chchen's picture
Training in progress, step 450
0926a73 verified
raw
history blame
10.4 kB
{"current_steps": 10, "total_steps": 3225, "loss": 1.3797, "lr": 3.0959752321981426e-06, "epoch": 0.015503875968992248, "percentage": 0.31, "elapsed_time": "0:01:17", "remaining_time": "6:55:05"}
{"current_steps": 20, "total_steps": 3225, "loss": 1.277, "lr": 6.191950464396285e-06, "epoch": 0.031007751937984496, "percentage": 0.62, "elapsed_time": "0:02:33", "remaining_time": "6:49:18"}
{"current_steps": 30, "total_steps": 3225, "loss": 1.1112, "lr": 9.287925696594429e-06, "epoch": 0.046511627906976744, "percentage": 0.93, "elapsed_time": "0:03:49", "remaining_time": "6:47:01"}
{"current_steps": 40, "total_steps": 3225, "loss": 0.7071, "lr": 1.238390092879257e-05, "epoch": 0.06201550387596899, "percentage": 1.24, "elapsed_time": "0:05:05", "remaining_time": "6:45:12"}
{"current_steps": 50, "total_steps": 3225, "loss": 0.4179, "lr": 1.5479876160990712e-05, "epoch": 0.07751937984496124, "percentage": 1.55, "elapsed_time": "0:06:21", "remaining_time": "6:43:47"}
{"current_steps": 50, "total_steps": 3225, "eval_loss": 0.34340164065361023, "epoch": 0.07751937984496124, "percentage": 1.55, "elapsed_time": "0:08:55", "remaining_time": "9:26:25"}
{"current_steps": 60, "total_steps": 3225, "loss": 0.3034, "lr": 1.8575851393188857e-05, "epoch": 0.09302325581395349, "percentage": 1.86, "elapsed_time": "0:10:15", "remaining_time": "9:01:01"}
{"current_steps": 70, "total_steps": 3225, "loss": 0.2055, "lr": 2.1671826625387e-05, "epoch": 0.10852713178294573, "percentage": 2.17, "elapsed_time": "0:11:31", "remaining_time": "8:39:23"}
{"current_steps": 80, "total_steps": 3225, "loss": 0.1391, "lr": 2.476780185758514e-05, "epoch": 0.12403100775193798, "percentage": 2.48, "elapsed_time": "0:12:47", "remaining_time": "8:22:57"}
{"current_steps": 90, "total_steps": 3225, "loss": 0.1286, "lr": 2.7863777089783283e-05, "epoch": 0.13953488372093023, "percentage": 2.79, "elapsed_time": "0:14:03", "remaining_time": "8:09:55"}
{"current_steps": 100, "total_steps": 3225, "loss": 0.0933, "lr": 3.0959752321981425e-05, "epoch": 0.15503875968992248, "percentage": 3.1, "elapsed_time": "0:15:20", "remaining_time": "7:59:15"}
{"current_steps": 100, "total_steps": 3225, "eval_loss": 0.08204219490289688, "epoch": 0.15503875968992248, "percentage": 3.1, "elapsed_time": "0:17:53", "remaining_time": "9:19:16"}
{"current_steps": 110, "total_steps": 3225, "loss": 0.1012, "lr": 3.4055727554179566e-05, "epoch": 0.17054263565891473, "percentage": 3.41, "elapsed_time": "0:19:15", "remaining_time": "9:05:34"}
{"current_steps": 120, "total_steps": 3225, "loss": 0.0923, "lr": 3.7151702786377715e-05, "epoch": 0.18604651162790697, "percentage": 3.72, "elapsed_time": "0:20:32", "remaining_time": "8:51:18"}
{"current_steps": 130, "total_steps": 3225, "loss": 0.1105, "lr": 4.024767801857585e-05, "epoch": 0.20155038759689922, "percentage": 4.03, "elapsed_time": "0:21:47", "remaining_time": "8:38:56"}
{"current_steps": 140, "total_steps": 3225, "loss": 0.0983, "lr": 4.3343653250774e-05, "epoch": 0.21705426356589147, "percentage": 4.34, "elapsed_time": "0:23:03", "remaining_time": "8:28:11"}
{"current_steps": 150, "total_steps": 3225, "loss": 0.0662, "lr": 4.6439628482972134e-05, "epoch": 0.23255813953488372, "percentage": 4.65, "elapsed_time": "0:24:19", "remaining_time": "8:18:41"}
{"current_steps": 150, "total_steps": 3225, "eval_loss": 0.0667666420340538, "epoch": 0.23255813953488372, "percentage": 4.65, "elapsed_time": "0:26:53", "remaining_time": "9:11:09"}
