Training in progress, epoch 2
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 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9cf155266efa24de528a1c7d55408c9af1083b012def8ce3aa81c3ef89aa61b
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:182a5aeceab2c1c700e4d2239aab0fcefc5cd0f47e6012fe56680c4e9d6d3c72
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bd60edf8d1c486198444ee6a627de82b100736942d0225b9d400a654ce63088
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ea4095ca77eaf13602eef2d60719a6b3ce8a75341a0d10912874face7642061
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -253,3 +253,250 @@
|
|
| 253 |
{"current_steps": 253, "total_steps": 1235, "loss": 0.4595, "lr": 3.868407827802192e-05, "epoch": 1.0242914979757085, "percentage": 20.49, "elapsed_time": "1:25:28", "remaining_time": "5:31:46"}
|
| 254 |
{"current_steps": 254, "total_steps": 1235, "loss": 0.451, "lr": 3.8663828447103804e-05, "epoch": 1.0283400809716599, "percentage": 20.57, "elapsed_time": "1:25:49", "remaining_time": "5:31:28"}
|
| 255 |
{"current_steps": 255, "total_steps": 1235, "loss": 0.4551, "lr": 3.8643429380710765e-05, "epoch": 1.0323886639676114, "percentage": 20.65, "elapsed_time": "1:26:08", "remaining_time": "5:31:02"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 253 |
{"current_steps": 253, "total_steps": 1235, "loss": 0.4595, "lr": 3.868407827802192e-05, "epoch": 1.0242914979757085, "percentage": 20.49, "elapsed_time": "1:25:28", "remaining_time": "5:31:46"}
|
| 254 |
{"current_steps": 254, "total_steps": 1235, "loss": 0.451, "lr": 3.8663828447103804e-05, "epoch": 1.0283400809716599, "percentage": 20.57, "elapsed_time": "1:25:49", "remaining_time": "5:31:28"}
|
| 255 |
{"current_steps": 255, "total_steps": 1235, "loss": 0.4551, "lr": 3.8643429380710765e-05, "epoch": 1.0323886639676114, "percentage": 20.65, "elapsed_time": "1:26:08", "remaining_time": "5:31:02"}
|
| 256 |
+
{"current_steps": 256, "total_steps": 1235, "loss": 0.454, "lr": 3.862288124195319e-05, "epoch": 1.0364372469635628, "percentage": 20.73, "elapsed_time": "1:26:26", "remaining_time": "5:30:34"}
|
| 257 |
+
{"current_steps": 257, "total_steps": 1235, "loss": 0.4641, "lr": 3.8602184195133464e-05, "epoch": 1.040485829959514, "percentage": 20.81, "elapsed_time": "1:26:47", "remaining_time": "5:30:16"}
|
| 258 |
+
{"current_steps": 258, "total_steps": 1235, "loss": 0.447, "lr": 3.8581338405744604e-05, "epoch": 1.0445344129554657, "percentage": 20.89, "elapsed_time": "1:27:09", "remaining_time": "5:30:01"}
|
| 259 |
+
{"current_steps": 259, "total_steps": 1235, "loss": 0.4702, "lr": 3.8560344040468996e-05, "epoch": 1.048582995951417, "percentage": 20.97, "elapsed_time": "1:27:26", "remaining_time": "5:29:29"}
|
| 260 |
+
{"current_steps": 260, "total_steps": 1235, "loss": 0.4568, "lr": 3.853920126717703e-05, "epoch": 1.0526315789473684, "percentage": 21.05, "elapsed_time": "1:27:49", "remaining_time": "5:29:19"}
|
| 261 |
+
{"current_steps": 261, "total_steps": 1235, "loss": 0.4765, "lr": 3.851791025492574e-05, "epoch": 1.05668016194332, "percentage": 21.13, "elapsed_time": "1:28:10", "remaining_time": "5:29:01"}
|
| 262 |
+
{"current_steps": 262, "total_steps": 1235, "loss": 0.4562, "lr": 3.8496471173957515e-05, "epoch": 1.0607287449392713, "percentage": 21.21, "elapsed_time": "1:28:28", "remaining_time": "5:28:33"}
|
| 263 |
+
{"current_steps": 263, "total_steps": 1235, "loss": 0.4696, "lr": 3.847488419569866e-05, "epoch": 1.0647773279352226, "percentage": 21.3, "elapsed_time": "1:28:46", "remaining_time": "5:28:05"}
|
| 264 |
+
{"current_steps": 264, "total_steps": 1235, "loss": 0.455, "lr": 3.8453149492758077e-05, "epoch": 1.0688259109311742, "percentage": 21.38, "elapsed_time": "1:29:07", "remaining_time": "5:27:46"}
|
| 265 |
+
{"current_steps": 265, "total_steps": 1235, "loss": 0.4589, "lr": 3.8431267238925886e-05, "epoch": 1.0728744939271255, "percentage": 21.46, "elapsed_time": "1:29:26", "remaining_time": "5:27:25"}
|
| 266 |
+
{"current_steps": 266, "total_steps": 1235, "loss": 0.4648, "lr": 3.840923760917199e-05, "epoch": 1.0769230769230769, "percentage": 21.54, "elapsed_time": "1:29:47", "remaining_time": "5:27:07"}
|
| 267 |
+
{"current_steps": 267, "total_steps": 1235, "loss": 0.469, "lr": 3.838706077964473e-05, "epoch": 1.0809716599190284, "percentage": 21.62, "elapsed_time": "1:30:09", "remaining_time": "5:26:50"}
|
| 268 |
+
{"current_steps": 268, "total_steps": 1235, "loss": 0.4506, "lr": 3.836473692766944e-05, "epoch": 1.0850202429149798, "percentage": 21.7, "elapsed_time": "1:30:29", "remaining_time": "5:26:30"}
|
| 269 |
+
{"current_steps": 269, "total_steps": 1235, "loss": 0.4502, "lr": 3.834226623174705e-05, "epoch": 1.0890688259109311, "percentage": 21.78, "elapsed_time": "1:30:51", "remaining_time": "5:26:15"}
|
| 270 |
+
{"current_steps": 270, "total_steps": 1235, "loss": 0.4527, "lr": 3.831964887155264e-05, "epoch": 1.0931174089068827, "percentage": 21.86, "elapsed_time": "1:31:09", "remaining_time": "5:25:47"}
|
| 271 |
+
{"current_steps": 271, "total_steps": 1235, "loss": 0.4501, "lr": 3.829688502793403e-05, "epoch": 1.097165991902834, "percentage": 21.94, "elapsed_time": "1:31:29", "remaining_time": "5:25:25"}
|
| 272 |
+
{"current_steps": 272, "total_steps": 1235, "loss": 0.4511, "lr": 3.827397488291029e-05, "epoch": 1.1012145748987854, "percentage": 22.02, "elapsed_time": "1:31:45", "remaining_time": "5:24:53"}
|
| 273 |
+
{"current_steps": 273, "total_steps": 1235, "loss": 0.4577, "lr": 3.8250918619670343e-05, "epoch": 1.1052631578947367, "percentage": 22.11, "elapsed_time": "1:32:02", "remaining_time": "5:24:21"}
|
| 274 |
+
{"current_steps": 274, "total_steps": 1235, "loss": 0.4561, "lr": 3.822771642257145e-05, "epoch": 1.1093117408906883, "percentage": 22.19, "elapsed_time": "1:32:23", "remaining_time": "5:24:01"}
|
| 275 |
+
{"current_steps": 275, "total_steps": 1235, "loss": 0.4419, "lr": 3.820436847713776e-05, "epoch": 1.1133603238866396, "percentage": 22.27, "elapsed_time": "1:32:41", "remaining_time": "5:23:33"}
|
| 276 |
+
{"current_steps": 276, "total_steps": 1235, "loss": 0.4537, "lr": 3.8180874970058826e-05, "epoch": 1.117408906882591, "percentage": 22.35, "elapsed_time": "1:33:02", "remaining_time": "5:23:17"}
|
| 277 |
+
{"current_steps": 277, "total_steps": 1235, "loss": 0.4477, "lr": 3.8157236089188103e-05, "epoch": 1.1214574898785425, "percentage": 22.43, "elapsed_time": "1:33:25", "remaining_time": "5:23:07"}
|
| 278 |
+
{"current_steps": 278, "total_steps": 1235, "loss": 0.4531, "lr": 3.813345202354145e-05, "epoch": 1.125506072874494, "percentage": 22.51, "elapsed_time": "1:33:46", "remaining_time": "5:22:48"}
