original_tiger_dataset_small / trainer_log.jsonl
sedrickkeh's picture
Training in progress, epoch 2
9b15115 verified
{"current_steps": 10, "total_steps": 675, "loss": 0.5829, "lr": 5e-06, "epoch": 0.0443213296398892, "percentage": 1.48, "elapsed_time": "0:05:24", "remaining_time": "5:59:25"}
{"current_steps": 20, "total_steps": 675, "loss": 0.513, "lr": 5e-06, "epoch": 0.0886426592797784, "percentage": 2.96, "elapsed_time": "0:10:45", "remaining_time": "5:52:22"}
{"current_steps": 30, "total_steps": 675, "loss": 0.4887, "lr": 5e-06, "epoch": 0.1329639889196676, "percentage": 4.44, "elapsed_time": "0:16:06", "remaining_time": "5:46:16"}
{"current_steps": 40, "total_steps": 675, "loss": 0.4649, "lr": 5e-06, "epoch": 0.1772853185595568, "percentage": 5.93, "elapsed_time": "0:21:26", "remaining_time": "5:40:18"}
{"current_steps": 50, "total_steps": 675, "loss": 0.4513, "lr": 5e-06, "epoch": 0.22160664819944598, "percentage": 7.41, "elapsed_time": "0:26:44", "remaining_time": "5:34:20"}
{"current_steps": 60, "total_steps": 675, "loss": 0.4487, "lr": 5e-06, "epoch": 0.2659279778393352, "percentage": 8.89, "elapsed_time": "0:32:03", "remaining_time": "5:28:40"}
{"current_steps": 70, "total_steps": 675, "loss": 0.4406, "lr": 5e-06, "epoch": 0.31024930747922436, "percentage": 10.37, "elapsed_time": "0:37:22", "remaining_time": "5:23:03"}
{"current_steps": 80, "total_steps": 675, "loss": 0.4359, "lr": 5e-06, "epoch": 0.3545706371191136, "percentage": 11.85, "elapsed_time": "0:42:41", "remaining_time": "5:17:34"}
{"current_steps": 90, "total_steps": 675, "loss": 0.4278, "lr": 5e-06, "epoch": 0.3988919667590028, "percentage": 13.33, "elapsed_time": "0:48:00", "remaining_time": "5:12:00"}
{"current_steps": 100, "total_steps": 675, "loss": 0.4266, "lr": 5e-06, "epoch": 0.44321329639889195, "percentage": 14.81, "elapsed_time": "0:53:18", "remaining_time": "5:06:34"}
{"current_steps": 110, "total_steps": 675, "loss": 0.4198, "lr": 5e-06, "epoch": 0.48753462603878117, "percentage": 16.3, "elapsed_time": "0:58:38", "remaining_time": "5:01:10"}
{"current_steps": 120, "total_steps": 675, "loss": 0.4201, "lr": 5e-06, "epoch": 0.5318559556786704, "percentage": 17.78, "elapsed_time": "1:03:58", "remaining_time": "4:55:50"}
{"current_steps": 130, "total_steps": 675, "loss": 0.4198, "lr": 5e-06, "epoch": 0.5761772853185596, "percentage": 19.26, "elapsed_time": "1:09:16", "remaining_time": "4:50:23"}
{"current_steps": 140, "total_steps": 675, "loss": 0.4181, "lr": 5e-06, "epoch": 0.6204986149584487, "percentage": 20.74, "elapsed_time": "1:14:36", "remaining_time": "4:45:06"}
{"current_steps": 150, "total_steps": 675, "loss": 0.4147, "lr": 5e-06, "epoch": 0.6648199445983379, "percentage": 22.22, "elapsed_time": "1:19:57", "remaining_time": "4:39:49"}
{"current_steps": 160, "total_steps": 675, "loss": 0.412, "lr": 5e-06, "epoch": 0.7091412742382271, "percentage": 23.7, "elapsed_time": "1:25:18", "remaining_time": "4:34:35"}
{"current_steps": 170, "total_steps": 675, "loss": 0.4166, "lr": 5e-06, "epoch": 0.7534626038781164, "percentage": 25.19, "elapsed_time": "1:30:38", "remaining_time": "4:29:14"}
