Training in progress, step 2200
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:a9e4d9eb45e8dfdc22ac8f5c0e74b627e13cd1ed46339ff86cb37ed73a5b20a6
|
| 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:ecfe7e40f5ddaa9bbca168d718c2832a6ceae4c21550df041592250c4ac21428
|
| 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:d38b8c631dd728a382df117670195c2ca23ed084b7d6fdb93c4b7d26e2d3a1d5
|
| 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:efc9e9055022f49e583791f98ce3edccba39a43f71a5d6926d16462a9949d264
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -398,3 +398,44 @@
|
|
| 398 |
{"current_steps": 1990, "total_steps": 9128, "loss": 0.1872, "lr": 3.833055323480253e-05, "epoch": 1.5262754123513618, "percentage": 21.8, "elapsed_time": "12:32:07", "remaining_time": "1 day, 20:57:49"}
|
| 399 |
{"current_steps": 1995, "total_steps": 9128, "loss": 0.2032, "lr": 3.831522397164592e-05, "epoch": 1.5301112389719984, "percentage": 21.86, "elapsed_time": "12:33:22", "remaining_time": "1 day, 20:53:38"}
|
| 400 |
{"current_steps": 2000, "total_steps": 9128, "loss": 0.2, "lr": 3.829982774520901e-05, "epoch": 1.5339470655926353, "percentage": 21.91, "elapsed_time": "12:34:36", "remaining_time": "1 day, 20:49:26"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 398 |
{"current_steps": 1990, "total_steps": 9128, "loss": 0.1872, "lr": 3.833055323480253e-05, "epoch": 1.5262754123513618, "percentage": 21.8, "elapsed_time": "12:32:07", "remaining_time": "1 day, 20:57:49"}
|
| 399 |
{"current_steps": 1995, "total_steps": 9128, "loss": 0.2032, "lr": 3.831522397164592e-05, "epoch": 1.5301112389719984, "percentage": 21.86, "elapsed_time": "12:33:22", "remaining_time": "1 day, 20:53:38"}
|
| 400 |
{"current_steps": 2000, "total_steps": 9128, "loss": 0.2, "lr": 3.829982774520901e-05, "epoch": 1.5339470655926353, "percentage": 21.91, "elapsed_time": "12:34:36", "remaining_time": "1 day, 20:49:26"}
|
| 401 |
+
{"current_steps": 2005, "total_steps": 9128, "loss": 0.2067, "lr": 3.828436461178278e-05, "epoch": 1.537782892213272, "percentage": 21.97, "elapsed_time": "12:37:21", "remaining_time": "1 day, 20:50:34"}
|
| 402 |
+
{"current_steps": 2010, "total_steps": 9128, "loss": 0.1986, "lr": 3.826883462790282e-05, "epoch": 1.5416187188339086, "percentage": 22.02, "elapsed_time": "12:38:35", "remaining_time": "1 day, 20:46:24"}
|
| 403 |
+
{"current_steps": 2015, "total_steps": 9128, "loss": 0.2013, "lr": 3.825323785034915e-05, "epoch": 1.5454545454545454, "percentage": 22.07, "elapsed_time": "12:39:50", "remaining_time": "1 day, 20:42:15"}
|
| 404 |
+
{"current_steps": 2020, "total_steps": 9128, "loss": 0.2057, "lr": 3.823757433614599e-05, "epoch": 1.5492903720751823, "percentage": 22.13, "elapsed_time": "12:41:05", "remaining_time": "1 day, 20:38:06"}
|
| 405 |
+
{"current_steps": 2025, "total_steps": 9128, "loss": 0.2949, "lr": 3.822184414256156e-05, "epoch": 1.553126198695819, "percentage": 22.18, "elapsed_time": "12:43:07", "remaining_time": "1 day, 20:36:46"}
|
| 406 |
+
{"current_steps": 2030, "total_steps": 9128, "loss": 0.3163, "lr": 3.820604732710786e-05, "epoch": 1.5569620253164556, "percentage": 22.24, "elapsed_time": "12:45:05", "remaining_time": "1 day, 20:35:10"}
|
| 407 |
+
{"current_steps": 2035, "total_steps": 9128, "loss": 0.3042, "lr": 3.819018394754051e-05, "epoch": 1.5607978519370924, "percentage": 22.29, "elapsed_time": "12:47:37", "remaining_time": "1 day, 20:35:33"}
|
| 408 |
+
{"current_steps": 2040, "total_steps": 9128, "loss": 0.3033, "lr": 3.8174254061858436e-05, "epoch": 1.5646336785577293, "percentage": 22.35, "elapsed_time": "12:49:58", "remaining_time": "1 day, 20:35:15"}
