sedrickkeh commited on
Commit
928bf66
·
verified ·
1 Parent(s): 1e97721

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 sha256:4d9e6a4ebd34705b6a20e1ec65f00a977bfb774630fa0ff6a9b52ed70f9b548f
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c275e27b68289951e241491910f36e44b3b7a4d5c2f7718598baa48dc6bad9ea
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c60b68c16be2eda0fc274839c1a270524eb9928b296aa5897dd8a64844339f5
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b12cdb7462f09973ac38ccfc870faf22de0de3d280f61706cca6dace2ec015da
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1239068a8483d6206e6aaac9c517f1fe049327a0cc774be888b3e263e9a35f78
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b29a485ab556be37ec9333079c6fdaedfcce6d279f5d2881e098bab2717ce53e
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f913dde7f121d7e067815841a0d8841f1ae94c5a0bbe079fc80e3f51cbde2a8
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09c04a62c1ef046321f25360c92e0d0a15c6a5c3ec7e263c1074d53b58bc5e20
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -88,3 +88,49 @@
88
  {"current_steps": 870, "total_steps": 1772, "loss": 0.5457, "lr": 5e-06, "epoch": 1.9633286318758816, "percentage": 49.1, "elapsed_time": "11:09:06", "remaining_time": "11:33:42"}
89
  {"current_steps": 880, "total_steps": 1772, "loss": 0.5435, "lr": 5e-06, "epoch": 1.9858956276445698, "percentage": 49.66, "elapsed_time": "11:16:42", "remaining_time": "11:25:56"}
90
  {"current_steps": 886, "total_steps": 1772, "eval_loss": 0.5871431231498718, "epoch": 1.9994358251057829, "percentage": 50.0, "elapsed_time": "11:27:27", "remaining_time": "11:27:27"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 870, "total_steps": 1772, "loss": 0.5457, "lr": 5e-06, "epoch": 1.9633286318758816, "percentage": 49.1, "elapsed_time": "11:09:06", "remaining_time": "11:33:42"}
89
  {"current_steps": 880, "total_steps": 1772, "loss": 0.5435, "lr": 5e-06, "epoch": 1.9858956276445698, "percentage": 49.66, "elapsed_time": "11:16:42", "remaining_time": "11:25:56"}
90
  {"current_steps": 886, "total_steps": 1772, "eval_loss": 0.5871431231498718, "epoch": 1.9994358251057829, "percentage": 50.0, "elapsed_time": "11:27:27", "remaining_time": "11:27:27"}
91
+ {"current_steps": 890, "total_steps": 1772, "loss": 0.5672, "lr": 5e-06, "epoch": 2.008462623413258, "percentage": 50.23, "elapsed_time": "11:31:28", "remaining_time": "11:25:15"}
92
+ {"current_steps": 900, "total_steps": 1772, "loss": 0.4779, "lr": 5e-06, "epoch": 2.0310296191819464, "percentage": 50.79, "elapsed_time": "11:39:04", "remaining_time": "11:17:19"}
93
+ {"current_steps": 910, "total_steps": 1772, "loss": 0.4796, "lr": 5e-06, "epoch": 2.0535966149506346, "percentage": 51.35, "elapsed_time": "11:46:41", "remaining_time": "11:09:24"}
94
+ {"current_steps": 920, "total_steps": 1772, "loss": 0.472, "lr": 5e-06, "epoch": 2.076163610719323, "percentage": 51.92, "elapsed_time": "11:54:18", "remaining_time": "11:01:30"}
95
+ {"current_steps": 930, "total_steps": 1772, "loss": 0.4792, "lr": 5e-06, "epoch": 2.098730606488011, "percentage": 52.48, "elapsed_time": "12:01:55", "remaining_time": "10:53:36"}
96
+ {"current_steps": 940, "total_steps": 1772, "loss": 0.4838, "lr": 5e-06, "epoch": 2.1212976022566994, "percentage": 53.05, "elapsed_time": "12:09:31", "remaining_time": "10:45:42"}
97
+ {"current_steps": 950, "total_steps": 1772, "loss": 0.4855, "lr": 5e-06, "epoch": 2.143864598025388, "percentage": 53.61, "elapsed_time": "12:17:08", "remaining_time": "10:37:49"}
98
