Training in progress, step 4600
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 sha256:5d15ee3c56517564b347e14933e4cb1d6ad745b494dace78409d289c96753bec
|
| 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 sha256:5c4827140ecdcc9774e124f4b5754dbe015d1ea51b5991c7864251e30da04971
|
| 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 sha256:29712fa03fe9ba6b6e471f03450992242520fbfc632d60b84c9e7179a5f439df
|
| 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:a30b125a73010f3eb48b100d2a808724488854a04467160f862da0c3000a987e
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -882,3 +882,46 @@
|
|
| 882 |
{"current_steps": 4410, "total_steps": 9128, "loss": 0.1573, "lr": 2.463450338922234e-05, "epoch": 3.38204833141542, "percentage": 48.31, "elapsed_time": "1 day, 3:47:38", "remaining_time": "1 day, 5:44:06"}
|
| 883 |
{"current_steps": 4415, "total_steps": 9128, "loss": 0.1555, "lr": 2.4597293691133918e-05, "epoch": 3.3858841580360566, "percentage": 48.37, "elapsed_time": "1 day, 3:48:55", "remaining_time": "1 day, 5:41:34"}
|
| 884 |
{"current_steps": 4420, "total_steps": 9128, "loss": 0.1683, "lr": 2.4560067184631555e-05, "epoch": 3.3897199846566934, "percentage": 48.42, "elapsed_time": "1 day, 3:50:11", "remaining_time": "1 day, 5:39:01"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 882 |
{"current_steps": 4410, "total_steps": 9128, "loss": 0.1573, "lr": 2.463450338922234e-05, "epoch": 3.38204833141542, "percentage": 48.31, "elapsed_time": "1 day, 3:47:38", "remaining_time": "1 day, 5:44:06"}
|
| 883 |
{"current_steps": 4415, "total_steps": 9128, "loss": 0.1555, "lr": 2.4597293691133918e-05, "epoch": 3.3858841580360566, "percentage": 48.37, "elapsed_time": "1 day, 3:48:55", "remaining_time": "1 day, 5:41:34"}
|
| 884 |
{"current_steps": 4420, "total_steps": 9128, "loss": 0.1683, "lr": 2.4560067184631555e-05, "epoch": 3.3897199846566934, "percentage": 48.42, "elapsed_time": "1 day, 3:50:11", "remaining_time": "1 day, 5:39:01"}
|
| 885 |
+
{"current_steps": 4425, "total_steps": 9128, "loss": 0.1573, "lr": 2.4522824005821075e-05, "epoch": 3.3935558112773303, "percentage": 48.48, "elapsed_time": "1 day, 3:51:25", "remaining_time": "1 day, 5:36:26"}
|
| 886 |
+
{"current_steps": 4430, "total_steps": 9128, "loss": 0.1518, "lr": 2.4485564290869298e-05, "epoch": 3.397391637897967, "percentage": 48.53, "elapsed_time": "1 day, 3:52:39", "remaining_time": "1 day, 5:33:50"}
|
| 887 |
+
{"current_steps": 4435, "total_steps": 9128, "loss": 0.1486, "lr": 2.444828817600347e-05, "epoch": 3.4012274645186036, "percentage": 48.59, "elapsed_time": "1 day, 3:53:53", "remaining_time": "1 day, 5:31:15"}
|
| 888 |
+
{"current_steps": 4440, "total_steps": 9128, "loss": 0.1687, "lr": 2.441099579751081e-05, "epoch": 3.4050632911392404, "percentage": 48.64, "elapsed_time": "1 day, 3:55:10", "remaining_time": "1 day, 5:28:44"}
|
| 889 |
+
