penfever commited on
Commit
e3d5e5c
·
verified ·
1 Parent(s): fbf676c

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 sha256:952de354da07df65ccea0d0f5d32dab424b5fe666ba337ab6c2f9c52dcfbc48c
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:465492e897435008fe9d946d7fcb6be162a81d81383c9fd66d227a5fc291b4c7
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:683b033ffb1a83a9853ec6b0e7aaebd522e1716f43828649698a5b9a0519217b
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df41219bbbd77ec6fda385ba95dbdb45909908ffe889785c7f0288e88ef5efe4
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:a9b316a0e38b86aceb5bcca72d66eccbce6bbfecfb5910794e7c28b6095d2b00
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e2e0982439b8b107949011c89bbdfbd087b64571a84b15fc04f9edac0ae674
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:e65eb75d8a7859d9cdb9a4a0071d9c10e24a9406177be252d3f7ef7cdc50c135
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0630173216a7bff51202d16b6690c6a99653e86e1ecda54594d411076fbcd3d5
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -318,3 +318,44 @@
318
  {"current_steps": 1590, "total_steps": 3850, "loss": 0.2617, "lr": 2.9220895487738627e-05, "epoch": 2.8917197452229297, "percentage": 41.3, "elapsed_time": "10:38:38", "remaining_time": "15:07:45"}
319
  {"current_steps": 1595, "total_steps": 3850, "loss": 0.2699, "lr": 2.9140345699015328e-05, "epoch": 2.9008189262966333, "percentage": 41.43, "elapsed_time": "10:40:37", "remaining_time": "15:05:42"}
320
  {"current_steps": 1600, "total_steps": 3850, "loss": 0.286, "lr": 2.905960806723219e-05, "epoch": 2.909918107370337, "percentage": 41.56, "elapsed_time": "10:42:28", "remaining_time": "15:03:29"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
318
  {"current_steps": 1590, "total_steps": 3850, "loss": 0.2617, "lr": 2.9220895487738627e-05, "epoch": 2.8917197452229297, "percentage": 41.3, "elapsed_time": "10:38:38", "remaining_time": "15:07:45"}
319
  {"current_steps": 1595, "total_steps": 3850, "loss": 0.2699, "lr": 2.9140345699015328e-05, "epoch": 2.9008189262966333, "percentage": 41.43, "elapsed_time": "10:40:37", "remaining_time": "15:05:42"}
320
  {"current_steps": 1600, "total_steps": 3850, "loss": 0.286, "lr": 2.905960806723219e-05, "epoch": 2.909918107370337, "percentage": 41.56, "elapsed_time": "10:42:28", "remaining_time": "15:03:29"}
321
+ {"current_steps": 1605, "total_steps": 3850, "loss": 0.2661, "lr": 2.8978684251626652e-05, "epoch": 2.91901728844404, "percentage": 41.69, "elapsed_time": "10:45:38", "remaining_time": "15:03:05"}
322
+ {"current_steps": 1610, "total_steps": 3850, "loss": 0.2496, "lr": 2.8897575915262418e-05, "epoch": 2.9281164695177435, "percentage": 41.82, "elapsed_time": "10:47:54", "remaining_time": "15:01:26"}
323
+ {"current_steps": 1615, "total_steps": 3850, "loss": 0.2614, "lr": 2.8816284724995273e-05, "epoch": 2.9372156505914466, "percentage": 41.95, "elapsed_time": "10:49:56", "remaining_time": "14:59:27"}
324
+ {"current_steps": 1620, "total_steps": 3850, "loss": 0.2622, "lr": 2.8734812351438823e-05, "epoch": 2.94631483166515, "percentage": 42.08, "elapsed_time": "10:51:53", "remaining_time": "14:57:20"}
325
+ {"current_steps": 1625, "total_steps": 3850, "loss": 0.2618, "lr": 2.8653160468930168e-05, "epoch": 2.9554140127388537, "percentage": 42.21, "elapsed_time": "10:53:49", "remaining_time": "14:55:14"}
326
+ {"current_steps": 1630, "total_steps": 3850, "loss": 0.2674, "lr": 2.85713307554955e-05, "epoch": 2.964513193812557, "percentage": 42.34, "elapsed_time": "10:55:42", "remaining_time": "14:53:02"}
