Training in progress, step 6000
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 sha256:4109189b6ab5263999bf1faf5b8cdf6aadb716c2ea96c38168d78f657530d5b2
|
| 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 sha256:6a08baf41080cddda6cc9da60fce6aefe7043be72e1e8e44753c7ae08e091245
|
| 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 sha256:2f65e50943fbe7a5eaa13a37d94dd558352ccaf08bd920637501390af20b70d7
|
| 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:db80ea583f361460520315da7d6f31ad19647eb0d3af66f616ae8e0350e0a9ae
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1158,3 +1158,43 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 1161 |
+
{"current_steps": 5805, "total_steps": 6713, "loss": 0.1778, "lr": 2.1933465304510394e-06, "epoch": 6.054251434533125, "percentage": 86.47, "elapsed_time": "1 day, 5:36:44", "remaining_time": "4:37:54"}
|
| 1162 |
+
{"current_steps": 5810, "total_steps": 6713, "loss": 0.1773, "lr": 2.1697285485257245e-06, "epoch": 6.059467918622849, "percentage": 86.55, "elapsed_time": "1 day, 5:39:38", "remaining_time": "4:36:35"}
|
| 1163 |
+
{"current_steps": 5815, "total_steps": 6713, "loss": 0.1795, "lr": 2.1462311200918816e-06, "epoch": 6.0646844027125715, "percentage": 86.62, "elapsed_time": "1 day, 5:42:19", "remaining_time": "4:35:14"}
|
| 1164 |
+
{"current_steps": 5820, "total_steps": 6713, "loss": 0.1605, "lr": 2.122854404019601e-06, "epoch": 6.069900886802295, "percentage": 86.7, "elapsed_time": "1 day, 5:45:04", "remaining_time": "4:33:53"}
|
| 1165 |
+
{"current_steps": 5825, "total_steps": 6713, "loss": 0.1685, "lr": 2.0995985583628366e-06, "epoch": 6.075117370892019, "percentage": 86.77, "elapsed_time": "1 day, 5:47:42", "remaining_time": "4:32:31"}
|
| 1166 |
+
{"current_steps": 5830, "total_steps": 6713, "loss": 0.1681, "lr": 2.076463740358299e-06, "epoch": 6.080333854981743, "percentage": 86.85, "elapsed_time": "1 day, 5:50:13", "remaining_time": "4:31:08"}
|
| 1167 |
+
{"current_steps": 5835, "total_steps": 6713, "loss": 0.1687, "lr": 2.053450106424426e-06, "epoch": 6.085550339071466, "percentage": 86.92, "elapsed_time": "1 day, 5:53:01", "remaining_time": "4:29:47"}
|
| 1168 |
+
{"current_steps": 5840, "total_steps": 6713, "loss": 0.1659, "lr": 2.030557812160301e-06, "epoch": 6.090766823161189, "percentage": 87.0, "elapsed_time": "1 day, 5:55:48", "remaining_time": "4:28:26"}
|
| 1169 |
+
{"current_steps": 5845, "total_steps": 6713, "loss": 0.1678, "lr": 2.0077870123446107e-06, "epoch": 6.095983307250913, "percentage": 87.07, "elapsed_time": "1 day, 5:58:32", "remaining_time": "4:27:05"}
|
| 1170 |
+
{"current_steps": 5850, "total_steps": 6713, "loss": 0.1684, "lr": 1.985137860934594e-06, "epoch": 6.101199791340637, "percentage": 87.14, "elapsed_time": "1 day, 6:01:19", "remaining_time": "4:25:44"}
|
| 1171 |
+
{"current_steps": 5855, "total_steps": 6713, "loss": 0.1664, "lr": 1.962610511065013e-06, "epoch": 6.10641627543036, "percentage": 87.22, "elapsed_time": "1 day, 6:04:09", "remaining_time": "4:24:23"}
|
| 1172 |
+
