Training in progress, step 9000
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 sha256:070c70fc2e45e02a25d986716b72127ce31f78801612a52ee985ebfae64a960c
|
| 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 sha256:39dac758e86d20841080c7bdfaa03fd7ac1039bc55eea02480fde0870d8b380c
|
| 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:fb072b31c89244d587b364531d7c9bebfe4777308d3b349072b5dca53646b79b
|
| 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 sha256:4a7607f72b45bd8744097a5c75c11f727570a06a3cd0bea8e9935d391f60602b
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1791,3 +1791,46 @@
|
|
| 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"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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"}
|
| 1794 |
+
{"current_steps": 8805, "total_steps": 9128, "loss": 0.1829, "lr": 1.5332710628190196e-07, "epoch": 6.753356348293057, "percentage": 96.46, "elapsed_time": "7:31:33", "remaining_time": "0:16:33"}
|
| 1795 |
+
{"current_steps": 8810, "total_steps": 9128, "loss": 0.1827, "lr": 1.4863712821028498e-07, "epoch": 6.757192174913694, "percentage": 96.52, "elapsed_time": "7:33:15", "remaining_time": "0:16:21"}
|
| 1796 |
+
{"current_steps": 8815, "total_steps": 9128, "loss": 0.1746, "lr": 1.440197297794299e-07, "epoch": 6.7610280015343305, "percentage": 96.57, "elapsed_time": "7:34:52", "remaining_time": "0:16:09"}
|
| 1797 |
+
{"current_steps": 8820, "total_steps": 9128, "loss": 0.1985, "lr": 1.3947492787125483e-07, "epoch": 6.764863828154967, "percentage": 96.63, "elapsed_time": "7:36:38", "remaining_time": "0:15:56"}
|
| 1798 |
+
{"current_steps": 8825, "total_steps": 9128, "loss": 0.1884, "lr": 1.350027391022568e-07, "epoch": 6.768699654775604, "percentage": 96.68, "elapsed_time": "7:38:22", "remaining_time": "0:15:44"}
|
| 1799 |
+
{"current_steps": 8830, "total_steps": 9128, "loss": 0.1982, "lr": 1.306031798234475e-07, "epoch": 6.772535481396241, "percentage": 96.74, "elapsed_time": "7:40:14", "remaining_time": "0:15:31"}
|
| 1800 |
+
{"current_steps": 8835, "total_steps": 9128, "loss": 0.189, "lr": 1.262762661202932e-07, "epoch": 6.776371308016878, "percentage": 96.79, "elapsed_time": "7:41:56", "remaining_time": "0:15:19"}
|
| 1801 |
+
{"current_steps": 8840, "total_steps": 9128, "loss": 0.1963, "lr": 1.2202201381265487e-07, "epoch": 6.780207134637514, "percentage": 96.84, "elapsed_time": "7:43:39", "remaining_time": "0:15:06"}
|
| 1802 |
+
{"current_steps": 8845, "total_steps": 9128, "loss": 0.1925, "lr": 1.1784043845473714e-07, "epoch": 6.784042961258151, "percentage": 96.9, "elapsed_time": "7:45:21", "remaining_time": "0:14:53"}
|
| 1803 |
+
{"current_steps": 8850, "total_steps": 9128, "loss": 0.1876, "lr": 1.1373155533502156e-07, "epoch": 6.787878787878788, "percentage": 96.95, "elapsed_time": "7:47:00", "remaining_time": "0:14:40"}
|
| 1804 |
+
{"current_steps": 8855, "total_steps": 9128, "loss": 0.185, "lr": 1.0969537947621789e-07, "epoch": 6.7917146144994245, "percentage": 97.01, "elapsed_time": "7:48:44", "remaining_time": "0:14:27"}
|
| 1805 |
+
{"current_steps": 8860, "total_steps": 9128, "loss": 0.1809, "lr": 1.0573192563520851e-07, "epoch": 6.795550441120062, "percentage": 97.06, "elapsed_time": "7:50:24", "remaining_time": "0:14:13"}
