ryanmarten commited on
Commit
6d243d7
·
verified ·
1 Parent(s): 7222c6b

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 sha256:57f4fa21337cc1317217dafc3985d6ab800347ca811acdf26699e92561305158
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5308826e87e55336e5bc0ac8f6118ecb61a2fa6c4bbd460bf1a41d18cf97e6f
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:eeeb44868eff67f02ef9559b47dfa4887285cc904d78594b1405b9864fa0a5c7
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f48b1c1579ac1febf571eb3d9c1644f687c4344ad3ceff0d82e2ff64bd1ddbf
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41ed3c05e107bb5965ef10f6103338e7c98cdad9d7ef108a250099c22e6ffa2a
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf0aa5b26636c9467145ef5b79db682dfff8555b2735085e7f065cd2ab4bfe2
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:d4522b29d26771ab4c3d4e8c3402545b916ced337c8f101f3b64a7d587e91a3d
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02a9e72c5f43772e17275297b4afc5feed862ec121020fb09413bf89aaf2462
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -97,3 +97,37 @@
97
  {"current_steps": 97, "total_steps": 224, "loss": 0.5777, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:16:38", "remaining_time": "4:17:26"}
98
  {"current_steps": 98, "total_steps": 224, "loss": 0.568, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:18:41", "remaining_time": "4:15:27"}
99
  {"current_steps": 99, "total_steps": 224, "loss": 0.5167, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:21:36", "remaining_time": "4:14:33"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97
  {"current_steps": 97, "total_steps": 224, "loss": 0.5777, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:16:38", "remaining_time": "4:17:26"}
98
  {"current_steps": 98, "total_steps": 224, "loss": 0.568, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:18:41", "remaining_time": "4:15:27"}
99
  {"current_steps": 99, "total_steps": 224, "loss": 0.5167, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:21:36", "remaining_time": "4:14:33"}
100
+ {"current_steps": 100, "total_steps": 224, "loss": 0.534, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "3:23:44", "remaining_time": "4:12:38"}
101
+ {"current_steps": 101, "total_steps": 224, "loss": 0.5281, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "3:25:40", "remaining_time": "4:10:28"}
102
+ {"current_steps": 102, "total_steps": 224, "loss": 0.5032, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "3:27:36", "remaining_time": "4:08:18"}
103
+ {"current_steps": 103, "total_steps": 224, "loss": 0.5088, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "3:29:38", "remaining_time": "4:06:16"}
104
+ {"current_steps": 104, "total_steps": 224, "loss": 0.5051, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "3:31:44", "remaining_time": "4:04:19"}
105
+ {"current_steps": 105, "total_steps": 224, "loss": 0.5111, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "3:33:46", "remaining_time": "4:02:16"}
106
+ {"current_steps": 106, "total_steps": 224, "loss": 0.5209, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "3:35:48", "remaining_time": "4:00:14"}
107
+ {"current_steps": 107, "total_steps": 224, "loss": 0.5174, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "3:37:54", "remaining_time": "3:58:16"}
108
+ {"current_steps": 108, "total_steps": 224, "loss": 0.5197, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "3:39:54", "remaining_time": "3:56:12"}
109
+ {"current_steps": 109, "total_steps": 224, "loss": 0.5286, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "3:41:54", "remaining_time": "3:54:07"}
110
+ {"current_steps": 110, "total_steps": 224, "loss": 0.5104, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "3:44:05", "remaining_time": "3:52:14"}
111
+ {"current_steps": 111, "total_steps": 224, "loss": 0.5196, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "3:46:13", "remaining_time": "3:50:17"}
112
+ {"current_steps": 112, "total_steps": 224, "loss": 0.495, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "3:48:08", "remaining_time": "3:48:08"}
113
+ {"current_steps": 113, "total_steps": 224, "loss": 0.5039, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "3:50:12", "remaining_time": "3:46:08"}
114
+ {"current_steps": 114, "total_steps": 224, "loss": 0.4848, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "3:52:14", "remaining_time": "3:44:05"}
115
+ {"current_steps": 115, "total_steps": 224, "loss": 0.4978, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "3:54:13", "remaining_time": "3:42:00"}
116
+ {"current_steps": 116, "total_steps": 224, "loss": 0.4983, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "3:56:07", "remaining_time": "3:39:50"}
117
+ {"current_steps": 117, "total_steps": 224, "loss": 0.5136, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "3:58:06", "remaining_time": "3:37:45"}
118
+ {"current_steps": 118, "total_steps": 224, "loss": 0.5121, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "4:00:07", "remaining_time": "3:35:42"}
119
+ {"current_steps": 119, "total_steps": 224, "loss": 0.5138, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "4:02:08", "remaining_time": "3:33:39"}
120
+ {"current_steps": 120, "total_steps": 224, "loss": 0.5305, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "4:04:06", "remaining_time": "3:31:33"}
121
+ {"current_steps": 121, "total_steps": 224, "loss": 0.5161, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "4:06:19", "remaining_time": "3:29:40"}
122
+ {"current_steps": 122, "total_steps": 224, "loss": 0.4942, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "4:08:15", "remaining_time": "3:27:33"}
123
+ {"current_steps": 123, "total_steps": 224, "loss": 0.5085, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "4:10:20", "remaining_time": "3:25:34"}
124
+ {"current_steps": 124, "total_steps": 224, "loss": 0.5074, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "4:12:20", "remaining_time": "3:23:30"}
125
+ {"current_steps": 125, "total_steps": 224, "loss": 0.519, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "4:14:05", "remaining_time": "3:21:14"}
126
+ {"current_steps": 126, "total_steps": 224, "loss": 0.5127, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "4:16:00", "remaining_time": "3:19:06"}
127
+ {"current_steps": 127, "total_steps": 224, "loss": 0.499, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "4:18:00", "remaining_time": "3:17:03"}
128
+ {"current_steps": 128, "total_steps": 224, "loss": 0.5039, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "4:20:03", "remaining_time": "3:15:02"}
129
+ {"current_steps": 129, "total_steps": 224, "loss": 0.5011, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "4:22:05", "remaining_time": "3:13:00"}
130
+ {"current_steps": 130, "total_steps": 224, "loss": 0.5034, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:24:12", "remaining_time": "3:11:02"}
131
+ {"current_steps": 131, "total_steps": 224, "loss": 0.4992, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:27:07", "remaining_time": "3:09:38"}
132
+ {"current_steps": 132, "total_steps": 224, "loss": 0.4462, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:29:12", "remaining_time": "3:07:37"}
133
+ {"current_steps": 133, "total_steps": 224, "loss": 0.4691, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "4:31:05", "remaining_time": "3:05:28"}