|
| 279 |
+
{"current_steps": 279, "total_steps": 1235, "loss": 0.4626, "lr": 3.810952296329563e-05, "epoch": 1.1295546558704452, "percentage": 22.59, "elapsed_time": "1:34:06", "remaining_time": "5:22:26"}
|
| 280 |
+
{"current_steps": 280, "total_steps": 1235, "loss": 0.4421, "lr": 3.808544909978676e-05, "epoch": 1.1336032388663968, "percentage": 22.67, "elapsed_time": "1:34:26", "remaining_time": "5:22:05"}
|
| 281 |
+
{"current_steps": 281, "total_steps": 1235, "loss": 0.4465, "lr": 3.806123062550882e-05, "epoch": 1.1376518218623481, "percentage": 22.75, "elapsed_time": "1:34:46", "remaining_time": "5:21:44"}
|
| 282 |
+
{"current_steps": 282, "total_steps": 1235, "loss": 0.4563, "lr": 3.803686773411208e-05, "epoch": 1.1417004048582995, "percentage": 22.83, "elapsed_time": "1:35:08", "remaining_time": "5:21:29"}
|
| 283 |
+
{"current_steps": 283, "total_steps": 1235, "loss": 0.453, "lr": 3.801236062040158e-05, "epoch": 1.145748987854251, "percentage": 22.91, "elapsed_time": "1:35:25", "remaining_time": "5:20:59"}
|
| 284 |
+
{"current_steps": 284, "total_steps": 1235, "loss": 0.4627, "lr": 3.798770948033553e-05, "epoch": 1.1497975708502024, "percentage": 23.0, "elapsed_time": "1:35:42", "remaining_time": "5:20:30"}
|
| 285 |
+
{"current_steps": 285, "total_steps": 1235, "loss": 0.4603, "lr": 3.796291451102381e-05, "epoch": 1.1538461538461537, "percentage": 23.08, "elapsed_time": "1:36:01", "remaining_time": "5:20:05"}
|
| 286 |
+
{"current_steps": 286, "total_steps": 1235, "loss": 0.4478, "lr": 3.793797591072631e-05, "epoch": 1.1578947368421053, "percentage": 23.16, "elapsed_time": "1:36:19", "remaining_time": "5:19:38"}
|
| 287 |
+
{"current_steps": 287, "total_steps": 1235, "loss": 0.4568, "lr": 3.791289387885144e-05, "epoch": 1.1619433198380567, "percentage": 23.24, "elapsed_time": "1:36:40", "remaining_time": "5:19:18"}
|
| 288 |
+
{"current_steps": 288, "total_steps": 1235, "loss": 0.4646, "lr": 3.788766861595443e-05, "epoch": 1.165991902834008, "percentage": 23.32, "elapsed_time": "1:36:59", "remaining_time": "5:18:55"}
|
| 289 |
+
{"current_steps": 289, "total_steps": 1235, "loss": 0.4724, "lr": 3.7862300323735835e-05, "epoch": 1.1700404858299596, "percentage": 23.4, "elapsed_time": "1:37:21", "remaining_time": "5:18:41"}
|
| 290 |
+
{"current_steps": 290, "total_steps": 1235, "loss": 0.4571, "lr": 3.783678920503983e-05, "epoch": 1.174089068825911, "percentage": 23.48, "elapsed_time": "1:37:40", "remaining_time": "5:18:18"}
|
| 291 |
+
{"current_steps": 291, "total_steps": 1235, "loss": 0.4401, "lr": 3.781113546385265e-05, "epoch": 1.1781376518218623, "percentage": 23.56, "elapsed_time": "1:37:59", "remaining_time": "5:17:54"}
|
| 292 |
+
{"current_steps": 292, "total_steps": 1235, "loss": 0.4658, "lr": 3.7785339305300916e-05, "epoch": 1.1821862348178138, "percentage": 23.64, "elapsed_time": "1:38:18", "remaining_time": "5:17:30"}
|
| 293 |
+
{"current_steps": 293, "total_steps": 1235, "loss": 0.4765, "lr": 3.7759400935650025e-05, "epoch": 1.1862348178137652, "percentage": 23.72, "elapsed_time": "1:38:38", "remaining_time": "5:17:09"}
|
| 294 |
+
{"current_steps": 294, "total_steps": 1235, "loss": 0.4564, "lr": 3.77333205623025e-05, "epoch": 1.1902834008097165, "percentage": 23.81, "elapsed_time": "1:38:57", "remaining_time": "5:16:43"}
|
| 295 |
+
{"current_steps": 295, "total_steps": 1235, "loss": 0.4475, "lr": 3.7707098393796295e-05, "epoch": 1.194331983805668, "percentage": 23.89, "elapsed_time": "1:39:20", "remaining_time": "5:16:31"}
|
| 296 |
+
{"current_steps": 296, "total_steps": 1235, "loss": 0.4619, "lr": 3.7680734639803185e-05, "epoch": 1.1983805668016194, "percentage": 23.97, "elapsed_time": "1:39:39", "remaining_time": "5:16:10"}
|
| 297 |
+
{"current_steps": 297, "total_steps": 1235, "loss": 0.4653, "lr": 3.765422951112704e-05, "epoch": 1.2024291497975708, "percentage": 24.05, "elapsed_time": "1:40:00", "remaining_time": "5:15:50"}
|
| 298 |
+
{"current_steps": 298, "total_steps": 1235, "loss": 0.4504, "lr": 3.762758321970216e-05, "epoch": 1.2064777327935223, "percentage": 24.13, "elapsed_time": "1:40:21", "remaining_time": "5:15:33"}
|
| 299 |
+
{"current_steps": 299, "total_steps": 1235, "loss": 0.4628, "lr": 3.7600795978591584e-05, "epoch": 1.2105263157894737, "percentage": 24.21, "elapsed_time": "1:40:42", "remaining_time": "5:15:15"}
|
| 300 |
+
{"current_steps": 300, "total_steps": 1235, "loss": 0.4727, "lr": 3.757386800198538e-05, "epoch": 1.214574898785425, "percentage": 24.29, "elapsed_time": "1:41:02", "remaining_time": "5:14:53"}
|
| 301 |
+
{"current_steps": 301, "total_steps": 1235, "loss": 0.4557, "lr": 3.7546799505198925e-05, "epoch": 1.2186234817813766, "percentage": 24.37, "elapsed_time": "1:41:20", "remaining_time": "5:14:27"}
|
| 302 |
+
{"current_steps": 302, "total_steps": 1235, "loss": 0.456, "lr": 3.7519590704671197e-05, "epoch": 1.222672064777328, "percentage": 24.45, "elapsed_time": "1:41:37", "remaining_time": "5:13:56"}
|
| 303 |
+
{"current_steps": 303, "total_steps": 1235, "loss": 0.4523, "lr": 3.749224181796305e-05, "epoch": 1.2267206477732793, "percentage": 24.53, "elapsed_time": "1:41:58", "remaining_time": "5:13:40"}
|
| 304 |
+
{"current_steps": 304, "total_steps": 1235, "loss": 0.466, "lr": 3.746475306375545e-05, "epoch": 1.2307692307692308, "percentage": 24.62, "elapsed_time": "1:42:15", "remaining_time": "5:13:10"}
|
| 305 |
+
{"current_steps": 305, "total_steps": 1235, "loss": 0.4609, "lr": 3.743712466184774e-05, "epoch": 1.2348178137651822, "percentage": 24.7, "elapsed_time": "1:42:37", "remaining_time": "5:12:56"}
|
| 306 |
+
{"current_steps": 306, "total_steps": 1235, "loss": 0.4478, "lr": 3.7409356833155885e-05, "epoch": 1.2388663967611335, "percentage": 24.78, "elapsed_time": "1:42:57", "remaining_time": "5:12:33"}
|
| 307 |
+
{"current_steps": 307, "total_steps": 1235, "loss": 0.4508, "lr": 3.73814497997107e-05, "epoch": 1.242914979757085, "percentage": 24.86, "elapsed_time": "1:43:15", "remaining_time": "5:12:09"}
|
| 308 |
+
{"current_steps": 308, "total_steps": 1235, "loss": 0.4609, "lr": 3.7353403784656095e-05, "epoch": 1.2469635627530364, "percentage": 24.94, "elapsed_time": "1:43:34", "remaining_time": "5:11:44"}
|
| 309 |
+
{"current_steps": 309, "total_steps": 1235, "loss": 0.4482, "lr": 3.732521901224724e-05, "epoch": 1.2510121457489878, "percentage": 25.02, "elapsed_time": "1:43:54", "remaining_time": "5:11:24"}
|
| 310 |
+
{"current_steps": 310, "total_steps": 1235, "loss": 0.4528, "lr": 3.7296895707848844e-05, "epoch": 1.2550607287449393, "percentage": 25.1, "elapsed_time": "1:44:13", "remaining_time": "5:10:59"}
