sedrickkeh commited on
Commit
b8e02ae
·
verified ·
1 Parent(s): c52829d

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:b1cf0d73a4944c76886e467ccd71da98f24a912867e5e9abaec18060b4494a79
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4867975036b3361c944b4583b1dfcaef18d8f5197ad2f234820bcb741609f2be
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:c30f08ffcacdc0461992ef8ef343531df084f80592cd8a29f36d948eaf7ccebd
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed93eb288b6917d3d7f6fa38afc0fee0df3e42d6cf96ba63407ef21ca90845c
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:471721731aede15e95ac5a1a3fcf2562385b737f0387e025076adface8669a05
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7acf80d314ac504b99e2993770cdcb8c95b0a41f588889bc50252639d2de3f7
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:c5e9a3ec7c3b93ce0e4574165b68e30a954f9a0ee4f5eda55d0c2e53af121f53
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43bc36220190231d2925021b58977aa333b1e8cdc8fa89c84f86262ffb9bc27
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -101,3 +101,38 @@
101
  {"current_steps": 101, "total_steps": 224, "loss": 0.3338, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "1:14:37", "remaining_time": "1:30:52"}
102
  {"current_steps": 102, "total_steps": 224, "loss": 0.3402, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "1:15:24", "remaining_time": "1:30:11"}
103
  {"current_steps": 103, "total_steps": 224, "loss": 0.3152, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "1:16:01", "remaining_time": "1:29:18"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
101
  {"current_steps": 101, "total_steps": 224, "loss": 0.3338, "lr": 1.344466850284333e-05, "epoch": 3.091139240506329, "percentage": 45.09, "elapsed_time": "1:14:37", "remaining_time": "1:30:52"}
102
  {"current_steps": 102, "total_steps": 224, "loss": 0.3402, "lr": 1.3297521276301666e-05, "epoch": 3.1215189873417724, "percentage": 45.54, "elapsed_time": "1:15:24", "remaining_time": "1:30:11"}
103
  {"current_steps": 103, "total_steps": 224, "loss": 0.3152, "lr": 1.3149568511086104e-05, "epoch": 3.151898734177215, "percentage": 45.98, "elapsed_time": "1:16:01", "remaining_time": "1:29:18"}
104
+ {"current_steps": 104, "total_steps": 224, "loss": 0.3116, "lr": 1.300084635000341e-05, "epoch": 3.1822784810126583, "percentage": 46.43, "elapsed_time": "1:16:42", "remaining_time": "1:28:30"}
105
+ {"current_steps": 105, "total_steps": 224, "loss": 0.3001, "lr": 1.2851391123813075e-05, "epoch": 3.212658227848101, "percentage": 46.88, "elapsed_time": "1:17:23", "remaining_time": "1:27:42"}
106
+ {"current_steps": 106, "total_steps": 224, "loss": 0.3524, "lr": 1.2701239342352223e-05, "epoch": 3.2430379746835443, "percentage": 47.32, "elapsed_time": "1:18:02", "remaining_time": "1:26:52"}
107
+ {"current_steps": 107, "total_steps": 224, "loss": 0.299, "lr": 1.2550427685616767e-05, "epoch": 3.2734177215189875, "percentage": 47.77, "elapsed_time": "1:18:44", "remaining_time": "1:26:05"}
108
+ {"current_steps": 108, "total_steps": 224, "loss": 0.3037, "lr": 1.239899299480098e-05, "epoch": 3.3037974683544302, "percentage": 48.21, "elapsed_time": "1:19:23", "remaining_time": "1:25:16"}
109
+ {"current_steps": 109, "total_steps": 224, "loss": 0.2915, "lr": 1.2246972263297718e-05, "epoch": 3.3341772151898734, "percentage": 48.66, "elapsed_time": "1:20:03", "remaining_time": "1:24:27"}
110
+ {"current_steps": 110, "total_steps": 224, "loss": 0.3032, "lr": 1.2094402627661447e-05, "epoch": 3.3645569620253166, "percentage": 49.11, "elapsed_time": "1:20:42", "remaining_time": "1:23:38"}
111
+ {"current_steps": 111, "total_steps": 224, "loss": 0.3103, "lr": 1.1941321358536278e-05, "epoch": 3.3949367088607594, "percentage": 49.55, "elapsed_time": "1:21:17", "remaining_time": "1:22:45"}
112
+ {"current_steps": 112, "total_steps": 224, "loss": 0.3146, "lr": 1.1787765851551296e-05, "epoch": 3.4253164556962026, "percentage": 50.0, "elapsed_time": "1:22:01", "remaining_time": "1:22:01"}
113
+ {"current_steps": 113, "total_steps": 224, "loss": 0.3086, "lr": 1.1633773618185302e-05, "epoch": 3.4556962025316453, "percentage": 50.45, "elapsed_time": "1:22:51", "remaining_time": "1:21:23"}
114
+ {"current_steps": 114, "total_steps": 224, "loss": 0.2863, "lr": 1.14793822766033e-05, "epoch": 3.4860759493670885, "percentage": 50.89, "elapsed_time": "1:23:21", "remaining_time": "1:20:25"}
115
