Training in progress, step 6800
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 sha256:43929bcb84854a628bdbfe411358ea57bdb2dfd0849a904a261469b886f4d586
|
| 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 sha256:492bb2cafab9a442ad608a55cb6561f378f38a4af107c2e39bf1f77f71c37f19
|
| 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 sha256:1ae91653ac81c53ed02f56846f5fd33eaf5e02fabfc713217498e36479d7ac50
|
| 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:daa21bb457105a867a7160aecfc9635ff015a2d1faaf14859764abb966497605
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1320,3 +1320,52 @@
|
|
| 1320 |
{"current_steps": 6600, "total_steps": 9128, "loss": 0.1686, "lr": 8.64693780011877e-06, "epoch": 5.061373225930188, "percentage": 72.3, "elapsed_time": "1 day, 16:59:44", "remaining_time": "15:42:09"}
|
| 1321 |
{"current_steps": 6605, "total_steps": 9128, "loss": 0.1635, "lr": 8.615475040796631e-06, "epoch": 5.065209052550824, "percentage": 72.36, "elapsed_time": "1 day, 17:03:53", "remaining_time": "15:41:09"}
|
| 1322 |
{"current_steps": 6610, "total_steps": 9128, "loss": 0.1704, "lr": 8.58405390505154e-06, "epoch": 5.069044879171462, "percentage": 72.41, "elapsed_time": "1 day, 17:06:43", "remaining_time": "15:39:40"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1320 |
{"current_steps": 6600, "total_steps": 9128, "loss": 0.1686, "lr": 8.64693780011877e-06, "epoch": 5.061373225930188, "percentage": 72.3, "elapsed_time": "1 day, 16:59:44", "remaining_time": "15:42:09"}
|
| 1321 |
{"current_steps": 6605, "total_steps": 9128, "loss": 0.1635, "lr": 8.615475040796631e-06, "epoch": 5.065209052550824, "percentage": 72.36, "elapsed_time": "1 day, 17:03:53", "remaining_time": "15:41:09"}
|
| 1322 |
{"current_steps": 6610, "total_steps": 9128, "loss": 0.1704, "lr": 8.58405390505154e-06, "epoch": 5.069044879171462, "percentage": 72.41, "elapsed_time": "1 day, 17:06:43", "remaining_time": "15:39:40"}
|
| 1323 |
+
{"current_steps": 6615, "total_steps": 9128, "loss": 0.1834, "lr": 8.552674507763994e-06, "epoch": 5.072880705792098, "percentage": 72.47, "elapsed_time": "1 day, 17:09:34", "remaining_time": "15:38:10"}
|
| 1324 |
+
{"current_steps": 6620, "total_steps": 9128, "loss": 0.1511, "lr": 8.521336963661899e-06, "epoch": 5.076716532412735, "percentage": 72.52, "elapsed_time": "1 day, 17:12:06", "remaining_time": "15:36:33"}
|
| 1325 |
+
{"current_steps": 6625, "total_steps": 9128, "loss": 0.1559, "lr": 8.490041387320168e-06, "epoch": 5.080552359033372, "percentage": 72.58, "elapsed_time": "1 day, 17:14:56", "remaining_time": "15:35:03"}
|
| 1326 |
+
{"current_steps": 6630, "total_steps": 9128, "loss": 0.1631, "lr": 8.458787893160216e-06, "epoch": 5.084388185654008, "percentage": 72.63, "elapsed_time": "1 day, 17:17:51", "remaining_time": "15:33:35"}
|
| 1327 |
+
{"current_steps": 6635, "total_steps": 9128, "loss": 0.1687, "lr": 8.42757659544966e-06, "epoch": 5.088224012274646, "percentage": 72.69, "elapsed_time": "1 day, 17:20:35", "remaining_time": "15:32:02"}
|
| 1328 |
+
