oh_v1.3_slim_orca_x.5 / trainer_log.jsonl
gsmyrnis's picture
Training in progress, epoch 3
915eca8 verified
{"current_steps": 10, "total_steps": 555, "loss": 1.0037, "learning_rate": 5e-06, "epoch": 0.05405405405405406, "percentage": 1.8, "elapsed_time": "0:00:59", "remaining_time": "0:54:22"}
{"current_steps": 20, "total_steps": 555, "loss": 0.901, "learning_rate": 5e-06, "epoch": 0.10810810810810811, "percentage": 3.6, "elapsed_time": "0:01:58", "remaining_time": "0:52:36"}
{"current_steps": 30, "total_steps": 555, "loss": 0.8638, "learning_rate": 5e-06, "epoch": 0.16216216216216217, "percentage": 5.41, "elapsed_time": "0:02:56", "remaining_time": "0:51:35"}
{"current_steps": 40, "total_steps": 555, "loss": 0.8438, "learning_rate": 5e-06, "epoch": 0.21621621621621623, "percentage": 7.21, "elapsed_time": "0:03:55", "remaining_time": "0:50:25"}
{"current_steps": 50, "total_steps": 555, "loss": 0.8171, "learning_rate": 5e-06, "epoch": 0.2702702702702703, "percentage": 9.01, "elapsed_time": "0:04:53", "remaining_time": "0:49:20"}
{"current_steps": 60, "total_steps": 555, "loss": 0.8064, "learning_rate": 5e-06, "epoch": 0.32432432432432434, "percentage": 10.81, "elapsed_time": "0:05:51", "remaining_time": "0:48:19"}
{"current_steps": 70, "total_steps": 555, "loss": 0.7927, "learning_rate": 5e-06, "epoch": 0.3783783783783784, "percentage": 12.61, "elapsed_time": "0:06:49", "remaining_time": "0:47:19"}
{"current_steps": 80, "total_steps": 555, "loss": 0.7747, "learning_rate": 5e-06, "epoch": 0.43243243243243246, "percentage": 14.41, "elapsed_time": "0:07:48", "remaining_time": "0:46:19"}
{"current_steps": 90, "total_steps": 555, "loss": 0.7703, "learning_rate": 5e-06, "epoch": 0.4864864864864865, "percentage": 16.22, "elapsed_time": "0:08:46", "remaining_time": "0:45:22"}
{"current_steps": 100, "total_steps": 555, "loss": 0.7602, "learning_rate": 5e-06, "epoch": 0.5405405405405406, "percentage": 18.02, "elapsed_time": "0:09:47", "remaining_time": "0:44:32"}
{"current_steps": 110, "total_steps": 555, "loss": 0.7629, "learning_rate": 5e-06, "epoch": 0.5945945945945946, "percentage": 19.82, "elapsed_time": "0:10:46", "remaining_time": "0:43:35"}
{"current_steps": 120, "total_steps": 555, "loss": 0.7571, "learning_rate": 5e-06, "epoch": 0.6486486486486487, "percentage": 21.62, "elapsed_time": "0:11:44", "remaining_time": "0:42:35"}
{"current_steps": 130, "total_steps": 555, "loss": 0.7581, "learning_rate": 5e-06, "epoch": 0.7027027027027027, "percentage": 23.42, "elapsed_time": "0:12:45", "remaining_time": "0:41:41"}
{"current_steps": 140, "total_steps": 555, "loss": 0.7576, "learning_rate": 5e-06, "epoch": 0.7567567567567568, "percentage": 25.23, "elapsed_time": "0:13:43", "remaining_time": "0:40:41"}
{"current_steps": 150, "total_steps": 555, "loss": 0.7491, "learning_rate": 5e-06, "epoch": 0.8108108108108109, "percentage": 27.03, "elapsed_time": "0:14:43", "remaining_time": "0:39:45"}
{"current_steps": 160, "total_steps": 555, "loss": 0.7484, "learning_rate": 5e-06, "epoch": 0.8648648648648649, "percentage": 28.83, "elapsed_time": "0:15:42", "remaining_time": "0:38:46"}
{"current_steps": 170, "total_steps": 555, "loss": 0.7437, "learning_rate": 5e-06, "epoch": 0.918918918918919, "percentage": 30.63, "elapsed_time": "0:16:41", "remaining_time": "0:37:47"}
{"current_steps": 180, "total_steps": 555, "loss": 0.743, "learning_rate": 5e-06, "epoch": 0.972972972972973, "percentage": 32.43, "elapsed_time": "0:17:41", "remaining_time": "0:36:52"}
{"current_steps": 185, "total_steps": 555, "eval_loss": 0.7390317320823669, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:18:28", "remaining_time": "0:36:57"}
