neginr commited on
Commit
efa1155
·
verified ·
1 Parent(s): 40c9700

Training in progress, epoch 3

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e30d8c6ac9906c2a0088e7940bd5c25c4a741dbfa8f373c1a3edadd1c820d62
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d968706c0cbfea8b57dcddb57f911b98e41cf52578d243c6cbf0293679cf5f1d
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f3ce578d25c0a3a611cd6d71550ee026136753f2b847e5022ee233c631b18f6
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14ad7269dc876aca26017f335dbcf2dcdcb23e7748dce30f8705d8259538fff
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e1298cba8b441aab5182506fb28d893ed86d3983fddf1cefe03e313d57ae2cb
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c836a79b528007d071b1c04899130b7932935d5fc092e7bdb86315c5814e35
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b1d422649a297622d234564a14d57867e6ce1dd51df14316d06c0cb8a32e7a7
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bebfed837af877d5462afe1d8815c717536a23ab35150f4ca619665fb3cbe77
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -88,3 +88,33 @@
88
  {"current_steps": 88, "total_steps": 145, "loss": 0.6195, "lr": 3.231493130585167e-05, "epoch": 2.951983298538622, "percentage": 60.69, "elapsed_time": "2:34:41", "remaining_time": "1:40:11"}
89
  {"current_steps": 89, "total_steps": 145, "loss": 0.6214, "lr": 3.136863212928776e-05, "epoch": 2.9853862212943634, "percentage": 61.38, "elapsed_time": "2:36:22", "remaining_time": "1:38:23"}
90
  {"current_steps": 90, "total_steps": 145, "loss": 0.5892, "lr": 3.0427373428497704e-05, "epoch": 3.0250521920668056, "percentage": 62.07, "elapsed_time": "2:39:57", "remaining_time": "1:37:45"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 88, "total_steps": 145, "loss": 0.6195, "lr": 3.231493130585167e-05, "epoch": 2.951983298538622, "percentage": 60.69, "elapsed_time": "2:34:41", "remaining_time": "1:40:11"}
89
  {"current_steps": 89, "total_steps": 145, "loss": 0.6214, "lr": 3.136863212928776e-05, "epoch": 2.9853862212943634, "percentage": 61.38, "elapsed_time": "2:36:22", "remaining_time": "1:38:23"}
90
  {"current_steps": 90, "total_steps": 145, "loss": 0.5892, "lr": 3.0427373428497704e-05, "epoch": 3.0250521920668056, "percentage": 62.07, "elapsed_time": "2:39:57", "remaining_time": "1:37:45"}
91
+ {"current_steps": 91, "total_steps": 145, "loss": 0.5744, "lr": 2.9491704872056525e-05, "epoch": 3.058455114822547, "percentage": 62.76, "elapsed_time": "2:41:39", "remaining_time": "1:35:55"}
92
+ {"current_steps": 90, "total_steps": 145, "loss": 0.5792, "lr": 3.0427373428497704e-05, "epoch": 3.1002087682672235, "percentage": 62.07, "elapsed_time": "0:01:53", "remaining_time": "0:01:09"}
93
+ {"current_steps": 91, "total_steps": 145, "loss": 0.571, "lr": 2.9491704872056525e-05, "epoch": 3.1336116910229643, "percentage": 62.76, "elapsed_time": "0:03:35", "remaining_time": "0:02:08"}
94
+ {"current_steps": 92, "total_steps": 145, "loss": 0.5665, "lr": 2.8562172864052437e-05, "epoch": 3.1670146137787056, "percentage": 63.45, "elapsed_time": "0:05:20", "remaining_time": "0:03:04"}
95
+ {"current_steps": 93, "total_steps": 145, "loss": 0.5734, "lr": 2.7639320225002108e-05, "epoch": 3.200417536534447, "percentage": 64.14, "elapsed_time": "0:07:04", "remaining_time": "0:03:57"}
96
+ {"current_steps": 94, "total_steps": 145, "loss": 0.5665, "lr": 2.6723685874858873e-05, "epoch": 3.233820459290188, "percentage": 64.83, "elapsed_time": "0:08:48", "remaining_time": "0:04:46"}
97
+ {"current_steps": 95, "total_steps": 145, "loss": 0.5649, "lr": 2.5815804518298575e-05, "epoch": 3.267223382045929, "percentage": 65.52, "elapsed_time": "0:10:33", "remaining_time": "0:05:33"}
98
+ {"current_steps": 96, "total_steps": 145, "loss": 0.5626, "lr": 2.4916206332467184e-05, "epoch": 3.30062630480167, "percentage": 66.21, "elapsed_time": "0:12:17", "remaining_time": "0:06:16"}
99
+ {"current_steps": 97, "total_steps": 145, "loss": 0.5672, "lr": 2.4025416657372186e-05, "epoch": 3.3340292275574113, "percentage": 66.9, "elapsed_time": "0:14:00", "remaining_time": "0:06:56"}
100
+ {"current_steps": 98, "total_steps": 145, "loss": 0.5701, "lr": 2.3143955689098844e-05, "epoch": 3.3674321503131526, "percentage": 67.59, "elapsed_time": "0:15:44", "remaining_time": "0:07:33"}
