penfever commited on
Commit
6c0730d
·
verified ·
1 Parent(s): 3b277b0

Training in progress, step 7000

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4fc5574bafc21f34c3e231bd409eb11f702e51ee08e833f75bbb4edc9480ba0
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ec5167d50839a5e1910ff1253cdcd212adae063a71eaf00b2daa5766fedaf3
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e2187091d360a1997b2366ccd45a0b621f3e44f72c0697d8d48fbcb0fde6eb6
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b123f196bee8d359af46b59229159db79db604ef8dbdf7e61d4685a3b34c415f
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:118ba5ca4efb636dc9256816cab3de19638801a869a807708a2859f7d1817442
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ddf865e7de6f6e3c8ea12803f90abd247dc1514dfc621f56b186e94dd68193
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51d8a3b003f187ffd6d1072181a2558bab20a0106fed7295d80d4969b661dee4
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fd2adb91c79a51b18813362737a17cb1a2c1569f1994ef2e06856ae23e3405e
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1358,3 +1358,43 @@
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"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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"}
1361
+ {"current_steps": 6805, "total_steps": 9625, "loss": 0.1923, "lr": 9.586233431000567e-06, "epoch": 4.949436158603128, "percentage": 70.7, "elapsed_time": "1 day, 21:12:22", "remaining_time": "18:44:00"}
1362
+ {"current_steps": 6810, "total_steps": 9625, "loss": 0.1944, "lr": 9.555286304148632e-06, "epoch": 4.953073845034558, "percentage": 70.75, "elapsed_time": "1 day, 21:14:03", "remaining_time": "18:41:53"}
1363
+ {"current_steps": 6815, "total_steps": 9625, "loss": 0.1926, "lr": 9.524373525167132e-06, "epoch": 4.956711531465988, "percentage": 70.81, "elapsed_time": "1 day, 21:15:41", "remaining_time": "18:39:45"}
1364
+ {"current_steps": 6820, "total_steps": 9625, "loss": 0.1924, "lr": 9.493495195714028e-06, "epoch": 4.960349217897417, "percentage": 70.86, "elapsed_time": "1 day, 21:17:21", "remaining_time": "18:37:37"}
1365
+ {"current_steps": 6825, "total_steps": 9625, "loss": 0.2105, "lr": 9.462651417333954e-06, "epoch": 4.963986904328847, "percentage": 70.91, "elapsed_time": "1 day, 21:19:03", "remaining_time": "18:35:30"}
1366
+ {"current_steps": 6830, "total_steps": 9625, "loss": 0.2074, "lr": 9.431842291457974e-06, "epoch": 4.967624590760277, "percentage": 70.96, "elapsed_time": "1 day, 21:20:38", "remaining_time": "18:33:21"}
1367
+ {"current_steps": 6835, "total_steps": 9625, "loss": 0.1951, "lr": 9.401067919403148e-06, "epoch": 4.971262277191706, "percentage": 71.01, "elapsed_time": "1 day, 21:22:19", "remaining_time": "18:31:14"}
1368
+ {"current_steps": 6840, "total_steps": 9625, "loss": 0.1921, "lr": 9.370328402372257e-06, "epoch": 4.974899963623136, "percentage": 71.06, "elapsed_time": "1 day, 21:23:58", "remaining_time": "18:29:06"}
1369
+ {"current_steps": 6845, "total_steps": 9625, "loss": 0.203, "lr": 9.339623841453476e-06, "epoch": 4.978537650054565, "percentage": 71.12, "elapsed_time": "1 day, 21:25:37", "remaining_time": "18:26:58"}
1370
