top_3_ranking_stackexchange / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 3
db05154 verified
{"current_steps": 10, "total_steps": 384, "loss": 0.9586, "lr": 5e-06, "epoch": 0.078125, "percentage": 2.6, "elapsed_time": "0:09:43", "remaining_time": "6:03:39"}
{"current_steps": 20, "total_steps": 384, "loss": 0.8607, "lr": 5e-06, "epoch": 0.15625, "percentage": 5.21, "elapsed_time": "0:19:21", "remaining_time": "5:52:27"}
{"current_steps": 30, "total_steps": 384, "loss": 0.8216, "lr": 5e-06, "epoch": 0.234375, "percentage": 7.81, "elapsed_time": "0:29:00", "remaining_time": "5:42:20"}
{"current_steps": 40, "total_steps": 384, "loss": 0.7988, "lr": 5e-06, "epoch": 0.3125, "percentage": 10.42, "elapsed_time": "0:38:38", "remaining_time": "5:32:17"}
{"current_steps": 50, "total_steps": 384, "loss": 0.7875, "lr": 5e-06, "epoch": 0.390625, "percentage": 13.02, "elapsed_time": "0:48:16", "remaining_time": "5:22:29"}
{"current_steps": 60, "total_steps": 384, "loss": 0.7797, "lr": 5e-06, "epoch": 0.46875, "percentage": 15.62, "elapsed_time": "0:57:54", "remaining_time": "5:12:44"}
{"current_steps": 70, "total_steps": 384, "loss": 0.7835, "lr": 5e-06, "epoch": 0.546875, "percentage": 18.23, "elapsed_time": "1:07:32", "remaining_time": "5:03:00"}
{"current_steps": 80, "total_steps": 384, "loss": 0.7683, "lr": 5e-06, "epoch": 0.625, "percentage": 20.83, "elapsed_time": "1:17:11", "remaining_time": "4:53:19"}
{"current_steps": 90, "total_steps": 384, "loss": 0.7716, "lr": 5e-06, "epoch": 0.703125, "percentage": 23.44, "elapsed_time": "1:26:49", "remaining_time": "4:43:38"}
{"current_steps": 100, "total_steps": 384, "loss": 0.7584, "lr": 5e-06, "epoch": 0.78125, "percentage": 26.04, "elapsed_time": "1:36:27", "remaining_time": "4:33:56"}
{"current_steps": 110, "total_steps": 384, "loss": 0.7556, "lr": 5e-06, "epoch": 0.859375, "percentage": 28.65, "elapsed_time": "1:46:05", "remaining_time": "4:24:14"}
{"current_steps": 120, "total_steps": 384, "loss": 0.7516, "lr": 5e-06, "epoch": 0.9375, "percentage": 31.25, "elapsed_time": "1:55:43", "remaining_time": "4:14:36"}
{"current_steps": 128, "total_steps": 384, "eval_loss": 0.7458022236824036, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "2:05:41", "remaining_time": "4:11:22"}
{"current_steps": 130, "total_steps": 384, "loss": 0.7472, "lr": 5e-06, "epoch": 1.015625, "percentage": 33.85, "elapsed_time": "2:08:44", "remaining_time": "4:11:31"}
{"current_steps": 140, "total_steps": 384, "loss": 0.7109, "lr": 5e-06, "epoch": 1.09375, "percentage": 36.46, "elapsed_time": "2:18:22", "remaining_time": "4:01:10"}
{"current_steps": 150, "total_steps": 384, "loss": 0.7018, "lr": 5e-06, "epoch": 1.171875, "percentage": 39.06, "elapsed_time": "2:28:01", "remaining_time": "3:50:55"}
{"current_steps": 160, "total_steps": 384, "loss": 0.7094, "lr": 5e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "2:37:40", "remaining_time": "3:40:44"}
{"current_steps": 170, "total_steps": 384, "loss": 0.7051, "lr": 5e-06, "epoch": 1.328125, "percentage": 44.27, "elapsed_time": "2:47:19", "remaining_time": "3:30:37"}
{"current_steps": 180, "total_steps": 384, "loss": 0.7085, "lr": 5e-06, "epoch": 1.40625, "percentage": 46.88, "elapsed_time": "2:56:57", "remaining_time": "3:20:33"}
{"current_steps": 190, "total_steps": 384, "loss": 0.7066, "lr": 5e-06, "epoch": 1.484375, "percentage": 49.48, "elapsed_time": "3:06:37", "remaining_time": "3:10:33"}
{"current_steps": 200, "total_steps": 384, "loss": 0.703, "lr": 5e-06, "epoch": 1.5625, "percentage": 52.08, "elapsed_time": "3:16:15", "remaining_time": "3:00:33"}
