penfever commited on
Commit
e1bccd6
·
verified ·
1 Parent(s): 18350b7

Training in progress, step 5800

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97913c267cc005ceb27c14ab9cd054dc23d35f07a1b06d9a6c4fa6ddaf0a123e
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd84436d653b8a6867bc5cedb16c1b492c8b85711dc5f07a0f66c938c942746
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:f765f289d2bff0fa1e32ae2e09b7338b02a37eb1cdba04efde32c1f07f9ddee7
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d6778749079e40c523deda851980cca8ae176a7d1d79d04e342b22d6000881
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56d03a749070e0a5ae11e585936ca375b1b0cb48fd6bd6d05d6fc9e88d72124b
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:650311c3caa623a65757ec3ba1e326a36c00d53df14093b88ddc680b15221522
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cc167935cf04c6a26b2f1ebeb3491bf5312b57fbafddc8c18633b02507ed7bf
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aff53c325fc2d50f68ce9db9d4ddabcde2a7d86e561dfb37fb38aa68aa69953
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1118,3 +1118,43 @@
1118
  {"current_steps": 5590, "total_steps": 6713, "loss": 0.1866, "lr": 3.320577511261589e-06, "epoch": 5.830464267083985, "percentage": 83.27, "elapsed_time": "1 day, 3:36:22", "remaining_time": "5:32:45"}
1119
  {"current_steps": 5595, "total_steps": 6713, "loss": 0.1743, "lr": 3.291937418815376e-06, "epoch": 5.835680751173709, "percentage": 83.35, "elapsed_time": "1 day, 3:39:14", "remaining_time": "5:31:33"}
1120
  {"current_steps": 5600, "total_steps": 6713, "loss": 0.1674, "lr": 3.2634102924159982e-06, "epoch": 5.840897235263433, "percentage": 83.42, "elapsed_time": "1 day, 3:41:58", "remaining_time": "5:30:19"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1118
  {"current_steps": 5590, "total_steps": 6713, "loss": 0.1866, "lr": 3.320577511261589e-06, "epoch": 5.830464267083985, "percentage": 83.27, "elapsed_time": "1 day, 3:36:22", "remaining_time": "5:32:45"}
1119
  {"current_steps": 5595, "total_steps": 6713, "loss": 0.1743, "lr": 3.291937418815376e-06, "epoch": 5.835680751173709, "percentage": 83.35, "elapsed_time": "1 day, 3:39:14", "remaining_time": "5:31:33"}
1120
  {"current_steps": 5600, "total_steps": 6713, "loss": 0.1674, "lr": 3.2634102924159982e-06, "epoch": 5.840897235263433, "percentage": 83.42, "elapsed_time": "1 day, 3:41:58", "remaining_time": "5:30:19"}
1121
+ {"current_steps": 5605, "total_steps": 6713, "loss": 0.1763, "lr": 3.2349963249401894e-06, "epoch": 5.846113719353156, "percentage": 83.49, "elapsed_time": "1 day, 3:46:07", "remaining_time": "5:29:21"}
1122
+ {"current_steps": 5610, "total_steps": 6713, "loss": 0.1822, "lr": 3.2066957084996163e-06, "epoch": 5.851330203442879, "percentage": 83.57, "elapsed_time": "1 day, 3:48:54", "remaining_time": "5:28:07"}
1123
+ {"current_steps": 5615, "total_steps": 6713, "loss": 0.1757, "lr": 3.178508634439539e-06, "epoch": 5.856546687532603, "percentage": 83.64, "elapsed_time": "1 day, 3:51:43", "remaining_time": "5:26:54"}
1124
+ {"current_steps": 5620, "total_steps": 6713, "loss": 0.1769, "lr": 3.150435293337557e-06, "epoch": 5.861763171622327, "percentage": 83.72, "elapsed_time": "1 day, 3:54:36", "remaining_time": "5:25:41"}
1125
+ {"current_steps": 5625, "total_steps": 6713, "loss": 0.174, "lr": 3.1224758750022934e-06, "epoch": 5.86697965571205, "percentage": 83.79, "elapsed_time": "1 day, 3:57:14", "remaining_time": "5:24:25"}
1126
+ {"current_steps": 5630, "total_steps": 6713, "loss": 0.1689, "lr": 3.0946305684721145e-06, "epoch": 5.8721961398017735, "percentage": 83.87, "elapsed_time": "1 day, 4:00:07", "remaining_time": "5:23:11"}
