ahmedheakl commited on
Commit
e0aa382
·
verified ·
1 Parent(s): c647947

Training in progress, step 236500

Browse files
Files changed (2) hide show
  1. model.safetensors +1 -1
  2. trainer_log.jsonl +51 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74dabfc8c99dce14d5584be6ff2d0222f36f1830873bb6979cae68676c2abd2e
3
  size 1260367448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d41445744208de8f93510b990d6a65e015d0e1d1cf8a2c9e5fe2110c0a3110b
3
  size 1260367448
trainer_log.jsonl CHANGED
@@ -23610,3 +23610,54 @@
23610
  {"current_steps": 236070, "total_steps": 236854, "loss": 0.0074, "lr": 3.337513466650233e-10, "epoch": 1.9933714719976356, "percentage": 99.67, "elapsed_time": "1 day, 2:39:10", "remaining_time": "0:05:18"}
23611
  {"current_steps": 236080, "total_steps": 236854, "loss": 0.0093, "lr": 3.252916723134325e-10, "epoch": 1.9934559118447996, "percentage": 99.67, "elapsed_time": "1 day, 2:39:15", "remaining_time": "0:05:14"}
23612
  {"current_steps": 236090, "total_steps": 236854, "loss": 0.0082, "lr": 3.169405898723055e-10, "epoch": 1.9935403516919634, "percentage": 99.68, "elapsed_time": "1 day, 2:39:19", "remaining_time": "0:05:10"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23610
  {"current_steps": 236070, "total_steps": 236854, "loss": 0.0074, "lr": 3.337513466650233e-10, "epoch": 1.9933714719976356, "percentage": 99.67, "elapsed_time": "1 day, 2:39:10", "remaining_time": "0:05:18"}
23611
  {"current_steps": 236080, "total_steps": 236854, "loss": 0.0093, "lr": 3.252916723134325e-10, "epoch": 1.9934559118447996, "percentage": 99.67, "elapsed_time": "1 day, 2:39:15", "remaining_time": "0:05:14"}
23612
  {"current_steps": 236090, "total_steps": 236854, "loss": 0.0082, "lr": 3.169405898723055e-10, "epoch": 1.9935403516919634, "percentage": 99.68, "elapsed_time": "1 day, 2:39:19", "remaining_time": "0:05:10"}
23613
+ {"current_steps": 236100, "total_steps": 236854, "loss": 0.0073, "lr": 3.086980995226085e-10, "epoch": 1.9936247915391272, "percentage": 99.68, "elapsed_time": "1 day, 2:39:25", "remaining_time": "0:05:06"}
23614
+ {"current_steps": 236110, "total_steps": 236854, "loss": 0.0054, "lr": 3.0056420144364274e-10, "epoch": 1.9937092313862912, "percentage": 99.69, "elapsed_time": "1 day, 2:39:29", "remaining_time": "0:05:02"}
23615
+ {"current_steps": 236120, "total_steps": 236854, "loss": 0.0034, "lr": 2.925388958119335e-10, "epoch": 1.9937936712334552, "percentage": 99.69, "elapsed_time": "1 day, 2:39:32", "remaining_time": "0:04:58"}
23616
+ {"current_steps": 236130, "total_steps": 236854, "loss": 0.0048, "lr": 2.846221828012308e-10, "epoch": 1.993878111080619, "percentage": 99.69, "elapsed_time": "1 day, 2:39:36", "remaining_time": "0:04:54"}
23617
+ {"current_steps": 236140, "total_steps": 236854, "loss": 0.0058, "lr": 2.768140625841742e-10, "epoch": 1.9939625509277827, "percentage": 99.7, "elapsed_time": "1 day, 2:39:40", "remaining_time": "0:04:50"}
23618
+ {"current_steps": 236150, "total_steps": 236854, "loss": 0.0041, "lr": 2.691145353306279e-10, "epoch": 1.9940469907749467, "percentage": 99.7, "elapsed_time": "1 day, 2:39:44", "remaining_time": "0:04:46"}
23619
