Training in progress, step 5400
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 sha256:3b881435c9d9a6b4c747447c8b557c5676a251215b9b418f0bd6c9f5247d4f0c
|
| 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:a11dffc3d704a91298b3c978d546f8dc1aa54b11c9792f246d1ad2ddb3d62c08
|
| 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:ab8e147bc28636c023dcccfc47b836ad49e1702c32c1e66f943cd1edca800392
|
| 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 sha256:8828a9a372b9d64fcf28199ee149a37128e4b35fe783e9cdcfa1a9abdc2e3e55
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1038,3 +1038,43 @@
|
|
| 1038 |
{"current_steps": 5190, "total_steps": 6713, "loss": 0.1732, "lr": 5.9593501125561885e-06, "epoch": 5.413145539906103, "percentage": 77.31, "elapsed_time": "23:54:17", "remaining_time": "7:00:53"}
|
| 1039 |
{"current_steps": 5195, "total_steps": 6713, "loss": 0.1727, "lr": 5.922362870247214e-06, "epoch": 5.418362023995827, "percentage": 77.39, "elapsed_time": "23:56:56", "remaining_time": "6:59:52"}
|
| 1040 |
{"current_steps": 5200, "total_steps": 6713, "loss": 0.1743, "lr": 5.885470809232143e-06, "epoch": 5.4235785080855505, "percentage": 77.46, "elapsed_time": "23:59:21", "remaining_time": "6:58:47"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1038 |
{"current_steps": 5190, "total_steps": 6713, "loss": 0.1732, "lr": 5.9593501125561885e-06, "epoch": 5.413145539906103, "percentage": 77.31, "elapsed_time": "23:54:17", "remaining_time": "7:00:53"}
|
| 1039 |
{"current_steps": 5195, "total_steps": 6713, "loss": 0.1727, "lr": 5.922362870247214e-06, "epoch": 5.418362023995827, "percentage": 77.39, "elapsed_time": "23:56:56", "remaining_time": "6:59:52"}
|
| 1040 |
{"current_steps": 5200, "total_steps": 6713, "loss": 0.1743, "lr": 5.885470809232143e-06, "epoch": 5.4235785080855505, "percentage": 77.46, "elapsed_time": "23:59:21", "remaining_time": "6:58:47"}
|
| 1041 |
+
{"current_steps": 5205, "total_steps": 6713, "loss": 0.1735, "lr": 5.8486741789444804e-06, "epoch": 5.428794992175274, "percentage": 77.54, "elapsed_time": "1 day, 0:03:32", "remaining_time": "6:58:13"}
|
| 1042 |
+
{"current_steps": 5210, "total_steps": 6713, "loss": 0.1674, "lr": 5.8119732281724715e-06, "epoch": 5.434011476264997, "percentage": 77.61, "elapsed_time": "1 day, 0:06:20", "remaining_time": "6:57:14"}
|
| 1043 |
+
{"current_steps": 5215, "total_steps": 6713, "loss": 0.1699, "lr": 5.775368205057488e-06, "epoch": 5.439227960354721, "percentage": 77.69, "elapsed_time": "1 day, 0:09:04", "remaining_time": "6:56:14"}
|
| 1044 |
+
{"current_steps": 5220, "total_steps": 6713, "loss": 0.1756, "lr": 5.738859357092297e-06, "epoch": 5.444444444444445, "percentage": 77.76, "elapsed_time": "1 day, 0:11:32", "remaining_time": "6:55:09"}
|
| 1045 |
+
{"current_steps": 5225, "total_steps": 6713, "loss": 0.1867, "lr": 5.7024469311194095e-06, "epoch": 5.449660928534168, "percentage": 77.83, "elapsed_time": "1 day, 0:14:12", "remaining_time": "6:54:08"}
|
| 1046 |
+
{"current_steps": 5230, "total_steps": 6713, "loss": 0.1802, "lr": 5.66613117332943e-06, "epoch": 5.454877412623891, "percentage": 77.91, "elapsed_time": "1 day, 0:16:56", "remaining_time": "6:53:07"}
|
| 1047 |
+
{"current_steps": 5235, "total_steps": 6713, "loss": 0.1728, "lr": 5.629912329259355e-06, "epoch": 5.460093896713615, "percentage": 77.98, "elapsed_time": "1 day, 0:19:41", "remaining_time": "6:52:06"}
|
| 1048 |
+