|
| 409 |
+
{"current_steps": 2045, "total_steps": 9128, "loss": 0.2997, "lr": 3.815825772830377e-05, "epoch": 1.568469505178366, "percentage": 22.4, "elapsed_time": "12:52:18", "remaining_time": "1 day, 20:34:57"}
|
| 410 |
+
{"current_steps": 2050, "total_steps": 9128, "loss": 0.311, "lr": 3.814219500536157e-05, "epoch": 1.5723053317990026, "percentage": 22.46, "elapsed_time": "12:54:37", "remaining_time": "1 day, 20:34:31"}
|
| 411 |
+
{"current_steps": 2055, "total_steps": 9128, "loss": 0.2933, "lr": 3.812606595175963e-05, "epoch": 1.5761411584196394, "percentage": 22.51, "elapsed_time": "12:57:00", "remaining_time": "1 day, 20:34:20"}
|
| 412 |
+
{"current_steps": 2060, "total_steps": 9128, "loss": 0.2991, "lr": 3.810987062646825e-05, "epoch": 1.5799769850402763, "percentage": 22.57, "elapsed_time": "12:59:11", "remaining_time": "1 day, 20:33:27"}
|
| 413 |
+
{"current_steps": 2065, "total_steps": 9128, "loss": 0.3053, "lr": 3.809360908870003e-05, "epoch": 1.583812811660913, "percentage": 22.62, "elapsed_time": "13:01:36", "remaining_time": "1 day, 20:33:23"}
|
| 414 |
+
{"current_steps": 2070, "total_steps": 9128, "loss": 0.3062, "lr": 3.807728139790967e-05, "epoch": 1.5876486382815496, "percentage": 22.68, "elapsed_time": "13:03:48", "remaining_time": "1 day, 20:32:31"}
|
| 415 |
+
{"current_steps": 2075, "total_steps": 9128, "loss": 0.3027, "lr": 3.8060887613793716e-05, "epoch": 1.5914844649021864, "percentage": 22.73, "elapsed_time": "13:06:03", "remaining_time": "1 day, 20:31:51"}
|
| 416 |
+
{"current_steps": 2080, "total_steps": 9128, "loss": 0.2997, "lr": 3.804442779629035e-05, "epoch": 1.5953202915228233, "percentage": 22.79, "elapsed_time": "13:08:42", "remaining_time": "1 day, 20:32:29"}
|
| 417 |
+
{"current_steps": 2085, "total_steps": 9128, "loss": 0.3042, "lr": 3.802790200557923e-05, "epoch": 1.59915611814346, "percentage": 22.84, "elapsed_time": "13:10:44", "remaining_time": "1 day, 20:31:06"}
|
| 418 |
+
{"current_steps": 2090, "total_steps": 9128, "loss": 0.2988, "lr": 3.801131030208118e-05, "epoch": 1.6029919447640966, "percentage": 22.9, "elapsed_time": "13:12:50", "remaining_time": "1 day, 20:29:53"}
|
| 419 |
+
{"current_steps": 2095, "total_steps": 9128, "loss": 0.3071, "lr": 3.799465274645802e-05, "epoch": 1.6068277713847334, "percentage": 22.95, "elapsed_time": "13:14:31", "remaining_time": "1 day, 20:27:14"}
|
| 420 |
+
{"current_steps": 2100, "total_steps": 9128, "loss": 0.3075, "lr": 3.797792939961235e-05, "epoch": 1.6106635980053703, "percentage": 23.01, "elapsed_time": "13:16:09", "remaining_time": "1 day, 20:24:28"}
|
| 421 |
+
{"current_steps": 2105, "total_steps": 9128, "loss": 0.3044, "lr": 3.796114032268729e-05, "epoch": 1.614499424626007, "percentage": 23.06, "elapsed_time": "13:17:52", "remaining_time": "1 day, 20:21:57"}
|
| 422 |
+
{"current_steps": 2110, "total_steps": 9128, "loss": 0.3141, "lr": 3.79442855770663e-05, "epoch": 1.6183352512466436, "percentage": 23.12, "elapsed_time": "13:19:29", "remaining_time": "1 day, 20:19:11"}
|
| 423 |
+
{"current_steps": 2115, "total_steps": 9128, "loss": 0.3108, "lr": 3.7927365224372925e-05, "epoch": 1.6221710778672804, "percentage": 23.17, "elapsed_time": "13:21:05", "remaining_time": "1 day, 20:16:17"}
|
| 424 |
+
{"current_steps": 2120, "total_steps": 9128, "loss": 0.306, "lr": 3.791037932647057e-05, "epoch": 1.6260069044879173, "percentage": 23.23, "elapsed_time": "13:22:48", "remaining_time": "1 day, 20:13:49"}
|
| 425 |
+
