sedrickkeh commited on
Commit
e3b5599
·
verified ·
1 Parent(s): 63dc119

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 sha256:77ab6bd4888fa3ad59fde35bae043002dcd0fc74c529b44a14e739b5b0c89b6e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb2bd17965c5565729eefc315dc0a31636406e6815851e73c7a9cf03947ebb6
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17512d00a78e7d69bdae69de85d1de184df9b441868a329b310467184bc8468c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cefcdac299cc23a70ca6c119bccf6d5fe97bfe867286ca29cf9fb8cdba1378f5
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02482d851e4ce3e70350c56eb07e9e09bb2d8c196b546adbc4baeda77550edaf
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a9d7e92ae873a39fc44c79179feb69f7b625de4a94451b76a2d47023108e368
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:928961851868c825e9e085b1221cbe54937b3bd4d8cc5cf817c3f2b74f6c0e18
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5a501f8e8c4f844b7dd326063bcddeb9064db61e386506c39806add613df6a8
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -84,3 +84,45 @@
84
  {"current_steps": 830, "total_steps": 1266, "loss": 0.6112, "lr": 5e-06, "epoch": 1.964211771665188, "percentage": 65.56, "elapsed_time": "7:30:10", "remaining_time": "3:56:28"}
85
  {"current_steps": 840, "total_steps": 1266, "loss": 0.5984, "lr": 5e-06, "epoch": 1.9878734102336586, "percentage": 66.35, "elapsed_time": "7:35:29", "remaining_time": "3:50:59"}
86
  {"current_steps": 845, "total_steps": 1266, "eval_loss": 0.640017032623291, "epoch": 1.999704229517894, "percentage": 66.75, "elapsed_time": "7:42:57", "remaining_time": "3:50:39"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
  {"current_steps": 830, "total_steps": 1266, "loss": 0.6112, "lr": 5e-06, "epoch": 1.964211771665188, "percentage": 65.56, "elapsed_time": "7:30:10", "remaining_time": "3:56:28"}
85
  {"current_steps": 840, "total_steps": 1266, "loss": 0.5984, "lr": 5e-06, "epoch": 1.9878734102336586, "percentage": 66.35, "elapsed_time": "7:35:29", "remaining_time": "3:50:59"}
86
  {"current_steps": 845, "total_steps": 1266, "eval_loss": 0.640017032623291, "epoch": 1.999704229517894, "percentage": 66.75, "elapsed_time": "7:42:57", "remaining_time": "3:50:39"}
87
+ {"current_steps": 850, "total_steps": 1266, "loss": 0.612, "lr": 5e-06, "epoch": 2.0118308192842353, "percentage": 67.14, "elapsed_time": "7:46:54", "remaining_time": "3:48:30"}
88
+ {"current_steps": 860, "total_steps": 1266, "loss": 0.5665, "lr": 5e-06, "epoch": 2.0354924578527065, "percentage": 67.93, "elapsed_time": "7:52:13", "remaining_time": "3:42:56"}
89
+ {"current_steps": 870, "total_steps": 1266, "loss": 0.5669, "lr": 5e-06, "epoch": 2.059154096421177, "percentage": 68.72, "elapsed_time": "7:57:31", "remaining_time": "3:37:21"}
90
+ {"current_steps": 880, "total_steps": 1266, "loss": 0.5576, "lr": 5e-06, "epoch": 2.082815734989648, "percentage": 69.51, "elapsed_time": "8:02:50", "remaining_time": "3:31:47"}
91
+ {"current_steps": 890, "total_steps": 1266, "loss": 0.5632, "lr": 5e-06, "epoch": 2.106477373558119, "percentage": 70.3, "elapsed_time": "8:08:11", "remaining_time": "3:26:14"}
92
+ {"current_steps": 900, "total_steps": 1266, "loss": 0.5673, "lr": 5e-06, "epoch": 2.1301390121265897, "percentage": 71.09, "elapsed_time": "8:13:32", "remaining_time": "3:20:42"}
