapsed_time": "0:07:09", "remaining_time": "1:18:07"}
{"current_steps": 80, "total_steps": 834, "loss": 0.8318, "lr": 5e-06, "epoch": 0.28776978417266186, "percentage": 9.59, "elapsed_time": "0:08:11", "remaining_time": "1:17:07"}
{"current_steps": 90, "total_steps": 834, "loss": 0.825, "lr": 5e-06, "epoch": 0.3237410071942446, "percentage": 10.79, "elapsed_time": "0:09:12", "remaining_time": "1:16:07"}
{"current_steps": 100, "total_steps": 834, "loss": 0.8225, "lr": 5e-06, "epoch": 0.3597122302158273, "percentage": 11.99, "elapsed_time": "0:10:14", "remaining_time": "1:15:12"}
{"current_steps": 110, "total_steps": 834, "loss": 0.8165, "lr": 5e-06, "epoch": 0.39568345323741005, "percentage": 13.19, "elapsed_time": "0:11:16", "remaining_time": "1:14:12"}
{"current_steps": 120, "total_steps": 834, "loss": 0.8162, "lr": 5e-06, "epoch": 0.4316546762589928, "percentage": 14.39, "elapsed_time": "0:12:18", "remaining_time": "1:13:11"}
{"current_steps": 130, "total_steps": 834, "loss": 0.8141, "lr": 5e-06, "epoch": 0.4676258992805755, "percentage": 15.59, "elapsed_time": "0:13:19", "remaining_time": "1:12:09"}
{"current_steps": 140, "total_steps": 834, "loss": 0.8113, "lr": 5e-06, "epoch": 0.5035971223021583, "percentage": 16.79, "elapsed_time": "0:14:20", "remaining_time": "1:11:07"}
{"current_steps": 150, "total_steps": 834, "loss": 0.8069, "lr": 5e-06, "epoch": 0.539568345323741, "percentage": 17.99, "elapsed_time": "0:15:22", "remaining_time": "1:10:06"}
{"current_steps": 160, "total_steps": 834, "loss": 0.8087, "lr": 5e-06, "epoch": 0.5755395683453237, "percentage": 19.18, "elapsed_time": "0:16:24", "remaining_time": "1:09:06"}
{"current_steps": 170, "total_steps": 834, "loss": 0.8048, "lr": 5e-06, "epoch": 0.6115107913669064, "percentage": 20.38, "elapsed_time": "0:17:26", "remaining_time": "1:08:05"}
{"current_steps": 180, "total_steps": 834, "loss": 0.8051, "lr": 5e-06, "epoch": 0.6474820143884892, "percentage": 21.58, "elapsed_time": "0:18:27", "remaining_time": "1:07:04"}
{"current_steps": 190, "total_steps": 834, "loss": 0.8044, "lr": 5e-06, "epoch": 0.6834532374100719, "percentage": 22.78, "elapsed_time": "0:19:29", "remaining_time": "1:06:02"}
{"current_steps": 200, "total_steps": 834, "loss": 0.7989, "lr": 5e-06, "epoch": 0.7194244604316546, "percentage": 23.98, "elapsed_time": "0:20:31", "remaining_time": "1:05:02"}
{"current_steps": 210, "total_steps": 834, "loss": 0.8025, "lr": 5e-06, "epoch": 0.7553956834532374, "percentage": 25.18, "elapsed_time": "0:21:33", "remaining_time": "1:04:02"}
{"current_steps": 220, "total_steps": 834, "loss": 0.7988, "lr": 5e-06, "epoch": 0.7913669064748201, "percentage": 26.38, "elapsed_time": "0:22:34", "remaining_time": "1:02:59"}
{"current_steps": 230, "total_steps": 834, "loss": 0.7985, "lr": 5e-06, "epoch": 0.8273381294964028, "percentage": 27.58, "elapsed_time": "0:23:36", "remaining_time": "1:01:58"}
{"current_steps": 240, "total_steps": 834, "loss": 0.7973, "lr": 5e-06, "epoch": 0.8633093525179856, "percentage": 28.78, "elapsed_time": "0:24:37", "remaining_time": "1:00:57"}
{"current_steps": 250, "total_steps": 834, "loss": 0.7933, "lr": 5e-06, "epoch": 0.8992805755395683, "percentage": 29.98, "elapsed_time": "0:25:39", "remaining_time": "0:59:57"}
{"current_steps": 260, "total_steps": 834, "loss": 0.7969, "lr": 5e-06, "epoch": 0.935251798561151, "percentage": 31.18, "elapsed_time": "0:26:41", "remaining_time": "0:58:55"}
{"current_steps": 270, "total_steps": 834, "loss": 0.7933, "lr": 5e-06, "epoch": 0.9712230215827338, "percentage": 32.37, "elapsed_time": "0:27:43", "remaining_time": "0:57:54"}
