ryanmarten commited on
Commit
129ddd3
·
verified ·
1 Parent(s): 6d8af57

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:c014cf493882e8343bd82432d25d5780a3b91c684fdd1ddb853c075bcf7293e4
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d64f3fa37099ce7d3670f69e8aec12f33ca38e41d54d559b8b2bb84175edddb
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11423c429d4f917452f98bb3a7b83e74417c1221bf4b1f36db708ba034239e86
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45c2ebebacbf770746308a9f050970161c730e2aba7dc70f06de70bc62af8fe
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08874ae21b38628dabdcc21c5f37aa17cfa33795b5cc804e91d9cbfc16978d70
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7dde78681958bde6063148006cd6ed759dda8e3307911fc787c91f27179fdc1
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90eb55a72ca1e574b50fbfed9585cb331962613dd9f185a924edac0ad72bd9cf
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e65496c2d24f21d56e389ef5a11500d0fab1b55b362adc5974fa7a45d66ca75
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -64,3 +64,36 @@
64
  {"current_steps": 64, "total_steps": 224, "loss": 0.6216, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "2:10:25", "remaining_time": "5:26:04"}
65
  {"current_steps": 65, "total_steps": 224, "loss": 0.612, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "2:12:39", "remaining_time": "5:24:30"}
66
  {"current_steps": 66, "total_steps": 224, "loss": 0.6075, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "2:15:39", "remaining_time": "5:24:45"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
  {"current_steps": 64, "total_steps": 224, "loss": 0.6216, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "2:10:25", "remaining_time": "5:26:04"}
65
  {"current_steps": 65, "total_steps": 224, "loss": 0.612, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "2:12:39", "remaining_time": "5:24:30"}
66
  {"current_steps": 66, "total_steps": 224, "loss": 0.6075, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "2:15:39", "remaining_time": "5:24:45"}
67
+ {"current_steps": 67, "total_steps": 224, "loss": 0.569, "lr": 1.7727005033820117e-05, "epoch": 2.050632911392405, "percentage": 29.91, "elapsed_time": "2:17:35", "remaining_time": "5:22:24"}
68
+ {"current_steps": 68, "total_steps": 224, "loss": 0.5695, "lr": 1.762685178110382e-05, "epoch": 2.081012658227848, "percentage": 30.36, "elapsed_time": "2:19:41", "remaining_time": "5:20:28"}
69
+ {"current_steps": 69, "total_steps": 224, "loss": 0.5858, "lr": 1.752483539436807e-05, "epoch": 2.1113924050632913, "percentage": 30.8, "elapsed_time": "2:21:51", "remaining_time": "5:18:40"}
70
+ {"current_steps": 70, "total_steps": 224, "loss": 0.5893, "lr": 1.7420980794800013e-05, "epoch": 2.141772151898734, "percentage": 31.25, "elapsed_time": "2:23:52", "remaining_time": "5:16:32"}
71
+ {"current_steps": 71, "total_steps": 224, "loss": 0.5665, "lr": 1.731531335263669e-05, "epoch": 2.1721518987341772, "percentage": 31.7, "elapsed_time": "2:25:53", "remaining_time": "5:14:22"}
72
+ {"current_steps": 72, "total_steps": 224, "loss": 0.5758, "lr": 1.720785888096743e-05, "epoch": 2.2025316455696204, "percentage": 32.14, "elapsed_time": "2:27:47", "remaining_time": "5:12:00"}
73
+ {"current_steps": 73, "total_steps": 224, "loss": 0.5643, "lr": 1.7098643629428035e-05, "epoch": 2.232911392405063, "percentage": 32.59, "elapsed_time": "2:29:48", "remaining_time": "5:09:51"}
74
+ {"current_steps": 74, "total_steps": 224, "loss": 0.5674, "lr": 1.698769427778842e-05, "epoch": 2.2632911392405064, "percentage": 33.04, "elapsed_time": "2:31:54", "remaining_time": "5:07:55"}
75
+ {"current_steps": 75, "total_steps": 224, "loss": 0.5521, "lr": 1.687503792943506e-05, "epoch": 2.293670886075949, "percentage": 33.48, "elapsed_time": "2:33:46", "remaining_time": "5:05:30"}
76
+ {"current_steps": 76, "total_steps": 224, "loss": 0.5721, "lr": 1.6760702104750046e-05, "epoch": 2.3240506329113924, "percentage": 33.93, "elapsed_time": "2:35:52", "remaining_time": "5:03:32"}
77
+ {"current_steps": 77, "total_steps": 224, "loss": 0.5785, "lr": 1.664471473438822e-05, "epoch": 2.3544303797468356, "percentage": 34.38, "elapsed_time": "2:37:49", "remaining_time": "5:01:17"}