93
+ {"current_steps": 910, "total_steps": 1266, "loss": 0.5608, "lr": 5e-06, "epoch": 2.1538006506950604, "percentage": 71.88, "elapsed_time": "8:18:51", "remaining_time": "3:15:09"}
94
+ {"current_steps": 920, "total_steps": 1266, "loss": 0.5622, "lr": 5e-06, "epoch": 2.1774622892635316, "percentage": 72.67, "elapsed_time": "8:24:11", "remaining_time": "3:09:37"}
95
+ {"current_steps": 930, "total_steps": 1266, "loss": 0.5634, "lr": 5e-06, "epoch": 2.2011239278320023, "percentage": 73.46, "elapsed_time": "8:29:32", "remaining_time": "3:04:05"}
96
+ {"current_steps": 940, "total_steps": 1266, "loss": 0.5642, "lr": 5e-06, "epoch": 2.2247855664004734, "percentage": 74.25, "elapsed_time": "8:34:53", "remaining_time": "2:58:34"}
97
+ {"current_steps": 950, "total_steps": 1266, "loss": 0.5701, "lr": 5e-06, "epoch": 2.248447204968944, "percentage": 75.04, "elapsed_time": "8:40:13", "remaining_time": "2:53:02"}
98
+ {"current_steps": 960, "total_steps": 1266, "loss": 0.5624, "lr": 5e-06, "epoch": 2.272108843537415, "percentage": 75.83, "elapsed_time": "8:45:32", "remaining_time": "2:47:30"}
99
+ {"current_steps": 970, "total_steps": 1266, "loss": 0.5688, "lr": 5e-06, "epoch": 2.295770482105886, "percentage": 76.62, "elapsed_time": "8:50:51", "remaining_time": "2:41:59"}
100
+ {"current_steps": 980, "total_steps": 1266, "loss": 0.5687, "lr": 5e-06, "epoch": 2.3194321206743567, "percentage": 77.41, "elapsed_time": "8:56:12", "remaining_time": "2:36:29"}
101
+ {"current_steps": 990, "total_steps": 1266, "loss": 0.5664, "lr": 5e-06, "epoch": 2.3430937592428274, "percentage": 78.2, "elapsed_time": "9:01:33", "remaining_time": "2:30:58"}
102
+ {"current_steps": 1000, "total_steps": 1266, "loss": 0.5679, "lr": 5e-06, "epoch": 2.3667553978112985, "percentage": 78.99, "elapsed_time": "9:06:55", "remaining_time": "2:25:28"}
103
+ {"current_steps": 1010, "total_steps": 1266, "loss": 0.5661, "lr": 5e-06, "epoch": 2.390417036379769, "percentage": 79.78, "elapsed_time": "9:12:14", "remaining_time": "2:19:58"}
104
+ {"current_steps": 1020, "total_steps": 1266, "loss": 0.5632, "lr": 5e-06, "epoch": 2.4140786749482404, "percentage": 80.57, "elapsed_time": "9:17:34", "remaining_time": "2:14:28"}
105
+ {"current_steps": 1030, "total_steps": 1266, "loss": 0.5646, "lr": 5e-06, "epoch": 2.437740313516711, "percentage": 81.36, "elapsed_time": "9:22:54", "remaining_time": "2:08:58"}
106
+ {"current_steps": 1040, "total_steps": 1266, "loss": 0.5663, "lr": 5e-06, "epoch": 2.4614019520851818, "percentage": 82.15, "elapsed_time": "9:28:15", "remaining_time": "2:03:29"}
107
+ {"current_steps": 1050, "total_steps": 1266, "loss": 0.5705, "lr": 5e-06, "epoch": 2.485063590653653, "percentage": 82.94, "elapsed_time": "9:33:36", "remaining_time": "1:57:59"}
108
+ {"current_steps": 1060, "total_steps": 1266, "loss": 0.5692, "lr": 5e-06, "epoch": 2.5087252292221236, "percentage": 83.73, "elapsed_time": "9:38:57", "remaining_time": "1:52:30"}
109
+ {"current_steps": 1070, "total_steps": 1266, "loss": 0.5693, "lr": 5e-06, "epoch": 2.5323868677905947, "percentage": 84.52, "elapsed_time": "9:44:18", "remaining_time": "1:47:01"}
110
+ {"current_steps": 1080, "total_steps": 1266, "loss": 0.5721, "lr": 5e-06, "epoch": 2.5560485063590654, "percentage": 85.31, "elapsed_time": "9:49:39", "remaining_time": "1:41:33"}
111
