Training in progress, step 5600
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:d1fd52ed959d2013839cbd18781dffe15371ddf82fe4984d3703ebf9a2e87e80
|
| 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 sha256:8d3c3a46c0557067bd710ab5f911e2686a42f8f41acb13d6b62bcbf6804ba130
|
| 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 sha256:34fda414d7774340f529f348870f2e9a8c3570b9688d8252003ab0db28e5a56b
|
| 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:d8191def14782bf4f8f0dfce74f4970d7556e01288be581efbc26bb2e3f5023f
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1080,3 +1080,44 @@
|
|
| 1080 |
{"current_steps": 5400, "total_steps": 9128, "loss": 0.1786, "lr": 1.711516751807883e-05, "epoch": 4.141158419639432, "percentage": 59.16, "elapsed_time": "1 day, 9:58:37", "remaining_time": "23:27:24"}
|
| 1081 |
{"current_steps": 5405, "total_steps": 9128, "loss": 0.1811, "lr": 1.7077330581848336e-05, "epoch": 4.144994246260069, "percentage": 59.21, "elapsed_time": "1 day, 10:02:56", "remaining_time": "23:27:11"}
|
| 1082 |
{"current_steps": 5410, "total_steps": 9128, "loss": 0.1815, "lr": 1.7039504331347477e-05, "epoch": 4.148830072880706, "percentage": 59.27, "elapsed_time": "1 day, 10:05:50", "remaining_time": "23:25:59"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1080 |
{"current_steps": 5400, "total_steps": 9128, "loss": 0.1786, "lr": 1.711516751807883e-05, "epoch": 4.141158419639432, "percentage": 59.16, "elapsed_time": "1 day, 9:58:37", "remaining_time": "23:27:24"}
|
| 1081 |
{"current_steps": 5405, "total_steps": 9128, "loss": 0.1811, "lr": 1.7077330581848336e-05, "epoch": 4.144994246260069, "percentage": 59.21, "elapsed_time": "1 day, 10:02:56", "remaining_time": "23:27:11"}
|
| 1082 |
{"current_steps": 5410, "total_steps": 9128, "loss": 0.1815, "lr": 1.7039504331347477e-05, "epoch": 4.148830072880706, "percentage": 59.27, "elapsed_time": "1 day, 10:05:50", "remaining_time": "23:25:59"}
|
| 1083 |
+
{"current_steps": 5415, "total_steps": 9128, "loss": 0.1792, "lr": 1.700168890487484e-05, "epoch": 4.152665899501343, "percentage": 59.32, "elapsed_time": "1 day, 10:08:36", "remaining_time": "23:24:42"}
|
| 1084 |
+
{"current_steps": 5420, "total_steps": 9128, "loss": 0.1763, "lr": 1.6963884440689462e-05, "epoch": 4.156501726121979, "percentage": 59.38, "elapsed_time": "1 day, 10:11:28", "remaining_time": "23:23:29"}
|
| 1085 |
+
{"current_steps": 5425, "total_steps": 9128, "loss": 0.1463, "lr": 1.6926091077010287e-05, "epoch": 4.160337552742616, "percentage": 59.43, "elapsed_time": "1 day, 10:13:26", "remaining_time": "23:21:38"}
|
| 1086 |
+
{"current_steps": 5430, "total_steps": 9128, "loss": 0.1798, "lr": 1.6888308952015658e-05, "epoch": 4.164173379363253, "percentage": 59.49, "elapsed_time": "1 day, 10:16:23", "remaining_time": "23:20:27"}
|
| 1087 |
+
{"current_steps": 5435, "total_steps": 9128, "loss": 0.1732, "lr": 1.685053820384287e-05, "epoch": 4.168009205983889, "percentage": 59.54, "elapsed_time": "1 day, 10:19:09", "remaining_time": "23:19:10"}
|
| 1088 |
+
{"current_steps": 5440, "total_steps": 9128, "loss": 0.1762, "lr": 1.6812778970587572e-05, "epoch": 4.171845032604526, "percentage": 59.6, "elapsed_time": "1 day, 10:22:02", "remaining_time": "23:17:56"}
|
| 1089 |
+
{"current_steps": 5445, "total_steps": 9128, "loss": 0.173, "lr": 1.6775031390303352e-05, "epoch": 4.175680859225163, "percentage": 59.65, "elapsed_time": "1 day, 10:25:01", "remaining_time": "23:16:46"}
|
| 1090 |
+
{"current_steps": 5450, "total_steps": 9128, "loss": 0.1722, "lr": 1.6737295601001182e-05, "epoch": 4.1795166858458, "percentage": 59.71, "elapsed_time": "1 day, 10:27:59", "remaining_time": "23:15:36"}
