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 sha256:0046655427449842b6178310dee1432111e03520a5c1b66aafcb398a426b878d
|
| 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 sha256:23a43c2521ef7747ac6dd404874c88514485bfb6f34ed22e3c31d4159ea380cd
|
| 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:ded39634aed615d1e2161e3e397b4e6942338471fefe129f834fb44c1f027b08
|
| 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 sha256:6a473c085e4194795bf775e27646cce6030e60f436fd97cfe827471710cf4e35
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1279,3 +1279,45 @@
|
|
| 1279 |
{"current_steps": 6395, "total_steps": 6713, "loss": 0.1633, "lr": 2.745789216426387e-07, "epoch": 6.669796557120501, "percentage": 95.26, "elapsed_time": "1 day, 11:01:44", "remaining_time": "1:44:30"}
|
| 1280 |
{"current_steps": 6400, "total_steps": 6713, "loss": 0.1677, "lr": 2.660578746589515e-07, "epoch": 6.675013041210224, "percentage": 95.34, "elapsed_time": "1 day, 11:04:29", "remaining_time": "1:42:55"}
|
| 1281 |
{"current_steps": 6405, "total_steps": 6713, "loss": 0.1833, "lr": 2.5767025220724717e-07, "epoch": 6.680229525299948, "percentage": 95.41, "elapsed_time": "1 day, 11:08:17", "remaining_time": "1:41:22"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1279 |
{"current_steps": 6395, "total_steps": 6713, "loss": 0.1633, "lr": 2.745789216426387e-07, "epoch": 6.669796557120501, "percentage": 95.26, "elapsed_time": "1 day, 11:01:44", "remaining_time": "1:44:30"}
|
| 1280 |
{"current_steps": 6400, "total_steps": 6713, "loss": 0.1677, "lr": 2.660578746589515e-07, "epoch": 6.675013041210224, "percentage": 95.34, "elapsed_time": "1 day, 11:04:29", "remaining_time": "1:42:55"}
|
| 1281 |
{"current_steps": 6405, "total_steps": 6713, "loss": 0.1833, "lr": 2.5767025220724717e-07, "epoch": 6.680229525299948, "percentage": 95.41, "elapsed_time": "1 day, 11:08:17", "remaining_time": "1:41:22"}
|
| 1282 |
+
{"current_steps": 6410, "total_steps": 6713, "loss": 0.1701, "lr": 2.4941611099766896e-07, "epoch": 6.685446009389671, "percentage": 95.49, "elapsed_time": "1 day, 11:10:46", "remaining_time": "1:39:46"}
|
| 1283 |
+
{"current_steps": 6415, "total_steps": 6713, "loss": 0.1656, "lr": 2.4129550683786194e-07, "epoch": 6.690662493479395, "percentage": 95.56, "elapsed_time": "1 day, 11:13:33", "remaining_time": "1:38:10"}
|
| 1284 |
+
{"current_steps": 6420, "total_steps": 6713, "loss": 0.1746, "lr": 2.3330849463261363e-07, "epoch": 6.6958789775691185, "percentage": 95.64, "elapsed_time": "1 day, 11:16:10", "remaining_time": "1:36:34"}
|
| 1285 |
+
{"current_steps": 6425, "total_steps": 6713, "loss": 0.158, "lr": 2.2545512838346716e-07, "epoch": 6.701095461658842, "percentage": 95.71, "elapsed_time": "1 day, 11:18:55", "remaining_time": "1:34:58"}
|
| 1286 |
+
{"current_steps": 6430, "total_steps": 6713, "loss": 0.1718, "lr": 2.1773546118836418e-07, "epoch": 6.706311945748565, "percentage": 95.78, "elapsed_time": "1 day, 11:21:24", "remaining_time": "1:33:22"}
|
| 1287 |
+
{"current_steps": 6435, "total_steps": 6713, "loss": 0.173, "lr": 2.1014954524128493e-07, "epoch": 6.711528429838289, "percentage": 95.86, "elapsed_time": "1 day, 11:24:04", "remaining_time": "1:31:45"}
|
| 1288 |
+
{"current_steps": 6440, "total_steps": 6713, "loss": 0.1703, "lr": 2.0269743183189528e-07, "epoch": 6.716744913928013, "percentage": 95.93, "elapsed_time": "1 day, 11:26:52", "remaining_time": "1:30:09"}
|
| 1289 |
+
{"current_steps": 6445, "total_steps": 6713, "loss": 0.168, "lr": 1.9537917134520023e-07, "epoch": 6.721961398017736, "percentage": 96.01, "elapsed_time": "1 day, 11:29:39", "remaining_time": "1:28:33"}
|
| 1290 |
+
