penfever commited on
Commit
e0a0585
·
verified ·
1 Parent(s): 06fc095

Training in progress, step 3800

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61c0d7b1745cc8835434a9160868141ffd6f6e20a9d9ddf030a0551a07f67945
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa2c6fe4cedb8e98d962b5fa6c7a77a190198143caa2a9ba3e52afc9a3727d3
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15a2b359361e74cb5815b5486b4141613a3d47af1fec2be820d835377aa1f0c6
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4fe4222e01a5d2c1068773c2b9fe8d37d9d545ace952a0878646ddf2214e38
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a5470da6120e1c836c3c99a792d49c8857b3847e0c058b103e512d010569e6e
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:366a30a5c3fc56e9bfd2e789ded0ad408327fb97b8367b9aa2825f4956b9568c
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:bb4114dbe0cebe9208006a0bcd8354b7bddbd1eab3af3c02b844ec22ff20b64d
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa7af238ac7b1f6a91f544cbab707fa591f66b41af24479b4fa8ab140919e5f5
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -741,3 +741,43 @@
741
  {"current_steps": 3590, "total_steps": 6713, "loss": 0.2229, "lr": 2.107597371835979e-05, "epoch": 3.743870631194575, "percentage": 53.48, "elapsed_time": "4:35:57", "remaining_time": "4:00:03"}
742
  {"current_steps": 3595, "total_steps": 6713, "loss": 0.2461, "lr": 2.1024040938900586e-05, "epoch": 3.7490871152842984, "percentage": 53.55, "elapsed_time": "4:37:34", "remaining_time": "4:00:44"}
743
  {"current_steps": 3600, "total_steps": 6713, "loss": 0.2212, "lr": 2.097210123572679e-05, "epoch": 3.7543035993740217, "percentage": 53.63, "elapsed_time": "4:39:15", "remaining_time": "4:01:28"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
741
  {"current_steps": 3590, "total_steps": 6713, "loss": 0.2229, "lr": 2.107597371835979e-05, "epoch": 3.743870631194575, "percentage": 53.48, "elapsed_time": "4:35:57", "remaining_time": "4:00:03"}
742
  {"current_steps": 3595, "total_steps": 6713, "loss": 0.2461, "lr": 2.1024040938900586e-05, "epoch": 3.7490871152842984, "percentage": 53.55, "elapsed_time": "4:37:34", "remaining_time": "4:00:44"}
743
  {"current_steps": 3600, "total_steps": 6713, "loss": 0.2212, "lr": 2.097210123572679e-05, "epoch": 3.7543035993740217, "percentage": 53.63, "elapsed_time": "4:39:15", "remaining_time": "4:01:28"}
744
+ {"current_steps": 3605, "total_steps": 6713, "loss": 0.2342, "lr": 2.092015496001155e-05, "epoch": 3.7595200834637454, "percentage": 53.7, "elapsed_time": "4:42:08", "remaining_time": "4:03:14"}
745
+ {"current_steps": 3610, "total_steps": 6713, "loss": 0.2223, "lr": 2.0868202462972458e-05, "epoch": 3.764736567553469, "percentage": 53.78, "elapsed_time": "4:43:46", "remaining_time": "4:03:55"}
746
+ {"current_steps": 3615, "total_steps": 6713, "loss": 0.2241, "lr": 2.0816244095869157e-05, "epoch": 3.7699530516431925, "percentage": 53.85, "elapsed_time": "4:45:33", "remaining_time": "4:04:42"}
747
+ {"current_steps": 3620, "total_steps": 6713, "loss": 0.2204, "lr": 2.0764280210001e-05, "epoch": 3.775169535732916, "percentage": 53.93, "elapsed_time": "4:47:19", "remaining_time": "4:05:29"}
748
+ {"current_steps": 3625, "total_steps": 6713, "loss": 0.2218, "lr": 2.0712311156704624e-05, "epoch": 3.7803860198226396, "percentage": 54.0, "elapsed_time": "4:49:04", "remaining_time": "4:06:14"}
749