+ {"current_steps": 960, "total_steps": 1772, "loss": 0.482, "lr": 5e-06, "epoch": 2.1664315937940763, "percentage": 54.18, "elapsed_time": "12:24:44", "remaining_time": "10:29:56"}
99
+ {"current_steps": 970, "total_steps": 1772, "loss": 0.48, "lr": 5e-06, "epoch": 2.1889985895627646, "percentage": 54.74, "elapsed_time": "12:32:21", "remaining_time": "10:22:03"}
100
+ {"current_steps": 980, "total_steps": 1772, "loss": 0.475, "lr": 5e-06, "epoch": 2.211565585331453, "percentage": 55.3, "elapsed_time": "12:39:57", "remaining_time": "10:14:10"}
101
+ {"current_steps": 990, "total_steps": 1772, "loss": 0.4748, "lr": 5e-06, "epoch": 2.234132581100141, "percentage": 55.87, "elapsed_time": "12:47:34", "remaining_time": "10:06:18"}
102
+ {"current_steps": 1000, "total_steps": 1772, "loss": 0.4839, "lr": 5e-06, "epoch": 2.2566995768688294, "percentage": 56.43, "elapsed_time": "12:55:11", "remaining_time": "9:58:26"}
103
+ {"current_steps": 1010, "total_steps": 1772, "loss": 0.4907, "lr": 5e-06, "epoch": 2.2792665726375176, "percentage": 57.0, "elapsed_time": "13:02:47", "remaining_time": "9:50:35"}
104
+ {"current_steps": 1020, "total_steps": 1772, "loss": 0.485, "lr": 5e-06, "epoch": 2.301833568406206, "percentage": 57.56, "elapsed_time": "13:10:24", "remaining_time": "9:42:44"}
105
+ {"current_steps": 1030, "total_steps": 1772, "loss": 0.489, "lr": 5e-06, "epoch": 2.324400564174894, "percentage": 58.13, "elapsed_time": "13:18:01", "remaining_time": "9:34:53"}
106
+ {"current_steps": 1040, "total_steps": 1772, "loss": 0.487, "lr": 5e-06, "epoch": 2.3469675599435824, "percentage": 58.69, "elapsed_time": "13:25:38", "remaining_time": "9:27:03"}
107
+ {"current_steps": 1050, "total_steps": 1772, "loss": 0.4849, "lr": 5e-06, "epoch": 2.3695345557122707, "percentage": 59.26, "elapsed_time": "13:33:15", "remaining_time": "9:19:12"}
108
+ {"current_steps": 1060, "total_steps": 1772, "loss": 0.4844, "lr": 5e-06, "epoch": 2.392101551480959, "percentage": 59.82, "elapsed_time": "13:40:52", "remaining_time": "9:11:22"}
109
+ {"current_steps": 1070, "total_steps": 1772, "loss": 0.4848, "lr": 5e-06, "epoch": 2.414668547249647, "percentage": 60.38, "elapsed_time": "13:48:29", "remaining_time": "9:03:33"}
110
+ {"current_steps": 1080, "total_steps": 1772, "loss": 0.4883, "lr": 5e-06, "epoch": 2.4372355430183354, "percentage": 60.95, "elapsed_time": "13:56:05", "remaining_time": "8:55:43"}
111
+ {"current_steps": 1090, "total_steps": 1772, "loss": 0.4863, "lr": 5e-06, "epoch": 2.459802538787024, "percentage": 61.51, "elapsed_time": "14:03:42", "remaining_time": "8:47:54"}
112
+ {"current_steps": 1100, "total_steps": 1772, "loss": 0.4896, "lr": 5e-06, "epoch": 2.4823695345557124, "percentage": 62.08, "elapsed_time": "14:11:19", "remaining_time": "8:40:04"}
113
+ {"current_steps": 1110, "total_steps": 1772, "loss": 0.4922, "lr": 5e-06, "epoch": 2.5049365303244007, "percentage": 62.64, "elapsed_time": "14:18:56", "remaining_time": "8:32:15"}
114
+ {"current_steps": 1120, "total_steps": 1772, "loss": 0.4838, "lr": 5e-06, "epoch": 2.527503526093089, "percentage": 63.21, "elapsed_time": "14:26:32", "remaining_time": "8:24:27"}
115
+ {"current_steps": 1130, "total_steps": 1772, "loss": 0.4883, "lr": 5e-06, "epoch": 2.550070521861777, "percentage": 63.77, "elapsed_time": "14:34:09", "remaining_time": "8:16:38"}
116
+ {"current_steps": 1140, "total_steps": 1772, "loss": 0.4871, "lr": 5e-06, "epoch": 2.5726375176304654, "percentage": 64.33, "elapsed_time": "14:41:46", "remaining_time": "8:08:50"}
117
+ {"current_steps": 1150, "total_steps": 1772, "loss": 0.4877, "lr": 5e-06, "epoch": 2.5952045133991537, "percentage": 64.9, "elapsed_time": "14:49:22", "remaining_time": "8:01:02"}