{"current_steps": 6640, "total_steps": 9128, "loss": 0.1683, "lr": 8.39640760830181e-06, "epoch": 5.092059838895282, "percentage": 72.74, "elapsed_time": "1 day, 17:23:30", "remaining_time": "15:30:34"}
|
| 1329 |
+
{"current_steps": 6645, "total_steps": 9128, "loss": 0.1664, "lr": 8.365281045675261e-06, "epoch": 5.095895665515918, "percentage": 72.8, "elapsed_time": "1 day, 17:26:32", "remaining_time": "15:29:07"}
|
| 1330 |
+
{"current_steps": 6650, "total_steps": 9128, "loss": 0.1472, "lr": 8.334197021373547e-06, "epoch": 5.099731492136556, "percentage": 72.85, "elapsed_time": "1 day, 17:29:30", "remaining_time": "15:27:40"}
|
| 1331 |
+
{"current_steps": 6655, "total_steps": 9128, "loss": 0.1498, "lr": 8.303155649044643e-06, "epoch": 5.103567318757192, "percentage": 72.91, "elapsed_time": "1 day, 17:32:28", "remaining_time": "15:26:12"}
|
| 1332 |
+
{"current_steps": 6660, "total_steps": 9128, "loss": 0.1441, "lr": 8.272157042180573e-06, "epoch": 5.107403145377829, "percentage": 72.96, "elapsed_time": "1 day, 17:35:24", "remaining_time": "15:24:43"}
|
| 1333 |
+
{"current_steps": 6665, "total_steps": 9128, "loss": 0.1715, "lr": 8.241201314117045e-06, "epoch": 5.111238971998466, "percentage": 73.02, "elapsed_time": "1 day, 17:38:01", "remaining_time": "15:23:07"}
|
| 1334 |
+
{"current_steps": 6670, "total_steps": 9128, "loss": 0.1539, "lr": 8.21028857803294e-06, "epoch": 5.115074798619102, "percentage": 73.07, "elapsed_time": "1 day, 17:40:28", "remaining_time": "15:21:27"}
|
| 1335 |
+
{"current_steps": 6675, "total_steps": 9128, "loss": 0.173, "lr": 8.179418946950003e-06, "epoch": 5.118910625239739, "percentage": 73.13, "elapsed_time": "1 day, 17:43:14", "remaining_time": "15:19:55"}
|
| 1336 |
+
{"current_steps": 6680, "total_steps": 9128, "loss": 0.177, "lr": 8.148592533732365e-06, "epoch": 5.122746451860376, "percentage": 73.18, "elapsed_time": "1 day, 17:46:08", "remaining_time": "15:18:24"}
|
| 1337 |
+
{"current_steps": 6685, "total_steps": 9128, "loss": 0.1716, "lr": 8.117809451086119e-06, "epoch": 5.1265822784810124, "percentage": 73.24, "elapsed_time": "1 day, 17:48:59", "remaining_time": "15:16:53"}
|
| 1338 |
+
{"current_steps": 6690, "total_steps": 9128, "loss": 0.1668, "lr": 8.087069811558976e-06, "epoch": 5.13041810510165, "percentage": 73.29, "elapsed_time": "1 day, 17:52:00", "remaining_time": "15:15:26"}
|
| 1339 |
+
{"current_steps": 6695, "total_steps": 9128, "loss": 0.1717, "lr": 8.0563737275398e-06, "epoch": 5.134253931722286, "percentage": 73.35, "elapsed_time": "1 day, 17:55:00", "remaining_time": "15:13:58"}
|
| 1340 |
+
{"current_steps": 6700, "total_steps": 9128, "loss": 0.1673, "lr": 8.025721311258171e-06, "epoch": 5.138089758342923, "percentage": 73.4, "elapsed_time": "1 day, 17:57:58", "remaining_time": "15:12:29"}
|
| 1341 |
+
{"current_steps": 6705, "total_steps": 9128, "loss": 0.1703, "lr": 7.995112674784078e-06, "epoch": 5.14192558496356, "percentage": 73.46, "elapsed_time": "1 day, 18:00:59", "remaining_time": "15:11:01"}
|
| 1342 |
+
{"current_steps": 6710, "total_steps": 9128, "loss": 0.1715, "lr": 7.964547930027395e-06, "epoch": 5.145761411584196, "percentage": 73.51, "elapsed_time": "1 day, 18:04:02", "remaining_time": "15:09:33"}
|
