penfever commited on
Commit
b723daa
·
verified ·
1 Parent(s): dc22948

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 sha256:8bb63150065055f10e3f86faef1ff411d36d6192eefe50364e0c993e763060c9
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e83f2b5221e41fdd3624a025c3acb8d8958aa75268e7e6ff89611de75c2dfd
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:951794a481558b423ca56742f6a431fe59b731214fbcb0f186a4a517f5c752f0
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09426ad3fa66ca6a96bd07fcb7885f70a6f48d655b7ab893ad7af9f813ffc331
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3434245ce736f20bdbbc2c48143572c82b770de72c364922b8852f1f171a7be3
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3437c8aa083f3e58f7cad87b11a21dcdfc0d6fbd451f3047205455e285c7e81
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:cb28fbff36ddd833c16d6080d1cabad3cd1835b36625967d28830d648f5b80c7
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043edd566027c17325e768ce5db984d44bbec9330239212d940b31aa3d5ee328
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1161,3 +1161,42 @@
1161
  {"current_steps": 5795, "total_steps": 6188, "loss": 0.0882, "lr": 4.919819013297677e-07, "epoch": 6.556876061120543, "percentage": 93.65, "elapsed_time": "21:05:17", "remaining_time": "1:25:48"}
1162
  {"current_steps": 5800, "total_steps": 6188, "loss": 0.0904, "lr": 4.796241165399939e-07, "epoch": 6.562535370684777, "percentage": 93.73, "elapsed_time": "21:07:02", "remaining_time": "1:24:45"}
1163
  {"current_steps": 5805, "total_steps": 6188, "loss": 0.0801, "lr": 4.674216323762881e-07, "epoch": 6.568194680249009, "percentage": 93.81, "elapsed_time": "21:10:01", "remaining_time": "1:23:47"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1161
  {"current_steps": 5795, "total_steps": 6188, "loss": 0.0882, "lr": 4.919819013297677e-07, "epoch": 6.556876061120543, "percentage": 93.65, "elapsed_time": "21:05:17", "remaining_time": "1:25:48"}
1162
  {"current_steps": 5800, "total_steps": 6188, "loss": 0.0904, "lr": 4.796241165399939e-07, "epoch": 6.562535370684777, "percentage": 93.73, "elapsed_time": "21:07:02", "remaining_time": "1:24:45"}
1163
  {"current_steps": 5805, "total_steps": 6188, "loss": 0.0801, "lr": 4.674216323762881e-07, "epoch": 6.568194680249009, "percentage": 93.81, "elapsed_time": "21:10:01", "remaining_time": "1:23:47"}
1164
+ {"current_steps": 5810, "total_steps": 6188, "loss": 0.1402, "lr": 4.5537454591943584e-07, "epoch": 6.573853989813243, "percentage": 93.89, "elapsed_time": "21:11:54", "remaining_time": "1:22:45"}
1165
+ {"current_steps": 5815, "total_steps": 6188, "loss": 0.2022, "lr": 4.434829530139095e-07, "epoch": 6.579513299377476, "percentage": 93.97, "elapsed_time": "21:13:54", "remaining_time": "1:21:42"}
1166
+ {"current_steps": 5820, "total_steps": 6188, "loss": 0.0839, "lr": 4.3174694826709107e-07, "epoch": 6.5851726089417095, "percentage": 94.05, "elapsed_time": "21:15:44", "remaining_time": "1:20:39"}
1167
+ {"current_steps": 5825, "total_steps": 6188, "loss": 0.1027, "lr": 4.201666250485503e-07, "epoch": 6.590831918505942, "percentage": 94.13, "elapsed_time": "21:17:29", "remaining_time": "1:19:36"}
1168
+ {"current_steps": 5830, "total_steps": 6188, "loss": 0.1448, "lr": 4.087420754892635e-07, "epoch": 6.5964912280701755, "percentage": 94.21, "elapsed_time": "21:19:38", "remaining_time": "1:18:34"}
1169
