Training in progress, step 5200
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 sha256:8fdb661d7c97130ca54b094ac9e0264b98a8d5c24cd8339cdce4acbbe35b83fe
|
| 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 sha256:9a07983c1ba93262b5c47c929f5508f3911d95f29c4bde5176cd2a275143b8c2
|
| 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 sha256:4e45f998edb788bf318c024fda4fbd550243466ad7d81a5935fb058a2a3233f1
|
| 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:bdf6262e8baa25c4f1ac9031c32e32b3efb427e627bfb87a904399f453a4a565
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1021,3 +1021,43 @@
|
|
| 1021 |
{"current_steps": 4990, "total_steps": 6713, "loss": 0.1523, "lr": 7.513947204275453e-06, "epoch": 5.204486176317162, "percentage": 74.33, "elapsed_time": "15:11:18", "remaining_time": "5:14:39"}
|
| 1022 |
{"current_steps": 4995, "total_steps": 6713, "loss": 0.1411, "lr": 7.473364440588404e-06, "epoch": 5.209702660406886, "percentage": 74.41, "elapsed_time": "15:14:17", "remaining_time": "5:14:27"}
|
| 1023 |
{"current_steps": 5000, "total_steps": 6713, "loss": 0.1531, "lr": 7.432866371610403e-06, "epoch": 5.214919144496609, "percentage": 74.48, "elapsed_time": "15:17:12", "remaining_time": "5:14:14"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1021 |
{"current_steps": 4990, "total_steps": 6713, "loss": 0.1523, "lr": 7.513947204275453e-06, "epoch": 5.204486176317162, "percentage": 74.33, "elapsed_time": "15:11:18", "remaining_time": "5:14:39"}
|
| 1022 |
{"current_steps": 4995, "total_steps": 6713, "loss": 0.1411, "lr": 7.473364440588404e-06, "epoch": 5.209702660406886, "percentage": 74.41, "elapsed_time": "15:14:17", "remaining_time": "5:14:27"}
|
| 1023 |
{"current_steps": 5000, "total_steps": 6713, "loss": 0.1531, "lr": 7.432866371610403e-06, "epoch": 5.214919144496609, "percentage": 74.48, "elapsed_time": "15:17:12", "remaining_time": "5:14:14"}
|
| 1024 |
+
{"current_steps": 5005, "total_steps": 6713, "loss": 0.1598, "lr": 7.392453271155786e-06, "epoch": 5.220135628586333, "percentage": 74.56, "elapsed_time": "15:21:21", "remaining_time": "5:14:25"}
|
| 1025 |
+
{"current_steps": 5010, "total_steps": 6713, "loss": 0.1455, "lr": 7.352125412464368e-06, "epoch": 5.225352112676056, "percentage": 74.63, "elapsed_time": "15:24:13", "remaining_time": "5:14:09"}
|
| 1026 |
+
{"current_steps": 5015, "total_steps": 6713, "loss": 0.1621, "lr": 7.311883068199659e-06, "epoch": 5.23056859676578, "percentage": 74.71, "elapsed_time": "15:27:02", "remaining_time": "5:13:52"}
|
| 1027 |
+
{"current_steps": 5020, "total_steps": 6713, "loss": 0.1428, "lr": 7.271726510446968e-06, "epoch": 5.2357850808555035, "percentage": 74.78, "elapsed_time": "15:29:54", "remaining_time": "5:13:36"}
|
| 1028 |
+
{"current_steps": 5025, "total_steps": 6713, "loss": 0.133, "lr": 7.231656010711609e-06, "epoch": 5.241001564945227, "percentage": 74.85, "elapsed_time": "15:32:53", "remaining_time": "5:13:22"}
|
| 1029 |
+
{"current_steps": 5030, "total_steps": 6713, "loss": 0.1333, "lr": 7.191671839917025e-06, "epoch": 5.24621804903495, "percentage": 74.93, "elapsed_time": "15:35:58", "remaining_time": "5:13:10"}
|
| 1030 |
+
{"current_steps": 5035, "total_steps": 6713, "loss": 0.138, "lr": 7.15177426840298e-06, "epoch": 5.251434533124674, "percentage": 75.0, "elapsed_time": "15:39:00", "remaining_time": "5:12:56"}
|
| 1031 |
+
