Training in progress, step 8000
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 sha256:6ebb008082583e656b6af53b08ab099ad7e3072b2b93f15a4913212bddec9c6a
|
| 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 sha256:485652b58a65a1d6fe7fce33e65259f93e88d1997af4a87e769200524efa2f1f
|
| 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 sha256:56c820054cae91d3f469ebfbc7c1d73dd85b90619d2f3a061ae857381de08410
|
| 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 sha256:707903a45f21d7cc18c2dbe8350466c5cb32d385dd0719d7c2903b956140dee4
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1572,3 +1572,43 @@
|
|
| 1572 |
{"current_steps": 7790, "total_steps": 9625, "loss": 0.2042, "lr": 4.272689743928087e-06, "epoch": 5.665696616951619, "percentage": 80.94, "elapsed_time": "4:34:56", "remaining_time": "1:04:45"}
|
| 1573 |
{"current_steps": 7795, "total_steps": 9625, "loss": 0.1954, "lr": 4.250310224635867e-06, "epoch": 5.669334303383049, "percentage": 80.99, "elapsed_time": "4:36:36", "remaining_time": "1:04:56"}
|
| 1574 |
{"current_steps": 7800, "total_steps": 9625, "loss": 0.1948, "lr": 4.2279824988460485e-06, "epoch": 5.672971989814478, "percentage": 81.04, "elapsed_time": "4:38:13", "remaining_time": "1:05:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1572 |
{"current_steps": 7790, "total_steps": 9625, "loss": 0.2042, "lr": 4.272689743928087e-06, "epoch": 5.665696616951619, "percentage": 80.94, "elapsed_time": "4:34:56", "remaining_time": "1:04:45"}
|
| 1573 |
{"current_steps": 7795, "total_steps": 9625, "loss": 0.1954, "lr": 4.250310224635867e-06, "epoch": 5.669334303383049, "percentage": 80.99, "elapsed_time": "4:36:36", "remaining_time": "1:04:56"}
|
| 1574 |
{"current_steps": 7800, "total_steps": 9625, "loss": 0.1948, "lr": 4.2279824988460485e-06, "epoch": 5.672971989814478, "percentage": 81.04, "elapsed_time": "4:38:13", "remaining_time": "1:05:05"}
|
| 1575 |
+
{"current_steps": 7805, "total_steps": 9625, "loss": 0.1938, "lr": 4.205706639984284e-06, "epoch": 5.676609676245907, "percentage": 81.09, "elapsed_time": "4:41:07", "remaining_time": "1:05:33"}
|
| 1576 |
+
{"current_steps": 7810, "total_steps": 9625, "loss": 0.1923, "lr": 4.183482721305641e-06, "epoch": 5.6802473626773375, "percentage": 81.14, "elapsed_time": "4:42:48", "remaining_time": "1:05:43"}
|
| 1577 |
+
{"current_steps": 7815, "total_steps": 9625, "loss": 0.1948, "lr": 4.161310815894397e-06, "epoch": 5.683885049108767, "percentage": 81.19, "elapsed_time": "4:44:26", "remaining_time": "1:05:52"}
|
| 1578 |
+
{"current_steps": 7820, "total_steps": 9625, "loss": 0.1911, "lr": 4.13919099666378e-06, "epoch": 5.687522735540196, "percentage": 81.25, "elapsed_time": "4:46:05", "remaining_time": "1:06:02"}
|
| 1579 |
+
{"current_steps": 7825, "total_steps": 9625, "loss": 0.193, "lr": 4.1171233363557105e-06, "epoch": 5.691160421971626, "percentage": 81.3, "elapsed_time": "4:47:44", "remaining_time": "1:06:11"}
|
| 1580 |
+
{"current_steps": 7830, "total_steps": 9625, "loss": 0.1879, "lr": 4.095107907540612e-06, "epoch": 5.694798108403056, "percentage": 81.35, "elapsed_time": "4:49:25", "remaining_time": "1:06:20"}
|
| 1581 |
+
{"current_steps": 7835, "total_steps": 9625, "loss": 0.1886, "lr": 4.073144782617111e-06, "epoch": 5.698435794834485, "percentage": 81.4, "elapsed_time": "4:51:01", "remaining_time": "1:06:29"}
|
| 1582 |
+