{"current_steps": 6450, "total_steps": 6713, "loss": 0.1608, "lr": 1.881948132611977e-07, "epoch": 6.727177882107459, "percentage": 96.08, "elapsed_time": "1 day, 11:32:33", "remaining_time": "1:26:57"}
|
| 1291 |
+
{"current_steps": 6455, "total_steps": 6713, "loss": 0.166, "lr": 1.811444061545542e-07, "epoch": 6.732394366197183, "percentage": 96.16, "elapsed_time": "1 day, 11:35:22", "remaining_time": "1:25:20"}
|
| 1292 |
+
{"current_steps": 6460, "total_steps": 6713, "loss": 0.1911, "lr": 1.7422799769426736e-07, "epoch": 6.737610850286907, "percentage": 96.23, "elapsed_time": "1 day, 11:38:06", "remaining_time": "1:23:44"}
|
| 1293 |
+
{"current_steps": 6465, "total_steps": 6713, "loss": 0.1716, "lr": 1.674456346433506e-07, "epoch": 6.7428273343766305, "percentage": 96.31, "elapsed_time": "1 day, 11:41:03", "remaining_time": "1:22:07"}
|
| 1294 |
+
{"current_steps": 6470, "total_steps": 6713, "loss": 0.157, "lr": 1.607973628585091e-07, "epoch": 6.748043818466353, "percentage": 96.38, "elapsed_time": "1 day, 11:44:01", "remaining_time": "1:20:31"}
|
| 1295 |
+
{"current_steps": 6475, "total_steps": 6713, "loss": 0.1771, "lr": 1.542832272898398e-07, "epoch": 6.753260302556077, "percentage": 96.45, "elapsed_time": "1 day, 11:46:43", "remaining_time": "1:18:54"}
|
| 1296 |
+
{"current_steps": 6480, "total_steps": 6713, "loss": 0.1677, "lr": 1.4790327198051624e-07, "epoch": 6.758476786645801, "percentage": 96.53, "elapsed_time": "1 day, 11:49:32", "remaining_time": "1:17:17"}
|
| 1297 |
+
{"current_steps": 6485, "total_steps": 6713, "loss": 0.159, "lr": 1.416575400664999e-07, "epoch": 6.763693270735525, "percentage": 96.6, "elapsed_time": "1 day, 11:52:19", "remaining_time": "1:15:40"}
|
| 1298 |
+
{"current_steps": 6490, "total_steps": 6713, "loss": 0.1651, "lr": 1.3554607377624263e-07, "epoch": 6.7689097548252475, "percentage": 96.68, "elapsed_time": "1 day, 11:55:01", "remaining_time": "1:14:02"}
|
| 1299 |
+
{"current_steps": 6495, "total_steps": 6713, "loss": 0.1626, "lr": 1.295689144304091e-07, "epoch": 6.774126238914971, "percentage": 96.75, "elapsed_time": "1 day, 11:57:48", "remaining_time": "1:12:25"}
|
| 1300 |
+
{"current_steps": 6500, "total_steps": 6713, "loss": 0.1737, "lr": 1.237261024415881e-07, "epoch": 6.779342723004695, "percentage": 96.83, "elapsed_time": "1 day, 12:00:45", "remaining_time": "1:10:48"}
|
| 1301 |
+
{"current_steps": 6505, "total_steps": 6713, "loss": 0.1673, "lr": 1.1801767731401958e-07, "epoch": 6.784559207094419, "percentage": 96.9, "elapsed_time": "1 day, 12:03:25", "remaining_time": "1:09:10"}
|
| 1302 |
+
{"current_steps": 6510, "total_steps": 6713, "loss": 0.1791, "lr": 1.1244367764333464e-07, "epoch": 6.789775691184142, "percentage": 96.98, "elapsed_time": "1 day, 12:06:02", "remaining_time": "1:07:32"}
|
| 1303 |
+
{"current_steps": 6515, "total_steps": 6713, "loss": 0.1649, "lr": 1.0700414111629365e-07, "epoch": 6.794992175273865, "percentage": 97.05, "elapsed_time": "1 day, 12:08:57", "remaining_time": "1:05:55"}
|
| 1304 |
+
{"current_steps": 6520, "total_steps": 6713, "loss": 0.1656, "lr": 1.0169910451052422e-07, "epoch": 6.800208659363589, "percentage": 97.12, "elapsed_time": "1 day, 12:11:54", "remaining_time": "1:04:17"}
|
| 1305 |
+
{"current_steps": 6525, "total_steps": 6713, "loss": 0.1725, "lr": 9.652860369428141e-08, "epoch": 6.805425143453313, "percentage": 97.2, "elapsed_time": "1 day, 12:14:40", "remaining_time": "1:02:39"}
|
| 1306 |
+
{"current_steps": 6530, "total_steps": 6713, "loss": 0.1673, "lr": 9.149267362619895e-08, "epoch": 6.810641627543036, "percentage": 97.27, "elapsed_time": "1 day, 12:17:34", "remaining_time": "1:01:01"}
|
| 1307 |