+ {"current_steps": 5835, "total_steps": 6188, "loss": 0.0726, "lr": 3.9747339048091136e-07, "epoch": 6.602150537634409, "percentage": 94.3, "elapsed_time": "21:21:32", "remaining_time": "1:17:31"}
1170
+ {"current_steps": 5840, "total_steps": 6188, "loss": 0.0746, "lr": 3.863606596751379e-07, "epoch": 6.6078098471986415, "percentage": 94.38, "elapsed_time": "21:23:10", "remaining_time": "1:16:27"}
1171
+ {"current_steps": 5845, "total_steps": 6188, "loss": 0.0732, "lr": 3.7540397148284837e-07, "epoch": 6.613469156762875, "percentage": 94.46, "elapsed_time": "21:24:50", "remaining_time": "1:15:23"}
1172
+ {"current_steps": 5850, "total_steps": 6188, "loss": 0.0688, "lr": 3.6460341307349653e-07, "epoch": 6.619128466327108, "percentage": 94.54, "elapsed_time": "21:26:37", "remaining_time": "1:14:20"}
1173
+ {"current_steps": 5855, "total_steps": 6188, "loss": 0.0679, "lr": 3.539590703743967e-07, "epoch": 6.624787775891341, "percentage": 94.62, "elapsed_time": "21:28:08", "remaining_time": "1:13:15"}
1174
+ {"current_steps": 5860, "total_steps": 6188, "loss": 0.0713, "lr": 3.434710280700415e-07, "epoch": 6.630447085455574, "percentage": 94.7, "elapsed_time": "21:29:36", "remaining_time": "1:12:10"}
1175
+ {"current_steps": 5865, "total_steps": 6188, "loss": 0.0597, "lr": 3.331393696014207e-07, "epoch": 6.636106395019808, "percentage": 94.78, "elapsed_time": "21:31:10", "remaining_time": "1:11:06"}
1176
+ {"current_steps": 5870, "total_steps": 6188, "loss": 0.1122, "lr": 3.22964177165368e-07, "epoch": 6.64176570458404, "percentage": 94.86, "elapsed_time": "21:33:19", "remaining_time": "1:10:03"}
1177
+ {"current_steps": 5875, "total_steps": 6188, "loss": 0.0538, "lr": 3.129455317138952e-07, "epoch": 6.647425014148274, "percentage": 94.94, "elapsed_time": "21:34:47", "remaining_time": "1:08:58"}
1178
+ {"current_steps": 5880, "total_steps": 6188, "loss": 0.0619, "lr": 3.030835129535592e-07, "epoch": 6.653084323712507, "percentage": 95.02, "elapsed_time": "21:36:21", "remaining_time": "1:07:54"}
1179
+ {"current_steps": 5885, "total_steps": 6188, "loss": 0.0609, "lr": 2.9337819934481814e-07, "epoch": 6.658743633276741, "percentage": 95.1, "elapsed_time": "21:37:53", "remaining_time": "1:06:49"}
1180
+ {"current_steps": 5890, "total_steps": 6188, "loss": 0.077, "lr": 2.838296681014185e-07, "epoch": 6.664402942840973, "percentage": 95.18, "elapsed_time": "21:39:46", "remaining_time": "1:05:45"}
1181
+ {"current_steps": 5895, "total_steps": 6188, "loss": 0.0921, "lr": 2.744379951897691e-07, "epoch": 6.670062252405207, "percentage": 95.27, "elapsed_time": "21:41:50", "remaining_time": "1:04:42"}
1182
+ {"current_steps": 5900, "total_steps": 6188, "loss": 0.0919, "lr": 2.65203255328339e-07, "epoch": 6.67572156196944, "percentage": 95.35, "elapsed_time": "21:43:38", "remaining_time": "1:03:38"}
1183
+ {"current_steps": 5905, "total_steps": 6188, "loss": 0.0778, "lr": 2.561255219870762e-07, "epoch": 6.681380871533673, "percentage": 95.43, "elapsed_time": "21:45:11", "remaining_time": "1:02:33"}
1184
+ {"current_steps": 5910, "total_steps": 6188, "loss": 0.0861, "lr": 2.472048673868033e-07, "epoch": 6.687040181097906, "percentage": 95.51, "elapsed_time": "21:46:57", "remaining_time": "1:01:28"}
1185
+ {"current_steps": 5915, "total_steps": 6188, "loss": 0.1018, "lr": 2.3844136249865367e-07, "epoch": 6.6926994906621395, "percentage": 95.59, "elapsed_time": "21:48:45", "remaining_time": "1:00:24"}
1186
