trainer_log.jsonl

{"current_steps": 5, "total_steps": 111, "loss": 1.7167, "learning_rate": 5e-07, "epoch": 0.13513513513513514, "percentage": 4.5, "elapsed_time": "0:01:09", "remaining_time": "0:24:36"}
{"current_steps": 10, "total_steps": 111, "loss": 1.5798, "learning_rate": 1e-06, "epoch": 0.2702702702702703, "percentage": 9.01, "elapsed_time": "0:02:14", "remaining_time": "0:22:37"}
{"current_steps": 15, "total_steps": 111, "loss": 1.2993, "learning_rate": 9.939652198703783e-07, "epoch": 0.40540540540540543, "percentage": 13.51, "elapsed_time": "0:03:19", "remaining_time": "0:21:16"}
{"current_steps": 20, "total_steps": 111, "loss": 1.1471, "learning_rate": 9.76006553766365e-07, "epoch": 0.5405405405405406, "percentage": 18.02, "elapsed_time": "0:04:25", "remaining_time": "0:20:08"}
{"current_steps": 25, "total_steps": 111, "loss": 1.0671, "learning_rate": 9.465575080933957e-07, "epoch": 0.6756756756756757, "percentage": 22.52, "elapsed_time": "0:05:31", "remaining_time": "0:18:59"}
{"current_steps": 30, "total_steps": 111, "loss": 1.0305, "learning_rate": 9.063289569141251e-07, "epoch": 0.8108108108108109, "percentage": 27.03, "elapsed_time": "0:06:36", "remaining_time": "0:17:50"}
{"current_steps": 35, "total_steps": 111, "loss": 1.0007, "learning_rate": 8.562919820737535e-07, "epoch": 0.9459459459459459, "percentage": 31.53, "elapsed_time": "0:07:41", "remaining_time": "0:16:42"}
{"current_steps": 40, "total_steps": 111, "loss": 0.946, "learning_rate": 7.97654432138333e-07, "epoch": 1.0810810810810811, "percentage": 36.04, "elapsed_time": "0:08:47", "remaining_time": "0:15:35"}
{"current_steps": 45, "total_steps": 111, "loss": 0.9231, "learning_rate": 7.318317659926636e-07, "epoch": 1.2162162162162162, "percentage": 40.54, "elapsed_time": "0:09:52", "remaining_time": "0:14:28"}
{"current_steps": 50, "total_steps": 111, "loss": 0.9036, "learning_rate": 6.604128849076838e-07, "epoch": 1.3513513513513513, "percentage": 45.05, "elapsed_time": "0:10:57", "remaining_time": "0:13:22"}
{"current_steps": 50, "total_steps": 111, "eval_loss": 0.9227461814880371, "epoch": 1.3513513513513513, "percentage": 45.05, "elapsed_time": "0:11:16", "remaining_time": "0:13:45"}
{"current_steps": 55, "total_steps": 111, "loss": 0.8885, "learning_rate": 5.851217778611993e-07, "epoch": 1.4864864864864864, "percentage": 49.55, "elapsed_time": "0:12:21", "remaining_time": "0:12:35"}
{"current_steps": 60, "total_steps": 111, "loss": 0.8794, "learning_rate": 5.077759059601755e-07, "epoch": 1.6216216216216215, "percentage": 54.05, "elapsed_time": "0:13:27", "remaining_time": "0:11:26"}
{"current_steps": 65, "total_steps": 111, "loss": 0.879, "learning_rate": 4.302423305280385e-07, "epoch": 1.7567567567567568, "percentage": 58.56, "elapsed_time": "0:14:32", "remaining_time": "0:10:17"}
{"current_steps": 70, "total_steps": 111, "loss": 0.8643, "learning_rate": 3.54392643886374e-07, "epoch": 1.8918918918918919, "percentage": 63.06, "elapsed_time": "0:15:38", "remaining_time": "0:09:09"}
{"current_steps": 75, "total_steps": 111, "loss": 0.8416, "learning_rate": 2.8205779076231446e-07, "epoch": 2.027027027027027, "percentage": 67.57, "elapsed_time": "0:16:44", "remaining_time": "0:08:01"}
{"current_steps": 80, "total_steps": 111, "loss": 0.8208, "learning_rate": 2.1498387089310865e-07, "epoch": 2.1621621621621623, "percentage": 72.07, "elapsed_time": "0:17:49", "remaining_time": "0:06:54"}
{"current_steps": 85, "total_steps": 111, "loss": 0.7978, "learning_rate": 1.5478998971412666e-07, "epoch": 2.2972972972972974, "percentage": 76.58, "elapsed_time": "0:18:54", "remaining_time": "0:05:47"}
{"current_steps": 90, "total_steps": 111, "loss": 0.8326, "learning_rate": 1.0292917457762323e-07, "epoch": 2.4324324324324325, "percentage": 81.08, "elapsed_time": "0:20:00", "remaining_time": "0:04:40"}
{"current_steps": 95, "total_steps": 111, "loss": 0.8153, "learning_rate": 6.065329995036572e-08, "epoch": 2.5675675675675675, "percentage": 85.59, "elapsed_time": "0:21:06", "remaining_time": "0:03:33"}
{"current_steps": 100, "total_steps": 111, "loss": 0.7997, "learning_rate": 2.8982868265005454e-08, "epoch": 2.7027027027027026, "percentage": 90.09, "elapsed_time": "0:22:12", "remaining_time": "0:02:26"}
{"current_steps": 100, "total_steps": 111, "eval_loss": 0.8954470157623291, "epoch": 2.7027027027027026, "percentage": 90.09, "elapsed_time": "0:22:31", "remaining_time": "0:02:28"}
{"current_steps": 105, "total_steps": 111, "loss": 0.7965, "learning_rate": 8.682375888868166e-09, "epoch": 2.8378378378378377, "percentage": 94.59, "elapsed_time": "0:23:35", "remaining_time": "0:01:20"}
{"current_steps": 110, "total_steps": 111, "loss": 0.8273, "learning_rate": 2.418588540059607e-10, "epoch": 2.972972972972973, "percentage": 99.1, "elapsed_time": "0:24:41", "remaining_time": "0:00:13"}
{"current_steps": 111, "total_steps": 111, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:25:25", "remaining_time": "0:00:00"}