|
| 311 |
+
{"current_steps": 311, "total_steps": 1235, "loss": 0.4518, "lr": 3.7268434097933275e-05, "epoch": 1.2591093117408907, "percentage": 25.18, "elapsed_time": "1:44:34", "remaining_time": "5:10:41"}
|
| 312 |
+
{"current_steps": 312, "total_steps": 1235, "loss": 0.4401, "lr": 3.723983441007882e-05, "epoch": 1.263157894736842, "percentage": 25.26, "elapsed_time": "1:44:55", "remaining_time": "5:10:25"}
|
| 313 |
+
{"current_steps": 313, "total_steps": 1235, "loss": 0.4655, "lr": 3.721109687296781e-05, "epoch": 1.2672064777327936, "percentage": 25.34, "elapsed_time": "1:45:14", "remaining_time": "5:09:59"}
|
| 314 |
+
{"current_steps": 314, "total_steps": 1235, "loss": 0.4692, "lr": 3.718222171638484e-05, "epoch": 1.271255060728745, "percentage": 25.43, "elapsed_time": "1:45:34", "remaining_time": "5:09:40"}
|
| 315 |
+
{"current_steps": 315, "total_steps": 1235, "loss": 0.4788, "lr": 3.715320917121488e-05, "epoch": 1.2753036437246963, "percentage": 25.51, "elapsed_time": "1:45:57", "remaining_time": "5:09:26"}
|
| 316 |
+
{"current_steps": 316, "total_steps": 1235, "loss": 0.4628, "lr": 3.712405946944149e-05, "epoch": 1.2793522267206479, "percentage": 25.59, "elapsed_time": "1:46:17", "remaining_time": "5:09:06"}
|
| 317 |
+
{"current_steps": 317, "total_steps": 1235, "loss": 0.4677, "lr": 3.709477284414488e-05, "epoch": 1.2834008097165992, "percentage": 25.67, "elapsed_time": "1:46:37", "remaining_time": "5:08:46"}
|
| 318 |
+
{"current_steps": 318, "total_steps": 1235, "loss": 0.4456, "lr": 3.7065349529500136e-05, "epoch": 1.2874493927125505, "percentage": 25.75, "elapsed_time": "1:46:57", "remaining_time": "5:08:26"}
|
| 319 |
+
{"current_steps": 319, "total_steps": 1235, "loss": 0.4411, "lr": 3.7035789760775305e-05, "epoch": 1.291497975708502, "percentage": 25.83, "elapsed_time": "1:47:19", "remaining_time": "5:08:10"}
|
| 320 |
+
{"current_steps": 320, "total_steps": 1235, "loss": 0.4616, "lr": 3.70060937743295e-05, "epoch": 1.2955465587044535, "percentage": 25.91, "elapsed_time": "1:47:40", "remaining_time": "5:07:52"}
|
| 321 |
+
{"current_steps": 321, "total_steps": 1235, "loss": 0.4574, "lr": 3.6976261807611045e-05, "epoch": 1.2995951417004048, "percentage": 25.99, "elapsed_time": "1:48:02", "remaining_time": "5:07:37"}
|
| 322 |
+
{"current_steps": 322, "total_steps": 1235, "loss": 0.4426, "lr": 3.694629409915555e-05, "epoch": 1.3036437246963564, "percentage": 26.07, "elapsed_time": "1:48:23", "remaining_time": "5:07:20"}
|
| 323 |
+
{"current_steps": 323, "total_steps": 1235, "loss": 0.456, "lr": 3.691619088858401e-05, "epoch": 1.3076923076923077, "percentage": 26.15, "elapsed_time": "1:48:43", "remaining_time": "5:06:59"}
|
| 324 |
+
{"current_steps": 324, "total_steps": 1235, "loss": 0.4644, "lr": 3.68859524166009e-05, "epoch": 1.311740890688259, "percentage": 26.23, "elapsed_time": "1:49:01", "remaining_time": "5:06:31"}
|
| 325 |
+
{"current_steps": 325, "total_steps": 1235, "loss": 0.4682, "lr": 3.6855578924992226e-05, "epoch": 1.3157894736842106, "percentage": 26.32, "elapsed_time": "1:49:22", "remaining_time": "5:06:15"}
|
| 326 |
+
{"current_steps": 326, "total_steps": 1235, "loss": 0.4555, "lr": 3.6825070656623626e-05, "epoch": 1.319838056680162, "percentage": 26.4, "elapsed_time": "1:49:43", "remaining_time": "5:05:56"}
|
| 327 |
+
{"current_steps": 327, "total_steps": 1235, "loss": 0.4531, "lr": 3.67944278554384e-05, "epoch": 1.3238866396761133, "percentage": 26.48, "elapsed_time": "1:50:01", "remaining_time": "5:05:31"}
|
| 328 |
+
{"current_steps": 328, "total_steps": 1235, "loss": 0.4487, "lr": 3.676365076645557e-05, "epoch": 1.3279352226720649, "percentage": 26.56, "elapsed_time": "1:50:23", "remaining_time": "5:05:15"}
|
| 329 |
+
{"current_steps": 329, "total_steps": 1235, "loss": 0.4554, "lr": 3.673273963576791e-05, "epoch": 1.3319838056680162, "percentage": 26.64, "elapsed_time": "1:50:44", "remaining_time": "5:04:57"}
|
| 330 |
+
{"current_steps": 330, "total_steps": 1235, "loss": 0.4567, "lr": 3.670169471054001e-05, "epoch": 1.3360323886639676, "percentage": 26.72, "elapsed_time": "1:51:01", "remaining_time": "5:04:29"}
|
| 331 |
+
{"current_steps": 331, "total_steps": 1235, "loss": 0.4506, "lr": 3.6670516239006254e-05, "epoch": 1.3400809716599191, "percentage": 26.8, "elapsed_time": "1:51:21", "remaining_time": "5:04:09"}
|
| 332 |
+
{"current_steps": 332, "total_steps": 1235, "loss": 0.4549, "lr": 3.663920447046888e-05, "epoch": 1.3441295546558705, "percentage": 26.88, "elapsed_time": "1:51:42", "remaining_time": "5:03:49"}
|
| 333 |
+
{"current_steps": 333, "total_steps": 1235, "loss": 0.456, "lr": 3.6607759655295954e-05, "epoch": 1.3481781376518218, "percentage": 26.96, "elapsed_time": "1:52:03", "remaining_time": "5:03:33"}
|
| 334 |
+
{"current_steps": 334, "total_steps": 1235, "loss": 0.4494, "lr": 3.657618204491937e-05, "epoch": 1.3522267206477734, "percentage": 27.04, "elapsed_time": "1:52:25", "remaining_time": "5:03:17"}
|
| 335 |
+
{"current_steps": 335, "total_steps": 1235, "loss": 0.4499, "lr": 3.6544471891832875e-05, "epoch": 1.3562753036437247, "percentage": 27.13, "elapsed_time": "1:52:42", "remaining_time": "5:02:47"}
|
| 336 |
+
{"current_steps": 336, "total_steps": 1235, "loss": 0.4586, "lr": 3.6512629449589983e-05, "epoch": 1.360323886639676, "percentage": 27.21, "elapsed_time": "1:53:04", "remaining_time": "5:02:31"}
|
| 337 |
+
{"current_steps": 337, "total_steps": 1235, "loss": 0.4506, "lr": 3.6480654972802045e-05, "epoch": 1.3643724696356276, "percentage": 27.29, "elapsed_time": "1:53:24", "remaining_time": "5:02:11"}
|
| 338 |
+
{"current_steps": 338, "total_steps": 1235, "loss": 0.4634, "lr": 3.644854871713611e-05, "epoch": 1.368421052631579, "percentage": 27.37, "elapsed_time": "1:53:44", "remaining_time": "5:01:50"}
|
| 339 |
+
{"current_steps": 339, "total_steps": 1235, "loss": 0.4493, "lr": 3.6416310939312924e-05, "epoch": 1.3724696356275303, "percentage": 27.45, "elapsed_time": "1:54:04", "remaining_time": "5:01:30"}
|
| 340 |
+
{"current_steps": 340, "total_steps": 1235, "loss": 0.4524, "lr": 3.638394189710493e-05, "epoch": 1.376518218623482, "percentage": 27.53, "elapsed_time": "1:54:21", "remaining_time": "5:01:02"}
|
| 341 |
+
{"current_steps": 341, "total_steps": 1235, "loss": 0.4451, "lr": 3.635144184933412e-05, "epoch": 1.3805668016194332, "percentage": 27.61, "elapsed_time": "1:54:41", "remaining_time": "5:00:41"}
|
| 342 |
+
{"current_steps": 342, "total_steps": 1235, "loss": 0.476, "lr": 3.6318811055869994e-05, "epoch": 1.3846153846153846, "percentage": 27.69, "elapsed_time": "1:55:00", "remaining_time": "5:00:17"}