{"current_steps": 180, "total_steps": 675, "loss": 0.4132, "lr": 5e-06, "epoch": 0.7977839335180056, "percentage": 26.67, "elapsed_time": "1:35:58", "remaining_time": "4:23:54"}
{"current_steps": 190, "total_steps": 675, "loss": 0.4136, "lr": 5e-06, "epoch": 0.8421052631578947, "percentage": 28.15, "elapsed_time": "1:41:20", "remaining_time": "4:18:41"}
{"current_steps": 200, "total_steps": 675, "loss": 0.4041, "lr": 5e-06, "epoch": 0.8864265927977839, "percentage": 29.63, "elapsed_time": "1:46:41", "remaining_time": "4:13:23"}
{"current_steps": 210, "total_steps": 675, "loss": 0.411, "lr": 5e-06, "epoch": 0.9307479224376731, "percentage": 31.11, "elapsed_time": "1:52:03", "remaining_time": "4:08:07"}
{"current_steps": 220, "total_steps": 675, "loss": 0.4061, "lr": 5e-06, "epoch": 0.9750692520775623, "percentage": 32.59, "elapsed_time": "1:57:26", "remaining_time": "4:02:52"}
{"current_steps": 225, "total_steps": 675, "eval_loss": 0.4077036678791046, "epoch": 0.997229916897507, "percentage": 33.33, "elapsed_time": "2:03:03", "remaining_time": "4:06:07"}
{"current_steps": 230, "total_steps": 675, "loss": 0.4093, "lr": 5e-06, "epoch": 1.0193905817174516, "percentage": 34.07, "elapsed_time": "2:06:40", "remaining_time": "4:05:04"}
{"current_steps": 240, "total_steps": 675, "loss": 0.3815, "lr": 5e-06, "epoch": 1.0637119113573408, "percentage": 35.56, "elapsed_time": "2:12:01", "remaining_time": "3:59:17"}
{"current_steps": 250, "total_steps": 675, "loss": 0.3761, "lr": 5e-06, "epoch": 1.10803324099723, "percentage": 37.04, "elapsed_time": "2:17:22", "remaining_time": "3:53:31"}
{"current_steps": 260, "total_steps": 675, "loss": 0.3818, "lr": 5e-06, "epoch": 1.1523545706371192, "percentage": 38.52, "elapsed_time": "2:22:45", "remaining_time": "3:47:51"}
{"current_steps": 270, "total_steps": 675, "loss": 0.3792, "lr": 5e-06, "epoch": 1.1966759002770084, "percentage": 40.0, "elapsed_time": "2:28:07", "remaining_time": "3:42:11"}
{"current_steps": 280, "total_steps": 675, "loss": 0.3768, "lr": 5e-06, "epoch": 1.2409972299168974, "percentage": 41.48, "elapsed_time": "2:33:29", "remaining_time": "3:36:32"}
{"current_steps": 290, "total_steps": 675, "loss": 0.3813, "lr": 5e-06, "epoch": 1.2853185595567866, "percentage": 42.96, "elapsed_time": "2:38:51", "remaining_time": "3:30:53"}
{"current_steps": 300, "total_steps": 675, "loss": 0.3819, "lr": 5e-06, "epoch": 1.3296398891966759, "percentage": 44.44, "elapsed_time": "2:44:12", "remaining_time": "3:25:15"}
{"current_steps": 310, "total_steps": 675, "loss": 0.38, "lr": 5e-06, "epoch": 1.373961218836565, "percentage": 45.93, "elapsed_time": "2:49:34", "remaining_time": "3:19:39"}
{"current_steps": 320, "total_steps": 675, "loss": 0.3755, "lr": 5e-06, "epoch": 1.4182825484764543, "percentage": 47.41, "elapsed_time": "2:54:57", "remaining_time": "3:14:05"}
{"current_steps": 330, "total_steps": 675, "loss": 0.3808, "lr": 5e-06, "epoch": 1.4626038781163435, "percentage": 48.89, "elapsed_time": "3:00:19", "remaining_time": "3:08:31"}
{"current_steps": 340, "total_steps": 675, "loss": 0.3778, "lr": 5e-06, "epoch": 1.5069252077562327, "percentage": 50.37, "elapsed_time": "3:05:41", "remaining_time": "3:02:57"}
