hp_ablations_llama3_epoch3 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
c227ce8 verified
{"current_steps": 10, "total_steps": 1266, "loss": 0.8881, "lr": 5e-06, "epoch": 0.02365464222353637, "percentage": 0.79, "elapsed_time": "0:04:54", "remaining_time": "10:17:09"}
{"current_steps": 20, "total_steps": 1266, "loss": 0.7888, "lr": 5e-06, "epoch": 0.04730928444707274, "percentage": 1.58, "elapsed_time": "0:09:45", "remaining_time": "10:08:13"}
{"current_steps": 30, "total_steps": 1266, "loss": 0.7578, "lr": 5e-06, "epoch": 0.0709639266706091, "percentage": 2.37, "elapsed_time": "0:14:36", "remaining_time": "10:01:58"}
{"current_steps": 40, "total_steps": 1266, "loss": 0.7402, "lr": 5e-06, "epoch": 0.09461856889414548, "percentage": 3.16, "elapsed_time": "0:19:27", "remaining_time": "9:56:35"}
{"current_steps": 50, "total_steps": 1266, "loss": 0.7286, "lr": 5e-06, "epoch": 0.11827321111768184, "percentage": 3.95, "elapsed_time": "0:24:19", "remaining_time": "9:51:23"}
{"current_steps": 60, "total_steps": 1266, "loss": 0.7167, "lr": 5e-06, "epoch": 0.1419278533412182, "percentage": 4.74, "elapsed_time": "0:29:10", "remaining_time": "9:46:15"}
{"current_steps": 70, "total_steps": 1266, "loss": 0.7122, "lr": 5e-06, "epoch": 0.16558249556475457, "percentage": 5.53, "elapsed_time": "0:34:00", "remaining_time": "9:41:11"}
{"current_steps": 80, "total_steps": 1266, "loss": 0.7019, "lr": 5e-06, "epoch": 0.18923713778829096, "percentage": 6.32, "elapsed_time": "0:38:52", "remaining_time": "9:36:14"}
{"current_steps": 90, "total_steps": 1266, "loss": 0.6865, "lr": 5e-06, "epoch": 0.21289178001182732, "percentage": 7.11, "elapsed_time": "0:43:42", "remaining_time": "9:31:13"}
{"current_steps": 100, "total_steps": 1266, "loss": 0.6854, "lr": 5e-06, "epoch": 0.23654642223536368, "percentage": 7.9, "elapsed_time": "0:48:33", "remaining_time": "9:26:14"}
{"current_steps": 110, "total_steps": 1266, "loss": 0.6904, "lr": 5e-06, "epoch": 0.26020106445890007, "percentage": 8.69, "elapsed_time": "0:53:24", "remaining_time": "9:21:18"}
{"current_steps": 120, "total_steps": 1266, "loss": 0.6776, "lr": 5e-06, "epoch": 0.2838557066824364, "percentage": 9.48, "elapsed_time": "0:58:15", "remaining_time": "9:16:23"}
{"current_steps": 130, "total_steps": 1266, "loss": 0.6738, "lr": 5e-06, "epoch": 0.3075103489059728, "percentage": 10.27, "elapsed_time": "1:03:06", "remaining_time": "9:11:28"}
{"current_steps": 140, "total_steps": 1266, "loss": 0.6822, "lr": 5e-06, "epoch": 0.33116499112950915, "percentage": 11.06, "elapsed_time": "1:07:57", "remaining_time": "9:06:34"}
{"current_steps": 150, "total_steps": 1266, "loss": 0.6649, "lr": 5e-06, "epoch": 0.35481963335304556, "percentage": 11.85, "elapsed_time": "1:12:48", "remaining_time": "9:01:39"}
{"current_steps": 160, "total_steps": 1266, "loss": 0.6696, "lr": 5e-06, "epoch": 0.3784742755765819, "percentage": 12.64, "elapsed_time": "1:17:39", "remaining_time": "8:56:48"}
