Training in progress, step 6600
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 sha256:2ec72f45c15ccc06edc9344333cfeefb0b4a14d5cbf94c2300b7f30e55bcf802
|
| 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 sha256:1fc5f072b8a86d51745e69d9f490f4d1155831aa8f4d951c3f85fcd15dd59c8c
|
| 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 sha256:56fc9f2598355a4c26c3c4ee3110b314bc20ac486c103e39277b48ee6f975079
|
| 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 sha256:9b25f6c3ed3e0ba5e3014a0a844371d7f1bed9429d88d638fb298601c2c822df
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1302,3 +1302,43 @@
|
|
| 1302 |
{"current_steps": 6395, "total_steps": 6713, "loss": 0.1826, "lr": 2.745789216426387e-07, "epoch": 6.669796557120501, "percentage": 95.26, "elapsed_time": "1 day, 1:53:18", "remaining_time": "1:17:14"}
|
| 1303 |
{"current_steps": 6400, "total_steps": 6713, "loss": 0.1748, "lr": 2.660578746589515e-07, "epoch": 6.675013041210224, "percentage": 95.34, "elapsed_time": "1 day, 1:54:55", "remaining_time": "1:16:02"}
|
| 1304 |
{"current_steps": 6405, "total_steps": 6713, "loss": 0.1991, "lr": 2.5767025220724717e-07, "epoch": 6.680229525299948, "percentage": 95.41, "elapsed_time": "1 day, 1:58:02", "remaining_time": "1:14:55"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1302 |
{"current_steps": 6395, "total_steps": 6713, "loss": 0.1826, "lr": 2.745789216426387e-07, "epoch": 6.669796557120501, "percentage": 95.26, "elapsed_time": "1 day, 1:53:18", "remaining_time": "1:17:14"}
|
| 1303 |
{"current_steps": 6400, "total_steps": 6713, "loss": 0.1748, "lr": 2.660578746589515e-07, "epoch": 6.675013041210224, "percentage": 95.34, "elapsed_time": "1 day, 1:54:55", "remaining_time": "1:16:02"}
|
| 1304 |
{"current_steps": 6405, "total_steps": 6713, "loss": 0.1991, "lr": 2.5767025220724717e-07, "epoch": 6.680229525299948, "percentage": 95.41, "elapsed_time": "1 day, 1:58:02", "remaining_time": "1:14:55"}
|
| 1305 |
+
{"current_steps": 6410, "total_steps": 6713, "loss": 0.1886, "lr": 2.4941611099766896e-07, "epoch": 6.685446009389671, "percentage": 95.49, "elapsed_time": "1 day, 1:59:46", "remaining_time": "1:13:43"}
|
| 1306 |
+
{"current_steps": 6415, "total_steps": 6713, "loss": 0.1959, "lr": 2.4129550683786194e-07, "epoch": 6.690662493479395, "percentage": 95.56, "elapsed_time": "1 day, 2:01:37", "remaining_time": "1:12:32"}
|
| 1307 |
+
{"current_steps": 6420, "total_steps": 6713, "loss": 0.1908, "lr": 2.3330849463261363e-07, "epoch": 6.6958789775691185, "percentage": 95.64, "elapsed_time": "1 day, 2:03:18", "remaining_time": "1:11:20"}
|
| 1308 |
+
{"current_steps": 6425, "total_steps": 6713, "loss": 0.1963, "lr": 2.2545512838346716e-07, "epoch": 6.701095461658842, "percentage": 95.71, "elapsed_time": "1 day, 2:05:01", "remaining_time": "1:10:09"}
|
| 1309 |
+
{"current_steps": 6430, "total_steps": 6713, "loss": 0.1905, "lr": 2.1773546118836418e-07, "epoch": 6.706311945748565, "percentage": 95.78, "elapsed_time": "1 day, 2:06:41", "remaining_time": "1:08:57"}
|
| 1310 |
+
{"current_steps": 6435, "total_steps": 6713, "loss": 0.1873, "lr": 2.1014954524128493e-07, "epoch": 6.711528429838289, "percentage": 95.86, "elapsed_time": "1 day, 2:08:20", "remaining_time": "1:07:45"}
|
| 1311 |
+
{"current_steps": 6440, "total_steps": 6713, "loss": 0.1856, "lr": 2.0269743183189528e-07, "epoch": 6.716744913928013, "percentage": 95.93, "elapsed_time": "1 day, 2:10:04", "remaining_time": "1:06:33"}
|
| 1312 |
+
