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:
|
| 3 |
size 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bb63150065055f10e3f86faef1ff411d36d6192eefe50364e0c993e763060c9
|
| 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:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:951794a481558b423ca56742f6a431fe59b731214fbcb0f186a4a517f5c752f0
|
| 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:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3434245ce736f20bdbbc2c48143572c82b770de72c364922b8852f1f171a7be3
|
| 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:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb28fbff36ddd833c16d6080d1cabad3cd1835b36625967d28830d648f5b80c7
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1124,3 +1124,40 @@
|
|
| 1124 |
{"current_steps": 5610, "total_steps": 6188, "loss": 0.1357, "lr": 1.0573966932722902e-06, "epoch": 6.347481607243917, "percentage": 90.66, "elapsed_time": "19:44:39", "remaining_time": "2:02:03"}
|
| 1125 |
{"current_steps": 5615, "total_steps": 6188, "loss": 0.1393, "lr": 1.039372254777702e-06, "epoch": 6.353140916808149, "percentage": 90.74, "elapsed_time": "19:47:44", "remaining_time": "2:01:12"}
|
| 1126 |
{"current_steps": 5620, "total_steps": 6188, "loss": 0.1463, "lr": 1.0214986636529112e-06, "epoch": 6.358800226372383, "percentage": 90.82, "elapsed_time": "19:50:36", "remaining_time": "2:00:19"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1124 |
{"current_steps": 5610, "total_steps": 6188, "loss": 0.1357, "lr": 1.0573966932722902e-06, "epoch": 6.347481607243917, "percentage": 90.66, "elapsed_time": "19:44:39", "remaining_time": "2:02:03"}
|
| 1125 |
{"current_steps": 5615, "total_steps": 6188, "loss": 0.1393, "lr": 1.039372254777702e-06, "epoch": 6.353140916808149, "percentage": 90.74, "elapsed_time": "19:47:44", "remaining_time": "2:01:12"}
|
| 1126 |
{"current_steps": 5620, "total_steps": 6188, "loss": 0.1463, "lr": 1.0214986636529112e-06, "epoch": 6.358800226372383, "percentage": 90.82, "elapsed_time": "19:50:36", "remaining_time": "2:00:19"}
|
| 1127 |
+
{"current_steps": 5625, "total_steps": 6188, "loss": 0.1441, "lr": 1.003776062097015e-06, "epoch": 6.364459535936616, "percentage": 90.9, "elapsed_time": "19:53:39", "remaining_time": "1:59:28"}
|
| 1128 |
+
{"current_steps": 5630, "total_steps": 6188, "loss": 0.1262, "lr": 9.862045911078733e-07, "epoch": 6.370118845500849, "percentage": 90.98, "elapsed_time": "19:56:44", "remaining_time": "1:58:36"}
|
| 1129 |
+
{"current_steps": 5635, "total_steps": 6188, "loss": 0.143, "lr": 9.687843904809725e-07, "epoch": 6.375778155065082, "percentage": 91.06, "elapsed_time": "19:59:47", "remaining_time": "1:57:44"}
|
| 1130 |
+
{"current_steps": 5640, "total_steps": 6188, "loss": 0.1321, "lr": 9.515155988083125e-07, "epoch": 6.3814374646293155, "percentage": 91.14, "elapsed_time": "20:02:53", "remaining_time": "1:56:52"}
|
| 1131 |
+
{"current_steps": 5645, "total_steps": 6188, "loss": 0.1326, "lr": 9.343983534773238e-07, "epoch": 6.387096774193548, "percentage": 91.22, "elapsed_time": "20:05:50", "remaining_time": "1:55:59"}