{"current_steps": 170, "total_steps": 1266, "loss": 0.6671, "lr": 5e-06, "epoch": 0.4021289178001183, "percentage": 13.43, "elapsed_time": "1:22:30", "remaining_time": "8:51:57"}
{"current_steps": 180, "total_steps": 1266, "loss": 0.6743, "lr": 5e-06, "epoch": 0.42578356002365464, "percentage": 14.22, "elapsed_time": "1:27:21", "remaining_time": "8:47:06"}
{"current_steps": 190, "total_steps": 1266, "loss": 0.6704, "lr": 5e-06, "epoch": 0.449438202247191, "percentage": 15.01, "elapsed_time": "1:32:13", "remaining_time": "8:42:15"}
{"current_steps": 200, "total_steps": 1266, "loss": 0.6692, "lr": 5e-06, "epoch": 0.47309284447072736, "percentage": 15.8, "elapsed_time": "1:37:04", "remaining_time": "8:37:25"}
{"current_steps": 210, "total_steps": 1266, "loss": 0.6696, "lr": 5e-06, "epoch": 0.4967474866942638, "percentage": 16.59, "elapsed_time": "1:41:55", "remaining_time": "8:32:34"}
{"current_steps": 220, "total_steps": 1266, "loss": 0.6688, "lr": 5e-06, "epoch": 0.5204021289178001, "percentage": 17.38, "elapsed_time": "1:46:47", "remaining_time": "8:27:45"}
{"current_steps": 230, "total_steps": 1266, "loss": 0.6605, "lr": 5e-06, "epoch": 0.5440567711413364, "percentage": 18.17, "elapsed_time": "1:51:39", "remaining_time": "8:22:54"}
{"current_steps": 240, "total_steps": 1266, "loss": 0.6649, "lr": 5e-06, "epoch": 0.5677114133648729, "percentage": 18.96, "elapsed_time": "1:56:30", "remaining_time": "8:18:04"}
{"current_steps": 250, "total_steps": 1266, "loss": 0.6618, "lr": 5e-06, "epoch": 0.5913660555884093, "percentage": 19.75, "elapsed_time": "2:01:21", "remaining_time": "8:13:13"}
{"current_steps": 260, "total_steps": 1266, "loss": 0.6525, "lr": 5e-06, "epoch": 0.6150206978119456, "percentage": 20.54, "elapsed_time": "2:06:12", "remaining_time": "8:08:21"}
{"current_steps": 270, "total_steps": 1266, "loss": 0.664, "lr": 5e-06, "epoch": 0.638675340035482, "percentage": 21.33, "elapsed_time": "2:11:04", "remaining_time": "8:03:30"}
{"current_steps": 280, "total_steps": 1266, "loss": 0.6658, "lr": 5e-06, "epoch": 0.6623299822590183, "percentage": 22.12, "elapsed_time": "2:15:55", "remaining_time": "7:58:39"}
{"current_steps": 290, "total_steps": 1266, "loss": 0.6599, "lr": 5e-06, "epoch": 0.6859846244825547, "percentage": 22.91, "elapsed_time": "2:20:46", "remaining_time": "7:53:47"}
{"current_steps": 300, "total_steps": 1266, "loss": 0.6536, "lr": 5e-06, "epoch": 0.7096392667060911, "percentage": 23.7, "elapsed_time": "2:25:37", "remaining_time": "7:48:56"}
{"current_steps": 310, "total_steps": 1266, "loss": 0.662, "lr": 5e-06, "epoch": 0.7332939089296274, "percentage": 24.49, "elapsed_time": "2:30:29", "remaining_time": "7:44:04"}
{"current_steps": 320, "total_steps": 1266, "loss": 0.656, "lr": 5e-06, "epoch": 0.7569485511531638, "percentage": 25.28, "elapsed_time": "2:35:20", "remaining_time": "7:39:13"}