{"current_steps": 190, "total_steps": 555, "loss": 0.7171, "learning_rate": 5e-06, "epoch": 1.027027027027027, "percentage": 34.23, "elapsed_time": "0:20:26", "remaining_time": "0:39:15"}
{"current_steps": 200, "total_steps": 555, "loss": 0.6929, "learning_rate": 5e-06, "epoch": 1.0810810810810811, "percentage": 36.04, "elapsed_time": "0:21:24", "remaining_time": "0:38:00"}
{"current_steps": 210, "total_steps": 555, "loss": 0.6902, "learning_rate": 5e-06, "epoch": 1.135135135135135, "percentage": 37.84, "elapsed_time": "0:22:22", "remaining_time": "0:36:46"}
{"current_steps": 220, "total_steps": 555, "loss": 0.6884, "learning_rate": 5e-06, "epoch": 1.1891891891891893, "percentage": 39.64, "elapsed_time": "0:23:21", "remaining_time": "0:35:34"}
{"current_steps": 230, "total_steps": 555, "loss": 0.6889, "learning_rate": 5e-06, "epoch": 1.2432432432432432, "percentage": 41.44, "elapsed_time": "0:24:19", "remaining_time": "0:34:22"}
{"current_steps": 240, "total_steps": 555, "loss": 0.6852, "learning_rate": 5e-06, "epoch": 1.2972972972972974, "percentage": 43.24, "elapsed_time": "0:25:19", "remaining_time": "0:33:13"}
{"current_steps": 250, "total_steps": 555, "loss": 0.6901, "learning_rate": 5e-06, "epoch": 1.3513513513513513, "percentage": 45.05, "elapsed_time": "0:26:17", "remaining_time": "0:32:04"}
{"current_steps": 260, "total_steps": 555, "loss": 0.6934, "learning_rate": 5e-06, "epoch": 1.4054054054054055, "percentage": 46.85, "elapsed_time": "0:27:15", "remaining_time": "0:30:56"}
{"current_steps": 270, "total_steps": 555, "loss": 0.6905, "learning_rate": 5e-06, "epoch": 1.4594594594594594, "percentage": 48.65, "elapsed_time": "0:28:15", "remaining_time": "0:29:50"}
{"current_steps": 280, "total_steps": 555, "loss": 0.685, "learning_rate": 5e-06, "epoch": 1.5135135135135136, "percentage": 50.45, "elapsed_time": "0:29:15", "remaining_time": "0:28:43"}
{"current_steps": 290, "total_steps": 555, "loss": 0.6934, "learning_rate": 5e-06, "epoch": 1.5675675675675675, "percentage": 52.25, "elapsed_time": "0:30:14", "remaining_time": "0:27:38"}
{"current_steps": 300, "total_steps": 555, "loss": 0.6851, "learning_rate": 5e-06, "epoch": 1.6216216216216215, "percentage": 54.05, "elapsed_time": "0:31:13", "remaining_time": "0:26:32"}
{"current_steps": 310, "total_steps": 555, "loss": 0.691, "learning_rate": 5e-06, "epoch": 1.6756756756756757, "percentage": 55.86, "elapsed_time": "0:32:12", "remaining_time": "0:25:27"}
{"current_steps": 320, "total_steps": 555, "loss": 0.6881, "learning_rate": 5e-06, "epoch": 1.7297297297297298, "percentage": 57.66, "elapsed_time": "0:33:13", "remaining_time": "0:24:23"}
{"current_steps": 330, "total_steps": 555, "loss": 0.6857, "learning_rate": 5e-06, "epoch": 1.7837837837837838, "percentage": 59.46, "elapsed_time": "0:34:11", "remaining_time": "0:23:18"}
{"current_steps": 340, "total_steps": 555, "loss": 0.6865, "learning_rate": 5e-06, "epoch": 1.8378378378378377, "percentage": 61.26, "elapsed_time": "0:35:10", "remaining_time": "0:22:14"}
{"current_steps": 350, "total_steps": 555, "loss": 0.6909, "learning_rate": 5e-06, "epoch": 1.8918918918918919, "percentage": 63.06, "elapsed_time": "0:36:11", "remaining_time": "0:21:11"}
{"current_steps": 360, "total_steps": 555, "loss": 0.6823, "learning_rate": 5e-06, "epoch": 1.945945945945946, "percentage": 64.86, "elapsed_time": "0:37:09", "remaining_time": "0:20:07"}
{"current_steps": 370, "total_steps": 555, "loss": 0.6864, "learning_rate": 5e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:38:08", "remaining_time": "0:19:04"}
{"current_steps": 370, "total_steps": 555, "eval_loss": 0.7247839570045471, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:38:26", "remaining_time": "0:19:13"}
