penfever commited on
Commit
fb42e64
·
verified ·
1 Parent(s): 34c4c7f

Training in progress, step 1800

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a57d25aae8a58725f17c9c616a6387dbcebbe45e4a54cc2f97d6d07098cb6356
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac2e498d01b361e3a27366d90207226345d46aae26b1872c4381aabfa2bf7b9c
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bd9e371fee33a1bc1be0823986cd049ed81083767fbabaa6bdb5f97018f5af5
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a06b685cd5f098c29d8f191f5a6015f5e2b9c15d523baa2b7cc46c5e3b51879
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:e54625be17b73b5ae9abd74af2b033e629f18bced0421411ba66b62b3552930f
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef43bfefdd303c5df66dabddd7a79b12d3e306cb02b056698c26bf24fc2b52f
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:145ed0475c0364754f0670a061b1b1daf88c3cb5966292562b61156781ca91a0
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6a1bb4539ab70ec9525f11246c5d363682c9e61ea603e255af600835aa7dc8
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -322,3 +322,40 @@
322
  {"current_steps": 1610, "total_steps": 9128, "loss": 0.2275, "lr": 3.929573250584258e-05, "epoch": 1.234752589182969, "percentage": 17.64, "elapsed_time": "10:54:58", "remaining_time": "2 days, 2:58:28"}
323
  {"current_steps": 1615, "total_steps": 9128, "loss": 0.2357, "lr": 3.928563826064568e-05, "epoch": 1.2385884158036058, "percentage": 17.69, "elapsed_time": "10:56:13", "remaining_time": "2 days, 2:52:45"}
324
  {"current_steps": 1620, "total_steps": 9128, "loss": 0.218, "lr": 3.927547350418433e-05, "epoch": 1.2424242424242424, "percentage": 17.75, "elapsed_time": "10:57:29", "remaining_time": "2 days, 2:47:09"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
322
  {"current_steps": 1610, "total_steps": 9128, "loss": 0.2275, "lr": 3.929573250584258e-05, "epoch": 1.234752589182969, "percentage": 17.64, "elapsed_time": "10:54:58", "remaining_time": "2 days, 2:58:28"}
323
  {"current_steps": 1615, "total_steps": 9128, "loss": 0.2357, "lr": 3.928563826064568e-05, "epoch": 1.2385884158036058, "percentage": 17.69, "elapsed_time": "10:56:13", "remaining_time": "2 days, 2:52:45"}
324
  {"current_steps": 1620, "total_steps": 9128, "loss": 0.218, "lr": 3.927547350418433e-05, "epoch": 1.2424242424242424, "percentage": 17.75, "elapsed_time": "10:57:29", "remaining_time": "2 days, 2:47:09"}
325
+ {"current_steps": 1625, "total_steps": 9128, "loss": 0.2374, "lr": 3.926523827362247e-05, "epoch": 1.246260069044879, "percentage": 17.8, "elapsed_time": "10:58:43", "remaining_time": "2 days, 2:41:28"}
326
+ {"current_steps": 1630, "total_steps": 9128, "loss": 0.2258, "lr": 3.9254932606381675e-05, "epoch": 1.250095895665516, "percentage": 17.86, "elapsed_time": "11:00:00", "remaining_time": "2 days, 2:36:00"}
327
+ {"current_steps": 1635, "total_steps": 9128, "loss": 0.219, "lr": 3.9244556540141045e-05, "epoch": 1.2539317222861528, "percentage": 17.91, "elapsed_time": "11:01:16", "remaining_time": "2 days, 2:30:33"}
328
+ {"current_steps": 1640, "total_steps": 9128, "loss": 0.2315, "lr": 3.9234110112837086e-05, "epoch": 1.2577675489067894, "percentage": 17.97, "elapsed_time": "11:02:33", "remaining_time": "2 days, 2:25:09"}
329
+ {"current_steps": 1645, "total_steps": 9128, "loss": 0.2212, "lr": 3.922359336266354e-05, "epoch": 1.261603375527426, "percentage": 18.02, "elapsed_time": "11:03:49", "remaining_time": "2 days, 2:19:40"}