{"current_steps": 160, "total_steps": 3225, "loss": 0.079, "lr": 4.953560371517028e-05, "epoch": 0.24806201550387597, "percentage": 4.96, "elapsed_time": "0:28:13", "remaining_time": "9:00:34"}
{"current_steps": 170, "total_steps": 3225, "loss": 0.0753, "lr": 5.2631578947368424e-05, "epoch": 0.26356589147286824, "percentage": 5.27, "elapsed_time": "0:29:29", "remaining_time": "8:49:52"}
{"current_steps": 180, "total_steps": 3225, "loss": 0.0691, "lr": 5.5727554179566566e-05, "epoch": 0.27906976744186046, "percentage": 5.58, "elapsed_time": "0:30:45", "remaining_time": "8:40:13"}
{"current_steps": 190, "total_steps": 3225, "loss": 0.0706, "lr": 5.882352941176471e-05, "epoch": 0.29457364341085274, "percentage": 5.89, "elapsed_time": "0:32:01", "remaining_time": "8:31:27"}
{"current_steps": 200, "total_steps": 3225, "loss": 0.0584, "lr": 6.191950464396285e-05, "epoch": 0.31007751937984496, "percentage": 6.2, "elapsed_time": "0:33:16", "remaining_time": "8:23:23"}
{"current_steps": 200, "total_steps": 3225, "eval_loss": 0.058870695531368256, "epoch": 0.31007751937984496, "percentage": 6.2, "elapsed_time": "0:35:50", "remaining_time": "9:01:58"}
{"current_steps": 210, "total_steps": 3225, "loss": 0.0659, "lr": 6.501547987616098e-05, "epoch": 0.32558139534883723, "percentage": 6.51, "elapsed_time": "0:37:10", "remaining_time": "8:53:37"}
{"current_steps": 220, "total_steps": 3225, "loss": 0.0563, "lr": 6.811145510835913e-05, "epoch": 0.34108527131782945, "percentage": 6.82, "elapsed_time": "0:38:25", "remaining_time": "8:44:54"}
{"current_steps": 230, "total_steps": 3225, "loss": 0.06, "lr": 7.120743034055728e-05, "epoch": 0.35658914728682173, "percentage": 7.13, "elapsed_time": "0:39:41", "remaining_time": "8:36:47"}
{"current_steps": 240, "total_steps": 3225, "loss": 0.0844, "lr": 7.430340557275543e-05, "epoch": 0.37209302325581395, "percentage": 7.44, "elapsed_time": "0:40:57", "remaining_time": "8:29:20"}
{"current_steps": 250, "total_steps": 3225, "loss": 0.0666, "lr": 7.739938080495357e-05, "epoch": 0.3875968992248062, "percentage": 7.75, "elapsed_time": "0:42:13", "remaining_time": "8:22:26"}
{"current_steps": 250, "total_steps": 3225, "eval_loss": 0.05274031311273575, "epoch": 0.3875968992248062, "percentage": 7.75, "elapsed_time": "0:44:46", "remaining_time": "8:52:49"}
{"current_steps": 260, "total_steps": 3225, "loss": 0.0531, "lr": 8.04953560371517e-05, "epoch": 0.40310077519379844, "percentage": 8.06, "elapsed_time": "0:46:07", "remaining_time": "8:45:55"}
{"current_steps": 270, "total_steps": 3225, "loss": 0.0542, "lr": 8.359133126934985e-05, "epoch": 0.4186046511627907, "percentage": 8.37, "elapsed_time": "0:47:23", "remaining_time": "8:38:36"}
{"current_steps": 280, "total_steps": 3225, "loss": 0.0835, "lr": 8.6687306501548e-05, "epoch": 0.43410852713178294, "percentage": 8.68, "elapsed_time": "0:48:38", "remaining_time": "8:31:40"}
{"current_steps": 290, "total_steps": 3225, "loss": 0.0561, "lr": 8.978328173374613e-05, "epoch": 0.4496124031007752, "percentage": 8.99, "elapsed_time": "0:49:54", "remaining_time": "8:25:09"}
{"current_steps": 300, "total_steps": 3225, "loss": 0.0448, "lr": 9.287925696594427e-05, "epoch": 0.46511627906976744, "percentage": 9.3, "elapsed_time": "0:51:10", "remaining_time": "8:18:59"}
{"current_steps": 300, "total_steps": 3225, "eval_loss": 0.052115585654973984, "epoch": 0.46511627906976744, "percentage": 9.3, "elapsed_time": "0:53:43", "remaining_time": "8:43:52"}