78
+ {"current_steps": 78, "total_steps": 224, "loss": 0.5636, "lr": 1.6527104152454096e-05, "epoch": 2.3848101265822783, "percentage": 34.82, "elapsed_time": "2:39:45", "remaining_time": "4:59:01"}
79
+ {"current_steps": 79, "total_steps": 224, "loss": 0.5741, "lr": 1.6407899089580263e-05, "epoch": 2.4151898734177215, "percentage": 35.27, "elapsed_time": "2:41:45", "remaining_time": "4:56:54"}
80
+ {"current_steps": 80, "total_steps": 224, "loss": 0.5549, "lr": 1.628712866590885e-05, "epoch": 2.4455696202531647, "percentage": 35.71, "elapsed_time": "2:43:54", "remaining_time": "4:55:02"}
81
+ {"current_steps": 81, "total_steps": 224, "loss": 0.5628, "lr": 1.6164822383977912e-05, "epoch": 2.4759493670886075, "percentage": 36.16, "elapsed_time": "2:46:02", "remaining_time": "4:53:07"}
82
+ {"current_steps": 82, "total_steps": 224, "loss": 0.5653, "lr": 1.604101012151436e-05, "epoch": 2.5063291139240507, "percentage": 36.61, "elapsed_time": "2:47:55", "remaining_time": "4:50:46"}
83
+ {"current_steps": 83, "total_steps": 224, "loss": 0.5788, "lr": 1.5915722124135227e-05, "epoch": 2.536708860759494, "percentage": 37.05, "elapsed_time": "2:49:52", "remaining_time": "4:48:35"}
84
+ {"current_steps": 84, "total_steps": 224, "loss": 0.5442, "lr": 1.5788988997959115e-05, "epoch": 2.5670886075949366, "percentage": 37.5, "elapsed_time": "2:51:52", "remaining_time": "4:46:26"}
85
+ {"current_steps": 85, "total_steps": 224, "loss": 0.5619, "lr": 1.5660841702129533e-05, "epoch": 2.59746835443038, "percentage": 37.95, "elapsed_time": "2:54:05", "remaining_time": "4:44:41"}
86
+ {"current_steps": 86, "total_steps": 224, "loss": 0.5593, "lr": 1.5531311541251995e-05, "epoch": 2.6278481012658226, "percentage": 38.39, "elapsed_time": "2:56:21", "remaining_time": "4:43:00"}
87
+ {"current_steps": 87, "total_steps": 224, "loss": 0.5578, "lr": 1.540043015774676e-05, "epoch": 2.6582278481012658, "percentage": 38.84, "elapsed_time": "2:58:23", "remaining_time": "4:40:54"}
88
+ {"current_steps": 88, "total_steps": 224, "loss": 0.5634, "lr": 1.5268229524119007e-05, "epoch": 2.688607594936709, "percentage": 39.29, "elapsed_time": "3:00:23", "remaining_time": "4:38:47"}
89
+ {"current_steps": 89, "total_steps": 224, "loss": 0.5688, "lr": 1.513474193514842e-05, "epoch": 2.7189873417721517, "percentage": 39.73, "elapsed_time": "3:02:27", "remaining_time": "4:36:46"}
90
+ {"current_steps": 90, "total_steps": 224, "loss": 0.5511, "lr": 1.5000000000000002e-05, "epoch": 2.749367088607595, "percentage": 40.18, "elapsed_time": "3:04:32", "remaining_time": "4:34:45"}
91
+ {"current_steps": 91, "total_steps": 224, "loss": 0.5742, "lr": 1.4864036634258112e-05, "epoch": 2.779746835443038, "percentage": 40.62, "elapsed_time": "3:06:32", "remaining_time": "4:32:38"}
92
+ {"current_steps": 92, "total_steps": 224, "loss": 0.5882, "lr": 1.4726885051885654e-05, "epoch": 2.810126582278481, "percentage": 41.07, "elapsed_time": "3:08:31", "remaining_time": "4:30:30"}
93
+ {"current_steps": 93, "total_steps": 224, "loss": 0.5708, "lr": 1.4588578757110359e-05, "epoch": 2.840506329113924, "percentage": 41.52, "elapsed_time": "3:10:40", "remaining_time": "4:28:34"}
94
+ {"current_steps": 94, "total_steps": 224, "loss": 0.5482, "lr": 1.4449151536240167e-05, "epoch": 2.8708860759493673, "percentage": 41.96, "elapsed_time": "3:12:32", "remaining_time": "4:26:17"}
95
+ {"current_steps": 95, "total_steps": 224, "loss": 0.5509, "lr": 1.4308637449409705e-05, "epoch": 2.90126582278481, "percentage": 42.41, "elapsed_time": "3:14:33", "remaining_time": "4:24:11"}
96
+ {"current_steps": 96, "total_steps": 224, "loss": 0.5636, "lr": 1.4167070822259868e-05, "epoch": 2.9316455696202532, "percentage": 42.86, "elapsed_time": "3:16:28", "remaining_time": "4:21:58"}
97
+ {"current_steps": 97, "total_steps": 224, "loss": 0.5731, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:18:27", "remaining_time": "4:19:49"}
98
+ {"current_steps": 98, "total_steps": 224, "loss": 0.5755, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:20:31", "remaining_time": "4:17:48"}
99
+ {"current_steps": 99, "total_steps": 224, "loss": 0.5171, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:23:22", "remaining_time": "4:16:46"}