{"current_steps": 330, "total_steps": 1266, "loss": 0.6541, "lr": 5e-06, "epoch": 0.7806031933767001, "percentage": 26.07, "elapsed_time": "2:40:11", "remaining_time": "7:34:21"}
{"current_steps": 340, "total_steps": 1266, "loss": 0.6539, "lr": 5e-06, "epoch": 0.8042578356002366, "percentage": 26.86, "elapsed_time": "2:45:02", "remaining_time": "7:29:29"}
{"current_steps": 350, "total_steps": 1266, "loss": 0.6602, "lr": 5e-06, "epoch": 0.8279124778237729, "percentage": 27.65, "elapsed_time": "2:49:53", "remaining_time": "7:24:37"}
{"current_steps": 360, "total_steps": 1266, "loss": 0.6537, "lr": 5e-06, "epoch": 0.8515671200473093, "percentage": 28.44, "elapsed_time": "2:54:44", "remaining_time": "7:19:46"}
{"current_steps": 370, "total_steps": 1266, "loss": 0.6571, "lr": 5e-06, "epoch": 0.8752217622708457, "percentage": 29.23, "elapsed_time": "2:59:35", "remaining_time": "7:14:55"}
{"current_steps": 380, "total_steps": 1266, "loss": 0.6478, "lr": 5e-06, "epoch": 0.898876404494382, "percentage": 30.02, "elapsed_time": "3:04:27", "remaining_time": "7:10:03"}
{"current_steps": 390, "total_steps": 1266, "loss": 0.6552, "lr": 5e-06, "epoch": 0.9225310467179184, "percentage": 30.81, "elapsed_time": "3:09:18", "remaining_time": "7:05:12"}
{"current_steps": 400, "total_steps": 1266, "loss": 0.6467, "lr": 5e-06, "epoch": 0.9461856889414547, "percentage": 31.6, "elapsed_time": "3:14:09", "remaining_time": "7:00:20"}
{"current_steps": 410, "total_steps": 1266, "loss": 0.6492, "lr": 5e-06, "epoch": 0.9698403311649911, "percentage": 32.39, "elapsed_time": "3:19:00", "remaining_time": "6:55:29"}
{"current_steps": 420, "total_steps": 1266, "loss": 0.6483, "lr": 5e-06, "epoch": 0.9934949733885275, "percentage": 33.18, "elapsed_time": "3:23:51", "remaining_time": "6:50:38"}
{"current_steps": 422, "total_steps": 1266, "eval_loss": 0.6504195332527161, "epoch": 0.9982259018332348, "percentage": 33.33, "elapsed_time": "3:28:57", "remaining_time": "6:57:54"}
{"current_steps": 430, "total_steps": 1266, "loss": 0.6374, "lr": 5e-06, "epoch": 1.0171496156120639, "percentage": 33.97, "elapsed_time": "3:33:25", "remaining_time": "6:54:55"}
{"current_steps": 440, "total_steps": 1266, "loss": 0.6056, "lr": 5e-06, "epoch": 1.0408042578356003, "percentage": 34.76, "elapsed_time": "3:38:16", "remaining_time": "6:49:46"}
{"current_steps": 450, "total_steps": 1266, "loss": 0.6041, "lr": 5e-06, "epoch": 1.0644589000591367, "percentage": 35.55, "elapsed_time": "3:43:08", "remaining_time": "6:44:37"}
{"current_steps": 460, "total_steps": 1266, "loss": 0.6125, "lr": 5e-06, "epoch": 1.0881135422826729, "percentage": 36.33, "elapsed_time": "3:48:00", "remaining_time": "6:39:30"}
{"current_steps": 470, "total_steps": 1266, "loss": 0.6114, "lr": 5e-06, "epoch": 1.1117681845062093, "percentage": 37.12, "elapsed_time": "3:52:51", "remaining_time": "6:34:23"}
