model / trainer_log.jsonl
tegana's picture
Training in progress, step 252
10194a2 verified
{"current_steps": 10, "total_steps": 252, "loss": 0.5328742027282715, "lr": 3.461538461538462e-05, "epoch": 0.11940298507462686, "percentage": 3.97, "elapsed_time": "0:02:47", "remaining_time": "1:07:31"}
{"current_steps": 20, "total_steps": 252, "loss": 0.28172030448913576, "lr": 7.307692307692307e-05, "epoch": 0.23880597014925373, "percentage": 7.94, "elapsed_time": "0:05:41", "remaining_time": "1:05:56"}
{"current_steps": 30, "total_steps": 252, "loss": 0.22340788841247558, "lr": 9.995652871840006e-05, "epoch": 0.3582089552238806, "percentage": 11.9, "elapsed_time": "0:08:54", "remaining_time": "1:05:58"}
{"current_steps": 40, "total_steps": 252, "loss": 0.19026432037353516, "lr": 9.918580696928205e-05, "epoch": 0.47761194029850745, "percentage": 15.87, "elapsed_time": "0:11:59", "remaining_time": "1:03:32"}
{"current_steps": 50, "total_steps": 252, "loss": 0.1776690363883972, "lr": 9.746617916180905e-05, "epoch": 0.5970149253731343, "percentage": 19.84, "elapsed_time": "0:15:08", "remaining_time": "1:01:11"}
{"current_steps": 60, "total_steps": 252, "loss": 0.16183719635009766, "lr": 9.483082082658983e-05, "epoch": 0.7164179104477612, "percentage": 23.81, "elapsed_time": "0:18:08", "remaining_time": "0:58:02"}
{"current_steps": 70, "total_steps": 252, "loss": 0.18729711771011354, "lr": 9.133057401836159e-05, "epoch": 0.835820895522388, "percentage": 27.78, "elapsed_time": "0:21:12", "remaining_time": "0:55:07"}
{"current_steps": 80, "total_steps": 252, "loss": 0.17510976791381835, "lr": 8.703296645714609e-05, "epoch": 0.9552238805970149, "percentage": 31.75, "elapsed_time": "0:24:14", "remaining_time": "0:52:07"}
{"current_steps": 90, "total_steps": 252, "loss": 0.15757997035980226, "lr": 8.202090876498144e-05, "epoch": 1.0716417910447762, "percentage": 35.71, "elapsed_time": "0:26:54", "remaining_time": "0:48:26"}
{"current_steps": 100, "total_steps": 252, "loss": 0.14641659259796141, "lr": 7.639109493149537e-05, "epoch": 1.191044776119403, "percentage": 39.68, "elapsed_time": "0:29:47", "remaining_time": "0:45:16"}
{"current_steps": 100, "total_steps": 252, "eval_loss": 0.1869809627532959, "epoch": 1.191044776119403, "percentage": 39.68, "elapsed_time": "0:30:00", "remaining_time": "0:45:37"}
{"current_steps": 110, "total_steps": 252, "loss": 0.11394469738006592, "lr": 7.02521368669762e-05, "epoch": 1.31044776119403, "percentage": 43.65, "elapsed_time": "0:32:56", "remaining_time": "0:42:30"}
{"current_steps": 120, "total_steps": 252, "loss": 0.11726579666137696, "lr": 6.372246903165446e-05, "epoch": 1.4298507462686567, "percentage": 47.62, "elapsed_time": "0:36:08", "remaining_time": "0:39:44"}
{"current_steps": 130, "total_steps": 252, "loss": 0.12615565061569214, "lr": 5.692806356566095e-05, "epoch": 1.5492537313432835, "percentage": 51.59, "elapsed_time": "0:39:02", "remaining_time": "0:36:38"}
{"current_steps": 140, "total_steps": 252, "loss": 0.11287055015563965, "lr": 5e-05, "epoch": 1.6686567164179105, "percentage": 55.56, "elapsed_time": "0:41:52", "remaining_time": "0:33:30"}
{"current_steps": 150, "total_steps": 252, "loss": 0.10663604736328125, "lr": 4.307193643433907e-05, "epoch": 1.7880597014925375, "percentage": 59.52, "elapsed_time": "0:45:19", "remaining_time": "0:30:48"}
{"current_steps": 160, "total_steps": 252, "loss": 0.107212233543396, "lr": 3.627753096834555e-05, "epoch": 1.9074626865671642, "percentage": 63.49, "elapsed_time": "0:48:27", "remaining_time": "0:27:51"}
{"current_steps": 170, "total_steps": 252, "loss": 0.11782596111297608, "lr": 2.9747863133023803e-05, "epoch": 2.023880597014925, "percentage": 67.46, "elapsed_time": "0:51:26", "remaining_time": "0:24:48"}
{"current_steps": 180, "total_steps": 252, "loss": 0.0834022581577301, "lr": 2.3608905068504637e-05, "epoch": 2.1432835820895524, "percentage": 71.43, "elapsed_time": "0:54:14", "remaining_time": "0:21:41"}
{"current_steps": 190, "total_steps": 252, "loss": 0.08206533193588257, "lr": 1.7979091235018565e-05, "epoch": 2.262686567164179, "percentage": 75.4, "elapsed_time": "0:57:31", "remaining_time": "0:18:46"}
{"current_steps": 200, "total_steps": 252, "loss": 0.08110529780387879, "lr": 1.2967033542853917e-05, "epoch": 2.382089552238806, "percentage": 79.37, "elapsed_time": "1:00:32", "remaining_time": "0:15:44"}
{"current_steps": 200, "total_steps": 252, "eval_loss": 0.1738630086183548, "epoch": 2.382089552238806, "percentage": 79.37, "elapsed_time": "1:00:45", "remaining_time": "0:15:47"}
{"current_steps": 210, "total_steps": 252, "loss": 0.08261927366256713, "lr": 8.669425981638413e-06, "epoch": 2.5014925373134327, "percentage": 83.33, "elapsed_time": "1:03:33", "remaining_time": "0:12:42"}
{"current_steps": 220, "total_steps": 252, "loss": 0.08233516216278076, "lr": 5.169179173410177e-06, "epoch": 2.62089552238806, "percentage": 87.3, "elapsed_time": "1:06:23", "remaining_time": "0:09:39"}
{"current_steps": 230, "total_steps": 252, "loss": 0.07825937271118164, "lr": 2.533820838190959e-06, "epoch": 2.7402985074626867, "percentage": 91.27, "elapsed_time": "1:09:29", "remaining_time": "0:06:38"}
{"current_steps": 240, "total_steps": 252, "loss": 0.08194915056228638, "lr": 8.141930307179468e-07, "epoch": 2.8597014925373134, "percentage": 95.24, "elapsed_time": "1:12:46", "remaining_time": "0:03:38"}
{"current_steps": 250, "total_steps": 252, "loss": 0.08224834203720092, "lr": 4.3471281599938295e-08, "epoch": 2.97910447761194, "percentage": 99.21, "elapsed_time": "1:15:55", "remaining_time": "0:00:36"}
{"current_steps": 252, "total_steps": 252, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:16:27", "remaining_time": "0:00:00"}