{"current_steps": 310, "total_steps": 3225, "loss": 0.0597, "lr": 9.597523219814242e-05, "epoch": 0.4806201550387597, "percentage": 9.61, "elapsed_time": "0:55:04", "remaining_time": "8:37:48"}
{"current_steps": 320, "total_steps": 3225, "loss": 0.0406, "lr": 9.907120743034056e-05, "epoch": 0.49612403100775193, "percentage": 9.92, "elapsed_time": "0:56:20", "remaining_time": "8:31:24"}
{"current_steps": 330, "total_steps": 3225, "loss": 0.0499, "lr": 9.999856438185238e-05, "epoch": 0.5116279069767442, "percentage": 10.23, "elapsed_time": "0:57:35", "remaining_time": "8:25:15"}
{"current_steps": 340, "total_steps": 3225, "loss": 0.0558, "lr": 9.999153298122152e-05, "epoch": 0.5271317829457365, "percentage": 10.54, "elapsed_time": "0:58:51", "remaining_time": "8:19:23"}
{"current_steps": 350, "total_steps": 3225, "loss": 0.0474, "lr": 9.997864293614054e-05, "epoch": 0.5426356589147286, "percentage": 10.85, "elapsed_time": "1:00:07", "remaining_time": "8:13:49"}
{"current_steps": 350, "total_steps": 3225, "eval_loss": 0.048954565078020096, "epoch": 0.5426356589147286, "percentage": 10.85, "elapsed_time": "1:02:40", "remaining_time": "8:34:48"}
{"current_steps": 360, "total_steps": 3225, "loss": 0.0462, "lr": 9.995989575722902e-05, "epoch": 0.5581395348837209, "percentage": 11.16, "elapsed_time": "1:04:00", "remaining_time": "8:29:26"}
{"current_steps": 370, "total_steps": 3225, "loss": 0.063, "lr": 9.993529364152018e-05, "epoch": 0.5736434108527132, "percentage": 11.47, "elapsed_time": "1:05:16", "remaining_time": "8:23:43"}
{"current_steps": 380, "total_steps": 3225, "loss": 0.0606, "lr": 9.990483947220319e-05, "epoch": 0.5891472868217055, "percentage": 11.78, "elapsed_time": "1:06:32", "remaining_time": "8:18:12"}
{"current_steps": 390, "total_steps": 3225, "loss": 0.0531, "lr": 9.986853681828546e-05, "epoch": 0.6046511627906976, "percentage": 12.09, "elapsed_time": "1:07:48", "remaining_time": "8:12:56"}
{"current_steps": 400, "total_steps": 3225, "loss": 0.0546, "lr": 9.982638993417425e-05, "epoch": 0.6201550387596899, "percentage": 12.4, "elapsed_time": "1:09:04", "remaining_time": "8:07:50"}
{"current_steps": 400, "total_steps": 3225, "eval_loss": 0.0430627167224884, "epoch": 0.6201550387596899, "percentage": 12.4, "elapsed_time": "1:11:37", "remaining_time": "8:25:52"}
{"current_steps": 410, "total_steps": 3225, "loss": 0.0509, "lr": 9.977840375917817e-05, "epoch": 0.6356589147286822, "percentage": 12.71, "elapsed_time": "1:12:58", "remaining_time": "8:20:58"}
{"current_steps": 420, "total_steps": 3225, "loss": 0.06, "lr": 9.972458391692827e-05, "epoch": 0.6511627906976745, "percentage": 13.02, "elapsed_time": "1:14:14", "remaining_time": "8:15:47"}
{"current_steps": 430, "total_steps": 3225, "loss": 0.0507, "lr": 9.966493671471904e-05, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "1:15:30", "remaining_time": "8:10:46"}
{"current_steps": 440, "total_steps": 3225, "loss": 0.0597, "lr": 9.959946914276922e-05, "epoch": 0.6821705426356589, "percentage": 13.64, "elapsed_time": "1:16:46", "remaining_time": "8:05:56"}
{"current_steps": 450, "total_steps": 3225, "loss": 0.0432, "lr": 9.952818887340257e-05, "epoch": 0.6976744186046512, "percentage": 13.95, "elapsed_time": "1:18:02", "remaining_time": "8:01:12"}
{"current_steps": 450, "total_steps": 3225, "eval_loss": 0.03933678939938545, "epoch": 0.6976744186046512, "percentage": 13.95, "elapsed_time": "1:20:35", "remaining_time": "8:16:57"}