{"current_steps": 480, "total_steps": 1266, "loss": 0.6114, "lr": 5e-06, "epoch": 1.1354228267297457, "percentage": 37.91, "elapsed_time": "3:57:43", "remaining_time": "6:29:16"}
{"current_steps": 490, "total_steps": 1266, "loss": 0.6086, "lr": 5e-06, "epoch": 1.1590774689532821, "percentage": 38.7, "elapsed_time": "4:02:35", "remaining_time": "6:24:11"}
{"current_steps": 500, "total_steps": 1266, "loss": 0.6048, "lr": 5e-06, "epoch": 1.1827321111768185, "percentage": 39.49, "elapsed_time": "4:07:27", "remaining_time": "6:19:05"}
{"current_steps": 510, "total_steps": 1266, "loss": 0.6045, "lr": 5e-06, "epoch": 1.2063867534003547, "percentage": 40.28, "elapsed_time": "4:12:18", "remaining_time": "6:14:01"}
{"current_steps": 520, "total_steps": 1266, "loss": 0.6106, "lr": 5e-06, "epoch": 1.2300413956238911, "percentage": 41.07, "elapsed_time": "4:17:10", "remaining_time": "6:08:56"}
{"current_steps": 530, "total_steps": 1266, "loss": 0.6116, "lr": 5e-06, "epoch": 1.2536960378474276, "percentage": 41.86, "elapsed_time": "4:22:01", "remaining_time": "6:03:52"}
{"current_steps": 540, "total_steps": 1266, "loss": 0.6119, "lr": 5e-06, "epoch": 1.277350680070964, "percentage": 42.65, "elapsed_time": "4:26:53", "remaining_time": "5:58:48"}
{"current_steps": 550, "total_steps": 1266, "loss": 0.6102, "lr": 5e-06, "epoch": 1.3010053222945004, "percentage": 43.44, "elapsed_time": "4:31:44", "remaining_time": "5:53:46"}
{"current_steps": 560, "total_steps": 1266, "loss": 0.6082, "lr": 5e-06, "epoch": 1.3246599645180366, "percentage": 44.23, "elapsed_time": "4:36:36", "remaining_time": "5:48:43"}
{"current_steps": 570, "total_steps": 1266, "loss": 0.6082, "lr": 5e-06, "epoch": 1.348314606741573, "percentage": 45.02, "elapsed_time": "4:41:27", "remaining_time": "5:43:40"}
{"current_steps": 580, "total_steps": 1266, "loss": 0.6118, "lr": 5e-06, "epoch": 1.3719692489651094, "percentage": 45.81, "elapsed_time": "4:46:19", "remaining_time": "5:38:38"}
{"current_steps": 590, "total_steps": 1266, "loss": 0.6123, "lr": 5e-06, "epoch": 1.3956238911886458, "percentage": 46.6, "elapsed_time": "4:51:10", "remaining_time": "5:33:37"}
{"current_steps": 600, "total_steps": 1266, "loss": 0.5995, "lr": 5e-06, "epoch": 1.4192785334121822, "percentage": 47.39, "elapsed_time": "4:56:01", "remaining_time": "5:28:35"}
{"current_steps": 610, "total_steps": 1266, "loss": 0.6012, "lr": 5e-06, "epoch": 1.4429331756357184, "percentage": 48.18, "elapsed_time": "5:00:53", "remaining_time": "5:23:35"}
{"current_steps": 620, "total_steps": 1266, "loss": 0.6039, "lr": 5e-06, "epoch": 1.4665878178592548, "percentage": 48.97, "elapsed_time": "5:05:45", "remaining_time": "5:18:34"}
{"current_steps": 630, "total_steps": 1266, "loss": 0.6145, "lr": 5e-06, "epoch": 1.4902424600827913, "percentage": 49.76, "elapsed_time": "5:10:36", "remaining_time": "5:13:34"}
{"current_steps": 640, "total_steps": 1266, "loss": 0.6128, "lr": 5e-06, "epoch": 1.5138971023063275, "percentage": 50.55, "elapsed_time": "5:15:27", "remaining_time": "5:08:33"}
