penfever commited on
Commit
837715f
·
verified ·
1 Parent(s): 34a987f

Training in progress, step 5200

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:792992549bc7d3644b538e5a3ed3c71ba5b5c000bcfcf68070311573fe87f006
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1589e19370956aad04ab7769c9d94ea6dae9dbc3667bfc869c42f38e6c613ef
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38417203f8b83879d0abf7861950ddd02674ba0484eeb13cb035ab44c767eb0d
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53b8afb631aef6da3d90848348fdaab3cf515a04275f7dc558b89897e2298968
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69165d5c2b797a12518ee45117ed4b34aab95805c2e6bb13824692c41edb60fe
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ddb7d282ca44748839f9636735f8c30fb31faa5e159c4aa7051f5f302391c06
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b05809d9bf678dc4641f69e5255834e349246ed83421a7eb6b39ae259ef2aed
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3a38660d9e06711faba5b0b345f6f079386788f22ef7cd11742d6ccc813f82
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -998,3 +998,43 @@
998
  {"current_steps": 4990, "total_steps": 6713, "loss": 0.183, "lr": 7.513947204275453e-06, "epoch": 5.204486176317162, "percentage": 74.33, "elapsed_time": "22:03:06", "remaining_time": "7:36:51"}
999
  {"current_steps": 4995, "total_steps": 6713, "loss": 0.172, "lr": 7.473364440588404e-06, "epoch": 5.209702660406886, "percentage": 74.41, "elapsed_time": "22:05:42", "remaining_time": "7:35:58"}
1000
  {"current_steps": 5000, "total_steps": 6713, "loss": 0.171, "lr": 7.432866371610403e-06, "epoch": 5.214919144496609, "percentage": 74.48, "elapsed_time": "22:08:34", "remaining_time": "7:35:10"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
998
  {"current_steps": 4990, "total_steps": 6713, "loss": 0.183, "lr": 7.513947204275453e-06, "epoch": 5.204486176317162, "percentage": 74.33, "elapsed_time": "22:03:06", "remaining_time": "7:36:51"}
999
  {"current_steps": 4995, "total_steps": 6713, "loss": 0.172, "lr": 7.473364440588404e-06, "epoch": 5.209702660406886, "percentage": 74.41, "elapsed_time": "22:05:42", "remaining_time": "7:35:58"}
1000
  {"current_steps": 5000, "total_steps": 6713, "loss": 0.171, "lr": 7.432866371610403e-06, "epoch": 5.214919144496609, "percentage": 74.48, "elapsed_time": "22:08:34", "remaining_time": "7:35:10"}
1001
+ {"current_steps": 5005, "total_steps": 6713, "loss": 0.1736, "lr": 7.392453271155786e-06, "epoch": 5.220135628586333, "percentage": 74.56, "elapsed_time": "22:12:45", "remaining_time": "7:34:49"}
1002
+ {"current_steps": 5010, "total_steps": 6713, "loss": 0.1717, "lr": 7.352125412464368e-06, "epoch": 5.225352112676056, "percentage": 74.63, "elapsed_time": "22:15:32", "remaining_time": "7:33:58"}
1003
+ {"current_steps": 5015, "total_steps": 6713, "loss": 0.1707, "lr": 7.311883068199659e-06, "epoch": 5.23056859676578, "percentage": 74.71, "elapsed_time": "22:18:16", "remaining_time": "7:33:07"}
1004
+ {"current_steps": 5020, "total_steps": 6713, "loss": 0.1781, "lr": 7.271726510446968e-06, "epoch": 5.2357850808555035, "percentage": 74.78, "elapsed_time": "22:21:11", "remaining_time": "7:32:19"}
1005
+ {"current_steps": 5025, "total_steps": 6713, "loss": 0.1677, "lr": 7.231656010711609e-06, "epoch": 5.241001564945227, "percentage": 74.85, "elapsed_time": "22:23:52", "remaining_time": "7:31:26"}
1006
+ {"current_steps": 5030, "total_steps": 6713, "loss": 0.1712, "lr": 7.191671839917025e-06, "epoch": 5.24621804903495, "percentage": 74.93, "elapsed_time": "22:26:33", "remaining_time": "7:30:33"}
