penfever commited on
Commit
56b814c
·
verified ·
1 Parent(s): 78d0ab9

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:d414606f39cff16063ea195679033f455fa27b6b61143f4d23d233a6a42ac9f0
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510925a05d521512dde309b025c72c8e610f9b86226910b0c7ee541b0707c364
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:da2376e026b5a77f7307d11f0a0c93da9fa758baf07e4a6d05d50fa36e4cfc93
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a56b1af47277643d6de82c5980c1476249dfe101d367ed71b5cba8588523720f
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97064aca29b2a360b41328ee5cbd4f2531fc383aef6aa17062e1874cea76a5ff
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666a209f397165e0960da73a68ccecc9aa24284e740a8968ad4002a5c61d2037
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c6d5b2cc48d4326b71807003667dcc09cb5f892ddbd72de5a7c50f9a55c36ca
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17698cdcfa458694ea69b3662abdc0328e43570ea14162173bf3dae8a12005d4
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -719,3 +719,44 @@
719
  {"current_steps": 3595, "total_steps": 9128, "loss": 0.2456, "lr": 3.037732682448179e-05, "epoch": 2.757192174913694, "percentage": 39.38, "elapsed_time": "22:21:55", "remaining_time": "1 day, 10:25:20"}
720
  {"current_steps": 3600, "total_steps": 9128, "loss": 0.2386, "lr": 3.0344616365873345e-05, "epoch": 2.7610280015343305, "percentage": 39.44, "elapsed_time": "22:23:34", "remaining_time": "1 day, 10:23:07"}
721
  {"current_steps": 3605, "total_steps": 9128, "loss": 0.2645, "lr": 3.0311868085753883e-05, "epoch": 2.7648638281549673, "percentage": 39.49, "elapsed_time": "22:26:33", "remaining_time": "1 day, 10:22:58"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
719
  {"current_steps": 3595, "total_steps": 9128, "loss": 0.2456, "lr": 3.037732682448179e-05, "epoch": 2.757192174913694, "percentage": 39.38, "elapsed_time": "22:21:55", "remaining_time": "1 day, 10:25:20"}
720
  {"current_steps": 3600, "total_steps": 9128, "loss": 0.2386, "lr": 3.0344616365873345e-05, "epoch": 2.7610280015343305, "percentage": 39.44, "elapsed_time": "22:23:34", "remaining_time": "1 day, 10:23:07"}
721
  {"current_steps": 3605, "total_steps": 9128, "loss": 0.2645, "lr": 3.0311868085753883e-05, "epoch": 2.7648638281549673, "percentage": 39.49, "elapsed_time": "22:26:33", "remaining_time": "1 day, 10:22:58"}
722
+ {"current_steps": 3610, "total_steps": 9128, "loss": 0.2543, "lr": 3.027908210385616e-05, "epoch": 2.768699654775604, "percentage": 39.55, "elapsed_time": "22:28:17", "remaining_time": "1 day, 10:20:55"}
723
+ {"current_steps": 3615, "total_steps": 9128, "loss": 0.2611, "lr": 3.0246258540050762e-05, "epoch": 2.7725354813962406, "percentage": 39.6, "elapsed_time": "22:30:10", "remaining_time": "1 day, 10:19:03"}
724
+ {"current_steps": 3620, "total_steps": 9128, "loss": 0.2547, "lr": 3.021339751434571e-05, "epoch": 2.7763713080168775, "percentage": 39.66, "elapsed_time": "22:31:51", "remaining_time": "1 day, 10:16:54"}
725
+ {"current_steps": 3625, "total_steps": 9128, "loss": 0.265, "lr": 3.0180499146885976e-05, "epoch": 2.7802071346375143, "percentage": 39.71, "elapsed_time": "22:33:33", "remaining_time": "1 day, 10:14:48"}
726
+ {"current_steps": 3630, "total_steps": 9128, "loss": 0.2588, "lr": 3.014756355795306e-05, "epoch": 2.784042961258151, "percentage": 39.77, "elapsed_time": "22:35:14", "remaining_time": "1 day, 10:12:39"}
727
+ {"current_steps": 3635, "total_steps": 9128, "loss": 0.2523, "lr": 3.011459086796453e-05, "epoch": 2.787878787878788, "percentage": 39.82, "elapsed_time": "22:36:53", "remaining_time": "1 day, 10:10:27"}
728