+ {"current_steps": 6850, "total_steps": 9625, "loss": 0.1977, "lr": 9.308954337620014e-06, "epoch": 4.982175336485994, "percentage": 71.17, "elapsed_time": "1 day, 21:27:17", "remaining_time": "18:24:51"}
1371
+ {"current_steps": 6855, "total_steps": 9625, "loss": 0.2096, "lr": 9.278319991729801e-06, "epoch": 4.985813022917425, "percentage": 71.22, "elapsed_time": "1 day, 21:28:56", "remaining_time": "18:22:43"}
1372
+ {"current_steps": 6860, "total_steps": 9625, "loss": 0.2021, "lr": 9.24772090452514e-06, "epoch": 4.989450709348854, "percentage": 71.27, "elapsed_time": "1 day, 21:30:41", "remaining_time": "18:20:38"}
1373
+ {"current_steps": 6865, "total_steps": 9625, "loss": 0.209, "lr": 9.217157176632378e-06, "epoch": 4.993088395780283, "percentage": 71.32, "elapsed_time": "1 day, 21:32:18", "remaining_time": "18:18:29"}
1374
+ {"current_steps": 6870, "total_steps": 9625, "loss": 0.2075, "lr": 9.1866289085616e-06, "epoch": 4.996726082211714, "percentage": 71.38, "elapsed_time": "1 day, 21:34:00", "remaining_time": "18:16:23"}
1375
+ {"current_steps": 6875, "total_steps": 9625, "loss": 0.1839, "lr": 9.156136200706265e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1 day, 21:35:33", "remaining_time": "18:14:13"}
1376
+ {"current_steps": 6880, "total_steps": 9625, "loss": 0.1068, "lr": 9.125679153342912e-06, "epoch": 5.003637686431429, "percentage": 71.48, "elapsed_time": "1 day, 21:37:20", "remaining_time": "18:12:08"}
1377
+ {"current_steps": 6885, "total_steps": 9625, "loss": 0.0827, "lr": 9.095257866630774e-06, "epoch": 5.00727537286286, "percentage": 71.53, "elapsed_time": "1 day, 21:38:58", "remaining_time": "18:10:01"}
1378
+ {"current_steps": 6890, "total_steps": 9625, "loss": 0.0745, "lr": 9.064872440611516e-06, "epoch": 5.010913059294289, "percentage": 71.58, "elapsed_time": "1 day, 21:40:36", "remaining_time": "18:07:53"}
1379
+ {"current_steps": 6895, "total_steps": 9625, "loss": 0.0965, "lr": 9.034522975208851e-06, "epoch": 5.014550745725718, "percentage": 71.64, "elapsed_time": "1 day, 21:42:12", "remaining_time": "18:05:44"}
1380
+ {"current_steps": 6900, "total_steps": 9625, "loss": 0.0763, "lr": 9.004209570228249e-06, "epoch": 5.018188432157148, "percentage": 71.69, "elapsed_time": "1 day, 21:43:57", "remaining_time": "18:03:39"}
1381
+ {"current_steps": 6905, "total_steps": 9625, "loss": 0.0917, "lr": 8.973932325356595e-06, "epoch": 5.021826118588578, "percentage": 71.74, "elapsed_time": "1 day, 21:45:32", "remaining_time": "18:01:31"}
1382
+ {"current_steps": 6910, "total_steps": 9625, "loss": 0.1281, "lr": 8.943691340161843e-06, "epoch": 5.025463805020007, "percentage": 71.79, "elapsed_time": "1 day, 21:47:15", "remaining_time": "17:59:25"}
1383
+ {"current_steps": 6915, "total_steps": 9625, "loss": 0.0857, "lr": 8.913486714092719e-06, "epoch": 5.029101491451437, "percentage": 71.84, "elapsed_time": "1 day, 21:48:53", "remaining_time": "17:57:17"}
1384
+ {"current_steps": 6920, "total_steps": 9625, "loss": 0.0934, "lr": 8.883318546478386e-06, "epoch": 5.032739177882866, "percentage": 71.9, "elapsed_time": "1 day, 21:50:35", "remaining_time": "17:55:11"}
1385
+ {"current_steps": 6925, "total_steps": 9625, "loss": 0.0993, "lr": 8.853186936528089e-06, "epoch": 5.036376864314296, "percentage": 71.95, "elapsed_time": "1 day, 21:52:57", "remaining_time": "17:53:21"}