{"current_steps": 278, "total_steps": 834, "eval_loss": 0.7923575043678284, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:29:00", "remaining_time": "0:58:00"}
{"current_steps": 280, "total_steps": 834, "loss": 0.7823, "lr": 5e-06, "epoch": 1.0071942446043165, "percentage": 33.57, "elapsed_time": "0:30:40", "remaining_time": "1:00:41"}
{"current_steps": 290, "total_steps": 834, "loss": 0.7574, "lr": 5e-06, "epoch": 1.0431654676258992, "percentage": 34.77, "elapsed_time": "0:31:41", "remaining_time": "0:59:26"}
{"current_steps": 300, "total_steps": 834, "loss": 0.7529, "lr": 5e-06, "epoch": 1.079136690647482, "percentage": 35.97, "elapsed_time": "0:32:42", "remaining_time": "0:58:13"}
{"current_steps": 310, "total_steps": 834, "loss": 0.7558, "lr": 5e-06, "epoch": 1.1151079136690647, "percentage": 37.17, "elapsed_time": "0:33:44", "remaining_time": "0:57:01"}
{"current_steps": 320, "total_steps": 834, "loss": 0.7623, "lr": 5e-06, "epoch": 1.1510791366906474, "percentage": 38.37, "elapsed_time": "0:34:45", "remaining_time": "0:55:49"}
{"current_steps": 330, "total_steps": 834, "loss": 0.7601, "lr": 5e-06, "epoch": 1.1870503597122302, "percentage": 39.57, "elapsed_time": "0:35:46", "remaining_time": "0:54:38"}
{"current_steps": 340, "total_steps": 834, "loss": 0.7535, "lr": 5e-06, "epoch": 1.223021582733813, "percentage": 40.77, "elapsed_time": "0:36:47", "remaining_time": "0:53:27"}
{"current_steps": 350, "total_steps": 834, "loss": 0.757, "lr": 5e-06, "epoch": 1.2589928057553956, "percentage": 41.97, "elapsed_time": "0:37:50", "remaining_time": "0:52:19"}
{"current_steps": 360, "total_steps": 834, "loss": 0.759, "lr": 5e-06, "epoch": 1.2949640287769784, "percentage": 43.17, "elapsed_time": "0:38:51", "remaining_time": "0:51:10"}
{"current_steps": 370, "total_steps": 834, "loss": 0.7567, "lr": 5e-06, "epoch": 1.330935251798561, "percentage": 44.36, "elapsed_time": "0:39:53", "remaining_time": "0:50:01"}
{"current_steps": 380, "total_steps": 834, "loss": 0.7592, "lr": 5e-06, "epoch": 1.3669064748201438, "percentage": 45.56, "elapsed_time": "0:40:55", "remaining_time": "0:48:53"}
{"current_steps": 390, "total_steps": 834, "loss": 0.7529, "lr": 5e-06, "epoch": 1.4028776978417266, "percentage": 46.76, "elapsed_time": "0:41:56", "remaining_time": "0:47:44"}
{"current_steps": 400, "total_steps": 834, "loss": 0.7554, "lr": 5e-06, "epoch": 1.4388489208633093, "percentage": 47.96, "elapsed_time": "0:42:58", "remaining_time": "0:46:37"}
{"current_steps": 410, "total_steps": 834, "loss": 0.7547, "lr": 5e-06, "epoch": 1.474820143884892, "percentage": 49.16, "elapsed_time": "0:43:59", "remaining_time": "0:45:29"}
{"current_steps": 420, "total_steps": 834, "loss": 0.7532, "lr": 5e-06, "epoch": 1.5107913669064748, "percentage": 50.36, "elapsed_time": "0:45:01", "remaining_time": "0:44:22"}
{"current_steps": 430, "total_steps": 834, "loss": 0.7585, "lr": 5e-06, "epoch": 1.5467625899280577, "percentage": 51.56, "elapsed_time": "0:46:02", "remaining_time": "0:43:15"}
{"current_steps": 440, "total_steps": 834, "loss": 0.7515, "lr": 5e-06, "epoch": 1.5827338129496402, "percentage": 52.76, "elapsed_time": "0:47:04", "remaining_time": "0:42:08"}
{"current_steps": 450, "total_steps": 834, "loss": 0.7562, "lr": 5e-06, "epoch": 1.6187050359712232, "percentage": 53.96, "elapsed_time": "0:48:06", "remaining_time": "0:41:02"}
{"current_steps": 460, "total_steps": 834, "loss": 0.7559, "lr": 5e-06, "epoch": 1.6546762589928057, "percentage": 55.16, "elapsed_time": "0:49:07", "remaining_time": "0:39:56"}