{"current_steps": 7840, "total_steps": 9625, "loss": 0.1888, "lr": 4.051234033811864e-06, "epoch": 5.702073481265915, "percentage": 81.45, "elapsed_time": "4:52:37", "remaining_time": "1:06:37"}
|
| 1583 |
+
{"current_steps": 7845, "total_steps": 9625, "loss": 0.2003, "lr": 4.029375733179259e-06, "epoch": 5.705711167697345, "percentage": 81.51, "elapsed_time": "4:54:13", "remaining_time": "1:06:45"}
|
| 1584 |
+
{"current_steps": 7850, "total_steps": 9625, "loss": 0.192, "lr": 4.007569952601222e-06, "epoch": 5.709348854128774, "percentage": 81.56, "elapsed_time": "4:55:59", "remaining_time": "1:06:55"}
|
| 1585 |
+
{"current_steps": 7855, "total_steps": 9625, "loss": 0.1911, "lr": 3.985816763786952e-06, "epoch": 5.712986540560204, "percentage": 81.61, "elapsed_time": "4:57:39", "remaining_time": "1:07:04"}
|
| 1586 |
+
{"current_steps": 7860, "total_steps": 9625, "loss": 0.1922, "lr": 3.964116238272708e-06, "epoch": 5.716624226991633, "percentage": 81.66, "elapsed_time": "4:59:27", "remaining_time": "1:07:14"}
|
| 1587 |
+
{"current_steps": 7865, "total_steps": 9625, "loss": 0.2, "lr": 3.942468447421568e-06, "epoch": 5.720261913423063, "percentage": 81.71, "elapsed_time": "5:01:06", "remaining_time": "1:07:22"}
|
| 1588 |
+
{"current_steps": 7870, "total_steps": 9625, "loss": 0.1903, "lr": 3.920873462423167e-06, "epoch": 5.723899599854493, "percentage": 81.77, "elapsed_time": "5:02:41", "remaining_time": "1:07:30"}
|
| 1589 |
+
{"current_steps": 7875, "total_steps": 9625, "loss": 0.1878, "lr": 3.899331354293518e-06, "epoch": 5.727537286285922, "percentage": 81.82, "elapsed_time": "5:04:24", "remaining_time": "1:07:38"}
|
| 1590 |
+
{"current_steps": 7880, "total_steps": 9625, "loss": 0.1917, "lr": 3.877842193874714e-06, "epoch": 5.731174972717351, "percentage": 81.87, "elapsed_time": "5:06:04", "remaining_time": "1:07:46"}
|
| 1591 |
+
{"current_steps": 7885, "total_steps": 9625, "loss": 0.1863, "lr": 3.856406051834751e-06, "epoch": 5.734812659148782, "percentage": 81.92, "elapsed_time": "5:07:50", "remaining_time": "1:07:55"}
|
| 1592 |
+
{"current_steps": 7890, "total_steps": 9625, "loss": 0.1872, "lr": 3.835022998667266e-06, "epoch": 5.738450345580211, "percentage": 81.97, "elapsed_time": "5:09:27", "remaining_time": "1:08:02"}
|
| 1593 |
+
{"current_steps": 7895, "total_steps": 9625, "loss": 0.1935, "lr": 3.8136931046912983e-06, "epoch": 5.74208803201164, "percentage": 82.03, "elapsed_time": "5:11:10", "remaining_time": "1:08:11"}
|
| 1594 |
+
{"current_steps": 7900, "total_steps": 9625, "loss": 0.1911, "lr": 3.7924164400510945e-06, "epoch": 5.745725718443071, "percentage": 82.08, "elapsed_time": "5:12:50", "remaining_time": "1:08:18"}
|
| 1595 |
+
{"current_steps": 7905, "total_steps": 9625, "loss": 0.2019, "lr": 3.7711930747158242e-06, "epoch": 5.7493634048745, "percentage": 82.13, "elapsed_time": "5:14:28", "remaining_time": "1:08:25"}
|
| 1596 |
+
{"current_steps": 7910, "total_steps": 9625, "loss": 0.1881, "lr": 3.7500230784794145e-06, "epoch": 5.753001091305929, "percentage": 82.18, "elapsed_time": "5:16:09", "remaining_time": "1:08:32"}
|
| 1597 |
+
{"current_steps": 7915, "total_steps": 9625, "loss": 0.1956, "lr": 3.7289065209602625e-06, "epoch": 5.756638777737359, "percentage": 82.23, "elapsed_time": "5:17:55", "remaining_time": "1:08:41"}
|
| 1598 |
+
{"current_steps": 7920, "total_steps": 9625, "loss": 0.1952, "lr": 3.7078434716010293e-06, "epoch": 5.760276464168789, "percentage": 82.29, "elapsed_time": "5:19:29", "remaining_time": "1:08:46"}