118
+ {"current_steps": 1160, "total_steps": 1772, "loss": 0.4915, "lr": 5e-06, "epoch": 2.617771509167842, "percentage": 65.46, "elapsed_time": "14:56:59", "remaining_time": "7:53:14"}
119
+ {"current_steps": 1170, "total_steps": 1772, "loss": 0.4809, "lr": 5e-06, "epoch": 2.64033850493653, "percentage": 66.03, "elapsed_time": "15:04:36", "remaining_time": "7:45:26"}
120
+ {"current_steps": 1180, "total_steps": 1772, "loss": 0.4913, "lr": 5e-06, "epoch": 2.6629055007052185, "percentage": 66.59, "elapsed_time": "15:12:12", "remaining_time": "7:37:39"}
121
+ {"current_steps": 1190, "total_steps": 1772, "loss": 0.4919, "lr": 5e-06, "epoch": 2.685472496473907, "percentage": 67.16, "elapsed_time": "15:19:49", "remaining_time": "7:29:51"}
122
+ {"current_steps": 1200, "total_steps": 1772, "loss": 0.4901, "lr": 5e-06, "epoch": 2.7080394922425954, "percentage": 67.72, "elapsed_time": "15:27:26", "remaining_time": "7:22:04"}
123
+ {"current_steps": 1210, "total_steps": 1772, "loss": 0.4913, "lr": 5e-06, "epoch": 2.7306064880112837, "percentage": 68.28, "elapsed_time": "15:35:02", "remaining_time": "7:14:17"}
124
+ {"current_steps": 1220, "total_steps": 1772, "loss": 0.4884, "lr": 5e-06, "epoch": 2.753173483779972, "percentage": 68.85, "elapsed_time": "15:42:39", "remaining_time": "7:06:30"}
125
+ {"current_steps": 1230, "total_steps": 1772, "loss": 0.4945, "lr": 5e-06, "epoch": 2.77574047954866, "percentage": 69.41, "elapsed_time": "15:50:16", "remaining_time": "6:58:44"}
126
+ {"current_steps": 1240, "total_steps": 1772, "loss": 0.4934, "lr": 5e-06, "epoch": 2.7983074753173485, "percentage": 69.98, "elapsed_time": "15:57:52", "remaining_time": "6:50:57"}
127
+ {"current_steps": 1250, "total_steps": 1772, "loss": 0.4933, "lr": 5e-06, "epoch": 2.8208744710860367, "percentage": 70.54, "elapsed_time": "16:05:29", "remaining_time": "6:43:11"}
128
+ {"current_steps": 1260, "total_steps": 1772, "loss": 0.495, "lr": 5e-06, "epoch": 2.843441466854725, "percentage": 71.11, "elapsed_time": "16:13:06", "remaining_time": "6:35:25"}
129
+ {"current_steps": 1270, "total_steps": 1772, "loss": 0.4919, "lr": 5e-06, "epoch": 2.8660084626234132, "percentage": 71.67, "elapsed_time": "16:20:43", "remaining_time": "6:27:39"}
130
+ {"current_steps": 1280, "total_steps": 1772, "loss": 0.4901, "lr": 5e-06, "epoch": 2.8885754583921015, "percentage": 72.23, "elapsed_time": "16:28:19", "remaining_time": "6:19:53"}
131
+ {"current_steps": 1290, "total_steps": 1772, "loss": 0.4938, "lr": 5e-06, "epoch": 2.9111424541607898, "percentage": 72.8, "elapsed_time": "16:35:56", "remaining_time": "6:12:07"}
132
+ {"current_steps": 1300, "total_steps": 1772, "loss": 0.4889, "lr": 5e-06, "epoch": 2.933709449929478, "percentage": 73.36, "elapsed_time": "16:43:33", "remaining_time": "6:04:22"}
133
+ {"current_steps": 1310, "total_steps": 1772, "loss": 0.493, "lr": 5e-06, "epoch": 2.9562764456981663, "percentage": 73.93, "elapsed_time": "16:51:10", "remaining_time": "5:56:36"}
134
+ {"current_steps": 1320, "total_steps": 1772, "loss": 0.4899, "lr": 5e-06, "epoch": 2.9788434414668545, "percentage": 74.49, "elapsed_time": "16:58:47", "remaining_time": "5:48:51"}
135
+ {"current_steps": 1329, "total_steps": 1772, "eval_loss": 0.6006776094436646, "epoch": 2.9991537376586743, "percentage": 75.0, "elapsed_time": "17:11:53", "remaining_time": "5:43:57"}
136
+ {"current_steps": 1330, "total_steps": 1772, "loss": 0.5325, "lr": 5e-06, "epoch": 3.0014104372355432, "percentage": 75.06, "elapsed_time": "17:13:32", "remaining_time": "5:43:28"}