|
| 1806 |
+
{"current_steps": 8865, "total_steps": 9128, "loss": 0.18, "lr": 1.0184120830299072e-07, "epoch": 6.799386267740698, "percentage": 97.12, "elapsed_time": "7:52:02", "remaining_time": "0:14:00"}
|
| 1807 |
+
{"current_steps": 8870, "total_steps": 9128, "loss": 0.1787, "lr": 9.80232417046234e-08, "epoch": 6.803222094361335, "percentage": 97.17, "elapsed_time": "7:53:46", "remaining_time": "0:13:46"}
|
| 1808 |
+
{"current_steps": 8875, "total_steps": 9128, "loss": 0.1705, "lr": 9.427803979918715e-08, "epoch": 6.807057920981972, "percentage": 97.23, "elapsed_time": "7:55:25", "remaining_time": "0:13:33"}
|
| 1809 |
+
{"current_steps": 8880, "total_steps": 9128, "loss": 0.1779, "lr": 9.060561627971087e-08, "epoch": 6.810893747602608, "percentage": 97.28, "elapsed_time": "7:57:06", "remaining_time": "0:13:19"}
|
| 1810 |
+
{"current_steps": 8885, "total_steps": 9128, "loss": 0.198, "lr": 8.700598457314302e-08, "epoch": 6.814729574223245, "percentage": 97.34, "elapsed_time": "7:58:43", "remaining_time": "0:13:05"}
|
| 1811 |
+
{"current_steps": 8890, "total_steps": 9128, "loss": 0.1899, "lr": 8.347915784029159e-08, "epoch": 6.818565400843882, "percentage": 97.39, "elapsed_time": "8:00:25", "remaining_time": "0:12:51"}
|
| 1812 |
+
{"current_steps": 8895, "total_steps": 9128, "loss": 0.1863, "lr": 8.002514897577973e-08, "epoch": 6.8224012274645185, "percentage": 97.45, "elapsed_time": "8:02:04", "remaining_time": "0:12:37"}
|
| 1813 |
+
{"current_steps": 8900, "total_steps": 9128, "loss": 0.1895, "lr": 7.664397060799467e-08, "epoch": 6.826237054085155, "percentage": 97.5, "elapsed_time": "8:03:45", "remaining_time": "0:12:23"}
|
| 1814 |
+
{"current_steps": 8905, "total_steps": 9128, "loss": 0.1881, "lr": 7.333563509904329e-08, "epoch": 6.830072880705792, "percentage": 97.56, "elapsed_time": "8:05:29", "remaining_time": "0:12:09"}
|
| 1815 |
+
{"current_steps": 8910, "total_steps": 9128, "loss": 0.1815, "lr": 7.01001545447122e-08, "epoch": 6.833908707326429, "percentage": 97.61, "elapsed_time": "8:07:15", "remaining_time": "0:11:55"}
|
| 1816 |
+
{"current_steps": 8915, "total_steps": 9128, "loss": 0.1852, "lr": 6.693754077441882e-08, "epoch": 6.837744533947066, "percentage": 97.67, "elapsed_time": "8:08:58", "remaining_time": "0:11:40"}
|
| 1817 |
+
{"current_steps": 8920, "total_steps": 9128, "loss": 0.1854, "lr": 6.384780535116264e-08, "epoch": 6.841580360567702, "percentage": 97.72, "elapsed_time": "8:10:40", "remaining_time": "0:11:26"}
|
| 1818 |
+
{"current_steps": 8925, "total_steps": 9128, "loss": 0.184, "lr": 6.083095957149176e-08, "epoch": 6.845416187188339, "percentage": 97.78, "elapsed_time": "8:12:21", "remaining_time": "0:11:11"}
|
| 1819 |
+
{"current_steps": 8930, "total_steps": 9128, "loss": 0.1777, "lr": 5.788701446546308e-08, "epoch": 6.849252013808976, "percentage": 97.83, "elapsed_time": "8:14:01", "remaining_time": "0:10:57"}
|
| 1820 |
+
{"current_steps": 8935, "total_steps": 9128, "loss": 0.1998, "lr": 5.50159807965911e-08, "epoch": 6.8530878404296125, "percentage": 97.89, "elapsed_time": "8:15:44", "remaining_time": "0:10:42"}
|
| 1821 |
+