+ {"current_steps": 236160, "total_steps": 236854, "loss": 0.0084, "lr": 2.615236012071254e-10, "epoch": 1.9941314306221107, "percentage": 99.71, "elapsed_time": "1 day, 2:39:47", "remaining_time": "0:04:42"}
23620
+ {"current_steps": 236170, "total_steps": 236854, "loss": 0.0022, "lr": 2.540412603785347e-10, "epoch": 1.9942158704692745, "percentage": 99.71, "elapsed_time": "1 day, 2:39:50", "remaining_time": "0:04:38"}
23621
+ {"current_steps": 236180, "total_steps": 236854, "loss": 0.0054, "lr": 2.466675130080587e-10, "epoch": 1.9943003103164383, "percentage": 99.72, "elapsed_time": "1 day, 2:39:54", "remaining_time": "0:04:33"}
23622
+ {"current_steps": 236190, "total_steps": 236854, "loss": 0.0033, "lr": 2.394023592550143e-10, "epoch": 1.994384750163602, "percentage": 99.72, "elapsed_time": "1 day, 2:39:57", "remaining_time": "0:04:29"}
23623
+ {"current_steps": 236200, "total_steps": 236854, "loss": 0.0065, "lr": 2.3224579927760836e-10, "epoch": 1.994469190010766, "percentage": 99.72, "elapsed_time": "1 day, 2:40:01", "remaining_time": "0:04:25"}
23624
+ {"current_steps": 236210, "total_steps": 236854, "loss": 0.0044, "lr": 2.251978332312721e-10, "epoch": 1.99455362985793, "percentage": 99.73, "elapsed_time": "1 day, 2:40:04", "remaining_time": "0:04:21"}
23625
+ {"current_steps": 236220, "total_steps": 236854, "loss": 0.0128, "lr": 2.1825846126921623e-10, "epoch": 1.9946380697050938, "percentage": 99.73, "elapsed_time": "1 day, 2:40:08", "remaining_time": "0:04:17"}
23626
+ {"current_steps": 236230, "total_steps": 236854, "loss": 0.0081, "lr": 2.1142768354243116e-10, "epoch": 1.9947225095522576, "percentage": 99.74, "elapsed_time": "1 day, 2:40:12", "remaining_time": "0:04:13"}
23627
+ {"current_steps": 236240, "total_steps": 236854, "loss": 0.0057, "lr": 2.047055001985765e-10, "epoch": 1.9948069493994216, "percentage": 99.74, "elapsed_time": "1 day, 2:40:16", "remaining_time": "0:04:09"}
23628
+ {"current_steps": 236250, "total_steps": 236854, "loss": 0.0089, "lr": 1.9809191138364658e-10, "epoch": 1.9948913892465856, "percentage": 99.74, "elapsed_time": "1 day, 2:40:20", "remaining_time": "0:04:05"}
23629
+ {"current_steps": 236260, "total_steps": 236854, "loss": 0.0059, "lr": 1.9158691724197042e-10, "epoch": 1.9949758290937494, "percentage": 99.75, "elapsed_time": "1 day, 2:40:24", "remaining_time": "0:04:01"}
23630
+ {"current_steps": 236270, "total_steps": 236854, "loss": 0.0079, "lr": 1.8519051791454633e-10, "epoch": 1.9950602689409132, "percentage": 99.75, "elapsed_time": "1 day, 2:40:28", "remaining_time": "0:03:57"}
23631
+ {"current_steps": 236280, "total_steps": 236854, "loss": 0.003, "lr": 1.789027135395971e-10, "epoch": 1.9951447087880771, "percentage": 99.76, "elapsed_time": "1 day, 2:40:32", "remaining_time": "0:03:53"}
23632
+ {"current_steps": 236290, "total_steps": 236854, "loss": 0.0087, "lr": 1.7272350425479035e-10, "epoch": 1.995229148635241, "percentage": 99.76, "elapsed_time": "1 day, 2:40:36", "remaining_time": "0:03:49"}
23633
+ {"current_steps": 236300, "total_steps": 236854, "loss": 0.0115, "lr": 1.6665289019390795e-10, "epoch": 1.995313588482405, "percentage": 99.77, "elapsed_time": "1 day, 2:40:41", "remaining_time": "0:03:45"}
23634
