rbelanec commited on
Commit
54b456e
·
verified ·
1 Parent(s): 25ff123

Training in progress, step 39800

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +42 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89f45947afc90d0d85b79f0bf0c9564073ba3b8e0ab93b228a73fc10543d68f0
3
  size 58745928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45a1b7f6b2d83813bba0bc8b63284dae044b25661d31cf5199ee92c8cf721fc2
3
  size 58745928
trainer_log.jsonl CHANGED
@@ -8117,3 +8117,45 @@
8117
  {"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 1.2397742806111168e-08, "epoch": 18.67043847241867, "percentage": 99.0, "elapsed_time": "6:19:03", "remaining_time": "0:03:49", "throughput": 1614.66, "total_tokens": 36723376}
8118
  {"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.6339649558067322, "epoch": 18.67043847241867, "percentage": 99.0, "elapsed_time": "6:19:31", "remaining_time": "0:03:50", "throughput": 1612.69, "total_tokens": 36723376}
8119
  {"current_steps": 39605, "total_steps": 40000, "loss": 0.0, "lr": 1.209052442764369e-08, "epoch": 18.672795851013674, "percentage": 99.01, "elapsed_time": "6:19:34", "remaining_time": "0:03:47", "throughput": 1612.67, "total_tokens": 36728448}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8117
  {"current_steps": 39600, "total_steps": 40000, "loss": 0.0, "lr": 1.2397742806111168e-08, "epoch": 18.67043847241867, "percentage": 99.0, "elapsed_time": "6:19:03", "remaining_time": "0:03:49", "throughput": 1614.66, "total_tokens": 36723376}
8118
  {"current_steps": 39600, "total_steps": 40000, "eval_loss": 0.6339649558067322, "epoch": 18.67043847241867, "percentage": 99.0, "elapsed_time": "6:19:31", "remaining_time": "0:03:50", "throughput": 1612.69, "total_tokens": 36723376}
8119
  {"current_steps": 39605, "total_steps": 40000, "loss": 0.0, "lr": 1.209052442764369e-08, "epoch": 18.672795851013674, "percentage": 99.01, "elapsed_time": "6:19:34", "remaining_time": "0:03:47", "throughput": 1612.67, "total_tokens": 36728448}
8120
+ {"current_steps": 39610, "total_steps": 40000, "loss": 0.0, "lr": 1.17871594988328e-08, "epoch": 18.675153229608675, "percentage": 99.02, "elapsed_time": "6:19:37", "remaining_time": "0:03:44", "throughput": 1612.71, "total_tokens": 36733072}
8121
+ {"current_steps": 39615, "total_steps": 40000, "loss": 0.0, "lr": 1.1487648066466072e-08, "epoch": 18.677510608203676, "percentage": 99.04, "elapsed_time": "6:19:39", "remaining_time": "0:03:41", "throughput": 1612.79, "total_tokens": 36738192}
8122
+ {"current_steps": 39620, "total_steps": 40000, "loss": 0.0, "lr": 1.1191990176728784e-08, "epoch": 18.67986798679868, "percentage": 99.05, "elapsed_time": "6:19:41", "remaining_time": "0:03:38", "throughput": 1612.83, "total_tokens": 36742304}
8123
+ {"current_steps": 39625, "total_steps": 40000, "loss": 0.0, "lr": 1.0900185875215018e-08, "epoch": 18.68222536539368, "percentage": 99.06, "elapsed_time": "6:19:43", "remaining_time": "0:03:35", "throughput": 1612.89, "total_tokens": 36747136}
8124
+ {"current_steps": 39630, "total_steps": 40000, "loss": 0.0, "lr": 1.0612235206924891e-08, "epoch": 18.684582743988685, "percentage": 99.08, "elapsed_time": "6:19:45", "remaining_time": "0:03:32", "throughput": 1612.95, "total_tokens": 36752048}
8125
+ {"current_steps": 39635, "total_steps": 40000, "loss": 0.0, "lr": 1.0328138216264549e-08, "epoch": 18.686940122583685, "percentage": 99.09, "elapsed_time": "6:19:47", "remaining_time": "0:03:29", "throughput": 1612.98, "total_tokens": 36755952}
8126
+ {"current_steps": 39640, "total_steps": 40000, "loss": 0.0, "lr": 1.004789494704339e-08, "epoch": 18.68929750117869, "percentage": 99.1, "elapsed_time": "6:19:49", "remaining_time": "0:03:26", "throughput": 1613.03, "total_tokens": 36760592}
8127
+ {"current_steps": 39645, "total_steps": 40000, "loss": 0.0, "lr": 9.771505442482397e-09, "epoch": 18.69165487977369, "percentage": 99.11, "elapsed_time": "6:19:52", "remaining_time": "0:03:24", "throughput": 1613.11, "total_tokens": 36766032}
8128
