Training in progress, step 300
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 4998056552
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f169a5cf7a218426bd887afae294bc4839c3a9229b597c792398fbc6018e83a
|
| 3 |
size 4998056552
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915962464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e546047a602208cf99253121ca7936c155134bd167636b7c1a63409bf20121f8
|
| 3 |
size 4915962464
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915962496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e676b882a8fbc19a333f5bd267b2cbb710f1609e2626e7a20a6b06262a4f4f3
|
| 3 |
size 4915962496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2704357976
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1c6e8d6ba96b7f403634157a75d29507bd38630b12976f5840d1d555880ac9c
|
| 3 |
size 2704357976
|
trainer_log.jsonl
CHANGED
|
@@ -248,3 +248,53 @@
|
|
| 248 |
{"current_steps": 248, "total_steps": 2820, "loss": 0.0923, "lr": 2.98842641148301e-05, "epoch": 0.17594891805604823, "percentage": 8.79, "elapsed_time": "16:27:38", "remaining_time": "7 days, 2:42:43"}
|
| 249 |
{"current_steps": 249, "total_steps": 2820, "loss": 0.1388, "lr": 2.9882072997712665e-05, "epoch": 0.17665838949982263, "percentage": 8.83, "elapsed_time": "16:32:28", "remaining_time": "7 days, 2:47:38"}
|
| 250 |
{"current_steps": 250, "total_steps": 2820, "loss": 0.1391, "lr": 2.9879861415314855e-05, "epoch": 0.17736786094359702, "percentage": 8.87, "elapsed_time": "16:36:16", "remaining_time": "7 days, 2:41:40"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 248 |
{"current_steps": 248, "total_steps": 2820, "loss": 0.0923, "lr": 2.98842641148301e-05, "epoch": 0.17594891805604823, "percentage": 8.79, "elapsed_time": "16:27:38", "remaining_time": "7 days, 2:42:43"}
|
| 249 |
{"current_steps": 249, "total_steps": 2820, "loss": 0.1388, "lr": 2.9882072997712665e-05, "epoch": 0.17665838949982263, "percentage": 8.83, "elapsed_time": "16:32:28", "remaining_time": "7 days, 2:47:38"}
|
| 250 |
{"current_steps": 250, "total_steps": 2820, "loss": 0.1391, "lr": 2.9879861415314855e-05, "epoch": 0.17736786094359702, "percentage": 8.87, "elapsed_time": "16:36:16", "remaining_time": "7 days, 2:41:40"}
|
| 251 |
+
{"current_steps": 251, "total_steps": 2820, "loss": 0.1281, "lr": 2.987762937067796e-05, "epoch": 0.17807733238737142, "percentage": 8.9, "elapsed_time": "16:41:10", "remaining_time": "7 days, 2:47:07"}
|
| 252 |
+
{"current_steps": 252, "total_steps": 2820, "loss": 0.1167, "lr": 2.9875376866871404e-05, "epoch": 0.17878680383114579, "percentage": 8.94, "elapsed_time": "16:44:44", "remaining_time": "7 days, 2:38:47"}
|
| 253 |
+
{"current_steps": 253, "total_steps": 2820, "loss": 0.1305, "lr": 2.9873103906992745e-05, "epoch": 0.17949627527492018, "percentage": 8.97, "elapsed_time": "16:48:47", "remaining_time": "7 days, 2:35:31"}
|
| 254 |
+
{"current_steps": 254, "total_steps": 2820, "loss": 0.1126, "lr": 2.9870810494167677e-05, "epoch": 0.18020574671869458, "percentage": 9.01, "elapsed_time": "16:52:24", "remaining_time": "7 days, 2:27:42"}
|
| 255 |
+
{"current_steps": 255, "total_steps": 2820, "loss": 0.1433, "lr": 2.9868496631550018e-05, "epoch": 0.18091521816246897, "percentage": 9.04, "elapsed_time": "16:56:26", "remaining_time": "7 days, 2:24:14"}
