penfever commited on
Commit
0c424a6
·
verified ·
1 Parent(s): a59a4b5

Training in progress, step 800

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8edf1689671b5167eab01aefc02dc9a307f75355c75c8d77fb8cb4b0b6dfb354
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5744ed4b9af8c65ba62454dfdb1db96025434d4457aca0ae3b4a48c1c3fea83f
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0094fe136b9c1e70d1ef9c0d70b1a85fa73d7f94c4be0cc01e1a29228d6be3c9
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9abfa3a7e4c84edf2a2b2abb9191cd8035b54b9af2992b32bf87bfe4a558b3
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6e54d439604df655963dbd916fa3bdee78851b9500a0f4ad6e95b84721cbcbb
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6199fe5cf3823340f77b85fa2134450a60ce65e1db3b46b12f0514c45418bbd2
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e15f6a202f08396e706f15d0499579279a80864fbd29912c70c6f4a169e2ba6
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12b116fd9c3d93288f5dfc64b7523bdb32310b54d139fb86668c3eefb37dce6
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -122,3 +122,42 @@
122
  {"current_steps": 610, "total_steps": 1652, "loss": 0.1775, "lr": 3.1851278939945974e-05, "epoch": 2.5859872611464967, "percentage": 36.92, "elapsed_time": "6:27:20", "remaining_time": "11:01:40"}
123
  {"current_steps": 615, "total_steps": 1652, "loss": 0.2035, "lr": 3.1680322120639436e-05, "epoch": 2.6072186836518045, "percentage": 37.23, "elapsed_time": "6:30:29", "remaining_time": "10:58:26"}
124
  {"current_steps": 620, "total_steps": 1652, "loss": 0.1815, "lr": 3.150806017392145e-05, "epoch": 2.6284501061571124, "percentage": 37.53, "elapsed_time": "6:33:39", "remaining_time": "10:55:15"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
122
  {"current_steps": 610, "total_steps": 1652, "loss": 0.1775, "lr": 3.1851278939945974e-05, "epoch": 2.5859872611464967, "percentage": 36.92, "elapsed_time": "6:27:20", "remaining_time": "11:01:40"}
123
  {"current_steps": 615, "total_steps": 1652, "loss": 0.2035, "lr": 3.1680322120639436e-05, "epoch": 2.6072186836518045, "percentage": 37.23, "elapsed_time": "6:30:29", "remaining_time": "10:58:26"}
124
  {"current_steps": 620, "total_steps": 1652, "loss": 0.1815, "lr": 3.150806017392145e-05, "epoch": 2.6284501061571124, "percentage": 37.53, "elapsed_time": "6:33:39", "remaining_time": "10:55:15"}
125
+ {"current_steps": 625, "total_steps": 1652, "loss": 0.1946, "lr": 3.1334512347873215e-05, "epoch": 2.6496815286624202, "percentage": 37.83, "elapsed_time": "6:36:49", "remaining_time": "10:52:04"}
126
+ {"current_steps": 630, "total_steps": 1652, "loss": 0.1946, "lr": 3.1159698034256595e-05, "epoch": 2.670912951167728, "percentage": 38.14, "elapsed_time": "6:39:58", "remaining_time": "10:48:50"}
127
+ {"current_steps": 635, "total_steps": 1652, "loss": 0.2026, "lr": 3.098363676634732e-05, "epoch": 2.692144373673036, "percentage": 38.44, "elapsed_time": "6:43:06", "remaining_time": "10:45:35"}
128
+ {"current_steps": 640, "total_steps": 1652, "loss": 0.1906, "lr": 3.080634821675239e-05, "epoch": 2.713375796178344, "percentage": 38.74, "elapsed_time": "6:46:14", "remaining_time": "10:42:22"}
129
+ {"current_steps": 645, "total_steps": 1652, "loss": 0.1943, "lr": 3.0627852195211944e-05, "epoch": 2.7346072186836516, "percentage": 39.04, "elapsed_time": "6:49:24", "remaining_time": "10:39:10"}
130