1386
+ {"current_steps": 6930, "total_steps": 9625, "loss": 0.074, "lr": 8.823091983330883e-06, "epoch": 5.040014550745726, "percentage": 72.0, "elapsed_time": "1 day, 21:54:46", "remaining_time": "17:51:17"}
1387
+ {"current_steps": 6935, "total_steps": 9625, "loss": 0.0811, "lr": 8.793033785855243e-06, "epoch": 5.043652237177155, "percentage": 72.05, "elapsed_time": "1 day, 21:56:40", "remaining_time": "17:49:16"}
1388
+ {"current_steps": 6940, "total_steps": 9625, "loss": 0.0838, "lr": 8.763012442948795e-06, "epoch": 5.047289923608585, "percentage": 72.1, "elapsed_time": "1 day, 21:58:30", "remaining_time": "17:47:14"}
1389
+ {"current_steps": 6945, "total_steps": 9625, "loss": 0.1083, "lr": 8.733028053337957e-06, "epoch": 5.050927610040015, "percentage": 72.16, "elapsed_time": "1 day, 22:00:17", "remaining_time": "17:45:09"}
1390
+ {"current_steps": 6950, "total_steps": 9625, "loss": 0.0761, "lr": 8.703080715627639e-06, "epoch": 5.054565296471444, "percentage": 72.21, "elapsed_time": "1 day, 22:01:58", "remaining_time": "17:43:03"}
1391
+ {"current_steps": 6955, "total_steps": 9625, "loss": 0.0759, "lr": 8.67317052830088e-06, "epoch": 5.058202982902873, "percentage": 72.26, "elapsed_time": "1 day, 22:03:32", "remaining_time": "17:40:54"}
1392
+ {"current_steps": 6960, "total_steps": 9625, "loss": 0.0694, "lr": 8.643297589718557e-06, "epoch": 5.061840669334304, "percentage": 72.31, "elapsed_time": "1 day, 22:05:07", "remaining_time": "17:38:46"}
1393
+ {"current_steps": 6965, "total_steps": 9625, "loss": 0.0891, "lr": 8.613461998119066e-06, "epoch": 5.065478355765733, "percentage": 72.36, "elapsed_time": "1 day, 22:06:37", "remaining_time": "17:36:36"}
1394
+ {"current_steps": 6970, "total_steps": 9625, "loss": 0.0894, "lr": 8.583663851617971e-06, "epoch": 5.069116042197162, "percentage": 72.42, "elapsed_time": "1 day, 22:08:23", "remaining_time": "17:34:31"}
1395
+ {"current_steps": 6975, "total_steps": 9625, "loss": 0.0885, "lr": 8.553903248207714e-06, "epoch": 5.072753728628593, "percentage": 72.47, "elapsed_time": "1 day, 22:10:03", "remaining_time": "17:32:25"}
1396
+ {"current_steps": 6980, "total_steps": 9625, "loss": 0.09, "lr": 8.524180285757253e-06, "epoch": 5.076391415060022, "percentage": 72.52, "elapsed_time": "1 day, 22:11:47", "remaining_time": "17:30:20"}
1397
+ {"current_steps": 6985, "total_steps": 9625, "loss": 0.1205, "lr": 8.49449506201176e-06, "epoch": 5.080029101491451, "percentage": 72.57, "elapsed_time": "1 day, 22:13:33", "remaining_time": "17:28:16"}
1398
+ {"current_steps": 6990, "total_steps": 9625, "loss": 0.0745, "lr": 8.464847674592338e-06, "epoch": 5.083666787922881, "percentage": 72.62, "elapsed_time": "1 day, 22:15:05", "remaining_time": "17:26:07"}
1399
+ {"current_steps": 6995, "total_steps": 9625, "loss": 0.1024, "lr": 8.435238220995623e-06, "epoch": 5.087304474354311, "percentage": 72.68, "elapsed_time": "1 day, 22:16:37", "remaining_time": "17:23:57"}
1400
+ {"current_steps": 7000, "total_steps": 9625, "loss": 0.1033, "lr": 8.405666798593532e-06, "epoch": 5.09094216078574, "percentage": 72.73, "elapsed_time": "1 day, 22:18:27", "remaining_time": "17:21:55"}