Training in progress, step 8800
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 sha256:24249bd5018505d6f31ebc8d54ed62b11e1700ba45b8319cd1237bd232648efe
|
| 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:d52c688c2966eac7d584f1973bf1141fa7710bc63ec65ec0ced169384e92b6f7
|
| 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 sha256:21e6b6d45e03747a2721dcf5cf2d7339d4ef5054f952cdffb9fdb3da6c7b894b
|
| 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 sha256:80716570b14205ca8b4a991d3bd43e9a4d7dd7a89cf63fa0606f6067ba11b97c
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1751,3 +1751,43 @@
|
|
| 1751 |
{"current_steps": 8590, "total_steps": 9128, "loss": 0.2121, "lr": 4.233737409312655e-07, "epoch": 6.5884158036056775, "percentage": 94.11, "elapsed_time": "6:14:36", "remaining_time": "0:23:27"}
|
| 1752 |
{"current_steps": 8595, "total_steps": 9128, "loss": 0.2109, "lr": 4.155825635709509e-07, "epoch": 6.592251630226314, "percentage": 94.16, "elapsed_time": "6:16:57", "remaining_time": "0:23:22"}
|
| 1753 |
{"current_steps": 8600, "total_steps": 9128, "loss": 0.2018, "lr": 4.078629898577635e-07, "epoch": 6.59608745684695, "percentage": 94.22, "elapsed_time": "6:19:33", "remaining_time": "0:23:18"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1751 |
{"current_steps": 8590, "total_steps": 9128, "loss": 0.2121, "lr": 4.233737409312655e-07, "epoch": 6.5884158036056775, "percentage": 94.11, "elapsed_time": "6:14:36", "remaining_time": "0:23:27"}
|
| 1752 |
{"current_steps": 8595, "total_steps": 9128, "loss": 0.2109, "lr": 4.155825635709509e-07, "epoch": 6.592251630226314, "percentage": 94.16, "elapsed_time": "6:16:57", "remaining_time": "0:23:22"}
|
| 1753 |
{"current_steps": 8600, "total_steps": 9128, "loss": 0.2018, "lr": 4.078629898577635e-07, "epoch": 6.59608745684695, "percentage": 94.22, "elapsed_time": "6:19:33", "remaining_time": "0:23:18"}
|
| 1754 |
+
{"current_steps": 8605, "total_steps": 9128, "loss": 0.2056, "lr": 4.00215048015653e-07, "epoch": 6.599923283467588, "percentage": 94.27, "elapsed_time": "6:22:51", "remaining_time": "0:23:16"}
|
| 1755 |
+
{"current_steps": 8610, "total_steps": 9128, "loss": 0.1988, "lr": 3.9263876600667216e-07, "epoch": 6.603759110088224, "percentage": 94.33, "elapsed_time": "6:24:47", "remaining_time": "0:23:08"}
|
| 1756 |
+
{"current_steps": 8615, "total_steps": 9128, "loss": 0.1999, "lr": 3.851341715308765e-07, "epoch": 6.6075949367088604, "percentage": 94.38, "elapsed_time": "6:26:30", "remaining_time": "0:23:00"}
|
| 1757 |
+
{"current_steps": 8620, "total_steps": 9128, "loss": 0.1977, "lr": 3.777012920262202e-07, "epoch": 6.611430763329498, "percentage": 94.43, "elapsed_time": "6:28:10", "remaining_time": "0:22:52"}
|
| 1758 |
+
{"current_steps": 8625, "total_steps": 9128, "loss": 0.197, "lr": 3.7034015466845373e-07, "epoch": 6.615266589950134, "percentage": 94.49, "elapsed_time": "6:29:51", "remaining_time": "0:22:44"}
|
| 1759 |
+
{"current_steps": 8630, "total_steps": 9128, "loss": 0.2065, "lr": 3.630507863710309e-07, "epoch": 6.619102416570771, "percentage": 94.54, "elapsed_time": "6:31:28", "remaining_time": "0:22:35"}
|
| 1760 |
+
{"current_steps": 8635, "total_steps": 9128, "loss": 0.2003, "lr": 3.55833213785004e-07, "epoch": 6.622938243191408, "percentage": 94.6, "elapsed_time": "6:33:05", "remaining_time": "0:22:26"}
|
| 1761 |
+