+ {"current_steps": 3630, "total_steps": 6713, "loss": 0.2291, "lr": 2.066033728735162e-05, "epoch": 3.7856025039123633, "percentage": 54.07, "elapsed_time": "4:50:43", "remaining_time": "4:06:55"}
750
+ {"current_steps": 3635, "total_steps": 6713, "loss": 0.2205, "lr": 2.0608358953346146e-05, "epoch": 3.7908189880020866, "percentage": 54.15, "elapsed_time": "4:52:24", "remaining_time": "4:07:36"}
751
+ {"current_steps": 3640, "total_steps": 6713, "loss": 0.2184, "lr": 2.0556376506122535e-05, "epoch": 3.79603547209181, "percentage": 54.22, "elapsed_time": "4:54:01", "remaining_time": "4:08:13"}
752
+ {"current_steps": 3645, "total_steps": 6713, "loss": 0.2392, "lr": 2.0504390297142935e-05, "epoch": 3.8012519561815337, "percentage": 54.3, "elapsed_time": "4:55:46", "remaining_time": "4:08:57"}
753
+ {"current_steps": 3650, "total_steps": 6713, "loss": 0.2343, "lr": 2.0452400677894936e-05, "epoch": 3.8064684402712574, "percentage": 54.37, "elapsed_time": "4:57:23", "remaining_time": "4:09:33"}
754
+ {"current_steps": 3655, "total_steps": 6713, "loss": 0.2395, "lr": 2.0400407999889165e-05, "epoch": 3.8116849243609807, "percentage": 54.45, "elapsed_time": "4:59:04", "remaining_time": "4:10:13"}
755
+ {"current_steps": 3660, "total_steps": 6713, "loss": 0.2342, "lr": 2.0348412614656952e-05, "epoch": 3.816901408450704, "percentage": 54.52, "elapsed_time": "5:00:40", "remaining_time": "4:10:48"}
756
+ {"current_steps": 3665, "total_steps": 6713, "loss": 0.2349, "lr": 2.0296414873747915e-05, "epoch": 3.8221178925404278, "percentage": 54.6, "elapsed_time": "5:02:21", "remaining_time": "4:11:26"}
757
+ {"current_steps": 3670, "total_steps": 6713, "loss": 0.2397, "lr": 2.0244415128727612e-05, "epoch": 3.8273343766301515, "percentage": 54.67, "elapsed_time": "5:04:04", "remaining_time": "4:12:07"}
758
+ {"current_steps": 3675, "total_steps": 6713, "loss": 0.2429, "lr": 2.0192413731175146e-05, "epoch": 3.832550860719875, "percentage": 54.74, "elapsed_time": "5:05:42", "remaining_time": "4:12:43"}
759
+ {"current_steps": 3680, "total_steps": 6713, "loss": 0.2221, "lr": 2.0140411032680775e-05, "epoch": 3.837767344809598, "percentage": 54.82, "elapsed_time": "5:07:28", "remaining_time": "4:13:25"}
760
+ {"current_steps": 3685, "total_steps": 6713, "loss": 0.2355, "lr": 2.008840738484359e-05, "epoch": 3.842983828899322, "percentage": 54.89, "elapsed_time": "5:09:06", "remaining_time": "4:13:59"}
761
+ {"current_steps": 3690, "total_steps": 6713, "loss": 0.2373, "lr": 2.0036403139269067e-05, "epoch": 3.8482003129890456, "percentage": 54.97, "elapsed_time": "5:10:45", "remaining_time": "4:14:35"}
762
+ {"current_steps": 3695, "total_steps": 6713, "loss": 0.23, "lr": 1.998439864756674e-05, "epoch": 3.853416797078769, "percentage": 55.04, "elapsed_time": "5:12:22", "remaining_time": "4:15:08"}
763
+ {"current_steps": 3700, "total_steps": 6713, "loss": 0.2275, "lr": 1.993239426134781e-05, "epoch": 3.8586332811684922, "percentage": 55.12, "elapsed_time": "5:14:03", "remaining_time": "4:15:44"}
764
+ {"current_steps": 3705, "total_steps": 6713, "loss": 0.2189, "lr": 1.988039033222275e-05, "epoch": 3.863849765258216, "percentage": 55.19, "elapsed_time": "5:15:47", "remaining_time": "4:16:23"}
765
+ {"current_steps": 3710, "total_steps": 6713, "loss": 0.2313, "lr": 1.982838721179896e-05, "epoch": 3.8690662493479397, "percentage": 55.27, "elapsed_time": "5:17:29", "remaining_time": "4:16:59"}
766
+ {"current_steps": 3715, "total_steps": 6713, "loss": 0.216, "lr": 1.9776385251678352e-05, "epoch": 3.874282733437663, "percentage": 55.34, "elapsed_time": "5:19:11", "remaining_time": "4:17:34"}
