sedrickkeh commited on
Commit
4ca98dc
·
verified ·
1 Parent(s): 349be3d

Training in progress, epoch 2

Browse files
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f56ad291be905b87447148ef8aba97253d8bb10f05c9ea02c8676cd28053842a
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85febb1d78fbf93c1481520e58440217728c1e6b4b6f16c111b3561b246b26ac
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac699851822ab6bdc7cf5b8e312c934963c7aa3fe13198c0f63dda0bdc9af7a1
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f751e29fbcae66c1bedad5ddc23e4d91cd9af862ae78034f49630df3ad2359a
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f10a846c950966f935e59580589f31f58ed1129bbf39ed1e2c744d96dd197c3
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f950bc3430f4e06965fdb39998d3510b1e61feee3b520b2b092d9676b7e0a14f
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -99,3 +99,51 @@
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.511, "learning_rate": 2e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:20:20", "remaining_time": "7:48:37"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.06807009875774384, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:35:37", "remaining_time": "7:46:23"}
101
  {"current_steps": 990, "total_steps": 1479, "loss": 0.4922, "learning_rate": 2e-06, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:39:04", "remaining_time": "7:43:50"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
  {"current_steps": 980, "total_steps": 1479, "loss": 0.511, "learning_rate": 2e-06, "epoch": 1.9848101265822784, "percentage": 66.26, "elapsed_time": "15:20:20", "remaining_time": "7:48:37"}
100
  {"current_steps": 987, "total_steps": 1479, "eval_loss": 0.06807009875774384, "epoch": 1.998987341772152, "percentage": 66.73, "elapsed_time": "15:35:37", "remaining_time": "7:46:23"}
101
  {"current_steps": 990, "total_steps": 1479, "loss": 0.4922, "learning_rate": 2e-06, "epoch": 2.0050632911392405, "percentage": 66.94, "elapsed_time": "15:39:04", "remaining_time": "7:43:50"}
102
+ {"current_steps": 1000, "total_steps": 1479, "loss": 0.4609, "learning_rate": 2e-06, "epoch": 2.0253164556962027, "percentage": 67.61, "elapsed_time": "15:48:23", "remaining_time": "7:34:16"}
103
+ {"current_steps": 1010, "total_steps": 1479, "loss": 0.461, "learning_rate": 2e-06, "epoch": 2.0455696202531644, "percentage": 68.29, "elapsed_time": "15:57:41", "remaining_time": "7:24:42"}
104
+ {"current_steps": 1020, "total_steps": 1479, "loss": 0.457, "learning_rate": 2e-06, "epoch": 2.0658227848101265, "percentage": 68.97, "elapsed_time": "16:07:00", "remaining_time": "7:15:09"}
105
+ {"current_steps": 1030, "total_steps": 1479, "loss": 0.4564, "learning_rate": 2e-06, "epoch": 2.0860759493670886, "percentage": 69.64, "elapsed_time": "16:16:18", "remaining_time": "7:05:35"}
106
+ {"current_steps": 1040, "total_steps": 1479, "loss": 0.4538, "learning_rate": 2e-06, "epoch": 2.1063291139240508, "percentage": 70.32, "elapsed_time": "16:25:35", "remaining_time": "6:56:01"}
107
+ {"current_steps": 1050, "total_steps": 1479, "loss": 0.463, "learning_rate": 2e-06, "epoch": 2.1265822784810124, "percentage": 70.99, "elapsed_time": "16:34:53", "remaining_time": "6:46:29"}
108
+ {"current_steps": 1060, "total_steps": 1479, "loss": 0.4576, "learning_rate": 2e-06, "epoch": 2.1468354430379746, "percentage": 71.67, "elapsed_time": "16:44:12", "remaining_time": "6:36:56"}
109
+ {"current_steps": 1070, "total_steps": 1479, "loss": 0.4598, "learning_rate": 2e-06, "epoch": 2.1670886075949367, "percentage": 72.35, "elapsed_time": "16:53:31", "remaining_time": "6:27:24"}
110
+ {"current_steps": 1080, "total_steps": 1479, "loss": 0.4578, "learning_rate": 2e-06, "epoch": 2.187341772151899, "percentage": 73.02, "elapsed_time": "17:02:48", "remaining_time": "6:17:52"}
111
