sedrickkeh commited on
Commit
86e8fa7
·
verified ·
1 Parent(s): 06d11cc

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cad8332c89e96afcd145b7621bdb23f377fc64bc20d8f2e81057f2122dbe91f
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb962e332427036eb85055303ee46cf24caf3cbf409a6ecf4b837df00f3505b0
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:436ff98f973629560ada114b2327ea88d1541140f70fd58e72546eb71c03c806
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb53c39e57940ac6153d0e9dfad56011495e3edc469c5049eba58c40f3aba2f5
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:fd3473698dfdf11fabb0274a9554bbf167094e27ec5e32006f2344907039378c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95dd36c5578523fb342007cb64eb95b364ea0aab1085a5ff32b4001904680643
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13b71493ba11dbebdaf2f54fb1c81023c3a6f554617bf51d45ec0df1f5a497f6
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:571e9f31c4b26cb0d0588c30fba7f74ab30aa316e04f378831025dc478043aa5
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -83,3 +83,42 @@
83
  {"current_steps": 83, "total_steps": 123, "loss": 1.3689, "lr": 2.9229249349905686e-06, "epoch": 2.008, "percentage": 67.48, "elapsed_time": "1:18:26", "remaining_time": "0:37:48"}
84
  {"current_steps": 84, "total_steps": 123, "loss": 0.8718, "lr": 2.7938944937838924e-06, "epoch": 2.032, "percentage": 68.29, "elapsed_time": "1:19:27", "remaining_time": "0:36:53"}
85
  {"current_steps": 85, "total_steps": 123, "loss": 0.8144, "lr": 2.6666633838716317e-06, "epoch": 2.056, "percentage": 69.11, "elapsed_time": "1:20:25", "remaining_time": "0:35:57"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83
  {"current_steps": 83, "total_steps": 123, "loss": 1.3689, "lr": 2.9229249349905686e-06, "epoch": 2.008, "percentage": 67.48, "elapsed_time": "1:18:26", "remaining_time": "0:37:48"}
84
  {"current_steps": 84, "total_steps": 123, "loss": 0.8718, "lr": 2.7938944937838924e-06, "epoch": 2.032, "percentage": 68.29, "elapsed_time": "1:19:27", "remaining_time": "0:36:53"}
85
  {"current_steps": 85, "total_steps": 123, "loss": 0.8144, "lr": 2.6666633838716317e-06, "epoch": 2.056, "percentage": 69.11, "elapsed_time": "1:20:25", "remaining_time": "0:35:57"}
86
+ {"current_steps": 86, "total_steps": 123, "loss": 0.7497, "lr": 2.5413353767719805e-06, "epoch": 2.08, "percentage": 69.92, "elapsed_time": "1:21:12", "remaining_time": "0:34:56"}
87
+ {"current_steps": 87, "total_steps": 123, "loss": 0.9051, "lr": 2.418012691805191e-06, "epoch": 2.104, "percentage": 70.73, "elapsed_time": "1:22:09", "remaining_time": "0:33:59"}
88
+ {"current_steps": 88, "total_steps": 123, "loss": 0.8908, "lr": 2.296795912722014e-06, "epoch": 2.128, "percentage": 71.54, "elapsed_time": "1:23:02", "remaining_time": "0:33:01"}
89
+ {"current_steps": 89, "total_steps": 123, "loss": 0.7216, "lr": 2.1777839056661555e-06, "epoch": 2.152, "percentage": 72.36, "elapsed_time": "1:23:48", "remaining_time": "0:32:01"}
90
+ {"current_steps": 90, "total_steps": 123, "loss": 0.8029, "lr": 2.061073738537635e-06, "epoch": 2.176, "percentage": 73.17, "elapsed_time": "1:24:41", "remaining_time": "0:31:03"}
