oh_v1.3_alpaca_x4 / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
cd73049 verified
{"current_steps": 10, "total_steps": 861, "loss": 1.0615, "lr": 5e-06, "epoch": 0.03475238922675934, "percentage": 1.16, "elapsed_time": "0:09:38", "remaining_time": "13:39:52"}
{"current_steps": 20, "total_steps": 861, "loss": 0.9179, "lr": 5e-06, "epoch": 0.06950477845351868, "percentage": 2.32, "elapsed_time": "0:19:12", "remaining_time": "13:27:39"}
{"current_steps": 30, "total_steps": 861, "loss": 0.8716, "lr": 5e-06, "epoch": 0.10425716768027801, "percentage": 3.48, "elapsed_time": "0:28:46", "remaining_time": "13:17:14"}
{"current_steps": 40, "total_steps": 861, "loss": 0.8538, "lr": 5e-06, "epoch": 0.13900955690703737, "percentage": 4.65, "elapsed_time": "0:38:20", "remaining_time": "13:07:07"}
{"current_steps": 50, "total_steps": 861, "loss": 0.8315, "lr": 5e-06, "epoch": 0.1737619461337967, "percentage": 5.81, "elapsed_time": "0:47:56", "remaining_time": "12:57:29"}
{"current_steps": 60, "total_steps": 861, "loss": 0.8137, "lr": 5e-06, "epoch": 0.20851433536055602, "percentage": 6.97, "elapsed_time": "0:57:29", "remaining_time": "12:47:30"}
{"current_steps": 70, "total_steps": 861, "loss": 0.8079, "lr": 5e-06, "epoch": 0.24326672458731538, "percentage": 8.13, "elapsed_time": "1:07:03", "remaining_time": "12:37:40"}
{"current_steps": 80, "total_steps": 861, "loss": 0.794, "lr": 5e-06, "epoch": 0.27801911381407474, "percentage": 9.29, "elapsed_time": "1:16:37", "remaining_time": "12:28:01"}
{"current_steps": 90, "total_steps": 861, "loss": 0.79, "lr": 5e-06, "epoch": 0.31277150304083406, "percentage": 10.45, "elapsed_time": "1:26:12", "remaining_time": "12:18:28"}
{"current_steps": 100, "total_steps": 861, "loss": 0.7808, "lr": 5e-06, "epoch": 0.3475238922675934, "percentage": 11.61, "elapsed_time": "1:35:47", "remaining_time": "12:08:58"}
{"current_steps": 110, "total_steps": 861, "loss": 0.7743, "lr": 5e-06, "epoch": 0.3822762814943527, "percentage": 12.78, "elapsed_time": "1:45:22", "remaining_time": "11:59:26"}
{"current_steps": 120, "total_steps": 861, "loss": 0.7727, "lr": 5e-06, "epoch": 0.41702867072111205, "percentage": 13.94, "elapsed_time": "1:54:57", "remaining_time": "11:49:54"}
{"current_steps": 130, "total_steps": 861, "loss": 0.7708, "lr": 5e-06, "epoch": 0.45178105994787143, "percentage": 15.1, "elapsed_time": "2:04:32", "remaining_time": "11:40:20"}
{"current_steps": 140, "total_steps": 861, "loss": 0.7663, "lr": 5e-06, "epoch": 0.48653344917463076, "percentage": 16.26, "elapsed_time": "2:14:06", "remaining_time": "11:30:41"}
{"current_steps": 150, "total_steps": 861, "loss": 0.7666, "lr": 5e-06, "epoch": 0.5212858384013901, "percentage": 17.42, "elapsed_time": "2:23:42", "remaining_time": "11:21:10"}
{"current_steps": 160, "total_steps": 861, "loss": 0.7677, "lr": 5e-06, "epoch": 0.5560382276281495, "percentage": 18.58, "elapsed_time": "2:33:17", "remaining_time": "11:11:36"}
{"current_steps": 170, "total_steps": 861, "loss": 0.7586, "lr": 5e-06, "epoch": 0.5907906168549087, "percentage": 19.74, "elapsed_time": "2:42:52", "remaining_time": "11:02:03"}
{"current_steps": 180, "total_steps": 861, "loss": 0.7581, "lr": 5e-06, "epoch": 0.6255430060816681, "percentage": 20.91, "elapsed_time": "2:52:26", "remaining_time": "10:52:25"}