+ {"current_steps": 1090, "total_steps": 1266, "loss": 0.5668, "lr": 5e-06, "epoch": 2.579710144927536, "percentage": 86.1, "elapsed_time": "9:55:01", "remaining_time": "1:36:04"}
112
+ {"current_steps": 1100, "total_steps": 1266, "loss": 0.5706, "lr": 5e-06, "epoch": 2.603371783496007, "percentage": 86.89, "elapsed_time": "10:00:22", "remaining_time": "1:30:36"}
113
+ {"current_steps": 1110, "total_steps": 1266, "loss": 0.5643, "lr": 5e-06, "epoch": 2.627033422064478, "percentage": 87.68, "elapsed_time": "10:05:43", "remaining_time": "1:25:07"}
114
+ {"current_steps": 1120, "total_steps": 1266, "loss": 0.5784, "lr": 5e-06, "epoch": 2.6506950606329487, "percentage": 88.47, "elapsed_time": "10:11:04", "remaining_time": "1:19:39"}
115
+ {"current_steps": 1130, "total_steps": 1266, "loss": 0.5642, "lr": 5e-06, "epoch": 2.67435669920142, "percentage": 89.26, "elapsed_time": "10:16:26", "remaining_time": "1:14:11"}
116
+ {"current_steps": 1140, "total_steps": 1266, "loss": 0.5647, "lr": 5e-06, "epoch": 2.6980183377698905, "percentage": 90.05, "elapsed_time": "10:21:48", "remaining_time": "1:08:43"}
117
+ {"current_steps": 1150, "total_steps": 1266, "loss": 0.5717, "lr": 5e-06, "epoch": 2.7216799763383612, "percentage": 90.84, "elapsed_time": "10:27:07", "remaining_time": "1:03:15"}
118
+ {"current_steps": 1160, "total_steps": 1266, "loss": 0.5722, "lr": 5e-06, "epoch": 2.7453416149068324, "percentage": 91.63, "elapsed_time": "10:32:28", "remaining_time": "0:57:47"}
119
+ {"current_steps": 1170, "total_steps": 1266, "loss": 0.5673, "lr": 5e-06, "epoch": 2.769003253475303, "percentage": 92.42, "elapsed_time": "10:37:50", "remaining_time": "0:52:20"}
120
+ {"current_steps": 1180, "total_steps": 1266, "loss": 0.5673, "lr": 5e-06, "epoch": 2.792664892043774, "percentage": 93.21, "elapsed_time": "10:43:11", "remaining_time": "0:46:52"}
121
+ {"current_steps": 1190, "total_steps": 1266, "loss": 0.5712, "lr": 5e-06, "epoch": 2.816326530612245, "percentage": 94.0, "elapsed_time": "10:48:31", "remaining_time": "0:41:25"}
122
+ {"current_steps": 1200, "total_steps": 1266, "loss": 0.5689, "lr": 5e-06, "epoch": 2.8399881691807156, "percentage": 94.79, "elapsed_time": "10:53:53", "remaining_time": "0:35:57"}
123
+ {"current_steps": 1210, "total_steps": 1266, "loss": 0.5683, "lr": 5e-06, "epoch": 2.8636498077491868, "percentage": 95.58, "elapsed_time": "10:59:14", "remaining_time": "0:30:30"}
124
+ {"current_steps": 1220, "total_steps": 1266, "loss": 0.5611, "lr": 5e-06, "epoch": 2.8873114463176575, "percentage": 96.37, "elapsed_time": "11:04:36", "remaining_time": "0:25:03"}
125
+ {"current_steps": 1230, "total_steps": 1266, "loss": 0.5713, "lr": 5e-06, "epoch": 2.9109730848861286, "percentage": 97.16, "elapsed_time": "11:09:57", "remaining_time": "0:19:36"}
126
+ {"current_steps": 1240, "total_steps": 1266, "loss": 0.5703, "lr": 5e-06, "epoch": 2.9346347234545993, "percentage": 97.95, "elapsed_time": "11:15:17", "remaining_time": "0:14:09"}
127
+ {"current_steps": 1250, "total_steps": 1266, "loss": 0.5791, "lr": 5e-06, "epoch": 2.95829636202307, "percentage": 98.74, "elapsed_time": "11:20:37", "remaining_time": "0:08:42"}
128
+ {"current_steps": 1260, "total_steps": 1266, "loss": 0.5714, "lr": 5e-06, "epoch": 2.9819580005915407, "percentage": 99.53, "elapsed_time": "11:25:58", "remaining_time": "0:03:15"}