+ {"current_steps": 39650, "total_steps": 40000, "loss": 0.0, "lr": 9.498969745200259e-09, "epoch": 18.694012258368694, "percentage": 99.12, "elapsed_time": "6:19:54", "remaining_time": "0:03:21", "throughput": 1613.15, "total_tokens": 36770176}
8129
+ {"current_steps": 39655, "total_steps": 40000, "loss": 0.0, "lr": 9.230287897230017e-09, "epoch": 18.696369636963695, "percentage": 99.14, "elapsed_time": "6:19:56", "remaining_time": "0:03:18", "throughput": 1613.18, "total_tokens": 36774224}
8130
+ {"current_steps": 39660, "total_steps": 40000, "loss": 0.0, "lr": 8.965459940002419e-09, "epoch": 18.6987270155587, "percentage": 99.15, "elapsed_time": "6:19:58", "remaining_time": "0:03:15", "throughput": 1613.23, "total_tokens": 36778800}
8131
+ {"current_steps": 39665, "total_steps": 40000, "loss": 0.0, "lr": 8.704485914357019e-09, "epoch": 18.7010843941537, "percentage": 99.16, "elapsed_time": "6:20:00", "remaining_time": "0:03:12", "throughput": 1613.3, "total_tokens": 36784064}
8132
+ {"current_steps": 39670, "total_steps": 40000, "loss": 0.0, "lr": 8.447365860539402e-09, "epoch": 18.703441772748704, "percentage": 99.17, "elapsed_time": "6:20:02", "remaining_time": "0:03:09", "throughput": 1613.37, "total_tokens": 36789184}
8133
+ {"current_steps": 39675, "total_steps": 40000, "loss": 0.0, "lr": 8.194099818201184e-09, "epoch": 18.705799151343705, "percentage": 99.19, "elapsed_time": "6:20:05", "remaining_time": "0:03:06", "throughput": 1613.44, "total_tokens": 36794528}
8134
+ {"current_steps": 39680, "total_steps": 40000, "loss": 0.0, "lr": 7.944687826400011e-09, "epoch": 18.70815652993871, "percentage": 99.2, "elapsed_time": "6:20:07", "remaining_time": "0:03:03", "throughput": 1613.47, "total_tokens": 36798592}
8135
+ {"current_steps": 39685, "total_steps": 40000, "loss": 0.0, "lr": 7.699129923599557e-09, "epoch": 18.71051390853371, "percentage": 99.21, "elapsed_time": "6:20:09", "remaining_time": "0:03:01", "throughput": 1613.52, "total_tokens": 36803360}
8136
+ {"current_steps": 39690, "total_steps": 40000, "loss": 0.0, "lr": 7.457426147663982e-09, "epoch": 18.712871287128714, "percentage": 99.22, "elapsed_time": "6:20:11", "remaining_time": "0:02:58", "throughput": 1613.56, "total_tokens": 36807536}
8137
+ {"current_steps": 39695, "total_steps": 40000, "loss": 0.0, "lr": 7.219576535871797e-09, "epoch": 18.715228665723714, "percentage": 99.24, "elapsed_time": "6:20:13", "remaining_time": "0:02:55", "throughput": 1613.62, "total_tokens": 36812368}
8138
+ {"current_steps": 39700, "total_steps": 40000, "loss": 0.0, "lr": 6.985581124896445e-09, "epoch": 18.71758604431872, "percentage": 99.25, "elapsed_time": "6:20:15", "remaining_time": "0:02:52", "throughput": 1613.67, "total_tokens": 36816928}
8139
+ {"current_steps": 39705, "total_steps": 40000, "loss": 0.0, "lr": 6.755439950828501e-09, "epoch": 18.71994342291372, "percentage": 99.26, "elapsed_time": "6:20:17", "remaining_time": "0:02:49", "throughput": 1613.69, "total_tokens": 36820832}
8140
+ {"current_steps": 39710, "total_steps": 40000, "loss": 0.0, "lr": 6.5291530491562444e-09, "epoch": 18.722300801508723, "percentage": 99.28, "elapsed_time": "6:20:19", "remaining_time": "0:02:46", "throughput": 1613.74, "total_tokens": 36825072}
8141
+ {"current_steps": 39715, "total_steps": 40000, "loss": 0.0, "lr": 6.3067204547739845e-09, "epoch": 18.724658180103724, "percentage": 99.29, "elapsed_time": "6:20:21", "remaining_time": "0:02:43", "throughput": 1613.79, "total_tokens": 36829552}
8142
+ {"current_steps": 39720, "total_steps": 40000, "loss": 0.0, "lr": 6.088142201987612e-09, "epoch": 18.727015558698728, "percentage": 99.3, "elapsed_time": "6:20:23", "remaining_time": "0:02:40", "throughput": 1613.81, "total_tokens": 36833312}
8143
+ {"current_steps": 39725, "total_steps": 40000, "loss": 0.0, "lr": 5.873418324503499e-09, "epoch": 18.72937293729373, "percentage": 99.31, "elapsed_time": "6:20:26", "remaining_time": "0:02:38", "throughput": 1613.86, "total_tokens": 36838032}
8144
+ {"current_steps": 39730, "total_steps": 40000, "loss": 0.0, "lr": 5.6625488554340465e-09, "epoch": 18.731730315888733, "percentage": 99.33, "elapsed_time": "6:20:28", "remaining_time": "0:02:35", "throughput": 1613.9, "total_tokens": 36842032}
