penfever commited on
Commit
76731bc
·
verified ·
1 Parent(s): 2a21d8a

Training in progress, step 6000

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37a60221ad5a787b71707630162c2e751e0707860f39541104d3bffb96d4d975
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe2164a32210c2f757b9038450ac8a3ebcd09b0fa5be1d6b46aa064deb7e49a
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:c02443c1e400253c447f4d9fdd5def0ecbed90cd00ca99cccfe34d2f900dc300
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9f6db7fd12a272ec3915e2de446692f15dcf34792fedc07b3b278607b609fb6
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60c2222b0479ddd3e62c2aacffed5af5c7a2d128b700c7b875075ec2fc7db289
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dadc1de14b16b0e4e9a8286930de8e13b6b8d53eea9553217dc4ead2858ee58
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:de0be374e90af3db2aa01ed4eb3eafa611cf3b1ac15c1c6f8c824e7fd5cc655d
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8892d3db17b47550012a8ec5b30a72b00875d049a4dcab465563bd9d9475c058
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1181,3 +1181,43 @@
1181
  {"current_steps": 5790, "total_steps": 6713, "loss": 0.1449, "lr": 2.2649221962549905e-06, "epoch": 6.0386019822639545, "percentage": 86.25, "elapsed_time": "20:50:10", "remaining_time": "3:19:17"}
1182
  {"current_steps": 5795, "total_steps": 6713, "loss": 0.1698, "lr": 2.2409435152213123e-06, "epoch": 6.043818466353677, "percentage": 86.33, "elapsed_time": "20:52:51", "remaining_time": "3:18:28"}
1183
  {"current_steps": 5800, "total_steps": 6713, "loss": 0.1479, "lr": 2.217084906182629e-06, "epoch": 6.049034950443401, "percentage": 86.4, "elapsed_time": "20:55:48", "remaining_time": "3:17:40"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1181
  {"current_steps": 5790, "total_steps": 6713, "loss": 0.1449, "lr": 2.2649221962549905e-06, "epoch": 6.0386019822639545, "percentage": 86.25, "elapsed_time": "20:50:10", "remaining_time": "3:19:17"}
1182
  {"current_steps": 5795, "total_steps": 6713, "loss": 0.1698, "lr": 2.2409435152213123e-06, "epoch": 6.043818466353677, "percentage": 86.33, "elapsed_time": "20:52:51", "remaining_time": "3:18:28"}
1183
  {"current_steps": 5800, "total_steps": 6713, "loss": 0.1479, "lr": 2.217084906182629e-06, "epoch": 6.049034950443401, "percentage": 86.4, "elapsed_time": "20:55:48", "remaining_time": "3:17:40"}
1184
+ {"current_steps": 5805, "total_steps": 6713, "loss": 0.1504, "lr": 2.1933465304510394e-06, "epoch": 6.054251434533125, "percentage": 86.47, "elapsed_time": "21:00:03", "remaining_time": "3:17:05"}
1185
+ {"current_steps": 5810, "total_steps": 6713, "loss": 0.1447, "lr": 2.1697285485257245e-06, "epoch": 6.059467918622849, "percentage": 86.55, "elapsed_time": "21:02:56", "remaining_time": "3:16:17"}
1186
+ {"current_steps": 5815, "total_steps": 6713, "loss": 0.1515, "lr": 2.1462311200918816e-06, "epoch": 6.0646844027125715, "percentage": 86.62, "elapsed_time": "21:05:57", "remaining_time": "3:15:29"}
1187
+ {"current_steps": 5820, "total_steps": 6713, "loss": 0.1394, "lr": 2.122854404019601e-06, "epoch": 6.069900886802295, "percentage": 86.7, "elapsed_time": "21:08:58", "remaining_time": "3:14:42"}
1188
+ {"current_steps": 5825, "total_steps": 6713, "loss": 0.1347, "lr": 2.0995985583628366e-06, "epoch": 6.075117370892019, "percentage": 86.77, "elapsed_time": "21:11:34", "remaining_time": "3:13:50"}
1189