{"current_steps": 650, "total_steps": 1266, "loss": 0.6037, "lr": 5e-06, "epoch": 1.537551744529864, "percentage": 51.34, "elapsed_time": "5:20:19", "remaining_time": "5:03:34"}
{"current_steps": 660, "total_steps": 1266, "loss": 0.6081, "lr": 5e-06, "epoch": 1.5612063867534003, "percentage": 52.13, "elapsed_time": "5:25:11", "remaining_time": "4:58:34"}
{"current_steps": 670, "total_steps": 1266, "loss": 0.605, "lr": 5e-06, "epoch": 1.5848610289769367, "percentage": 52.92, "elapsed_time": "5:30:02", "remaining_time": "4:53:35"}
{"current_steps": 680, "total_steps": 1266, "loss": 0.609, "lr": 5e-06, "epoch": 1.6085156712004731, "percentage": 53.71, "elapsed_time": "5:34:54", "remaining_time": "4:48:36"}
{"current_steps": 690, "total_steps": 1266, "loss": 0.6023, "lr": 5e-06, "epoch": 1.6321703134240093, "percentage": 54.5, "elapsed_time": "5:39:46", "remaining_time": "4:43:38"}
{"current_steps": 700, "total_steps": 1266, "loss": 0.6098, "lr": 5e-06, "epoch": 1.655824955647546, "percentage": 55.29, "elapsed_time": "5:44:37", "remaining_time": "4:38:39"}
{"current_steps": 710, "total_steps": 1266, "loss": 0.6083, "lr": 5e-06, "epoch": 1.6794795978710821, "percentage": 56.08, "elapsed_time": "5:49:29", "remaining_time": "4:33:40"}
{"current_steps": 720, "total_steps": 1266, "loss": 0.6145, "lr": 5e-06, "epoch": 1.7031342400946186, "percentage": 56.87, "elapsed_time": "5:54:20", "remaining_time": "4:28:42"}
{"current_steps": 730, "total_steps": 1266, "loss": 0.6102, "lr": 5e-06, "epoch": 1.726788882318155, "percentage": 57.66, "elapsed_time": "5:59:11", "remaining_time": "4:23:44"}
{"current_steps": 740, "total_steps": 1266, "loss": 0.6047, "lr": 5e-06, "epoch": 1.7504435245416912, "percentage": 58.45, "elapsed_time": "6:04:03", "remaining_time": "4:18:46"}
{"current_steps": 750, "total_steps": 1266, "loss": 0.6104, "lr": 5e-06, "epoch": 1.7740981667652278, "percentage": 59.24, "elapsed_time": "6:08:54", "remaining_time": "4:13:48"}
{"current_steps": 760, "total_steps": 1266, "loss": 0.6152, "lr": 5e-06, "epoch": 1.797752808988764, "percentage": 60.03, "elapsed_time": "6:13:45", "remaining_time": "4:08:50"}
{"current_steps": 770, "total_steps": 1266, "loss": 0.6159, "lr": 5e-06, "epoch": 1.8214074512123004, "percentage": 60.82, "elapsed_time": "6:18:36", "remaining_time": "4:03:53"}
{"current_steps": 780, "total_steps": 1266, "loss": 0.6077, "lr": 5e-06, "epoch": 1.8450620934358368, "percentage": 61.61, "elapsed_time": "6:23:27", "remaining_time": "3:58:55"}
{"current_steps": 790, "total_steps": 1266, "loss": 0.6064, "lr": 5e-06, "epoch": 1.868716735659373, "percentage": 62.4, "elapsed_time": "6:28:19", "remaining_time": "3:53:58"}
{"current_steps": 800, "total_steps": 1266, "loss": 0.613, "lr": 5e-06, "epoch": 1.8923713778829097, "percentage": 63.19, "elapsed_time": "6:33:10", "remaining_time": "3:49:01"}