330
+ {"current_steps": 1650, "total_steps": 9128, "loss": 0.211, "lr": 3.9213006328071265e-05, "epoch": 1.265439202148063, "percentage": 18.08, "elapsed_time": "11:05:03", "remaining_time": "2 days, 2:14:05"}
331
+ {"current_steps": 1655, "total_steps": 9128, "loss": 0.2103, "lr": 3.9202349047768094e-05, "epoch": 1.2692750287686996, "percentage": 18.13, "elapsed_time": "11:06:17", "remaining_time": "2 days, 2:08:32"}
332
+ {"current_steps": 1660, "total_steps": 9128, "loss": 0.2194, "lr": 3.919162156071868e-05, "epoch": 1.2731108553893364, "percentage": 18.19, "elapsed_time": "11:07:33", "remaining_time": "2 days, 2:03:13"}
333
+ {"current_steps": 1665, "total_steps": 9128, "loss": 0.2297, "lr": 3.918082390614437e-05, "epoch": 1.276946682009973, "percentage": 18.24, "elapsed_time": "11:08:48", "remaining_time": "2 days, 1:57:47"}
334
+ {"current_steps": 1670, "total_steps": 9128, "loss": 0.2302, "lr": 3.916995612352305e-05, "epoch": 1.28078250863061, "percentage": 18.3, "elapsed_time": "11:10:07", "remaining_time": "2 days, 1:52:40"}
335
+ {"current_steps": 1675, "total_steps": 9128, "loss": 0.2222, "lr": 3.915901825258902e-05, "epoch": 1.2846183352512466, "percentage": 18.35, "elapsed_time": "11:11:21", "remaining_time": "2 days, 1:47:15"}
336
+ {"current_steps": 1680, "total_steps": 9128, "loss": 0.2224, "lr": 3.9148010333332814e-05, "epoch": 1.2884541618718834, "percentage": 18.4, "elapsed_time": "11:12:38", "remaining_time": "2 days, 1:42:01"}
337
+ {"current_steps": 1685, "total_steps": 9128, "loss": 0.2199, "lr": 3.913693240600107e-05, "epoch": 1.29228998849252, "percentage": 18.46, "elapsed_time": "11:13:56", "remaining_time": "2 days, 1:36:56"}
338
+ {"current_steps": 1690, "total_steps": 9128, "loss": 0.2251, "lr": 3.912578451109641e-05, "epoch": 1.296125815113157, "percentage": 18.51, "elapsed_time": "11:15:17", "remaining_time": "2 days, 1:32:05"}
339
+ {"current_steps": 1695, "total_steps": 9128, "loss": 0.2203, "lr": 3.9114566689377246e-05, "epoch": 1.2999616417337936, "percentage": 18.57, "elapsed_time": "11:16:32", "remaining_time": "2 days, 1:26:47"}
340
+ {"current_steps": 1700, "total_steps": 9128, "loss": 0.2137, "lr": 3.910327898185768e-05, "epoch": 1.3037974683544304, "percentage": 18.62, "elapsed_time": "11:17:45", "remaining_time": "2 days, 1:21:26"}
341
+ {"current_steps": 1705, "total_steps": 9128, "loss": 0.2127, "lr": 3.909192142980729e-05, "epoch": 1.307633294975067, "percentage": 18.68, "elapsed_time": "11:19:00", "remaining_time": "2 days, 1:16:11"}
342
+ {"current_steps": 1710, "total_steps": 9128, "loss": 0.2131, "lr": 3.908049407475104e-05, "epoch": 1.311469121595704, "percentage": 18.73, "elapsed_time": "11:20:16", "remaining_time": "2 days, 1:11:02"}
343
+ {"current_steps": 1715, "total_steps": 9128, "loss": 0.2138, "lr": 3.90689969584691e-05, "epoch": 1.3153049482163406, "percentage": 18.79, "elapsed_time": "11:21:31", "remaining_time": "2 days, 1:05:50"}
344
+ {"current_steps": 1720, "total_steps": 9128, "loss": 0.224, "lr": 3.905743012299671e-05, "epoch": 1.3191407748369774, "percentage": 18.84, "elapsed_time": "11:22:51", "remaining_time": "2 days, 1:01:01"}
345
+ {"current_steps": 1725, "total_steps": 9128, "loss": 0.2076, "lr": 3.904579361062399e-05, "epoch": 1.322976601457614, "percentage": 18.9, "elapsed_time": "11:24:06", "remaining_time": "2 days, 0:55:53"}