+ {"current_steps": 5830, "total_steps": 6713, "loss": 0.1437, "lr": 2.076463740358299e-06, "epoch": 6.080333854981743, "percentage": 86.85, "elapsed_time": "21:14:33", "remaining_time": "3:13:02"}
1190
+ {"current_steps": 5835, "total_steps": 6713, "loss": 0.151, "lr": 2.053450106424426e-06, "epoch": 6.085550339071466, "percentage": 86.92, "elapsed_time": "21:17:26", "remaining_time": "3:12:13"}
1191
+ {"current_steps": 5840, "total_steps": 6713, "loss": 0.1339, "lr": 2.030557812160301e-06, "epoch": 6.090766823161189, "percentage": 87.0, "elapsed_time": "21:20:22", "remaining_time": "3:11:23"}
1192
+ {"current_steps": 5845, "total_steps": 6713, "loss": 0.1331, "lr": 2.0077870123446107e-06, "epoch": 6.095983307250913, "percentage": 87.07, "elapsed_time": "21:23:29", "remaining_time": "3:10:36"}
1193
+ {"current_steps": 5850, "total_steps": 6713, "loss": 0.1362, "lr": 1.985137860934594e-06, "epoch": 6.101199791340637, "percentage": 87.14, "elapsed_time": "21:26:27", "remaining_time": "3:09:46"}
1194
+ {"current_steps": 5855, "total_steps": 6713, "loss": 0.1632, "lr": 1.962610511065013e-06, "epoch": 6.10641627543036, "percentage": 87.22, "elapsed_time": "21:29:24", "remaining_time": "3:08:57"}
1195
+ {"current_steps": 5860, "total_steps": 6713, "loss": 0.1449, "lr": 1.940205115047098e-06, "epoch": 6.1116327595200834, "percentage": 87.29, "elapsed_time": "21:32:25", "remaining_time": "3:08:07"}
1196
+ {"current_steps": 5865, "total_steps": 6713, "loss": 0.141, "lr": 1.917921824367539e-06, "epoch": 6.116849243609807, "percentage": 87.37, "elapsed_time": "21:35:18", "remaining_time": "3:07:17"}
1197
+ {"current_steps": 5870, "total_steps": 6713, "loss": 0.1516, "lr": 1.8957607896874419e-06, "epoch": 6.122065727699531, "percentage": 87.44, "elapsed_time": "21:38:13", "remaining_time": "3:06:26"}
1198
+ {"current_steps": 5875, "total_steps": 6713, "loss": 0.1619, "lr": 1.8737221608413314e-06, "epoch": 6.127282211789254, "percentage": 87.52, "elapsed_time": "21:41:11", "remaining_time": "3:05:36"}
1199
+ {"current_steps": 5880, "total_steps": 6713, "loss": 0.1785, "lr": 1.8518060868361099e-06, "epoch": 6.132498695878978, "percentage": 87.59, "elapsed_time": "21:44:13", "remaining_time": "3:04:45"}
1200
+ {"current_steps": 5885, "total_steps": 6713, "loss": 0.1595, "lr": 1.8300127158500714e-06, "epoch": 6.137715179968701, "percentage": 87.67, "elapsed_time": "21:47:17", "remaining_time": "3:03:55"}
1201
+ {"current_steps": 5890, "total_steps": 6713, "loss": 0.1511, "lr": 1.8083421952319047e-06, "epoch": 6.142931664058425, "percentage": 87.74, "elapsed_time": "21:50:24", "remaining_time": "3:03:06"}
1202
+ {"current_steps": 5895, "total_steps": 6713, "loss": 0.1481, "lr": 1.786794671499672e-06, "epoch": 6.148148148148148, "percentage": 87.81, "elapsed_time": "21:53:28", "remaining_time": "3:02:15"}
1203
+ {"current_steps": 5900, "total_steps": 6713, "loss": 0.1532, "lr": 1.7653702903398384e-06, "epoch": 6.153364632237872, "percentage": 87.89, "elapsed_time": "21:56:22", "remaining_time": "3:01:23"}
1204
+ {"current_steps": 5905, "total_steps": 6713, "loss": 0.1491, "lr": 1.7440691966062816e-06, "epoch": 6.158581116327595, "percentage": 87.96, "elapsed_time": "21:59:24", "remaining_time": "3:00:32"}
1205
+ {"current_steps": 5910, "total_steps": 6713, "loss": 0.1546, "lr": 1.722891534319313e-06, "epoch": 6.163797600417318, "percentage": 88.04, "elapsed_time": "22:02:31", "remaining_time": "2:59:41"}
1206
+ {"current_steps": 5915, "total_steps": 6713, "loss": 0.1534, "lr": 1.7018374466646981e-06, "epoch": 6.169014084507042, "percentage": 88.11, "elapsed_time": "22:05:35", "remaining_time": "2:58:50"}