{"current_steps": 190, "total_steps": 861, "loss": 0.7578, "lr": 5e-06, "epoch": 0.6602953953084274, "percentage": 22.07, "elapsed_time": "3:02:01", "remaining_time": "10:42:51"}
{"current_steps": 200, "total_steps": 861, "loss": 0.755, "lr": 5e-06, "epoch": 0.6950477845351868, "percentage": 23.23, "elapsed_time": "3:11:36", "remaining_time": "10:33:15"}
{"current_steps": 210, "total_steps": 861, "loss": 0.756, "lr": 5e-06, "epoch": 0.7298001737619462, "percentage": 24.39, "elapsed_time": "3:21:11", "remaining_time": "10:23:40"}
{"current_steps": 220, "total_steps": 861, "loss": 0.7547, "lr": 5e-06, "epoch": 0.7645525629887054, "percentage": 25.55, "elapsed_time": "3:30:44", "remaining_time": "10:14:02"}
{"current_steps": 230, "total_steps": 861, "loss": 0.7511, "lr": 5e-06, "epoch": 0.7993049522154648, "percentage": 26.71, "elapsed_time": "3:40:18", "remaining_time": "10:04:24"}
{"current_steps": 240, "total_steps": 861, "loss": 0.7536, "lr": 5e-06, "epoch": 0.8340573414422241, "percentage": 27.87, "elapsed_time": "3:49:52", "remaining_time": "9:54:49"}
{"current_steps": 250, "total_steps": 861, "loss": 0.7495, "lr": 5e-06, "epoch": 0.8688097306689835, "percentage": 29.04, "elapsed_time": "3:59:27", "remaining_time": "9:45:14"}
{"current_steps": 260, "total_steps": 861, "loss": 0.7473, "lr": 5e-06, "epoch": 0.9035621198957429, "percentage": 30.2, "elapsed_time": "4:09:02", "remaining_time": "9:35:39"}
{"current_steps": 270, "total_steps": 861, "loss": 0.7475, "lr": 5e-06, "epoch": 0.9383145091225021, "percentage": 31.36, "elapsed_time": "4:18:37", "remaining_time": "9:26:05"}
{"current_steps": 280, "total_steps": 861, "loss": 0.7466, "lr": 5e-06, "epoch": 0.9730668983492615, "percentage": 32.52, "elapsed_time": "4:28:12", "remaining_time": "9:16:31"}
{"current_steps": 287, "total_steps": 861, "eval_loss": 0.7464137077331543, "epoch": 0.9973935708079931, "percentage": 33.33, "elapsed_time": "4:40:36", "remaining_time": "9:21:13"}
{"current_steps": 290, "total_steps": 861, "loss": 0.7656, "lr": 5e-06, "epoch": 1.0082536924413554, "percentage": 33.68, "elapsed_time": "4:44:06", "remaining_time": "9:19:23"}
{"current_steps": 300, "total_steps": 861, "loss": 0.6927, "lr": 5e-06, "epoch": 1.0430060816681146, "percentage": 34.84, "elapsed_time": "4:53:42", "remaining_time": "9:09:14"}
{"current_steps": 310, "total_steps": 861, "loss": 0.6937, "lr": 5e-06, "epoch": 1.077758470894874, "percentage": 36.0, "elapsed_time": "5:03:19", "remaining_time": "8:59:07"}
{"current_steps": 320, "total_steps": 861, "loss": 0.6956, "lr": 5e-06, "epoch": 1.1125108601216334, "percentage": 37.17, "elapsed_time": "5:12:55", "remaining_time": "8:49:02"}
{"current_steps": 330, "total_steps": 861, "loss": 0.6945, "lr": 5e-06, "epoch": 1.1472632493483927, "percentage": 38.33, "elapsed_time": "5:22:31", "remaining_time": "8:38:59"}
{"current_steps": 340, "total_steps": 861, "loss": 0.6928, "lr": 5e-06, "epoch": 1.1820156385751521, "percentage": 39.49, "elapsed_time": "5:32:08", "remaining_time": "8:28:57"}
{"current_steps": 350, "total_steps": 861, "loss": 0.6975, "lr": 5e-06, "epoch": 1.2167680278019113, "percentage": 40.65, "elapsed_time": "5:41:44", "remaining_time": "8:18:56"}