|
| 343 |
+
{"current_steps": 343, "total_steps": 1235, "loss": 0.4532, "lr": 3.628604977762752e-05, "epoch": 1.3886639676113361, "percentage": 27.77, "elapsed_time": "1:55:19", "remaining_time": "4:59:53"}
|
| 344 |
+
{"current_steps": 344, "total_steps": 1235, "loss": 0.4586, "lr": 3.6253158276565004e-05, "epoch": 1.3927125506072875, "percentage": 27.85, "elapsed_time": "1:55:40", "remaining_time": "4:59:35"}
|
| 345 |
+
{"current_steps": 345, "total_steps": 1235, "loss": 0.4591, "lr": 3.6220136815682016e-05, "epoch": 1.3967611336032388, "percentage": 27.94, "elapsed_time": "1:56:00", "remaining_time": "4:59:15"}
|
| 346 |
+
{"current_steps": 346, "total_steps": 1235, "loss": 0.4375, "lr": 3.618698565901727e-05, "epoch": 1.4008097165991904, "percentage": 28.02, "elapsed_time": "1:56:21", "remaining_time": "4:58:58"}
|
| 347 |
+
{"current_steps": 347, "total_steps": 1235, "loss": 0.4753, "lr": 3.615370507164654e-05, "epoch": 1.4048582995951417, "percentage": 28.1, "elapsed_time": "1:56:41", "remaining_time": "4:58:36"}
|
| 348 |
+
{"current_steps": 348, "total_steps": 1235, "loss": 0.4627, "lr": 3.61202953196805e-05, "epoch": 1.408906882591093, "percentage": 28.18, "elapsed_time": "1:57:02", "remaining_time": "4:58:18"}
|
| 349 |
+
{"current_steps": 349, "total_steps": 1235, "loss": 0.4445, "lr": 3.6086756670262654e-05, "epoch": 1.4129554655870447, "percentage": 28.26, "elapsed_time": "1:57:21", "remaining_time": "4:57:56"}
|
| 350 |
+
{"current_steps": 350, "total_steps": 1235, "loss": 0.4529, "lr": 3.6053089391567135e-05, "epoch": 1.417004048582996, "percentage": 28.34, "elapsed_time": "1:57:41", "remaining_time": "4:57:36"}
|
| 351 |
+
{"current_steps": 351, "total_steps": 1235, "loss": 0.4552, "lr": 3.601929375279662e-05, "epoch": 1.4210526315789473, "percentage": 28.42, "elapsed_time": "1:58:02", "remaining_time": "4:57:16"}
|
| 352 |
+
{"current_steps": 352, "total_steps": 1235, "loss": 0.453, "lr": 3.598537002418012e-05, "epoch": 1.425101214574899, "percentage": 28.5, "elapsed_time": "1:58:23", "remaining_time": "4:56:58"}
|
| 353 |
+
{"current_steps": 353, "total_steps": 1235, "loss": 0.4511, "lr": 3.5951318476970885e-05, "epoch": 1.4291497975708503, "percentage": 28.58, "elapsed_time": "1:58:44", "remaining_time": "4:56:41"}
|
| 354 |
+
{"current_steps": 354, "total_steps": 1235, "loss": 0.4471, "lr": 3.591713938344416e-05, "epoch": 1.4331983805668016, "percentage": 28.66, "elapsed_time": "1:59:06", "remaining_time": "4:56:24"}
|
| 355 |
+
{"current_steps": 355, "total_steps": 1235, "loss": 0.455, "lr": 3.588283301689507e-05, "epoch": 1.4372469635627532, "percentage": 28.74, "elapsed_time": "1:59:28", "remaining_time": "4:56:10"}
|
| 356 |
+
{"current_steps": 356, "total_steps": 1235, "loss": 0.4601, "lr": 3.5848399651636424e-05, "epoch": 1.4412955465587045, "percentage": 28.83, "elapsed_time": "1:59:48", "remaining_time": "4:55:49"}
|
| 357 |
+
{"current_steps": 357, "total_steps": 1235, "loss": 0.4254, "lr": 3.5813839562996473e-05, "epoch": 1.4453441295546559, "percentage": 28.91, "elapsed_time": "2:00:07", "remaining_time": "4:55:26"}
|
| 358 |
+
{"current_steps": 358, "total_steps": 1235, "loss": 0.4456, "lr": 3.5779153027316775e-05, "epoch": 1.4493927125506074, "percentage": 28.99, "elapsed_time": "2:00:28", "remaining_time": "4:55:07"}
|
| 359 |
+
{"current_steps": 359, "total_steps": 1235, "loss": 0.4462, "lr": 3.574434032194994e-05, "epoch": 1.4534412955465588, "percentage": 29.07, "elapsed_time": "2:00:46", "remaining_time": "4:54:41"}
|
| 360 |
+
{"current_steps": 360, "total_steps": 1235, "loss": 0.459, "lr": 3.5709401725257436e-05, "epoch": 1.45748987854251, "percentage": 29.15, "elapsed_time": "2:01:07", "remaining_time": "4:54:24"}
|
| 361 |
+
{"current_steps": 361, "total_steps": 1235, "loss": 0.4532, "lr": 3.5674337516607346e-05, "epoch": 1.4615384615384617, "percentage": 29.23, "elapsed_time": "2:01:29", "remaining_time": "4:54:08"}
|
| 362 |
+
{"current_steps": 362, "total_steps": 1235, "loss": 0.4496, "lr": 3.563914797637216e-05, "epoch": 1.465587044534413, "percentage": 29.31, "elapsed_time": "2:01:49", "remaining_time": "4:53:47"}
|
| 363 |
+
{"current_steps": 363, "total_steps": 1235, "loss": 0.4482, "lr": 3.560383338592649e-05, "epoch": 1.4696356275303644, "percentage": 29.39, "elapsed_time": "2:02:09", "remaining_time": "4:53:25"}
|
| 364 |
+
{"current_steps": 364, "total_steps": 1235, "loss": 0.4696, "lr": 3.556839402764487e-05, "epoch": 1.4736842105263157, "percentage": 29.47, "elapsed_time": "2:02:29", "remaining_time": "4:53:05"}
|
| 365 |
+
{"current_steps": 365, "total_steps": 1235, "loss": 0.4503, "lr": 3.553283018489946e-05, "epoch": 1.4777327935222673, "percentage": 29.55, "elapsed_time": "2:02:49", "remaining_time": "4:52:44"}
|
| 366 |
+
{"current_steps": 366, "total_steps": 1235, "loss": 0.4595, "lr": 3.54971421420578e-05, "epoch": 1.4817813765182186, "percentage": 29.64, "elapsed_time": "2:03:11", "remaining_time": "4:52:29"}
|
| 367 |
+
{"current_steps": 367, "total_steps": 1235, "loss": 0.4523, "lr": 3.5461330184480524e-05, "epoch": 1.48582995951417, "percentage": 29.72, "elapsed_time": "2:03:31", "remaining_time": "4:52:09"}
|
| 368 |
+
{"current_steps": 368, "total_steps": 1235, "loss": 0.441, "lr": 3.54253945985191e-05, "epoch": 1.4898785425101215, "percentage": 29.8, "elapsed_time": "2:03:50", "remaining_time": "4:51:45"}
|
| 369 |
+
{"current_steps": 369, "total_steps": 1235, "loss": 0.4311, "lr": 3.5389335671513524e-05, "epoch": 1.4939271255060729, "percentage": 29.88, "elapsed_time": "2:04:11", "remaining_time": "4:51:26"}
|
| 370 |
+
{"current_steps": 370, "total_steps": 1235, "loss": 0.4531, "lr": 3.5353153691789986e-05, "epoch": 1.4979757085020242, "percentage": 29.96, "elapsed_time": "2:04:32", "remaining_time": "4:51:08"}
|
| 371 |
+
{"current_steps": 371, "total_steps": 1235, "loss": 0.4439, "lr": 3.531684894865866e-05, "epoch": 1.5020242914979756, "percentage": 30.04, "elapsed_time": "2:04:51", "remaining_time": "4:50:46"}
|
| 372 |
+
{"current_steps": 372, "total_steps": 1235, "loss": 0.4553, "lr": 3.528042173241128e-05, "epoch": 1.5060728744939271, "percentage": 30.12, "elapsed_time": "2:05:10", "remaining_time": "4:50:23"}
|
| 373 |
+
{"current_steps": 373, "total_steps": 1235, "loss": 0.4508, "lr": 3.524387233431892e-05, "epoch": 1.5101214574898787, "percentage": 30.2, "elapsed_time": "2:05:28", "remaining_time": "4:49:59"}
|
| 374 |
+
{"current_steps": 374, "total_steps": 1235, "loss": 0.4686, "lr": 3.520720104662958e-05, "epoch": 1.5141700404858298, "percentage": 30.28, "elapsed_time": "2:05:49", "remaining_time": "4:49:39"}
