ryanmarten commited on
Commit
d1d8b7d
·
verified ·
1 Parent(s): 0c4486e

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 sha256:3154eb3b3d19d9bb62568b8cd4d9c0414156d33d331afd8b663819b7e812a1c1
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36bb5708d2b066afe3dc3a0562b967335cb5309803878e56cb63d90c07a7a6e
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8421d261ca4e3211025e9ebe0ea9321ee3208413b3bdc1039253d12be6b01947
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f1386d1d5a0ebf955dd812043c0ee1a4e137404942743d6f22c23dd252679f
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66f88371331c7ae4de63e3ccf23f1013ba8fab55df8010d2bf0fa0d038c2314e
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c01764e0c2792f1370230b7c856deac7a1b009a7cec7bf9f549fa2fa0eee7aba
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:113b91bc01a9471bdf479068fd8968294aecea8ad86445e1cf860975005fc90d
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d9c958bd1d540be1054da592e61012a30f72327dd1feb51eaa24b91ad55798
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -97,3 +97,35 @@
97
  {"current_steps": 97, "total_steps": 224, "loss": 0.4131, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:59:19", "remaining_time": "5:13:20"}
98
  {"current_steps": 98, "total_steps": 224, "loss": 0.4051, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "4:01:54", "remaining_time": "5:11:01"}
99
  {"current_steps": 99, "total_steps": 224, "loss": 0.3711, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "4:05:11", "remaining_time": "5:09:35"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97
  {"current_steps": 97, "total_steps": 224, "loss": 0.4131, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:59:19", "remaining_time": "5:13:20"}
98
  {"current_steps": 98, "total_steps": 224, "loss": 0.4051, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "4:01:54", "remaining_time": "5:11:01"}
99
  {"current_steps": 99, "total_steps": 224, "loss": 0.3711, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "4:05:11", "remaining_time": "5:09:35"}
100
+ {"current_steps": 100, "total_steps": 224, "loss": 0.3663, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "4:07:29", "remaining_time": "5:06:52"}
101
+ {"current_steps": 101, "total_steps": 224, "loss": 0.3646, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "4:09:50", "remaining_time": "5:04:15"}
102
+ {"current_steps": 102, "total_steps": 224, "loss": 0.3614, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "4:12:15", "remaining_time": "5:01:43"}
103
+ {"current_steps": 103, "total_steps": 224, "loss": 0.3541, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "4:14:47", "remaining_time": "4:59:19"}
104
+ {"current_steps": 104, "total_steps": 224, "loss": 0.3596, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "4:17:06", "remaining_time": "4:56:39"}
105
+ {"current_steps": 105, "total_steps": 224, "loss": 0.3651, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "4:19:31", "remaining_time": "4:54:07"}
106
+ {"current_steps": 106, "total_steps": 224, "loss": 0.3608, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "4:22:06", "remaining_time": "4:51:47"}
107
+ {"current_steps": 107, "total_steps": 224, "loss": 0.3608, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "4:24:34", "remaining_time": "4:49:18"}
108
+ {"current_steps": 108, "total_steps": 224, "loss": 0.363, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "4:27:10", "remaining_time": "4:46:57"}
109
+ {"current_steps": 109, "total_steps": 224, "loss": 0.3618, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "4:29:30", "remaining_time": "4:44:20"}
110
+ {"current_steps": 110, "total_steps": 224, "loss": 0.3554, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "4:32:07", "remaining_time": "4:42:00"}
111
+ {"current_steps": 111, "total_steps": 224, "loss": 0.338, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "4:34:45", "remaining_time": "4:39:42"}
112
+ {"current_steps": 112, "total_steps": 224, "loss": 0.3557, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "4:37:05", "remaining_time": "4:37:05"}
113
+ {"current_steps": 113, "total_steps": 224, "loss": 0.3499, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "4:39:32", "remaining_time": "4:34:35"}
114
+ {"current_steps": 114, "total_steps": 224, "loss": 0.3602, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "4:42:06", "remaining_time": "4:32:12"}
115
+ {"current_steps": 115, "total_steps": 224, "loss": 0.3468, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "4:44:24", "remaining_time": "4:29:34"}
116
+ {"current_steps": 116, "total_steps": 224, "loss": 0.3591, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "4:46:44", "remaining_time": "4:26:57"}
117
+ {"current_steps": 117, "total_steps": 224, "loss": 0.3512, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "4:49:11", "remaining_time": "4:24:28"}
118
+ {"current_steps": 118, "total_steps": 224, "loss": 0.3529, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "4:51:37", "remaining_time": "4:21:58"}
119
+ {"current_steps": 119, "total_steps": 224, "loss": 0.3446, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "4:53:48", "remaining_time": "4:19:14"}
120
+ {"current_steps": 120, "total_steps": 224, "loss": 0.3585, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "4:56:19", "remaining_time": "4:16:48"}
121
+ {"current_steps": 121, "total_steps": 224, "loss": 0.3554, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "4:58:48", "remaining_time": "4:14:21"}
122
+ {"current_steps": 122, "total_steps": 224, "loss": 0.3579, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "5:01:13", "remaining_time": "4:11:50"}
123
+ {"current_steps": 123, "total_steps": 224, "loss": 0.361, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "5:03:40", "remaining_time": "4:09:21"}
124
+ {"current_steps": 124, "total_steps": 224, "loss": 0.3545, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "5:06:00", "remaining_time": "4:06:46"}
125
+ {"current_steps": 125, "total_steps": 224, "loss": 0.3653, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "5:08:18", "remaining_time": "4:04:10"}
126
+ {"current_steps": 126, "total_steps": 224, "loss": 0.3433, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "5:10:33", "remaining_time": "4:01:32"}
127
+ {"current_steps": 127, "total_steps": 224, "loss": 0.3476, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "5:13:00", "remaining_time": "3:59:03"}
128
+ {"current_steps": 128, "total_steps": 224, "loss": 0.3673, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "5:15:33", "remaining_time": "3:56:40"}
129
+ {"current_steps": 129, "total_steps": 224, "loss": 0.3683, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "5:18:18", "remaining_time": "3:54:25"}
130
+ {"current_steps": 130, "total_steps": 224, "loss": 0.3583, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "5:20:39", "remaining_time": "3:51:51"}
131
+ {"current_steps": 131, "total_steps": 224, "loss": 0.3381, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "5:24:03", "remaining_time": "3:50:03"}