|
| 256 |
+
{"current_steps": 256, "total_steps": 2820, "loss": 0.116, "lr": 2.9866162322321703e-05, "epoch": 0.18162468960624334, "percentage": 9.08, "elapsed_time": "16:59:44", "remaining_time": "7 days, 2:13:24"}
|
| 257 |
+
{"current_steps": 257, "total_steps": 2820, "loss": 0.142, "lr": 2.9863807569692787e-05, "epoch": 0.18233416105001773, "percentage": 9.11, "elapsed_time": "17:04:23", "remaining_time": "7 days, 2:16:04"}
|
| 258 |
+
{"current_steps": 258, "total_steps": 2820, "loss": 0.1174, "lr": 2.9861432376901444e-05, "epoch": 0.18304363249379213, "percentage": 9.15, "elapsed_time": "17:08:24", "remaining_time": "7 days, 2:12:24"}
|
| 259 |
+
{"current_steps": 259, "total_steps": 2820, "loss": 0.1226, "lr": 2.9859036747213955e-05, "epoch": 0.18375310393756653, "percentage": 9.18, "elapsed_time": "17:12:07", "remaining_time": "7 days, 2:05:43"}
|
| 260 |
+
{"current_steps": 260, "total_steps": 2820, "loss": 0.1433, "lr": 2.9856620683924694e-05, "epoch": 0.1844625753813409, "percentage": 9.22, "elapsed_time": "17:16:28", "remaining_time": "7 days, 2:05:19"}
|
| 261 |
+
{"current_steps": 261, "total_steps": 2820, "loss": 0.1345, "lr": 2.9854184190356146e-05, "epoch": 0.1851720468251153, "percentage": 9.26, "elapsed_time": "17:20:35", "remaining_time": "7 days, 2:02:33"}
|
| 262 |
+
{"current_steps": 262, "total_steps": 2820, "loss": 0.1359, "lr": 2.985172726985889e-05, "epoch": 0.18588151826888968, "percentage": 9.29, "elapsed_time": "17:23:56", "remaining_time": "7 days, 1:52:22"}
|
| 263 |
+
{"current_steps": 263, "total_steps": 2820, "loss": 0.1364, "lr": 2.984924992581159e-05, "epoch": 0.18659098971266405, "percentage": 9.33, "elapsed_time": "17:27:46", "remaining_time": "7 days, 1:46:56"}
|
| 264 |
+
{"current_steps": 264, "total_steps": 2820, "loss": 0.1261, "lr": 2.9846752161620994e-05, "epoch": 0.18730046115643845, "percentage": 9.36, "elapsed_time": "17:32:12", "remaining_time": "7 days, 1:47:22"}
|
| 265 |
+
{"current_steps": 265, "total_steps": 2820, "loss": 0.1491, "lr": 2.9844233980721944e-05, "epoch": 0.18800993260021284, "percentage": 9.4, "elapsed_time": "17:36:13", "remaining_time": "7 days, 1:43:37"}
|
| 266 |
+
{"current_steps": 266, "total_steps": 2820, "loss": 0.1479, "lr": 2.9841695386577345e-05, "epoch": 0.18871940404398724, "percentage": 9.43, "elapsed_time": "17:39:56", "remaining_time": "7 days, 1:37:03"}
|
| 267 |
+
{"current_steps": 267, "total_steps": 2820, "loss": 0.1366, "lr": 2.983913638267818e-05, "epoch": 0.1894288754877616, "percentage": 9.47, "elapsed_time": "17:43:59", "remaining_time": "7 days, 1:33:45"}
|
| 268 |
+
{"current_steps": 268, "total_steps": 2820, "loss": 0.1543, "lr": 2.9836556972543502e-05, "epoch": 0.190138346931536, "percentage": 9.5, "elapsed_time": "17:47:38", "remaining_time": "7 days, 1:26:27"}
|
| 269 |
+
{"current_steps": 269, "total_steps": 2820, "loss": 0.1309, "lr": 2.9833957159720414e-05, "epoch": 0.1908478183753104, "percentage": 9.54, "elapsed_time": "17:51:22", "remaining_time": "7 days, 1:20:08"}
|
| 270 |
+
{"current_steps": 270, "total_steps": 2820, "loss": 0.1304, "lr": 2.9831336947784083e-05, "epoch": 0.1915572898190848, "percentage": 9.57, "elapsed_time": "17:55:36", "remaining_time": "7 days, 1:18:28"}