{"current_steps": 380, "total_steps": 555, "loss": 0.6319, "learning_rate": 5e-06, "epoch": 2.054054054054054, "percentage": 68.47, "elapsed_time": "0:41:16", "remaining_time": "0:19:00"}
{"current_steps": 390, "total_steps": 555, "loss": 0.6295, "learning_rate": 5e-06, "epoch": 2.108108108108108, "percentage": 70.27, "elapsed_time": "0:42:14", "remaining_time": "0:17:52"}
{"current_steps": 400, "total_steps": 555, "loss": 0.6338, "learning_rate": 5e-06, "epoch": 2.1621621621621623, "percentage": 72.07, "elapsed_time": "0:43:13", "remaining_time": "0:16:44"}
{"current_steps": 410, "total_steps": 555, "loss": 0.6345, "learning_rate": 5e-06, "epoch": 2.2162162162162162, "percentage": 73.87, "elapsed_time": "0:44:11", "remaining_time": "0:15:37"}
{"current_steps": 420, "total_steps": 555, "loss": 0.6318, "learning_rate": 5e-06, "epoch": 2.27027027027027, "percentage": 75.68, "elapsed_time": "0:45:10", "remaining_time": "0:14:31"}
{"current_steps": 430, "total_steps": 555, "loss": 0.6307, "learning_rate": 5e-06, "epoch": 2.3243243243243246, "percentage": 77.48, "elapsed_time": "0:46:08", "remaining_time": "0:13:24"}
{"current_steps": 440, "total_steps": 555, "loss": 0.6327, "learning_rate": 5e-06, "epoch": 2.3783783783783785, "percentage": 79.28, "elapsed_time": "0:47:08", "remaining_time": "0:12:19"}
{"current_steps": 450, "total_steps": 555, "loss": 0.6373, "learning_rate": 5e-06, "epoch": 2.4324324324324325, "percentage": 81.08, "elapsed_time": "0:48:08", "remaining_time": "0:11:14"}
{"current_steps": 460, "total_steps": 555, "loss": 0.6345, "learning_rate": 5e-06, "epoch": 2.4864864864864864, "percentage": 82.88, "elapsed_time": "0:49:07", "remaining_time": "0:10:08"}
{"current_steps": 470, "total_steps": 555, "loss": 0.6353, "learning_rate": 5e-06, "epoch": 2.5405405405405403, "percentage": 84.68, "elapsed_time": "0:50:06", "remaining_time": "0:09:03"}
{"current_steps": 480, "total_steps": 555, "loss": 0.6375, "learning_rate": 5e-06, "epoch": 2.5945945945945947, "percentage": 86.49, "elapsed_time": "0:51:05", "remaining_time": "0:07:58"}
{"current_steps": 490, "total_steps": 555, "loss": 0.6416, "learning_rate": 5e-06, "epoch": 2.6486486486486487, "percentage": 88.29, "elapsed_time": "0:52:05", "remaining_time": "0:06:54"}
{"current_steps": 500, "total_steps": 555, "loss": 0.6328, "learning_rate": 5e-06, "epoch": 2.7027027027027026, "percentage": 90.09, "elapsed_time": "0:53:04", "remaining_time": "0:05:50"}
{"current_steps": 510, "total_steps": 555, "loss": 0.6336, "learning_rate": 5e-06, "epoch": 2.756756756756757, "percentage": 91.89, "elapsed_time": "0:54:02", "remaining_time": "0:04:46"}
{"current_steps": 520, "total_steps": 555, "loss": 0.6375, "learning_rate": 5e-06, "epoch": 2.810810810810811, "percentage": 93.69, "elapsed_time": "0:55:01", "remaining_time": "0:03:42"}
{"current_steps": 530, "total_steps": 555, "loss": 0.6392, "learning_rate": 5e-06, "epoch": 2.864864864864865, "percentage": 95.5, "elapsed_time": "0:56:00", "remaining_time": "0:02:38"}
{"current_steps": 540, "total_steps": 555, "loss": 0.6382, "learning_rate": 5e-06, "epoch": 2.918918918918919, "percentage": 97.3, "elapsed_time": "0:56:58", "remaining_time": "0:01:34"}
{"current_steps": 550, "total_steps": 555, "loss": 0.6385, "learning_rate": 5e-06, "epoch": 2.972972972972973, "percentage": 99.1, "elapsed_time": "0:57:57", "remaining_time": "0:00:31"}
{"current_steps": 555, "total_steps": 555, "eval_loss": 0.7265511751174927, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:00:19", "remaining_time": "0:00:00"}
{"current_steps": 555, "total_steps": 555, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:01:52", "remaining_time": "0:00:00"}