ryanmarten commited on
Commit
9b5ddb8
·
verified ·
1 Parent(s): db716fb

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 sha256:853fdf894082a13a5b0a62892a432e8ec685145215a67cd82061c5ce4c6a7781
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b3348ce0b40a3958584cf273f668143b2ff57928ff3ebb47cb2a5643ad6e30
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c12b109ade814e1c0d495bcdef27660fbb1ab27857d04b235aae833e6d3d3fa
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b3db465f521684ebc55d98077ed0e270b758f85295055816e967ad68b374f7
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42f1e31696a7fb65d9e09afabbe2596b6f8bc44934d11d02bbac54eb700a5383
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c947d61cb007899c56985f8ed35bf8efd38f2589f5587c9c9f9e9a703ae033c
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ce7264bbec946b1892a1d9e3a249e0ce809e94baf27be5a97513ba99108ab2a
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd7ef09e862137d9eb5220077094d0defe1cead1ea4348839a6bd7c3fe3eb9a9
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -97,3 +97,36 @@
97
  {"current_steps": 97, "total_steps": 224, "loss": 0.5596, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:15:09", "remaining_time": "4:15:30"}
98
  {"current_steps": 98, "total_steps": 224, "loss": 0.567, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:17:05", "remaining_time": "4:13:24"}
99
  {"current_steps": 99, "total_steps": 224, "loss": 0.4939, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:19:54", "remaining_time": "4:12:24"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97
  {"current_steps": 97, "total_steps": 224, "loss": 0.5596, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:15:09", "remaining_time": "4:15:30"}
98
  {"current_steps": 98, "total_steps": 224, "loss": 0.567, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:17:05", "remaining_time": "4:13:24"}
99
  {"current_steps": 99, "total_steps": 224, "loss": 0.4939, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:19:54", "remaining_time": "4:12:24"}
100
+ {"current_steps": 100, "total_steps": 224, "loss": 0.5157, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "3:21:52", "remaining_time": "4:10:19"}
101
+ {"current_steps": 101, "total_steps": 224, "loss": 0.51, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "3:23:47", "remaining_time": "4:08:10"}
102
+ {"current_steps": 102, "total_steps": 224, "loss": 0.5088, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "3:25:47", "remaining_time": "4:06:08"}
103
+ {"current_steps": 103, "total_steps": 224, "loss": 0.5105, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "3:27:43", "remaining_time": "4:04:01"}
104
+ {"current_steps": 104, "total_steps": 224, "loss": 0.5088, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "3:29:51", "remaining_time": "4:02:08"}
105
+ {"current_steps": 105, "total_steps": 224, "loss": 0.5016, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "3:31:56", "remaining_time": "4:00:11"}
106
+ {"current_steps": 106, "total_steps": 224, "loss": 0.5114, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "3:33:52", "remaining_time": "3:58:04"}
107
+ {"current_steps": 107, "total_steps": 224, "loss": 0.5156, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "3:35:49", "remaining_time": "3:56:00"}
108
+ {"current_steps": 108, "total_steps": 224, "loss": 0.5058, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "3:38:01", "remaining_time": "3:54:10"}
109
+ {"current_steps": 109, "total_steps": 224, "loss": 0.5151, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "3:40:03", "remaining_time": "3:52:10"}
110
+ {"current_steps": 110, "total_steps": 224, "loss": 0.491, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "3:42:09", "remaining_time": "3:50:13"}
111
+ {"current_steps": 111, "total_steps": 224, "loss": 0.496, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "3:44:10", "remaining_time": "3:48:12"}
112
+ {"current_steps": 112, "total_steps": 224, "loss": 0.487, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "3:46:01", "remaining_time": "3:46:01"}
113
+ {"current_steps": 113, "total_steps": 224, "loss": 0.5086, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "3:48:06", "remaining_time": "3:44:03"}
114
+ {"current_steps": 114, "total_steps": 224, "loss": 0.4992, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "3:50:00", "remaining_time": "3:41:56"}
115
+ {"current_steps": 115, "total_steps": 224, "loss": 0.4734, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "3:51:58", "remaining_time": "3:39:51"}
116
+ {"current_steps": 116, "total_steps": 224, "loss": 0.4958, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "3:54:07", "remaining_time": "3:37:58"}
117
+ {"current_steps": 117, "total_steps": 224, "loss": 0.4945, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "3:56:06", "remaining_time": "3:35:55"}
118
+ {"current_steps": 118, "total_steps": 224, "loss": 0.51, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "3:57:50", "remaining_time": "3:33:39"}
119
+ {"current_steps": 119, "total_steps": 224, "loss": 0.4814, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "3:59:53", "remaining_time": "3:31:39"}
120
+ {"current_steps": 120, "total_steps": 224, "loss": 0.4961, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "4:01:48", "remaining_time": "3:29:33"}
121
+ {"current_steps": 121, "total_steps": 224, "loss": 0.4894, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "4:03:36", "remaining_time": "3:27:22"}
122
+ {"current_steps": 122, "total_steps": 224, "loss": 0.5103, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "4:05:37", "remaining_time": "3:25:21"}
123
+ {"current_steps": 123, "total_steps": 224, "loss": 0.4887, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "4:07:34", "remaining_time": "3:23:17"}
124
+ {"current_steps": 124, "total_steps": 224, "loss": 0.4896, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "4:09:28", "remaining_time": "3:21:11"}
125
+ {"current_steps": 125, "total_steps": 224, "loss": 0.5161, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "4:11:22", "remaining_time": "3:19:05"}
126
+ {"current_steps": 126, "total_steps": 224, "loss": 0.4917, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "4:13:26", "remaining_time": "3:17:06"}
127
+ {"current_steps": 127, "total_steps": 224, "loss": 0.5058, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "4:15:30", "remaining_time": "3:15:08"}
128
+ {"current_steps": 128, "total_steps": 224, "loss": 0.5058, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "4:17:31", "remaining_time": "3:13:08"}
129
+ {"current_steps": 129, "total_steps": 224, "loss": 0.4958, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "4:19:19", "remaining_time": "3:10:58"}
130
+ {"current_steps": 130, "total_steps": 224, "loss": 0.4839, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:21:36", "remaining_time": "3:09:10"}
131
+ {"current_steps": 131, "total_steps": 224, "loss": 0.4684, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:24:32", "remaining_time": "3:07:48"}
132
+ {"current_steps": 132, "total_steps": 224, "loss": 0.4512, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:26:32", "remaining_time": "3:05:46"}