{"current_steps": 8640, "total_steps": 9128, "loss": 0.1971, "lr": 3.486874632989312e-07, "epoch": 6.626774069812044, "percentage": 94.65, "elapsed_time": "6:34:51", "remaining_time": "0:22:18"}
|
| 1762 |
+
{"current_steps": 8645, "total_steps": 9128, "loss": 0.2011, "lr": 3.4161356103877606e-07, "epoch": 6.630609896432682, "percentage": 94.71, "elapsed_time": "6:36:30", "remaining_time": "0:22:09"}
|
| 1763 |
+
{"current_steps": 8650, "total_steps": 9128, "loss": 0.19, "lr": 3.346115328678146e-07, "epoch": 6.634445723053318, "percentage": 94.76, "elapsed_time": "6:38:14", "remaining_time": "0:22:00"}
|
| 1764 |
+
{"current_steps": 8655, "total_steps": 9128, "loss": 0.1819, "lr": 3.2768140438654173e-07, "epoch": 6.6382815496739545, "percentage": 94.82, "elapsed_time": "6:39:55", "remaining_time": "0:21:51"}
|
| 1765 |
+
{"current_steps": 8660, "total_steps": 9128, "loss": 0.1916, "lr": 3.2082320093257623e-07, "epoch": 6.642117376294592, "percentage": 94.87, "elapsed_time": "6:41:35", "remaining_time": "0:21:42"}
|
| 1766 |
+
{"current_steps": 8665, "total_steps": 9128, "loss": 0.1977, "lr": 3.140369475805627e-07, "epoch": 6.645953202915228, "percentage": 94.93, "elapsed_time": "6:43:13", "remaining_time": "0:21:32"}
|
| 1767 |
+
{"current_steps": 8670, "total_steps": 9128, "loss": 0.1939, "lr": 3.0732266914209165e-07, "epoch": 6.649789029535865, "percentage": 94.98, "elapsed_time": "6:44:55", "remaining_time": "0:21:23"}
|
| 1768 |
+
{"current_steps": 8675, "total_steps": 9128, "loss": 0.1917, "lr": 3.006803901655997e-07, "epoch": 6.653624856156502, "percentage": 95.04, "elapsed_time": "6:46:36", "remaining_time": "0:21:13"}
|
| 1769 |
+
{"current_steps": 8680, "total_steps": 9128, "loss": 0.1868, "lr": 2.941101349362785e-07, "epoch": 6.657460682777138, "percentage": 95.09, "elapsed_time": "6:48:15", "remaining_time": "0:21:04"}
|
| 1770 |
+
{"current_steps": 8685, "total_steps": 9128, "loss": 0.199, "lr": 2.8761192747599474e-07, "epoch": 6.661296509397776, "percentage": 95.15, "elapsed_time": "6:49:58", "remaining_time": "0:20:54"}
|
| 1771 |
+
{"current_steps": 8690, "total_steps": 9128, "loss": 0.1842, "lr": 2.8118579154319923e-07, "epoch": 6.665132336018412, "percentage": 95.2, "elapsed_time": "6:51:39", "remaining_time": "0:20:44"}
|
| 1772 |
+
{"current_steps": 8695, "total_steps": 9128, "loss": 0.1898, "lr": 2.748317506328313e-07, "epoch": 6.6689681626390485, "percentage": 95.26, "elapsed_time": "6:53:18", "remaining_time": "0:20:34"}
|
| 1773 |
+
{"current_steps": 8700, "total_steps": 9128, "loss": 0.185, "lr": 2.685498279762433e-07, "epoch": 6.672803989259686, "percentage": 95.31, "elapsed_time": "6:54:57", "remaining_time": "0:20:24"}
|
| 1774 |
+
{"current_steps": 8705, "total_steps": 9128, "loss": 0.1915, "lr": 2.6234004654111854e-07, "epoch": 6.676639815880322, "percentage": 95.37, "elapsed_time": "6:56:41", "remaining_time": "0:20:14"}
|
| 1775 |
+
{"current_steps": 8710, "total_steps": 9128, "loss": 0.1866, "lr": 2.562024290313625e-07, "epoch": 6.680475642500959, "percentage": 95.42, "elapsed_time": "6:58:20", "remaining_time": "0:20:04"}
|
| 1776 |
+
{"current_steps": 8715, "total_steps": 9128, "loss": 0.1936, "lr": 2.501369978870627e-07, "epoch": 6.684311469121596, "percentage": 95.48, "elapsed_time": "6:59:59", "remaining_time": "0:19:54"}
|
| 1777 |
+
{"current_steps": 8720, "total_steps": 9128, "loss": 0.1911, "lr": 2.441437752843623e-07, "epoch": 6.688147295742232, "percentage": 95.53, "elapsed_time": "7:01:34", "remaining_time": "0:19:43"}
