Training in progress, step 6600
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:a0a485bb21934e2d1e885c19573bdd42aa0ed8a44d8158c7ef5e3f9225261580
|
| 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:db99f2cd2cb0b9fafb7b90f55fa632e2acd9a216c68f8ad2b2d9882e14363add
|
| 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 sha256:3a99c287df32d9234cf51f64d467db64edb1cc963a8f976df99a5e81165a25c7
|
| 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 sha256:7a4584d51fd6cf9a1edf607401d70d60c1278a2b4cabbde3dd9abbd1cf8f8e61
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1278,3 +1278,43 @@
|
|
| 1278 |
{"current_steps": 6390, "total_steps": 9625, "loss": 0.2173, "lr": 1.2264312839761434e-05, "epoch": 4.647508184794471, "percentage": 66.39, "elapsed_time": "1 day, 18:50:02", "remaining_time": "21:41:06"}
|
| 1279 |
{"current_steps": 6395, "total_steps": 9625, "loss": 0.2006, "lr": 1.2230879686451438e-05, "epoch": 4.6511458712259, "percentage": 66.44, "elapsed_time": "1 day, 18:51:44", "remaining_time": "21:38:56"}
|
| 1280 |
{"current_steps": 6400, "total_steps": 9625, "loss": 0.2086, "lr": 1.2197472082213048e-05, "epoch": 4.65478355765733, "percentage": 66.49, "elapsed_time": "1 day, 18:53:26", "remaining_time": "21:36:46"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1278 |
{"current_steps": 6390, "total_steps": 9625, "loss": 0.2173, "lr": 1.2264312839761434e-05, "epoch": 4.647508184794471, "percentage": 66.39, "elapsed_time": "1 day, 18:50:02", "remaining_time": "21:41:06"}
|
| 1279 |
{"current_steps": 6395, "total_steps": 9625, "loss": 0.2006, "lr": 1.2230879686451438e-05, "epoch": 4.6511458712259, "percentage": 66.44, "elapsed_time": "1 day, 18:51:44", "remaining_time": "21:38:56"}
|
| 1280 |
{"current_steps": 6400, "total_steps": 9625, "loss": 0.2086, "lr": 1.2197472082213048e-05, "epoch": 4.65478355765733, "percentage": 66.49, "elapsed_time": "1 day, 18:53:26", "remaining_time": "21:36:46"}
|
| 1281 |
+
{"current_steps": 6405, "total_steps": 9625, "loss": 0.201, "lr": 1.2164090136908526e-05, "epoch": 4.65842124408876, "percentage": 66.55, "elapsed_time": "1 day, 18:56:09", "remaining_time": "21:35:06"}
|
| 1282 |
+
{"current_steps": 6410, "total_steps": 9625, "loss": 0.2178, "lr": 1.213073396031578e-05, "epoch": 4.662058930520189, "percentage": 66.6, "elapsed_time": "1 day, 18:57:49", "remaining_time": "21:32:56"}
|
| 1283 |
+
{"current_steps": 6415, "total_steps": 9625, "loss": 0.2189, "lr": 1.2097403662127966e-05, "epoch": 4.665696616951619, "percentage": 66.65, "elapsed_time": "1 day, 18:59:29", "remaining_time": "21:30:44"}
|
| 1284 |
+
{"current_steps": 6420, "total_steps": 9625, "loss": 0.2087, "lr": 1.2064099351953136e-05, "epoch": 4.669334303383049, "percentage": 66.7, "elapsed_time": "1 day, 19:01:09", "remaining_time": "21:28:34"}
|
| 1285 |
+
{"current_steps": 6425, "total_steps": 9625, "loss": 0.2086, "lr": 1.2030821139313895e-05, "epoch": 4.672971989814478, "percentage": 66.75, "elapsed_time": "1 day, 19:02:46", "remaining_time": "21:26:21"}
|
| 1286 |
+
{"current_steps": 6430, "total_steps": 9625, "loss": 0.2076, "lr": 1.1997569133646993e-05, "epoch": 4.676609676245907, "percentage": 66.81, "elapsed_time": "1 day, 19:04:27", "remaining_time": "21:24:11"}
|
| 1287 |
+
{"current_steps": 6435, "total_steps": 9625, "loss": 0.2061, "lr": 1.1964343444303044e-05, "epoch": 4.6802473626773375, "percentage": 66.86, "elapsed_time": "1 day, 19:06:08", "remaining_time": "21:22:01"}
|
| 1288 |
+