+ {"current_steps": 3640, "total_steps": 9128, "loss": 0.2489, "lr": 3.008158119747364e-05, "epoch": 2.7917146144994245, "percentage": 39.88, "elapsed_time": "22:38:37", "remaining_time": "1 day, 10:08:22"}
729
+ {"current_steps": 3645, "total_steps": 9128, "loss": 0.2469, "lr": 3.004853466716883e-05, "epoch": 2.7955504411200613, "percentage": 39.93, "elapsed_time": "22:40:15", "remaining_time": "1 day, 10:06:10"}
730
+ {"current_steps": 3650, "total_steps": 9128, "loss": 0.25, "lr": 3.0015451397873307e-05, "epoch": 2.799386267740698, "percentage": 39.99, "elapsed_time": "22:41:51", "remaining_time": "1 day, 10:03:55"}
731
+ {"current_steps": 3655, "total_steps": 9128, "loss": 0.2393, "lr": 2.998233151054458e-05, "epoch": 2.8032220943613346, "percentage": 40.04, "elapsed_time": "22:43:35", "remaining_time": "1 day, 10:01:50"}
732
+ {"current_steps": 3660, "total_steps": 9128, "loss": 0.2382, "lr": 2.9949175126274075e-05, "epoch": 2.8070579209819715, "percentage": 40.1, "elapsed_time": "22:45:12", "remaining_time": "1 day, 9:59:36"}
733
+ {"current_steps": 3665, "total_steps": 9128, "loss": 0.2447, "lr": 2.9915982366286642e-05, "epoch": 2.8108937476026084, "percentage": 40.15, "elapsed_time": "22:46:52", "remaining_time": "1 day, 9:57:26"}
734
+ {"current_steps": 3670, "total_steps": 9128, "loss": 0.264, "lr": 2.9882753351940115e-05, "epoch": 2.814729574223245, "percentage": 40.21, "elapsed_time": "22:48:29", "remaining_time": "1 day, 9:55:12"}
735
+ {"current_steps": 3675, "total_steps": 9128, "loss": 0.2566, "lr": 2.9849488204724902e-05, "epoch": 2.818565400843882, "percentage": 40.26, "elapsed_time": "22:50:09", "remaining_time": "1 day, 9:53:02"}
736
+ {"current_steps": 3680, "total_steps": 9128, "loss": 0.2559, "lr": 2.9816187046263495e-05, "epoch": 2.8224012274645185, "percentage": 40.32, "elapsed_time": "22:51:46", "remaining_time": "1 day, 9:50:49"}
737
+ {"current_steps": 3685, "total_steps": 9128, "loss": 0.2523, "lr": 2.9782849998310067e-05, "epoch": 2.8262370540851554, "percentage": 40.37, "elapsed_time": "22:53:26", "remaining_time": "1 day, 9:48:39"}
738
+ {"current_steps": 3690, "total_steps": 9128, "loss": 0.2512, "lr": 2.974947718275e-05, "epoch": 2.830072880705792, "percentage": 40.43, "elapsed_time": "22:55:09", "remaining_time": "1 day, 9:46:35"}
739
+ {"current_steps": 3695, "total_steps": 9128, "loss": 0.2443, "lr": 2.971606872159944e-05, "epoch": 2.8339087073264286, "percentage": 40.48, "elapsed_time": "22:56:54", "remaining_time": "1 day, 9:44:33"}
740
+ {"current_steps": 3700, "total_steps": 9128, "loss": 0.2478, "lr": 2.9682624737004877e-05, "epoch": 2.8377445339470655, "percentage": 40.53, "elapsed_time": "22:58:36", "remaining_time": "1 day, 9:42:26"}
741
+ {"current_steps": 3705, "total_steps": 9128, "loss": 0.2504, "lr": 2.9649145351242663e-05, "epoch": 2.8415803605677024, "percentage": 40.59, "elapsed_time": "23:00:17", "remaining_time": "1 day, 9:40:19"}
742
+ {"current_steps": 3710, "total_steps": 9128, "loss": 0.2491, "lr": 2.96156306867186e-05, "epoch": 2.845416187188339, "percentage": 40.64, "elapsed_time": "23:01:56", "remaining_time": "1 day, 9:38:09"}
743
+ {"current_steps": 3715, "total_steps": 9128, "loss": 0.2453, "lr": 2.958208086596746e-05, "epoch": 2.849252013808976, "percentage": 40.7, "elapsed_time": "23:03:35", "remaining_time": "1 day, 9:35:59"}
744
+ {"current_steps": 3720, "total_steps": 9128, "loss": 0.2676, "lr": 2.954849601165255e-05, "epoch": 2.8530878404296125, "percentage": 40.75, "elapsed_time": "23:05:19", "remaining_time": "1 day, 9:33:56"}
745
+ {"current_steps": 3725, "total_steps": 9128, "loss": 0.2621, "lr": 2.951487624656528e-05, "epoch": 2.8569236670502494, "percentage": 40.81, "elapsed_time": "23:06:58", "remaining_time": "1 day, 9:31:46"}