346
+ {"current_steps": 1730, "total_steps": 9128, "loss": 0.2131, "lr": 3.9034087463895826e-05, "epoch": 1.326812428078251, "percentage": 18.95, "elapsed_time": "11:25:20", "remaining_time": "2 days, 0:50:41"}
347
+ {"current_steps": 1735, "total_steps": 9128, "loss": 0.2169, "lr": 3.90223117256117e-05, "epoch": 1.3306482546988876, "percentage": 19.01, "elapsed_time": "11:26:33", "remaining_time": "2 days, 0:45:30"}
348
+ {"current_steps": 1740, "total_steps": 9128, "loss": 0.219, "lr": 3.9010466438825505e-05, "epoch": 1.3344840813195242, "percentage": 19.06, "elapsed_time": "11:27:49", "remaining_time": "2 days, 0:40:27"}
349
+ {"current_steps": 1745, "total_steps": 9128, "loss": 0.2097, "lr": 3.899855164684546e-05, "epoch": 1.338319907940161, "percentage": 19.12, "elapsed_time": "11:29:04", "remaining_time": "2 days, 0:35:25"}
350
+ {"current_steps": 1750, "total_steps": 9128, "loss": 0.207, "lr": 3.898656739323386e-05, "epoch": 1.342155734560798, "percentage": 19.17, "elapsed_time": "11:30:18", "remaining_time": "2 days, 0:30:20"}
351
+ {"current_steps": 1755, "total_steps": 9128, "loss": 0.2009, "lr": 3.897451372180699e-05, "epoch": 1.3459915611814346, "percentage": 19.23, "elapsed_time": "11:31:32", "remaining_time": "2 days, 0:25:15"}
352
+ {"current_steps": 1760, "total_steps": 9128, "loss": 0.2147, "lr": 3.896239067663494e-05, "epoch": 1.3498273878020712, "percentage": 19.28, "elapsed_time": "11:32:48", "remaining_time": "2 days, 0:20:20"}
353
+ {"current_steps": 1765, "total_steps": 9128, "loss": 0.2099, "lr": 3.895019830204141e-05, "epoch": 1.353663214422708, "percentage": 19.34, "elapsed_time": "11:34:04", "remaining_time": "2 days, 0:15:28"}
354
+ {"current_steps": 1770, "total_steps": 9128, "loss": 0.2118, "lr": 3.8937936642603616e-05, "epoch": 1.357499041043345, "percentage": 19.39, "elapsed_time": "11:35:19", "remaining_time": "2 days, 0:10:32"}
355
+ {"current_steps": 1775, "total_steps": 9128, "loss": 0.2128, "lr": 3.892560574315207e-05, "epoch": 1.3613348676639816, "percentage": 19.45, "elapsed_time": "11:36:35", "remaining_time": "2 days, 0:05:37"}
356
+ {"current_steps": 1780, "total_steps": 9128, "loss": 0.2218, "lr": 3.891320564877044e-05, "epoch": 1.3651706942846182, "percentage": 19.5, "elapsed_time": "11:37:50", "remaining_time": "2 days, 0:00:45"}
357
+ {"current_steps": 1785, "total_steps": 9128, "loss": 0.2006, "lr": 3.890073640479536e-05, "epoch": 1.369006520905255, "percentage": 19.56, "elapsed_time": "11:39:04", "remaining_time": "1 day, 23:55:46"}
358
+ {"current_steps": 1790, "total_steps": 9128, "loss": 0.2233, "lr": 3.888819805681635e-05, "epoch": 1.372842347525892, "percentage": 19.61, "elapsed_time": "11:40:22", "remaining_time": "1 day, 23:51:06"}
359
+ {"current_steps": 1795, "total_steps": 9128, "loss": 0.2142, "lr": 3.887559065067551e-05, "epoch": 1.3766781741465286, "percentage": 19.66, "elapsed_time": "11:41:40", "remaining_time": "1 day, 23:46:28"}
360
+ {"current_steps": 1800, "total_steps": 9128, "loss": 0.2287, "lr": 3.886291423246746e-05, "epoch": 1.3805140007671652, "percentage": 19.72, "elapsed_time": "11:42:56", "remaining_time": "1 day, 23:41:46"}
361
+ {"current_steps": 1805, "total_steps": 9128, "loss": 0.2034, "lr": 3.885016884853915e-05, "epoch": 1.384349827387802, "percentage": 19.77, "elapsed_time": "11:45:33", "remaining_time": "1 day, 23:42:30"}