+
{"current_steps": 6535, "total_steps": 6713, "loss": 0.1841, "lr": 8.659134835504956e-08, "epoch": 6.8158581116327595, "percentage": 97.35, "elapsed_time": "1 day, 12:20:08", "remaining_time": "0:59:22"}
|
| 1308 |
+
{"current_steps": 6540, "total_steps": 6713, "loss": 0.1597, "lr": 8.18246610195339e-08, "epoch": 6.821074595722483, "percentage": 97.42, "elapsed_time": "1 day, 12:22:54", "remaining_time": "0:57:44"}
|
| 1309 |
+
{"current_steps": 6545, "total_steps": 6713, "loss": 0.1574, "lr": 7.719264384802527e-08, "epoch": 6.826291079812207, "percentage": 97.5, "elapsed_time": "1 day, 12:25:49", "remaining_time": "0:56:06"}
|
| 1310 |
+
{"current_steps": 6550, "total_steps": 6713, "loss": 0.1863, "lr": 7.269532815838532e-08, "epoch": 6.83150756390193, "percentage": 97.57, "elapsed_time": "1 day, 12:28:42", "remaining_time": "0:54:28"}
|
| 1311 |
+
{"current_steps": 6555, "total_steps": 6713, "loss": 0.1583, "lr": 6.833274435772196e-08, "epoch": 6.836724047991654, "percentage": 97.65, "elapsed_time": "1 day, 12:31:36", "remaining_time": "0:52:49"}
|
| 1312 |
+
{"current_steps": 6560, "total_steps": 6713, "loss": 0.1672, "lr": 6.410492194220963e-08, "epoch": 6.841940532081377, "percentage": 97.72, "elapsed_time": "1 day, 12:34:14", "remaining_time": "0:51:10"}
|
| 1313 |
+
{"current_steps": 6565, "total_steps": 6713, "loss": 0.1641, "lr": 6.001188949687153e-08, "epoch": 6.847157016171101, "percentage": 97.8, "elapsed_time": "1 day, 12:37:03", "remaining_time": "0:49:31"}
|
| 1314 |
+
{"current_steps": 6570, "total_steps": 6713, "loss": 0.1609, "lr": 5.6053674695395463e-08, "epoch": 6.852373500260824, "percentage": 97.87, "elapsed_time": "1 day, 12:39:56", "remaining_time": "0:47:52"}
|
| 1315 |
+
{"current_steps": 6575, "total_steps": 6713, "loss": 0.1834, "lr": 5.22303042999428e-08, "epoch": 6.857589984350548, "percentage": 97.94, "elapsed_time": "1 day, 12:42:30", "remaining_time": "0:46:13"}
|
| 1316 |
+
{"current_steps": 6580, "total_steps": 6713, "loss": 0.1698, "lr": 4.8541804160968655e-08, "epoch": 6.862806468440271, "percentage": 98.02, "elapsed_time": "1 day, 12:45:14", "remaining_time": "0:44:34"}
|
| 1317 |
+
{"current_steps": 6585, "total_steps": 6713, "loss": 0.1672, "lr": 4.498819921705089e-08, "epoch": 6.868022952529994, "percentage": 98.09, "elapsed_time": "1 day, 12:47:40", "remaining_time": "0:42:54"}
|
| 1318 |
+
{"current_steps": 6590, "total_steps": 6713, "loss": 0.1626, "lr": 4.15695134947125e-08, "epoch": 6.873239436619718, "percentage": 98.17, "elapsed_time": "1 day, 12:50:19", "remaining_time": "0:41:15"}
|
| 1319 |
+
{"current_steps": 6595, "total_steps": 6713, "loss": 0.1681, "lr": 3.8285770108272836e-08, "epoch": 6.878455920709442, "percentage": 98.24, "elapsed_time": "1 day, 12:53:10", "remaining_time": "0:39:35"}
|
| 1320 |
+
{"current_steps": 6600, "total_steps": 6713, "loss": 0.1659, "lr": 3.5136991259672183e-08, "epoch": 6.8836724047991655, "percentage": 98.32, "elapsed_time": "1 day, 12:56:07", "remaining_time": "0:37:56"}
|
| 1321 |
+
{"current_steps": 6605, "total_steps": 6713, "loss": 0.1785, "lr": 3.212319823834298e-08, "epoch": 6.888888888888889, "percentage": 98.39, "elapsed_time": "1 day, 13:00:11", "remaining_time": "0:36:18"}
|
| 1322 |
+
{"current_steps": 6610, "total_steps": 6713, "loss": 0.1673, "lr": 2.9244411421049946e-08, "epoch": 6.894105372978612, "percentage": 98.47, "elapsed_time": "1 day, 13:03:01", "remaining_time": "0:34:38"}
|
| 1323 |
+
{"current_steps": 6615, "total_steps": 6713, "loss": 0.1669, "lr": 2.6500650271759077e-08, "epoch": 6.899321857068336, "percentage": 98.54, "elapsed_time": "1 day, 13:05:44", "remaining_time": "0:32:58"}
|