|
| 375 |
+
{"current_steps": 375, "total_steps": 1235, "loss": 0.4515, "lr": 3.5170408162565904e-05, "epoch": 1.5182186234817814, "percentage": 30.36, "elapsed_time": "2:06:08", "remaining_time": "4:49:17"}
|
| 376 |
+
{"current_steps": 376, "total_steps": 1235, "loss": 0.4562, "lr": 3.513349397632281e-05, "epoch": 1.522267206477733, "percentage": 30.45, "elapsed_time": "2:06:27", "remaining_time": "4:48:54"}
|
| 377 |
+
{"current_steps": 377, "total_steps": 1235, "loss": 0.4677, "lr": 3.5096458783065145e-05, "epoch": 1.526315789473684, "percentage": 30.53, "elapsed_time": "2:06:43", "remaining_time": "4:48:25"}
|
| 378 |
+
{"current_steps": 378, "total_steps": 1235, "loss": 0.4444, "lr": 3.505930287892533e-05, "epoch": 1.5303643724696356, "percentage": 30.61, "elapsed_time": "2:07:02", "remaining_time": "4:48:02"}
|
| 379 |
+
{"current_steps": 379, "total_steps": 1235, "loss": 0.4487, "lr": 3.502202656100099e-05, "epoch": 1.5344129554655872, "percentage": 30.69, "elapsed_time": "2:07:19", "remaining_time": "4:47:34"}
|
| 380 |
+
{"current_steps": 380, "total_steps": 1235, "loss": 0.4612, "lr": 3.498463012735256e-05, "epoch": 1.5384615384615383, "percentage": 30.77, "elapsed_time": "2:07:40", "remaining_time": "4:47:15"}
|
| 381 |
+
{"current_steps": 381, "total_steps": 1235, "loss": 0.4353, "lr": 3.494711387700094e-05, "epoch": 1.54251012145749, "percentage": 30.85, "elapsed_time": "2:08:02", "remaining_time": "4:47:00"}
|
| 382 |
+
{"current_steps": 382, "total_steps": 1235, "loss": 0.4495, "lr": 3.490947810992505e-05, "epoch": 1.5465587044534415, "percentage": 30.93, "elapsed_time": "2:08:21", "remaining_time": "4:46:36"}
|
| 383 |
+
{"current_steps": 383, "total_steps": 1235, "loss": 0.4652, "lr": 3.48717231270595e-05, "epoch": 1.5506072874493926, "percentage": 31.01, "elapsed_time": "2:08:40", "remaining_time": "4:46:14"}
|
| 384 |
+
{"current_steps": 384, "total_steps": 1235, "loss": 0.433, "lr": 3.483384923029211e-05, "epoch": 1.5546558704453441, "percentage": 31.09, "elapsed_time": "2:09:01", "remaining_time": "4:45:55"}
|
| 385 |
+
{"current_steps": 385, "total_steps": 1235, "loss": 0.4355, "lr": 3.479585672246156e-05, "epoch": 1.5587044534412957, "percentage": 31.17, "elapsed_time": "2:09:21", "remaining_time": "4:45:35"}
|
| 386 |
+
{"current_steps": 386, "total_steps": 1235, "loss": 0.4557, "lr": 3.4757745907354924e-05, "epoch": 1.5627530364372468, "percentage": 31.26, "elapsed_time": "2:09:42", "remaining_time": "4:45:18"}
|
| 387 |
+
{"current_steps": 387, "total_steps": 1235, "loss": 0.4494, "lr": 3.471951708970527e-05, "epoch": 1.5668016194331984, "percentage": 31.34, "elapsed_time": "2:10:04", "remaining_time": "4:45:01"}
|
| 388 |
+
{"current_steps": 388, "total_steps": 1235, "loss": 0.4522, "lr": 3.468117057518921e-05, "epoch": 1.5708502024291497, "percentage": 31.42, "elapsed_time": "2:10:27", "remaining_time": "4:44:46"}
|
| 389 |
+
{"current_steps": 389, "total_steps": 1235, "loss": 0.4462, "lr": 3.4642706670424426e-05, "epoch": 1.574898785425101, "percentage": 31.5, "elapsed_time": "2:10:45", "remaining_time": "4:44:22"}
|
| 390 |
+
{"current_steps": 390, "total_steps": 1235, "loss": 0.452, "lr": 3.460412568296731e-05, "epoch": 1.5789473684210527, "percentage": 31.58, "elapsed_time": "2:11:04", "remaining_time": "4:43:59"}
|
| 391 |
+
{"current_steps": 391, "total_steps": 1235, "loss": 0.4399, "lr": 3.456542792131039e-05, "epoch": 1.582995951417004, "percentage": 31.66, "elapsed_time": "2:11:23", "remaining_time": "4:43:36"}
|
| 392 |
+
{"current_steps": 392, "total_steps": 1235, "loss": 0.4368, "lr": 3.4526613694879936e-05, "epoch": 1.5870445344129553, "percentage": 31.74, "elapsed_time": "2:11:43", "remaining_time": "4:43:17"}
|
| 393 |
+
{"current_steps": 393, "total_steps": 1235, "loss": 0.4316, "lr": 3.448768331403348e-05, "epoch": 1.591093117408907, "percentage": 31.82, "elapsed_time": "2:12:03", "remaining_time": "4:42:55"}
|
| 394 |
+
{"current_steps": 394, "total_steps": 1235, "loss": 0.4471, "lr": 3.44486370900573e-05, "epoch": 1.5951417004048583, "percentage": 31.9, "elapsed_time": "2:12:23", "remaining_time": "4:42:35"}
|
| 395 |
+
{"current_steps": 395, "total_steps": 1235, "loss": 0.4567, "lr": 3.440947533516396e-05, "epoch": 1.5991902834008096, "percentage": 31.98, "elapsed_time": "2:12:41", "remaining_time": "4:42:10"}
|
| 396 |
+
{"current_steps": 396, "total_steps": 1235, "loss": 0.4659, "lr": 3.4370198362489816e-05, "epoch": 1.6032388663967612, "percentage": 32.06, "elapsed_time": "2:13:01", "remaining_time": "4:41:50"}
|
| 397 |
+
{"current_steps": 397, "total_steps": 1235, "loss": 0.4474, "lr": 3.43308064860925e-05, "epoch": 1.6072874493927125, "percentage": 32.15, "elapsed_time": "2:13:23", "remaining_time": "4:41:33"}
|
| 398 |
+
{"current_steps": 398, "total_steps": 1235, "loss": 0.4421, "lr": 3.4291300020948393e-05, "epoch": 1.6113360323886639, "percentage": 32.23, "elapsed_time": "2:13:42", "remaining_time": "4:41:11"}
|
| 399 |
+
{"current_steps": 399, "total_steps": 1235, "loss": 0.4557, "lr": 3.425167928295015e-05, "epoch": 1.6153846153846154, "percentage": 32.31, "elapsed_time": "2:13:59", "remaining_time": "4:40:43"}
|
| 400 |
+
{"current_steps": 400, "total_steps": 1235, "loss": 0.46, "lr": 3.421194458890411e-05, "epoch": 1.6194331983805668, "percentage": 32.39, "elapsed_time": "2:14:19", "remaining_time": "4:40:24"}
|
| 401 |
+
{"current_steps": 401, "total_steps": 1235, "loss": 0.4369, "lr": 3.4172096256527865e-05, "epoch": 1.623481781376518, "percentage": 32.47, "elapsed_time": "2:14:39", "remaining_time": "4:40:02"}
|
| 402 |
+
{"current_steps": 402, "total_steps": 1235, "loss": 0.448, "lr": 3.4132134604447595e-05, "epoch": 1.6275303643724697, "percentage": 32.55, "elapsed_time": "2:15:00", "remaining_time": "4:39:45"}
|
| 403 |
+
{"current_steps": 403, "total_steps": 1235, "loss": 0.4511, "lr": 3.409205995219561e-05, "epoch": 1.631578947368421, "percentage": 32.63, "elapsed_time": "2:15:21", "remaining_time": "4:39:26"}
|
| 404 |
+
{"current_steps": 404, "total_steps": 1235, "loss": 0.4476, "lr": 3.4051872620207765e-05, "epoch": 1.6356275303643724, "percentage": 32.71, "elapsed_time": "2:15:42", "remaining_time": "4:39:07"}
|
| 405 |
+
{"current_steps": 405, "total_steps": 1235, "loss": 0.447, "lr": 3.40115729298209e-05, "epoch": 1.639676113360324, "percentage": 32.79, "elapsed_time": "2:16:04", "remaining_time": "4:38:52"}
|
| 406 |
+
{"current_steps": 406, "total_steps": 1235, "loss": 0.4498, "lr": 3.397116120327025e-05, "epoch": 1.6437246963562753, "percentage": 32.87, "elapsed_time": "2:16:25", "remaining_time": "4:38:33"}