{"current_steps": 6445, "total_steps": 6713, "loss": 0.1817, "lr": 1.9537917134520023e-07, "epoch": 6.721961398017736, "percentage": 96.01, "elapsed_time": "1 day, 2:11:43", "remaining_time": "1:05:21"}
|
| 1313 |
+
{"current_steps": 6450, "total_steps": 6713, "loss": 0.1782, "lr": 1.881948132611977e-07, "epoch": 6.727177882107459, "percentage": 96.08, "elapsed_time": "1 day, 2:13:19", "remaining_time": "1:04:09"}
|
| 1314 |
+
{"current_steps": 6455, "total_steps": 6713, "loss": 0.1785, "lr": 1.811444061545542e-07, "epoch": 6.732394366197183, "percentage": 96.16, "elapsed_time": "1 day, 2:15:01", "remaining_time": "1:02:57"}
|
| 1315 |
+
{"current_steps": 6460, "total_steps": 6713, "loss": 0.172, "lr": 1.7422799769426736e-07, "epoch": 6.737610850286907, "percentage": 96.23, "elapsed_time": "1 day, 2:16:39", "remaining_time": "1:01:44"}
|
| 1316 |
+
{"current_steps": 6465, "total_steps": 6713, "loss": 0.1757, "lr": 1.674456346433506e-07, "epoch": 6.7428273343766305, "percentage": 96.31, "elapsed_time": "1 day, 2:18:18", "remaining_time": "1:00:32"}
|
| 1317 |
+
{"current_steps": 6470, "total_steps": 6713, "loss": 0.1975, "lr": 1.607973628585091e-07, "epoch": 6.748043818466353, "percentage": 96.38, "elapsed_time": "1 day, 2:19:55", "remaining_time": "0:59:20"}
|
| 1318 |
+
{"current_steps": 6475, "total_steps": 6713, "loss": 0.1913, "lr": 1.542832272898398e-07, "epoch": 6.753260302556077, "percentage": 96.45, "elapsed_time": "1 day, 2:21:35", "remaining_time": "0:58:08"}
|
| 1319 |
+
{"current_steps": 6480, "total_steps": 6713, "loss": 0.1843, "lr": 1.4790327198051624e-07, "epoch": 6.758476786645801, "percentage": 96.53, "elapsed_time": "1 day, 2:23:13", "remaining_time": "0:56:55"}
|
| 1320 |
+
{"current_steps": 6485, "total_steps": 6713, "loss": 0.193, "lr": 1.416575400664999e-07, "epoch": 6.763693270735525, "percentage": 96.6, "elapsed_time": "1 day, 2:24:53", "remaining_time": "0:55:43"}
|
| 1321 |
+
{"current_steps": 6490, "total_steps": 6713, "loss": 0.1845, "lr": 1.3554607377624263e-07, "epoch": 6.7689097548252475, "percentage": 96.68, "elapsed_time": "1 day, 2:26:39", "remaining_time": "0:54:31"}
|
| 1322 |
+
{"current_steps": 6495, "total_steps": 6713, "loss": 0.1814, "lr": 1.295689144304091e-07, "epoch": 6.774126238914971, "percentage": 96.75, "elapsed_time": "1 day, 2:28:24", "remaining_time": "0:53:18"}
|
| 1323 |
+
{"current_steps": 6500, "total_steps": 6713, "loss": 0.1837, "lr": 1.237261024415881e-07, "epoch": 6.779342723004695, "percentage": 96.83, "elapsed_time": "1 day, 2:30:07", "remaining_time": "0:52:06"}
|
| 1324 |
+
{"current_steps": 6505, "total_steps": 6713, "loss": 0.1862, "lr": 1.1801767731401958e-07, "epoch": 6.784559207094419, "percentage": 96.9, "elapsed_time": "1 day, 2:31:49", "remaining_time": "0:50:53"}
|
| 1325 |
+
{"current_steps": 6510, "total_steps": 6713, "loss": 0.1836, "lr": 1.1244367764333464e-07, "epoch": 6.789775691184142, "percentage": 96.98, "elapsed_time": "1 day, 2:33:28", "remaining_time": "0:49:41"}
|
| 1326 |
+
{"current_steps": 6515, "total_steps": 6713, "loss": 0.1797, "lr": 1.0700414111629365e-07, "epoch": 6.794992175273865, "percentage": 97.05, "elapsed_time": "1 day, 2:35:07", "remaining_time": "0:48:28"}
|
| 1327 |
+
{"current_steps": 6520, "total_steps": 6713, "loss": 0.1962, "lr": 1.0169910451052422e-07, "epoch": 6.800208659363589, "percentage": 97.12, "elapsed_time": "1 day, 2:36:51", "remaining_time": "0:47:16"}
|
| 1328 |
+
{"current_steps": 6525, "total_steps": 6713, "loss": 0.1974, "lr": 9.652860369428141e-08, "epoch": 6.805425143453313, "percentage": 97.2, "elapsed_time": "1 day, 2:38:30", "remaining_time": "0:46:03"}