|
| 1091 |
+
{"current_steps": 5455, "total_steps": 9128, "loss": 0.1804, "lr": 1.6699571740648905e-05, "epoch": 4.183352512466437, "percentage": 59.76, "elapsed_time": "1 day, 10:30:57", "remaining_time": "23:14:25"}
|
| 1092 |
+
{"current_steps": 5460, "total_steps": 9128, "loss": 0.1755, "lr": 1.6661859947170776e-05, "epoch": 4.187188339087073, "percentage": 59.82, "elapsed_time": "1 day, 10:33:30", "remaining_time": "23:12:58"}
|
| 1093 |
+
{"current_steps": 5465, "total_steps": 9128, "loss": 0.146, "lr": 1.6624160358446928e-05, "epoch": 4.19102416570771, "percentage": 59.87, "elapsed_time": "1 day, 10:35:44", "remaining_time": "23:11:17"}
|
| 1094 |
+
{"current_steps": 5470, "total_steps": 9128, "loss": 0.171, "lr": 1.658647311231285e-05, "epoch": 4.194859992328347, "percentage": 59.93, "elapsed_time": "1 day, 10:38:35", "remaining_time": "23:10:02"}
|
| 1095 |
+
{"current_steps": 5475, "total_steps": 9128, "loss": 0.1777, "lr": 1.6548798346558924e-05, "epoch": 4.198695818948983, "percentage": 59.98, "elapsed_time": "1 day, 10:41:27", "remaining_time": "23:08:46"}
|
| 1096 |
+
{"current_steps": 5480, "total_steps": 9128, "loss": 0.1718, "lr": 1.651113619892991e-05, "epoch": 4.2025316455696204, "percentage": 60.04, "elapsed_time": "1 day, 10:44:08", "remaining_time": "23:07:23"}
|
| 1097 |
+
{"current_steps": 5485, "total_steps": 9128, "loss": 0.1682, "lr": 1.647348680712441e-05, "epoch": 4.206367472190257, "percentage": 60.09, "elapsed_time": "1 day, 10:46:54", "remaining_time": "23:06:04"}
|
| 1098 |
+
{"current_steps": 5490, "total_steps": 9128, "loss": 0.174, "lr": 1.6435850308794395e-05, "epoch": 4.210203298810894, "percentage": 60.14, "elapsed_time": "1 day, 10:49:50", "remaining_time": "23:04:51"}
|
| 1099 |
+
{"current_steps": 5495, "total_steps": 9128, "loss": 0.1717, "lr": 1.639822684154472e-05, "epoch": 4.214039125431531, "percentage": 60.2, "elapsed_time": "1 day, 10:52:24", "remaining_time": "23:03:23"}
|
| 1100 |
+
{"current_steps": 5500, "total_steps": 9128, "loss": 0.1709, "lr": 1.636061654293256e-05, "epoch": 4.217874952052167, "percentage": 60.25, "elapsed_time": "1 day, 10:53:39", "remaining_time": "23:01:02"}
|
| 1101 |
+
{"current_steps": 5505, "total_steps": 9128, "loss": 0.1569, "lr": 1.6323019550466958e-05, "epoch": 4.221710778672804, "percentage": 60.31, "elapsed_time": "1 day, 10:54:54", "remaining_time": "22:58:42"}
|
| 1102 |
+
{"current_steps": 5510, "total_steps": 9128, "loss": 0.1565, "lr": 1.628543600160833e-05, "epoch": 4.225546605293441, "percentage": 60.36, "elapsed_time": "1 day, 10:56:08", "remaining_time": "22:56:22"}
|
| 1103 |
+
{"current_steps": 5515, "total_steps": 9128, "loss": 0.1494, "lr": 1.62478660337679e-05, "epoch": 4.229382431914077, "percentage": 60.42, "elapsed_time": "1 day, 10:57:24", "remaining_time": "22:54:03"}
|
| 1104 |
+
{"current_steps": 5520, "total_steps": 9128, "loss": 0.1516, "lr": 1.6210309784307275e-05, "epoch": 4.2332182585347145, "percentage": 60.47, "elapsed_time": "1 day, 10:58:40", "remaining_time": "22:51:44"}
|
| 1105 |
+
{"current_steps": 5525, "total_steps": 9128, "loss": 0.1581, "lr": 1.6172767390537874e-05, "epoch": 4.237054085155351, "percentage": 60.53, "elapsed_time": "1 day, 10:59:55", "remaining_time": "22:49:24"}
|
| 1106 |
+
{"current_steps": 5530, "total_steps": 9128, "loss": 0.1401, "lr": 1.613523898972048e-05, "epoch": 4.240889911775987, "percentage": 60.58, "elapsed_time": "1 day, 11:01:09", "remaining_time": "22:47:05"}
|
| 1107 |
+