|
| 407 |
+
{"current_steps": 407, "total_steps": 1235, "loss": 0.4367, "lr": 3.3930637763686916e-05, "epoch": 1.6477732793522266, "percentage": 32.96, "elapsed_time": "2:16:45", "remaining_time": "4:38:13"}
|
| 408 |
+
{"current_steps": 408, "total_steps": 1235, "loss": 0.4432, "lr": 3.389000293509524e-05, "epoch": 1.6518218623481782, "percentage": 33.04, "elapsed_time": "2:17:06", "remaining_time": "4:37:54"}
|
| 409 |
+
{"current_steps": 409, "total_steps": 1235, "loss": 0.4579, "lr": 3.3849257042410225e-05, "epoch": 1.6558704453441295, "percentage": 33.12, "elapsed_time": "2:17:24", "remaining_time": "4:37:29"}
|
| 410 |
+
{"current_steps": 410, "total_steps": 1235, "loss": 0.4621, "lr": 3.380840041143494e-05, "epoch": 1.6599190283400809, "percentage": 33.2, "elapsed_time": "2:17:43", "remaining_time": "4:37:08"}
|
| 411 |
+
{"current_steps": 411, "total_steps": 1235, "loss": 0.4615, "lr": 3.376743336885792e-05, "epoch": 1.6639676113360324, "percentage": 33.28, "elapsed_time": "2:18:06", "remaining_time": "4:36:54"}
|
| 412 |
+
{"current_steps": 412, "total_steps": 1235, "loss": 0.4457, "lr": 3.372635624225055e-05, "epoch": 1.6680161943319838, "percentage": 33.36, "elapsed_time": "2:18:23", "remaining_time": "4:36:25"}
|
| 413 |
+
{"current_steps": 413, "total_steps": 1235, "loss": 0.4341, "lr": 3.3685169360064445e-05, "epoch": 1.6720647773279351, "percentage": 33.44, "elapsed_time": "2:18:42", "remaining_time": "4:36:05"}
|
| 414 |
+
{"current_steps": 414, "total_steps": 1235, "loss": 0.4644, "lr": 3.3643873051628804e-05, "epoch": 1.6761133603238867, "percentage": 33.52, "elapsed_time": "2:19:02", "remaining_time": "4:35:43"}
|
| 415 |
+
{"current_steps": 415, "total_steps": 1235, "loss": 0.4589, "lr": 3.3602467647147814e-05, "epoch": 1.680161943319838, "percentage": 33.6, "elapsed_time": "2:19:21", "remaining_time": "4:35:21"}
|
| 416 |
+
{"current_steps": 416, "total_steps": 1235, "loss": 0.4396, "lr": 3.356095347769799e-05, "epoch": 1.6842105263157894, "percentage": 33.68, "elapsed_time": "2:19:42", "remaining_time": "4:35:02"}
|
| 417 |
+
{"current_steps": 417, "total_steps": 1235, "loss": 0.4595, "lr": 3.351933087522552e-05, "epoch": 1.688259109311741, "percentage": 33.77, "elapsed_time": "2:20:01", "remaining_time": "4:34:40"}
|
| 418 |
+
{"current_steps": 418, "total_steps": 1235, "loss": 0.4426, "lr": 3.3477600172543626e-05, "epoch": 1.6923076923076923, "percentage": 33.85, "elapsed_time": "2:20:20", "remaining_time": "4:34:18"}
|
| 419 |
+
{"current_steps": 419, "total_steps": 1235, "loss": 0.4634, "lr": 3.3435761703329894e-05, "epoch": 1.6963562753036436, "percentage": 33.93, "elapsed_time": "2:20:39", "remaining_time": "4:33:55"}
|
| 420 |
+
{"current_steps": 420, "total_steps": 1235, "loss": 0.4578, "lr": 3.3393815802123606e-05, "epoch": 1.7004048582995952, "percentage": 34.01, "elapsed_time": "2:20:59", "remaining_time": "4:33:35"}
|
| 421 |
+
{"current_steps": 421, "total_steps": 1235, "loss": 0.4349, "lr": 3.335176280432308e-05, "epoch": 1.7044534412955465, "percentage": 34.09, "elapsed_time": "2:21:20", "remaining_time": "4:33:16"}
|
| 422 |
+
{"current_steps": 422, "total_steps": 1235, "loss": 0.4537, "lr": 3.330960304618295e-05, "epoch": 1.708502024291498, "percentage": 34.17, "elapsed_time": "2:21:37", "remaining_time": "4:32:49"}
|
| 423 |
+
{"current_steps": 423, "total_steps": 1235, "loss": 0.4541, "lr": 3.326733686481153e-05, "epoch": 1.7125506072874495, "percentage": 34.25, "elapsed_time": "2:21:58", "remaining_time": "4:32:33"}
|
| 424 |
+
{"current_steps": 424, "total_steps": 1235, "loss": 0.4312, "lr": 3.3224964598168084e-05, "epoch": 1.7165991902834008, "percentage": 34.33, "elapsed_time": "2:22:18", "remaining_time": "4:32:12"}
|
| 425 |
+
{"current_steps": 425, "total_steps": 1235, "loss": 0.458, "lr": 3.318248658506012e-05, "epoch": 1.7206477732793521, "percentage": 34.41, "elapsed_time": "2:22:39", "remaining_time": "4:31:54"}
|
| 426 |
+
{"current_steps": 426, "total_steps": 1235, "loss": 0.4335, "lr": 3.313990316514069e-05, "epoch": 1.7246963562753037, "percentage": 34.49, "elapsed_time": "2:22:58", "remaining_time": "4:31:31"}
|
| 427 |
+
{"current_steps": 427, "total_steps": 1235, "loss": 0.4557, "lr": 3.309721467890571e-05, "epoch": 1.728744939271255, "percentage": 34.57, "elapsed_time": "2:23:13", "remaining_time": "4:31:00"}
|
| 428 |
+
{"current_steps": 428, "total_steps": 1235, "loss": 0.4474, "lr": 3.305442146769115e-05, "epoch": 1.7327935222672064, "percentage": 34.66, "elapsed_time": "2:23:33", "remaining_time": "4:30:41"}
|
| 429 |
+
{"current_steps": 429, "total_steps": 1235, "loss": 0.442, "lr": 3.30115238736704e-05, "epoch": 1.736842105263158, "percentage": 34.74, "elapsed_time": "2:23:55", "remaining_time": "4:30:24"}
|
| 430 |
+
{"current_steps": 430, "total_steps": 1235, "loss": 0.45, "lr": 3.296852223985148e-05, "epoch": 1.7408906882591093, "percentage": 34.82, "elapsed_time": "2:24:16", "remaining_time": "4:30:05"}
|
| 431 |
+
{"current_steps": 431, "total_steps": 1235, "loss": 0.4489, "lr": 3.2925416910074315e-05, "epoch": 1.7449392712550607, "percentage": 34.9, "elapsed_time": "2:24:36", "remaining_time": "4:29:45"}
|
| 432 |
+
{"current_steps": 432, "total_steps": 1235, "loss": 0.454, "lr": 3.288220822900796e-05, "epoch": 1.7489878542510122, "percentage": 34.98, "elapsed_time": "2:24:56", "remaining_time": "4:29:24"}
|
| 433 |
+
{"current_steps": 433, "total_steps": 1235, "loss": 0.4412, "lr": 3.283889654214788e-05, "epoch": 1.7530364372469636, "percentage": 35.06, "elapsed_time": "2:25:16", "remaining_time": "4:29:05"}
|
| 434 |
+
{"current_steps": 434, "total_steps": 1235, "loss": 0.4433, "lr": 3.279548219581317e-05, "epoch": 1.757085020242915, "percentage": 35.14, "elapsed_time": "2:25:33", "remaining_time": "4:28:38"}
|
| 435 |
+
{"current_steps": 435, "total_steps": 1235, "loss": 0.4469, "lr": 3.275196553714379e-05, "epoch": 1.7611336032388665, "percentage": 35.22, "elapsed_time": "2:25:51", "remaining_time": "4:28:15"}
|
| 436 |
+
{"current_steps": 436, "total_steps": 1235, "loss": 0.4436, "lr": 3.270834691409778e-05, "epoch": 1.7651821862348178, "percentage": 35.3, "elapsed_time": "2:26:12", "remaining_time": "4:27:55"}
|
| 437 |
+
{"current_steps": 437, "total_steps": 1235, "loss": 0.4586, "lr": 3.266462667544849e-05, "epoch": 1.7692307692307692, "percentage": 35.38, "elapsed_time": "2:26:33", "remaining_time": "4:27:37"}
|
| 438 |
+
{"current_steps": 438, "total_steps": 1235, "loss": 0.455, "lr": 3.262080517078178e-05, "epoch": 1.7732793522267207, "percentage": 35.47, "elapsed_time": "2:26:54", "remaining_time": "4:27:18"}
