penfever commited on
Commit
df6ce52
·
verified ·
1 Parent(s): 6487cef

Training in progress, step 5400

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55e494e92dd17b4eed76a8e5c70ab0c77fa39279b6122cf82bbd64b7dba5c056
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3987c7c593d831001f89d71833f54726a38237873d0ac42b20277a5f820a3315
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:214616fbf87a73a9c4018a07f799ed8183b225d8bb6abddf5e5fed36c3c22b54
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00aa45e193f707b89bb958db9bf92931bfe43d5db1faec12e81f2c76753f6702
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8536a155a321858aafac2acbd7be14eb40155abdb29b9170626763decf5422dc
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:401c6c0b42c2fee55acf5a69bf5b435e8adb8aad13ab8bdc82bbb8be297c56d9
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2477f96b052a531c304cdbe7011f3d042991e9ed1f408226648c7cd8c47d41b
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d515c22ba6a5604a24385cb48cb634e5786f8e6dc30111d22de95b1b33cde34
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1041,3 +1041,42 @@
1041
  {"current_steps": 5205, "total_steps": 9128, "loss": 0.2257, "lr": 1.8597664695101455e-05, "epoch": 3.991944764096663, "percentage": 57.02, "elapsed_time": "1 day, 8:09:45", "remaining_time": "1 day, 0:14:27"}
1042
  {"current_steps": 5210, "total_steps": 9128, "loss": 0.228, "lr": 1.8559519253476598e-05, "epoch": 3.9957805907173, "percentage": 57.08, "elapsed_time": "1 day, 8:11:27", "remaining_time": "1 day, 0:12:29"}
1043
  {"current_steps": 5215, "total_steps": 9128, "loss": 0.2322, "lr": 1.8521379078471248e-05, "epoch": 3.9996164173379363, "percentage": 57.13, "elapsed_time": "1 day, 8:13:14", "remaining_time": "1 day, 0:10:35"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1041
  {"current_steps": 5205, "total_steps": 9128, "loss": 0.2257, "lr": 1.8597664695101455e-05, "epoch": 3.991944764096663, "percentage": 57.02, "elapsed_time": "1 day, 8:09:45", "remaining_time": "1 day, 0:14:27"}
1042
  {"current_steps": 5210, "total_steps": 9128, "loss": 0.228, "lr": 1.8559519253476598e-05, "epoch": 3.9957805907173, "percentage": 57.08, "elapsed_time": "1 day, 8:11:27", "remaining_time": "1 day, 0:12:29"}
1043
  {"current_steps": 5215, "total_steps": 9128, "loss": 0.2322, "lr": 1.8521379078471248e-05, "epoch": 3.9996164173379363, "percentage": 57.13, "elapsed_time": "1 day, 8:13:14", "remaining_time": "1 day, 0:10:35"}
1044
+ {"current_steps": 5220, "total_steps": 9128, "loss": 0.1776, "lr": 1.848324430953177e-05, "epoch": 4.003068661296509, "percentage": 57.19, "elapsed_time": "1 day, 8:15:51", "remaining_time": "1 day, 0:09:18"}
1045
+ {"current_steps": 5225, "total_steps": 9128, "loss": 0.1918, "lr": 1.8445115086084756e-05, "epoch": 4.006904487917146, "percentage": 57.24, "elapsed_time": "1 day, 8:18:54", "remaining_time": "1 day, 0:08:20"}
1046
+ {"current_steps": 5230, "total_steps": 9128, "loss": 0.1841, "lr": 1.8406991547536514e-05, "epoch": 4.010740314537783, "percentage": 57.3, "elapsed_time": "1 day, 8:21:35", "remaining_time": "1 day, 0:07:06"}
1047
+ {"current_steps": 5235, "total_steps": 9128, "loss": 0.177, "lr": 1.8368873833272574e-05, "epoch": 4.01457614115842, "percentage": 57.35, "elapsed_time": "1 day, 8:24:40", "remaining_time": "1 day, 0:06:09"}
1048
+ {"current_steps": 5240, "total_steps": 9128, "loss": 0.184, "lr": 1.8330762082657185e-05, "epoch": 4.018411967779056, "percentage": 57.41, "elapsed_time": "1 day, 8:27:42", "remaining_time": "1 day, 0:05:10"}
1049