|
| 271 |
+
{"current_steps": 271, "total_steps": 2820, "loss": 0.1372, "lr": 2.982869634033773e-05, "epoch": 0.19226676126285916, "percentage": 9.61, "elapsed_time": "17:59:23", "remaining_time": "7 days, 1:12:37"}
|
| 272 |
+
{"current_steps": 272, "total_steps": 2820, "loss": 0.1276, "lr": 2.9826035341012623e-05, "epoch": 0.19297623270663355, "percentage": 9.65, "elapsed_time": "18:03:08", "remaining_time": "7 days, 1:06:31"}
|
| 273 |
+
{"current_steps": 273, "total_steps": 2820, "loss": 0.1466, "lr": 2.9823353953468073e-05, "epoch": 0.19368570415040795, "percentage": 9.68, "elapsed_time": "18:07:01", "remaining_time": "7 days, 1:01:32"}
|
| 274 |
+
{"current_steps": 274, "total_steps": 2820, "loss": 0.1419, "lr": 2.982065218139142e-05, "epoch": 0.19439517559418235, "percentage": 9.72, "elapsed_time": "18:10:30", "remaining_time": "7 days, 0:52:54"}
|
| 275 |
+
{"current_steps": 275, "total_steps": 2820, "loss": 0.1487, "lr": 2.981793002849804e-05, "epoch": 0.1951046470379567, "percentage": 9.75, "elapsed_time": "18:14:17", "remaining_time": "7 days, 0:47:12"}
|
| 276 |
+
{"current_steps": 276, "total_steps": 2820, "loss": 0.1616, "lr": 2.9815187498531348e-05, "epoch": 0.1958141184817311, "percentage": 9.79, "elapsed_time": "18:18:04", "remaining_time": "7 days, 0:41:25"}
|
| 277 |
+
{"current_steps": 277, "total_steps": 2820, "loss": 0.1892, "lr": 2.9812424595262763e-05, "epoch": 0.1965235899255055, "percentage": 9.82, "elapsed_time": "18:22:11", "remaining_time": "7 days, 0:38:40"}
|
| 278 |
+
{"current_steps": 278, "total_steps": 2820, "loss": 0.1529, "lr": 2.9809641322491727e-05, "epoch": 0.1972330613692799, "percentage": 9.86, "elapsed_time": "18:25:34", "remaining_time": "7 days, 0:29:11"}
|
| 279 |
+
{"current_steps": 279, "total_steps": 2820, "loss": 0.1278, "lr": 2.9806837684045697e-05, "epoch": 0.19794253281305427, "percentage": 9.89, "elapsed_time": "18:29:26", "remaining_time": "7 days, 0:24:15"}
|
| 280 |
+
{"current_steps": 280, "total_steps": 2820, "loss": 0.1271, "lr": 2.9804013683780137e-05, "epoch": 0.19865200425682866, "percentage": 9.93, "elapsed_time": "18:32:57", "remaining_time": "7 days, 0:16:11"}
|
| 281 |
+
{"current_steps": 281, "total_steps": 2820, "loss": 0.1514, "lr": 2.98011693255785e-05, "epoch": 0.19936147570060306, "percentage": 9.96, "elapsed_time": "18:37:19", "remaining_time": "7 days, 0:15:38"}
|
| 282 |
+
{"current_steps": 282, "total_steps": 2820, "loss": 0.1657, "lr": 2.979830461335225e-05, "epoch": 0.20007094714437743, "percentage": 10.0, "elapsed_time": "18:41:44", "remaining_time": "7 days, 0:15:41"}
|
| 283 |
+
{"current_steps": 283, "total_steps": 2820, "loss": 0.1394, "lr": 2.9795419551040836e-05, "epoch": 0.20078041858815182, "percentage": 10.04, "elapsed_time": "18:46:17", "remaining_time": "7 days, 0:16:49"}
|
| 284 |
+
{"current_steps": 284, "total_steps": 2820, "loss": 0.125, "lr": 2.9792514142611683e-05, "epoch": 0.20148989003192622, "percentage": 10.07, "elapsed_time": "18:50:17", "remaining_time": "7 days, 0:12:58"}
|
| 285 |
+
{"current_steps": 285, "total_steps": 2820, "loss": 0.1169, "lr": 2.9789588392060205e-05, "epoch": 0.2021993614757006, "percentage": 10.11, "elapsed_time": "18:54:26", "remaining_time": "7 days, 0:10:36"}
|