{"current_steps": 810, "total_steps": 1266, "loss": 0.6126, "lr": 5e-06, "epoch": 1.9160260201064458, "percentage": 63.98, "elapsed_time": "6:38:01", "remaining_time": "3:44:04"}
{"current_steps": 820, "total_steps": 1266, "loss": 0.5994, "lr": 5e-06, "epoch": 1.9396806623299823, "percentage": 64.77, "elapsed_time": "6:42:52", "remaining_time": "3:39:07"}
{"current_steps": 830, "total_steps": 1266, "loss": 0.612, "lr": 5e-06, "epoch": 1.9633353045535187, "percentage": 65.56, "elapsed_time": "6:47:44", "remaining_time": "3:34:10"}
{"current_steps": 840, "total_steps": 1266, "loss": 0.5968, "lr": 5e-06, "epoch": 1.9869899467770549, "percentage": 66.35, "elapsed_time": "6:52:35", "remaining_time": "3:29:14"}
{"current_steps": 845, "total_steps": 1266, "eval_loss": 0.6400034427642822, "epoch": 1.9988172678888232, "percentage": 66.75, "elapsed_time": "6:58:57", "remaining_time": "3:28:44"}
{"current_steps": 850, "total_steps": 1266, "loss": 0.5995, "lr": 5e-06, "epoch": 2.0106445890005915, "percentage": 67.14, "elapsed_time": "7:02:09", "remaining_time": "3:26:36"}
{"current_steps": 860, "total_steps": 1266, "loss": 0.5669, "lr": 5e-06, "epoch": 2.0342992312241277, "percentage": 67.93, "elapsed_time": "7:07:00", "remaining_time": "3:21:35"}
{"current_steps": 870, "total_steps": 1266, "loss": 0.5668, "lr": 5e-06, "epoch": 2.057953873447664, "percentage": 68.72, "elapsed_time": "7:11:51", "remaining_time": "3:16:34"}
{"current_steps": 880, "total_steps": 1266, "loss": 0.559, "lr": 5e-06, "epoch": 2.0816085156712005, "percentage": 69.51, "elapsed_time": "7:16:43", "remaining_time": "3:11:33"}
{"current_steps": 890, "total_steps": 1266, "loss": 0.5615, "lr": 5e-06, "epoch": 2.1052631578947367, "percentage": 70.3, "elapsed_time": "7:21:34", "remaining_time": "3:06:33"}
{"current_steps": 900, "total_steps": 1266, "loss": 0.567, "lr": 5e-06, "epoch": 2.1289178001182734, "percentage": 71.09, "elapsed_time": "7:26:25", "remaining_time": "3:01:32"}
{"current_steps": 910, "total_steps": 1266, "loss": 0.5616, "lr": 5e-06, "epoch": 2.1525724423418096, "percentage": 71.88, "elapsed_time": "7:31:16", "remaining_time": "2:56:32"}
{"current_steps": 920, "total_steps": 1266, "loss": 0.5634, "lr": 5e-06, "epoch": 2.1762270845653457, "percentage": 72.67, "elapsed_time": "7:36:07", "remaining_time": "2:51:32"}
{"current_steps": 930, "total_steps": 1266, "loss": 0.5627, "lr": 5e-06, "epoch": 2.1998817267888824, "percentage": 73.46, "elapsed_time": "7:40:59", "remaining_time": "2:46:32"}
{"current_steps": 940, "total_steps": 1266, "loss": 0.5643, "lr": 5e-06, "epoch": 2.2235363690124186, "percentage": 74.25, "elapsed_time": "7:45:50", "remaining_time": "2:41:33"}
{"current_steps": 950, "total_steps": 1266, "loss": 0.5702, "lr": 5e-06, "epoch": 2.247191011235955, "percentage": 75.04, "elapsed_time": "7:50:41", "remaining_time": "2:36:34"}