{"current_steps": 6440, "total_steps": 9625, "loss": 0.2088, "lr": 1.1931144180546074e-05, "epoch": 4.683885049108767, "percentage": 66.91, "elapsed_time": "1 day, 19:07:46", "remaining_time": "21:19:49"}
|
| 1289 |
+
{"current_steps": 6445, "total_steps": 9625, "loss": 0.2047, "lr": 1.189797145155323e-05, "epoch": 4.687522735540196, "percentage": 66.96, "elapsed_time": "1 day, 19:09:26", "remaining_time": "21:17:38"}
|
| 1290 |
+
{"current_steps": 6450, "total_steps": 9625, "loss": 0.2079, "lr": 1.1864825366414405e-05, "epoch": 4.691160421971626, "percentage": 67.01, "elapsed_time": "1 day, 19:11:04", "remaining_time": "21:15:27"}
|
| 1291 |
+
{"current_steps": 6455, "total_steps": 9625, "loss": 0.2021, "lr": 1.1831706034131849e-05, "epoch": 4.694798108403056, "percentage": 67.06, "elapsed_time": "1 day, 19:12:45", "remaining_time": "21:13:16"}
|
| 1292 |
+
{"current_steps": 6460, "total_steps": 9625, "loss": 0.2027, "lr": 1.1798613563619861e-05, "epoch": 4.698435794834485, "percentage": 67.12, "elapsed_time": "1 day, 19:14:21", "remaining_time": "21:11:04"}
|
| 1293 |
+
{"current_steps": 6465, "total_steps": 9625, "loss": 0.2042, "lr": 1.176554806370438e-05, "epoch": 4.702073481265915, "percentage": 67.17, "elapsed_time": "1 day, 19:15:57", "remaining_time": "21:08:52"}
|
| 1294 |
+
{"current_steps": 6470, "total_steps": 9625, "loss": 0.2152, "lr": 1.1732509643122673e-05, "epoch": 4.705711167697345, "percentage": 67.22, "elapsed_time": "1 day, 19:17:33", "remaining_time": "21:06:39"}
|
| 1295 |
+
{"current_steps": 6475, "total_steps": 9625, "loss": 0.2057, "lr": 1.169949841052294e-05, "epoch": 4.709348854128774, "percentage": 67.27, "elapsed_time": "1 day, 19:19:18", "remaining_time": "21:04:31"}
|
| 1296 |
+
{"current_steps": 6480, "total_steps": 9625, "loss": 0.2049, "lr": 1.1666514474463963e-05, "epoch": 4.712986540560204, "percentage": 67.32, "elapsed_time": "1 day, 19:20:59", "remaining_time": "21:02:21"}
|
| 1297 |
+
{"current_steps": 6485, "total_steps": 9625, "loss": 0.2058, "lr": 1.1633557943414797e-05, "epoch": 4.716624226991633, "percentage": 67.38, "elapsed_time": "1 day, 19:22:47", "remaining_time": "21:00:15"}
|
| 1298 |
+
{"current_steps": 6490, "total_steps": 9625, "loss": 0.2122, "lr": 1.1600628925754331e-05, "epoch": 4.720261913423063, "percentage": 67.43, "elapsed_time": "1 day, 19:24:25", "remaining_time": "20:58:04"}
|
| 1299 |
+
{"current_steps": 6495, "total_steps": 9625, "loss": 0.2047, "lr": 1.1567727529771004e-05, "epoch": 4.723899599854493, "percentage": 67.48, "elapsed_time": "1 day, 19:26:02", "remaining_time": "20:55:52"}
|
| 1300 |
+
{"current_steps": 6500, "total_steps": 9625, "loss": 0.202, "lr": 1.1534853863662398e-05, "epoch": 4.727537286285922, "percentage": 67.53, "elapsed_time": "1 day, 19:27:46", "remaining_time": "20:53:44"}
|
| 1301 |
+
{"current_steps": 6505, "total_steps": 9625, "loss": 0.2058, "lr": 1.1502008035534924e-05, "epoch": 4.731174972717351, "percentage": 67.58, "elapsed_time": "1 day, 19:29:26", "remaining_time": "20:51:33"}
|
| 1302 |
+
{"current_steps": 6510, "total_steps": 9625, "loss": 0.1998, "lr": 1.1469190153403443e-05, "epoch": 4.734812659148782, "percentage": 67.64, "elapsed_time": "1 day, 19:31:11", "remaining_time": "20:49:26"}
|
| 1303 |
+
{"current_steps": 6515, "total_steps": 9625, "loss": 0.2015, "lr": 1.1436400325190898e-05, "epoch": 4.738450345580211, "percentage": 67.69, "elapsed_time": "1 day, 19:32:48", "remaining_time": "20:47:15"}
|
| 1304 |
+
{"current_steps": 6520, "total_steps": 9625, "loss": 0.2068, "lr": 1.1403638658727995e-05, "epoch": 4.74208803201164, "percentage": 67.74, "elapsed_time": "1 day, 19:34:30", "remaining_time": "20:45:06"}