+ {"current_steps": 236310, "total_steps": 236854, "loss": 0.0052, "lr": 1.6069087148851137e-10, "epoch": 1.9953980283295687, "percentage": 99.77, "elapsed_time": "1 day, 2:40:45", "remaining_time": "0:03:41"}
23635
+ {"current_steps": 236320, "total_steps": 236854, "loss": 0.0089, "lr": 1.5483744826849668e-10, "epoch": 1.9954824681767325, "percentage": 99.77, "elapsed_time": "1 day, 2:40:49", "remaining_time": "0:03:37"}
23636
+ {"current_steps": 236330, "total_steps": 236854, "loss": 0.0097, "lr": 1.490926206609844e-10, "epoch": 1.9955669080238965, "percentage": 99.78, "elapsed_time": "1 day, 2:40:53", "remaining_time": "0:03:32"}
23637
+ {"current_steps": 236340, "total_steps": 236854, "loss": 0.0049, "lr": 1.4345638879087464e-10, "epoch": 1.9956513478710605, "percentage": 99.78, "elapsed_time": "1 day, 2:40:56", "remaining_time": "0:03:28"}
23638
+ {"current_steps": 236350, "total_steps": 236854, "loss": 0.0085, "lr": 1.3792875277973683e-10, "epoch": 1.9957357877182242, "percentage": 99.79, "elapsed_time": "1 day, 2:41:00", "remaining_time": "0:03:24"}
23639
+ {"current_steps": 236360, "total_steps": 236854, "loss": 0.0041, "lr": 1.3250971274858525e-10, "epoch": 1.995820227565388, "percentage": 99.79, "elapsed_time": "1 day, 2:41:04", "remaining_time": "0:03:20"}
23640
+ {"current_steps": 236370, "total_steps": 236854, "loss": 0.0034, "lr": 1.2719926881454848e-10, "epoch": 1.995904667412552, "percentage": 99.8, "elapsed_time": "1 day, 2:41:08", "remaining_time": "0:03:16"}
23641
+ {"current_steps": 236380, "total_steps": 236854, "loss": 0.0077, "lr": 1.2199742109308966e-10, "epoch": 1.995989107259716, "percentage": 99.8, "elapsed_time": "1 day, 2:41:11", "remaining_time": "0:03:12"}
23642
+ {"current_steps": 236390, "total_steps": 236854, "loss": 0.0048, "lr": 1.1690416969745155e-10, "epoch": 1.9960735471068798, "percentage": 99.8, "elapsed_time": "1 day, 2:41:15", "remaining_time": "0:03:08"}
23643
+ {"current_steps": 236400, "total_steps": 236854, "loss": 0.0082, "lr": 1.1191951473810137e-10, "epoch": 1.9961579869540436, "percentage": 99.81, "elapsed_time": "1 day, 2:41:19", "remaining_time": "0:03:04"}
23644
+ {"current_steps": 236410, "total_steps": 236854, "loss": 0.0055, "lr": 1.0704345632328583e-10, "epoch": 1.9962424268012073, "percentage": 99.81, "elapsed_time": "1 day, 2:41:24", "remaining_time": "0:03:00"}
23645
+ {"current_steps": 236420, "total_steps": 236854, "loss": 0.0075, "lr": 1.0227599455847614e-10, "epoch": 1.9963268666483713, "percentage": 99.82, "elapsed_time": "1 day, 2:41:27", "remaining_time": "0:02:56"}
23646
+ {"current_steps": 236430, "total_steps": 236854, "loss": 0.0093, "lr": 9.761712954803326e-11, "epoch": 1.9964113064955353, "percentage": 99.82, "elapsed_time": "1 day, 2:41:31", "remaining_time": "0:02:52"}
23647
+ {"current_steps": 236440, "total_steps": 236854, "loss": 0.0056, "lr": 9.306686139298749e-11, "epoch": 1.996495746342699, "percentage": 99.83, "elapsed_time": "1 day, 2:41:35", "remaining_time": "0:02:48"}
23648
+ {"current_steps": 236450, "total_steps": 236854, "loss": 0.0033, "lr": 8.862519019159355e-11, "epoch": 1.9965801861898629, "percentage": 99.83, "elapsed_time": "1 day, 2:41:38", "remaining_time": "0:02:44"}
23649