|
| 1132 |
+
{"current_steps": 5650, "total_steps": 6188, "loss": 0.1383, "lr": 9.174327906697522e-07, "epoch": 6.3927560837577815, "percentage": 91.31, "elapsed_time": "20:08:51", "remaining_time": "1:55:06"}
|
| 1133 |
+
{"current_steps": 5655, "total_steps": 6188, "loss": 0.142, "lr": 9.006190453605867e-07, "epoch": 6.398415393322015, "percentage": 91.39, "elapsed_time": "20:11:51", "remaining_time": "1:54:13"}
|
| 1134 |
+
{"current_steps": 5660, "total_steps": 6188, "loss": 0.1325, "lr": 8.839572513169869e-07, "epoch": 6.4040747028862475, "percentage": 91.47, "elapsed_time": "20:14:55", "remaining_time": "1:53:20"}
|
| 1135 |
+
{"current_steps": 5665, "total_steps": 6188, "loss": 0.1436, "lr": 8.674475410972083e-07, "epoch": 6.409734012450481, "percentage": 91.55, "elapsed_time": "20:18:00", "remaining_time": "1:52:26"}
|
| 1136 |
+
{"current_steps": 5670, "total_steps": 6188, "loss": 0.1505, "lr": 8.510900460495608e-07, "epoch": 6.415393322014714, "percentage": 91.63, "elapsed_time": "20:21:04", "remaining_time": "1:51:33"}
|
| 1137 |
+
{"current_steps": 5675, "total_steps": 6188, "loss": 0.1473, "lr": 8.348848963113498e-07, "epoch": 6.421052631578947, "percentage": 91.71, "elapsed_time": "20:24:05", "remaining_time": "1:50:39"}
|
| 1138 |
+
{"current_steps": 5680, "total_steps": 6188, "loss": 0.1087, "lr": 8.188322208078614e-07, "epoch": 6.42671194114318, "percentage": 91.79, "elapsed_time": "20:26:07", "remaining_time": "1:49:39"}
|
| 1139 |
+
{"current_steps": 5685, "total_steps": 6188, "loss": 0.0764, "lr": 8.02932147251314e-07, "epoch": 6.432371250707414, "percentage": 91.87, "elapsed_time": "20:27:44", "remaining_time": "1:48:37"}
|
| 1140 |
+
{"current_steps": 5690, "total_steps": 6188, "loss": 0.0687, "lr": 7.87184802139851e-07, "epoch": 6.438030560271647, "percentage": 91.95, "elapsed_time": "20:29:22", "remaining_time": "1:47:35"}
|
| 1141 |
+
{"current_steps": 5695, "total_steps": 6188, "loss": 0.0866, "lr": 7.715903107565426e-07, "epoch": 6.44368986983588, "percentage": 92.03, "elapsed_time": "20:30:55", "remaining_time": "1:46:33"}
|
| 1142 |
+
{"current_steps": 5700, "total_steps": 6188, "loss": 0.0712, "lr": 7.56148797168379e-07, "epoch": 6.449349179400113, "percentage": 92.11, "elapsed_time": "20:32:39", "remaining_time": "1:45:32"}
|
| 1143 |
+
{"current_steps": 5705, "total_steps": 6188, "loss": 0.0749, "lr": 7.408603842252837e-07, "epoch": 6.455008488964347, "percentage": 92.19, "elapsed_time": "20:34:14", "remaining_time": "1:44:29"}
|
| 1144 |
+
{"current_steps": 5710, "total_steps": 6188, "loss": 0.1219, "lr": 7.257251935591436e-07, "epoch": 6.460667798528579, "percentage": 92.28, "elapsed_time": "20:35:56", "remaining_time": "1:43:27"}
|
| 1145 |
+
{"current_steps": 5715, "total_steps": 6188, "loss": 0.0738, "lr": 7.107433455828317e-07, "epoch": 6.466327108092813, "percentage": 92.36, "elapsed_time": "20:37:34", "remaining_time": "1:42:25"}
|
| 1146 |
+
{"current_steps": 5720, "total_steps": 6188, "loss": 0.0882, "lr": 6.959149594892567e-07, "epoch": 6.471986417657046, "percentage": 92.44, "elapsed_time": "20:39:20", "remaining_time": "1:41:24"}