{"current_steps": 960, "total_steps": 1266, "loss": 0.564, "lr": 5e-06, "epoch": 2.2708456534594914, "percentage": 75.83, "elapsed_time": "7:55:33", "remaining_time": "2:31:35"}
{"current_steps": 970, "total_steps": 1266, "loss": 0.5657, "lr": 5e-06, "epoch": 2.2945002956830276, "percentage": 76.62, "elapsed_time": "8:00:24", "remaining_time": "2:26:36"}
{"current_steps": 980, "total_steps": 1266, "loss": 0.5696, "lr": 5e-06, "epoch": 2.3181549379065642, "percentage": 77.41, "elapsed_time": "8:05:16", "remaining_time": "2:21:37"}
{"current_steps": 990, "total_steps": 1266, "loss": 0.5673, "lr": 5e-06, "epoch": 2.3418095801301004, "percentage": 78.2, "elapsed_time": "8:10:07", "remaining_time": "2:16:38"}
{"current_steps": 1000, "total_steps": 1266, "loss": 0.5674, "lr": 5e-06, "epoch": 2.365464222353637, "percentage": 78.99, "elapsed_time": "8:14:59", "remaining_time": "2:11:40"}
{"current_steps": 1010, "total_steps": 1266, "loss": 0.5656, "lr": 5e-06, "epoch": 2.3891188645771733, "percentage": 79.78, "elapsed_time": "8:19:51", "remaining_time": "2:06:41"}
{"current_steps": 1020, "total_steps": 1266, "loss": 0.5632, "lr": 5e-06, "epoch": 2.4127735068007095, "percentage": 80.57, "elapsed_time": "8:24:43", "remaining_time": "2:01:43"}
{"current_steps": 1030, "total_steps": 1266, "loss": 0.5662, "lr": 5e-06, "epoch": 2.436428149024246, "percentage": 81.36, "elapsed_time": "8:29:34", "remaining_time": "1:56:45"}
{"current_steps": 1040, "total_steps": 1266, "loss": 0.5669, "lr": 5e-06, "epoch": 2.4600827912477823, "percentage": 82.15, "elapsed_time": "8:34:26", "remaining_time": "1:51:47"}
{"current_steps": 1050, "total_steps": 1266, "loss": 0.5694, "lr": 5e-06, "epoch": 2.483737433471319, "percentage": 82.94, "elapsed_time": "8:39:17", "remaining_time": "1:46:49"}
{"current_steps": 1060, "total_steps": 1266, "loss": 0.5686, "lr": 5e-06, "epoch": 2.507392075694855, "percentage": 83.73, "elapsed_time": "8:44:08", "remaining_time": "1:41:51"}
{"current_steps": 1070, "total_steps": 1266, "loss": 0.5709, "lr": 5e-06, "epoch": 2.5310467179183913, "percentage": 84.52, "elapsed_time": "8:49:00", "remaining_time": "1:36:54"}
{"current_steps": 1080, "total_steps": 1266, "loss": 0.5718, "lr": 5e-06, "epoch": 2.554701360141928, "percentage": 85.31, "elapsed_time": "8:53:52", "remaining_time": "1:31:56"}
{"current_steps": 1090, "total_steps": 1266, "loss": 0.5661, "lr": 5e-06, "epoch": 2.578356002365464, "percentage": 86.1, "elapsed_time": "8:58:43", "remaining_time": "1:26:59"}
{"current_steps": 1100, "total_steps": 1266, "loss": 0.5681, "lr": 5e-06, "epoch": 2.6020106445890008, "percentage": 86.89, "elapsed_time": "9:03:35", "remaining_time": "1:22:01"}
{"current_steps": 1110, "total_steps": 1266, "loss": 0.566, "lr": 5e-06, "epoch": 2.625665286812537, "percentage": 87.68, "elapsed_time": "9:08:26", "remaining_time": "1:17:04"}
{"current_steps": 1120, "total_steps": 1266, "loss": 0.5773, "lr": 5e-06, "epoch": 2.649319929036073, "percentage": 88.47, "elapsed_time": "9:13:17", "remaining_time": "1:12:07"}
