ryanmarten commited on
Commit
34e13ae
·
verified ·
1 Parent(s): 0df6073

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cdf6e8da8e2dd3cd8ca276ae975b5e5bbc414b5dfd9517de17f4e59b90c57d80
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c86bfa53e6d4ef91bc17bc77fa872b3983a19ec1f4037bb40a4dccfef0bec01f
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02ac8f2091604ec108baa80e087cc15a23b93848081dac70035ea431952d4123
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8e29e5e3f799cc3ed6d92ae136012a3776baea89896d67b891122ac4b7b5c0
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:fb8dadfbfa981d10b9ed6a7135e3acc9c4977cf31073079330f3a24a368d94c4
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acf150647b444fccf27e3f997e958165d9f6fb5995041c4a85bc09bb2f5739fd
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b4324c3bfde0c12bcbf6cc8159e4237e82546abc396efe16c7ff461cc80b2f8
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5886e09ce16a8f87830cf23c5206099e29b30774fcdf872d277ca353988c75
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -65,3 +65,35 @@
65
  {"current_steps": 65, "total_steps": 224, "loss": 0.629, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "1:47:43", "remaining_time": "4:23:30"}
66
  {"current_steps": 66, "total_steps": 224, "loss": 0.5857, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "1:50:07", "remaining_time": "4:23:38"}
67
  {"current_steps": 67, "total_steps": 224, "loss": 0.5681, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "1:51:47", "remaining_time": "4:21:57"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
  {"current_steps": 65, "total_steps": 224, "loss": 0.629, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "1:47:43", "remaining_time": "4:23:30"}
66
  {"current_steps": 66, "total_steps": 224, "loss": 0.5857, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "1:50:07", "remaining_time": "4:23:38"}
67
  {"current_steps": 67, "total_steps": 224, "loss": 0.5681, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "1:51:47", "remaining_time": "4:21:57"}
68
+ {"current_steps": 68, "total_steps": 224, "loss": 0.5719, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "1:53:25", "remaining_time": "4:20:12"}
69
+ {"current_steps": 69, "total_steps": 224, "loss": 0.553, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "1:55:03", "remaining_time": "4:18:28"}
70
+ {"current_steps": 70, "total_steps": 224, "loss": 0.5707, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "1:56:55", "remaining_time": "4:17:14"}
71
+ {"current_steps": 71, "total_steps": 224, "loss": 0.5813, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "1:58:54", "remaining_time": "4:16:13"}
72
+ {"current_steps": 72, "total_steps": 224, "loss": 0.5767, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "2:00:24", "remaining_time": "4:14:12"}
73
+ {"current_steps": 73, "total_steps": 224, "loss": 0.5688, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "2:02:15", "remaining_time": "4:12:52"}
74
+ {"current_steps": 74, "total_steps": 224, "loss": 0.5627, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "2:03:41", "remaining_time": "4:10:42"}
75
+ {"current_steps": 75, "total_steps": 224, "loss": 0.5603, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "2:05:18", "remaining_time": "4:08:57"}
76
+ {"current_steps": 76, "total_steps": 224, "loss": 0.5621, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "2:06:52", "remaining_time": "4:07:04"}
77
+ {"current_steps": 77, "total_steps": 224, "loss": 0.5612, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "2:08:38", "remaining_time": "4:05:35"}
78
+ {"current_steps": 78, "total_steps": 224, "loss": 0.5575, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "2:10:23", "remaining_time": "4:04:04"}
79
+ {"current_steps": 79, "total_steps": 224, "loss": 0.5528, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "2:11:44", "remaining_time": "4:01:48"}
80
+ {"current_steps": 80, "total_steps": 224, "loss": 0.5469, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "2:13:27", "remaining_time": "4:00:12"}
81
+ {"current_steps": 81, "total_steps": 224, "loss": 0.5675, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "2:15:18", "remaining_time": "3:58:52"}
82
+ {"current_steps": 82, "total_steps": 224, "loss": 0.5811, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "2:16:54", "remaining_time": "3:57:05"}
83
+ {"current_steps": 83, "total_steps": 224, "loss": 0.5497, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "2:18:14", "remaining_time": "3:54:51"}
84
+ {"current_steps": 84, "total_steps": 224, "loss": 0.5544, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "2:19:42", "remaining_time": "3:52:51"}
85
+ {"current_steps": 85, "total_steps": 224, "loss": 0.5622, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "2:21:24", "remaining_time": "3:51:14"}
86
+ {"current_steps": 86, "total_steps": 224, "loss": 0.5485, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "2:23:05", "remaining_time": "3:49:36"}
87
+ {"current_steps": 87, "total_steps": 224, "loss": 0.547, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "2:24:46", "remaining_time": "3:47:58"}
88
+ {"current_steps": 88, "total_steps": 224, "loss": 0.5709, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "2:26:30", "remaining_time": "3:46:24"}
89
+ {"current_steps": 89, "total_steps": 224, "loss": 0.5706, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "2:27:58", "remaining_time": "3:44:27"}
90
+ {"current_steps": 90, "total_steps": 224, "loss": 0.5672, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "2:29:38", "remaining_time": "3:42:48"}
91
+ {"current_steps": 91, "total_steps": 224, "loss": 0.5863, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "2:31:12", "remaining_time": "3:40:59"}
92
+ {"current_steps": 92, "total_steps": 224, "loss": 0.5691, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "2:32:46", "remaining_time": "3:39:12"}
93
+ {"current_steps": 93, "total_steps": 224, "loss": 0.5701, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "2:34:32", "remaining_time": "3:37:41"}
94
+ {"current_steps": 94, "total_steps": 224, "loss": 0.5558, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "2:36:15", "remaining_time": "3:36:05"}
95
+ {"current_steps": 95, "total_steps": 224, "loss": 0.5672, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "2:37:56", "remaining_time": "3:34:27"}
96
+ {"current_steps": 96, "total_steps": 224, "loss": 0.5614, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "2:39:33", "remaining_time": "3:32:44"}
97
+ {"current_steps": 97, "total_steps": 224, "loss": 0.5393, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "2:40:50", "remaining_time": "3:30:35"}
98
+ {"current_steps": 98, "total_steps": 224, "loss": 0.5532, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "2:42:40", "remaining_time": "3:29:08"}
99
+ {"current_steps": 99, "total_steps": 224, "loss": 0.5193, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "2:45:08", "remaining_time": "3:28:31"}