|
| 1599 |
+
{"current_steps": 7925, "total_steps": 9625, "loss": 0.1918, "lr": 3.6868339996684244e-06, "epoch": 5.763914150600218, "percentage": 82.34, "elapsed_time": "5:21:12", "remaining_time": "1:08:54"}
|
| 1600 |
+
{"current_steps": 7930, "total_steps": 9625, "loss": 0.1865, "lr": 3.665878174252957e-06, "epoch": 5.767551837031648, "percentage": 82.39, "elapsed_time": "5:22:52", "remaining_time": "1:09:00"}
|
| 1601 |
+
{"current_steps": 7935, "total_steps": 9625, "loss": 0.1867, "lr": 3.6449760642687303e-06, "epoch": 5.771189523463077, "percentage": 82.44, "elapsed_time": "5:24:31", "remaining_time": "1:09:07"}
|
| 1602 |
+
{"current_steps": 7940, "total_steps": 9625, "loss": 0.1739, "lr": 3.624127738453185e-06, "epoch": 5.774827209894507, "percentage": 82.49, "elapsed_time": "5:26:10", "remaining_time": "1:09:13"}
|
| 1603 |
+
{"current_steps": 7945, "total_steps": 9625, "loss": 0.2056, "lr": 3.6033332653668908e-06, "epoch": 5.778464896325937, "percentage": 82.55, "elapsed_time": "5:27:51", "remaining_time": "1:09:19"}
|
| 1604 |
+
{"current_steps": 7950, "total_steps": 9625, "loss": 0.1896, "lr": 3.5825927133933358e-06, "epoch": 5.782102582757366, "percentage": 82.6, "elapsed_time": "5:29:39", "remaining_time": "1:09:27"}
|
| 1605 |
+
{"current_steps": 7955, "total_steps": 9625, "loss": 0.2015, "lr": 3.5619061507386765e-06, "epoch": 5.785740269188796, "percentage": 82.65, "elapsed_time": "5:31:23", "remaining_time": "1:09:34"}
|
| 1606 |
+
{"current_steps": 7960, "total_steps": 9625, "loss": 0.1945, "lr": 3.541273645431529e-06, "epoch": 5.789377955620226, "percentage": 82.7, "elapsed_time": "5:33:07", "remaining_time": "1:09:40"}
|
| 1607 |
+
{"current_steps": 7965, "total_steps": 9625, "loss": 0.202, "lr": 3.520695265322727e-06, "epoch": 5.793015642051655, "percentage": 82.75, "elapsed_time": "5:34:47", "remaining_time": "1:09:46"}
|
| 1608 |
+
{"current_steps": 7970, "total_steps": 9625, "loss": 0.1931, "lr": 3.5001710780851284e-06, "epoch": 5.796653328483085, "percentage": 82.81, "elapsed_time": "5:36:26", "remaining_time": "1:09:51"}
|
| 1609 |
+
{"current_steps": 7975, "total_steps": 9625, "loss": 0.1865, "lr": 3.4797011512133595e-06, "epoch": 5.800291014914515, "percentage": 82.86, "elapsed_time": "5:38:03", "remaining_time": "1:09:56"}
|
| 1610 |
+
{"current_steps": 7980, "total_steps": 9625, "loss": 0.1842, "lr": 3.4592855520236167e-06, "epoch": 5.803928701345944, "percentage": 82.91, "elapsed_time": "5:39:43", "remaining_time": "1:10:01"}
|
| 1611 |
+
{"current_steps": 7985, "total_steps": 9625, "loss": 0.1839, "lr": 3.438924347653445e-06, "epoch": 5.807566387777373, "percentage": 82.96, "elapsed_time": "5:41:20", "remaining_time": "1:10:06"}
|
| 1612 |
+
{"current_steps": 7990, "total_steps": 9625, "loss": 0.1777, "lr": 3.4186176050614937e-06, "epoch": 5.811204074208804, "percentage": 83.01, "elapsed_time": "5:42:58", "remaining_time": "1:10:11"}
|
| 1613 |
+
{"current_steps": 7995, "total_steps": 9625, "loss": 0.1824, "lr": 3.398365391027323e-06, "epoch": 5.814841760640233, "percentage": 83.06, "elapsed_time": "5:44:42", "remaining_time": "1:10:16"}
|
| 1614 |
+
{"current_steps": 8000, "total_steps": 9625, "loss": 0.1692, "lr": 3.3781677721511773e-06, "epoch": 5.818479447071662, "percentage": 83.12, "elapsed_time": "5:46:17", "remaining_time": "1:10:20"}
|