+ {"current_steps": 1090, "total_steps": 1479, "loss": 0.4545, "learning_rate": 2e-06, "epoch": 2.207594936708861, "percentage": 73.7, "elapsed_time": "17:12:06", "remaining_time": "6:08:20"}
112
+ {"current_steps": 1100, "total_steps": 1479, "loss": 0.4649, "learning_rate": 2e-06, "epoch": 2.2278481012658227, "percentage": 74.37, "elapsed_time": "17:21:23", "remaining_time": "5:58:48"}
113
+ {"current_steps": 1110, "total_steps": 1479, "loss": 0.4602, "learning_rate": 2e-06, "epoch": 2.248101265822785, "percentage": 75.05, "elapsed_time": "17:30:42", "remaining_time": "5:49:17"}
114
+ {"current_steps": 1120, "total_steps": 1479, "loss": 0.4619, "learning_rate": 2e-06, "epoch": 2.268354430379747, "percentage": 75.73, "elapsed_time": "17:40:00", "remaining_time": "5:39:46"}
115
+ {"current_steps": 1130, "total_steps": 1479, "loss": 0.4635, "learning_rate": 2e-06, "epoch": 2.2886075949367086, "percentage": 76.4, "elapsed_time": "17:49:18", "remaining_time": "5:30:15"}
116
+ {"current_steps": 1140, "total_steps": 1479, "loss": 0.4581, "learning_rate": 2e-06, "epoch": 2.3088607594936708, "percentage": 77.08, "elapsed_time": "17:58:37", "remaining_time": "5:20:44"}
117
+ {"current_steps": 1150, "total_steps": 1479, "loss": 0.4658, "learning_rate": 2e-06, "epoch": 2.329113924050633, "percentage": 77.76, "elapsed_time": "18:07:55", "remaining_time": "5:11:14"}
118
+ {"current_steps": 1160, "total_steps": 1479, "loss": 0.4653, "learning_rate": 2e-06, "epoch": 2.349367088607595, "percentage": 78.43, "elapsed_time": "18:17:13", "remaining_time": "5:01:44"}
119
+ {"current_steps": 1170, "total_steps": 1479, "loss": 0.4654, "learning_rate": 2e-06, "epoch": 2.369620253164557, "percentage": 79.11, "elapsed_time": "18:26:32", "remaining_time": "4:52:14"}
120
+ {"current_steps": 1180, "total_steps": 1479, "loss": 0.4647, "learning_rate": 2e-06, "epoch": 2.389873417721519, "percentage": 79.78, "elapsed_time": "18:35:51", "remaining_time": "4:42:44"}
121
+ {"current_steps": 1190, "total_steps": 1479, "loss": 0.4643, "learning_rate": 2e-06, "epoch": 2.410126582278481, "percentage": 80.46, "elapsed_time": "18:45:09", "remaining_time": "4:33:15"}
122
+ {"current_steps": 1200, "total_steps": 1479, "loss": 0.4627, "learning_rate": 2e-06, "epoch": 2.430379746835443, "percentage": 81.14, "elapsed_time": "18:54:27", "remaining_time": "4:23:45"}
123
+ {"current_steps": 1210, "total_steps": 1479, "loss": 0.4611, "learning_rate": 2e-06, "epoch": 2.4506329113924052, "percentage": 81.81, "elapsed_time": "19:03:46", "remaining_time": "4:14:16"}
124
+ {"current_steps": 1220, "total_steps": 1479, "loss": 0.4646, "learning_rate": 2e-06, "epoch": 2.470886075949367, "percentage": 82.49, "elapsed_time": "19:13:03", "remaining_time": "4:04:47"}
125
+ {"current_steps": 1230, "total_steps": 1479, "loss": 0.4638, "learning_rate": 2e-06, "epoch": 2.491139240506329, "percentage": 83.16, "elapsed_time": "19:22:21", "remaining_time": "3:55:18"}
126
+ {"current_steps": 1240, "total_steps": 1479, "loss": 0.4681, "learning_rate": 2e-06, "epoch": 2.511392405063291, "percentage": 83.84, "elapsed_time": "19:31:40", "remaining_time": "3:45:49"}
127
+ {"current_steps": 1250, "total_steps": 1479, "loss": 0.4602, "learning_rate": 2e-06, "epoch": 2.5316455696202533, "percentage": 84.52, "elapsed_time": "19:40:58", "remaining_time": "3:36:21"}
128
+ {"current_steps": 1260, "total_steps": 1479, "loss": 0.4553, "learning_rate": 2e-06, "epoch": 2.5518987341772155, "percentage": 85.19, "elapsed_time": "19:50:15", "remaining_time": "3:26:52"}
129
+ {"current_steps": 1270, "total_steps": 1479, "loss": 0.4626, "learning_rate": 2e-06, "epoch": 2.572151898734177, "percentage": 85.87, "elapsed_time": "19:59:32", "remaining_time": "3:17:24"}
130
+ {"current_steps": 1280, "total_steps": 1479, "loss": 0.4649, "learning_rate": 2e-06, "epoch": 2.5924050632911393, "percentage": 86.54, "elapsed_time": "20:08:50", "remaining_time": "3:07:56"}