| 286 |
+
{"current_steps": 286, "total_steps": 2820, "loss": 0.1379, "lr": 2.9786642303409785e-05, "epoch": 0.20290883291947498, "percentage": 10.14, "elapsed_time": "18:58:24", "remaining_time": "7 days, 0:06:25"}
|
| 287 |
+
{"current_steps": 287, "total_steps": 2820, "loss": 0.1374, "lr": 2.9783675880711783e-05, "epoch": 0.20361830436324937, "percentage": 10.18, "elapsed_time": "19:02:16", "remaining_time": "7 days, 0:01:29"}
|
| 288 |
+
{"current_steps": 288, "total_steps": 2820, "loss": 0.1663, "lr": 2.9780689128045504e-05, "epoch": 0.20432777580702377, "percentage": 10.21, "elapsed_time": "19:06:38", "remaining_time": "7 days, 0:00:49"}
|
| 289 |
+
{"current_steps": 289, "total_steps": 2820, "loss": 0.1604, "lr": 2.9777682049518226e-05, "epoch": 0.20503724725079817, "percentage": 10.25, "elapsed_time": "19:10:13", "remaining_time": "6 days, 23:53:22"}
|
| 290 |
+
{"current_steps": 290, "total_steps": 2820, "loss": 0.1263, "lr": 2.9774654649265173e-05, "epoch": 0.20574671869457253, "percentage": 10.28, "elapsed_time": "19:14:18", "remaining_time": "6 days, 23:50:20"}
|
| 291 |
+
{"current_steps": 291, "total_steps": 2820, "loss": 0.1261, "lr": 2.977160693144952e-05, "epoch": 0.20645619013834693, "percentage": 10.32, "elapsed_time": "19:17:57", "remaining_time": "6 days, 23:43:28"}
|
| 292 |
+
{"current_steps": 292, "total_steps": 2820, "loss": 0.1441, "lr": 2.976853890026236e-05, "epoch": 0.20716566158212132, "percentage": 10.35, "elapsed_time": "19:21:49", "remaining_time": "6 days, 23:38:28"}
|
| 293 |
+
{"current_steps": 293, "total_steps": 2820, "loss": 0.1336, "lr": 2.976545055992276e-05, "epoch": 0.20787513302589572, "percentage": 10.39, "elapsed_time": "19:26:27", "remaining_time": "6 days, 23:40:13"}
|
| 294 |
+
{"current_steps": 294, "total_steps": 2820, "loss": 0.1265, "lr": 2.976234191467767e-05, "epoch": 0.2085846044696701, "percentage": 10.43, "elapsed_time": "19:30:24", "remaining_time": "6 days, 23:35:56"}
|
| 295 |
+
{"current_steps": 295, "total_steps": 2820, "loss": 0.1345, "lr": 2.9759212968802e-05, "epoch": 0.20929407591344448, "percentage": 10.46, "elapsed_time": "19:34:02", "remaining_time": "6 days, 23:29:03"}
|
| 296 |
+
{"current_steps": 296, "total_steps": 2820, "loss": 0.1967, "lr": 2.9756063726598554e-05, "epoch": 0.21000354735721888, "percentage": 10.5, "elapsed_time": "19:39:08", "remaining_time": "6 days, 23:34:32"}
|
| 297 |
+
{"current_steps": 297, "total_steps": 2820, "loss": 0.1506, "lr": 2.9752894192398057e-05, "epoch": 0.21071301880099327, "percentage": 10.53, "elapsed_time": "19:43:04", "remaining_time": "6 days, 23:30:10"}
|
| 298 |
+
{"current_steps": 298, "total_steps": 2820, "loss": 0.1262, "lr": 2.974970437055914e-05, "epoch": 0.21142249024476764, "percentage": 10.57, "elapsed_time": "19:47:05", "remaining_time": "6 days, 23:26:26"}
|
| 299 |
+
{"current_steps": 299, "total_steps": 2820, "loss": 0.1342, "lr": 2.974649426546832e-05, "epoch": 0.21213196168854204, "percentage": 10.6, "elapsed_time": "19:50:49", "remaining_time": "6 days, 23:20:25"}
|
| 300 |
+
{"current_steps": 300, "total_steps": 2820, "loss": 0.1305, "lr": 2.974326388154002e-05, "epoch": 0.21284143313231643, "percentage": 10.64, "elapsed_time": "19:55:07", "remaining_time": "6 days, 23:18:59"}
|