ryanmarten commited on
Commit
28f93ed
·
verified ·
1 Parent(s): 3fb4fe2

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:f848648753fc19fd52965ac3275c38387608b776581b00e5d8a0e2393b89413c
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0169cb22f3dad96085977cced7453ff18954c0c1c840114ff46913382f553e8e
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89886407786793ec9dcd3e309ecf3d4cd931cb54ff0ba825e0865a8b184122a0
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4fcf19a8ec2c631b30be97697369dd85a373e79b61a20474780c149cbcf082
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c2c7facf891398f6e7ffccf4ffafe704defaa50f42a85cba1fa5e1287ce2926
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4b24345098b50f195d82c1ef79a7f89875acb31023ce0e1e8f39de3c58bf77
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55564cdfeb95ea3175e0b234ee0d861dac4673106386c9afe7025cc7f87563c0
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b91c8a58a6e3b46822ce66c98bb5b9d538116a14d1ad96b53fa82b334b72c5b
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -97,3 +97,36 @@
97
  {"current_steps": 97, "total_steps": 224, "loss": 0.5748, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:18:33", "remaining_time": "4:19:57"}
98
  {"current_steps": 98, "total_steps": 224, "loss": 0.5695, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:20:30", "remaining_time": "4:17:48"}
99
  {"current_steps": 99, "total_steps": 224, "loss": 0.5002, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:23:21", "remaining_time": "4:16:46"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97
  {"current_steps": 97, "total_steps": 224, "loss": 0.5748, "lr": 1.402448623755254e-05, "epoch": 2.962025316455696, "percentage": 43.3, "elapsed_time": "3:18:33", "remaining_time": "4:19:57"}
98
  {"current_steps": 98, "total_steps": 224, "loss": 0.5695, "lr": 1.3880918526722497e-05, "epoch": 2.992405063291139, "percentage": 43.75, "elapsed_time": "3:20:30", "remaining_time": "4:17:48"}
99
  {"current_steps": 99, "total_steps": 224, "loss": 0.5002, "lr": 1.3736402761368597e-05, "epoch": 3.030379746835443, "percentage": 44.2, "elapsed_time": "3:23:21", "remaining_time": "4:16:46"}
100
+ {"current_steps": 100, "total_steps": 224, "loss": 0.4881, "lr": 1.3590974244686248e-05, "epoch": 3.060759493670886, "percentage": 44.64, "elapsed_time": "3:25:18", "remaining_time": "4:14:34"}
101
+ {"current_steps": 101, "total_steps": 224, "loss": 0.5085, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "3:27:27", "remaining_time": "4:12:38"}
102
+ {"current_steps": 102, "total_steps": 224, "loss": 0.5094, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "3:29:29", "remaining_time": "4:10:33"}
103
+ {"current_steps": 103, "total_steps": 224, "loss": 0.5194, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "3:31:31", "remaining_time": "4:08:29"}
104
+ {"current_steps": 104, "total_steps": 224, "loss": 0.4885, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "3:33:31", "remaining_time": "4:06:23"}
105
+ {"current_steps": 105, "total_steps": 224, "loss": 0.5012, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "3:35:37", "remaining_time": "4:04:22"}
106
+ {"current_steps": 106, "total_steps": 224, "loss": 0.4982, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "3:37:46", "remaining_time": "4:02:26"}
107
+ {"current_steps": 107, "total_steps": 224, "loss": 0.5037, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "3:39:47", "remaining_time": "4:00:19"}
108
+ {"current_steps": 108, "total_steps": 224, "loss": 0.5098, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "3:41:55", "remaining_time": "3:58:21"}
109
+ {"current_steps": 109, "total_steps": 224, "loss": 0.4985, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "3:43:58", "remaining_time": "3:56:18"}
110
+ {"current_steps": 110, "total_steps": 224, "loss": 0.498, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "3:45:59", "remaining_time": "3:54:12"}
111
+ {"current_steps": 111, "total_steps": 224, "loss": 0.4983, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "3:47:46", "remaining_time": "3:51:52"}
112
+ {"current_steps": 112, "total_steps": 224, "loss": 0.5066, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "3:49:55", "remaining_time": "3:49:55"}
113
+ {"current_steps": 113, "total_steps": 224, "loss": 0.4945, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "3:51:54", "remaining_time": "3:47:48"}
114
+ {"current_steps": 114, "total_steps": 224, "loss": 0.5074, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "3:53:56", "remaining_time": "3:45:43"}
115
+ {"current_steps": 115, "total_steps": 224, "loss": 0.4973, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "3:55:52", "remaining_time": "3:43:34"}
116
+ {"current_steps": 116, "total_steps": 224, "loss": 0.4923, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "3:57:41", "remaining_time": "3:41:17"}
117
+ {"current_steps": 117, "total_steps": 224, "loss": 0.4964, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "3:59:45", "remaining_time": "3:39:15"}
118
+ {"current_steps": 118, "total_steps": 224, "loss": 0.4961, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "4:01:46", "remaining_time": "3:37:11"}
119
+ {"current_steps": 119, "total_steps": 224, "loss": 0.5019, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "4:03:53", "remaining_time": "3:35:12"}
120
+ {"current_steps": 120, "total_steps": 224, "loss": 0.4872, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "4:05:48", "remaining_time": "3:33:02"}
121
+ {"current_steps": 121, "total_steps": 224, "loss": 0.488, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "4:07:56", "remaining_time": "3:31:03"}
122
+ {"current_steps": 122, "total_steps": 224, "loss": 0.4882, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "4:09:43", "remaining_time": "3:28:47"}
123
+ {"current_steps": 123, "total_steps": 224, "loss": 0.5146, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "4:11:42", "remaining_time": "3:26:41"}
124
+ {"current_steps": 124, "total_steps": 224, "loss": 0.5085, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "4:13:46", "remaining_time": "3:24:39"}
125
+ {"current_steps": 125, "total_steps": 224, "loss": 0.4964, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "4:15:49", "remaining_time": "3:22:37"}
126
+ {"current_steps": 126, "total_steps": 224, "loss": 0.5028, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "4:17:55", "remaining_time": "3:20:36"}
127
+ {"current_steps": 127, "total_steps": 224, "loss": 0.5165, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "4:19:56", "remaining_time": "3:18:32"}
128
+ {"current_steps": 128, "total_steps": 224, "loss": 0.509, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "4:22:05", "remaining_time": "3:16:34"}
129
+ {"current_steps": 129, "total_steps": 224, "loss": 0.4985, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "4:24:13", "remaining_time": "3:14:34"}
130
+ {"current_steps": 130, "total_steps": 224, "loss": 0.5018, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "4:26:13", "remaining_time": "3:12:29"}
131
+ {"current_steps": 131, "total_steps": 224, "loss": 0.4854, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "4:29:20", "remaining_time": "3:11:12"}
132
+ {"current_steps": 132, "total_steps": 224, "loss": 0.4629, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "4:31:28", "remaining_time": "3:09:12"}