91
+ {"current_steps": 91, "total_steps": 123, "loss": 0.9015, "lr": 1.946760601822809e-06, "epoch": 2.2, "percentage": 73.98, "elapsed_time": "1:25:31", "remaining_time": "0:30:04"}
92
+ {"current_steps": 92, "total_steps": 123, "loss": 0.7919, "lr": 1.8349377309556487e-06, "epoch": 2.224, "percentage": 74.8, "elapsed_time": "1:26:22", "remaining_time": "0:29:06"}
93
+ {"current_steps": 93, "total_steps": 123, "loss": 0.7993, "lr": 1.7256963302735752e-06, "epoch": 2.248, "percentage": 75.61, "elapsed_time": "1:27:16", "remaining_time": "0:28:09"}
94
+ {"current_steps": 94, "total_steps": 123, "loss": 0.7369, "lr": 1.6191254986299044e-06, "epoch": 2.2720000000000002, "percentage": 76.42, "elapsed_time": "1:28:17", "remaining_time": "0:27:14"}
95
+ {"current_steps": 95, "total_steps": 123, "loss": 0.9214, "lr": 1.5153121567235334e-06, "epoch": 2.296, "percentage": 77.24, "elapsed_time": "1:29:12", "remaining_time": "0:26:17"}
96
+ {"current_steps": 96, "total_steps": 123, "loss": 0.8425, "lr": 1.4143409762051829e-06, "epoch": 2.32, "percentage": 78.05, "elapsed_time": "1:30:16", "remaining_time": "0:25:23"}
97
+ {"current_steps": 97, "total_steps": 123, "loss": 0.7417, "lr": 1.3162943106179748e-06, "epoch": 2.344, "percentage": 78.86, "elapsed_time": "1:31:13", "remaining_time": "0:24:27"}
98
+ {"current_steps": 98, "total_steps": 123, "loss": 0.8874, "lr": 1.2212521282287093e-06, "epoch": 2.368, "percentage": 79.67, "elapsed_time": "1:32:17", "remaining_time": "0:23:32"}
99
+ {"current_steps": 99, "total_steps": 123, "loss": 0.8052, "lr": 1.1292919468045876e-06, "epoch": 2.392, "percentage": 80.49, "elapsed_time": "1:33:03", "remaining_time": "0:22:33"}
100
+ {"current_steps": 100, "total_steps": 123, "loss": 0.8252, "lr": 1.0404887703886252e-06, "epoch": 2.416, "percentage": 81.3, "elapsed_time": "1:34:00", "remaining_time": "0:21:37"}
101
+ {"current_steps": 101, "total_steps": 123, "loss": 0.7867, "lr": 9.549150281252633e-07, "epoch": 2.44, "percentage": 82.11, "elapsed_time": "1:34:47", "remaining_time": "0:20:38"}
102
+ {"current_steps": 102, "total_steps": 123, "loss": 0.9062, "lr": 8.7264051518613e-07, "epoch": 2.464, "percentage": 82.93, "elapsed_time": "1:35:41", "remaining_time": "0:19:42"}
103
+ {"current_steps": 103, "total_steps": 123, "loss": 0.7844, "lr": 7.937323358440935e-07, "epoch": 2.488, "percentage": 83.74, "elapsed_time": "1:36:28", "remaining_time": "0:18:43"}
104
+ {"current_steps": 104, "total_steps": 123, "loss": 0.7702, "lr": 7.182548487420555e-07, "epoch": 2.512, "percentage": 84.55, "elapsed_time": "1:37:15", "remaining_time": "0:17:46"}
105
+ {"current_steps": 105, "total_steps": 123, "loss": 0.9273, "lr": 6.462696144011149e-07, "epoch": 2.536, "percentage": 85.37, "elapsed_time": "1:38:13", "remaining_time": "0:16:50"}
106
+ {"current_steps": 106, "total_steps": 123, "loss": 0.8128, "lr": 5.778353450109286e-07, "epoch": 2.56, "percentage": 86.18, "elapsed_time": "1:39:10", "remaining_time": "0:15:54"}
107
+ {"current_steps": 107, "total_steps": 123, "loss": 0.7965, "lr": 5.130078565432089e-07, "epoch": 2.584, "percentage": 86.99, "elapsed_time": "1:40:01", "remaining_time": "0:14:57"}