{"current_steps": 350, "total_steps": 675, "loss": 0.3779, "lr": 5e-06, "epoch": 1.5512465373961217, "percentage": 51.85, "elapsed_time": "3:11:03", "remaining_time": "2:57:24"}
{"current_steps": 360, "total_steps": 675, "loss": 0.374, "lr": 5e-06, "epoch": 1.595567867036011, "percentage": 53.33, "elapsed_time": "3:16:24", "remaining_time": "2:51:51"}
{"current_steps": 370, "total_steps": 675, "loss": 0.3776, "lr": 5e-06, "epoch": 1.6398891966759002, "percentage": 54.81, "elapsed_time": "3:21:46", "remaining_time": "2:46:19"}
{"current_steps": 380, "total_steps": 675, "loss": 0.3805, "lr": 5e-06, "epoch": 1.6842105263157894, "percentage": 56.3, "elapsed_time": "3:27:08", "remaining_time": "2:40:48"}
{"current_steps": 390, "total_steps": 675, "loss": 0.3776, "lr": 5e-06, "epoch": 1.7285318559556786, "percentage": 57.78, "elapsed_time": "3:32:30", "remaining_time": "2:35:17"}
{"current_steps": 400, "total_steps": 675, "loss": 0.3759, "lr": 5e-06, "epoch": 1.7728531855955678, "percentage": 59.26, "elapsed_time": "3:37:52", "remaining_time": "2:29:47"}
{"current_steps": 410, "total_steps": 675, "loss": 0.3797, "lr": 5e-06, "epoch": 1.817174515235457, "percentage": 60.74, "elapsed_time": "3:43:12", "remaining_time": "2:24:16"}
{"current_steps": 420, "total_steps": 675, "loss": 0.3736, "lr": 5e-06, "epoch": 1.8614958448753463, "percentage": 62.22, "elapsed_time": "3:48:33", "remaining_time": "2:18:46"}
{"current_steps": 430, "total_steps": 675, "loss": 0.3761, "lr": 5e-06, "epoch": 1.9058171745152355, "percentage": 63.7, "elapsed_time": "3:53:56", "remaining_time": "2:13:17"}
{"current_steps": 440, "total_steps": 675, "loss": 0.3731, "lr": 5e-06, "epoch": 1.9501385041551247, "percentage": 65.19, "elapsed_time": "3:59:17", "remaining_time": "2:07:48"}
{"current_steps": 450, "total_steps": 675, "loss": 0.3726, "lr": 5e-06, "epoch": 1.994459833795014, "percentage": 66.67, "elapsed_time": "4:04:37", "remaining_time": "2:02:18"}
{"current_steps": 451, "total_steps": 675, "eval_loss": 0.3975733816623688, "epoch": 1.9988919667590028, "percentage": 66.81, "elapsed_time": "4:07:48", "remaining_time": "2:03:04"}
{"current_steps": 460, "total_steps": 675, "loss": 0.3629, "lr": 5e-06, "epoch": 2.038781163434903, "percentage": 68.15, "elapsed_time": "4:13:44", "remaining_time": "1:58:35"}
{"current_steps": 470, "total_steps": 675, "loss": 0.3425, "lr": 5e-06, "epoch": 2.0831024930747923, "percentage": 69.63, "elapsed_time": "4:19:04", "remaining_time": "1:53:00"}
{"current_steps": 480, "total_steps": 675, "loss": 0.3458, "lr": 5e-06, "epoch": 2.1274238227146816, "percentage": 71.11, "elapsed_time": "4:24:24", "remaining_time": "1:47:25"}
{"current_steps": 490, "total_steps": 675, "loss": 0.3487, "lr": 5e-06, "epoch": 2.1717451523545708, "percentage": 72.59, "elapsed_time": "4:29:45", "remaining_time": "1:41:50"}
{"current_steps": 500, "total_steps": 675, "loss": 0.344, "lr": 5e-06, "epoch": 2.21606648199446, "percentage": 74.07, "elapsed_time": "4:35:05", "remaining_time": "1:36:16"}
{"current_steps": 510, "total_steps": 675, "loss": 0.3469, "lr": 5e-06, "epoch": 2.260387811634349, "percentage": 75.56, "elapsed_time": "4:40:25", "remaining_time": "1:30:43"}