327
+ {"current_steps": 1635, "total_steps": 3850, "loss": 0.2524, "lr": 2.8489324892815604e-05, "epoch": 2.9736123748862604, "percentage": 42.47, "elapsed_time": "10:57:47", "remaining_time": "14:51:07"}
328
+ {"current_steps": 1640, "total_steps": 3850, "loss": 0.2641, "lr": 2.8407144566191315e-05, "epoch": 2.9827115559599635, "percentage": 42.6, "elapsed_time": "10:59:50", "remaining_time": "14:49:10"}
329
+ {"current_steps": 1645, "total_steps": 3850, "loss": 0.2804, "lr": 2.8324791464508856e-05, "epoch": 2.991810737033667, "percentage": 42.73, "elapsed_time": "11:01:36", "remaining_time": "14:46:50"}
330
+ {"current_steps": 1650, "total_steps": 3850, "loss": 0.2554, "lr": 2.824226728020516e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "11:03:27", "remaining_time": "14:44:37"}
331
+ {"current_steps": 1655, "total_steps": 3850, "loss": 0.2479, "lr": 2.8159573709233074e-05, "epoch": 3.0090991810737036, "percentage": 42.99, "elapsed_time": "11:05:16", "remaining_time": "14:42:20"}
332
+ {"current_steps": 1660, "total_steps": 3850, "loss": 0.2109, "lr": 2.80767124510265e-05, "epoch": 3.0181983621474067, "percentage": 43.12, "elapsed_time": "11:07:10", "remaining_time": "14:40:11"}
333
+ {"current_steps": 1665, "total_steps": 3850, "loss": 0.2474, "lr": 2.7993685208465483e-05, "epoch": 3.02729754322111, "percentage": 43.25, "elapsed_time": "11:09:13", "remaining_time": "14:38:13"}
334
+ {"current_steps": 1670, "total_steps": 3850, "loss": 0.2465, "lr": 2.7910493687841213e-05, "epoch": 3.0363967242948133, "percentage": 43.38, "elapsed_time": "11:10:58", "remaining_time": "14:35:52"}
335
+ {"current_steps": 1675, "total_steps": 3850, "loss": 0.2359, "lr": 2.7827139598820947e-05, "epoch": 3.045495905368517, "percentage": 43.51, "elapsed_time": "11:12:46", "remaining_time": "14:33:35"}
336
+ {"current_steps": 1680, "total_steps": 3850, "loss": 0.22, "lr": 2.774362465441288e-05, "epoch": 3.05459508644222, "percentage": 43.64, "elapsed_time": "11:14:50", "remaining_time": "14:31:40"}
337
+ {"current_steps": 1685, "total_steps": 3850, "loss": 0.2209, "lr": 2.7659950570930956e-05, "epoch": 3.0636942675159236, "percentage": 43.77, "elapsed_time": "11:16:48", "remaining_time": "14:29:36"}
338
+ {"current_steps": 1690, "total_steps": 3850, "loss": 0.2398, "lr": 2.7576119067959565e-05, "epoch": 3.072793448589627, "percentage": 43.9, "elapsed_time": "11:18:40", "remaining_time": "14:27:24"}
339
+ {"current_steps": 1695, "total_steps": 3850, "loss": 0.2305, "lr": 2.7492131868318247e-05, "epoch": 3.08189262966333, "percentage": 44.03, "elapsed_time": "11:20:30", "remaining_time": "14:25:11"}
340
+ {"current_steps": 1700, "total_steps": 3850, "loss": 0.2255, "lr": 2.7407990698026227e-05, "epoch": 3.0909918107370338, "percentage": 44.16, "elapsed_time": "11:22:49", "remaining_time": "14:23:34"}
341
+ {"current_steps": 1705, "total_steps": 3850, "loss": 0.2451, "lr": 2.7323697286266998e-05, "epoch": 3.100090991810737, "percentage": 44.29, "elapsed_time": "11:24:41", "remaining_time": "14:21:22"}
342
+ {"current_steps": 1710, "total_steps": 3850, "loss": 0.2337, "lr": 2.7239253365352774e-05, "epoch": 3.1091901728844404, "percentage": 44.42, "elapsed_time": "11:26:49", "remaining_time": "14:19:32"}
343
+ {"current_steps": 1715, "total_steps": 3850, "loss": 0.2387, "lr": 2.7154660670688867e-05, "epoch": 3.1182893539581436, "percentage": 44.55, "elapsed_time": "11:28:29", "remaining_time": "14:17:05"}
344