{"current_steps": 5040, "total_steps": 6713, "loss": 0.1555, "lr": 7.111963565923723e-06, "epoch": 5.256651017214398, "percentage": 75.08, "elapsed_time": "15:41:54", "remaining_time": "5:12:39"}
|
| 1032 |
+
{"current_steps": 5045, "total_steps": 6713, "loss": 0.1774, "lr": 7.07224000164618e-06, "epoch": 5.261867501304121, "percentage": 75.15, "elapsed_time": "15:44:32", "remaining_time": "5:12:17"}
|
| 1033 |
+
{"current_steps": 5050, "total_steps": 6713, "loss": 0.1661, "lr": 7.032603844148098e-06, "epoch": 5.267083985393844, "percentage": 75.23, "elapsed_time": "15:47:32", "remaining_time": "5:12:01"}
|
| 1034 |
+
{"current_steps": 5055, "total_steps": 6713, "loss": 0.1444, "lr": 6.993055361416281e-06, "epoch": 5.272300469483568, "percentage": 75.3, "elapsed_time": "15:50:29", "remaining_time": "5:11:45"}
|
| 1035 |
+
{"current_steps": 5060, "total_steps": 6713, "loss": 0.1531, "lr": 6.953594820844725e-06, "epoch": 5.277516953573292, "percentage": 75.38, "elapsed_time": "15:53:31", "remaining_time": "5:11:29"}
|
| 1036 |
+
{"current_steps": 5065, "total_steps": 6713, "loss": 0.1575, "lr": 6.914222489232834e-06, "epoch": 5.2827334376630155, "percentage": 75.45, "elapsed_time": "15:56:34", "remaining_time": "5:11:14"}
|
| 1037 |
+
{"current_steps": 5070, "total_steps": 6713, "loss": 0.1659, "lr": 6.874938632783639e-06, "epoch": 5.287949921752738, "percentage": 75.53, "elapsed_time": "15:59:41", "remaining_time": "5:11:00"}
|
| 1038 |
+
{"current_steps": 5075, "total_steps": 6713, "loss": 0.1531, "lr": 6.835743517101947e-06, "epoch": 5.293166405842462, "percentage": 75.6, "elapsed_time": "16:02:46", "remaining_time": "5:10:44"}
|
| 1039 |
+
{"current_steps": 5080, "total_steps": 6713, "loss": 0.1565, "lr": 6.796637407192608e-06, "epoch": 5.298382889932186, "percentage": 75.67, "elapsed_time": "16:05:45", "remaining_time": "5:10:26"}
|
| 1040 |
+
{"current_steps": 5085, "total_steps": 6713, "loss": 0.1476, "lr": 6.7576205674586405e-06, "epoch": 5.30359937402191, "percentage": 75.75, "elapsed_time": "16:08:48", "remaining_time": "5:10:10"}
|
| 1041 |
+
{"current_steps": 5090, "total_steps": 6713, "loss": 0.1426, "lr": 6.718693261699542e-06, "epoch": 5.3088158581116325, "percentage": 75.82, "elapsed_time": "16:11:52", "remaining_time": "5:09:53"}
|
| 1042 |
+
{"current_steps": 5095, "total_steps": 6713, "loss": 0.175, "lr": 6.679855753109419e-06, "epoch": 5.314032342201356, "percentage": 75.9, "elapsed_time": "16:14:55", "remaining_time": "5:09:36"}
|
| 1043 |
+
{"current_steps": 5100, "total_steps": 6713, "loss": 0.1732, "lr": 6.64110830427527e-06, "epoch": 5.31924882629108, "percentage": 75.97, "elapsed_time": "16:18:00", "remaining_time": "5:09:19"}
|
| 1044 |
+
{"current_steps": 5105, "total_steps": 6713, "loss": 0.1425, "lr": 6.602451177175162e-06, "epoch": 5.324465310380804, "percentage": 76.05, "elapsed_time": "16:21:05", "remaining_time": "5:09:01"}
|
| 1045 |
+
{"current_steps": 5110, "total_steps": 6713, "loss": 0.1535, "lr": 6.563884633176505e-06, "epoch": 5.329681794470527, "percentage": 76.12, "elapsed_time": "16:23:59", "remaining_time": "5:08:40"}
|
| 1046 |
+
{"current_steps": 5115, "total_steps": 6713, "loss": 0.1559, "lr": 6.5254089330342366e-06, "epoch": 5.33489827856025, "percentage": 76.2, "elapsed_time": "16:27:03", "remaining_time": "5:08:22"}
|
| 1047 |
+
{"current_steps": 5120, "total_steps": 6713, "loss": 0.136, "lr": 6.487024336889107e-06, "epoch": 5.340114762649974, "percentage": 76.27, "elapsed_time": "16:30:07", "remaining_time": "5:08:03"}
