Training in progress, step 6800
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:c4fc5574bafc21f34c3e231bd409eb11f702e51ee08e833f75bbb4edc9480ba0
|
| 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 sha256:2e2187091d360a1997b2366ccd45a0b621f3e44f72c0697d8d48fbcb0fde6eb6
|
| 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 sha256:118ba5ca4efb636dc9256816cab3de19638801a869a807708a2859f7d1817442
|
| 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 sha256:51d8a3b003f187ffd6d1072181a2558bab20a0106fed7295d80d4969b661dee4
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -1318,3 +1318,43 @@
|
|
| 1318 |
{"current_steps": 6590, "total_steps": 9625, "loss": 0.2155, "lr": 1.0947992474547595e-05, "epoch": 4.793015642051655, "percentage": 68.47, "elapsed_time": "1 day, 19:58:09", "remaining_time": "20:14:59"}
|
| 1319 |
{"current_steps": 6595, "total_steps": 9625, "loss": 0.2063, "lr": 1.091566611019622e-05, "epoch": 4.796653328483085, "percentage": 68.52, "elapsed_time": "1 day, 19:59:48", "remaining_time": "20:12:49"}
|
| 1320 |
{"current_steps": 6600, "total_steps": 9625, "loss": 0.1991, "lr": 1.088336962005036e-05, "epoch": 4.800291014914515, "percentage": 68.57, "elapsed_time": "1 day, 20:01:26", "remaining_time": "20:10:39"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1318 |
{"current_steps": 6590, "total_steps": 9625, "loss": 0.2155, "lr": 1.0947992474547595e-05, "epoch": 4.793015642051655, "percentage": 68.47, "elapsed_time": "1 day, 19:58:09", "remaining_time": "20:14:59"}
|
| 1319 |
{"current_steps": 6595, "total_steps": 9625, "loss": 0.2063, "lr": 1.091566611019622e-05, "epoch": 4.796653328483085, "percentage": 68.52, "elapsed_time": "1 day, 19:59:48", "remaining_time": "20:12:49"}
|
| 1320 |
{"current_steps": 6600, "total_steps": 9625, "loss": 0.1991, "lr": 1.088336962005036e-05, "epoch": 4.800291014914515, "percentage": 68.57, "elapsed_time": "1 day, 20:01:26", "remaining_time": "20:10:39"}
|
| 1321 |
+
{"current_steps": 6605, "total_steps": 9625, "loss": 0.1974, "lr": 1.0851103110318366e-05, "epoch": 4.803928701345944, "percentage": 68.62, "elapsed_time": "1 day, 20:04:13", "remaining_time": "20:09:01"}
|
| 1322 |
+
{"current_steps": 6610, "total_steps": 9625, "loss": 0.1973, "lr": 1.0818866687109957e-05, "epoch": 4.807566387777373, "percentage": 68.68, "elapsed_time": "1 day, 20:05:51", "remaining_time": "20:06:50"}
|
| 1323 |
+
{"current_steps": 6615, "total_steps": 9625, "loss": 0.1911, "lr": 1.0786660456435955e-05, "epoch": 4.811204074208804, "percentage": 68.73, "elapsed_time": "1 day, 20:07:30", "remaining_time": "20:04:41"}
|
| 1324 |
+
{"current_steps": 6620, "total_steps": 9625, "loss": 0.1955, "lr": 1.075448452420786e-05, "epoch": 4.814841760640233, "percentage": 68.78, "elapsed_time": "1 day, 20:09:15", "remaining_time": "20:02:34"}
|
| 1325 |
+
{"current_steps": 6625, "total_steps": 9625, "loss": 0.183, "lr": 1.0722338996237553e-05, "epoch": 4.818479447071662, "percentage": 68.83, "elapsed_time": "1 day, 20:10:51", "remaining_time": "20:00:23"}
|
| 1326 |
+
{"current_steps": 6630, "total_steps": 9625, "loss": 0.2003, "lr": 1.0690223978236936e-05, "epoch": 4.822117133503092, "percentage": 68.88, "elapsed_time": "1 day, 20:12:31", "remaining_time": "19:58:14"}
|
| 1327 |
+
{"current_steps": 6635, "total_steps": 9625, "loss": 0.223, "lr": 1.0658139575817548e-05, "epoch": 4.825754819934522, "percentage": 68.94, "elapsed_time": "1 day, 20:14:09", "remaining_time": "19:56:04"}
|
| 1328 |
+