|
| 1147 |
+
{"current_steps": 5725, "total_steps": 6188, "loss": 0.0933, "lr": 6.812401532504109e-07, "epoch": 6.477645727221279, "percentage": 92.52, "elapsed_time": "20:41:40", "remaining_time": "1:40:25"}
|
| 1148 |
+
{"current_steps": 5730, "total_steps": 6188, "loss": 0.0688, "lr": 6.667190436164351e-07, "epoch": 6.483305036785512, "percentage": 92.6, "elapsed_time": "20:43:28", "remaining_time": "1:39:23"}
|
| 1149 |
+
{"current_steps": 5735, "total_steps": 6188, "loss": 0.072, "lr": 6.523517461146856e-07, "epoch": 6.4889643463497455, "percentage": 92.68, "elapsed_time": "20:45:20", "remaining_time": "1:38:22"}
|
| 1150 |
+
{"current_steps": 5740, "total_steps": 6188, "loss": 0.0693, "lr": 6.381383750488113e-07, "epoch": 6.494623655913978, "percentage": 92.76, "elapsed_time": "20:47:08", "remaining_time": "1:37:20"}
|
| 1151 |
+
{"current_steps": 5745, "total_steps": 6188, "loss": 0.1099, "lr": 6.240790434978628e-07, "epoch": 6.5002829654782115, "percentage": 92.84, "elapsed_time": "20:48:58", "remaining_time": "1:36:18"}
|
| 1152 |
+
{"current_steps": 5750, "total_steps": 6188, "loss": 0.0653, "lr": 6.101738633153686e-07, "epoch": 6.505942275042445, "percentage": 92.92, "elapsed_time": "20:50:39", "remaining_time": "1:35:16"}
|
| 1153 |
+
{"current_steps": 5755, "total_steps": 6188, "loss": 0.073, "lr": 5.964229451284586e-07, "epoch": 6.511601584606678, "percentage": 93.0, "elapsed_time": "20:52:22", "remaining_time": "1:34:13"}
|
| 1154 |
+
{"current_steps": 5760, "total_steps": 6188, "loss": 0.0605, "lr": 5.828263983369864e-07, "epoch": 6.517260894170911, "percentage": 93.08, "elapsed_time": "20:53:56", "remaining_time": "1:33:10"}
|
| 1155 |
+
{"current_steps": 5765, "total_steps": 6188, "loss": 0.0811, "lr": 5.693843311126523e-07, "epoch": 6.522920203735144, "percentage": 93.16, "elapsed_time": "20:55:26", "remaining_time": "1:32:06"}
|
| 1156 |
+
{"current_steps": 5770, "total_steps": 6188, "loss": 0.0757, "lr": 5.560968503981378e-07, "epoch": 6.528579513299378, "percentage": 93.24, "elapsed_time": "20:57:07", "remaining_time": "1:31:04"}
|
| 1157 |
+
{"current_steps": 5775, "total_steps": 6188, "loss": 0.0851, "lr": 5.429640619062726e-07, "epoch": 6.53423882286361, "percentage": 93.33, "elapsed_time": "20:58:48", "remaining_time": "1:30:01"}
|
| 1158 |
+
{"current_steps": 5780, "total_steps": 6188, "loss": 0.0827, "lr": 5.299860701191772e-07, "epoch": 6.539898132427844, "percentage": 93.41, "elapsed_time": "21:00:25", "remaining_time": "1:28:58"}
|
| 1159 |
+
{"current_steps": 5785, "total_steps": 6188, "loss": 0.1145, "lr": 5.171629782874354e-07, "epoch": 6.545557441992077, "percentage": 93.49, "elapsed_time": "21:02:18", "remaining_time": "1:27:56"}
|
| 1160 |
+
{"current_steps": 5790, "total_steps": 6188, "loss": 0.0643, "lr": 5.044948884292766e-07, "epoch": 6.55121675155631, "percentage": 93.57, "elapsed_time": "21:03:49", "remaining_time": "1:26:52"}
|
| 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"}
|