| 1343 |
+
{"current_steps": 6715, "total_steps": 9128, "loss": 0.1713, "lr": 7.934027188737541e-06, "epoch": 5.149597238204833, "percentage": 73.56, "elapsed_time": "1 day, 18:06:58", "remaining_time": "15:08:03"}
|
| 1344 |
+
{"current_steps": 6720, "total_steps": 9128, "loss": 0.167, "lr": 7.903550562503049e-06, "epoch": 5.15343306482547, "percentage": 73.62, "elapsed_time": "1 day, 18:09:44", "remaining_time": "15:06:29"}
|
| 1345 |
+
{"current_steps": 6725, "total_steps": 9128, "loss": 0.1652, "lr": 7.873118162751159e-06, "epoch": 5.1572688914461065, "percentage": 73.67, "elapsed_time": "1 day, 18:12:34", "remaining_time": "15:04:56"}
|
| 1346 |
+
{"current_steps": 6730, "total_steps": 9128, "loss": 0.1383, "lr": 7.842730100747409e-06, "epoch": 5.161104718066744, "percentage": 73.73, "elapsed_time": "1 day, 18:14:33", "remaining_time": "15:03:06"}
|
| 1347 |
+
{"current_steps": 6735, "total_steps": 9128, "loss": 0.1658, "lr": 7.812386487595238e-06, "epoch": 5.16494054468738, "percentage": 73.78, "elapsed_time": "1 day, 18:17:30", "remaining_time": "15:01:35"}
|
| 1348 |
+
{"current_steps": 6740, "total_steps": 9128, "loss": 0.1638, "lr": 7.782087434235573e-06, "epoch": 5.168776371308017, "percentage": 73.84, "elapsed_time": "1 day, 18:20:12", "remaining_time": "15:00:00"}
|
| 1349 |
+
{"current_steps": 6745, "total_steps": 9128, "loss": 0.1683, "lr": 7.751833051446414e-06, "epoch": 5.172612197928654, "percentage": 73.89, "elapsed_time": "1 day, 18:23:10", "remaining_time": "14:58:30"}
|
| 1350 |
+
{"current_steps": 6750, "total_steps": 9128, "loss": 0.163, "lr": 7.721623449842451e-06, "epoch": 5.17644802454929, "percentage": 73.95, "elapsed_time": "1 day, 18:26:08", "remaining_time": "14:56:59"}
|
| 1351 |
+
{"current_steps": 6755, "total_steps": 9128, "loss": 0.1681, "lr": 7.691458739874636e-06, "epoch": 5.180283851169927, "percentage": 74.0, "elapsed_time": "1 day, 18:29:06", "remaining_time": "14:55:29"}
|
| 1352 |
+
{"current_steps": 6760, "total_steps": 9128, "loss": 0.1684, "lr": 7.6613390318298e-06, "epoch": 5.184119677790564, "percentage": 74.06, "elapsed_time": "1 day, 18:32:00", "remaining_time": "14:53:57"}
|
| 1353 |
+
{"current_steps": 6765, "total_steps": 9128, "loss": 0.1459, "lr": 7.631264435830235e-06, "epoch": 5.1879555044112005, "percentage": 74.11, "elapsed_time": "1 day, 18:34:26", "remaining_time": "14:52:15"}
|
| 1354 |
+
{"current_steps": 6770, "total_steps": 9128, "loss": 0.15, "lr": 7.601235061833294e-06, "epoch": 5.191791331031838, "percentage": 74.17, "elapsed_time": "1 day, 18:36:48", "remaining_time": "14:50:32"}
|
| 1355 |
+
{"current_steps": 6775, "total_steps": 9128, "loss": 0.1623, "lr": 7.5712510196309965e-06, "epoch": 5.195627157652474, "percentage": 74.22, "elapsed_time": "1 day, 18:39:36", "remaining_time": "14:48:58"}
|
| 1356 |
+
{"current_steps": 6780, "total_steps": 9128, "loss": 0.1693, "lr": 7.54131241884962e-06, "epoch": 5.199462984273111, "percentage": 74.28, "elapsed_time": "1 day, 18:42:28", "remaining_time": "14:47:25"}
|
| 1357 |
+