{"current_steps": 6640, "total_steps": 9625, "loss": 0.2028, "lr": 1.0626085894490272e-05, "epoch": 4.829392506365951, "percentage": 68.99, "elapsed_time": "1 day, 20:15:48", "remaining_time": "19:53:54"}
|
| 1329 |
+
{"current_steps": 6645, "total_steps": 9625, "loss": 0.2115, "lr": 1.0594063039664962e-05, "epoch": 4.833030192797381, "percentage": 69.04, "elapsed_time": "1 day, 20:17:26", "remaining_time": "19:51:45"}
|
| 1330 |
+
{"current_steps": 6650, "total_steps": 9625, "loss": 0.2038, "lr": 1.0562071116650095e-05, "epoch": 4.836667879228811, "percentage": 69.09, "elapsed_time": "1 day, 20:19:06", "remaining_time": "19:49:35"}
|
| 1331 |
+
{"current_steps": 6655, "total_steps": 9625, "loss": 0.2052, "lr": 1.053011023065242e-05, "epoch": 4.84030556566024, "percentage": 69.14, "elapsed_time": "1 day, 20:20:50", "remaining_time": "19:47:28"}
|
| 1332 |
+
{"current_steps": 6660, "total_steps": 9625, "loss": 0.2024, "lr": 1.0498180486776617e-05, "epoch": 4.84394325209167, "percentage": 69.19, "elapsed_time": "1 day, 20:22:35", "remaining_time": "19:45:22"}
|
| 1333 |
+
{"current_steps": 6665, "total_steps": 9625, "loss": 0.1924, "lr": 1.046628199002497e-05, "epoch": 4.847580938523099, "percentage": 69.25, "elapsed_time": "1 day, 20:24:17", "remaining_time": "19:43:14"}
|
| 1334 |
+
{"current_steps": 6670, "total_steps": 9625, "loss": 0.2049, "lr": 1.0434414845296992e-05, "epoch": 4.851218624954529, "percentage": 69.3, "elapsed_time": "1 day, 20:25:59", "remaining_time": "19:41:06"}
|
| 1335 |
+
{"current_steps": 6675, "total_steps": 9625, "loss": 0.1976, "lr": 1.0402579157389115e-05, "epoch": 4.854856311385959, "percentage": 69.35, "elapsed_time": "1 day, 20:27:39", "remaining_time": "19:38:57"}
|
| 1336 |
+
{"current_steps": 6680, "total_steps": 9625, "loss": 0.2031, "lr": 1.0370775030994295e-05, "epoch": 4.858493997817388, "percentage": 69.4, "elapsed_time": "1 day, 20:29:15", "remaining_time": "19:36:47"}
|
| 1337 |
+
{"current_steps": 6685, "total_steps": 9625, "loss": 0.2146, "lr": 1.0339002570701702e-05, "epoch": 4.862131684248817, "percentage": 69.45, "elapsed_time": "1 day, 20:31:01", "remaining_time": "19:34:41"}
|
| 1338 |
+
{"current_steps": 6690, "total_steps": 9625, "loss": 0.2037, "lr": 1.0307261880996387e-05, "epoch": 4.865769370680248, "percentage": 69.51, "elapsed_time": "1 day, 20:32:41", "remaining_time": "19:32:32"}
|
| 1339 |
+
{"current_steps": 6695, "total_steps": 9625, "loss": 0.2151, "lr": 1.027555306625891e-05, "epoch": 4.869407057111677, "percentage": 69.56, "elapsed_time": "1 day, 20:34:18", "remaining_time": "19:30:22"}
|
| 1340 |
+
{"current_steps": 6700, "total_steps": 9625, "loss": 0.2067, "lr": 1.0243876230765024e-05, "epoch": 4.873044743543106, "percentage": 69.61, "elapsed_time": "1 day, 20:35:53", "remaining_time": "19:28:12"}
|
| 1341 |
+
{"current_steps": 6705, "total_steps": 9625, "loss": 0.2193, "lr": 1.0212231478685286e-05, "epoch": 4.876682429974537, "percentage": 69.66, "elapsed_time": "1 day, 20:37:33", "remaining_time": "19:26:04"}
|
| 1342 |
+
{"current_steps": 6710, "total_steps": 9625, "loss": 0.2154, "lr": 1.0180618914084776e-05, "epoch": 4.880320116405966, "percentage": 69.71, "elapsed_time": "1 day, 20:39:14", "remaining_time": "19:23:55"}
|
| 1343 |
+
{"current_steps": 6715, "total_steps": 9625, "loss": 0.2132, "lr": 1.0149038640922715e-05, "epoch": 4.883957802837395, "percentage": 69.77, "elapsed_time": "1 day, 20:40:50", "remaining_time": "19:21:45"}
|
| 1344 |
+
{"current_steps": 6720, "total_steps": 9625, "loss": 0.2136, "lr": 1.011749076305212e-05, "epoch": 4.887595489268825, "percentage": 69.82, "elapsed_time": "1 day, 20:42:38", "remaining_time": "19:19:40"}