8145
+ {"current_steps": 39735, "total_steps": 40000, "loss": 0.0, "lr": 5.455533827297688e-09, "epoch": 18.734087694483733, "percentage": 99.34, "elapsed_time": "6:20:30", "remaining_time": "0:02:32", "throughput": 1613.95, "total_tokens": 36846752}
8146
+ {"current_steps": 39740, "total_steps": 40000, "loss": 0.0, "lr": 5.252373272018885e-09, "epoch": 18.736445073078738, "percentage": 99.35, "elapsed_time": "6:20:32", "remaining_time": "0:02:29", "throughput": 1614.04, "total_tokens": 36852960}
8147
+ {"current_steps": 39745, "total_steps": 40000, "loss": 0.0, "lr": 5.053067220925356e-09, "epoch": 18.738802451673738, "percentage": 99.36, "elapsed_time": "6:20:34", "remaining_time": "0:02:26", "throughput": 1614.09, "total_tokens": 36857424}
8148
+ {"current_steps": 39750, "total_steps": 40000, "loss": 0.0, "lr": 4.857615704759177e-09, "epoch": 18.741159830268742, "percentage": 99.38, "elapsed_time": "6:20:36", "remaining_time": "0:02:23", "throughput": 1614.12, "total_tokens": 36861408}
8149
+ {"current_steps": 39755, "total_steps": 40000, "loss": 0.0, "lr": 4.666018753654577e-09, "epoch": 18.743517208863743, "percentage": 99.39, "elapsed_time": "6:20:39", "remaining_time": "0:02:20", "throughput": 1614.18, "total_tokens": 36866176}
8150
+ {"current_steps": 39760, "total_steps": 40000, "loss": 0.0, "lr": 4.478276397162917e-09, "epoch": 18.745874587458747, "percentage": 99.4, "elapsed_time": "6:20:41", "remaining_time": "0:02:17", "throughput": 1614.23, "total_tokens": 36870672}
8151
+ {"current_steps": 39765, "total_steps": 40000, "loss": 0.0, "lr": 4.294388664233262e-09, "epoch": 18.748231966053748, "percentage": 99.41, "elapsed_time": "6:20:43", "remaining_time": "0:02:14", "throughput": 1614.25, "total_tokens": 36874544}
8152
+ {"current_steps": 39770, "total_steps": 40000, "loss": 0.0, "lr": 4.114355583223484e-09, "epoch": 18.750589344648752, "percentage": 99.42, "elapsed_time": "6:20:45", "remaining_time": "0:02:12", "throughput": 1614.33, "total_tokens": 36879888}
8153
+ {"current_steps": 39775, "total_steps": 40000, "loss": 0.0, "lr": 3.9381771818974845e-09, "epoch": 18.752946723243753, "percentage": 99.44, "elapsed_time": "6:20:47", "remaining_time": "0:02:09", "throughput": 1614.4, "total_tokens": 36885008}
8154
+ {"current_steps": 39780, "total_steps": 40000, "loss": 0.0, "lr": 3.765853487427973e-09, "epoch": 18.755304101838757, "percentage": 99.45, "elapsed_time": "6:20:49", "remaining_time": "0:02:06", "throughput": 1614.48, "total_tokens": 36890608}
8155
+ {"current_steps": 39785, "total_steps": 40000, "loss": 0.0, "lr": 3.5973845263825857e-09, "epoch": 18.757661480433757, "percentage": 99.46, "elapsed_time": "6:20:51", "remaining_time": "0:02:03", "throughput": 1614.54, "total_tokens": 36895440}
8156
+ {"current_steps": 39790, "total_steps": 40000, "loss": 0.0, "lr": 3.4327703247488684e-09, "epoch": 18.76001885902876, "percentage": 99.48, "elapsed_time": "6:20:54", "remaining_time": "0:02:00", "throughput": 1614.63, "total_tokens": 36900960}
8157
+ {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 18.762376237623762, "percentage": 99.49, "elapsed_time": "6:20:56", "remaining_time": "0:01:57", "throughput": 1614.67, "total_tokens": 36905440}
8158
+ {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 18.764733616218766, "percentage": 99.5, "elapsed_time": "6:20:58", "remaining_time": "0:01:54", "throughput": 1614.73, "total_tokens": 36910256}
8159
+ {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.6301184892654419, "epoch": 18.764733616218766, "percentage": 99.5, "elapsed_time": "6:21:26", "remaining_time": "0:01:55", "throughput": 1612.77, "total_tokens": 36910256}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 18.767090994813767, "percentage": 99.51, "elapsed_time": "6:21:29", "remaining_time": "0:01:52", "throughput": 1612.71, "total_tokens": 36914608}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 18.76944837340877, "percentage": 99.52, "elapsed_time": "6:21:31", "remaining_time": "0:01:49", "throughput": 1612.76, "total_tokens": 36918928}