Training in progress, step 1200
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 sha256:99aaa921c845c84229f73e116c91b4110fbc7781d30a4d2f98eeabb420256dba
|
| 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:c33a0f3f073720e6bb3c06970391e827d6020dcab4d6990a560721e6860ad228
|
| 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 sha256:4cd69efeac811fbedac1f0b307e970d29f6c907e72d219ae4c72a5103202caa0
|
| 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 sha256:4443d2e8314a6aa44675622fe36e145290b213153248f4b277d57e7a5509b348
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -198,3 +198,43 @@
|
|
| 198 |
{"current_steps": 990, "total_steps": 1652, "loss": 0.1573, "lr": 1.6633500390248414e-05, "epoch": 4.195329087048832, "percentage": 59.93, "elapsed_time": "10:27:00", "remaining_time": "6:59:16"}
|
| 199 |
{"current_steps": 995, "total_steps": 1652, "loss": 0.1518, "lr": 1.642529618771324e-05, "epoch": 4.2165605095541405, "percentage": 60.23, "elapsed_time": "10:30:09", "remaining_time": "6:56:05"}
|
| 200 |
{"current_steps": 1000, "total_steps": 1652, "loss": 0.1813, "lr": 1.6217491412855233e-05, "epoch": 4.237791932059448, "percentage": 60.53, "elapsed_time": "10:33:17", "remaining_time": "6:52:54"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 198 |
{"current_steps": 990, "total_steps": 1652, "loss": 0.1573, "lr": 1.6633500390248414e-05, "epoch": 4.195329087048832, "percentage": 59.93, "elapsed_time": "10:27:00", "remaining_time": "6:59:16"}
|
| 199 |
{"current_steps": 995, "total_steps": 1652, "loss": 0.1518, "lr": 1.642529618771324e-05, "epoch": 4.2165605095541405, "percentage": 60.23, "elapsed_time": "10:30:09", "remaining_time": "6:56:05"}
|
| 200 |
{"current_steps": 1000, "total_steps": 1652, "loss": 0.1813, "lr": 1.6217491412855233e-05, "epoch": 4.237791932059448, "percentage": 60.53, "elapsed_time": "10:33:17", "remaining_time": "6:52:54"}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 1652, "loss": 0.1753, "lr": 1.60101092852145e-05, "epoch": 4.259023354564756, "percentage": 60.84, "elapsed_time": "10:37:33", "remaining_time": "6:50:27"}
|
| 202 |
+
{"current_steps": 1010, "total_steps": 1652, "loss": 0.1579, "lr": 1.5803172977105686e-05, "epoch": 4.280254777070064, "percentage": 61.14, "elapsed_time": "10:40:43", "remaining_time": "6:47:16"}
|
| 203 |
+
{"current_steps": 1015, "total_steps": 1652, "loss": 0.1607, "lr": 1.5596705611028792e-05, "epoch": 4.301486199575372, "percentage": 61.44, "elapsed_time": "10:43:54", "remaining_time": "6:44:06"}
|
| 204 |
+
{"current_steps": 1020, "total_steps": 1652, "loss": 0.162, "lr": 1.5390730257085494e-05, "epoch": 4.322717622080679, "percentage": 61.74, "elapsed_time": "10:47:03", "remaining_time": "6:40:55"}
|
| 205 |
+
{"current_steps": 1025, "total_steps": 1652, "loss": 0.1734, "lr": 1.5185269930401381e-05, "epoch": 4.343949044585988, "percentage": 62.05, "elapsed_time": "10:50:13", "remaining_time": "6:37:44"}
|
| 206 |
+
{"current_steps": 1030, "total_steps": 1652, "loss": 0.1632, "lr": 1.4980347588554302e-05, "epoch": 4.365180467091295, "percentage": 62.35, "elapsed_time": "10:53:23", "remaining_time": "6:34:34"}
|
| 207 |
+
{"current_steps": 1035, "total_steps": 1652, "loss": 0.1897, "lr": 1.4775986129009137e-05, "epoch": 4.386411889596603, "percentage": 62.65, "elapsed_time": "10:56:32", "remaining_time": "6:31:23"}
|
| 208 |
+