{"current_steps": 520, "total_steps": 675, "loss": 0.344, "lr": 5e-06, "epoch": 2.3047091412742384, "percentage": 77.04, "elapsed_time": "4:45:45", "remaining_time": "1:25:10"}
{"current_steps": 530, "total_steps": 675, "loss": 0.3422, "lr": 5e-06, "epoch": 2.349030470914127, "percentage": 78.52, "elapsed_time": "4:51:05", "remaining_time": "1:19:38"}
{"current_steps": 540, "total_steps": 675, "loss": 0.3481, "lr": 5e-06, "epoch": 2.393351800554017, "percentage": 80.0, "elapsed_time": "4:56:26", "remaining_time": "1:14:06"}
{"current_steps": 550, "total_steps": 675, "loss": 0.3475, "lr": 5e-06, "epoch": 2.4376731301939056, "percentage": 81.48, "elapsed_time": "5:01:47", "remaining_time": "1:08:35"}
{"current_steps": 560, "total_steps": 675, "loss": 0.35, "lr": 5e-06, "epoch": 2.481994459833795, "percentage": 82.96, "elapsed_time": "5:07:07", "remaining_time": "1:03:04"}
{"current_steps": 570, "total_steps": 675, "loss": 0.3466, "lr": 5e-06, "epoch": 2.526315789473684, "percentage": 84.44, "elapsed_time": "5:12:27", "remaining_time": "0:57:33"}
{"current_steps": 580, "total_steps": 675, "loss": 0.3459, "lr": 5e-06, "epoch": 2.5706371191135733, "percentage": 85.93, "elapsed_time": "5:17:46", "remaining_time": "0:52:02"}
{"current_steps": 590, "total_steps": 675, "loss": 0.3448, "lr": 5e-06, "epoch": 2.6149584487534625, "percentage": 87.41, "elapsed_time": "5:23:07", "remaining_time": "0:46:33"}
{"current_steps": 600, "total_steps": 675, "loss": 0.3482, "lr": 5e-06, "epoch": 2.6592797783933517, "percentage": 88.89, "elapsed_time": "5:28:29", "remaining_time": "0:41:03"}
{"current_steps": 610, "total_steps": 675, "loss": 0.3481, "lr": 5e-06, "epoch": 2.703601108033241, "percentage": 90.37, "elapsed_time": "5:33:49", "remaining_time": "0:35:34"}
{"current_steps": 620, "total_steps": 675, "loss": 0.3474, "lr": 5e-06, "epoch": 2.74792243767313, "percentage": 91.85, "elapsed_time": "5:39:11", "remaining_time": "0:30:05"}
{"current_steps": 630, "total_steps": 675, "loss": 0.3429, "lr": 5e-06, "epoch": 2.7922437673130194, "percentage": 93.33, "elapsed_time": "5:44:32", "remaining_time": "0:24:36"}
{"current_steps": 640, "total_steps": 675, "loss": 0.3491, "lr": 5e-06, "epoch": 2.8365650969529086, "percentage": 94.81, "elapsed_time": "5:49:53", "remaining_time": "0:19:08"}
{"current_steps": 650, "total_steps": 675, "loss": 0.3479, "lr": 5e-06, "epoch": 2.880886426592798, "percentage": 96.3, "elapsed_time": "5:55:13", "remaining_time": "0:13:39"}
{"current_steps": 660, "total_steps": 675, "loss": 0.3472, "lr": 5e-06, "epoch": 2.925207756232687, "percentage": 97.78, "elapsed_time": "6:00:33", "remaining_time": "0:08:11"}
{"current_steps": 670, "total_steps": 675, "loss": 0.3467, "lr": 5e-06, "epoch": 2.9695290858725762, "percentage": 99.26, "elapsed_time": "6:05:53", "remaining_time": "0:02:43"}
{"current_steps": 675, "total_steps": 675, "eval_loss": 0.39780595898628235, "epoch": 2.9916897506925206, "percentage": 100.0, "elapsed_time": "6:12:28", "remaining_time": "0:00:00"}
{"current_steps": 675, "total_steps": 675, "epoch": 2.9916897506925206, "percentage": 100.0, "elapsed_time": "6:14:03", "remaining_time": "0:00:00"}