+ {"current_steps": 236460, "total_steps": 236854, "loss": 0.0065, "lr": 8.429211604099597e-11, "epoch": 1.9966646260370269, "percentage": 99.83, "elapsed_time": "1 day, 2:41:41", "remaining_time": "0:02:40"}
23650
+ {"current_steps": 236470, "total_steps": 236854, "loss": 0.0062, "lr": 8.006763903445347e-11, "epoch": 1.9967490658841909, "percentage": 99.84, "elapsed_time": "1 day, 2:41:45", "remaining_time": "0:02:36"}
23651
+ {"current_steps": 236480, "total_steps": 236854, "loss": 0.0055, "lr": 7.595175926466969e-11, "epoch": 1.9968335057313547, "percentage": 99.84, "elapsed_time": "1 day, 2:41:48", "remaining_time": "0:02:31"}
23652
+ {"current_steps": 236490, "total_steps": 236854, "loss": 0.0124, "lr": 7.194447682046246e-11, "epoch": 1.9969179455785184, "percentage": 99.85, "elapsed_time": "1 day, 2:41:52", "remaining_time": "0:02:27"}
23653
+ {"current_steps": 236500, "total_steps": 236854, "loss": 0.0102, "lr": 6.80457917895394e-11, "epoch": 1.9970023854256824, "percentage": 99.85, "elapsed_time": "1 day, 2:41:57", "remaining_time": "0:02:23"}
23654
+ {"current_steps": 236510, "total_steps": 236854, "loss": 0.0051, "lr": 6.425570425572236e-11, "epoch": 1.9970868252728464, "percentage": 99.85, "elapsed_time": "1 day, 2:42:09", "remaining_time": "0:02:19"}
23655
+ {"current_steps": 236520, "total_steps": 236854, "loss": 0.0086, "lr": 6.057421430172295e-11, "epoch": 1.9971712651200102, "percentage": 99.86, "elapsed_time": "1 day, 2:42:13", "remaining_time": "0:02:15"}
23656
+ {"current_steps": 236530, "total_steps": 236854, "loss": 0.0071, "lr": 5.70013220069221e-11, "epoch": 1.997255704967174, "percentage": 99.86, "elapsed_time": "1 day, 2:42:18", "remaining_time": "0:02:11"}
23657
+ {"current_steps": 236540, "total_steps": 236854, "loss": 0.0062, "lr": 5.353702745014566e-11, "epoch": 1.9973401448143377, "percentage": 99.87, "elapsed_time": "1 day, 2:42:22", "remaining_time": "0:02:07"}
23658
+ {"current_steps": 236550, "total_steps": 236854, "loss": 0.008, "lr": 5.018133070577858e-11, "epoch": 1.9974245846615017, "percentage": 99.87, "elapsed_time": "1 day, 2:42:26", "remaining_time": "0:02:03"}
23659
+ {"current_steps": 236560, "total_steps": 236854, "loss": 0.0078, "lr": 4.693423184709556e-11, "epoch": 1.9975090245086657, "percentage": 99.88, "elapsed_time": "1 day, 2:42:30", "remaining_time": "0:01:59"}
23660
+ {"current_steps": 236570, "total_steps": 236854, "loss": 0.0049, "lr": 4.379573094404066e-11, "epoch": 1.9975934643558295, "percentage": 99.88, "elapsed_time": "1 day, 2:42:34", "remaining_time": "0:01:55"}
23661
+ {"current_steps": 236580, "total_steps": 236854, "loss": 0.0065, "lr": 4.0765828065447713e-11, "epoch": 1.9976779042029933, "percentage": 99.88, "elapsed_time": "1 day, 2:42:39", "remaining_time": "0:01:51"}
23662
+ {"current_steps": 236590, "total_steps": 236854, "loss": 0.0028, "lr": 3.7844523276264756e-11, "epoch": 1.9977623440501573, "percentage": 99.89, "elapsed_time": "1 day, 2:42:43", "remaining_time": "0:01:47"}
23663
+ {"current_steps": 236600, "total_steps": 236854, "loss": 0.0069, "lr": 3.503181664088473e-11, "epoch": 1.9978467838973213, "percentage": 99.89, "elapsed_time": "1 day, 2:42:47", "remaining_time": "0:01:43"}