1007
+ {"current_steps": 5035, "total_steps": 6713, "loss": 0.1813, "lr": 7.15177426840298e-06, "epoch": 5.251434533124674, "percentage": 75.0, "elapsed_time": "22:29:16", "remaining_time": "7:29:40"}
1008
+ {"current_steps": 5040, "total_steps": 6713, "loss": 0.1801, "lr": 7.111963565923723e-06, "epoch": 5.256651017214398, "percentage": 75.08, "elapsed_time": "22:32:06", "remaining_time": "7:28:49"}
1009
+ {"current_steps": 5045, "total_steps": 6713, "loss": 0.1692, "lr": 7.07224000164618e-06, "epoch": 5.261867501304121, "percentage": 75.15, "elapsed_time": "22:34:59", "remaining_time": "7:27:59"}
1010
+ {"current_steps": 5050, "total_steps": 6713, "loss": 0.1683, "lr": 7.032603844148098e-06, "epoch": 5.267083985393844, "percentage": 75.23, "elapsed_time": "22:37:51", "remaining_time": "7:27:09"}
1011
+ {"current_steps": 5055, "total_steps": 6713, "loss": 0.1846, "lr": 6.993055361416281e-06, "epoch": 5.272300469483568, "percentage": 75.3, "elapsed_time": "22:40:27", "remaining_time": "7:26:13"}
1012
+ {"current_steps": 5060, "total_steps": 6713, "loss": 0.1721, "lr": 6.953594820844725e-06, "epoch": 5.277516953573292, "percentage": 75.38, "elapsed_time": "22:43:23", "remaining_time": "7:25:23"}
1013
+ {"current_steps": 5065, "total_steps": 6713, "loss": 0.1602, "lr": 6.914222489232834e-06, "epoch": 5.2827334376630155, "percentage": 75.45, "elapsed_time": "22:46:14", "remaining_time": "7:24:31"}
1014
+ {"current_steps": 5070, "total_steps": 6713, "loss": 0.1755, "lr": 6.874938632783639e-06, "epoch": 5.287949921752738, "percentage": 75.53, "elapsed_time": "22:48:45", "remaining_time": "7:23:33"}
1015
+ {"current_steps": 5075, "total_steps": 6713, "loss": 0.169, "lr": 6.835743517101947e-06, "epoch": 5.293166405842462, "percentage": 75.6, "elapsed_time": "22:51:38", "remaining_time": "7:22:42"}
1016
+ {"current_steps": 5080, "total_steps": 6713, "loss": 0.1677, "lr": 6.796637407192608e-06, "epoch": 5.298382889932186, "percentage": 75.67, "elapsed_time": "22:54:28", "remaining_time": "7:21:50"}
1017
+ {"current_steps": 5085, "total_steps": 6713, "loss": 0.1734, "lr": 6.7576205674586405e-06, "epoch": 5.30359937402191, "percentage": 75.75, "elapsed_time": "22:57:27", "remaining_time": "7:21:00"}
1018
+ {"current_steps": 5090, "total_steps": 6713, "loss": 0.1739, "lr": 6.718693261699542e-06, "epoch": 5.3088158581116325, "percentage": 75.82, "elapsed_time": "22:59:56", "remaining_time": "7:20:00"}
1019
+ {"current_steps": 5095, "total_steps": 6713, "loss": 0.1798, "lr": 6.679855753109419e-06, "epoch": 5.314032342201356, "percentage": 75.9, "elapsed_time": "23:02:35", "remaining_time": "7:19:03"}
1020
+ {"current_steps": 5100, "total_steps": 6713, "loss": 0.179, "lr": 6.64110830427527e-06, "epoch": 5.31924882629108, "percentage": 75.97, "elapsed_time": "23:05:23", "remaining_time": "7:18:09"}
1021
+ {"current_steps": 5105, "total_steps": 6713, "loss": 0.1733, "lr": 6.602451177175162e-06, "epoch": 5.324465310380804, "percentage": 76.05, "elapsed_time": "23:08:03", "remaining_time": "7:17:12"}
1022
+ {"current_steps": 5110, "total_steps": 6713, "loss": 0.1784, "lr": 6.563884633176505e-06, "epoch": 5.329681794470527, "percentage": 76.12, "elapsed_time": "23:10:59", "remaining_time": "7:16:21"}
1023
+ {"current_steps": 5115, "total_steps": 6713, "loss": 0.1662, "lr": 6.5254089330342366e-06, "epoch": 5.33489827856025, "percentage": 76.2, "elapsed_time": "23:13:48", "remaining_time": "7:15:26"}