|
| 1778 |
+
{"current_steps": 8725, "total_steps": 9128, "loss": 0.1896, "lr": 2.382227831354067e-07, "epoch": 6.691983122362869, "percentage": 95.59, "elapsed_time": "7:03:18", "remaining_time": "0:19:33"}
|
| 1779 |
+
{"current_steps": 8730, "total_steps": 9128, "loss": 0.1876, "lr": 2.323740430882615e-07, "epoch": 6.695818948983506, "percentage": 95.64, "elapsed_time": "7:04:59", "remaining_time": "0:19:22"}
|
| 1780 |
+
{"current_steps": 8735, "total_steps": 9128, "loss": 0.1961, "lr": 2.2659757652681246e-07, "epoch": 6.6996547756041425, "percentage": 95.69, "elapsed_time": "7:06:41", "remaining_time": "0:19:11"}
|
| 1781 |
+
{"current_steps": 8740, "total_steps": 9128, "loss": 0.1888, "lr": 2.2089340457071672e-07, "epoch": 6.70349060222478, "percentage": 95.75, "elapsed_time": "7:08:26", "remaining_time": "0:19:01"}
|
| 1782 |
+
{"current_steps": 8745, "total_steps": 9128, "loss": 0.1813, "lr": 2.152615480753073e-07, "epoch": 6.707326428845416, "percentage": 95.8, "elapsed_time": "7:10:04", "remaining_time": "0:18:50"}
|
| 1783 |
+
{"current_steps": 8750, "total_steps": 9128, "loss": 0.1959, "lr": 2.0970202763151092e-07, "epoch": 6.711162255466053, "percentage": 95.86, "elapsed_time": "7:11:43", "remaining_time": "0:18:39"}
|
| 1784 |
+
{"current_steps": 8755, "total_steps": 9128, "loss": 0.1894, "lr": 2.0421486356579923e-07, "epoch": 6.71499808208669, "percentage": 95.91, "elapsed_time": "7:13:26", "remaining_time": "0:18:28"}
|
| 1785 |
+
{"current_steps": 8760, "total_steps": 9128, "loss": 0.1853, "lr": 1.9880007594008655e-07, "epoch": 6.718833908707326, "percentage": 95.97, "elapsed_time": "7:15:12", "remaining_time": "0:18:16"}
|
| 1786 |
+
{"current_steps": 8765, "total_steps": 9128, "loss": 0.1783, "lr": 1.9345768455167224e-07, "epoch": 6.722669735327964, "percentage": 96.02, "elapsed_time": "7:16:48", "remaining_time": "0:18:05"}
|
| 1787 |
+
{"current_steps": 8770, "total_steps": 9128, "loss": 0.1946, "lr": 1.881877089331563e-07, "epoch": 6.7265055619486, "percentage": 96.08, "elapsed_time": "7:18:29", "remaining_time": "0:17:53"}
|
| 1788 |
+
{"current_steps": 8775, "total_steps": 9128, "loss": 0.1822, "lr": 1.8299016835238826e-07, "epoch": 6.7303413885692365, "percentage": 96.13, "elapsed_time": "7:20:13", "remaining_time": "0:17:42"}
|
| 1789 |
+
{"current_steps": 8780, "total_steps": 9128, "loss": 0.1951, "lr": 1.7786508181237393e-07, "epoch": 6.734177215189874, "percentage": 96.19, "elapsed_time": "7:21:50", "remaining_time": "0:17:30"}
|
| 1790 |
+
{"current_steps": 8785, "total_steps": 9128, "loss": 0.1857, "lr": 1.7281246805121998e-07, "epoch": 6.73801304181051, "percentage": 96.24, "elapsed_time": "7:23:31", "remaining_time": "0:17:19"}
|
| 1791 |
+
{"current_steps": 8790, "total_steps": 9128, "loss": 0.2035, "lr": 1.678323455420605e-07, "epoch": 6.741848868431147, "percentage": 96.3, "elapsed_time": "7:25:15", "remaining_time": "0:17:07"}
|
| 1792 |
+
{"current_steps": 8795, "total_steps": 9128, "loss": 0.1825, "lr": 1.6292473249298833e-07, "epoch": 6.745684695051784, "percentage": 96.35, "elapsed_time": "7:26:55", "remaining_time": "0:16:55"}
|
| 1793 |
+
{"current_steps": 8800, "total_steps": 9128, "loss": 0.1974, "lr": 1.5808964684699723e-07, "epoch": 6.74952052167242, "percentage": 96.41, "elapsed_time": "7:28:37", "remaining_time": "0:16:43"}
|