{"current_steps": 4445, "total_steps": 9128, "loss": 0.1631, "lr": 2.4373687291738003e-05, "epoch": 3.4088991177598773, "percentage": 48.7, "elapsed_time": "1 day, 3:56:26", "remaining_time": "1 day, 5:26:12"}
|
| 890 |
+
{"current_steps": 4450, "total_steps": 9128, "loss": 0.1561, "lr": 2.4336362795090694e-05, "epoch": 3.412734944380514, "percentage": 48.75, "elapsed_time": "1 day, 3:57:41", "remaining_time": "1 day, 5:23:39"}
|
| 891 |
+
{"current_steps": 4455, "total_steps": 9128, "loss": 0.1558, "lr": 2.4299022444032986e-05, "epoch": 3.4165707710011506, "percentage": 48.81, "elapsed_time": "1 day, 3:58:57", "remaining_time": "1 day, 5:21:07"}
|
| 892 |
+
{"current_steps": 4460, "total_steps": 9128, "loss": 0.1618, "lr": 2.4261666375086957e-05, "epoch": 3.4204065976217874, "percentage": 48.86, "elapsed_time": "1 day, 4:00:15", "remaining_time": "1 day, 5:18:36"}
|
| 893 |
+
{"current_steps": 4465, "total_steps": 9128, "loss": 0.1594, "lr": 2.4224294724832152e-05, "epoch": 3.4242424242424243, "percentage": 48.92, "elapsed_time": "1 day, 4:01:29", "remaining_time": "1 day, 5:16:03"}
|
| 894 |
+
{"current_steps": 4470, "total_steps": 9128, "loss": 0.1571, "lr": 2.418690762990508e-05, "epoch": 3.428078250863061, "percentage": 48.97, "elapsed_time": "1 day, 4:02:44", "remaining_time": "1 day, 5:13:30"}
|
| 895 |
+
{"current_steps": 4475, "total_steps": 9128, "loss": 0.158, "lr": 2.414950522699872e-05, "epoch": 3.4319140774836976, "percentage": 49.02, "elapsed_time": "1 day, 4:03:58", "remaining_time": "1 day, 5:10:57"}
|
| 896 |
+
{"current_steps": 4480, "total_steps": 9128, "loss": 0.1506, "lr": 2.4112087652862018e-05, "epoch": 3.4357499041043345, "percentage": 49.08, "elapsed_time": "1 day, 4:05:12", "remaining_time": "1 day, 5:08:24"}
|
| 897 |
+
{"current_steps": 4485, "total_steps": 9128, "loss": 0.1582, "lr": 2.4074655044299395e-05, "epoch": 3.4395857307249713, "percentage": 49.13, "elapsed_time": "1 day, 4:06:28", "remaining_time": "1 day, 5:05:53"}
|
| 898 |
+
{"current_steps": 4490, "total_steps": 9128, "loss": 0.1604, "lr": 2.4037207538170223e-05, "epoch": 3.4434215573456077, "percentage": 49.19, "elapsed_time": "1 day, 4:07:45", "remaining_time": "1 day, 5:03:23"}
|
| 899 |
+
{"current_steps": 4495, "total_steps": 9128, "loss": 0.1551, "lr": 2.399974527138837e-05, "epoch": 3.4472573839662446, "percentage": 49.24, "elapsed_time": "1 day, 4:08:59", "remaining_time": "1 day, 5:00:50"}
|
| 900 |
+
{"current_steps": 4500, "total_steps": 9128, "loss": 0.1608, "lr": 2.3962268380921635e-05, "epoch": 3.4510932105868815, "percentage": 49.3, "elapsed_time": "1 day, 4:10:13", "remaining_time": "1 day, 4:58:17"}
|
| 901 |
+
{"current_steps": 4505, "total_steps": 9128, "loss": 0.1622, "lr": 2.3924777003791318e-05, "epoch": 3.4549290372075183, "percentage": 49.35, "elapsed_time": "1 day, 4:11:28", "remaining_time": "1 day, 4:55:47"}
|
| 902 |