{"current_steps": 1040, "total_steps": 1652, "loss": 0.1672, "lr": 1.4572208386559304e-05, "epoch": 4.407643312101911, "percentage": 62.95, "elapsed_time": "10:59:42", "remaining_time": "6:28:12"}
|
| 209 |
+
{"current_steps": 1045, "total_steps": 1652, "loss": 0.1598, "lr": 1.436903713077526e-05, "epoch": 4.428874734607219, "percentage": 63.26, "elapsed_time": "11:02:52", "remaining_time": "6:25:02"}
|
| 210 |
+
{"current_steps": 1050, "total_steps": 1652, "loss": 0.1619, "lr": 1.4166495063460295e-05, "epoch": 4.450106157112526, "percentage": 63.56, "elapsed_time": "11:06:01", "remaining_time": "6:21:51"}
|
| 211 |
+
{"current_steps": 1055, "total_steps": 1652, "loss": 0.1806, "lr": 1.3964604816113896e-05, "epoch": 4.471337579617835, "percentage": 63.86, "elapsed_time": "11:09:09", "remaining_time": "6:18:39"}
|
| 212 |
+
{"current_steps": 1060, "total_steps": 1652, "loss": 0.1715, "lr": 1.3763388947402953e-05, "epoch": 4.492569002123142, "percentage": 64.16, "elapsed_time": "11:12:17", "remaining_time": "6:15:28"}
|
| 213 |
+
{"current_steps": 1065, "total_steps": 1652, "loss": 0.1691, "lr": 1.3562869940641123e-05, "epoch": 4.51380042462845, "percentage": 64.47, "elapsed_time": "11:15:26", "remaining_time": "6:12:17"}
|
| 214 |
+
{"current_steps": 1070, "total_steps": 1652, "loss": 0.1601, "lr": 1.3363070201276606e-05, "epoch": 4.535031847133758, "percentage": 64.77, "elapsed_time": "11:18:35", "remaining_time": "6:09:06"}
|
| 215 |
+
{"current_steps": 1075, "total_steps": 1652, "loss": 0.1715, "lr": 1.316401205438862e-05, "epoch": 4.556263269639066, "percentage": 65.07, "elapsed_time": "11:21:44", "remaining_time": "6:05:55"}
|
| 216 |
+
{"current_steps": 1080, "total_steps": 1652, "loss": 0.1734, "lr": 1.2965717742192866e-05, "epoch": 4.5774946921443735, "percentage": 65.38, "elapsed_time": "11:24:53", "remaining_time": "6:02:44"}
|
| 217 |
+
{"current_steps": 1085, "total_steps": 1652, "loss": 0.1702, "lr": 1.276820942155622e-05, "epoch": 4.598726114649682, "percentage": 65.68, "elapsed_time": "11:28:02", "remaining_time": "5:59:33"}
|
| 218 |
+
{"current_steps": 1090, "total_steps": 1652, "loss": 0.1714, "lr": 1.2571509161521007e-05, "epoch": 4.619957537154989, "percentage": 65.98, "elapsed_time": "11:31:12", "remaining_time": "5:56:22"}
|
| 219 |
+
{"current_steps": 1095, "total_steps": 1652, "loss": 0.1954, "lr": 1.2375638940839062e-05, "epoch": 4.6411889596602975, "percentage": 66.28, "elapsed_time": "11:34:20", "remaining_time": "5:53:11"}
|
| 220 |
+
{"current_steps": 1100, "total_steps": 1652, "loss": 0.1619, "lr": 1.2180620645515875e-05, "epoch": 4.662420382165605, "percentage": 66.59, "elapsed_time": "11:37:30", "remaining_time": "5:50:01"}
|
| 221 |
+
{"current_steps": 1105, "total_steps": 1652, "loss": 0.1794, "lr": 1.1986476066365125e-05, "epoch": 4.683651804670913, "percentage": 66.89, "elapsed_time": "11:40:39", "remaining_time": "5:46:50"}
|
| 222 |
+
{"current_steps": 1110, "total_steps": 1652, "loss": 0.1964, "lr": 1.179322689657381e-05, "epoch": 4.704883227176221, "percentage": 67.19, "elapsed_time": "11:43:47", "remaining_time": "5:43:39"}
|
| 223 |
+
{"current_steps": 1115, "total_steps": 1652, "loss": 0.1633, "lr": 1.1600894729278333e-05, "epoch": 4.726114649681529, "percentage": 67.49, "elapsed_time": "11:46:55", "remaining_time": "5:40:28"}
|
| 224 |
+
{"current_steps": 1120, "total_steps": 1652, "loss": 0.1663, "lr": 1.1409501055151726e-05, "epoch": 4.747346072186836, "percentage": 67.8, "elapsed_time": "11:50:04", "remaining_time": "5:37:17"}