+ {"current_steps": 1720, "total_steps": 3850, "loss": 0.2232, "lr": 2.706992094073803e-05, "epoch": 3.127388535031847, "percentage": 44.68, "elapsed_time": "11:30:46", "remaining_time": "14:15:25"}
345
+ {"current_steps": 1725, "total_steps": 3850, "loss": 0.2488, "lr": 2.6985035916984746e-05, "epoch": 3.1364877161055507, "percentage": 44.81, "elapsed_time": "11:32:32", "remaining_time": "14:13:07"}
346
+ {"current_steps": 1730, "total_steps": 3850, "loss": 0.2331, "lr": 2.6900007343899414e-05, "epoch": 3.1455868971792538, "percentage": 44.94, "elapsed_time": "11:34:24", "remaining_time": "14:10:57"}
347
+ {"current_steps": 1735, "total_steps": 3850, "loss": 0.2378, "lr": 2.6814836968902535e-05, "epoch": 3.1546860782529573, "percentage": 45.06, "elapsed_time": "11:36:12", "remaining_time": "14:08:41"}
348
+ {"current_steps": 1740, "total_steps": 3850, "loss": 0.2372, "lr": 2.6729526542328755e-05, "epoch": 3.1637852593266604, "percentage": 45.19, "elapsed_time": "11:38:18", "remaining_time": "14:06:47"}
349
+ {"current_steps": 1745, "total_steps": 3850, "loss": 0.2351, "lr": 2.6644077817390933e-05, "epoch": 3.172884440400364, "percentage": 45.32, "elapsed_time": "11:40:13", "remaining_time": "14:04:41"}
350
+ {"current_steps": 1750, "total_steps": 3850, "loss": 0.2388, "lr": 2.6558492550144092e-05, "epoch": 3.1819836214740675, "percentage": 45.45, "elapsed_time": "11:42:04", "remaining_time": "14:02:29"}
351
+ {"current_steps": 1755, "total_steps": 3850, "loss": 0.2321, "lr": 2.6472772499449323e-05, "epoch": 3.1910828025477707, "percentage": 45.58, "elapsed_time": "11:43:49", "remaining_time": "14:00:10"}
352
+ {"current_steps": 1760, "total_steps": 3850, "loss": 0.2365, "lr": 2.6386919426937655e-05, "epoch": 3.200181983621474, "percentage": 45.71, "elapsed_time": "11:45:34", "remaining_time": "13:57:52"}
353
+ {"current_steps": 1765, "total_steps": 3850, "loss": 0.2525, "lr": 2.6300935096973858e-05, "epoch": 3.2092811646951773, "percentage": 45.84, "elapsed_time": "11:47:37", "remaining_time": "13:55:55"}
354
+ {"current_steps": 1770, "total_steps": 3850, "loss": 0.231, "lr": 2.6214821276620157e-05, "epoch": 3.218380345768881, "percentage": 45.97, "elapsed_time": "11:49:35", "remaining_time": "13:53:52"}
355
+ {"current_steps": 1775, "total_steps": 3850, "loss": 0.2216, "lr": 2.6128579735599924e-05, "epoch": 3.227479526842584, "percentage": 46.1, "elapsed_time": "11:51:37", "remaining_time": "13:51:54"}
356
+ {"current_steps": 1780, "total_steps": 3850, "loss": 0.2391, "lr": 2.6042212246261337e-05, "epoch": 3.2365787079162875, "percentage": 46.23, "elapsed_time": "11:53:53", "remaining_time": "13:50:12"}
357
+ {"current_steps": 1785, "total_steps": 3850, "loss": 0.2215, "lr": 2.595572058354092e-05, "epoch": 3.245677888989991, "percentage": 46.36, "elapsed_time": "11:56:03", "remaining_time": "13:48:23"}
358
+ {"current_steps": 1790, "total_steps": 3850, "loss": 0.2415, "lr": 2.5869106524927096e-05, "epoch": 3.254777070063694, "percentage": 46.49, "elapsed_time": "11:58:09", "remaining_time": "13:46:28"}
359
+ {"current_steps": 1795, "total_steps": 3850, "loss": 0.2297, "lr": 2.5782371850423627e-05, "epoch": 3.2638762511373978, "percentage": 46.62, "elapsed_time": "12:00:10", "remaining_time": "13:44:29"}
360
+ {"current_steps": 1800, "total_steps": 3850, "loss": 0.2287, "lr": 2.5695518342513047e-05, "epoch": 3.272975432211101, "percentage": 46.75, "elapsed_time": "12:02:08", "remaining_time": "13:42:26"}
361
+ {"current_steps": 1805, "total_steps": 3850, "loss": 0.235, "lr": 2.5608547786120056e-05, "epoch": 3.2820746132848044, "percentage": 46.88, "elapsed_time": "12:05:11", "remaining_time": "13:41:36"}