108
+ {"current_steps": 108, "total_steps": 123, "loss": 0.7753, "lr": 4.5184002322740784e-07, "epoch": 2.608, "percentage": 87.8, "elapsed_time": "1:40:57", "remaining_time": "0:14:01"}
109
+ {"current_steps": 109, "total_steps": 123, "loss": 0.8232, "lr": 3.9438173442575e-07, "epoch": 2.632, "percentage": 88.62, "elapsed_time": "1:41:49", "remaining_time": "0:13:04"}
110
+ {"current_steps": 110, "total_steps": 123, "loss": 0.8859, "lr": 3.406798539427386e-07, "epoch": 2.656, "percentage": 89.43, "elapsed_time": "1:42:51", "remaining_time": "0:12:09"}
111
+ {"current_steps": 111, "total_steps": 123, "loss": 0.81, "lr": 2.9077818180237693e-07, "epoch": 2.68, "percentage": 90.24, "elapsed_time": "1:43:44", "remaining_time": "0:11:12"}
112
+ {"current_steps": 112, "total_steps": 123, "loss": 0.7866, "lr": 2.447174185242324e-07, "epoch": 2.7039999999999997, "percentage": 91.06, "elapsed_time": "1:44:39", "remaining_time": "0:10:16"}
113
+ {"current_steps": 113, "total_steps": 123, "loss": 0.8428, "lr": 2.0253513192751374e-07, "epoch": 2.7279999999999998, "percentage": 91.87, "elapsed_time": "1:45:34", "remaining_time": "0:09:20"}
114
+ {"current_steps": 114, "total_steps": 123, "loss": 0.8939, "lr": 1.6426572649021477e-07, "epoch": 2.752, "percentage": 92.68, "elapsed_time": "1:46:34", "remaining_time": "0:08:24"}
115
+ {"current_steps": 115, "total_steps": 123, "loss": 0.7411, "lr": 1.2994041528833267e-07, "epoch": 2.776, "percentage": 93.5, "elapsed_time": "1:47:24", "remaining_time": "0:07:28"}
116
+ {"current_steps": 116, "total_steps": 123, "loss": 0.8683, "lr": 9.958719453803278e-08, "epoch": 2.8, "percentage": 94.31, "elapsed_time": "1:48:15", "remaining_time": "0:06:31"}
117
+ {"current_steps": 117, "total_steps": 123, "loss": 0.7558, "lr": 7.32308207615351e-08, "epoch": 2.824, "percentage": 95.12, "elapsed_time": "1:49:09", "remaining_time": "0:05:35"}
118
+ {"current_steps": 118, "total_steps": 123, "loss": 0.8281, "lr": 5.089279059533658e-08, "epoch": 2.848, "percentage": 95.93, "elapsed_time": "1:50:07", "remaining_time": "0:04:39"}
119
+ {"current_steps": 119, "total_steps": 123, "loss": 0.8886, "lr": 3.25913232572489e-08, "epoch": 2.872, "percentage": 96.75, "elapsed_time": "1:51:09", "remaining_time": "0:03:44"}
120
+ {"current_steps": 120, "total_steps": 123, "loss": 0.7874, "lr": 1.834134568654333e-08, "epoch": 2.896, "percentage": 97.56, "elapsed_time": "1:51:53", "remaining_time": "0:02:47"}
121
+ {"current_steps": 121, "total_steps": 123, "loss": 0.8983, "lr": 8.15448036932176e-09, "epoch": 2.92, "percentage": 98.37, "elapsed_time": "1:52:58", "remaining_time": "0:01:52"}
122
+ {"current_steps": 122, "total_steps": 123, "loss": 0.6968, "lr": 2.0390358590538507e-09, "epoch": 2.944, "percentage": 99.19, "elapsed_time": "1:53:49", "remaining_time": "0:00:55"}
123
+ {"current_steps": 123, "total_steps": 123, "loss": 0.8298, "lr": 0.0, "epoch": 2.968, "percentage": 100.0, "elapsed_time": "1:54:50", "remaining_time": "0:00:00"}
124
+ {"current_steps": 123, "total_steps": 123, "epoch": 2.968, "percentage": 100.0, "elapsed_time": "1:57:00", "remaining_time": "0:00:00"}