ryanmarten commited on
Commit
233762f
·
verified ·
1 Parent(s): 66be402

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:f96f3359a87a35e1490e1a3c0a7e10a0ec7c05162cde9c83437f28c91240996a
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba7391d2a44c369ec9aa8fa818ee7b099eca3dd1286cc87a680da0d18d5889a3
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65d1a542baf7278c5fccb986417c728990ed27160977333590d105e4d9f0b561
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc11d2e914a859cde96b3ff8a18323127335d32bd7020de8dfb3f045532d480
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:084744618bf02ff228956a52e721dc28947fd6da55f8e37bd92c4d8f0cf27df3
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c00d995877d191885b35d634ecea735417ab3df9266aafb84016d4e211a328d
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:b561870ac8a3b9765be80f8d429100d3f2e97abe96664145c882d2f25730f8c3
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:243a2c81bf2f8f203a1d1719313c88ea0c65c152b87ece9de11e1018a2ed187e
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -64,3 +64,36 @@
64
  {"current_steps": 64, "total_steps": 224, "loss": 0.6187, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "2:06:30", "remaining_time": "5:16:15"}
65
  {"current_steps": 65, "total_steps": 224, "loss": 0.6125, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "2:08:32", "remaining_time": "5:14:25"}
66
  {"current_steps": 66, "total_steps": 224, "loss": 0.584, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "2:11:25", "remaining_time": "5:14:37"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
  {"current_steps": 64, "total_steps": 224, "loss": 0.6187, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "2:06:30", "remaining_time": "5:16:15"}
65
  {"current_steps": 65, "total_steps": 224, "loss": 0.6125, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "2:08:32", "remaining_time": "5:14:25"}
66
  {"current_steps": 66, "total_steps": 224, "loss": 0.584, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "2:11:25", "remaining_time": "5:14:37"}
67
+ {"current_steps": 67, "total_steps": 224, "loss": 0.5624, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "2:13:21", "remaining_time": "5:12:30"}
68
+ {"current_steps": 68, "total_steps": 224, "loss": 0.5459, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "2:15:14", "remaining_time": "5:10:15"}
69
+ {"current_steps": 69, "total_steps": 224, "loss": 0.5684, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "2:17:13", "remaining_time": "5:08:15"}
70
+ {"current_steps": 70, "total_steps": 224, "loss": 0.549, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "2:19:11", "remaining_time": "5:06:13"}
71
+ {"current_steps": 71, "total_steps": 224, "loss": 0.5395, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "2:21:07", "remaining_time": "5:04:06"}
72
+ {"current_steps": 72, "total_steps": 224, "loss": 0.5603, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "2:23:05", "remaining_time": "5:02:04"}
73
+ {"current_steps": 73, "total_steps": 224, "loss": 0.5542, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "2:25:12", "remaining_time": "5:00:21"}
74
+ {"current_steps": 74, "total_steps": 224, "loss": 0.5523, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "2:27:14", "remaining_time": "4:58:28"}
75
+ {"current_steps": 75, "total_steps": 224, "loss": 0.5586, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "2:29:17", "remaining_time": "4:56:34"}
76
+ {"current_steps": 76, "total_steps": 224, "loss": 0.5559, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "2:31:23", "remaining_time": "4:54:48"}
77
+ {"current_steps": 77, "total_steps": 224, "loss": 0.5661, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "2:33:26", "remaining_time": "4:52:55"}
78
+ {"current_steps": 78, "total_steps": 224, "loss": 0.5402, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "2:35:29", "remaining_time": "4:51:03"}
79
+ {"current_steps": 79, "total_steps": 224, "loss": 0.5438, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "2:37:26", "remaining_time": "4:48:59"}
80
+ {"current_steps": 80, "total_steps": 224, "loss": 0.5573, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "2:39:26", "remaining_time": "4:46:58"}
81
+ {"current_steps": 81, "total_steps": 224, "loss": 0.5369, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "2:41:11", "remaining_time": "4:44:33"}
82
+ {"current_steps": 82, "total_steps": 224, "loss": 0.5447, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "2:43:12", "remaining_time": "4:42:38"}
83
+ {"current_steps": 83, "total_steps": 224, "loss": 0.5636, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "2:45:07", "remaining_time": "4:40:30"}
84
+ {"current_steps": 84, "total_steps": 224, "loss": 0.5635, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "2:47:08", "remaining_time": "4:38:33"}
85
+ {"current_steps": 85, "total_steps": 224, "loss": 0.5394, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "2:49:11", "remaining_time": "4:36:40"}
86
+ {"current_steps": 86, "total_steps": 224, "loss": 0.5337, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "2:51:07", "remaining_time": "4:34:34"}
87
+ {"current_steps": 87, "total_steps": 224, "loss": 0.549, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "2:53:05", "remaining_time": "4:32:34"}
88
+ {"current_steps": 88, "total_steps": 224, "loss": 0.5404, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "2:54:52", "remaining_time": "4:30:15"}
89
+ {"current_steps": 89, "total_steps": 224, "loss": 0.5526, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "2:56:47", "remaining_time": "4:28:10"}
90
+ {"current_steps": 90, "total_steps": 224, "loss": 0.5469, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "2:58:45", "remaining_time": "4:26:08"}
91
+ {"current_steps": 91, "total_steps": 224, "loss": 0.5268, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "3:00:49", "remaining_time": "4:24:17"}
92
+ {"current_steps": 92, "total_steps": 224, "loss": 0.5244, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "3:02:43", "remaining_time": "4:22:10"}
93
+ {"current_steps": 93, "total_steps": 224, "loss": 0.5356, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "3:04:48", "remaining_time": "4:20:19"}
94
+ {"current_steps": 94, "total_steps": 224, "loss": 0.5315, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "3:06:44", "remaining_time": "4:18:15"}
95
+ {"current_steps": 95, "total_steps": 224, "loss": 0.5295, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "3:08:35", "remaining_time": "4:16:05"}
96
+ {"current_steps": 96, "total_steps": 224, "loss": 0.5404, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "3:10:34", "remaining_time": "4:14:06"}
97
+ {"current_steps": 97, "total_steps": 224, "loss": 0.5492, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:12:17", "remaining_time": "4:11:45"}
98
+ {"current_steps": 98, "total_steps": 224, "loss": 0.5482, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:14:14", "remaining_time": "4:09:44"}
99
+ {"current_steps": 99, "total_steps": 224, "loss": 0.4865, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:17:10", "remaining_time": "4:08:56"}