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:a8cb91d521e4740ef5177d961a136c071ba42241ce58a75015e93dd01e8f37a5
|
| 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 sha256:3c00fce57e768efb10e45ba22647e073aed17c837393c853305c3e4910cf5992
|
| 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:aef7128b07625c6c86e90622ae206357b89b626b9b73d97961892331fc4cdd72
|
| 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 sha256:197dd760771eb1f6202bc782dc3584bca2b89c3f5c60721025bdd50145499982
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1003,3 +1003,43 @@
|
|
| 1003 |
{"current_steps": 4990, "total_steps": 6188, "loss": 0.1455, "lr": 4.403144073722501e-06, "epoch": 5.646293152235427, "percentage": 80.64, "elapsed_time": "13:46:14", "remaining_time": "3:18:21"}
|
| 1004 |
{"current_steps": 4995, "total_steps": 6188, "loss": 0.1419, "lr": 4.367893544535757e-06, "epoch": 5.65195246179966, "percentage": 80.72, "elapsed_time": "13:49:18", "remaining_time": "3:18:04"}
|
| 1005 |
{"current_steps": 5000, "total_steps": 6188, "loss": 0.1333, "lr": 4.332767381597575e-06, "epoch": 5.657611771363894, "percentage": 80.8, "elapsed_time": "13:52:14", "remaining_time": "3:17:44"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1003 |
{"current_steps": 4990, "total_steps": 6188, "loss": 0.1455, "lr": 4.403144073722501e-06, "epoch": 5.646293152235427, "percentage": 80.64, "elapsed_time": "13:46:14", "remaining_time": "3:18:21"}
|
| 1004 |
{"current_steps": 4995, "total_steps": 6188, "loss": 0.1419, "lr": 4.367893544535757e-06, "epoch": 5.65195246179966, "percentage": 80.72, "elapsed_time": "13:49:18", "remaining_time": "3:18:04"}
|
| 1005 |
{"current_steps": 5000, "total_steps": 6188, "loss": 0.1333, "lr": 4.332767381597575e-06, "epoch": 5.657611771363894, "percentage": 80.8, "elapsed_time": "13:52:14", "remaining_time": "3:17:44"}
|
| 1006 |
+
{"current_steps": 5005, "total_steps": 6188, "loss": 0.1375, "lr": 4.297765864365453e-06, "epoch": 5.663271080928126, "percentage": 80.88, "elapsed_time": "13:56:13", "remaining_time": "3:17:39"}
|
| 1007 |
+
{"current_steps": 5010, "total_steps": 6188, "loss": 0.1448, "lr": 4.262889271305204e-06, "epoch": 5.66893039049236, "percentage": 80.96, "elapsed_time": "13:59:12", "remaining_time": "3:17:19"}
|
| 1008 |
+
{"current_steps": 5015, "total_steps": 6188, "loss": 0.1452, "lr": 4.228137879888774e-06, "epoch": 5.674589700056593, "percentage": 81.04, "elapsed_time": "14:02:02", "remaining_time": "3:16:57"}
|
| 1009 |
+
{"current_steps": 5020, "total_steps": 6188, "loss": 0.1296, "lr": 4.193511966592041e-06, "epoch": 5.680249009620827, "percentage": 81.12, "elapsed_time": "14:05:07", "remaining_time": "3:16:37"}
|
| 1010 |
+
{"current_steps": 5025, "total_steps": 6188, "loss": 0.1283, "lr": 4.1590118068925815e-06, "epoch": 5.685908319185059, "percentage": 81.21, "elapsed_time": "14:08:09", "remaining_time": "3:16:17"}
|
| 1011 |
+
{"current_steps": 5030, "total_steps": 6188, "loss": 0.1478, "lr": 4.124637675267511e-06, "epoch": 5.691567628749293, "percentage": 81.29, "elapsed_time": "14:11:13", "remaining_time": "3:15:58"}
|
| 1012 |
+
{"current_steps": 5035, "total_steps": 6188, "loss": 0.1636, "lr": 4.090389845191278e-06, "epoch": 5.697226938313526, "percentage": 81.37, "elapsed_time": "14:14:08", "remaining_time": "3:15:35"}
|
| 1013 |
+