|
| 225 |
+
{"current_steps": 1125, "total_steps": 1652, "loss": 0.1481, "lr": 1.1219067260002352e-05, "epoch": 4.768577494692145, "percentage": 68.1, "elapsed_time": "11:53:13", "remaining_time": "5:34:06"}
|
| 226 |
+
{"current_steps": 1130, "total_steps": 1652, "loss": 0.1763, "lr": 1.1029614622384307e-05, "epoch": 4.789808917197452, "percentage": 68.4, "elapsed_time": "11:56:22", "remaining_time": "5:30:55"}
|
| 227 |
+
{"current_steps": 1135, "total_steps": 1652, "loss": 0.1665, "lr": 1.0841164311219812e-05, "epoch": 4.81104033970276, "percentage": 68.7, "elapsed_time": "11:59:30", "remaining_time": "5:27:44"}
|
| 228 |
+
{"current_steps": 1140, "total_steps": 1652, "loss": 0.1727, "lr": 1.0653737383433869e-05, "epoch": 4.832271762208068, "percentage": 69.01, "elapsed_time": "12:02:39", "remaining_time": "5:24:33"}
|
| 229 |
+
{"current_steps": 1145, "total_steps": 1652, "loss": 0.1664, "lr": 1.0467354781601395e-05, "epoch": 4.853503184713376, "percentage": 69.31, "elapsed_time": "12:05:47", "remaining_time": "5:21:22"}
|
| 230 |
+
{"current_steps": 1150, "total_steps": 1652, "loss": 0.165, "lr": 1.0282037331607167e-05, "epoch": 4.8747346072186835, "percentage": 69.61, "elapsed_time": "12:08:56", "remaining_time": "5:18:11"}
|
| 231 |
+
{"current_steps": 1155, "total_steps": 1652, "loss": 0.1613, "lr": 1.0097805740318797e-05, "epoch": 4.895966029723992, "percentage": 69.92, "elapsed_time": "12:12:05", "remaining_time": "5:15:01"}
|
| 232 |
+
{"current_steps": 1160, "total_steps": 1652, "loss": 0.1855, "lr": 9.914680593273e-06, "epoch": 4.917197452229299, "percentage": 70.22, "elapsed_time": "12:15:13", "remaining_time": "5:11:50"}
|
| 233 |
+
{"current_steps": 1165, "total_steps": 1652, "loss": 0.1692, "lr": 9.732682352375418e-06, "epoch": 4.9384288747346075, "percentage": 70.52, "elapsed_time": "12:18:22", "remaining_time": "5:08:39"}
|
| 234 |
+
{"current_steps": 1170, "total_steps": 1652, "loss": 0.1666, "lr": 9.551831353614272e-06, "epoch": 4.959660297239915, "percentage": 70.82, "elapsed_time": "12:21:31", "remaining_time": "5:05:29"}
|
| 235 |
+
{"current_steps": 1175, "total_steps": 1652, "loss": 0.1838, "lr": 9.372147804788063e-06, "epoch": 4.980891719745223, "percentage": 71.13, "elapsed_time": "12:24:40", "remaining_time": "5:02:18"}
|
| 236 |
+
{"current_steps": 1180, "total_steps": 1652, "loss": 0.1652, "lr": 9.193651783247616e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "12:27:29", "remaining_time": "4:58:59"}
|
| 237 |
+
{"current_steps": 1185, "total_steps": 1652, "loss": 0.1657, "lr": 9.016363233652686e-06, "epoch": 5.021231422505308, "percentage": 71.73, "elapsed_time": "12:30:38", "remaining_time": "4:55:49"}
|
| 238 |
+
{"current_steps": 1190, "total_steps": 1652, "loss": 0.1813, "lr": 8.840301965743405e-06, "epoch": 5.042462845010616, "percentage": 72.03, "elapsed_time": "12:33:47", "remaining_time": "4:52:38"}
|
| 239 |
+
{"current_steps": 1195, "total_steps": 1652, "loss": 0.1678, "lr": 8.665487652126785e-06, "epoch": 5.063694267515924, "percentage": 72.34, "elapsed_time": "12:36:56", "remaining_time": "4:49:28"}
|
| 240 |
+
{"current_steps": 1200, "total_steps": 1652, "loss": 0.1691, "lr": 8.491939826078552e-06, "epoch": 5.084925690021231, "percentage": 72.64, "elapsed_time": "12:40:05", "remaining_time": "4:46:18"}
|