{"current_steps": 210, "total_steps": 384, "loss": 0.7057, "lr": 5e-06, "epoch": 1.640625, "percentage": 54.69, "elapsed_time": "3:25:54", "remaining_time": "2:50:36"}
{"current_steps": 220, "total_steps": 384, "loss": 0.7035, "lr": 5e-06, "epoch": 1.71875, "percentage": 57.29, "elapsed_time": "3:35:33", "remaining_time": "2:40:41"}
{"current_steps": 230, "total_steps": 384, "loss": 0.7013, "lr": 5e-06, "epoch": 1.796875, "percentage": 59.9, "elapsed_time": "3:45:12", "remaining_time": "2:30:47"}
{"current_steps": 240, "total_steps": 384, "loss": 0.7012, "lr": 5e-06, "epoch": 1.875, "percentage": 62.5, "elapsed_time": "3:54:52", "remaining_time": "2:20:55"}
{"current_steps": 250, "total_steps": 384, "loss": 0.7023, "lr": 5e-06, "epoch": 1.953125, "percentage": 65.1, "elapsed_time": "4:04:30", "remaining_time": "2:11:03"}
{"current_steps": 256, "total_steps": 384, "eval_loss": 0.732055127620697, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "4:12:33", "remaining_time": "2:06:16"}
{"current_steps": 260, "total_steps": 384, "loss": 0.6879, "lr": 5e-06, "epoch": 2.03125, "percentage": 67.71, "elapsed_time": "4:17:37", "remaining_time": "2:02:52"}
{"current_steps": 270, "total_steps": 384, "loss": 0.6546, "lr": 5e-06, "epoch": 2.109375, "percentage": 70.31, "elapsed_time": "4:27:15", "remaining_time": "1:52:50"}
{"current_steps": 280, "total_steps": 384, "loss": 0.6547, "lr": 5e-06, "epoch": 2.1875, "percentage": 72.92, "elapsed_time": "4:36:53", "remaining_time": "1:42:50"}
{"current_steps": 290, "total_steps": 384, "loss": 0.6556, "lr": 5e-06, "epoch": 2.265625, "percentage": 75.52, "elapsed_time": "4:46:31", "remaining_time": "1:32:52"}
{"current_steps": 300, "total_steps": 384, "loss": 0.6514, "lr": 5e-06, "epoch": 2.34375, "percentage": 78.12, "elapsed_time": "4:56:09", "remaining_time": "1:22:55"}
{"current_steps": 310, "total_steps": 384, "loss": 0.6553, "lr": 5e-06, "epoch": 2.421875, "percentage": 80.73, "elapsed_time": "5:05:48", "remaining_time": "1:12:59"}
{"current_steps": 320, "total_steps": 384, "loss": 0.6547, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "5:15:27", "remaining_time": "1:03:05"}
{"current_steps": 330, "total_steps": 384, "loss": 0.6618, "lr": 5e-06, "epoch": 2.578125, "percentage": 85.94, "elapsed_time": "5:25:05", "remaining_time": "0:53:11"}
{"current_steps": 340, "total_steps": 384, "loss": 0.66, "lr": 5e-06, "epoch": 2.65625, "percentage": 88.54, "elapsed_time": "5:34:43", "remaining_time": "0:43:19"}
{"current_steps": 350, "total_steps": 384, "loss": 0.6627, "lr": 5e-06, "epoch": 2.734375, "percentage": 91.15, "elapsed_time": "5:44:21", "remaining_time": "0:33:27"}
{"current_steps": 360, "total_steps": 384, "loss": 0.6586, "lr": 5e-06, "epoch": 2.8125, "percentage": 93.75, "elapsed_time": "5:53:59", "remaining_time": "0:23:35"}
{"current_steps": 370, "total_steps": 384, "loss": 0.6632, "lr": 5e-06, "epoch": 2.890625, "percentage": 96.35, "elapsed_time": "6:03:38", "remaining_time": "0:13:45"}
{"current_steps": 380, "total_steps": 384, "loss": 0.6572, "lr": 5e-06, "epoch": 2.96875, "percentage": 98.96, "elapsed_time": "6:13:16", "remaining_time": "0:03:55"}
{"current_steps": 384, "total_steps": 384, "eval_loss": 0.7316058278083801, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:20:36", "remaining_time": "0:00:00"}
{"current_steps": 384, "total_steps": 384, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "6:21:52", "remaining_time": "0:00:00"}