1127
+ {"current_steps": 5635, "total_steps": 6713, "loss": 0.1705, "lr": 3.066899562013872e-06, "epoch": 5.877412623891497, "percentage": 83.94, "elapsed_time": "1 day, 4:02:49", "remaining_time": "5:21:55"}
1128
+ {"current_steps": 5640, "total_steps": 6713, "loss": 0.179, "lr": 3.0392830431216037e-06, "epoch": 5.882629107981221, "percentage": 84.02, "elapsed_time": "1 day, 4:05:37", "remaining_time": "5:20:41"}
1129
+ {"current_steps": 5645, "total_steps": 6713, "loss": 0.1787, "lr": 3.01178119851528e-06, "epoch": 5.887845592070944, "percentage": 84.09, "elapsed_time": "1 day, 4:08:18", "remaining_time": "5:19:25"}
1130
+ {"current_steps": 5650, "total_steps": 6713, "loss": 0.1765, "lr": 2.9843942141395365e-06, "epoch": 5.893062076160668, "percentage": 84.17, "elapsed_time": "1 day, 4:10:51", "remaining_time": "5:18:07"}
1131
+ {"current_steps": 5655, "total_steps": 6713, "loss": 0.1763, "lr": 2.9571222751624317e-06, "epoch": 5.898278560250391, "percentage": 84.24, "elapsed_time": "1 day, 4:13:23", "remaining_time": "5:16:49"}
1132
+ {"current_steps": 5660, "total_steps": 6713, "loss": 0.1804, "lr": 2.9299655659741622e-06, "epoch": 5.903495044340115, "percentage": 84.31, "elapsed_time": "1 day, 4:16:09", "remaining_time": "5:15:33"}
1133
+ {"current_steps": 5665, "total_steps": 6713, "loss": 0.1897, "lr": 2.9029242701858606e-06, "epoch": 5.908711528429838, "percentage": 84.39, "elapsed_time": "1 day, 4:18:48", "remaining_time": "5:14:16"}
1134
+ {"current_steps": 5670, "total_steps": 6713, "loss": 0.167, "lr": 2.8759985706283068e-06, "epoch": 5.913928012519562, "percentage": 84.46, "elapsed_time": "1 day, 4:21:43", "remaining_time": "5:13:02"}
1135
+ {"current_steps": 5675, "total_steps": 6713, "loss": 0.1711, "lr": 2.8491886493507313e-06, "epoch": 5.919144496609285, "percentage": 84.54, "elapsed_time": "1 day, 4:24:39", "remaining_time": "5:11:47"}
1136
+ {"current_steps": 5680, "total_steps": 6713, "loss": 0.1736, "lr": 2.8224946876195593e-06, "epoch": 5.924360980699009, "percentage": 84.61, "elapsed_time": "1 day, 4:27:39", "remaining_time": "5:10:33"}
1137
+ {"current_steps": 5685, "total_steps": 6713, "loss": 0.1723, "lr": 2.795916865917201e-06, "epoch": 5.929577464788732, "percentage": 84.69, "elapsed_time": "1 day, 4:30:25", "remaining_time": "5:09:17"}
1138
+ {"current_steps": 5690, "total_steps": 6713, "loss": 0.1733, "lr": 2.7694553639408163e-06, "epoch": 5.934793948878456, "percentage": 84.76, "elapsed_time": "1 day, 4:33:02", "remaining_time": "5:07:59"}
1139
+ {"current_steps": 5695, "total_steps": 6713, "loss": 0.1736, "lr": 2.7431103606011113e-06, "epoch": 5.9400104329681795, "percentage": 84.84, "elapsed_time": "1 day, 4:35:56", "remaining_time": "5:06:43"}
1140
+ {"current_steps": 5700, "total_steps": 6713, "loss": 0.1727, "lr": 2.71688203402112e-06, "epoch": 5.945226917057903, "percentage": 84.91, "elapsed_time": "1 day, 4:38:35", "remaining_time": "5:05:25"}
1141
+ {"current_steps": 5705, "total_steps": 6713, "loss": 0.187, "lr": 2.690770561535019e-06, "epoch": 5.950443401147626, "percentage": 84.98, "elapsed_time": "1 day, 4:41:24", "remaining_time": "5:04:09"}
1142
+ {"current_steps": 5710, "total_steps": 6713, "loss": 0.1632, "lr": 2.664776119686896e-06, "epoch": 5.95565988523735, "percentage": 85.06, "elapsed_time": "1 day, 4:44:11", "remaining_time": "5:02:52"}
1143
+ {"current_steps": 5715, "total_steps": 6713, "loss": 0.1657, "lr": 2.6388988842295947e-06, "epoch": 5.960876369327074, "percentage": 85.13, "elapsed_time": "1 day, 4:47:09", "remaining_time": "5:01:36"}