{"current_steps": 5860, "total_steps": 6713, "loss": 0.1805, "lr": 1.940205115047098e-06, "epoch": 6.1116327595200834, "percentage": 87.29, "elapsed_time": "1 day, 6:06:57", "remaining_time": "4:23:01"}
|
| 1173 |
+
{"current_steps": 5865, "total_steps": 6713, "loss": 0.1609, "lr": 1.917921824367539e-06, "epoch": 6.116849243609807, "percentage": 87.37, "elapsed_time": "1 day, 6:09:46", "remaining_time": "4:21:40"}
|
| 1174 |
+
{"current_steps": 5870, "total_steps": 6713, "loss": 0.1709, "lr": 1.8957607896874419e-06, "epoch": 6.122065727699531, "percentage": 87.44, "elapsed_time": "1 day, 6:12:26", "remaining_time": "4:20:17"}
|
| 1175 |
+
{"current_steps": 5875, "total_steps": 6713, "loss": 0.1712, "lr": 1.8737221608413314e-06, "epoch": 6.127282211789254, "percentage": 87.52, "elapsed_time": "1 day, 6:15:16", "remaining_time": "4:18:55"}
|
| 1176 |
+
{"current_steps": 5880, "total_steps": 6713, "loss": 0.1675, "lr": 1.8518060868361099e-06, "epoch": 6.132498695878978, "percentage": 87.59, "elapsed_time": "1 day, 6:17:58", "remaining_time": "4:17:32"}
|
| 1177 |
+
{"current_steps": 5885, "total_steps": 6713, "loss": 0.1751, "lr": 1.8300127158500714e-06, "epoch": 6.137715179968701, "percentage": 87.67, "elapsed_time": "1 day, 6:20:50", "remaining_time": "4:16:11"}
|
| 1178 |
+
{"current_steps": 5890, "total_steps": 6713, "loss": 0.1691, "lr": 1.8083421952319047e-06, "epoch": 6.142931664058425, "percentage": 87.74, "elapsed_time": "1 day, 6:23:40", "remaining_time": "4:14:49"}
|
| 1179 |
+
{"current_steps": 5895, "total_steps": 6713, "loss": 0.1617, "lr": 1.786794671499672e-06, "epoch": 6.148148148148148, "percentage": 87.81, "elapsed_time": "1 day, 6:26:22", "remaining_time": "4:13:25"}
|
| 1180 |
+
{"current_steps": 5900, "total_steps": 6713, "loss": 0.1756, "lr": 1.7653702903398384e-06, "epoch": 6.153364632237872, "percentage": 87.89, "elapsed_time": "1 day, 6:28:55", "remaining_time": "4:12:01"}
|
| 1181 |
+
{"current_steps": 5905, "total_steps": 6713, "loss": 0.1683, "lr": 1.7440691966062816e-06, "epoch": 6.158581116327595, "percentage": 87.96, "elapsed_time": "1 day, 6:31:38", "remaining_time": "4:10:37"}
|
| 1182 |
+
{"current_steps": 5910, "total_steps": 6713, "loss": 0.1603, "lr": 1.722891534319313e-06, "epoch": 6.163797600417318, "percentage": 88.04, "elapsed_time": "1 day, 6:34:17", "remaining_time": "4:09:13"}
|
| 1183 |
+
{"current_steps": 5915, "total_steps": 6713, "loss": 0.1769, "lr": 1.7018374466646981e-06, "epoch": 6.169014084507042, "percentage": 88.11, "elapsed_time": "1 day, 6:36:53", "remaining_time": "4:07:49"}
|
| 1184 |
+
{"current_steps": 5920, "total_steps": 6713, "loss": 0.1776, "lr": 1.6809070759927015e-06, "epoch": 6.174230568596766, "percentage": 88.19, "elapsed_time": "1 day, 6:39:31", "remaining_time": "4:06:24"}
|
| 1185 |
+
{"current_steps": 5925, "total_steps": 6713, "loss": 0.1685, "lr": 1.6601005638171065e-06, "epoch": 6.1794470526864895, "percentage": 88.26, "elapsed_time": "1 day, 6:42:18", "remaining_time": "4:05:01"}
|
| 1186 |
+
{"current_steps": 5930, "total_steps": 6713, "loss": 0.1705, "lr": 1.639418050814281e-06, "epoch": 6.184663536776213, "percentage": 88.34, "elapsed_time": "1 day, 6:45:04", "remaining_time": "4:03:37"}
