penfever commited on
Commit
31309aa
·
verified ·
1 Parent(s): de7c3f3

Training in progress, step 3400

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b06bdbb4bdde9a7c9c13e2d2faad6eec6f3b84da845f4ed3b8e68c2ea7127cd5
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0783ba4d086623d4a7dc31f07c9e0996933525dc9dd23ba9771564de01d31d0
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b6a21371bf4118ae91ecd6c1bf537cefb9ede5c088aa2d7c469707e123e6d69
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a7f9d9745fe2e1f953b232c02c39e387199faa5ace0e17d9d79537a026cfff
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ba08d449e116e0c7969e16938839268d8a51b13a1f0f9c201d194733a4da8fe
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d263ecd70f1db7672446d46cb5da18db754ce0fb62dff4815f3958be3143bf
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:475a6a3e4e280e9060d99cb88190d3ebabba2e1a7984671892adb4cde8fc5aee
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6e1d752281d88047fd330bea09b91a4041e5e24ad082088af4bbe72af484769
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -640,3 +640,42 @@
640
  {"current_steps": 3200, "total_steps": 3850, "loss": 0.1952, "lr": 3.383842065838907e-06, "epoch": 5.818926296633303, "percentage": 83.12, "elapsed_time": "21:25:18", "remaining_time": "4:21:04"}
641
  {"current_steps": 3205, "total_steps": 3850, "loss": 0.1918, "lr": 3.3335517205818e-06, "epoch": 5.828025477707007, "percentage": 83.25, "elapsed_time": "21:28:35", "remaining_time": "4:19:19"}
642
  {"current_steps": 3210, "total_steps": 3850, "loss": 0.1941, "lr": 3.2836038871666444e-06, "epoch": 5.837124658780709, "percentage": 83.38, "elapsed_time": "21:30:28", "remaining_time": "4:17:17"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
640
  {"current_steps": 3200, "total_steps": 3850, "loss": 0.1952, "lr": 3.383842065838907e-06, "epoch": 5.818926296633303, "percentage": 83.12, "elapsed_time": "21:25:18", "remaining_time": "4:21:04"}
641
  {"current_steps": 3205, "total_steps": 3850, "loss": 0.1918, "lr": 3.3335517205818e-06, "epoch": 5.828025477707007, "percentage": 83.25, "elapsed_time": "21:28:35", "remaining_time": "4:19:19"}
642
  {"current_steps": 3210, "total_steps": 3850, "loss": 0.1941, "lr": 3.2836038871666444e-06, "epoch": 5.837124658780709, "percentage": 83.38, "elapsed_time": "21:30:28", "remaining_time": "4:17:17"}
643
+ {"current_steps": 3215, "total_steps": 3850, "loss": 0.1943, "lr": 3.2339995920703517e-06, "epoch": 5.846223839854413, "percentage": 83.51, "elapsed_time": "21:32:36", "remaining_time": "4:15:18"}
644
+ {"current_steps": 3220, "total_steps": 3850, "loss": 0.1908, "lr": 3.184739854709784e-06, "epoch": 5.855323020928116, "percentage": 83.64, "elapsed_time": "21:34:42", "remaining_time": "4:13:18"}
645
+ {"current_steps": 3225, "total_steps": 3850, "loss": 0.1944, "lr": 3.1358256874208214e-06, "epoch": 5.86442220200182, "percentage": 83.77, "elapsed_time": "21:36:37", "remaining_time": "4:11:17"}
646
+ {"current_steps": 3230, "total_steps": 3850, "loss": 0.177, "lr": 3.0872580954375177e-06, "epoch": 5.8735213830755235, "percentage": 83.9, "elapsed_time": "21:38:48", "remaining_time": "4:09:18"}
647
+ {"current_steps": 3235, "total_steps": 3850, "loss": 0.2001, "lr": 3.039038076871481e-06, "epoch": 5.882620564149226, "percentage": 84.03, "elapsed_time": "21:40:51", "remaining_time": "4:07:18"}
648