+ {"current_steps": 115, "total_steps": 224, "loss": 0.3134, "lr": 1.132462954246688e-05, "epoch": 3.5164556962025317, "percentage": 51.34, "elapsed_time": "1:24:10", "remaining_time": "1:19:46"}
116
+ {"current_steps": 116, "total_steps": 224, "loss": 0.304, "lr": 1.1169553219720828e-05, "epoch": 3.546835443037975, "percentage": 51.79, "elapsed_time": "1:24:49", "remaining_time": "1:18:58"}
117
+ {"current_steps": 117, "total_steps": 224, "loss": 0.3106, "lr": 1.1014191191358118e-05, "epoch": 3.5772151898734177, "percentage": 52.23, "elapsed_time": "1:25:40", "remaining_time": "1:18:20"}
118
+ {"current_steps": 118, "total_steps": 224, "loss": 0.3236, "lr": 1.085858141016566e-05, "epoch": 3.607594936708861, "percentage": 52.68, "elapsed_time": "1:26:28", "remaining_time": "1:17:40"}
119
+ {"current_steps": 119, "total_steps": 224, "loss": 0.2767, "lr": 1.070276188945293e-05, "epoch": 3.6379746835443036, "percentage": 53.12, "elapsed_time": "1:27:17", "remaining_time": "1:17:01"}
120
+ {"current_steps": 120, "total_steps": 224, "loss": 0.3, "lr": 1.0546770693765859e-05, "epoch": 3.668354430379747, "percentage": 53.57, "elapsed_time": "1:27:59", "remaining_time": "1:16:15"}
121
+ {"current_steps": 121, "total_steps": 224, "loss": 0.3023, "lr": 1.0390645929588197e-05, "epoch": 3.69873417721519, "percentage": 54.02, "elapsed_time": "1:28:49", "remaining_time": "1:15:37"}
122
+ {"current_steps": 122, "total_steps": 224, "loss": 0.2992, "lr": 1.0234425736032607e-05, "epoch": 3.729113924050633, "percentage": 54.46, "elapsed_time": "1:29:25", "remaining_time": "1:14:46"}
123
+ {"current_steps": 123, "total_steps": 224, "loss": 0.3033, "lr": 1.007814827552384e-05, "epoch": 3.759493670886076, "percentage": 54.91, "elapsed_time": "1:30:13", "remaining_time": "1:14:05"}
124
+ {"current_steps": 124, "total_steps": 224, "loss": 0.307, "lr": 9.92185172447616e-06, "epoch": 3.7898734177215188, "percentage": 55.36, "elapsed_time": "1:30:49", "remaining_time": "1:13:15"}
125
+ {"current_steps": 125, "total_steps": 224, "loss": 0.3255, "lr": 9.765574263967397e-06, "epoch": 3.820253164556962, "percentage": 55.8, "elapsed_time": "1:31:35", "remaining_time": "1:12:32"}
126
+ {"current_steps": 126, "total_steps": 224, "loss": 0.2935, "lr": 9.609354070411807e-06, "epoch": 3.850632911392405, "percentage": 56.25, "elapsed_time": "1:32:13", "remaining_time": "1:11:43"}
127
+ {"current_steps": 127, "total_steps": 224, "loss": 0.3161, "lr": 9.453229306234143e-06, "epoch": 3.8810126582278484, "percentage": 56.7, "elapsed_time": "1:33:01", "remaining_time": "1:11:03"}
128
+ {"current_steps": 128, "total_steps": 224, "loss": 0.318, "lr": 9.297238110547075e-06, "epoch": 3.911392405063291, "percentage": 57.14, "elapsed_time": "1:33:50", "remaining_time": "1:10:23"}
129
+ {"current_steps": 129, "total_steps": 224, "loss": 0.2975, "lr": 9.14141858983434e-06, "epoch": 3.9417721518987343, "percentage": 57.59, "elapsed_time": "1:34:35", "remaining_time": "1:09:39"}
130
+ {"current_steps": 130, "total_steps": 224, "loss": 0.3, "lr": 8.985808808641883e-06, "epoch": 3.972151898734177, "percentage": 58.04, "elapsed_time": "1:35:10", "remaining_time": "1:08:49"}
131
+ {"current_steps": 131, "total_steps": 224, "loss": 0.3041, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "1:36:38", "remaining_time": "1:08:36"}
132
+ {"current_steps": 132, "total_steps": 224, "loss": 0.211, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "1:37:20", "remaining_time": "1:07:50"}
133
+ {"current_steps": 133, "total_steps": 224, "loss": 0.2164, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "1:38:11", "remaining_time": "1:07:10"}
134
+ {"current_steps": 134, "total_steps": 224, "loss": 0.2216, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "1:38:49", "remaining_time": "1:06:22"}
135
+ {"current_steps": 135, "total_steps": 224, "loss": 0.2105, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "1:39:26", "remaining_time": "1:05:33"}
136
+ {"current_steps": 136, "total_steps": 224, "loss": 0.2421, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "1:40:11", "remaining_time": "1:04:50"}
137
+ {"current_steps": 137, "total_steps": 224, "loss": 0.2126, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "1:40:50", "remaining_time": "1:04:02"}
138
+ {"current_steps": 138, "total_steps": 224, "loss": 0.2341, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "1:41:41", "remaining_time": "1:03:22"}