ryanmarten commited on
Commit
15ac89c
·
verified ·
1 Parent(s): 129ddd3

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 sha256:6d64f3fa37099ce7d3670f69e8aec12f33ca38e41d54d559b8b2bb84175edddb
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca0564aaf878cf4a8a31c3eb574a6f2b3b1e003e2a85ac8797cb04026c0e8c6
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:a45c2ebebacbf770746308a9f050970161c730e2aba7dc70f06de70bc62af8fe
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82654dbef41e9e49710a861558ab27ee04f2ba87a13c9cd2977c40c2a431d900
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:a7dde78681958bde6063148006cd6ed759dda8e3307911fc787c91f27179fdc1
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b01c7a6d0b628055ddde8b88bf49656ee8398e22806387b6379e78ec447678a2
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e65496c2d24f21d56e389ef5a11500d0fab1b55b362adc5974fa7a45d66ca75
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5fc0062509fbeff5d6261c71ada1c1e62c8870f41d479318ed2776ea531fbd
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -97,3 +97,36 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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"}
100
+ {"current_steps": 100, "total_steps": 224, "loss": 0.5226, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "3:25:24", "remaining_time": "4:14:42"}
101
+ {"current_steps": 101, "total_steps": 224, "loss": 0.519, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "3:27:19", "remaining_time": "4:12:28"}
102
+ {"current_steps": 102, "total_steps": 224, "loss": 0.5242, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "3:29:26", "remaining_time": "4:10:30"}
103
+ {"current_steps": 103, "total_steps": 224, "loss": 0.5241, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "3:31:30", "remaining_time": "4:08:27"}
104
+ {"current_steps": 104, "total_steps": 224, "loss": 0.529, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "3:33:35", "remaining_time": "4:06:27"}
105
+ {"current_steps": 105, "total_steps": 224, "loss": 0.5078, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "3:35:32", "remaining_time": "4:04:17"}
106
+ {"current_steps": 106, "total_steps": 224, "loss": 0.4978, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "3:37:25", "remaining_time": "4:02:02"}
107
+ {"current_steps": 107, "total_steps": 224, "loss": 0.5011, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "3:39:37", "remaining_time": "4:00:09"}
108
+ {"current_steps": 108, "total_steps": 224, "loss": 0.4819, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "3:41:50", "remaining_time": "3:58:16"}
109
+ {"current_steps": 109, "total_steps": 224, "loss": 0.5137, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "3:43:44", "remaining_time": "3:56:03"}
110
+ {"current_steps": 110, "total_steps": 224, "loss": 0.4969, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "3:45:46", "remaining_time": "3:53:58"}
111
+ {"current_steps": 111, "total_steps": 224, "loss": 0.5074, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "3:47:53", "remaining_time": "3:51:59"}
112
+ {"current_steps": 112, "total_steps": 224, "loss": 0.4899, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "3:49:56", "remaining_time": "3:49:56"}
113
+ {"current_steps": 113, "total_steps": 224, "loss": 0.4928, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "3:51:57", "remaining_time": "3:47:51"}
114
+ {"current_steps": 114, "total_steps": 224, "loss": 0.487, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "3:53:49", "remaining_time": "3:45:37"}
115
+ {"current_steps": 115, "total_steps": 224, "loss": 0.4886, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "3:56:01", "remaining_time": "3:43:42"}
116
+ {"current_steps": 116, "total_steps": 224, "loss": 0.5036, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "3:57:59", "remaining_time": "3:41:34"}
117
+ {"current_steps": 117, "total_steps": 224, "loss": 0.5045, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "4:00:03", "remaining_time": "3:39:32"}
118
+ {"current_steps": 118, "total_steps": 224, "loss": 0.4883, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "4:02:08", "remaining_time": "3:37:31"}
119
+ {"current_steps": 119, "total_steps": 224, "loss": 0.5054, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "4:04:11", "remaining_time": "3:35:28"}
120
+ {"current_steps": 120, "total_steps": 224, "loss": 0.5041, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "4:06:05", "remaining_time": "3:33:16"}
121
+ {"current_steps": 121, "total_steps": 224, "loss": 0.5086, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "4:08:08", "remaining_time": "3:31:13"}
122
+ {"current_steps": 122, "total_steps": 224, "loss": 0.5193, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "4:10:15", "remaining_time": "3:29:14"}
123
+ {"current_steps": 123, "total_steps": 224, "loss": 0.4813, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "4:12:27", "remaining_time": "3:27:17"}
124
+ {"current_steps": 124, "total_steps": 224, "loss": 0.5085, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "4:14:24", "remaining_time": "3:25:10"}
125
+ {"current_steps": 125, "total_steps": 224, "loss": 0.5159, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "4:16:31", "remaining_time": "3:23:10"}
126
+ {"current_steps": 126, "total_steps": 224, "loss": 0.5173, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "4:18:27", "remaining_time": "3:21:01"}
127
+ {"current_steps": 127, "total_steps": 224, "loss": 0.4984, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "4:20:29", "remaining_time": "3:18:57"}
128
+ {"current_steps": 128, "total_steps": 224, "loss": 0.4944, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "4:22:33", "remaining_time": "3:16:55"}
129
+ {"current_steps": 129, "total_steps": 224, "loss": 0.5004, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "4:24:27", "remaining_time": "3:14:45"}
130
+ {"current_steps": 130, "total_steps": 224, "loss": 0.5368, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:26:34", "remaining_time": "3:12:44"}
131
+ {"current_steps": 131, "total_steps": 224, "loss": 0.4772, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:29:23", "remaining_time": "3:11:14"}
132
+ {"current_steps": 132, "total_steps": 224, "loss": 0.4651, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:31:24", "remaining_time": "3:09:10"}