+
{"current_steps": 4510, "total_steps": 9128, "loss": 0.1561, "lr": 2.3887271277071655e-05, "epoch": 3.458764863828155, "percentage": 49.41, "elapsed_time": "1 day, 4:12:43", "remaining_time": "1 day, 4:53:15"}
|
| 903 |
+
{"current_steps": 4515, "total_steps": 9128, "loss": 0.1599, "lr": 2.3849751337889377e-05, "epoch": 3.4626006904487916, "percentage": 49.46, "elapsed_time": "1 day, 4:13:58", "remaining_time": "1 day, 4:50:44"}
|
| 904 |
+
{"current_steps": 4520, "total_steps": 9128, "loss": 0.1549, "lr": 2.381221732342315e-05, "epoch": 3.4664365170694285, "percentage": 49.52, "elapsed_time": "1 day, 4:15:12", "remaining_time": "1 day, 4:48:12"}
|
| 905 |
+
{"current_steps": 4525, "total_steps": 9128, "loss": 0.1623, "lr": 2.3774669370903113e-05, "epoch": 3.4702723436900653, "percentage": 49.57, "elapsed_time": "1 day, 4:16:26", "remaining_time": "1 day, 4:45:40"}
|
| 906 |
+
{"current_steps": 4530, "total_steps": 9128, "loss": 0.158, "lr": 2.3737107617610376e-05, "epoch": 3.4741081703107017, "percentage": 49.63, "elapsed_time": "1 day, 4:17:40", "remaining_time": "1 day, 4:43:09"}
|
| 907 |
+
{"current_steps": 4535, "total_steps": 9128, "loss": 0.1687, "lr": 2.369953220087649e-05, "epoch": 3.4779439969313386, "percentage": 49.68, "elapsed_time": "1 day, 4:18:56", "remaining_time": "1 day, 4:40:39"}
|
| 908 |
+
{"current_steps": 4540, "total_steps": 9128, "loss": 0.1607, "lr": 2.3661943258082952e-05, "epoch": 3.4817798235519755, "percentage": 49.74, "elapsed_time": "1 day, 4:20:15", "remaining_time": "1 day, 4:38:13"}
|
| 909 |
+
{"current_steps": 4545, "total_steps": 9128, "loss": 0.1594, "lr": 2.362434092666075e-05, "epoch": 3.4856156501726123, "percentage": 49.79, "elapsed_time": "1 day, 4:21:29", "remaining_time": "1 day, 4:35:43"}
|
| 910 |
+
{"current_steps": 4550, "total_steps": 9128, "loss": 0.1573, "lr": 2.3586725344089785e-05, "epoch": 3.489451476793249, "percentage": 49.85, "elapsed_time": "1 day, 4:22:42", "remaining_time": "1 day, 4:33:11"}
|
| 911 |
+
{"current_steps": 4555, "total_steps": 9128, "loss": 0.1511, "lr": 2.3549096647898436e-05, "epoch": 3.4932873034138856, "percentage": 49.9, "elapsed_time": "1 day, 4:23:57", "remaining_time": "1 day, 4:30:41"}
|
| 912 |
+
{"current_steps": 4560, "total_steps": 9128, "loss": 0.1627, "lr": 2.3511454975662992e-05, "epoch": 3.4971231300345225, "percentage": 49.96, "elapsed_time": "1 day, 4:25:12", "remaining_time": "1 day, 4:28:11"}
|
| 913 |
+
{"current_steps": 4565, "total_steps": 9128, "loss": 0.1535, "lr": 2.347380046500723e-05, "epoch": 3.5009589566551593, "percentage": 50.01, "elapsed_time": "1 day, 4:26:26", "remaining_time": "1 day, 4:25:41"}
|
| 914 |
+
{"current_steps": 4570, "total_steps": 9128, "loss": 0.1508, "lr": 2.343613325360182e-05, "epoch": 3.5047947832757957, "percentage": 50.07, "elapsed_time": "1 day, 4:27:42", "remaining_time": "1 day, 4:23:13"}
|