{"current_steps": 360, "total_steps": 861, "loss": 0.693, "lr": 5e-06, "epoch": 1.2515204170286707, "percentage": 41.81, "elapsed_time": "5:51:20", "remaining_time": "8:08:56"}
{"current_steps": 370, "total_steps": 861, "loss": 0.6919, "lr": 5e-06, "epoch": 1.28627280625543, "percentage": 42.97, "elapsed_time": "6:00:56", "remaining_time": "7:58:58"}
{"current_steps": 380, "total_steps": 861, "loss": 0.7012, "lr": 5e-06, "epoch": 1.3210251954821894, "percentage": 44.13, "elapsed_time": "6:10:33", "remaining_time": "7:49:02"}
{"current_steps": 390, "total_steps": 861, "loss": 0.6976, "lr": 5e-06, "epoch": 1.3557775847089486, "percentage": 45.3, "elapsed_time": "6:20:08", "remaining_time": "7:39:05"}
{"current_steps": 400, "total_steps": 861, "loss": 0.6923, "lr": 5e-06, "epoch": 1.390529973935708, "percentage": 46.46, "elapsed_time": "6:29:44", "remaining_time": "7:29:10"}
{"current_steps": 410, "total_steps": 861, "loss": 0.6957, "lr": 5e-06, "epoch": 1.4252823631624674, "percentage": 47.62, "elapsed_time": "6:39:19", "remaining_time": "7:19:15"}
{"current_steps": 420, "total_steps": 861, "loss": 0.6945, "lr": 5e-06, "epoch": 1.4600347523892268, "percentage": 48.78, "elapsed_time": "6:48:54", "remaining_time": "7:09:20"}
{"current_steps": 430, "total_steps": 861, "loss": 0.6929, "lr": 5e-06, "epoch": 1.4947871416159861, "percentage": 49.94, "elapsed_time": "6:58:28", "remaining_time": "6:59:27"}
{"current_steps": 440, "total_steps": 861, "loss": 0.6926, "lr": 5e-06, "epoch": 1.5295395308427455, "percentage": 51.1, "elapsed_time": "7:08:04", "remaining_time": "6:49:35"}
{"current_steps": 450, "total_steps": 861, "loss": 0.6922, "lr": 5e-06, "epoch": 1.564291920069505, "percentage": 52.26, "elapsed_time": "7:17:39", "remaining_time": "6:39:43"}
{"current_steps": 460, "total_steps": 861, "loss": 0.6902, "lr": 5e-06, "epoch": 1.599044309296264, "percentage": 53.43, "elapsed_time": "7:27:15", "remaining_time": "6:29:53"}
{"current_steps": 470, "total_steps": 861, "loss": 0.6925, "lr": 5e-06, "epoch": 1.6337966985230234, "percentage": 54.59, "elapsed_time": "7:36:52", "remaining_time": "6:20:04"}
{"current_steps": 480, "total_steps": 861, "loss": 0.6857, "lr": 5e-06, "epoch": 1.6685490877497828, "percentage": 55.75, "elapsed_time": "7:46:28", "remaining_time": "6:10:15"}
{"current_steps": 490, "total_steps": 861, "loss": 0.689, "lr": 5e-06, "epoch": 1.703301476976542, "percentage": 56.91, "elapsed_time": "7:56:03", "remaining_time": "6:00:26"}
{"current_steps": 500, "total_steps": 861, "loss": 0.6939, "lr": 5e-06, "epoch": 1.7380538662033014, "percentage": 58.07, "elapsed_time": "8:05:39", "remaining_time": "5:50:38"}
{"current_steps": 510, "total_steps": 861, "loss": 0.6916, "lr": 5e-06, "epoch": 1.7728062554300608, "percentage": 59.23, "elapsed_time": "8:15:16", "remaining_time": "5:40:51"}
{"current_steps": 520, "total_steps": 861, "loss": 0.6913, "lr": 5e-06, "epoch": 1.8075586446568201, "percentage": 60.39, "elapsed_time": "8:24:51", "remaining_time": "5:31:03"}
{"current_steps": 530, "total_steps": 861, "loss": 0.687, "lr": 5e-06, "epoch": 1.8423110338835795, "percentage": 61.56, "elapsed_time": "8:34:27", "remaining_time": "5:21:17"}
