question_generation_model / trainer_log.jsonl
tokhey's picture
Training in progress, step 225
73beb7b verified
{"current_steps": 5, "total_steps": 225, "loss": 0.5835, "lr": 8.695652173913044e-05, "epoch": 0.06666666666666667, "percentage": 2.22, "elapsed_time": "0:02:29", "remaining_time": "1:49:33"}
{"current_steps": 10, "total_steps": 225, "loss": 0.6482, "lr": 0.0001956521739130435, "epoch": 0.13333333333333333, "percentage": 4.44, "elapsed_time": "0:05:03", "remaining_time": "1:48:38"}
{"current_steps": 15, "total_steps": 225, "loss": 0.566, "lr": 0.00030434782608695655, "epoch": 0.2, "percentage": 6.67, "elapsed_time": "0:07:38", "remaining_time": "1:47:00"}
{"current_steps": 20, "total_steps": 225, "loss": 0.5803, "lr": 0.0004130434782608696, "epoch": 0.26666666666666666, "percentage": 8.89, "elapsed_time": "0:10:14", "remaining_time": "1:44:59"}
{"current_steps": 25, "total_steps": 225, "loss": 0.5898, "lr": 0.0004999697658150374, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:12:50", "remaining_time": "1:42:41"}
{"current_steps": 30, "total_steps": 225, "loss": 0.5948, "lr": 0.0004989123369922546, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:15:25", "remaining_time": "1:40:16"}
{"current_steps": 35, "total_steps": 225, "loss": 0.5853, "lr": 0.0004963505038221703, "epoch": 0.4666666666666667, "percentage": 15.56, "elapsed_time": "0:18:01", "remaining_time": "1:37:49"}
{"current_steps": 40, "total_steps": 225, "loss": 0.5324, "lr": 0.0004922997497999166, "epoch": 0.5333333333333333, "percentage": 17.78, "elapsed_time": "0:20:36", "remaining_time": "1:35:19"}
{"current_steps": 45, "total_steps": 225, "loss": 0.554, "lr": 0.00048678455732775007, "epoch": 0.6, "percentage": 20.0, "elapsed_time": "0:23:22", "remaining_time": "1:33:29"}
{"current_steps": 50, "total_steps": 225, "loss": 0.6044, "lr": 0.00047983825974555906, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:26:00", "remaining_time": "1:31:01"}
{"current_steps": 55, "total_steps": 225, "loss": 0.5653, "lr": 0.0004715028398670787, "epoch": 0.7333333333333333, "percentage": 24.44, "elapsed_time": "0:28:39", "remaining_time": "1:28:34"}
{"current_steps": 60, "total_steps": 225, "loss": 0.5539, "lr": 0.00046182867623944434, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:31:17", "remaining_time": "1:26:03"}
{"current_steps": 65, "total_steps": 225, "loss": 0.5267, "lr": 0.00045087423865966894, "epoch": 0.8666666666666667, "percentage": 28.89, "elapsed_time": "0:33:56", "remaining_time": "1:23:31"}
{"current_steps": 70, "total_steps": 225, "loss": 0.5533, "lr": 0.0004387057347883143, "epoch": 0.9333333333333333, "percentage": 31.11, "elapsed_time": "0:36:34", "remaining_time": "1:20:58"}
{"current_steps": 75, "total_steps": 225, "loss": 0.5016, "lr": 0.0004253967099961942, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:39:12", "remaining_time": "1:18:25"}
{"current_steps": 80, "total_steps": 225, "loss": 0.4856, "lr": 0.0004110276028625994, "epoch": 1.0666666666666667, "percentage": 35.56, "elapsed_time": "0:41:51", "remaining_time": "1:15:51"}
{"current_steps": 85, "total_steps": 225, "loss": 0.4632, "lr": 0.00039568525901157527, "epoch": 1.1333333333333333, "percentage": 37.78, "elapsed_time": "0:44:37", "remaining_time": "1:13:29"}
{"current_steps": 90, "total_steps": 225, "loss": 0.5097, "lr": 0.0003794624062245813, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "0:47:15", "remaining_time": "1:10:53"}
{"current_steps": 95, "total_steps": 225, "loss": 0.4476, "lr": 0.000362457094001909, "epoch": 1.2666666666666666, "percentage": 42.22, "elapsed_time": "0:49:54", "remaining_time": "1:08:17"}
{"current_steps": 100, "total_steps": 225, "loss": 0.4919, "lr": 0.00034477210096009486, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:52:32", "remaining_time": "1:05:41"}
{"current_steps": 100, "total_steps": 225, "eval_loss": 0.506523609161377, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:53:17", "remaining_time": "1:06:37"}
{"current_steps": 105, "total_steps": 225, "loss": 0.3816, "lr": 0.00032651431364697186, "epoch": 1.4, "percentage": 46.67, "elapsed_time": "0:55:56", "remaining_time": "1:03:55"}
{"current_steps": 110, "total_steps": 225, "loss": 0.4784, "lr": 0.0003077940805287425, "epoch": 1.4666666666666668, "percentage": 48.89, "elapsed_time": "0:58:34", "remaining_time": "1:01:14"}
{"current_steps": 115, "total_steps": 225, "loss": 0.4422, "lr": 0.00028872454505352117, "epoch": 1.5333333333333332, "percentage": 51.11, "elapsed_time": "1:01:13", "remaining_time": "0:58:33"}