{"current_steps": 5040, "total_steps": 6188, "loss": 0.1345, "lr": 4.056268589133516e-06, "epoch": 5.702886247877759, "percentage": 81.45, "elapsed_time": "14:17:05", "remaining_time": "3:15:13"}
|
| 1014 |
+
{"current_steps": 5045, "total_steps": 6188, "loss": 0.1426, "lr": 4.022274178556844e-06, "epoch": 5.708545557441992, "percentage": 81.53, "elapsed_time": "14:20:05", "remaining_time": "3:14:51"}
|
| 1015 |
+
{"current_steps": 5050, "total_steps": 6188, "loss": 0.156, "lr": 3.988406883914717e-06, "epoch": 5.7142048670062255, "percentage": 81.61, "elapsed_time": "14:22:55", "remaining_time": "3:14:27"}
|
| 1016 |
+
{"current_steps": 5055, "total_steps": 6188, "loss": 0.1716, "lr": 3.954666974649295e-06, "epoch": 5.719864176570458, "percentage": 81.69, "elapsed_time": "14:25:53", "remaining_time": "3:14:04"}
|
| 1017 |
+
{"current_steps": 5060, "total_steps": 6188, "loss": 0.1661, "lr": 3.921054719189272e-06, "epoch": 5.7255234861346915, "percentage": 81.77, "elapsed_time": "14:28:52", "remaining_time": "3:13:41"}
|
| 1018 |
+
{"current_steps": 5065, "total_steps": 6188, "loss": 0.1464, "lr": 3.887570384947745e-06, "epoch": 5.731182795698925, "percentage": 81.85, "elapsed_time": "14:31:58", "remaining_time": "3:13:20"}
|
| 1019 |
+
{"current_steps": 5070, "total_steps": 6188, "loss": 0.1466, "lr": 3.854214238320109e-06, "epoch": 5.7368421052631575, "percentage": 81.93, "elapsed_time": "14:35:02", "remaining_time": "3:12:57"}
|
| 1020 |
+
{"current_steps": 5075, "total_steps": 6188, "loss": 0.1483, "lr": 3.8209865446819105e-06, "epoch": 5.742501414827391, "percentage": 82.01, "elapsed_time": "14:38:04", "remaining_time": "3:12:34"}
|
| 1021 |
+
{"current_steps": 5080, "total_steps": 6188, "loss": 0.1549, "lr": 3.7878875683867476e-06, "epoch": 5.748160724391624, "percentage": 82.09, "elapsed_time": "14:40:56", "remaining_time": "3:12:08"}
|
| 1022 |
+
{"current_steps": 5085, "total_steps": 6188, "loss": 0.1454, "lr": 3.7549175727641606e-06, "epoch": 5.753820033955858, "percentage": 82.18, "elapsed_time": "14:44:03", "remaining_time": "3:11:45"}
|
| 1023 |
+
{"current_steps": 5090, "total_steps": 6188, "loss": 0.1539, "lr": 3.7220768201175615e-06, "epoch": 5.75947934352009, "percentage": 82.26, "elapsed_time": "14:47:11", "remaining_time": "3:11:22"}
|
| 1024 |
+
{"current_steps": 5095, "total_steps": 6188, "loss": 0.153, "lr": 3.689365571722112e-06, "epoch": 5.765138653084324, "percentage": 82.34, "elapsed_time": "14:50:15", "remaining_time": "3:10:58"}
|
| 1025 |
+
{"current_steps": 5100, "total_steps": 6188, "loss": 0.1385, "lr": 3.6567840878226577e-06, "epoch": 5.770797962648556, "percentage": 82.42, "elapsed_time": "14:53:02", "remaining_time": "3:10:30"}
|
| 1026 |
+
{"current_steps": 5105, "total_steps": 6188, "loss": 0.1302, "lr": 3.624332627631679e-06, "epoch": 5.77645727221279, "percentage": 82.5, "elapsed_time": "14:56:08", "remaining_time": "3:10:06"}
|
| 1027 |
+
{"current_steps": 5110, "total_steps": 6188, "loss": 0.1547, "lr": 3.5920114493271974e-06, "epoch": 5.782116581777023, "percentage": 82.58, "elapsed_time": "14:59:10", "remaining_time": "3:09:41"}
|
| 1028 |
+
{"current_steps": 5115, "total_steps": 6188, "loss": 0.1551, "lr": 3.5598208100507314e-06, "epoch": 5.787775891341257, "percentage": 82.66, "elapsed_time": "15:02:11", "remaining_time": "3:09:15"}
|
| 1029 |
+
{"current_steps": 5120, "total_steps": 6188, "loss": 0.1471, "lr": 3.5277609659052712e-06, "epoch": 5.793435200905489, "percentage": 82.74, "elapsed_time": "15:05:09", "remaining_time": "3:08:48"}