+ {"current_steps": 5920, "total_steps": 6188, "loss": 0.0753, "lr": 2.2983507704351426e-07, "epoch": 6.698358800226372, "percentage": 95.67, "elapsed_time": "21:50:20", "remaining_time": "0:59:19"}
1187
+ {"current_steps": 5925, "total_steps": 6188, "loss": 0.093, "lr": 2.213860794914524e-07, "epoch": 6.7040181097906055, "percentage": 95.75, "elapsed_time": "21:51:53", "remaining_time": "0:58:13"}
1188
+ {"current_steps": 5930, "total_steps": 6188, "loss": 0.0749, "lr": 2.1309443706118538e-07, "epoch": 6.709677419354839, "percentage": 95.83, "elapsed_time": "21:53:35", "remaining_time": "0:57:09"}
1189
+ {"current_steps": 5935, "total_steps": 6188, "loss": 0.0752, "lr": 2.049602157195363e-07, "epoch": 6.7153367289190715, "percentage": 95.91, "elapsed_time": "21:55:34", "remaining_time": "0:56:04"}
1190
+ {"current_steps": 5940, "total_steps": 6188, "loss": 0.0648, "lr": 1.9698348018092338e-07, "epoch": 6.720996038483305, "percentage": 95.99, "elapsed_time": "21:57:19", "remaining_time": "0:54:59"}
1191
+ {"current_steps": 5945, "total_steps": 6188, "loss": 0.0647, "lr": 1.8916429390682944e-07, "epoch": 6.726655348047538, "percentage": 96.07, "elapsed_time": "21:59:18", "remaining_time": "0:53:55"}
1192
+ {"current_steps": 5950, "total_steps": 6188, "loss": 0.068, "lr": 1.8150271910530204e-07, "epoch": 6.732314657611772, "percentage": 96.15, "elapsed_time": "22:00:55", "remaining_time": "0:52:50"}
1193
+ {"current_steps": 5955, "total_steps": 6188, "loss": 0.0797, "lr": 1.7399881673046736e-07, "epoch": 6.737973967176004, "percentage": 96.23, "elapsed_time": "22:03:05", "remaining_time": "0:51:46"}
1194
+ {"current_steps": 5960, "total_steps": 6188, "loss": 0.0781, "lr": 1.666526464820284e-07, "epoch": 6.743633276740238, "percentage": 96.32, "elapsed_time": "22:04:46", "remaining_time": "0:50:40"}
1195
+ {"current_steps": 5965, "total_steps": 6188, "loss": 0.0863, "lr": 1.594642668048052e-07, "epoch": 6.74929258630447, "percentage": 96.4, "elapsed_time": "22:06:22", "remaining_time": "0:49:35"}
1196
+ {"current_steps": 5970, "total_steps": 6188, "loss": 0.0593, "lr": 1.5243373488826653e-07, "epoch": 6.754951895868704, "percentage": 96.48, "elapsed_time": "22:07:59", "remaining_time": "0:48:29"}
1197
+ {"current_steps": 5975, "total_steps": 6188, "loss": 0.0741, "lr": 1.4556110666606783e-07, "epoch": 6.760611205432937, "percentage": 96.56, "elapsed_time": "22:09:46", "remaining_time": "0:47:24"}
1198
+ {"current_steps": 5980, "total_steps": 6188, "loss": 0.0725, "lr": 1.388464368156095e-07, "epoch": 6.766270514997171, "percentage": 96.64, "elapsed_time": "22:11:24", "remaining_time": "0:46:18"}
1199
+ {"current_steps": 5985, "total_steps": 6188, "loss": 0.0589, "lr": 1.322897787576105e-07, "epoch": 6.771929824561403, "percentage": 96.72, "elapsed_time": "22:12:59", "remaining_time": "0:45:12"}
1200
+ {"current_steps": 5990, "total_steps": 6188, "loss": 0.0734, "lr": 1.2589118465566875e-07, "epoch": 6.777589134125637, "percentage": 96.8, "elapsed_time": "22:14:38", "remaining_time": "0:44:07"}
1201
+ {"current_steps": 5995, "total_steps": 6188, "loss": 0.0728, "lr": 1.1965070541585912e-07, "epoch": 6.78324844368987, "percentage": 96.88, "elapsed_time": "22:16:12", "remaining_time": "0:43:01"}
1202
+ {"current_steps": 6000, "total_steps": 6188, "loss": 0.0845, "lr": 1.1356839068632053e-07, "epoch": 6.788907753254103, "percentage": 96.96, "elapsed_time": "22:18:02", "remaining_time": "0:41:55"}