{"current_steps": 540, "total_steps": 861, "loss": 0.6871, "lr": 5e-06, "epoch": 1.877063423110339, "percentage": 62.72, "elapsed_time": "8:44:03", "remaining_time": "5:11:31"}
{"current_steps": 550, "total_steps": 861, "loss": 0.6885, "lr": 5e-06, "epoch": 1.9118158123370983, "percentage": 63.88, "elapsed_time": "8:53:38", "remaining_time": "5:01:45"}
{"current_steps": 560, "total_steps": 861, "loss": 0.6885, "lr": 5e-06, "epoch": 1.9465682015638577, "percentage": 65.04, "elapsed_time": "9:03:13", "remaining_time": "4:51:58"}
{"current_steps": 570, "total_steps": 861, "loss": 0.693, "lr": 5e-06, "epoch": 1.9813205907906168, "percentage": 66.2, "elapsed_time": "9:12:49", "remaining_time": "4:42:13"}
{"current_steps": 575, "total_steps": 861, "eval_loss": 0.7325075268745422, "epoch": 1.9986967854039965, "percentage": 66.78, "elapsed_time": "9:22:53", "remaining_time": "4:39:58"}
{"current_steps": 580, "total_steps": 861, "loss": 0.694, "lr": 5e-06, "epoch": 2.016507384882711, "percentage": 67.36, "elapsed_time": "9:28:40", "remaining_time": "4:35:30"}
{"current_steps": 590, "total_steps": 861, "loss": 0.6416, "lr": 5e-06, "epoch": 2.05125977410947, "percentage": 68.52, "elapsed_time": "9:38:16", "remaining_time": "4:25:37"}
{"current_steps": 600, "total_steps": 861, "loss": 0.6347, "lr": 5e-06, "epoch": 2.086012163336229, "percentage": 69.69, "elapsed_time": "9:47:52", "remaining_time": "4:15:43"}
{"current_steps": 610, "total_steps": 861, "loss": 0.6382, "lr": 5e-06, "epoch": 2.1207645525629886, "percentage": 70.85, "elapsed_time": "9:57:28", "remaining_time": "4:05:50"}
{"current_steps": 620, "total_steps": 861, "loss": 0.6316, "lr": 5e-06, "epoch": 2.155516941789748, "percentage": 72.01, "elapsed_time": "10:07:04", "remaining_time": "3:55:58"}
{"current_steps": 630, "total_steps": 861, "loss": 0.64, "lr": 5e-06, "epoch": 2.1902693310165073, "percentage": 73.17, "elapsed_time": "10:16:38", "remaining_time": "3:46:06"}
{"current_steps": 640, "total_steps": 861, "loss": 0.6352, "lr": 5e-06, "epoch": 2.2250217202432667, "percentage": 74.33, "elapsed_time": "10:26:14", "remaining_time": "3:36:15"}
{"current_steps": 650, "total_steps": 861, "loss": 0.6415, "lr": 5e-06, "epoch": 2.259774109470026, "percentage": 75.49, "elapsed_time": "10:35:50", "remaining_time": "3:26:24"}
{"current_steps": 660, "total_steps": 861, "loss": 0.6409, "lr": 5e-06, "epoch": 2.2945264986967855, "percentage": 76.66, "elapsed_time": "10:45:26", "remaining_time": "3:16:34"}
{"current_steps": 670, "total_steps": 861, "loss": 0.641, "lr": 5e-06, "epoch": 2.329278887923545, "percentage": 77.82, "elapsed_time": "10:55:02", "remaining_time": "3:06:44"}
{"current_steps": 680, "total_steps": 861, "loss": 0.6343, "lr": 5e-06, "epoch": 2.3640312771503043, "percentage": 78.98, "elapsed_time": "11:04:38", "remaining_time": "2:56:54"}
{"current_steps": 690, "total_steps": 861, "loss": 0.6424, "lr": 5e-06, "epoch": 2.3987836663770636, "percentage": 80.14, "elapsed_time": "11:14:14", "remaining_time": "2:47:05"}
{"current_steps": 700, "total_steps": 861, "loss": 0.6402, "lr": 5e-06, "epoch": 2.4335360556038226, "percentage": 81.3, "elapsed_time": "11:23:50", "remaining_time": "2:37:17"}