{"current_steps": 470, "total_steps": 834, "loss": 0.757, "lr": 5e-06, "epoch": 1.6906474820143886, "percentage": 56.35, "elapsed_time": "0:50:09", "remaining_time": "0:38:50"}
{"current_steps": 480, "total_steps": 834, "loss": 0.7552, "lr": 5e-06, "epoch": 1.7266187050359711, "percentage": 57.55, "elapsed_time": "0:51:10", "remaining_time": "0:37:44"}
{"current_steps": 490, "total_steps": 834, "loss": 0.753, "lr": 5e-06, "epoch": 1.762589928057554, "percentage": 58.75, "elapsed_time": "0:52:12", "remaining_time": "0:36:39"}
{"current_steps": 500, "total_steps": 834, "loss": 0.7594, "lr": 5e-06, "epoch": 1.7985611510791366, "percentage": 59.95, "elapsed_time": "0:53:13", "remaining_time": "0:35:33"}
{"current_steps": 510, "total_steps": 834, "loss": 0.7554, "lr": 5e-06, "epoch": 1.8345323741007196, "percentage": 61.15, "elapsed_time": "0:54:14", "remaining_time": "0:34:27"}
{"current_steps": 520, "total_steps": 834, "loss": 0.7537, "lr": 5e-06, "epoch": 1.870503597122302, "percentage": 62.35, "elapsed_time": "0:55:15", "remaining_time": "0:33:22"}
{"current_steps": 530, "total_steps": 834, "loss": 0.7555, "lr": 5e-06, "epoch": 1.906474820143885, "percentage": 63.55, "elapsed_time": "0:56:16", "remaining_time": "0:32:16"}
{"current_steps": 540, "total_steps": 834, "loss": 0.7509, "lr": 5e-06, "epoch": 1.9424460431654675, "percentage": 64.75, "elapsed_time": "0:57:18", "remaining_time": "0:31:11"}
{"current_steps": 550, "total_steps": 834, "loss": 0.7503, "lr": 5e-06, "epoch": 1.9784172661870505, "percentage": 65.95, "elapsed_time": "0:58:19", "remaining_time": "0:30:07"}
{"current_steps": 556, "total_steps": 834, "eval_loss": 0.7788412570953369, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:59:24", "remaining_time": "0:29:42"}
{"current_steps": 560, "total_steps": 834, "loss": 0.735, "lr": 5e-06, "epoch": 2.014388489208633, "percentage": 67.15, "elapsed_time": "1:01:16", "remaining_time": "0:29:58"}
{"current_steps": 570, "total_steps": 834, "loss": 0.7131, "lr": 5e-06, "epoch": 2.050359712230216, "percentage": 68.35, "elapsed_time": "1:02:17", "remaining_time": "0:28:50"}
{"current_steps": 580, "total_steps": 834, "loss": 0.7129, "lr": 5e-06, "epoch": 2.0863309352517985, "percentage": 69.54, "elapsed_time": "1:03:19", "remaining_time": "0:27:43"}
{"current_steps": 590, "total_steps": 834, "loss": 0.7154, "lr": 5e-06, "epoch": 2.1223021582733814, "percentage": 70.74, "elapsed_time": "1:04:20", "remaining_time": "0:26:36"}
{"current_steps": 600, "total_steps": 834, "loss": 0.7163, "lr": 5e-06, "epoch": 2.158273381294964, "percentage": 71.94, "elapsed_time": "1:05:22", "remaining_time": "0:25:29"}
{"current_steps": 610, "total_steps": 834, "loss": 0.7197, "lr": 5e-06, "epoch": 2.194244604316547, "percentage": 73.14, "elapsed_time": "1:06:25", "remaining_time": "0:24:23"}
{"current_steps": 620, "total_steps": 834, "loss": 0.7192, "lr": 5e-06, "epoch": 2.2302158273381294, "percentage": 74.34, "elapsed_time": "1:07:27", "remaining_time": "0:23:17"}
{"current_steps": 630, "total_steps": 834, "loss": 0.717, "lr": 5e-06, "epoch": 2.2661870503597124, "percentage": 75.54, "elapsed_time": "1:08:29", "remaining_time": "0:22:10"}
{"current_steps": 640, "total_steps": 834, "loss": 0.7171, "lr": 5e-06, "epoch": 2.302158273381295, "percentage": 76.74, "elapsed_time": "1:09:31", "remaining_time": "0:21:04"}
{"current_steps": 650, "total_steps": 834, "loss": 0.7179, "lr": 5e-06, "epoch": 2.338129496402878, "percentage": 77.94, "elapsed_time": "1:10:32", "remaining_time": "0:19:58"}