|
| 1048 |
+
{"current_steps": 5125, "total_steps": 6713, "loss": 0.1468, "lr": 6.448731104265871e-06, "epoch": 5.345331246739698, "percentage": 76.34, "elapsed_time": "16:33:10", "remaining_time": "5:07:44"}
|
| 1049 |
+
{"current_steps": 5130, "total_steps": 6713, "loss": 0.1368, "lr": 6.410529494071596e-06, "epoch": 5.350547730829421, "percentage": 76.42, "elapsed_time": "16:36:15", "remaining_time": "5:07:25"}
|
| 1050 |
+
{"current_steps": 5135, "total_steps": 6713, "loss": 0.1434, "lr": 6.372419764593825e-06, "epoch": 5.3557642149191445, "percentage": 76.49, "elapsed_time": "16:39:15", "remaining_time": "5:07:04"}
|
| 1051 |
+
{"current_steps": 5140, "total_steps": 6713, "loss": 0.1415, "lr": 6.334402173498926e-06, "epoch": 5.360980699008868, "percentage": 76.57, "elapsed_time": "16:42:13", "remaining_time": "5:06:42"}
|
| 1052 |
+
{"current_steps": 5145, "total_steps": 6713, "loss": 0.1505, "lr": 6.296476977830272e-06, "epoch": 5.366197183098592, "percentage": 76.64, "elapsed_time": "16:45:14", "remaining_time": "5:06:21"}
|
| 1053 |
+
{"current_steps": 5150, "total_steps": 6713, "loss": 0.1409, "lr": 6.2586444340065625e-06, "epoch": 5.371413667188315, "percentage": 76.72, "elapsed_time": "16:48:18", "remaining_time": "5:06:01"}
|
| 1054 |
+
{"current_steps": 5155, "total_steps": 6713, "loss": 0.1431, "lr": 6.22090479782004e-06, "epoch": 5.376630151278039, "percentage": 76.79, "elapsed_time": "16:51:24", "remaining_time": "5:05:40"}
|
| 1055 |
+
{"current_steps": 5160, "total_steps": 6713, "loss": 0.1563, "lr": 6.18325832443478e-06, "epoch": 5.381846635367762, "percentage": 76.87, "elapsed_time": "16:54:28", "remaining_time": "5:05:19"}
|
| 1056 |
+
{"current_steps": 5165, "total_steps": 6713, "loss": 0.1563, "lr": 6.145705268384996e-06, "epoch": 5.387063119457486, "percentage": 76.94, "elapsed_time": "16:57:30", "remaining_time": "5:04:57"}
|
| 1057 |
+
{"current_steps": 5170, "total_steps": 6713, "loss": 0.1976, "lr": 6.108245883573258e-06, "epoch": 5.392279603547209, "percentage": 77.01, "elapsed_time": "17:00:13", "remaining_time": "5:04:29"}
|
| 1058 |
+
{"current_steps": 5175, "total_steps": 6713, "loss": 0.213, "lr": 6.070880423268839e-06, "epoch": 5.397496087636933, "percentage": 77.09, "elapsed_time": "17:02:09", "remaining_time": "5:03:47"}
|
| 1059 |
+
{"current_steps": 5180, "total_steps": 6713, "loss": 0.2086, "lr": 6.033609140105949e-06, "epoch": 5.402712571726656, "percentage": 77.16, "elapsed_time": "17:04:42", "remaining_time": "5:03:15"}
|
| 1060 |
+
{"current_steps": 5185, "total_steps": 6713, "loss": 0.2079, "lr": 5.996432286082061e-06, "epoch": 5.40792905581638, "percentage": 77.24, "elapsed_time": "17:07:06", "remaining_time": "5:02:41"}
|
| 1061 |
+
{"current_steps": 5190, "total_steps": 6713, "loss": 0.2135, "lr": 5.9593501125561885e-06, "epoch": 5.413145539906103, "percentage": 77.31, "elapsed_time": "17:09:27", "remaining_time": "5:02:05"}
|
| 1062 |
+
{"current_steps": 5195, "total_steps": 6713, "loss": 0.2188, "lr": 5.922362870247214e-06, "epoch": 5.418362023995827, "percentage": 77.39, "elapsed_time": "17:11:48", "remaining_time": "5:01:29"}
|
| 1063 |
+
{"current_steps": 5200, "total_steps": 6713, "loss": 0.2103, "lr": 5.885470809232143e-06, "epoch": 5.4235785080855505, "percentage": 77.46, "elapsed_time": "17:14:11", "remaining_time": "5:00:54"}
|