{"current_steps": 710, "total_steps": 861, "loss": 0.6405, "lr": 5e-06, "epoch": 2.468288444830582, "percentage": 82.46, "elapsed_time": "11:33:27", "remaining_time": "2:27:28"}
{"current_steps": 720, "total_steps": 861, "loss": 0.639, "lr": 5e-06, "epoch": 2.5030408340573413, "percentage": 83.62, "elapsed_time": "11:43:03", "remaining_time": "2:17:40"}
{"current_steps": 730, "total_steps": 861, "loss": 0.6451, "lr": 5e-06, "epoch": 2.5377932232841007, "percentage": 84.79, "elapsed_time": "11:52:40", "remaining_time": "2:07:53"}
{"current_steps": 740, "total_steps": 861, "loss": 0.6451, "lr": 5e-06, "epoch": 2.57254561251086, "percentage": 85.95, "elapsed_time": "12:02:16", "remaining_time": "1:58:06"}
{"current_steps": 750, "total_steps": 861, "loss": 0.6452, "lr": 5e-06, "epoch": 2.6072980017376195, "percentage": 87.11, "elapsed_time": "12:11:51", "remaining_time": "1:48:18"}
{"current_steps": 760, "total_steps": 861, "loss": 0.6435, "lr": 5e-06, "epoch": 2.642050390964379, "percentage": 88.27, "elapsed_time": "12:21:27", "remaining_time": "1:38:32"}
{"current_steps": 770, "total_steps": 861, "loss": 0.6393, "lr": 5e-06, "epoch": 2.6768027801911383, "percentage": 89.43, "elapsed_time": "12:31:03", "remaining_time": "1:28:45"}
{"current_steps": 780, "total_steps": 861, "loss": 0.6416, "lr": 5e-06, "epoch": 2.711555169417897, "percentage": 90.59, "elapsed_time": "12:40:39", "remaining_time": "1:18:59"}
{"current_steps": 790, "total_steps": 861, "loss": 0.6413, "lr": 5e-06, "epoch": 2.7463075586446566, "percentage": 91.75, "elapsed_time": "12:50:15", "remaining_time": "1:09:13"}
{"current_steps": 800, "total_steps": 861, "loss": 0.6441, "lr": 5e-06, "epoch": 2.781059947871416, "percentage": 92.92, "elapsed_time": "12:59:51", "remaining_time": "0:59:27"}
{"current_steps": 810, "total_steps": 861, "loss": 0.6432, "lr": 5e-06, "epoch": 2.8158123370981754, "percentage": 94.08, "elapsed_time": "13:09:28", "remaining_time": "0:49:42"}
{"current_steps": 820, "total_steps": 861, "loss": 0.644, "lr": 5e-06, "epoch": 2.8505647263249347, "percentage": 95.24, "elapsed_time": "13:19:04", "remaining_time": "0:39:57"}
{"current_steps": 830, "total_steps": 861, "loss": 0.6399, "lr": 5e-06, "epoch": 2.885317115551694, "percentage": 96.4, "elapsed_time": "13:28:41", "remaining_time": "0:30:12"}
{"current_steps": 840, "total_steps": 861, "loss": 0.6454, "lr": 5e-06, "epoch": 2.9200695047784535, "percentage": 97.56, "elapsed_time": "13:38:16", "remaining_time": "0:20:27"}
{"current_steps": 850, "total_steps": 861, "loss": 0.6416, "lr": 5e-06, "epoch": 2.954821894005213, "percentage": 98.72, "elapsed_time": "13:47:52", "remaining_time": "0:10:42"}
{"current_steps": 860, "total_steps": 861, "loss": 0.644, "lr": 5e-06, "epoch": 2.9895742832319723, "percentage": 99.88, "elapsed_time": "13:57:29", "remaining_time": "0:00:58"}
{"current_steps": 861, "total_steps": 861, "eval_loss": 0.7338809370994568, "epoch": 2.993049522154648, "percentage": 100.0, "elapsed_time": "14:04:47", "remaining_time": "0:00:00"}
{"current_steps": 861, "total_steps": 861, "epoch": 2.993049522154648, "percentage": 100.0, "elapsed_time": "14:06:14", "remaining_time": "0:00:00"}