ryanmarten commited on
Commit
e021052
·
verified ·
1 Parent(s): 36e54ef

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 sha256:6c6b482dfe7d60123df4946b64b64a6a085fbead69c6f4f6ad0c03684b7a9df2
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:535f70e8f1f6530de4f3fe3c25d9c01d9dfe62b7190175f43a212f2c9bb45ddf
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d22cfb5ca886665e7433060bc85776072bbd7c83d64a7c047999ac702ce696d
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09ac0dbeb37653ab67eb85a68baa505936dceb483010d9205271341aac95bf9
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:c3c957b80cebb04cb7976a3950daeb61e78e416ee4913ae81220341228803d68
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f562f094f901a1c48a207cc972525f75d8012e04a7151084cfc51559d0a1b7
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8765b5427d097d5983722b571e23f849e560526eb862cb406f9674e1c2800c48
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4681c4a8f3d2b65cab9b8eed2cdacd1bd8eae9d548bd02b3ef2424dd315643a
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -65,3 +65,35 @@
65
  {"current_steps": 65, "total_steps": 224, "loss": 0.5958, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "1:41:27", "remaining_time": "4:08:11"}
66
  {"current_steps": 66, "total_steps": 224, "loss": 0.5517, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "1:43:46", "remaining_time": "4:08:25"}
67
  {"current_steps": 67, "total_steps": 224, "loss": 0.4376, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "1:45:12", "remaining_time": "4:06:32"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
  {"current_steps": 65, "total_steps": 224, "loss": 0.5958, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "1:41:27", "remaining_time": "4:08:11"}
66
  {"current_steps": 66, "total_steps": 224, "loss": 0.5517, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "1:43:46", "remaining_time": "4:08:25"}
67
  {"current_steps": 67, "total_steps": 224, "loss": 0.4376, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "1:45:12", "remaining_time": "4:06:32"}
68
+ {"current_steps": 68, "total_steps": 224, "loss": 0.4406, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "1:46:54", "remaining_time": "4:05:16"}
69
+ {"current_steps": 69, "total_steps": 224, "loss": 0.4699, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "1:48:32", "remaining_time": "4:03:49"}
70
+ {"current_steps": 70, "total_steps": 224, "loss": 0.46, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "1:50:11", "remaining_time": "4:02:25"}
71
+ {"current_steps": 71, "total_steps": 224, "loss": 0.4842, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "1:51:47", "remaining_time": "4:00:55"}
72
+ {"current_steps": 72, "total_steps": 224, "loss": 0.4777, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "1:53:06", "remaining_time": "3:58:46"}
73
+ {"current_steps": 73, "total_steps": 224, "loss": 0.4747, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "1:54:43", "remaining_time": "3:57:17"}
74
+ {"current_steps": 74, "total_steps": 224, "loss": 0.4641, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "1:56:21", "remaining_time": "3:55:51"}
75
+ {"current_steps": 75, "total_steps": 224, "loss": 0.4425, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "1:57:45", "remaining_time": "3:53:57"}
76
+ {"current_steps": 76, "total_steps": 224, "loss": 0.4503, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "1:59:12", "remaining_time": "3:52:07"}
77
+ {"current_steps": 77, "total_steps": 224, "loss": 0.4451, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "2:00:47", "remaining_time": "3:50:36"}
78
+ {"current_steps": 78, "total_steps": 224, "loss": 0.4311, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "2:02:28", "remaining_time": "3:49:14"}
79
+ {"current_steps": 79, "total_steps": 224, "loss": 0.4767, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "2:04:10", "remaining_time": "3:47:54"}
80
+ {"current_steps": 80, "total_steps": 224, "loss": 0.4856, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "2:05:49", "remaining_time": "3:46:28"}
81
+ {"current_steps": 81, "total_steps": 224, "loss": 0.4653, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "2:07:15", "remaining_time": "3:44:40"}
82
+ {"current_steps": 82, "total_steps": 224, "loss": 0.4641, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "2:08:53", "remaining_time": "3:43:12"}
83
+ {"current_steps": 83, "total_steps": 224, "loss": 0.4667, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "2:10:24", "remaining_time": "3:41:32"}
84
+ {"current_steps": 84, "total_steps": 224, "loss": 0.494, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "2:12:05", "remaining_time": "3:40:09"}
85
+ {"current_steps": 85, "total_steps": 224, "loss": 0.4623, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "2:13:29", "remaining_time": "3:38:17"}
86
+ {"current_steps": 86, "total_steps": 224, "loss": 0.4292, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "2:15:02", "remaining_time": "3:36:41"}
87
+ {"current_steps": 87, "total_steps": 224, "loss": 0.4403, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "2:16:17", "remaining_time": "3:34:36"}
88
+ {"current_steps": 88, "total_steps": 224, "loss": 0.4815, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "2:17:33", "remaining_time": "3:32:35"}
89
+ {"current_steps": 89, "total_steps": 224, "loss": 0.4311, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "2:18:46", "remaining_time": "3:30:29"}
90
+ {"current_steps": 90, "total_steps": 224, "loss": 0.4556, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "2:20:25", "remaining_time": "3:29:04"}
91
+ {"current_steps": 91, "total_steps": 224, "loss": 0.452, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "2:22:15", "remaining_time": "3:27:54"}
92
+ {"current_steps": 92, "total_steps": 224, "loss": 0.4517, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "2:23:32", "remaining_time": "3:25:57"}
93
+ {"current_steps": 93, "total_steps": 224, "loss": 0.4671, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "2:25:15", "remaining_time": "3:24:36"}
94
+ {"current_steps": 94, "total_steps": 224, "loss": 0.4697, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "2:27:03", "remaining_time": "3:23:23"}
95
+ {"current_steps": 95, "total_steps": 224, "loss": 0.444, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "2:28:29", "remaining_time": "3:21:38"}
96
+ {"current_steps": 96, "total_steps": 224, "loss": 0.4728, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "2:30:05", "remaining_time": "3:20:07"}
97
+ {"current_steps": 97, "total_steps": 224, "loss": 0.4647, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "2:31:41", "remaining_time": "3:18:36"}
98
+ {"current_steps": 98, "total_steps": 224, "loss": 0.4622, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "2:33:19", "remaining_time": "3:17:08"}
99
+ {"current_steps": 99, "total_steps": 224, "loss": 0.3839, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "2:35:45", "remaining_time": "3:16:39"}