ryanmarten commited on
Commit
8f49a24
·
verified ·
1 Parent(s): 233762f

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:ba7391d2a44c369ec9aa8fa818ee7b099eca3dd1286cc87a680da0d18d5889a3
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276620edab5f8a26dca45bd7c9030bae589e078d278f6b7d36b062cb364dd0a7
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dc11d2e914a859cde96b3ff8a18323127335d32bd7020de8dfb3f045532d480
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20db1fce7340fc34fb1e23f3a3bbe80b804f9cd24dba468f663af951e2b86b40
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c00d995877d191885b35d634ecea735417ab3df9266aafb84016d4e211a328d
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5513ac5a131f703f5615d815f4dd48afd7f6720589b2295fab44122ee9087617
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:243a2c81bf2f8f203a1d1719313c88ea0c65c152b87ece9de11e1018a2ed187e
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:445dc7eecb1d37a2f576e914a8428af09dc8498a2cc51eab8a76923c19849f65
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -97,3 +97,36 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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"}
100
+ {"current_steps": 100, "total_steps": 224, "loss": 0.4953, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "3:19:01", "remaining_time": "4:06:47"}
101
+ {"current_steps": 101, "total_steps": 224, "loss": 0.5028, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "3:21:16", "remaining_time": "4:05:07"}
102
+ {"current_steps": 102, "total_steps": 224, "loss": 0.4833, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "3:22:57", "remaining_time": "4:02:45"}
103
+ {"current_steps": 103, "total_steps": 224, "loss": 0.4771, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "3:25:03", "remaining_time": "4:00:54"}
104
+ {"current_steps": 104, "total_steps": 224, "loss": 0.4763, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "3:26:54", "remaining_time": "3:58:44"}
105
+ {"current_steps": 105, "total_steps": 224, "loss": 0.4775, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "3:28:57", "remaining_time": "3:56:49"}
106
+ {"current_steps": 106, "total_steps": 224, "loss": 0.4835, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "3:31:01", "remaining_time": "3:54:54"}
107
+ {"current_steps": 107, "total_steps": 224, "loss": 0.4975, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "3:33:02", "remaining_time": "3:52:56"}
108
+ {"current_steps": 108, "total_steps": 224, "loss": 0.4981, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "3:35:08", "remaining_time": "3:51:04"}
109
+ {"current_steps": 109, "total_steps": 224, "loss": 0.4861, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "3:37:10", "remaining_time": "3:49:07"}
110
+ {"current_steps": 110, "total_steps": 224, "loss": 0.4741, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "3:39:01", "remaining_time": "3:46:59"}
111
+ {"current_steps": 111, "total_steps": 224, "loss": 0.4706, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "3:41:02", "remaining_time": "3:45:01"}
112
+ {"current_steps": 112, "total_steps": 224, "loss": 0.4627, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "3:42:52", "remaining_time": "3:42:52"}
113
+ {"current_steps": 113, "total_steps": 224, "loss": 0.4999, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "3:44:51", "remaining_time": "3:40:52"}
114
+ {"current_steps": 114, "total_steps": 224, "loss": 0.4913, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "3:46:51", "remaining_time": "3:38:53"}
115
+ {"current_steps": 115, "total_steps": 224, "loss": 0.4898, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "3:48:52", "remaining_time": "3:36:55"}
116
+ {"current_steps": 116, "total_steps": 224, "loss": 0.4881, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "3:50:32", "remaining_time": "3:34:38"}
117
+ {"current_steps": 117, "total_steps": 224, "loss": 0.4957, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "3:52:34", "remaining_time": "3:32:42"}
118
+ {"current_steps": 118, "total_steps": 224, "loss": 0.4835, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "3:54:39", "remaining_time": "3:30:47"}
119
+ {"current_steps": 119, "total_steps": 224, "loss": 0.4699, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "3:56:24", "remaining_time": "3:28:35"}
120
+ {"current_steps": 120, "total_steps": 224, "loss": 0.4693, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "3:58:29", "remaining_time": "3:26:41"}
121
+ {"current_steps": 121, "total_steps": 224, "loss": 0.4821, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "4:00:23", "remaining_time": "3:24:37"}
122
+ {"current_steps": 122, "total_steps": 224, "loss": 0.4833, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "4:02:16", "remaining_time": "3:22:33"}
123
+ {"current_steps": 123, "total_steps": 224, "loss": 0.4822, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "4:04:19", "remaining_time": "3:20:37"}
124
+ {"current_steps": 124, "total_steps": 224, "loss": 0.4797, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "4:06:23", "remaining_time": "3:18:42"}
125
+ {"current_steps": 125, "total_steps": 224, "loss": 0.4848, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "4:08:11", "remaining_time": "3:16:33"}
126
+ {"current_steps": 126, "total_steps": 224, "loss": 0.4819, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "4:09:54", "remaining_time": "3:14:22"}
127
+ {"current_steps": 127, "total_steps": 224, "loss": 0.5034, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "4:11:46", "remaining_time": "3:12:17"}
128
+ {"current_steps": 128, "total_steps": 224, "loss": 0.4906, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "4:13:38", "remaining_time": "3:10:13"}
129
+ {"current_steps": 129, "total_steps": 224, "loss": 0.4967, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "4:15:35", "remaining_time": "3:08:13"}
130
+ {"current_steps": 130, "total_steps": 224, "loss": 0.4898, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:17:34", "remaining_time": "3:06:14"}
131
+ {"current_steps": 131, "total_steps": 224, "loss": 0.4654, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:20:21", "remaining_time": "3:04:50"}
132
+ {"current_steps": 132, "total_steps": 224, "loss": 0.4492, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:22:22", "remaining_time": "3:02:52"}