{"current_steps": 6785, "total_steps": 9128, "loss": 0.1632, "lr": 7.5114193689493e-06, "epoch": 5.203298810893748, "percentage": 74.33, "elapsed_time": "1 day, 18:45:09", "remaining_time": "14:45:48"}
|
| 1358 |
+
{"current_steps": 6790, "total_steps": 9128, "loss": 0.1555, "lr": 7.481571979223634e-06, "epoch": 5.207134637514384, "percentage": 74.39, "elapsed_time": "1 day, 18:48:01", "remaining_time": "14:44:14"}
|
| 1359 |
+
{"current_steps": 6795, "total_steps": 9128, "loss": 0.1666, "lr": 7.451770358799273e-06, "epoch": 5.210970464135021, "percentage": 74.44, "elapsed_time": "1 day, 18:50:57", "remaining_time": "14:42:42"}
|
| 1360 |
+
{"current_steps": 6800, "total_steps": 9128, "loss": 0.1617, "lr": 7.4220146166355355e-06, "epoch": 5.214806290755658, "percentage": 74.5, "elapsed_time": "1 day, 18:53:10", "remaining_time": "14:40:56"}
|
| 1361 |
+
{"current_steps": 6805, "total_steps": 9128, "loss": 0.1547, "lr": 7.392304861524e-06, "epoch": 5.2186421173762945, "percentage": 74.55, "elapsed_time": "1 day, 18:55:34", "remaining_time": "14:39:13"}
|
| 1362 |
+
{"current_steps": 6810, "total_steps": 9128, "loss": 0.1422, "lr": 7.362641202088103e-06, "epoch": 5.222477943996932, "percentage": 74.61, "elapsed_time": "1 day, 18:56:49", "remaining_time": "14:37:06"}
|
| 1363 |
+
{"current_steps": 6815, "total_steps": 9128, "loss": 0.1389, "lr": 7.333023746782757e-06, "epoch": 5.226313770617568, "percentage": 74.66, "elapsed_time": "1 day, 18:58:04", "remaining_time": "14:34:59"}
|
| 1364 |
+
{"current_steps": 6820, "total_steps": 9128, "loss": 0.1419, "lr": 7.303452603893932e-06, "epoch": 5.230149597238205, "percentage": 74.72, "elapsed_time": "1 day, 18:59:23", "remaining_time": "14:32:54"}
|
| 1365 |
+
{"current_steps": 6825, "total_steps": 9128, "loss": 0.1351, "lr": 7.273927881538305e-06, "epoch": 5.233985423858842, "percentage": 74.77, "elapsed_time": "1 day, 19:00:38", "remaining_time": "14:30:48"}
|
| 1366 |
+
{"current_steps": 6830, "total_steps": 9128, "loss": 0.1449, "lr": 7.244449687662787e-06, "epoch": 5.237821250479478, "percentage": 74.82, "elapsed_time": "1 day, 19:01:53", "remaining_time": "14:28:41"}
|
| 1367 |
+
{"current_steps": 6835, "total_steps": 9128, "loss": 0.1249, "lr": 7.215018130044202e-06, "epoch": 5.241657077100115, "percentage": 74.88, "elapsed_time": "1 day, 19:03:07", "remaining_time": "14:26:35"}
|
| 1368 |
+
{"current_steps": 6840, "total_steps": 9128, "loss": 0.1456, "lr": 7.185633316288862e-06, "epoch": 5.245492903720752, "percentage": 74.93, "elapsed_time": "1 day, 19:04:20", "remaining_time": "14:24:28"}
|
| 1369 |
+
{"current_steps": 6845, "total_steps": 9128, "loss": 0.1334, "lr": 7.156295353832161e-06, "epoch": 5.2493287303413885, "percentage": 74.99, "elapsed_time": "1 day, 19:05:35", "remaining_time": "14:22:21"}
|
| 1370 |
+
{"current_steps": 6850, "total_steps": 9128, "loss": 0.1363, "lr": 7.127004349938234e-06, "epoch": 5.253164556962025, "percentage": 75.04, "elapsed_time": "1 day, 19:06:53", "remaining_time": "14:20:17"}
|
| 1371 |
+
{"current_steps": 6855, "total_steps": 9128, "loss": 0.1355, "lr": 7.0977604116994795e-06, "epoch": 5.257000383582662, "percentage": 75.1, "elapsed_time": "1 day, 19:08:12", "remaining_time": "14:18:12"}
|