1207
+ {"current_steps": 5920, "total_steps": 6713, "loss": 0.1518, "lr": 1.6809070759927015e-06, "epoch": 6.174230568596766, "percentage": 88.19, "elapsed_time": "22:08:28", "remaining_time": "2:57:57"}
1208
+ {"current_steps": 5925, "total_steps": 6713, "loss": 0.1306, "lr": 1.6601005638171065e-06, "epoch": 6.1794470526864895, "percentage": 88.26, "elapsed_time": "22:11:29", "remaining_time": "2:57:04"}
1209
+ {"current_steps": 5930, "total_steps": 6713, "loss": 0.1425, "lr": 1.639418050814281e-06, "epoch": 6.184663536776213, "percentage": 88.34, "elapsed_time": "22:14:36", "remaining_time": "2:56:13"}
1210
+ {"current_steps": 5935, "total_steps": 6713, "loss": 0.1547, "lr": 1.6188596768221976e-06, "epoch": 6.189880020865936, "percentage": 88.41, "elapsed_time": "22:17:36", "remaining_time": "2:55:20"}
1211
+ {"current_steps": 5940, "total_steps": 6713, "loss": 0.1512, "lr": 1.5984255808395198e-06, "epoch": 6.19509650495566, "percentage": 88.49, "elapsed_time": "22:20:32", "remaining_time": "2:54:27"}
1212
+ {"current_steps": 5945, "total_steps": 6713, "loss": 0.1475, "lr": 1.5781159010246306e-06, "epoch": 6.200312989045384, "percentage": 88.56, "elapsed_time": "22:23:28", "remaining_time": "2:53:33"}
1213
+ {"current_steps": 5950, "total_steps": 6713, "loss": 0.1424, "lr": 1.557930774694727e-06, "epoch": 6.2055294731351065, "percentage": 88.63, "elapsed_time": "22:26:15", "remaining_time": "2:52:38"}
1214
+ {"current_steps": 5955, "total_steps": 6713, "loss": 0.143, "lr": 1.5378703383248694e-06, "epoch": 6.21074595722483, "percentage": 88.71, "elapsed_time": "22:29:15", "remaining_time": "2:51:44"}
1215
+ {"current_steps": 5960, "total_steps": 6713, "loss": 0.1482, "lr": 1.5179347275470812e-06, "epoch": 6.215962441314554, "percentage": 88.78, "elapsed_time": "22:32:08", "remaining_time": "2:50:49"}
1216
+ {"current_steps": 5965, "total_steps": 6713, "loss": 0.15, "lr": 1.4981240771494032e-06, "epoch": 6.221178925404278, "percentage": 88.86, "elapsed_time": "22:34:59", "remaining_time": "2:49:54"}
1217
+ {"current_steps": 5970, "total_steps": 6713, "loss": 0.1413, "lr": 1.4784385210750052e-06, "epoch": 6.2263954094940015, "percentage": 88.93, "elapsed_time": "22:37:48", "remaining_time": "2:48:59"}
1218
+ {"current_steps": 5975, "total_steps": 6713, "loss": 0.1606, "lr": 1.458878192421278e-06, "epoch": 6.231611893583724, "percentage": 89.01, "elapsed_time": "22:40:31", "remaining_time": "2:48:02"}
1219
+ {"current_steps": 5980, "total_steps": 6713, "loss": 0.1326, "lr": 1.4394432234389167e-06, "epoch": 6.236828377673448, "percentage": 89.08, "elapsed_time": "22:43:29", "remaining_time": "2:47:07"}
1220
+ {"current_steps": 5985, "total_steps": 6713, "loss": 0.1279, "lr": 1.4201337455310537e-06, "epoch": 6.242044861763172, "percentage": 89.16, "elapsed_time": "22:46:31", "remaining_time": "2:46:13"}
1221
+ {"current_steps": 5990, "total_steps": 6713, "loss": 0.1305, "lr": 1.4009498892523388e-06, "epoch": 6.247261345852895, "percentage": 89.23, "elapsed_time": "22:49:36", "remaining_time": "2:45:18"}
1222
+ {"current_steps": 5995, "total_steps": 6713, "loss": 0.1365, "lr": 1.3818917843080848e-06, "epoch": 6.2524778299426185, "percentage": 89.3, "elapsed_time": "22:52:39", "remaining_time": "2:44:23"}
1223
+ {"current_steps": 6000, "total_steps": 6713, "loss": 0.1538, "lr": 1.3629595595533673e-06, "epoch": 6.257694314032342, "percentage": 89.38, "elapsed_time": "22:55:32", "remaining_time": "2:43:27"}