{"current_steps": 660, "total_steps": 834, "loss": 0.7208, "lr": 5e-06, "epoch": 2.3741007194244603, "percentage": 79.14, "elapsed_time": "1:11:34", "remaining_time": "0:18:52"}
{"current_steps": 670, "total_steps": 834, "loss": 0.7201, "lr": 5e-06, "epoch": 2.4100719424460433, "percentage": 80.34, "elapsed_time": "1:12:36", "remaining_time": "0:17:46"}
{"current_steps": 680, "total_steps": 834, "loss": 0.7165, "lr": 5e-06, "epoch": 2.446043165467626, "percentage": 81.53, "elapsed_time": "1:13:38", "remaining_time": "0:16:40"}
{"current_steps": 690, "total_steps": 834, "loss": 0.7199, "lr": 5e-06, "epoch": 2.4820143884892087, "percentage": 82.73, "elapsed_time": "1:14:39", "remaining_time": "0:15:34"}
{"current_steps": 700, "total_steps": 834, "loss": 0.7228, "lr": 5e-06, "epoch": 2.5179856115107913, "percentage": 83.93, "elapsed_time": "1:15:41", "remaining_time": "0:14:29"}
{"current_steps": 710, "total_steps": 834, "loss": 0.7211, "lr": 5e-06, "epoch": 2.553956834532374, "percentage": 85.13, "elapsed_time": "1:16:42", "remaining_time": "0:13:23"}
{"current_steps": 720, "total_steps": 834, "loss": 0.7192, "lr": 5e-06, "epoch": 2.5899280575539567, "percentage": 86.33, "elapsed_time": "1:17:44", "remaining_time": "0:12:18"}
{"current_steps": 730, "total_steps": 834, "loss": 0.7208, "lr": 5e-06, "epoch": 2.6258992805755397, "percentage": 87.53, "elapsed_time": "1:18:45", "remaining_time": "0:11:13"}
{"current_steps": 740, "total_steps": 834, "loss": 0.7184, "lr": 5e-06, "epoch": 2.661870503597122, "percentage": 88.73, "elapsed_time": "1:19:46", "remaining_time": "0:10:08"}
{"current_steps": 750, "total_steps": 834, "loss": 0.7139, "lr": 5e-06, "epoch": 2.697841726618705, "percentage": 89.93, "elapsed_time": "1:20:48", "remaining_time": "0:09:03"}
{"current_steps": 760, "total_steps": 834, "loss": 0.7207, "lr": 5e-06, "epoch": 2.7338129496402876, "percentage": 91.13, "elapsed_time": "1:21:49", "remaining_time": "0:07:58"}
{"current_steps": 770, "total_steps": 834, "loss": 0.7193, "lr": 5e-06, "epoch": 2.7697841726618706, "percentage": 92.33, "elapsed_time": "1:22:51", "remaining_time": "0:06:53"}
{"current_steps": 780, "total_steps": 834, "loss": 0.7185, "lr": 5e-06, "epoch": 2.805755395683453, "percentage": 93.53, "elapsed_time": "1:23:53", "remaining_time": "0:05:48"}
{"current_steps": 790, "total_steps": 834, "loss": 0.7217, "lr": 5e-06, "epoch": 2.841726618705036, "percentage": 94.72, "elapsed_time": "1:24:54", "remaining_time": "0:04:43"}
{"current_steps": 800, "total_steps": 834, "loss": 0.7213, "lr": 5e-06, "epoch": 2.8776978417266186, "percentage": 95.92, "elapsed_time": "1:25:55", "remaining_time": "0:03:39"}
{"current_steps": 810, "total_steps": 834, "loss": 0.7183, "lr": 5e-06, "epoch": 2.9136690647482015, "percentage": 97.12, "elapsed_time": "1:26:57", "remaining_time": "0:02:34"}
{"current_steps": 820, "total_steps": 834, "loss": 0.7216, "lr": 5e-06, "epoch": 2.949640287769784, "percentage": 98.32, "elapsed_time": "1:27:58", "remaining_time": "0:01:30"}
{"current_steps": 830, "total_steps": 834, "loss": 0.7198, "lr": 5e-06, "epoch": 2.985611510791367, "percentage": 99.52, "elapsed_time": "1:29:01", "remaining_time": "0:00:25"}
{"current_steps": 834, "total_steps": 834, "eval_loss": 0.7752296328544617, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:31:23", "remaining_time": "0:00:00"}
{"current_steps": 834, "total_steps": 834, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:32:50", "remaining_time": "0:00:00"}