|
| 1305 |
+
{"current_steps": 6525, "total_steps": 9625, "loss": 0.205, "lr": 1.1370905261752815e-05, "epoch": 4.745725718443071, "percentage": 67.79, "elapsed_time": "1 day, 19:36:11", "remaining_time": "20:42:56"}
|
| 1306 |
+
{"current_steps": 6530, "total_steps": 9625, "loss": 0.2169, "lr": 1.1338200241910485e-05, "epoch": 4.7493634048745, "percentage": 67.84, "elapsed_time": "1 day, 19:37:48", "remaining_time": "20:40:45"}
|
| 1307 |
+
{"current_steps": 6535, "total_steps": 9625, "loss": 0.2014, "lr": 1.1305523706752812e-05, "epoch": 4.753001091305929, "percentage": 67.9, "elapsed_time": "1 day, 19:39:30", "remaining_time": "20:38:36"}
|
| 1308 |
+
{"current_steps": 6540, "total_steps": 9625, "loss": 0.2076, "lr": 1.1272875763737914e-05, "epoch": 4.756638777737359, "percentage": 67.95, "elapsed_time": "1 day, 19:41:16", "remaining_time": "20:36:29"}
|
| 1309 |
+
{"current_steps": 6545, "total_steps": 9625, "loss": 0.2092, "lr": 1.1240256520229904e-05, "epoch": 4.760276464168789, "percentage": 68.0, "elapsed_time": "1 day, 19:42:50", "remaining_time": "20:34:16"}
|
| 1310 |
+
{"current_steps": 6550, "total_steps": 9625, "loss": 0.2058, "lr": 1.120766608349849e-05, "epoch": 4.763914150600218, "percentage": 68.05, "elapsed_time": "1 day, 19:44:33", "remaining_time": "20:32:08"}
|
| 1311 |
+
{"current_steps": 6555, "total_steps": 9625, "loss": 0.1995, "lr": 1.1175104560718686e-05, "epoch": 4.767551837031648, "percentage": 68.1, "elapsed_time": "1 day, 19:46:14", "remaining_time": "20:29:59"}
|
| 1312 |
+
{"current_steps": 6560, "total_steps": 9625, "loss": 0.1991, "lr": 1.1142572058970389e-05, "epoch": 4.771189523463077, "percentage": 68.16, "elapsed_time": "1 day, 19:47:52", "remaining_time": "20:27:48"}
|
| 1313 |
+
{"current_steps": 6565, "total_steps": 9625, "loss": 0.1869, "lr": 1.111006868523806e-05, "epoch": 4.774827209894507, "percentage": 68.21, "elapsed_time": "1 day, 19:49:31", "remaining_time": "20:25:38"}
|
| 1314 |
+
{"current_steps": 6570, "total_steps": 9625, "loss": 0.2196, "lr": 1.1077594546410384e-05, "epoch": 4.778464896325937, "percentage": 68.26, "elapsed_time": "1 day, 19:51:12", "remaining_time": "20:23:29"}
|
| 1315 |
+
{"current_steps": 6575, "total_steps": 9625, "loss": 0.2023, "lr": 1.1045149749279905e-05, "epoch": 4.782102582757366, "percentage": 68.31, "elapsed_time": "1 day, 19:53:00", "remaining_time": "20:21:23"}
|
| 1316 |
+
{"current_steps": 6580, "total_steps": 9625, "loss": 0.214, "lr": 1.1012734400542682e-05, "epoch": 4.785740269188796, "percentage": 68.36, "elapsed_time": "1 day, 19:54:44", "remaining_time": "20:19:16"}
|
| 1317 |
+
{"current_steps": 6585, "total_steps": 9625, "loss": 0.2075, "lr": 1.09803486067979e-05, "epoch": 4.789377955620226, "percentage": 68.42, "elapsed_time": "1 day, 19:56:29", "remaining_time": "20:17:09"}
|
| 1318 |
+
{"current_steps": 6590, "total_steps": 9625, "loss": 0.2155, "lr": 1.0947992474547595e-05, "epoch": 4.793015642051655, "percentage": 68.47, "elapsed_time": "1 day, 19:58:09", "remaining_time": "20:14:59"}
|
| 1319 |
+
{"current_steps": 6595, "total_steps": 9625, "loss": 0.2063, "lr": 1.091566611019622e-05, "epoch": 4.796653328483085, "percentage": 68.52, "elapsed_time": "1 day, 19:59:48", "remaining_time": "20:12:49"}
|
| 1320 |
+
{"current_steps": 6600, "total_steps": 9625, "loss": 0.1991, "lr": 1.088336962005036e-05, "epoch": 4.800291014914515, "percentage": 68.57, "elapsed_time": "1 day, 20:01:26", "remaining_time": "20:10:39"}
|