+ {"current_steps": 3240, "total_steps": 3850, "loss": 0.184, "lr": 2.9911666226913374e-06, "epoch": 5.89171974522293, "percentage": 84.16, "elapsed_time": "21:42:50", "remaining_time": "4:05:17"}
649
+ {"current_steps": 3245, "total_steps": 3850, "loss": 0.1972, "lr": 2.9436447167023674e-06, "epoch": 5.900818926296633, "percentage": 84.29, "elapsed_time": "21:44:49", "remaining_time": "4:03:16"}
650
+ {"current_steps": 3250, "total_steps": 3850, "loss": 0.1979, "lr": 2.896473335526313e-06, "epoch": 5.909918107370337, "percentage": 84.42, "elapsed_time": "21:46:46", "remaining_time": "4:01:14"}
651
+ {"current_steps": 3255, "total_steps": 3850, "loss": 0.2019, "lr": 2.849653448581271e-06, "epoch": 5.91901728844404, "percentage": 84.55, "elapsed_time": "21:48:42", "remaining_time": "3:59:13"}
652
+ {"current_steps": 3260, "total_steps": 3850, "loss": 0.1945, "lr": 2.8031860180617898e-06, "epoch": 5.928116469517743, "percentage": 84.68, "elapsed_time": "21:50:28", "remaining_time": "3:57:10"}
653
+ {"current_steps": 3265, "total_steps": 3850, "loss": 0.2018, "lr": 2.757071998919094e-06, "epoch": 5.937215650591447, "percentage": 84.81, "elapsed_time": "21:52:20", "remaining_time": "3:55:08"}
654
+ {"current_steps": 3270, "total_steps": 3850, "loss": 0.1798, "lr": 2.7113123388414674e-06, "epoch": 5.94631483166515, "percentage": 84.94, "elapsed_time": "21:54:04", "remaining_time": "3:53:04"}
655
+ {"current_steps": 3275, "total_steps": 3850, "loss": 0.1958, "lr": 2.665907978234754e-06, "epoch": 5.955414012738854, "percentage": 85.06, "elapsed_time": "21:56:01", "remaining_time": "3:51:03"}
656
+ {"current_steps": 3280, "total_steps": 3850, "loss": 0.2124, "lr": 2.6208598502030546e-06, "epoch": 5.964513193812557, "percentage": 85.19, "elapsed_time": "21:58:10", "remaining_time": "3:49:04"}
657
+ {"current_steps": 3285, "total_steps": 3850, "loss": 0.1758, "lr": 2.5761688805295305e-06, "epoch": 5.97361237488626, "percentage": 85.32, "elapsed_time": "22:00:25", "remaining_time": "3:47:06"}
658
+ {"current_steps": 3290, "total_steps": 3850, "loss": 0.1948, "lr": 2.531835987657407e-06, "epoch": 5.9827115559599635, "percentage": 85.45, "elapsed_time": "22:02:13", "remaining_time": "3:45:03"}
659
+ {"current_steps": 3295, "total_steps": 3850, "loss": 0.1954, "lr": 2.487862082671064e-06, "epoch": 5.991810737033667, "percentage": 85.58, "elapsed_time": "22:04:16", "remaining_time": "3:43:03"}
660
+ {"current_steps": 3300, "total_steps": 3850, "loss": 0.2004, "lr": 2.4442480692773398e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "22:06:06", "remaining_time": "3:41:01"}
661
+ {"current_steps": 3305, "total_steps": 3850, "loss": 0.1874, "lr": 2.400994843786939e-06, "epoch": 6.0090991810737036, "percentage": 85.84, "elapsed_time": "22:08:16", "remaining_time": "3:39:02"}
662
+ {"current_steps": 3310, "total_steps": 3850, "loss": 0.1806, "lr": 2.3581032950960215e-06, "epoch": 6.018198362147407, "percentage": 85.97, "elapsed_time": "22:10:01", "remaining_time": "3:36:59"}
663
+ {"current_steps": 3315, "total_steps": 3850, "loss": 0.1795, "lr": 2.3155743046679468e-06, "epoch": 6.02729754322111, "percentage": 86.1, "elapsed_time": "22:12:00", "remaining_time": "3:34:58"}
664
+ {"current_steps": 3320, "total_steps": 3850, "loss": 0.2045, "lr": 2.273408746515133e-06, "epoch": 6.036396724294813, "percentage": 86.23, "elapsed_time": "22:13:53", "remaining_time": "3:32:56"}
665
