ryanmarten commited on
Commit
19f1012
·
verified ·
1 Parent(s): 524cc90

Training in progress, epoch 4

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7807ca5bb877c0d4db187239f9c5c3ca4c15e21df69bb9c1877c2839573d095
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6876f39e5952281ec1fdcea0c37aa402f73d249e882955b9febf93d4f42c8bca
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:606ff387bc3bd0792b543cb6d874f2ed85e49bb0b422e10afcd7162b3b1cc60d
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2db154239dcfb4f899410fb0c63d28cc9817575c25ea29c7a9723943851564b4
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b6055adb72abb3ca5ee7f69d3974066b81881c86da872292fa7825a4fe3bc55
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:badfdb4140c21afae3548ce89196bff0003bafd49da7e5c2303c03a5ca0d7b58
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c2be3cfbd1fb576257b45025247df8d1334afac30f42fe5640367f807b0952e
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5635de501441dbded225af899de6a9e829764939a5aee6a6b2d29bb246a0c3
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -131,3 +131,36 @@
131
  {"current_steps": 131, "total_steps": 224, "loss": 1.2171, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "2:51:06", "remaining_time": "2:01:28"}
132
  {"current_steps": 132, "total_steps": 224, "loss": 1.2108, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "2:52:17", "remaining_time": "2:00:05"}
133
  {"current_steps": 133, "total_steps": 224, "loss": 1.2043, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "2:53:36", "remaining_time": "1:58:46"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
131
  {"current_steps": 131, "total_steps": 224, "loss": 1.2171, "lr": 8.830446780279175e-06, "epoch": 4.010126582278481, "percentage": 58.48, "elapsed_time": "2:51:06", "remaining_time": "2:01:28"}
132
  {"current_steps": 132, "total_steps": 224, "loss": 1.2108, "lr": 8.675370457533122e-06, "epoch": 4.040506329113924, "percentage": 58.93, "elapsed_time": "2:52:17", "remaining_time": "2:00:05"}
133
  {"current_steps": 133, "total_steps": 224, "loss": 1.2043, "lr": 8.520617723396702e-06, "epoch": 4.0708860759493675, "percentage": 59.38, "elapsed_time": "2:53:36", "remaining_time": "1:58:46"}
134
+ {"current_steps": 134, "total_steps": 224, "loss": 1.1994, "lr": 8.366226381814698e-06, "epoch": 4.10126582278481, "percentage": 59.82, "elapsed_time": "2:54:49", "remaining_time": "1:57:24"}
135
+ {"current_steps": 135, "total_steps": 224, "loss": 1.1415, "lr": 8.212234148448708e-06, "epoch": 4.131645569620253, "percentage": 60.27, "elapsed_time": "2:56:07", "remaining_time": "1:56:06"}
136
+ {"current_steps": 136, "total_steps": 224, "loss": 1.161, "lr": 8.058678641463724e-06, "epoch": 4.162025316455696, "percentage": 60.71, "elapsed_time": "2:57:20", "remaining_time": "1:54:44"}
137
+ {"current_steps": 137, "total_steps": 224, "loss": 1.1673, "lr": 7.905597372338558e-06, "epoch": 4.192405063291139, "percentage": 61.16, "elapsed_time": "2:58:37", "remaining_time": "1:53:25"}
138
+ {"current_steps": 138, "total_steps": 224, "loss": 1.2017, "lr": 7.753027736702283e-06, "epoch": 4.222784810126583, "percentage": 61.61, "elapsed_time": "3:00:02", "remaining_time": "1:52:12"}
139
+ {"current_steps": 139, "total_steps": 224, "loss": 1.1799, "lr": 7.601007005199022e-06, "epoch": 4.253164556962025, "percentage": 62.05, "elapsed_time": "3:01:20", "remaining_time": "1:50:53"}
140
+ {"current_steps": 140, "total_steps": 224, "loss": 1.171, "lr": 7.449572314383237e-06, "epoch": 4.283544303797468, "percentage": 62.5, "elapsed_time": "3:02:40", "remaining_time": "1:49:36"}
141
+ {"current_steps": 141, "total_steps": 224, "loss": 1.2067, "lr": 7.298760657647779e-06, "epoch": 4.313924050632911, "percentage": 62.95, "elapsed_time": "3:04:00", "remaining_time": "1:48:18"}
142
+ {"current_steps": 142, "total_steps": 224, "loss": 1.2001, "lr": 7.148608876186931e-06, "epoch": 4.3443037974683545, "percentage": 63.39, "elapsed_time": "3:05:16", "remaining_time": "1:46:59"}
143
+ {"current_steps": 143, "total_steps": 224, "loss": 1.1856, "lr": 6.999153649996595e-06, "epoch": 4.374683544303798, "percentage": 63.84, "elapsed_time": "3:06:26", "remaining_time": "1:45:36"}
144
+ {"current_steps": 144, "total_steps": 224, "loss": 1.174, "lr": 6.8504314889138956e-06, "epoch": 4.405063291139241, "percentage": 64.29, "elapsed_time": "3:07:29", "remaining_time": "1:44:09"}