1024
+ {"current_steps": 5120, "total_steps": 6713, "loss": 0.1803, "lr": 6.487024336889107e-06, "epoch": 5.340114762649974, "percentage": 76.27, "elapsed_time": "23:16:25", "remaining_time": "7:14:28"}
1025
+ {"current_steps": 5125, "total_steps": 6713, "loss": 0.1885, "lr": 6.448731104265871e-06, "epoch": 5.345331246739698, "percentage": 76.34, "elapsed_time": "23:19:00", "remaining_time": "7:13:29"}
1026
+ {"current_steps": 5130, "total_steps": 6713, "loss": 0.176, "lr": 6.410529494071596e-06, "epoch": 5.350547730829421, "percentage": 76.42, "elapsed_time": "23:21:39", "remaining_time": "7:12:31"}
1027
+ {"current_steps": 5135, "total_steps": 6713, "loss": 0.1775, "lr": 6.372419764593825e-06, "epoch": 5.3557642149191445, "percentage": 76.49, "elapsed_time": "23:24:22", "remaining_time": "7:11:34"}
1028
+ {"current_steps": 5140, "total_steps": 6713, "loss": 0.1699, "lr": 6.334402173498926e-06, "epoch": 5.360980699008868, "percentage": 76.57, "elapsed_time": "23:27:07", "remaining_time": "7:10:37"}
1029
+ {"current_steps": 5145, "total_steps": 6713, "loss": 0.1683, "lr": 6.296476977830272e-06, "epoch": 5.366197183098592, "percentage": 76.64, "elapsed_time": "23:29:47", "remaining_time": "7:09:39"}
1030
+ {"current_steps": 5150, "total_steps": 6713, "loss": 0.186, "lr": 6.2586444340065625e-06, "epoch": 5.371413667188315, "percentage": 76.72, "elapsed_time": "23:32:14", "remaining_time": "7:08:36"}
1031
+ {"current_steps": 5155, "total_steps": 6713, "loss": 0.1714, "lr": 6.22090479782004e-06, "epoch": 5.376630151278039, "percentage": 76.79, "elapsed_time": "23:34:54", "remaining_time": "7:07:37"}
1032
+ {"current_steps": 5160, "total_steps": 6713, "loss": 0.1691, "lr": 6.18325832443478e-06, "epoch": 5.381846635367762, "percentage": 76.87, "elapsed_time": "23:37:48", "remaining_time": "7:06:42"}
1033
+ {"current_steps": 5165, "total_steps": 6713, "loss": 0.1778, "lr": 6.145705268384996e-06, "epoch": 5.387063119457486, "percentage": 76.94, "elapsed_time": "23:40:33", "remaining_time": "7:05:45"}
1034
+ {"current_steps": 5170, "total_steps": 6713, "loss": 0.1822, "lr": 6.108245883573258e-06, "epoch": 5.392279603547209, "percentage": 77.01, "elapsed_time": "23:43:23", "remaining_time": "7:04:48"}
1035
+ {"current_steps": 5175, "total_steps": 6713, "loss": 0.182, "lr": 6.070880423268839e-06, "epoch": 5.397496087636933, "percentage": 77.09, "elapsed_time": "23:46:07", "remaining_time": "7:03:50"}
1036
+ {"current_steps": 5180, "total_steps": 6713, "loss": 0.167, "lr": 6.033609140105949e-06, "epoch": 5.402712571726656, "percentage": 77.16, "elapsed_time": "23:48:50", "remaining_time": "7:02:51"}
1037
+ {"current_steps": 5185, "total_steps": 6713, "loss": 0.1809, "lr": 5.996432286082061e-06, "epoch": 5.40792905581638, "percentage": 77.24, "elapsed_time": "23:51:32", "remaining_time": "7:01:52"}
1038
+ {"current_steps": 5190, "total_steps": 6713, "loss": 0.1732, "lr": 5.9593501125561885e-06, "epoch": 5.413145539906103, "percentage": 77.31, "elapsed_time": "23:54:17", "remaining_time": "7:00:53"}
1039
+ {"current_steps": 5195, "total_steps": 6713, "loss": 0.1727, "lr": 5.922362870247214e-06, "epoch": 5.418362023995827, "percentage": 77.39, "elapsed_time": "23:56:56", "remaining_time": "6:59:52"}
1040
+ {"current_steps": 5200, "total_steps": 6713, "loss": 0.1743, "lr": 5.885470809232143e-06, "epoch": 5.4235785080855505, "percentage": 77.46, "elapsed_time": "23:59:21", "remaining_time": "6:58:47"}