1144
+ {"current_steps": 5720, "total_steps": 6713, "loss": 0.1774, "lr": 2.6131390301234927e-06, "epoch": 5.966092853416797, "percentage": 85.21, "elapsed_time": "1 day, 4:49:44", "remaining_time": "5:00:17"}
1145
+ {"current_steps": 5725, "total_steps": 6713, "loss": 0.1782, "lr": 2.587496731535326e-06, "epoch": 5.97130933750652, "percentage": 85.28, "elapsed_time": "1 day, 4:52:24", "remaining_time": "4:58:58"}
1146
+ {"current_steps": 5730, "total_steps": 6713, "loss": 0.177, "lr": 2.561972161837041e-06, "epoch": 5.976525821596244, "percentage": 85.36, "elapsed_time": "1 day, 4:55:19", "remaining_time": "4:57:41"}
1147
+ {"current_steps": 5735, "total_steps": 6713, "loss": 0.1869, "lr": 2.536565493604575e-06, "epoch": 5.981742305685968, "percentage": 85.43, "elapsed_time": "1 day, 4:57:53", "remaining_time": "4:56:21"}
1148
+ {"current_steps": 5740, "total_steps": 6713, "loss": 0.1545, "lr": 2.511276898616737e-06, "epoch": 5.9869587897756915, "percentage": 85.51, "elapsed_time": "1 day, 5:00:50", "remaining_time": "4:55:05"}
1149
+ {"current_steps": 5745, "total_steps": 6713, "loss": 0.1742, "lr": 2.4861065478539925e-06, "epoch": 5.992175273865414, "percentage": 85.58, "elapsed_time": "1 day, 5:03:20", "remaining_time": "4:53:44"}
1150
+ {"current_steps": 5750, "total_steps": 6713, "loss": 0.1696, "lr": 2.4610546114973666e-06, "epoch": 5.997391757955138, "percentage": 85.65, "elapsed_time": "1 day, 5:05:53", "remaining_time": "4:52:24"}
1151
+ {"current_steps": 5755, "total_steps": 6713, "loss": 0.1715, "lr": 2.4361212589272488e-06, "epoch": 6.002086593635889, "percentage": 85.73, "elapsed_time": "1 day, 5:08:09", "remaining_time": "4:51:00"}
1152
+ {"current_steps": 5760, "total_steps": 6713, "loss": 0.1756, "lr": 2.41130665872227e-06, "epoch": 6.007303077725613, "percentage": 85.8, "elapsed_time": "1 day, 5:10:43", "remaining_time": "4:49:39"}
1153
+ {"current_steps": 5765, "total_steps": 6713, "loss": 0.1601, "lr": 2.3866109786581484e-06, "epoch": 6.012519561815337, "percentage": 85.88, "elapsed_time": "1 day, 5:13:33", "remaining_time": "4:48:21"}
1154
+ {"current_steps": 5770, "total_steps": 6713, "loss": 0.157, "lr": 2.3620343857065776e-06, "epoch": 6.01773604590506, "percentage": 85.95, "elapsed_time": "1 day, 5:16:27", "remaining_time": "4:47:03"}
1155
+ {"current_steps": 5775, "total_steps": 6713, "loss": 0.1651, "lr": 2.3375770460340654e-06, "epoch": 6.022952529994783, "percentage": 86.03, "elapsed_time": "1 day, 5:19:10", "remaining_time": "4:45:43"}
1156
+ {"current_steps": 5780, "total_steps": 6713, "loss": 0.1653, "lr": 2.313239125000841e-06, "epoch": 6.028169014084507, "percentage": 86.1, "elapsed_time": "1 day, 5:21:52", "remaining_time": "4:44:23"}
1157
+ {"current_steps": 5785, "total_steps": 6713, "loss": 0.1534, "lr": 2.2890207871597192e-06, "epoch": 6.033385498174231, "percentage": 86.18, "elapsed_time": "1 day, 5:24:50", "remaining_time": "4:43:06"}
1158
+ {"current_steps": 5790, "total_steps": 6713, "loss": 0.1735, "lr": 2.2649221962549905e-06, "epoch": 6.0386019822639545, "percentage": 86.25, "elapsed_time": "1 day, 5:27:27", "remaining_time": "4:41:45"}
1159
+ {"current_steps": 5795, "total_steps": 6713, "loss": 0.1684, "lr": 2.2409435152213123e-06, "epoch": 6.043818466353677, "percentage": 86.33, "elapsed_time": "1 day, 5:30:04", "remaining_time": "4:40:24"}
1160
+ {"current_steps": 5800, "total_steps": 6713, "loss": 0.1666, "lr": 2.217084906182629e-06, "epoch": 6.049034950443401, "percentage": 86.4, "elapsed_time": "1 day, 5:32:50", "remaining_time": "4:39:04"}