| 915 |
+
{"current_steps": 4575, "total_steps": 9128, "loss": 0.1516, "lr": 2.33984534791639e-05, "epoch": 3.5086306098964326, "percentage": 50.12, "elapsed_time": "1 day, 4:28:57", "remaining_time": "1 day, 4:20:44"}
|
| 916 |
+
{"current_steps": 4580, "total_steps": 9128, "loss": 0.1669, "lr": 2.336076127945653e-05, "epoch": 3.5124664365170695, "percentage": 50.18, "elapsed_time": "1 day, 4:30:12", "remaining_time": "1 day, 4:18:15"}
|
| 917 |
+
{"current_steps": 4585, "total_steps": 9128, "loss": 0.1506, "lr": 2.3323056792288198e-05, "epoch": 3.5163022631377063, "percentage": 50.23, "elapsed_time": "1 day, 4:31:26", "remaining_time": "1 day, 4:15:45"}
|
| 918 |
+
{"current_steps": 4590, "total_steps": 9128, "loss": 0.1574, "lr": 2.3285340155512313e-05, "epoch": 3.520138089758343, "percentage": 50.28, "elapsed_time": "1 day, 4:32:48", "remaining_time": "1 day, 4:13:24"}
|
| 919 |
+
{"current_steps": 4595, "total_steps": 9128, "loss": 0.1448, "lr": 2.324761150702672e-05, "epoch": 3.5239739163789796, "percentage": 50.34, "elapsed_time": "1 day, 4:34:08", "remaining_time": "1 day, 4:11:00"}
|
| 920 |
+
{"current_steps": 4600, "total_steps": 9128, "loss": 0.1466, "lr": 2.3209870984773157e-05, "epoch": 3.5278097429996165, "percentage": 50.39, "elapsed_time": "1 day, 4:35:21", "remaining_time": "1 day, 4:08:31"}
|
| 921 |
+
{"current_steps": 4605, "total_steps": 9128, "loss": 0.1549, "lr": 2.3172118726736797e-05, "epoch": 3.5316455696202533, "percentage": 50.45, "elapsed_time": "1 day, 4:38:04", "remaining_time": "1 day, 4:07:28"}
|
| 922 |
+
{"current_steps": 4610, "total_steps": 9128, "loss": 0.1544, "lr": 2.3134354870945698e-05, "epoch": 3.5354813962408898, "percentage": 50.5, "elapsed_time": "1 day, 4:39:20", "remaining_time": "1 day, 4:05:01"}
|
| 923 |
+
{"current_steps": 4615, "total_steps": 9128, "loss": 0.1528, "lr": 2.3096579555470354e-05, "epoch": 3.5393172228615266, "percentage": 50.56, "elapsed_time": "1 day, 4:40:36", "remaining_time": "1 day, 4:02:34"}
|
| 924 |
+
{"current_steps": 4620, "total_steps": 9128, "loss": 0.1551, "lr": 2.3058792918423122e-05, "epoch": 3.5431530494821635, "percentage": 50.61, "elapsed_time": "1 day, 4:41:52", "remaining_time": "1 day, 4:00:07"}
|
| 925 |
+
{"current_steps": 4625, "total_steps": 9128, "loss": 0.156, "lr": 2.302099509795778e-05, "epoch": 3.5469888761028, "percentage": 50.67, "elapsed_time": "1 day, 4:43:07", "remaining_time": "1 day, 3:57:40"}
|
| 926 |
+
{"current_steps": 4630, "total_steps": 9128, "loss": 0.1658, "lr": 2.2983186232268966e-05, "epoch": 3.5508247027234368, "percentage": 50.72, "elapsed_time": "1 day, 4:44:25", "remaining_time": "1 day, 3:55:15"}
|
| 927 |
+
{"current_steps": 4635, "total_steps": 9128, "loss": 0.267, "lr": 2.2945366459591735e-05, "epoch": 3.5546605293440736, "percentage": 50.78, "elapsed_time": "1 day, 4:46:46", "remaining_time": "1 day, 3:53:51"}
|