+ {"current_steps": 650, "total_steps": 1652, "loss": 0.1871, "lr": 3.0448168646385733e-05, "epoch": 2.7558386411889595, "percentage": 39.35, "elapsed_time": "6:52:32", "remaining_time": "10:35:57"}
131
+ {"current_steps": 655, "total_steps": 1652, "loss": 0.2121, "lr": 3.0267317647624584e-05, "epoch": 2.777070063694268, "percentage": 39.65, "elapsed_time": "6:55:40", "remaining_time": "10:32:43"}
132
+ {"current_steps": 660, "total_steps": 1652, "loss": 0.2165, "lr": 3.0085319406727003e-05, "epoch": 2.798301486199575, "percentage": 39.95, "elapsed_time": "6:58:48", "remaining_time": "10:29:29"}
133
+ {"current_steps": 665, "total_steps": 1652, "loss": 0.1886, "lr": 2.9902194259681203e-05, "epoch": 2.8195329087048835, "percentage": 40.25, "elapsed_time": "7:01:57", "remaining_time": "10:26:17"}
134
+ {"current_steps": 670, "total_steps": 1652, "loss": 0.1662, "lr": 2.9717962668392837e-05, "epoch": 2.840764331210191, "percentage": 40.56, "elapsed_time": "7:05:06", "remaining_time": "10:23:04"}
135
+ {"current_steps": 675, "total_steps": 1652, "loss": 0.186, "lr": 2.9532645218398608e-05, "epoch": 2.861995753715499, "percentage": 40.86, "elapsed_time": "7:08:15", "remaining_time": "10:19:52"}
136
+ {"current_steps": 680, "total_steps": 1652, "loss": 0.1798, "lr": 2.9346262616566128e-05, "epoch": 2.8832271762208066, "percentage": 41.16, "elapsed_time": "7:11:24", "remaining_time": "10:16:39"}
137
+ {"current_steps": 685, "total_steps": 1652, "loss": 0.1856, "lr": 2.9158835688780188e-05, "epoch": 2.904458598726115, "percentage": 41.46, "elapsed_time": "7:14:32", "remaining_time": "10:13:26"}
138
+ {"current_steps": 690, "total_steps": 1652, "loss": 0.1673, "lr": 2.89703853776157e-05, "epoch": 2.9256900212314223, "percentage": 41.77, "elapsed_time": "7:17:40", "remaining_time": "10:10:12"}
139
+ {"current_steps": 695, "total_steps": 1652, "loss": 0.1836, "lr": 2.878093273999765e-05, "epoch": 2.9469214437367306, "percentage": 42.07, "elapsed_time": "7:20:49", "remaining_time": "10:07:00"}
140
+ {"current_steps": 700, "total_steps": 1652, "loss": 0.1885, "lr": 2.859049894484828e-05, "epoch": 2.968152866242038, "percentage": 42.37, "elapsed_time": "7:23:57", "remaining_time": "10:03:46"}
141
+ {"current_steps": 705, "total_steps": 1652, "loss": 0.2006, "lr": 2.8399105270721668e-05, "epoch": 2.9893842887473463, "percentage": 42.68, "elapsed_time": "7:27:06", "remaining_time": "10:00:34"}
142
+ {"current_steps": 710, "total_steps": 1652, "loss": 0.168, "lr": 2.8206773103426187e-05, "epoch": 3.008492569002123, "percentage": 42.98, "elapsed_time": "7:29:57", "remaining_time": "9:56:58"}
143
+ {"current_steps": 715, "total_steps": 1652, "loss": 0.2028, "lr": 2.8013523933634875e-05, "epoch": 3.029723991507431, "percentage": 43.28, "elapsed_time": "7:33:05", "remaining_time": "9:53:46"}
144
+ {"current_steps": 720, "total_steps": 1652, "loss": 0.1776, "lr": 2.7819379354484124e-05, "epoch": 3.050955414012739, "percentage": 43.58, "elapsed_time": "7:36:14", "remaining_time": "9:50:34"}
145
+ {"current_steps": 725, "total_steps": 1652, "loss": 0.1852, "lr": 2.762436105916094e-05, "epoch": 3.0721868365180467, "percentage": 43.89, "elapsed_time": "7:39:23", "remaining_time": "9:47:22"}
146
+ {"current_steps": 730, "total_steps": 1652, "loss": 0.2002, "lr": 2.742849083847899e-05, "epoch": 3.0934182590233545, "percentage": 44.19, "elapsed_time": "7:42:31", "remaining_time": "9:44:10"}