|
| 439 |
+
{"current_steps": 439, "total_steps": 1235, "loss": 0.4529, "lr": 3.257688275049323e-05, "epoch": 1.777327935222672, "percentage": 35.55, "elapsed_time": "2:27:15", "remaining_time": "4:27:00"}
|
| 440 |
+
{"current_steps": 440, "total_steps": 1235, "loss": 0.4374, "lr": 3.253285976578535e-05, "epoch": 1.7813765182186234, "percentage": 35.63, "elapsed_time": "2:27:36", "remaining_time": "4:26:42"}
|
| 441 |
+
{"current_steps": 441, "total_steps": 1235, "loss": 0.461, "lr": 3.2488736568664756e-05, "epoch": 1.785425101214575, "percentage": 35.71, "elapsed_time": "2:27:58", "remaining_time": "4:26:25"}
|
| 442 |
+
{"current_steps": 442, "total_steps": 1235, "loss": 0.4345, "lr": 3.244451351193935e-05, "epoch": 1.7894736842105263, "percentage": 35.79, "elapsed_time": "2:28:20", "remaining_time": "4:26:08"}
|
| 443 |
+
{"current_steps": 443, "total_steps": 1235, "loss": 0.4567, "lr": 3.240019094921551e-05, "epoch": 1.7935222672064777, "percentage": 35.87, "elapsed_time": "2:28:39", "remaining_time": "4:25:45"}
|
| 444 |
+
{"current_steps": 444, "total_steps": 1235, "loss": 0.4588, "lr": 3.235576923489527e-05, "epoch": 1.7975708502024292, "percentage": 35.95, "elapsed_time": "2:29:01", "remaining_time": "4:25:29"}
|
| 445 |
+
{"current_steps": 445, "total_steps": 1235, "loss": 0.4427, "lr": 3.2311248724173476e-05, "epoch": 1.8016194331983806, "percentage": 36.03, "elapsed_time": "2:29:23", "remaining_time": "4:25:12"}
|
| 446 |
+
{"current_steps": 446, "total_steps": 1235, "loss": 0.4456, "lr": 3.226662977303494e-05, "epoch": 1.805668016194332, "percentage": 36.11, "elapsed_time": "2:29:44", "remaining_time": "4:24:54"}
|
| 447 |
+
{"current_steps": 447, "total_steps": 1235, "loss": 0.4444, "lr": 3.2221912738251626e-05, "epoch": 1.8097165991902835, "percentage": 36.19, "elapsed_time": "2:30:04", "remaining_time": "4:24:33"}
|
| 448 |
+
{"current_steps": 448, "total_steps": 1235, "loss": 0.4509, "lr": 3.2177097977379736e-05, "epoch": 1.8137651821862348, "percentage": 36.28, "elapsed_time": "2:30:22", "remaining_time": "4:24:09"}
|
| 449 |
+
{"current_steps": 449, "total_steps": 1235, "loss": 0.443, "lr": 3.21321858487569e-05, "epoch": 1.8178137651821862, "percentage": 36.36, "elapsed_time": "2:30:42", "remaining_time": "4:23:49"}
|
| 450 |
+
{"current_steps": 450, "total_steps": 1235, "loss": 0.4363, "lr": 3.208717671149931e-05, "epoch": 1.8218623481781377, "percentage": 36.44, "elapsed_time": "2:31:01", "remaining_time": "4:23:27"}
|
| 451 |
+
{"current_steps": 451, "total_steps": 1235, "loss": 0.4571, "lr": 3.204207092549882e-05, "epoch": 1.825910931174089, "percentage": 36.52, "elapsed_time": "2:31:21", "remaining_time": "4:23:06"}
|
| 452 |
+
{"current_steps": 452, "total_steps": 1235, "loss": 0.4351, "lr": 3.19968688514201e-05, "epoch": 1.8299595141700404, "percentage": 36.6, "elapsed_time": "2:31:42", "remaining_time": "4:22:47"}
|
| 453 |
+
{"current_steps": 453, "total_steps": 1235, "loss": 0.4386, "lr": 3.195157085069774e-05, "epoch": 1.834008097165992, "percentage": 36.68, "elapsed_time": "2:32:00", "remaining_time": "4:22:24"}
|
| 454 |
+
{"current_steps": 454, "total_steps": 1235, "loss": 0.4488, "lr": 3.190617728553332e-05, "epoch": 1.8380566801619433, "percentage": 36.76, "elapsed_time": "2:32:19", "remaining_time": "4:22:02"}
|
| 455 |
+
{"current_steps": 455, "total_steps": 1235, "loss": 0.4609, "lr": 3.1860688518892606e-05, "epoch": 1.8421052631578947, "percentage": 36.84, "elapsed_time": "2:32:35", "remaining_time": "4:21:35"}
|
| 456 |
+
{"current_steps": 456, "total_steps": 1235, "loss": 0.4483, "lr": 3.181510491450254e-05, "epoch": 1.8461538461538463, "percentage": 36.92, "elapsed_time": "2:32:54", "remaining_time": "4:21:13"}
|
| 457 |
+
{"current_steps": 457, "total_steps": 1235, "loss": 0.4379, "lr": 3.176942683684842e-05, "epoch": 1.8502024291497976, "percentage": 37.0, "elapsed_time": "2:33:15", "remaining_time": "4:20:54"}
|
| 458 |
+
{"current_steps": 458, "total_steps": 1235, "loss": 0.4391, "lr": 3.1723654651170934e-05, "epoch": 1.854251012145749, "percentage": 37.09, "elapsed_time": "2:33:37", "remaining_time": "4:20:37"}
|
| 459 |
+
{"current_steps": 459, "total_steps": 1235, "loss": 0.4194, "lr": 3.167778872346327e-05, "epoch": 1.8582995951417005, "percentage": 37.17, "elapsed_time": "2:33:56", "remaining_time": "4:20:15"}
|
| 460 |
+
{"current_steps": 460, "total_steps": 1235, "loss": 0.4506, "lr": 3.163182942046815e-05, "epoch": 1.8623481781376519, "percentage": 37.25, "elapsed_time": "2:34:15", "remaining_time": "4:19:53"}
|
| 461 |
+
{"current_steps": 461, "total_steps": 1235, "loss": 0.4465, "lr": 3.158577710967494e-05, "epoch": 1.8663967611336032, "percentage": 37.33, "elapsed_time": "2:34:35", "remaining_time": "4:19:33"}
|
| 462 |
+
{"current_steps": 462, "total_steps": 1235, "loss": 0.4443, "lr": 3.153963215931669e-05, "epoch": 1.8704453441295548, "percentage": 37.41, "elapsed_time": "2:34:54", "remaining_time": "4:19:11"}
|
| 463 |
+
{"current_steps": 463, "total_steps": 1235, "loss": 0.4621, "lr": 3.14933949383672e-05, "epoch": 1.874493927125506, "percentage": 37.49, "elapsed_time": "2:35:15", "remaining_time": "4:18:53"}
|
| 464 |
+
{"current_steps": 464, "total_steps": 1235, "loss": 0.4538, "lr": 3.144706581653805e-05, "epoch": 1.8785425101214575, "percentage": 37.57, "elapsed_time": "2:35:34", "remaining_time": "4:18:30"}
|
| 465 |
+
{"current_steps": 465, "total_steps": 1235, "loss": 0.4365, "lr": 3.140064516427566e-05, "epoch": 1.882591093117409, "percentage": 37.65, "elapsed_time": "2:35:55", "remaining_time": "4:18:11"}
|
| 466 |
+
{"current_steps": 466, "total_steps": 1235, "loss": 0.4451, "lr": 3.135413335275833e-05, "epoch": 1.8866396761133604, "percentage": 37.73, "elapsed_time": "2:36:15", "remaining_time": "4:17:52"}
|
| 467 |
+
{"current_steps": 467, "total_steps": 1235, "loss": 0.4377, "lr": 3.130753075389327e-05, "epoch": 1.8906882591093117, "percentage": 37.81, "elapsed_time": "2:36:35", "remaining_time": "4:17:31"}
|
| 468 |
+
{"current_steps": 468, "total_steps": 1235, "loss": 0.4361, "lr": 3.1260837740313625e-05, "epoch": 1.8947368421052633, "percentage": 37.89, "elapsed_time": "2:36:55", "remaining_time": "4:17:10"}
|
| 469 |
+
{"current_steps": 469, "total_steps": 1235, "loss": 0.466, "lr": 3.121405468537547e-05, "epoch": 1.8987854251012146, "percentage": 37.98, "elapsed_time": "2:37:15", "remaining_time": "4:16:51"}
|
| 470 |
+
{"current_steps": 470, "total_steps": 1235, "loss": 0.4602, "lr": 3.116718196315488e-05, "epoch": 1.902834008097166, "percentage": 38.06, "elapsed_time": "2:37:34", "remaining_time": "4:16:28"}