{"current_steps": 2125, "total_steps": 9128, "loss": 0.3072, "lr": 3.7893327945462315e-05, "epoch": 1.629842731108554, "percentage": 23.28, "elapsed_time": "13:24:29", "remaining_time": "1 day, 20:11:12"}
|
| 426 |
+
{"current_steps": 2130, "total_steps": 9128, "loss": 0.2955, "lr": 3.787621114369062e-05, "epoch": 1.6336785577291906, "percentage": 23.33, "elapsed_time": "13:26:11", "remaining_time": "1 day, 20:08:42"}
|
| 427 |
+
{"current_steps": 2135, "total_steps": 9128, "loss": 0.2813, "lr": 3.7859028983737154e-05, "epoch": 1.6375143843498274, "percentage": 23.39, "elapsed_time": "13:27:54", "remaining_time": "1 day, 20:06:13"}
|
| 428 |
+
{"current_steps": 2140, "total_steps": 9128, "loss": 0.3023, "lr": 3.784178152842254e-05, "epoch": 1.6413502109704643, "percentage": 23.44, "elapsed_time": "13:29:31", "remaining_time": "1 day, 20:03:25"}
|
| 429 |
+
{"current_steps": 2145, "total_steps": 9128, "loss": 0.3015, "lr": 3.782446884080614e-05, "epoch": 1.645186037591101, "percentage": 23.5, "elapsed_time": "13:31:10", "remaining_time": "1 day, 20:00:44"}
|
| 430 |
+
{"current_steps": 2150, "total_steps": 9128, "loss": 0.309, "lr": 3.7807090984185795e-05, "epoch": 1.6490218642117376, "percentage": 23.55, "elapsed_time": "13:32:48", "remaining_time": "1 day, 19:58:01"}
|
| 431 |
+
{"current_steps": 2155, "total_steps": 9128, "loss": 0.287, "lr": 3.7789648022097625e-05, "epoch": 1.6528576908323744, "percentage": 23.61, "elapsed_time": "13:34:28", "remaining_time": "1 day, 19:55:24"}
|
| 432 |
+
{"current_steps": 2160, "total_steps": 9128, "loss": 0.2875, "lr": 3.777214001831579e-05, "epoch": 1.656693517453011, "percentage": 23.66, "elapsed_time": "13:36:07", "remaining_time": "1 day, 19:52:45"}
|
| 433 |
+
{"current_steps": 2165, "total_steps": 9128, "loss": 0.3035, "lr": 3.775456703685226e-05, "epoch": 1.6605293440736477, "percentage": 23.72, "elapsed_time": "13:37:47", "remaining_time": "1 day, 19:50:09"}
|
| 434 |
+
{"current_steps": 2170, "total_steps": 9128, "loss": 0.2939, "lr": 3.773692914195655e-05, "epoch": 1.6643651706942846, "percentage": 23.77, "elapsed_time": "13:39:30", "remaining_time": "1 day, 19:47:41"}
|
| 435 |
+
{"current_steps": 2175, "total_steps": 9128, "loss": 0.283, "lr": 3.7719226398115515e-05, "epoch": 1.6682009973149214, "percentage": 23.83, "elapsed_time": "13:41:07", "remaining_time": "1 day, 19:44:58"}
|
| 436 |
+
{"current_steps": 2180, "total_steps": 9128, "loss": 0.3001, "lr": 3.770145887005313e-05, "epoch": 1.672036823935558, "percentage": 23.88, "elapsed_time": "13:42:48", "remaining_time": "1 day, 19:42:24"}
|
| 437 |
+
{"current_steps": 2185, "total_steps": 9128, "loss": 0.3003, "lr": 3.768362662273021e-05, "epoch": 1.6758726505561947, "percentage": 23.94, "elapsed_time": "13:44:26", "remaining_time": "1 day, 19:39:42"}
|
| 438 |
+
{"current_steps": 2190, "total_steps": 9128, "loss": 0.2908, "lr": 3.766572972134419e-05, "epoch": 1.6797084771768316, "percentage": 23.99, "elapsed_time": "13:46:08", "remaining_time": "1 day, 19:37:14"}
|
| 439 |
+
{"current_steps": 2195, "total_steps": 9128, "loss": 0.301, "lr": 3.764776823132891e-05, "epoch": 1.6835443037974684, "percentage": 24.05, "elapsed_time": "13:47:42", "remaining_time": "1 day, 19:34:21"}
|
| 440 |
+
{"current_steps": 2200, "total_steps": 9128, "loss": 0.2993, "lr": 3.762974221835433e-05, "epoch": 1.687380130418105, "percentage": 24.1, "elapsed_time": "13:49:19", "remaining_time": "1 day, 19:31:36"}
|
| 441 |
+
{"current_steps": 2205, "total_steps": 9128, "loss": 0.2959, "lr": 3.761165174832634e-05, "epoch": 1.6912159570387417, "percentage": 24.16, "elapsed_time": "13:52:18", "remaining_time": "1 day, 19:33:12"}
|