{"current_steps": 5240, "total_steps": 6713, "loss": 0.1719, "lr": 5.593790643790935e-06, "epoch": 5.465310380803339, "percentage": 78.06, "elapsed_time": "1 day, 0:22:18", "remaining_time": "6:51:04"}
|
| 1049 |
+
{"current_steps": 5245, "total_steps": 6713, "loss": 0.1783, "lr": 5.557766361149013e-06, "epoch": 5.470526864893062, "percentage": 78.13, "elapsed_time": "1 day, 0:25:06", "remaining_time": "6:50:03"}
|
| 1050 |
+
{"current_steps": 5250, "total_steps": 6713, "loss": 0.1753, "lr": 5.521839724899887e-06, "epoch": 5.475743348982785, "percentage": 78.21, "elapsed_time": "1 day, 0:27:37", "remaining_time": "6:48:58"}
|
| 1051 |
+
{"current_steps": 5255, "total_steps": 6713, "loss": 0.1715, "lr": 5.48601097794963e-06, "epoch": 5.480959833072509, "percentage": 78.28, "elapsed_time": "1 day, 0:30:19", "remaining_time": "6:47:56"}
|
| 1052 |
+
{"current_steps": 5260, "total_steps": 6713, "loss": 0.1814, "lr": 5.450280362542495e-06, "epoch": 5.486176317162233, "percentage": 78.36, "elapsed_time": "1 day, 0:33:13", "remaining_time": "6:46:57"}
|
| 1053 |
+
{"current_steps": 5265, "total_steps": 6713, "loss": 0.176, "lr": 5.414648120259225e-06, "epoch": 5.491392801251957, "percentage": 78.43, "elapsed_time": "1 day, 0:35:55", "remaining_time": "6:45:54"}
|
| 1054 |
+
{"current_steps": 5270, "total_steps": 6713, "loss": 0.188, "lr": 5.379114492015467e-06, "epoch": 5.4966092853416795, "percentage": 78.5, "elapsed_time": "1 day, 0:38:45", "remaining_time": "6:44:54"}
|
| 1055 |
+
{"current_steps": 5275, "total_steps": 6713, "loss": 0.1737, "lr": 5.343679718060104e-06, "epoch": 5.501825769431403, "percentage": 78.58, "elapsed_time": "1 day, 0:41:35", "remaining_time": "6:43:53"}
|
| 1056 |
+
{"current_steps": 5280, "total_steps": 6713, "loss": 0.1793, "lr": 5.308344037973672e-06, "epoch": 5.507042253521127, "percentage": 78.65, "elapsed_time": "1 day, 0:44:22", "remaining_time": "6:42:51"}
|
| 1057 |
+
{"current_steps": 5285, "total_steps": 6713, "loss": 0.172, "lr": 5.2731076906666786e-06, "epoch": 5.51225873761085, "percentage": 78.73, "elapsed_time": "1 day, 0:47:04", "remaining_time": "6:41:48"}
|
| 1058 |
+
{"current_steps": 5290, "total_steps": 6713, "loss": 0.1723, "lr": 5.237970914378068e-06, "epoch": 5.517475221700574, "percentage": 78.8, "elapsed_time": "1 day, 0:49:56", "remaining_time": "6:40:47"}
|
| 1059 |
+
{"current_steps": 5295, "total_steps": 6713, "loss": 0.169, "lr": 5.202933946673532e-06, "epoch": 5.522691705790297, "percentage": 78.88, "elapsed_time": "1 day, 0:52:43", "remaining_time": "6:39:45"}
|
| 1060 |
+
{"current_steps": 5300, "total_steps": 6713, "loss": 0.1781, "lr": 5.1679970244439695e-06, "epoch": 5.527908189880021, "percentage": 78.95, "elapsed_time": "1 day, 0:55:32", "remaining_time": "6:38:43"}
|
| 1061 |
+
{"current_steps": 5305, "total_steps": 6713, "loss": 0.1619, "lr": 5.13316038390383e-06, "epoch": 5.533124673969745, "percentage": 79.03, "elapsed_time": "1 day, 0:58:24", "remaining_time": "6:37:41"}
|
| 1062 |
+
{"current_steps": 5310, "total_steps": 6713, "loss": 0.1795, "lr": 5.098424260589565e-06, "epoch": 5.538341158059468, "percentage": 79.1, "elapsed_time": "1 day, 1:01:07", "remaining_time": "6:36:37"}
|
| 1063 |
+
{"current_steps": 5315, "total_steps": 6713, "loss": 0.1747, "lr": 5.063788889357995e-06, "epoch": 5.5435576421491914, "percentage": 79.17, "elapsed_time": "1 day, 1:03:57", "remaining_time": "6:35:34"}
|
| 1064 |
+
{"current_steps": 5320, "total_steps": 6713, "loss": 0.1657, "lr": 5.029254504384733e-06, "epoch": 5.548774126238915, "percentage": 79.25, "elapsed_time": "1 day, 1:06:39", "remaining_time": "6:34:30"}