147
+ {"current_steps": 735, "total_steps": 1652, "loss": 0.1666, "lr": 2.7231790578443785e-05, "epoch": 3.1146496815286624, "percentage": 44.49, "elapsed_time": "7:45:41", "remaining_time": "9:41:00"}
148
+ {"current_steps": 740, "total_steps": 1652, "loss": 0.1877, "lr": 2.7034282257807136e-05, "epoch": 3.1358811040339702, "percentage": 44.79, "elapsed_time": "7:48:50", "remaining_time": "9:37:49"}
149
+ {"current_steps": 745, "total_steps": 1652, "loss": 0.1819, "lr": 2.683598794561138e-05, "epoch": 3.157112526539278, "percentage": 45.1, "elapsed_time": "7:51:59", "remaining_time": "9:34:37"}
150
+ {"current_steps": 750, "total_steps": 1652, "loss": 0.1758, "lr": 2.66369297987234e-05, "epoch": 3.178343949044586, "percentage": 45.4, "elapsed_time": "7:55:09", "remaining_time": "9:31:27"}
151
+ {"current_steps": 755, "total_steps": 1652, "loss": 0.1607, "lr": 2.643713005935888e-05, "epoch": 3.199575371549894, "percentage": 45.7, "elapsed_time": "7:58:18", "remaining_time": "9:28:16"}
152
+ {"current_steps": 760, "total_steps": 1652, "loss": 0.1732, "lr": 2.6236611052597055e-05, "epoch": 3.2208067940552016, "percentage": 46.0, "elapsed_time": "8:01:28", "remaining_time": "9:25:05"}
153
+ {"current_steps": 765, "total_steps": 1652, "loss": 0.1782, "lr": 2.603539518388611e-05, "epoch": 3.2420382165605095, "percentage": 46.31, "elapsed_time": "8:04:37", "remaining_time": "9:21:54"}
154
+ {"current_steps": 770, "total_steps": 1652, "loss": 0.1794, "lr": 2.5833504936539712e-05, "epoch": 3.2632696390658174, "percentage": 46.61, "elapsed_time": "8:07:45", "remaining_time": "9:18:42"}
155
+ {"current_steps": 775, "total_steps": 1652, "loss": 0.1948, "lr": 2.563096286922474e-05, "epoch": 3.284501061571125, "percentage": 46.91, "elapsed_time": "8:10:53", "remaining_time": "9:15:30"}
156
+ {"current_steps": 780, "total_steps": 1652, "loss": 0.1825, "lr": 2.54277916134407e-05, "epoch": 3.305732484076433, "percentage": 47.22, "elapsed_time": "8:14:04", "remaining_time": "9:12:20"}
157
+ {"current_steps": 785, "total_steps": 1652, "loss": 0.1861, "lr": 2.5224013870990868e-05, "epoch": 3.326963906581741, "percentage": 47.52, "elapsed_time": "8:17:14", "remaining_time": "9:09:10"}
158
+ {"current_steps": 790, "total_steps": 1652, "loss": 0.1929, "lr": 2.5019652411445704e-05, "epoch": 3.3481953290870488, "percentage": 47.82, "elapsed_time": "8:20:23", "remaining_time": "9:06:00"}
159
+ {"current_steps": 795, "total_steps": 1652, "loss": 0.1737, "lr": 2.4814730069598624e-05, "epoch": 3.3694267515923566, "percentage": 48.12, "elapsed_time": "8:23:33", "remaining_time": "9:02:49"}
160
+ {"current_steps": 800, "total_steps": 1652, "loss": 0.1916, "lr": 2.460926974291451e-05, "epoch": 3.3906581740976645, "percentage": 48.43, "elapsed_time": "8:26:41", "remaining_time": "8:59:37"}
161
+ {"current_steps": 805, "total_steps": 1652, "loss": 0.1705, "lr": 2.440329438897122e-05, "epoch": 3.4118895966029723, "percentage": 48.73, "elapsed_time": "8:31:00", "remaining_time": "8:57:40"}
162
+ {"current_steps": 810, "total_steps": 1652, "loss": 0.1584, "lr": 2.419682702289432e-05, "epoch": 3.43312101910828, "percentage": 49.03, "elapsed_time": "8:34:10", "remaining_time": "8:54:29"}
163
+ {"current_steps": 815, "total_steps": 1652, "loss": 0.1632, "lr": 2.3989890714785505e-05, "epoch": 3.454352441613588, "percentage": 49.33, "elapsed_time": "8:37:19", "remaining_time": "8:51:17"}