|
| 1329 |
+
{"current_steps": 6530, "total_steps": 6713, "loss": 0.1923, "lr": 9.149267362619895e-08, "epoch": 6.810641627543036, "percentage": 97.27, "elapsed_time": "1 day, 2:40:10", "remaining_time": "0:44:50"}
|
| 1330 |
+
{"current_steps": 6535, "total_steps": 6713, "loss": 0.2001, "lr": 8.659134835504956e-08, "epoch": 6.8158581116327595, "percentage": 97.35, "elapsed_time": "1 day, 2:41:47", "remaining_time": "0:43:37"}
|
| 1331 |
+
{"current_steps": 6540, "total_steps": 6713, "loss": 0.1904, "lr": 8.18246610195339e-08, "epoch": 6.821074595722483, "percentage": 97.42, "elapsed_time": "1 day, 2:43:26", "remaining_time": "0:42:24"}
|
| 1332 |
+
{"current_steps": 6545, "total_steps": 6713, "loss": 0.2042, "lr": 7.719264384802527e-08, "epoch": 6.826291079812207, "percentage": 97.5, "elapsed_time": "1 day, 2:45:11", "remaining_time": "0:41:12"}
|
| 1333 |
+
{"current_steps": 6550, "total_steps": 6713, "loss": 0.2007, "lr": 7.269532815838532e-08, "epoch": 6.83150756390193, "percentage": 97.57, "elapsed_time": "1 day, 2:46:50", "remaining_time": "0:39:59"}
|
| 1334 |
+
{"current_steps": 6555, "total_steps": 6713, "loss": 0.1914, "lr": 6.833274435772196e-08, "epoch": 6.836724047991654, "percentage": 97.65, "elapsed_time": "1 day, 2:48:35", "remaining_time": "0:38:46"}
|
| 1335 |
+
{"current_steps": 6560, "total_steps": 6713, "loss": 0.1929, "lr": 6.410492194220963e-08, "epoch": 6.841940532081377, "percentage": 97.72, "elapsed_time": "1 day, 2:50:15", "remaining_time": "0:37:33"}
|
| 1336 |
+
{"current_steps": 6565, "total_steps": 6713, "loss": 0.1907, "lr": 6.001188949687153e-08, "epoch": 6.847157016171101, "percentage": 97.8, "elapsed_time": "1 day, 2:51:55", "remaining_time": "0:36:20"}
|
| 1337 |
+
{"current_steps": 6570, "total_steps": 6713, "loss": 0.1942, "lr": 5.6053674695395463e-08, "epoch": 6.852373500260824, "percentage": 97.87, "elapsed_time": "1 day, 2:53:31", "remaining_time": "0:35:07"}
|
| 1338 |
+
{"current_steps": 6575, "total_steps": 6713, "loss": 0.1936, "lr": 5.22303042999428e-08, "epoch": 6.857589984350548, "percentage": 97.94, "elapsed_time": "1 day, 2:55:11", "remaining_time": "0:33:54"}
|
| 1339 |
+
{"current_steps": 6580, "total_steps": 6713, "loss": 0.1799, "lr": 4.8541804160968655e-08, "epoch": 6.862806468440271, "percentage": 98.02, "elapsed_time": "1 day, 2:56:56", "remaining_time": "0:32:40"}
|
| 1340 |
+
{"current_steps": 6585, "total_steps": 6713, "loss": 0.1923, "lr": 4.498819921705089e-08, "epoch": 6.868022952529994, "percentage": 98.09, "elapsed_time": "1 day, 2:58:39", "remaining_time": "0:31:27"}
|
| 1341 |
+
{"current_steps": 6590, "total_steps": 6713, "loss": 0.1817, "lr": 4.15695134947125e-08, "epoch": 6.873239436619718, "percentage": 98.17, "elapsed_time": "1 day, 3:00:21", "remaining_time": "0:30:14"}
|
| 1342 |
+
{"current_steps": 6595, "total_steps": 6713, "loss": 0.1975, "lr": 3.8285770108272836e-08, "epoch": 6.878455920709442, "percentage": 98.24, "elapsed_time": "1 day, 3:02:01", "remaining_time": "0:29:01"}
|
| 1343 |
+
{"current_steps": 6600, "total_steps": 6713, "loss": 0.1922, "lr": 3.5136991259672183e-08, "epoch": 6.8836724047991655, "percentage": 98.32, "elapsed_time": "1 day, 3:03:43", "remaining_time": "0:27:48"}
|
| 1344 |
+
{"current_steps": 6605, "total_steps": 6713, "loss": 0.1966, "lr": 3.212319823834298e-08, "epoch": 6.888888888888889, "percentage": 98.39, "elapsed_time": "1 day, 3:06:45", "remaining_time": "0:26:35"}
|