|
| 471 |
+
{"current_steps": 471, "total_steps": 1235, "loss": 0.4365, "lr": 3.1120219948444894e-05, "epoch": 1.9068825910931175, "percentage": 38.14, "elapsed_time": "2:37:53", "remaining_time": "4:16:06"}
|
| 472 |
+
{"current_steps": 472, "total_steps": 1235, "loss": 0.4364, "lr": 3.107316901675252e-05, "epoch": 1.9109311740890689, "percentage": 38.22, "elapsed_time": "2:38:15", "remaining_time": "4:15:49"}
|
| 473 |
+
{"current_steps": 473, "total_steps": 1235, "loss": 0.4232, "lr": 3.1026029544295745e-05, "epoch": 1.9149797570850202, "percentage": 38.3, "elapsed_time": "2:38:32", "remaining_time": "4:15:25"}
|
| 474 |
+
{"current_steps": 474, "total_steps": 1235, "loss": 0.4559, "lr": 3.097880190800057e-05, "epoch": 1.9190283400809718, "percentage": 38.38, "elapsed_time": "2:38:51", "remaining_time": "4:15:02"}
|
| 475 |
+
{"current_steps": 475, "total_steps": 1235, "loss": 0.4559, "lr": 3.093148648549788e-05, "epoch": 1.9230769230769231, "percentage": 38.46, "elapsed_time": "2:39:12", "remaining_time": "4:14:43"}
|
| 476 |
+
{"current_steps": 476, "total_steps": 1235, "loss": 0.4452, "lr": 3.088408365512055e-05, "epoch": 1.9271255060728745, "percentage": 38.54, "elapsed_time": "2:39:31", "remaining_time": "4:14:22"}
|
| 477 |
+
{"current_steps": 477, "total_steps": 1235, "loss": 0.4604, "lr": 3.083659379590034e-05, "epoch": 1.931174089068826, "percentage": 38.62, "elapsed_time": "2:39:51", "remaining_time": "4:14:02"}
|
| 478 |
+
{"current_steps": 478, "total_steps": 1235, "loss": 0.4275, "lr": 3.0789017287564913e-05, "epoch": 1.9352226720647774, "percentage": 38.7, "elapsed_time": "2:40:11", "remaining_time": "4:13:40"}
|
| 479 |
+
{"current_steps": 479, "total_steps": 1235, "loss": 0.4282, "lr": 3.074135451053475e-05, "epoch": 1.9392712550607287, "percentage": 38.79, "elapsed_time": "2:40:31", "remaining_time": "4:13:20"}
|
| 480 |
+
{"current_steps": 480, "total_steps": 1235, "loss": 0.4403, "lr": 3.069360584592015e-05, "epoch": 1.9433198380566803, "percentage": 38.87, "elapsed_time": "2:40:51", "remaining_time": "4:13:01"}
|
| 481 |
+
{"current_steps": 481, "total_steps": 1235, "loss": 0.4483, "lr": 3.064577167551816e-05, "epoch": 1.9473684210526314, "percentage": 38.95, "elapsed_time": "2:41:10", "remaining_time": "4:12:39"}
|
| 482 |
+
{"current_steps": 482, "total_steps": 1235, "loss": 0.4501, "lr": 3.059785238180953e-05, "epoch": 1.951417004048583, "percentage": 39.03, "elapsed_time": "2:41:28", "remaining_time": "4:12:16"}
|
| 483 |
+
{"current_steps": 483, "total_steps": 1235, "loss": 0.4374, "lr": 3.054984834795566e-05, "epoch": 1.9554655870445345, "percentage": 39.11, "elapsed_time": "2:41:49", "remaining_time": "4:11:57"}
|
| 484 |
+
{"current_steps": 484, "total_steps": 1235, "loss": 0.4536, "lr": 3.0501759957795537e-05, "epoch": 1.9595141700404857, "percentage": 39.19, "elapsed_time": "2:42:09", "remaining_time": "4:11:36"}
|
| 485 |
+
{"current_steps": 485, "total_steps": 1235, "loss": 0.4544, "lr": 3.0453587595842627e-05, "epoch": 1.9635627530364372, "percentage": 39.27, "elapsed_time": "2:42:26", "remaining_time": "4:11:11"}
|
| 486 |
+
{"current_steps": 486, "total_steps": 1235, "loss": 0.4568, "lr": 3.0405331647281856e-05, "epoch": 1.9676113360323888, "percentage": 39.35, "elapsed_time": "2:42:44", "remaining_time": "4:10:49"}
|
| 487 |
+
{"current_steps": 487, "total_steps": 1235, "loss": 0.4558, "lr": 3.0356992497966508e-05, "epoch": 1.97165991902834, "percentage": 39.43, "elapsed_time": "2:43:03", "remaining_time": "4:10:26"}
|
| 488 |
+
{"current_steps": 488, "total_steps": 1235, "loss": 0.4465, "lr": 3.0308570534415137e-05, "epoch": 1.9757085020242915, "percentage": 39.51, "elapsed_time": "2:43:21", "remaining_time": "4:10:03"}
|
| 489 |
+
{"current_steps": 489, "total_steps": 1235, "loss": 0.4434, "lr": 3.0260066143808467e-05, "epoch": 1.979757085020243, "percentage": 39.6, "elapsed_time": "2:43:42", "remaining_time": "4:09:44"}
|
| 490 |
+
{"current_steps": 490, "total_steps": 1235, "loss": 0.435, "lr": 3.021147971398632e-05, "epoch": 1.9838056680161942, "percentage": 39.68, "elapsed_time": "2:44:02", "remaining_time": "4:09:24"}
|
| 491 |
+
{"current_steps": 491, "total_steps": 1235, "loss": 0.4371, "lr": 3.0162811633444478e-05, "epoch": 1.9878542510121457, "percentage": 39.76, "elapsed_time": "2:44:22", "remaining_time": "4:09:03"}
|
| 492 |
+
{"current_steps": 492, "total_steps": 1235, "loss": 0.4498, "lr": 3.0114062291331635e-05, "epoch": 1.9919028340080973, "percentage": 39.84, "elapsed_time": "2:44:43", "remaining_time": "4:08:46"}
|
| 493 |
+
{"current_steps": 493, "total_steps": 1235, "loss": 0.461, "lr": 3.0065232077446217e-05, "epoch": 1.9959514170040484, "percentage": 39.92, "elapsed_time": "2:45:03", "remaining_time": "4:08:25"}
|
| 494 |
+
{"current_steps": 494, "total_steps": 1235, "loss": 0.4308, "lr": 3.001632138223332e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "2:45:23", "remaining_time": "4:08:04"}
|
| 495 |
+
{"current_steps": 495, "total_steps": 1235, "loss": 0.3424, "lr": 2.9967330596781565e-05, "epoch": 2.0040485829959516, "percentage": 40.08, "elapsed_time": "2:47:32", "remaining_time": "4:10:27"}
|
| 496 |
+
{"current_steps": 496, "total_steps": 1235, "loss": 0.332, "lr": 2.9918260112819952e-05, "epoch": 2.0080971659919027, "percentage": 40.16, "elapsed_time": "2:47:54", "remaining_time": "4:10:09"}
|
| 497 |
+
{"current_steps": 497, "total_steps": 1235, "loss": 0.3557, "lr": 2.9869110322714778e-05, "epoch": 2.0121457489878543, "percentage": 40.24, "elapsed_time": "2:48:16", "remaining_time": "4:09:52"}
|
| 498 |
+
{"current_steps": 498, "total_steps": 1235, "loss": 0.3581, "lr": 2.9819881619466447e-05, "epoch": 2.016194331983806, "percentage": 40.32, "elapsed_time": "2:48:37", "remaining_time": "4:09:33"}
|
| 499 |
+
{"current_steps": 499, "total_steps": 1235, "loss": 0.3555, "lr": 2.9770574396706364e-05, "epoch": 2.020242914979757, "percentage": 40.4, "elapsed_time": "2:48:56", "remaining_time": "4:09:10"}
|
| 500 |
+
{"current_steps": 500, "total_steps": 1235, "loss": 0.3642, "lr": 2.972118904869376e-05, "epoch": 2.0242914979757085, "percentage": 40.49, "elapsed_time": "2:49:17", "remaining_time": "4:08:51"}
|
| 501 |
+
{"current_steps": 501, "total_steps": 1235, "loss": 0.3462, "lr": 2.9671725970312563e-05, "epoch": 2.02834008097166, "percentage": 40.57, "elapsed_time": "2:49:37", "remaining_time": "4:08:30"}
|
| 502 |
+
{"current_steps": 502, "total_steps": 1235, "loss": 0.3462, "lr": 2.9622185557068238e-05, "epoch": 2.032388663967611, "percentage": 40.65, "elapsed_time": "2:49:55", "remaining_time": "4:08:07"}
|