{"current_steps": 8940, "total_steps": 9128, "loss": 0.1959, "lr": 5.2217869061816914e-08, "epoch": 6.85692366705025, "percentage": 97.94, "elapsed_time": "8:17:24", "remaining_time": "0:10:27"}
|
| 1822 |
+
{"current_steps": 8945, "total_steps": 9128, "loss": 0.1927, "lr": 4.949268949146824e-08, "epoch": 6.860759493670886, "percentage": 98.0, "elapsed_time": "8:19:06", "remaining_time": "0:10:12"}
|
| 1823 |
+
{"current_steps": 8950, "total_steps": 9128, "loss": 0.1998, "lr": 4.684045204922161e-08, "epoch": 6.864595320291523, "percentage": 98.05, "elapsed_time": "8:20:42", "remaining_time": "0:09:57"}
|
| 1824 |
+
{"current_steps": 8955, "total_steps": 9128, "loss": 0.1923, "lr": 4.42611664320669e-08, "epoch": 6.86843114691216, "percentage": 98.1, "elapsed_time": "8:22:20", "remaining_time": "0:09:42"}
|
| 1825 |
+
{"current_steps": 8960, "total_steps": 9128, "loss": 0.2047, "lr": 4.1754842070269584e-08, "epoch": 6.872266973532796, "percentage": 98.16, "elapsed_time": "8:24:05", "remaining_time": "0:09:27"}
|
| 1826 |
+
{"current_steps": 8965, "total_steps": 9128, "loss": 0.1998, "lr": 3.932148812733516e-08, "epoch": 6.876102800153433, "percentage": 98.21, "elapsed_time": "8:25:43", "remaining_time": "0:09:11"}
|
| 1827 |
+
{"current_steps": 8970, "total_steps": 9128, "loss": 0.1976, "lr": 3.696111349998255e-08, "epoch": 6.87993862677407, "percentage": 98.27, "elapsed_time": "8:27:31", "remaining_time": "0:08:56"}
|
| 1828 |
+
{"current_steps": 8975, "total_steps": 9128, "loss": 0.1912, "lr": 3.4673726818101884e-08, "epoch": 6.8837744533947065, "percentage": 98.32, "elapsed_time": "8:29:12", "remaining_time": "0:08:40"}
|
| 1829 |
+
{"current_steps": 8980, "total_steps": 9128, "loss": 0.1933, "lr": 3.2459336444736754e-08, "epoch": 6.887610280015343, "percentage": 98.38, "elapsed_time": "8:30:51", "remaining_time": "0:08:25"}
|
| 1830 |
+
{"current_steps": 8985, "total_steps": 9128, "loss": 0.1982, "lr": 3.031795047603536e-08, "epoch": 6.89144610663598, "percentage": 98.43, "elapsed_time": "8:32:26", "remaining_time": "0:08:09"}
|
| 1831 |
+
{"current_steps": 8990, "total_steps": 9128, "loss": 0.1961, "lr": 2.8249576741234964e-08, "epoch": 6.895281933256617, "percentage": 98.49, "elapsed_time": "8:34:06", "remaining_time": "0:07:53"}
|
| 1832 |
+
{"current_steps": 8995, "total_steps": 9128, "loss": 0.1779, "lr": 2.625422280263079e-08, "epoch": 6.899117759877253, "percentage": 98.54, "elapsed_time": "8:35:52", "remaining_time": "0:07:37"}
|
| 1833 |
+
{"current_steps": 9000, "total_steps": 9128, "loss": 0.1936, "lr": 2.433189595554275e-08, "epoch": 6.90295358649789, "percentage": 98.6, "elapsed_time": "8:37:36", "remaining_time": "0:07:21"}
|
| 1834 |
+
{"current_steps": 9005, "total_steps": 9128, "loss": 0.1847, "lr": 2.248260322829543e-08, "epoch": 6.906789413118527, "percentage": 98.65, "elapsed_time": "8:40:30", "remaining_time": "0:07:06"}
|
| 1835 |
+
{"current_steps": 9010, "total_steps": 9128, "loss": 0.1961, "lr": 2.0706351382184796e-08, "epoch": 6.910625239739164, "percentage": 98.71, "elapsed_time": "8:42:11", "remaining_time": "0:06:50"}
|
| 1836 |
+
{"current_steps": 9015, "total_steps": 9128, "loss": 0.1939, "lr": 1.9003146911462656e-08, "epoch": 6.9144610663598005, "percentage": 98.76, "elapsed_time": "8:43:53", "remaining_time": "0:06:34"}
|