+ {"current_steps": 5245, "total_steps": 9128, "loss": 0.1859, "lr": 1.8292656435032762e-05, "epoch": 4.022247794399693, "percentage": 57.46, "elapsed_time": "1 day, 8:30:47", "remaining_time": "1 day, 0:04:12"}
1050
+ {"current_steps": 5250, "total_steps": 9128, "loss": 0.1947, "lr": 1.8254557029719424e-05, "epoch": 4.02608362102033, "percentage": 57.52, "elapsed_time": "1 day, 8:33:43", "remaining_time": "1 day, 0:03:09"}
1051
+ {"current_steps": 5255, "total_steps": 9128, "loss": 0.1817, "lr": 1.821646400601448e-05, "epoch": 4.0299194476409665, "percentage": 57.57, "elapsed_time": "1 day, 8:36:40", "remaining_time": "1 day, 0:02:05"}
1052
+ {"current_steps": 5260, "total_steps": 9128, "loss": 0.1771, "lr": 1.8178377503191875e-05, "epoch": 4.033755274261603, "percentage": 57.62, "elapsed_time": "1 day, 8:39:22", "remaining_time": "1 day, 0:00:50"}
1053
+ {"current_steps": 5265, "total_steps": 9128, "loss": 0.1634, "lr": 1.8140297660501745e-05, "epoch": 4.03759110088224, "percentage": 57.68, "elapsed_time": "1 day, 8:41:57", "remaining_time": "23:59:31"}
1054
+ {"current_steps": 5270, "total_steps": 9128, "loss": 0.1824, "lr": 1.8102224617169855e-05, "epoch": 4.041426927502877, "percentage": 57.73, "elapsed_time": "1 day, 8:44:48", "remaining_time": "23:58:22"}
1055
+ {"current_steps": 5275, "total_steps": 9128, "loss": 0.1711, "lr": 1.8064158512397112e-05, "epoch": 4.045262754123514, "percentage": 57.79, "elapsed_time": "1 day, 8:47:35", "remaining_time": "23:57:11"}
1056
+ {"current_steps": 5280, "total_steps": 9128, "loss": 0.1777, "lr": 1.802609948535907e-05, "epoch": 4.04909858074415, "percentage": 57.84, "elapsed_time": "1 day, 8:50:27", "remaining_time": "23:56:02"}
1057
+ {"current_steps": 5285, "total_steps": 9128, "loss": 0.1712, "lr": 1.798804767520539e-05, "epoch": 4.052934407364787, "percentage": 57.9, "elapsed_time": "1 day, 8:53:17", "remaining_time": "23:54:53"}
1058
+ {"current_steps": 5290, "total_steps": 9128, "loss": 0.1736, "lr": 1.795000322105934e-05, "epoch": 4.056770233985424, "percentage": 57.95, "elapsed_time": "1 day, 8:55:56", "remaining_time": "23:53:35"}
1059
+ {"current_steps": 5295, "total_steps": 9128, "loss": 0.1798, "lr": 1.7911966262017327e-05, "epoch": 4.0606060606060606, "percentage": 58.01, "elapsed_time": "1 day, 8:58:43", "remaining_time": "23:52:22"}
1060
+ {"current_steps": 5300, "total_steps": 9128, "loss": 0.172, "lr": 1.7873936937148312e-05, "epoch": 4.064441887226697, "percentage": 58.06, "elapsed_time": "1 day, 9:01:32", "remaining_time": "23:51:11"}
1061
+ {"current_steps": 5305, "total_steps": 9128, "loss": 0.1794, "lr": 1.783591538549338e-05, "epoch": 4.068277713847334, "percentage": 58.12, "elapsed_time": "1 day, 9:04:28", "remaining_time": "23:50:05"}
1062
+ {"current_steps": 5310, "total_steps": 9128, "loss": 0.1915, "lr": 1.779790174606518e-05, "epoch": 4.072113540467971, "percentage": 58.17, "elapsed_time": "1 day, 9:07:17", "remaining_time": "23:48:54"}
1063
+ {"current_steps": 5315, "total_steps": 9128, "loss": 0.1728, "lr": 1.775989615784742e-05, "epoch": 4.075949367088608, "percentage": 58.23, "elapsed_time": "1 day, 9:09:42", "remaining_time": "23:47:25"}
1064
+ {"current_steps": 5320, "total_steps": 9128, "loss": 0.1618, "lr": 1.77218987597944e-05, "epoch": 4.079785193709244, "percentage": 58.28, "elapsed_time": "1 day, 9:12:35", "remaining_time": "23:46:16"}
1065
+ {"current_steps": 5325, "total_steps": 9128, "loss": 0.1743, "lr": 1.768390969083046e-05, "epoch": 4.083621020329881, "percentage": 58.34, "elapsed_time": "1 day, 9:15:29", "remaining_time": "23:45:08"}