{"current_steps": 1130, "total_steps": 1266, "loss": 0.5646, "lr": 5e-06, "epoch": 2.67297457125961, "percentage": 89.26, "elapsed_time": "9:18:09", "remaining_time": "1:07:10"}
{"current_steps": 1140, "total_steps": 1266, "loss": 0.5653, "lr": 5e-06, "epoch": 2.696629213483146, "percentage": 90.05, "elapsed_time": "9:23:00", "remaining_time": "1:02:13"}
{"current_steps": 1150, "total_steps": 1266, "loss": 0.5689, "lr": 5e-06, "epoch": 2.7202838557066826, "percentage": 90.84, "elapsed_time": "9:27:52", "remaining_time": "0:57:16"}
{"current_steps": 1160, "total_steps": 1266, "loss": 0.5751, "lr": 5e-06, "epoch": 2.743938497930219, "percentage": 91.63, "elapsed_time": "9:32:43", "remaining_time": "0:52:20"}
{"current_steps": 1170, "total_steps": 1266, "loss": 0.5659, "lr": 5e-06, "epoch": 2.767593140153755, "percentage": 92.42, "elapsed_time": "9:37:35", "remaining_time": "0:47:23"}
{"current_steps": 1180, "total_steps": 1266, "loss": 0.5696, "lr": 5e-06, "epoch": 2.7912477823772917, "percentage": 93.21, "elapsed_time": "9:42:27", "remaining_time": "0:42:26"}
{"current_steps": 1190, "total_steps": 1266, "loss": 0.5692, "lr": 5e-06, "epoch": 2.814902424600828, "percentage": 94.0, "elapsed_time": "9:47:18", "remaining_time": "0:37:30"}
{"current_steps": 1200, "total_steps": 1266, "loss": 0.5676, "lr": 5e-06, "epoch": 2.8385570668243645, "percentage": 94.79, "elapsed_time": "9:52:10", "remaining_time": "0:32:34"}
{"current_steps": 1210, "total_steps": 1266, "loss": 0.569, "lr": 5e-06, "epoch": 2.8622117090479007, "percentage": 95.58, "elapsed_time": "9:57:01", "remaining_time": "0:27:37"}
{"current_steps": 1220, "total_steps": 1266, "loss": 0.563, "lr": 5e-06, "epoch": 2.885866351271437, "percentage": 96.37, "elapsed_time": "10:01:53", "remaining_time": "0:22:41"}
{"current_steps": 1230, "total_steps": 1266, "loss": 0.5695, "lr": 5e-06, "epoch": 2.9095209934949735, "percentage": 97.16, "elapsed_time": "10:06:45", "remaining_time": "0:17:45"}
{"current_steps": 1240, "total_steps": 1266, "loss": 0.5706, "lr": 5e-06, "epoch": 2.9331756357185097, "percentage": 97.95, "elapsed_time": "10:11:36", "remaining_time": "0:12:49"}
{"current_steps": 1250, "total_steps": 1266, "loss": 0.5786, "lr": 5e-06, "epoch": 2.9568302779420463, "percentage": 98.74, "elapsed_time": "10:16:28", "remaining_time": "0:07:53"}
{"current_steps": 1260, "total_steps": 1266, "loss": 0.572, "lr": 5e-06, "epoch": 2.9804849201655825, "percentage": 99.53, "elapsed_time": "10:21:19", "remaining_time": "0:02:57"}
{"current_steps": 1266, "total_steps": 1266, "eval_loss": 0.6413525938987732, "epoch": 2.9946777054997042, "percentage": 100.0, "elapsed_time": "10:29:01", "remaining_time": "0:00:00"}
{"current_steps": 1266, "total_steps": 1266, "epoch": 2.9946777054997042, "percentage": 100.0, "elapsed_time": "10:30:10", "remaining_time": "0:00:00"}