|
| 1065 |
+
{"current_steps": 5325, "total_steps": 6713, "loss": 0.1845, "lr": 4.9948213391626325e-06, "epoch": 5.553990610328638, "percentage": 79.32, "elapsed_time": "1 day, 1:09:09", "remaining_time": "6:33:22"}
|
| 1066 |
+
{"current_steps": 5330, "total_steps": 6713, "loss": 0.168, "lr": 4.960489626500153e-06, "epoch": 5.559207094418362, "percentage": 79.4, "elapsed_time": "1 day, 1:11:53", "remaining_time": "6:32:17"}
|
| 1067 |
+
{"current_steps": 5335, "total_steps": 6713, "loss": 0.1774, "lr": 4.926259598519851e-06, "epoch": 5.5644235785080856, "percentage": 79.47, "elapsed_time": "1 day, 1:14:24", "remaining_time": "6:31:09"}
|
| 1068 |
+
{"current_steps": 5340, "total_steps": 6713, "loss": 0.1689, "lr": 4.892131486656733e-06, "epoch": 5.569640062597809, "percentage": 79.55, "elapsed_time": "1 day, 1:17:16", "remaining_time": "6:30:07"}
|
| 1069 |
+
{"current_steps": 5345, "total_steps": 6713, "loss": 0.1695, "lr": 4.858105521656768e-06, "epoch": 5.574856546687533, "percentage": 79.62, "elapsed_time": "1 day, 1:20:12", "remaining_time": "6:29:04"}
|
| 1070 |
+
{"current_steps": 5350, "total_steps": 6713, "loss": 0.1658, "lr": 4.824181933575272e-06, "epoch": 5.580073030777256, "percentage": 79.7, "elapsed_time": "1 day, 1:22:51", "remaining_time": "6:27:58"}
|
| 1071 |
+
{"current_steps": 5355, "total_steps": 6713, "loss": 0.1714, "lr": 4.790360951775392e-06, "epoch": 5.58528951486698, "percentage": 79.77, "elapsed_time": "1 day, 1:25:39", "remaining_time": "6:26:53"}
|
| 1072 |
+
{"current_steps": 5360, "total_steps": 6713, "loss": 0.17, "lr": 4.756642804926517e-06, "epoch": 5.590505998956703, "percentage": 79.85, "elapsed_time": "1 day, 1:28:14", "remaining_time": "6:25:45"}
|
| 1073 |
+
{"current_steps": 5365, "total_steps": 6713, "loss": 0.1827, "lr": 4.7230277210027685e-06, "epoch": 5.595722483046426, "percentage": 79.92, "elapsed_time": "1 day, 1:30:55", "remaining_time": "6:24:39"}
|
| 1074 |
+
{"current_steps": 5370, "total_steps": 6713, "loss": 0.1668, "lr": 4.689515927281427e-06, "epoch": 5.60093896713615, "percentage": 79.99, "elapsed_time": "1 day, 1:33:51", "remaining_time": "6:23:36"}
|
| 1075 |
+
{"current_steps": 5375, "total_steps": 6713, "loss": 0.1741, "lr": 4.6561076503414235e-06, "epoch": 5.606155451225874, "percentage": 80.07, "elapsed_time": "1 day, 1:36:36", "remaining_time": "6:22:30"}
|
| 1076 |
+
{"current_steps": 5380, "total_steps": 6713, "loss": 0.1698, "lr": 4.622803116061789e-06, "epoch": 5.6113719353155975, "percentage": 80.14, "elapsed_time": "1 day, 1:39:18", "remaining_time": "6:21:23"}
|
| 1077 |
+
{"current_steps": 5385, "total_steps": 6713, "loss": 0.1733, "lr": 4.589602549620127e-06, "epoch": 5.616588419405321, "percentage": 80.22, "elapsed_time": "1 day, 1:41:57", "remaining_time": "6:20:15"}
|
| 1078 |
+
{"current_steps": 5390, "total_steps": 6713, "loss": 0.1809, "lr": 4.556506175491097e-06, "epoch": 5.621804903495044, "percentage": 80.29, "elapsed_time": "1 day, 1:44:33", "remaining_time": "6:19:07"}
|
| 1079 |
+
{"current_steps": 5395, "total_steps": 6713, "loss": 0.1677, "lr": 4.523514217444918e-06, "epoch": 5.627021387584768, "percentage": 80.37, "elapsed_time": "1 day, 1:47:19", "remaining_time": "6:18:00"}
|
| 1080 |
+
{"current_steps": 5400, "total_steps": 6713, "loss": 0.1753, "lr": 4.490626898545805e-06, "epoch": 5.632237871674492, "percentage": 80.44, "elapsed_time": "1 day, 1:49:57", "remaining_time": "6:16:52"}
|