101
+ {"current_steps": 99, "total_steps": 145, "loss": 0.5648, "lr": 2.2272338176030354e-05, "epoch": 3.4008350730688934, "percentage": 68.28, "elapsed_time": "0:17:28", "remaining_time": "0:08:07"}
102
+ {"current_steps": 100, "total_steps": 145, "loss": 0.5637, "lr": 2.141107311824926e-05, "epoch": 3.4342379958246347, "percentage": 68.97, "elapsed_time": "0:19:12", "remaining_time": "0:08:38"}
103
+ {"current_steps": 101, "total_steps": 145, "loss": 0.5698, "lr": 2.056066347029576e-05, "epoch": 3.4676409185803756, "percentage": 69.66, "elapsed_time": "0:20:56", "remaining_time": "0:09:07"}
104
+ {"current_steps": 102, "total_steps": 145, "loss": 0.5678, "lr": 1.9721605847456397e-05, "epoch": 3.501043841336117, "percentage": 70.34, "elapsed_time": "0:22:39", "remaining_time": "0:09:32"}
105
+ {"current_steps": 103, "total_steps": 145, "loss": 0.5687, "lr": 1.8894390235754686e-05, "epoch": 3.534446764091858, "percentage": 71.03, "elapsed_time": "0:24:22", "remaining_time": "0:09:56"}
106
+ {"current_steps": 104, "total_steps": 145, "loss": 0.5612, "lr": 1.807949970581321e-05, "epoch": 3.567849686847599, "percentage": 71.72, "elapsed_time": "0:26:07", "remaining_time": "0:10:17"}
107
+ {"current_steps": 105, "total_steps": 145, "loss": 0.5621, "lr": 1.7277410130753775e-05, "epoch": 3.6012526096033404, "percentage": 72.41, "elapsed_time": "0:27:50", "remaining_time": "0:10:36"}
108
+ {"current_steps": 106, "total_steps": 145, "loss": 0.5602, "lr": 1.648858990830108e-05, "epoch": 3.6346555323590817, "percentage": 73.1, "elapsed_time": "0:29:33", "remaining_time": "0:10:52"}
109
+ {"current_steps": 107, "total_steps": 145, "loss": 0.5625, "lr": 1.5713499687251554e-05, "epoch": 3.6680584551148225, "percentage": 73.79, "elapsed_time": "0:31:17", "remaining_time": "0:11:06"}
110
+ {"current_steps": 108, "total_steps": 145, "loss": 0.5566, "lr": 1.4952592098467453e-05, "epoch": 3.701461377870564, "percentage": 74.48, "elapsed_time": "0:33:01", "remaining_time": "0:11:18"}
111
+ {"current_steps": 109, "total_steps": 145, "loss": 0.5563, "lr": 1.4206311490553187e-05, "epoch": 3.7348643006263047, "percentage": 75.17, "elapsed_time": "0:34:43", "remaining_time": "0:11:28"}
112
+ {"current_steps": 110, "total_steps": 145, "loss": 0.5642, "lr": 1.3475093670368202e-05, "epoch": 3.768267223382046, "percentage": 75.86, "elapsed_time": "0:36:27", "remaining_time": "0:11:36"}
113
+ {"current_steps": 111, "total_steps": 145, "loss": 0.5619, "lr": 1.275936564852811e-05, "epoch": 3.801670146137787, "percentage": 76.55, "elapsed_time": "0:38:10", "remaining_time": "0:11:41"}
114
+ {"current_steps": 112, "total_steps": 145, "loss": 0.5627, "lr": 1.2059545390042526e-05, "epoch": 3.835073068893528, "percentage": 77.24, "elapsed_time": "0:39:55", "remaining_time": "0:11:45"}
115
+ {"current_steps": 113, "total_steps": 145, "loss": 0.5597, "lr": 1.1376041570235162e-05, "epoch": 3.8684759916492695, "percentage": 77.93, "elapsed_time": "0:41:37", "remaining_time": "0:11:47"}
116
+ {"current_steps": 114, "total_steps": 145, "loss": 0.5646, "lr": 1.070925333608907e-05, "epoch": 3.9018789144050103, "percentage": 78.62, "elapsed_time": "0:43:22", "remaining_time": "0:11:47"}
117
+ {"current_steps": 115, "total_steps": 145, "loss": 0.5663, "lr": 1.0059570073155953e-05, "epoch": 3.9352818371607516, "percentage": 79.31, "elapsed_time": "0:45:05", "remaining_time": "0:11:45"}
118
+ {"current_steps": 116, "total_steps": 145, "loss": 0.5628, "lr": 9.427371178166065e-06, "epoch": 3.968684759916493, "percentage": 80.0, "elapsed_time": "0:46:50", "remaining_time": "0:11:42"}
119
+ {"current_steps": 117, "total_steps": 145, "loss": 0.5657, "lr": 8.81302583747111e-06, "epoch": 4.002087682672234, "percentage": 80.69, "elapsed_time": "0:50:27", "remaining_time": "0:12:04"}
120
+ {"current_steps": 118, "total_steps": 145, "loss": 0.5431, "lr": 8.216892811449834e-06, "epoch": 4.035490605427975, "percentage": 81.38, "elapsed_time": "0:52:08", "remaining_time": "0:11:55"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:432f21c0023de5964fdaaabc9bd735905b6086caef723fada8215e998cb31bf4
3
- size 7352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93cbfa6dfb89b131018cef7d27341a129af9a9ecebe0cdb130c945c8576e216f
3
+ size 7416