131
+ {"current_steps": 1290, "total_steps": 1479, "loss": 0.4704, "learning_rate": 2e-06, "epoch": 2.6126582278481014, "percentage": 87.22, "elapsed_time": "20:18:09", "remaining_time": "2:58:28"}
132
+ {"current_steps": 1300, "total_steps": 1479, "loss": 0.4638, "learning_rate": 2e-06, "epoch": 2.632911392405063, "percentage": 87.9, "elapsed_time": "20:27:28", "remaining_time": "2:49:00"}
133
+ {"current_steps": 1310, "total_steps": 1479, "loss": 0.4629, "learning_rate": 2e-06, "epoch": 2.6531645569620252, "percentage": 88.57, "elapsed_time": "20:36:47", "remaining_time": "2:39:33"}
134
+ {"current_steps": 1320, "total_steps": 1479, "loss": 0.4654, "learning_rate": 2e-06, "epoch": 2.6734177215189874, "percentage": 89.25, "elapsed_time": "20:46:05", "remaining_time": "2:30:05"}
135
+ {"current_steps": 1330, "total_steps": 1479, "loss": 0.468, "learning_rate": 2e-06, "epoch": 2.6936708860759495, "percentage": 89.93, "elapsed_time": "20:55:22", "remaining_time": "2:20:38"}
136
+ {"current_steps": 1340, "total_steps": 1479, "loss": 0.4656, "learning_rate": 2e-06, "epoch": 2.7139240506329116, "percentage": 90.6, "elapsed_time": "21:04:41", "remaining_time": "2:11:11"}
137
+ {"current_steps": 1350, "total_steps": 1479, "loss": 0.4642, "learning_rate": 2e-06, "epoch": 2.7341772151898733, "percentage": 91.28, "elapsed_time": "21:13:59", "remaining_time": "2:01:44"}
138
+ {"current_steps": 1360, "total_steps": 1479, "loss": 0.4599, "learning_rate": 2e-06, "epoch": 2.7544303797468355, "percentage": 91.95, "elapsed_time": "21:23:16", "remaining_time": "1:52:17"}
139
+ {"current_steps": 1370, "total_steps": 1479, "loss": 0.4659, "learning_rate": 2e-06, "epoch": 2.7746835443037976, "percentage": 92.63, "elapsed_time": "21:32:33", "remaining_time": "1:42:50"}
140
+ {"current_steps": 1380, "total_steps": 1479, "loss": 0.4636, "learning_rate": 2e-06, "epoch": 2.7949367088607593, "percentage": 93.31, "elapsed_time": "21:41:52", "remaining_time": "1:33:23"}
141
+ {"current_steps": 1390, "total_steps": 1479, "loss": 0.4662, "learning_rate": 2e-06, "epoch": 2.8151898734177214, "percentage": 93.98, "elapsed_time": "21:51:10", "remaining_time": "1:23:57"}
142
+ {"current_steps": 1400, "total_steps": 1479, "loss": 0.4594, "learning_rate": 2e-06, "epoch": 2.8354430379746836, "percentage": 94.66, "elapsed_time": "22:00:28", "remaining_time": "1:14:30"}
143
+ {"current_steps": 1410, "total_steps": 1479, "loss": 0.4684, "learning_rate": 2e-06, "epoch": 2.8556962025316457, "percentage": 95.33, "elapsed_time": "22:09:45", "remaining_time": "1:05:04"}
144
+ {"current_steps": 1420, "total_steps": 1479, "loss": 0.4633, "learning_rate": 2e-06, "epoch": 2.875949367088608, "percentage": 96.01, "elapsed_time": "22:19:02", "remaining_time": "0:55:38"}
145
+ {"current_steps": 1430, "total_steps": 1479, "loss": 0.4641, "learning_rate": 2e-06, "epoch": 2.8962025316455695, "percentage": 96.69, "elapsed_time": "22:28:20", "remaining_time": "0:46:12"}
146
+ {"current_steps": 1440, "total_steps": 1479, "loss": 0.4665, "learning_rate": 2e-06, "epoch": 2.9164556962025316, "percentage": 97.36, "elapsed_time": "22:37:38", "remaining_time": "0:36:46"}
147
+ {"current_steps": 1450, "total_steps": 1479, "loss": 0.4752, "learning_rate": 2e-06, "epoch": 2.9367088607594938, "percentage": 98.04, "elapsed_time": "22:46:57", "remaining_time": "0:27:20"}
148
+ {"current_steps": 1460, "total_steps": 1479, "loss": 0.4618, "learning_rate": 2e-06, "epoch": 2.9569620253164555, "percentage": 98.72, "elapsed_time": "22:56:14", "remaining_time": "0:17:54"}
149
+ {"current_steps": 1470, "total_steps": 1479, "loss": 0.4663, "learning_rate": 2e-06, "epoch": 2.9772151898734176, "percentage": 99.39, "elapsed_time": "23:05:33", "remaining_time": "0:08:28"}