|
| 1030 |
+
{"current_steps": 5125, "total_steps": 6188, "loss": 0.1447, "lr": 3.4958321719532106e-06, "epoch": 5.799094510469723, "percentage": 82.82, "elapsed_time": "15:07:53", "remaining_time": "3:08:18"}
|
| 1031 |
+
{"current_steps": 5130, "total_steps": 6188, "loss": 0.1351, "lr": 3.4640346822143324e-06, "epoch": 5.804753820033956, "percentage": 82.9, "elapsed_time": "15:10:49", "remaining_time": "3:07:50"}
|
| 1032 |
+
{"current_steps": 5135, "total_steps": 6188, "loss": 0.1485, "lr": 3.4323687496637837e-06, "epoch": 5.810413129598189, "percentage": 82.98, "elapsed_time": "15:13:43", "remaining_time": "3:07:22"}
|
| 1033 |
+
{"current_steps": 5140, "total_steps": 6188, "loss": 0.1516, "lr": 3.4008346262300852e-06, "epoch": 5.816072439162422, "percentage": 83.06, "elapsed_time": "15:16:36", "remaining_time": "3:06:53"}
|
| 1034 |
+
{"current_steps": 5145, "total_steps": 6188, "loss": 0.1414, "lr": 3.3694325627930846e-06, "epoch": 5.8217317487266556, "percentage": 83.14, "elapsed_time": "15:19:29", "remaining_time": "3:06:24"}
|
| 1035 |
+
{"current_steps": 5150, "total_steps": 6188, "loss": 0.1519, "lr": 3.3381628091819907e-06, "epoch": 5.827391058290889, "percentage": 83.23, "elapsed_time": "15:22:22", "remaining_time": "3:05:54"}
|
| 1036 |
+
{"current_steps": 5155, "total_steps": 6188, "loss": 0.1435, "lr": 3.3070256141733913e-06, "epoch": 5.8330503678551215, "percentage": 83.31, "elapsed_time": "15:25:12", "remaining_time": "3:05:24"}
|
| 1037 |
+
{"current_steps": 5160, "total_steps": 6188, "loss": 0.1242, "lr": 3.2760212254892453e-06, "epoch": 5.838709677419355, "percentage": 83.39, "elapsed_time": "15:28:09", "remaining_time": "3:04:54"}
|
| 1038 |
+
{"current_steps": 5165, "total_steps": 6188, "loss": 0.1275, "lr": 3.245149889794932e-06, "epoch": 5.8443689869835875, "percentage": 83.47, "elapsed_time": "15:31:11", "remaining_time": "3:04:26"}
|
| 1039 |
+
{"current_steps": 5170, "total_steps": 6188, "loss": 0.1335, "lr": 3.2144118526972943e-06, "epoch": 5.850028296547821, "percentage": 83.55, "elapsed_time": "15:34:15", "remaining_time": "3:03:57"}
|
| 1040 |
+
{"current_steps": 5175, "total_steps": 6188, "loss": 0.143, "lr": 3.1838073587426676e-06, "epoch": 5.855687606112054, "percentage": 83.63, "elapsed_time": "15:37:14", "remaining_time": "3:03:27"}
|
| 1041 |
+
{"current_steps": 5180, "total_steps": 6188, "loss": 0.1638, "lr": 3.153336651414933e-06, "epoch": 5.861346915676288, "percentage": 83.71, "elapsed_time": "15:40:04", "remaining_time": "3:02:55"}
|
| 1042 |
+
{"current_steps": 5185, "total_steps": 6188, "loss": 0.1724, "lr": 3.1229999731336137e-06, "epoch": 5.86700622524052, "percentage": 83.79, "elapsed_time": "15:42:56", "remaining_time": "3:02:24"}
|
| 1043 |
+
{"current_steps": 5190, "total_steps": 6188, "loss": 0.1387, "lr": 3.0927975652518994e-06, "epoch": 5.872665534804754, "percentage": 83.87, "elapsed_time": "15:45:51", "remaining_time": "3:01:52"}
|
| 1044 |
+
{"current_steps": 5195, "total_steps": 6188, "loss": 0.1473, "lr": 3.062729668054756e-06, "epoch": 5.878324844368987, "percentage": 83.95, "elapsed_time": "15:48:53", "remaining_time": "3:01:22"}
|
| 1045 |
+
{"current_steps": 5200, "total_steps": 6188, "loss": 0.1493, "lr": 3.032796520757002e-06, "epoch": 5.88398415393322, "percentage": 84.03, "elapsed_time": "15:51:58", "remaining_time": "3:00:52"}
|