{"current_steps": 120, "total_steps": 225, "loss": 0.4828, "lr": 0.0002694209618222516, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "1:03:51", "remaining_time": "0:55:52"}
{"current_steps": 125, "total_steps": 225, "loss": 0.4853, "lr": 0.00025, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "1:06:42", "remaining_time": "0:53:21"}
{"current_steps": 130, "total_steps": 225, "loss": 0.4392, "lr": 0.00023057903817774841, "epoch": 1.7333333333333334, "percentage": 57.78, "elapsed_time": "1:09:21", "remaining_time": "0:50:40"}
{"current_steps": 135, "total_steps": 225, "loss": 0.4489, "lr": 0.00021127545494647882, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "1:11:59", "remaining_time": "0:47:59"}
{"current_steps": 140, "total_steps": 225, "loss": 0.4856, "lr": 0.00019220591947125766, "epoch": 1.8666666666666667, "percentage": 62.22, "elapsed_time": "1:14:37", "remaining_time": "0:45:18"}
{"current_steps": 145, "total_steps": 225, "loss": 0.4406, "lr": 0.0001734856863530282, "epoch": 1.9333333333333333, "percentage": 64.44, "elapsed_time": "1:17:15", "remaining_time": "0:42:37"}
{"current_steps": 150, "total_steps": 225, "loss": 0.4405, "lr": 0.0001552278990399052, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:19:53", "remaining_time": "0:39:56"}
{"current_steps": 155, "total_steps": 225, "loss": 0.3784, "lr": 0.00013754290599809105, "epoch": 2.066666666666667, "percentage": 68.89, "elapsed_time": "1:22:32", "remaining_time": "0:37:16"}
{"current_steps": 160, "total_steps": 225, "loss": 0.4102, "lr": 0.00012053759377541865, "epoch": 2.1333333333333333, "percentage": 71.11, "elapsed_time": "1:25:10", "remaining_time": "0:34:36"}
{"current_steps": 165, "total_steps": 225, "loss": 0.3926, "lr": 0.00010431474098842477, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "1:27:58", "remaining_time": "0:31:59"}
{"current_steps": 170, "total_steps": 225, "loss": 0.4028, "lr": 8.897239713740058e-05, "epoch": 2.2666666666666666, "percentage": 75.56, "elapsed_time": "1:30:36", "remaining_time": "0:29:18"}
{"current_steps": 175, "total_steps": 225, "loss": 0.4216, "lr": 7.460329000380586e-05, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "1:33:15", "remaining_time": "0:26:38"}
{"current_steps": 180, "total_steps": 225, "loss": 0.4194, "lr": 6.12942652116858e-05, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "1:35:53", "remaining_time": "0:23:58"}
{"current_steps": 185, "total_steps": 225, "loss": 0.3448, "lr": 4.912576134033106e-05, "epoch": 2.466666666666667, "percentage": 82.22, "elapsed_time": "1:38:32", "remaining_time": "0:21:18"}
{"current_steps": 190, "total_steps": 225, "loss": 0.3779, "lr": 3.8171323760555655e-05, "epoch": 2.533333333333333, "percentage": 84.44, "elapsed_time": "1:41:11", "remaining_time": "0:18:38"}
{"current_steps": 195, "total_steps": 225, "loss": 0.3846, "lr": 2.8497160132921336e-05, "epoch": 2.6, "percentage": 86.67, "elapsed_time": "1:43:50", "remaining_time": "0:15:58"}
{"current_steps": 200, "total_steps": 225, "loss": 0.3998, "lr": 2.0161740254440898e-05, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "1:46:28", "remaining_time": "0:13:18"}
{"current_steps": 200, "total_steps": 225, "eval_loss": 0.5051587224006653, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "1:47:13", "remaining_time": "0:13:24"}
{"current_steps": 205, "total_steps": 225, "loss": 0.4098, "lr": 1.3215442672249972e-05, "epoch": 2.7333333333333334, "percentage": 91.11, "elapsed_time": "1:50:00", "remaining_time": "0:10:43"}
{"current_steps": 210, "total_steps": 225, "loss": 0.3316, "lr": 7.70025020008347e-06, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "1:52:39", "remaining_time": "0:08:02"}
{"current_steps": 215, "total_steps": 225, "loss": 0.3406, "lr": 3.64949617782967e-06, "epoch": 2.8666666666666667, "percentage": 95.56, "elapsed_time": "1:55:18", "remaining_time": "0:05:21"}
{"current_steps": 220, "total_steps": 225, "loss": 0.3846, "lr": 1.0876630077453487e-06, "epoch": 2.9333333333333336, "percentage": 97.78, "elapsed_time": "1:57:56", "remaining_time": "0:02:40"}
{"current_steps": 225, "total_steps": 225, "loss": 0.3517, "lr": 3.023418496261865e-08, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:00:35", "remaining_time": "0:00:00"}
{"current_steps": 225, "total_steps": 225, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:00:43", "remaining_time": "0:00:00"}