767
+ {"current_steps": 3720, "total_steps": 6713, "loss": 0.236, "lr": 1.9724384803455013e-05, "epoch": 3.8794992175273864, "percentage": 55.41, "elapsed_time": "5:20:50", "remaining_time": "4:18:08"}
768
+ {"current_steps": 3725, "total_steps": 6713, "loss": 0.2285, "lr": 1.9672386218712794e-05, "epoch": 3.88471570161711, "percentage": 55.49, "elapsed_time": "5:22:31", "remaining_time": "4:18:42"}
769
+ {"current_steps": 3730, "total_steps": 6713, "loss": 0.2358, "lr": 1.962038984902295e-05, "epoch": 3.889932185706834, "percentage": 55.56, "elapsed_time": "5:24:09", "remaining_time": "4:19:14"}
770
+ {"current_steps": 3735, "total_steps": 6713, "loss": 0.2199, "lr": 1.9568396045941766e-05, "epoch": 3.895148669796557, "percentage": 55.64, "elapsed_time": "5:25:49", "remaining_time": "4:19:46"}
771
+ {"current_steps": 3740, "total_steps": 6713, "loss": 0.237, "lr": 1.951640516100817e-05, "epoch": 3.9003651538862805, "percentage": 55.71, "elapsed_time": "5:27:30", "remaining_time": "4:20:20"}
772
+ {"current_steps": 3745, "total_steps": 6713, "loss": 0.228, "lr": 1.9464417545741352e-05, "epoch": 3.905581637976004, "percentage": 55.79, "elapsed_time": "5:29:15", "remaining_time": "4:20:56"}
773
+ {"current_steps": 3750, "total_steps": 6713, "loss": 0.2202, "lr": 1.941243355163841e-05, "epoch": 3.910798122065728, "percentage": 55.86, "elapsed_time": "5:31:03", "remaining_time": "4:21:34"}
774
+ {"current_steps": 3755, "total_steps": 6713, "loss": 0.2212, "lr": 1.936045353017195e-05, "epoch": 3.9160146061554513, "percentage": 55.94, "elapsed_time": "5:32:47", "remaining_time": "4:22:09"}
775
+ {"current_steps": 3760, "total_steps": 6713, "loss": 0.2226, "lr": 1.9308477832787724e-05, "epoch": 3.9212310902451746, "percentage": 56.01, "elapsed_time": "5:34:31", "remaining_time": "4:22:43"}
776
+ {"current_steps": 3765, "total_steps": 6713, "loss": 0.2198, "lr": 1.9256506810902226e-05, "epoch": 3.9264475743348983, "percentage": 56.09, "elapsed_time": "5:36:10", "remaining_time": "4:23:13"}
777
+ {"current_steps": 3770, "total_steps": 6713, "loss": 0.2163, "lr": 1.9204540815900368e-05, "epoch": 3.931664058424622, "percentage": 56.16, "elapsed_time": "5:37:53", "remaining_time": "4:23:46"}
778
+ {"current_steps": 3775, "total_steps": 6713, "loss": 0.2172, "lr": 1.915258019913306e-05, "epoch": 3.9368805425143454, "percentage": 56.23, "elapsed_time": "5:39:27", "remaining_time": "4:24:11"}
779
+ {"current_steps": 3780, "total_steps": 6713, "loss": 0.2181, "lr": 1.9100625311914855e-05, "epoch": 3.9420970266040687, "percentage": 56.31, "elapsed_time": "5:41:07", "remaining_time": "4:24:41"}
780
+ {"current_steps": 3785, "total_steps": 6713, "loss": 0.229, "lr": 1.9048676505521552e-05, "epoch": 3.9473135106937924, "percentage": 56.38, "elapsed_time": "5:42:51", "remaining_time": "4:25:14"}
781
+ {"current_steps": 3790, "total_steps": 6713, "loss": 0.2411, "lr": 1.8996734131187867e-05, "epoch": 3.952529994783516, "percentage": 56.46, "elapsed_time": "5:44:25", "remaining_time": "4:25:38"}
782
+ {"current_steps": 3795, "total_steps": 6713, "loss": 0.2184, "lr": 1.894479854010499e-05, "epoch": 3.9577464788732395, "percentage": 56.53, "elapsed_time": "5:46:04", "remaining_time": "4:26:05"}
783
+ {"current_steps": 3800, "total_steps": 6713, "loss": 0.2195, "lr": 1.8892870083418272e-05, "epoch": 3.962962962962963, "percentage": 56.61, "elapsed_time": "5:47:44", "remaining_time": "4:26:34"}