+ {"current_steps": 3325, "total_steps": 3850, "loss": 0.1911, "lr": 2.2316074871811157e-06, "epoch": 6.045495905368517, "percentage": 86.36, "elapsed_time": "22:16:02", "remaining_time": "3:30:57"}
666
+ {"current_steps": 3330, "total_steps": 3850, "loss": 0.1837, "lr": 2.190171385722726e-06, "epoch": 6.05459508644222, "percentage": 86.49, "elapsed_time": "22:18:01", "remaining_time": "3:28:56"}
667
+ {"current_steps": 3335, "total_steps": 3850, "loss": 0.1814, "lr": 2.1491012936924548e-06, "epoch": 6.063694267515924, "percentage": 86.62, "elapsed_time": "22:20:01", "remaining_time": "3:26:55"}
668
+ {"current_steps": 3340, "total_steps": 3850, "loss": 0.1885, "lr": 2.108398055120926e-06, "epoch": 6.072793448589627, "percentage": 86.75, "elapsed_time": "22:21:50", "remaining_time": "3:24:53"}
669
+ {"current_steps": 3345, "total_steps": 3850, "loss": 0.1938, "lr": 2.068062506499584e-06, "epoch": 6.08189262966333, "percentage": 86.88, "elapsed_time": "22:24:04", "remaining_time": "3:22:55"}
670
+ {"current_steps": 3350, "total_steps": 3850, "loss": 0.1814, "lr": 2.0280954767634674e-06, "epoch": 6.090991810737034, "percentage": 87.01, "elapsed_time": "22:25:58", "remaining_time": "3:20:53"}
671
+ {"current_steps": 3355, "total_steps": 3850, "loss": 0.1726, "lr": 1.988497787274195e-06, "epoch": 6.100090991810737, "percentage": 87.14, "elapsed_time": "22:27:55", "remaining_time": "3:18:52"}
672
+ {"current_steps": 3360, "total_steps": 3850, "loss": 0.1739, "lr": 1.9492702518030905e-06, "epoch": 6.10919017288444, "percentage": 87.27, "elapsed_time": "22:29:51", "remaining_time": "3:16:51"}
673
+ {"current_steps": 3365, "total_steps": 3850, "loss": 0.1872, "lr": 1.910413676514438e-06, "epoch": 6.1182893539581436, "percentage": 87.4, "elapsed_time": "22:31:49", "remaining_time": "3:14:50"}
674
+ {"current_steps": 3370, "total_steps": 3850, "loss": 0.1849, "lr": 1.8719288599489304e-06, "epoch": 6.127388535031847, "percentage": 87.53, "elapsed_time": "22:33:42", "remaining_time": "3:12:48"}
675
+ {"current_steps": 3375, "total_steps": 3850, "loss": 0.1876, "lr": 1.833816593007256e-06, "epoch": 6.136487716105551, "percentage": 87.66, "elapsed_time": "22:35:45", "remaining_time": "3:10:48"}
676
+ {"current_steps": 3380, "total_steps": 3850, "loss": 0.1799, "lr": 1.796077658933848e-06, "epoch": 6.145586897179254, "percentage": 87.79, "elapsed_time": "22:37:37", "remaining_time": "3:08:46"}
677
+ {"current_steps": 3385, "total_steps": 3850, "loss": 0.1756, "lr": 1.7587128333007709e-06, "epoch": 6.154686078252957, "percentage": 87.92, "elapsed_time": "22:39:39", "remaining_time": "3:06:46"}
678
+ {"current_steps": 3390, "total_steps": 3850, "loss": 0.1882, "lr": 1.7217228839918098e-06, "epoch": 6.16378525932666, "percentage": 88.05, "elapsed_time": "22:41:23", "remaining_time": "3:04:43"}
679
+ {"current_steps": 3395, "total_steps": 3850, "loss": 0.1896, "lr": 1.6851085711866598e-06, "epoch": 6.172884440400364, "percentage": 88.18, "elapsed_time": "22:43:16", "remaining_time": "3:02:42"}
680
+ {"current_steps": 3400, "total_steps": 3850, "loss": 0.179, "lr": 1.648870647345322e-06, "epoch": 6.1819836214740675, "percentage": 88.31, "elapsed_time": "22:45:07", "remaining_time": "3:00:40"}
681
+ {"current_steps": 3405, "total_steps": 3850, "loss": 0.1759, "lr": 1.6130098571926468e-06, "epoch": 6.191082802547771, "percentage": 88.44, "elapsed_time": "22:48:08", "remaining_time": "2:58:48"}