746
+ {"current_steps": 3730, "total_steps": 9128, "loss": 0.2597, "lr": 2.948122169362468e-05, "epoch": 2.8607594936708862, "percentage": 40.86, "elapsed_time": "23:08:38", "remaining_time": "1 day, 9:29:37"}
747
+ {"current_steps": 3735, "total_steps": 9128, "loss": 0.2666, "lr": 2.944753247587699e-05, "epoch": 2.8645953202915226, "percentage": 40.92, "elapsed_time": "23:10:14", "remaining_time": "1 day, 9:27:23"}
748
+ {"current_steps": 3740, "total_steps": 9128, "loss": 0.2574, "lr": 2.9413808716495173e-05, "epoch": 2.8684311469121595, "percentage": 40.97, "elapsed_time": "23:11:52", "remaining_time": "1 day, 9:25:11"}
749
+ {"current_steps": 3745, "total_steps": 9128, "loss": 0.2674, "lr": 2.9380050538778498e-05, "epoch": 2.8722669735327964, "percentage": 41.03, "elapsed_time": "23:13:37", "remaining_time": "1 day, 9:23:10"}
750
+ {"current_steps": 3750, "total_steps": 9128, "loss": 0.2691, "lr": 2.9346258066152056e-05, "epoch": 2.8761028001534332, "percentage": 41.08, "elapsed_time": "23:15:14", "remaining_time": "1 day, 9:20:58"}
751
+ {"current_steps": 3755, "total_steps": 9128, "loss": 0.2588, "lr": 2.931243142216633e-05, "epoch": 2.87993862677407, "percentage": 41.14, "elapsed_time": "23:17:01", "remaining_time": "1 day, 9:19:00"}
752
+ {"current_steps": 3760, "total_steps": 9128, "loss": 0.2583, "lr": 2.927857073049674e-05, "epoch": 2.8837744533947065, "percentage": 41.19, "elapsed_time": "23:18:41", "remaining_time": "1 day, 9:16:52"}
753
+ {"current_steps": 3765, "total_steps": 9128, "loss": 0.2601, "lr": 2.9244676114943203e-05, "epoch": 2.8876102800153434, "percentage": 41.25, "elapsed_time": "23:20:20", "remaining_time": "1 day, 9:14:41"}
754
+ {"current_steps": 3770, "total_steps": 9128, "loss": 0.2642, "lr": 2.921074769942965e-05, "epoch": 2.8914461066359802, "percentage": 41.3, "elapsed_time": "23:21:55", "remaining_time": "1 day, 9:12:27"}
755
+ {"current_steps": 3775, "total_steps": 9128, "loss": 0.2603, "lr": 2.9176785608003584e-05, "epoch": 2.8952819332566166, "percentage": 41.36, "elapsed_time": "23:23:34", "remaining_time": "1 day, 9:10:17"}
756
+ {"current_steps": 3780, "total_steps": 9128, "loss": 0.2392, "lr": 2.9142789964835655e-05, "epoch": 2.8991177598772535, "percentage": 41.41, "elapsed_time": "23:25:21", "remaining_time": "1 day, 9:08:19"}
757
+ {"current_steps": 3785, "total_steps": 9128, "loss": 0.2548, "lr": 2.9108760894219173e-05, "epoch": 2.9029535864978904, "percentage": 41.47, "elapsed_time": "23:27:03", "remaining_time": "1 day, 9:06:14"}
758
+ {"current_steps": 3790, "total_steps": 9128, "loss": 0.247, "lr": 2.9074698520569654e-05, "epoch": 2.906789413118527, "percentage": 41.52, "elapsed_time": "23:28:45", "remaining_time": "1 day, 9:04:09"}
759
+ {"current_steps": 3795, "total_steps": 9128, "loss": 0.2588, "lr": 2.9040602968424386e-05, "epoch": 2.9106252397391636, "percentage": 41.58, "elapsed_time": "23:30:24", "remaining_time": "1 day, 9:02:00"}
760
+ {"current_steps": 3800, "total_steps": 9128, "loss": 0.2543, "lr": 2.9006474362441962e-05, "epoch": 2.9144610663598005, "percentage": 41.63, "elapsed_time": "23:32:05", "remaining_time": "1 day, 8:59:54"}
761
+ {"current_steps": 3805, "total_steps": 9128, "loss": 0.2595, "lr": 2.8972312827401824e-05, "epoch": 2.9182968929804374, "percentage": 41.68, "elapsed_time": "23:35:00", "remaining_time": "1 day, 8:59:31"}
762
+ {"current_steps": 3810, "total_steps": 9128, "loss": 0.2533, "lr": 2.89381184882038e-05, "epoch": 2.9221327196010742, "percentage": 41.74, "elapsed_time": "23:36:37", "remaining_time": "1 day, 8:57:20"}