1066
+ {"current_steps": 5330, "total_steps": 9128, "loss": 0.1715, "lr": 1.7645929089849476e-05, "epoch": 4.087456846950518, "percentage": 58.39, "elapsed_time": "1 day, 9:18:15", "remaining_time": "23:43:53"}
1067
+ {"current_steps": 5335, "total_steps": 9128, "loss": 0.1803, "lr": 1.760795709571438e-05, "epoch": 4.091292673571155, "percentage": 58.45, "elapsed_time": "1 day, 9:21:08", "remaining_time": "23:42:44"}
1068
+ {"current_steps": 5340, "total_steps": 9128, "loss": 0.1701, "lr": 1.756999384725665e-05, "epoch": 4.095128500191791, "percentage": 58.5, "elapsed_time": "1 day, 9:24:09", "remaining_time": "23:41:40"}
1069
+ {"current_steps": 5345, "total_steps": 9128, "loss": 0.1645, "lr": 1.753203948327575e-05, "epoch": 4.098964326812428, "percentage": 58.56, "elapsed_time": "1 day, 9:27:11", "remaining_time": "23:40:37"}
1070
+ {"current_steps": 5350, "total_steps": 9128, "loss": 0.1528, "lr": 1.7494094142538697e-05, "epoch": 4.102800153433065, "percentage": 58.61, "elapsed_time": "1 day, 9:30:12", "remaining_time": "23:39:32"}
1071
+ {"current_steps": 5355, "total_steps": 9128, "loss": 0.1539, "lr": 1.7456157963779478e-05, "epoch": 4.106635980053702, "percentage": 58.67, "elapsed_time": "1 day, 9:33:06", "remaining_time": "23:38:23"}
1072
+ {"current_steps": 5360, "total_steps": 9128, "loss": 0.1805, "lr": 1.741823108569863e-05, "epoch": 4.110471806674338, "percentage": 58.72, "elapsed_time": "1 day, 9:35:52", "remaining_time": "23:37:07"}
1073
+ {"current_steps": 5365, "total_steps": 9128, "loss": 0.1628, "lr": 1.738031364696266e-05, "epoch": 4.114307633294975, "percentage": 58.78, "elapsed_time": "1 day, 9:38:09", "remaining_time": "23:35:31"}
1074
+ {"current_steps": 5370, "total_steps": 9128, "loss": 0.182, "lr": 1.7342405786203546e-05, "epoch": 4.118143459915612, "percentage": 58.83, "elapsed_time": "1 day, 9:40:56", "remaining_time": "23:34:17"}
1075
+ {"current_steps": 5375, "total_steps": 9128, "loss": 0.188, "lr": 1.7304507642018285e-05, "epoch": 4.121979286536249, "percentage": 58.88, "elapsed_time": "1 day, 9:43:52", "remaining_time": "23:33:07"}
1076
+ {"current_steps": 5380, "total_steps": 9128, "loss": 0.1808, "lr": 1.726661935296833e-05, "epoch": 4.125815113156885, "percentage": 58.94, "elapsed_time": "1 day, 9:46:43", "remaining_time": "23:31:55"}
1077
+ {"current_steps": 5385, "total_steps": 9128, "loss": 0.1745, "lr": 1.7228741057579096e-05, "epoch": 4.129650939777522, "percentage": 58.99, "elapsed_time": "1 day, 9:49:36", "remaining_time": "23:30:44"}
1078
+ {"current_steps": 5390, "total_steps": 9128, "loss": 0.1828, "lr": 1.7190872894339465e-05, "epoch": 4.133486766398159, "percentage": 59.05, "elapsed_time": "1 day, 9:52:37", "remaining_time": "23:29:38"}
1079
+ {"current_steps": 5395, "total_steps": 9128, "loss": 0.1758, "lr": 1.7153015001701284e-05, "epoch": 4.137322593018795, "percentage": 59.1, "elapsed_time": "1 day, 9:55:38", "remaining_time": "23:28:32"}
1080
+ {"current_steps": 5400, "total_steps": 9128, "loss": 0.1786, "lr": 1.711516751807883e-05, "epoch": 4.141158419639432, "percentage": 59.16, "elapsed_time": "1 day, 9:58:37", "remaining_time": "23:27:24"}
1081
+ {"current_steps": 5405, "total_steps": 9128, "loss": 0.1811, "lr": 1.7077330581848336e-05, "epoch": 4.144994246260069, "percentage": 59.21, "elapsed_time": "1 day, 10:02:56", "remaining_time": "23:27:11"}
1082
+ {"current_steps": 5410, "total_steps": 9128, "loss": 0.1815, "lr": 1.7039504331347477e-05, "epoch": 4.148830072880706, "percentage": 59.27, "elapsed_time": "1 day, 10:05:50", "remaining_time": "23:25:59"}