|
| 1345 |
+
{"current_steps": 6725, "total_steps": 9625, "loss": 0.2068, "lr": 1.0085975384219493e-05, "epoch": 4.891233175700255, "percentage": 69.87, "elapsed_time": "1 day, 20:44:14", "remaining_time": "19:17:31"}
|
| 1346 |
+
{"current_steps": 6730, "total_steps": 9625, "loss": 0.2076, "lr": 1.0054492608064446e-05, "epoch": 4.894870862131684, "percentage": 69.92, "elapsed_time": "1 day, 20:45:52", "remaining_time": "19:15:21"}
|
| 1347 |
+
{"current_steps": 6735, "total_steps": 9625, "loss": 0.2117, "lr": 1.0023042538119383e-05, "epoch": 4.898508548563114, "percentage": 69.97, "elapsed_time": "1 day, 20:47:28", "remaining_time": "19:13:12"}
|
| 1348 |
+
{"current_steps": 6740, "total_steps": 9625, "loss": 0.2, "lr": 9.991625277809167e-06, "epoch": 4.902146234994543, "percentage": 70.03, "elapsed_time": "1 day, 20:49:07", "remaining_time": "19:11:03"}
|
| 1349 |
+
{"current_steps": 6745, "total_steps": 9625, "loss": 0.1918, "lr": 9.960240930450728e-06, "epoch": 4.905783921425973, "percentage": 70.08, "elapsed_time": "1 day, 20:50:54", "remaining_time": "19:08:58"}
|
| 1350 |
+
{"current_steps": 6750, "total_steps": 9625, "loss": 0.209, "lr": 9.928889599252802e-06, "epoch": 4.909421607857403, "percentage": 70.13, "elapsed_time": "1 day, 20:52:34", "remaining_time": "19:06:50"}
|
| 1351 |
+
{"current_steps": 6755, "total_steps": 9625, "loss": 0.1973, "lr": 9.897571387315507e-06, "epoch": 4.913059294288832, "percentage": 70.18, "elapsed_time": "1 day, 20:54:18", "remaining_time": "19:04:43"}
|
| 1352 |
+
{"current_steps": 6760, "total_steps": 9625, "loss": 0.2167, "lr": 9.866286397630102e-06, "epoch": 4.916696980720262, "percentage": 70.23, "elapsed_time": "1 day, 20:55:53", "remaining_time": "19:02:33"}
|
| 1353 |
+
{"current_steps": 6765, "total_steps": 9625, "loss": 0.2039, "lr": 9.835034733078538e-06, "epoch": 4.920334667151692, "percentage": 70.29, "elapsed_time": "1 day, 20:57:33", "remaining_time": "19:00:25"}
|
| 1354 |
+
{"current_steps": 6770, "total_steps": 9625, "loss": 0.2064, "lr": 9.803816496433213e-06, "epoch": 4.923972353583121, "percentage": 70.34, "elapsed_time": "1 day, 20:59:15", "remaining_time": "18:58:18"}
|
| 1355 |
+
{"current_steps": 6775, "total_steps": 9625, "loss": 0.2061, "lr": 9.77263179035657e-06, "epoch": 4.92761004001455, "percentage": 70.39, "elapsed_time": "1 day, 21:00:51", "remaining_time": "18:56:09"}
|
| 1356 |
+
{"current_steps": 6780, "total_steps": 9625, "loss": 0.208, "lr": 9.741480717400803e-06, "epoch": 4.931247726445981, "percentage": 70.44, "elapsed_time": "1 day, 21:02:33", "remaining_time": "18:54:02"}
|
| 1357 |
+
{"current_steps": 6785, "total_steps": 9625, "loss": 0.2021, "lr": 9.710363380007501e-06, "epoch": 4.93488541287741, "percentage": 70.49, "elapsed_time": "1 day, 21:04:22", "remaining_time": "18:51:58"}
|
| 1358 |
+
{"current_steps": 6790, "total_steps": 9625, "loss": 0.1967, "lr": 9.679279880507294e-06, "epoch": 4.938523099308839, "percentage": 70.55, "elapsed_time": "1 day, 21:06:09", "remaining_time": "18:49:53"}
|
| 1359 |
+
{"current_steps": 6795, "total_steps": 9625, "loss": 0.199, "lr": 9.64823032111957e-06, "epoch": 4.942160785740269, "percentage": 70.6, "elapsed_time": "1 day, 21:07:50", "remaining_time": "18:47:46"}
|
| 1360 |
+
{"current_steps": 6800, "total_steps": 9625, "loss": 0.1996, "lr": 9.617214803952055e-06, "epoch": 4.945798472171699, "percentage": 70.65, "elapsed_time": "1 day, 21:09:33", "remaining_time": "18:45:39"}
|