{"current_steps": 5535, "total_steps": 9128, "loss": 0.1619, "lr": 1.6097724719064706e-05, "epoch": 4.244725738396625, "percentage": 60.64, "elapsed_time": "1 day, 11:02:23", "remaining_time": "22:44:45"}
|
| 1108 |
+
{"current_steps": 5540, "total_steps": 9128, "loss": 0.1435, "lr": 1.6060224715728507e-05, "epoch": 4.248561565017261, "percentage": 60.69, "elapsed_time": "1 day, 11:03:37", "remaining_time": "22:42:24"}
|
| 1109 |
+
{"current_steps": 5545, "total_steps": 9128, "loss": 0.1519, "lr": 1.602273911681766e-05, "epoch": 4.252397391637898, "percentage": 60.75, "elapsed_time": "1 day, 11:04:52", "remaining_time": "22:40:06"}
|
| 1110 |
+
{"current_steps": 5550, "total_steps": 9128, "loss": 0.1512, "lr": 1.5985268059385314e-05, "epoch": 4.256233218258535, "percentage": 60.8, "elapsed_time": "1 day, 11:06:11", "remaining_time": "22:37:49"}
|
| 1111 |
+
{"current_steps": 5555, "total_steps": 9128, "loss": 0.1463, "lr": 1.59478116804314e-05, "epoch": 4.260069044879171, "percentage": 60.86, "elapsed_time": "1 day, 11:07:28", "remaining_time": "22:35:32"}
|
| 1112 |
+
{"current_steps": 5560, "total_steps": 9128, "loss": 0.1381, "lr": 1.5910370116902223e-05, "epoch": 4.2639048714998085, "percentage": 60.91, "elapsed_time": "1 day, 11:08:43", "remaining_time": "22:33:13"}
|
| 1113 |
+
{"current_steps": 5565, "total_steps": 9128, "loss": 0.1411, "lr": 1.5872943505689914e-05, "epoch": 4.267740698120445, "percentage": 60.97, "elapsed_time": "1 day, 11:09:57", "remaining_time": "22:30:54"}
|
| 1114 |
+
{"current_steps": 5570, "total_steps": 9128, "loss": 0.1402, "lr": 1.583553198363191e-05, "epoch": 4.271576524741081, "percentage": 61.02, "elapsed_time": "1 day, 11:11:13", "remaining_time": "22:28:36"}
|
| 1115 |
+
{"current_steps": 5575, "total_steps": 9128, "loss": 0.1461, "lr": 1.5798135687510517e-05, "epoch": 4.275412351361719, "percentage": 61.08, "elapsed_time": "1 day, 11:12:28", "remaining_time": "22:26:18"}
|
| 1116 |
+
{"current_steps": 5580, "total_steps": 9128, "loss": 0.1528, "lr": 1.576075475405235e-05, "epoch": 4.279248177982355, "percentage": 61.13, "elapsed_time": "1 day, 11:13:48", "remaining_time": "22:24:02"}
|
| 1117 |
+
{"current_steps": 5585, "total_steps": 9128, "loss": 0.1519, "lr": 1.572338931992785e-05, "epoch": 4.283084004602992, "percentage": 61.19, "elapsed_time": "1 day, 11:15:04", "remaining_time": "22:21:45"}
|
| 1118 |
+
{"current_steps": 5590, "total_steps": 9128, "loss": 0.1445, "lr": 1.5686039521750817e-05, "epoch": 4.286919831223629, "percentage": 61.24, "elapsed_time": "1 day, 11:16:21", "remaining_time": "22:19:28"}
|
| 1119 |
+
{"current_steps": 5595, "total_steps": 9128, "loss": 0.1477, "lr": 1.5648705496077848e-05, "epoch": 4.290755657844265, "percentage": 61.29, "elapsed_time": "1 day, 11:17:39", "remaining_time": "22:17:12"}
|
| 1120 |
+
{"current_steps": 5600, "total_steps": 9128, "loss": 0.1479, "lr": 1.5611387379407906e-05, "epoch": 4.2945914844649025, "percentage": 61.35, "elapsed_time": "1 day, 11:19:00", "remaining_time": "22:14:58"}
|
| 1121 |
+
{"current_steps": 5605, "total_steps": 9128, "loss": 0.1454, "lr": 1.5574085308181777e-05, "epoch": 4.298427311085539, "percentage": 61.4, "elapsed_time": "1 day, 11:21:32", "remaining_time": "22:13:28"}
|
| 1122 |
+
{"current_steps": 5610, "total_steps": 9128, "loss": 0.136, "lr": 1.5536799418781563e-05, "epoch": 4.302263137706175, "percentage": 61.46, "elapsed_time": "1 day, 11:22:46", "remaining_time": "22:11:10"}
|
| 1123 |
+
{"current_steps": 5615, "total_steps": 9128, "loss": 0.1425, "lr": 1.5499529847530236e-05, "epoch": 4.306098964326813, "percentage": 61.51, "elapsed_time": "1 day, 11:24:00", "remaining_time": "22:08:52"}
|