145
+ {"current_steps": 145, "total_steps": 224, "loss": 1.1685, "lr": 6.702478723698336e-06, "epoch": 4.435443037974683, "percentage": 64.73, "elapsed_time": "3:08:46", "remaining_time": "1:42:51"}
146
+ {"current_steps": 146, "total_steps": 224, "loss": 1.1392, "lr": 6.555331497156671e-06, "epoch": 4.465822784810126, "percentage": 65.18, "elapsed_time": "3:10:08", "remaining_time": "1:41:34"}
147
+ {"current_steps": 147, "total_steps": 224, "loss": 1.1866, "lr": 6.4090257553137566e-06, "epoch": 4.49620253164557, "percentage": 65.62, "elapsed_time": "3:11:18", "remaining_time": "1:40:12"}
148
+ {"current_steps": 148, "total_steps": 224, "loss": 1.1458, "lr": 6.263597238631405e-06, "epoch": 4.526582278481013, "percentage": 66.07, "elapsed_time": "3:12:30", "remaining_time": "1:38:51"}
149
+ {"current_steps": 149, "total_steps": 224, "loss": 1.1861, "lr": 6.119081473277502e-06, "epoch": 4.556962025316456, "percentage": 66.52, "elapsed_time": "3:14:00", "remaining_time": "1:37:39"}
150
+ {"current_steps": 150, "total_steps": 224, "loss": 1.1776, "lr": 5.975513762447465e-06, "epoch": 4.587341772151898, "percentage": 66.96, "elapsed_time": "3:15:15", "remaining_time": "1:36:19"}
151
+ {"current_steps": 151, "total_steps": 224, "loss": 1.1705, "lr": 5.832929177740134e-06, "epoch": 4.6177215189873415, "percentage": 67.41, "elapsed_time": "3:16:26", "remaining_time": "1:34:58"}
152
+ {"current_steps": 152, "total_steps": 224, "loss": 1.2053, "lr": 5.6913625505902966e-06, "epoch": 4.648101265822785, "percentage": 67.86, "elapsed_time": "3:17:39", "remaining_time": "1:33:37"}
153
+ {"current_steps": 153, "total_steps": 224, "loss": 1.2065, "lr": 5.550848463759835e-06, "epoch": 4.678481012658228, "percentage": 68.3, "elapsed_time": "3:18:51", "remaining_time": "1:32:16"}
154
+ {"current_steps": 154, "total_steps": 224, "loss": 1.1688, "lr": 5.411421242889643e-06, "epoch": 4.708860759493671, "percentage": 68.75, "elapsed_time": "3:20:08", "remaining_time": "1:30:58"}
155
+ {"current_steps": 155, "total_steps": 224, "loss": 1.1829, "lr": 5.273114948114346e-06, "epoch": 4.739240506329114, "percentage": 69.2, "elapsed_time": "3:21:34", "remaining_time": "1:29:44"}
156
+ {"current_steps": 156, "total_steps": 224, "loss": 1.2133, "lr": 5.135963365741892e-06, "epoch": 4.769620253164557, "percentage": 69.64, "elapsed_time": "3:22:54", "remaining_time": "1:28:26"}
157
+ {"current_steps": 157, "total_steps": 224, "loss": 1.1912, "lr": 5.000000000000003e-06, "epoch": 4.8, "percentage": 70.09, "elapsed_time": "3:24:12", "remaining_time": "1:27:08"}
158
+ {"current_steps": 158, "total_steps": 224, "loss": 1.1425, "lr": 4.865258064851579e-06, "epoch": 4.830379746835443, "percentage": 70.54, "elapsed_time": "3:25:29", "remaining_time": "1:25:50"}
159
+ {"current_steps": 159, "total_steps": 224, "loss": 1.1611, "lr": 4.731770475880995e-06, "epoch": 4.860759493670886, "percentage": 70.98, "elapsed_time": "3:26:51", "remaining_time": "1:24:33"}
160
+ {"current_steps": 160, "total_steps": 224, "loss": 1.1407, "lr": 4.599569842253244e-06, "epoch": 4.891139240506329, "percentage": 71.43, "elapsed_time": "3:28:08", "remaining_time": "1:23:15"}
161
+ {"current_steps": 161, "total_steps": 224, "loss": 1.1649, "lr": 4.468688458748006e-06, "epoch": 4.921518987341772, "percentage": 71.88, "elapsed_time": "3:29:21", "remaining_time": "1:21:55"}
162
+ {"current_steps": 162, "total_steps": 224, "loss": 1.1881, "lr": 4.339158297870469e-06, "epoch": 4.951898734177215, "percentage": 72.32, "elapsed_time": "3:30:45", "remaining_time": "1:20:39"}
163
+ {"current_steps": 163, "total_steps": 224, "loss": 1.1918, "lr": 4.211011002040885e-06, "epoch": 4.982278481012658, "percentage": 72.77, "elapsed_time": "3:32:10", "remaining_time": "1:19:24"}
164
+ {"current_steps": 164, "total_steps": 224, "loss": 1.1736, "lr": 4.084277875864776e-06, "epoch": 5.020253164556962, "percentage": 73.21, "elapsed_time": "3:34:26", "remaining_time": "1:18:27"}
165
+ {"current_steps": 165, "total_steps": 224, "loss": 1.1528, "lr": 3.958989878485644e-06, "epoch": 5.050632911392405, "percentage": 73.66, "elapsed_time": "3:35:40", "remaining_time": "1:17:07"}
166
+ {"current_steps": 166, "total_steps": 224, "loss": 1.1458, "lr": 3.83517761602209e-06, "epoch": 5.0810126582278485, "percentage": 74.11, "elapsed_time": "3:36:55", "remaining_time": "1:15:47"}