|
| 1187 |
+
{"current_steps": 5935, "total_steps": 6713, "loss": 0.1668, "lr": 1.6188596768221976e-06, "epoch": 6.189880020865936, "percentage": 88.41, "elapsed_time": "1 day, 6:47:50", "remaining_time": "4:02:13"}
|
| 1188 |
+
{"current_steps": 5940, "total_steps": 6713, "loss": 0.1657, "lr": 1.5984255808395198e-06, "epoch": 6.19509650495566, "percentage": 88.49, "elapsed_time": "1 day, 6:50:45", "remaining_time": "4:00:50"}
|
| 1189 |
+
{"current_steps": 5945, "total_steps": 6713, "loss": 0.1752, "lr": 1.5781159010246306e-06, "epoch": 6.200312989045384, "percentage": 88.56, "elapsed_time": "1 day, 6:53:27", "remaining_time": "3:59:26"}
|
| 1190 |
+
{"current_steps": 5950, "total_steps": 6713, "loss": 0.1741, "lr": 1.557930774694727e-06, "epoch": 6.2055294731351065, "percentage": 88.63, "elapsed_time": "1 day, 6:56:16", "remaining_time": "3:58:02"}
|
| 1191 |
+
{"current_steps": 5955, "total_steps": 6713, "loss": 0.1588, "lr": 1.5378703383248694e-06, "epoch": 6.21074595722483, "percentage": 88.71, "elapsed_time": "1 day, 6:59:00", "remaining_time": "3:56:37"}
|
| 1192 |
+
{"current_steps": 5960, "total_steps": 6713, "loss": 0.1619, "lr": 1.5179347275470812e-06, "epoch": 6.215962441314554, "percentage": 88.78, "elapsed_time": "1 day, 7:01:44", "remaining_time": "3:55:12"}
|
| 1193 |
+
{"current_steps": 5965, "total_steps": 6713, "loss": 0.1709, "lr": 1.4981240771494032e-06, "epoch": 6.221178925404278, "percentage": 88.86, "elapsed_time": "1 day, 7:04:34", "remaining_time": "3:53:48"}
|
| 1194 |
+
{"current_steps": 5970, "total_steps": 6713, "loss": 0.1719, "lr": 1.4784385210750052e-06, "epoch": 6.2263954094940015, "percentage": 88.93, "elapsed_time": "1 day, 7:07:06", "remaining_time": "3:52:22"}
|
| 1195 |
+
{"current_steps": 5975, "total_steps": 6713, "loss": 0.1657, "lr": 1.458878192421278e-06, "epoch": 6.231611893583724, "percentage": 89.01, "elapsed_time": "1 day, 7:09:57", "remaining_time": "3:50:58"}
|
| 1196 |
+
{"current_steps": 5980, "total_steps": 6713, "loss": 0.1812, "lr": 1.4394432234389167e-06, "epoch": 6.236828377673448, "percentage": 89.08, "elapsed_time": "1 day, 7:12:28", "remaining_time": "3:49:31"}
|
| 1197 |
+
{"current_steps": 5985, "total_steps": 6713, "loss": 0.166, "lr": 1.4201337455310537e-06, "epoch": 6.242044861763172, "percentage": 89.16, "elapsed_time": "1 day, 7:15:12", "remaining_time": "3:48:05"}
|
| 1198 |
+
{"current_steps": 5990, "total_steps": 6713, "loss": 0.1653, "lr": 1.4009498892523388e-06, "epoch": 6.247261345852895, "percentage": 89.23, "elapsed_time": "1 day, 7:17:51", "remaining_time": "3:46:39"}
|
| 1199 |
+
{"current_steps": 5995, "total_steps": 6713, "loss": 0.1734, "lr": 1.3818917843080848e-06, "epoch": 6.2524778299426185, "percentage": 89.3, "elapsed_time": "1 day, 7:20:38", "remaining_time": "3:45:14"}
|
| 1200 |
+
{"current_steps": 6000, "total_steps": 6713, "loss": 0.164, "lr": 1.3629595595533673e-06, "epoch": 6.257694314032342, "percentage": 89.38, "elapsed_time": "1 day, 7:23:17", "remaining_time": "3:43:47"}
|