rbelanec commited on
Commit
4deb85d
·
verified ·
1 Parent(s): f085466

Training in progress, step 40000

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 sha256:76de0c9ad915006092fcb1fee1fd359815fbe9eeb6880ca52342f34c7fed4e75
3
  size 18124968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0244147f4255a2448aae6f5353900da5dc50e6153c03117b7dff80b92d6e2416
3
  size 18124968
trainer_log.jsonl CHANGED
@@ -8157,3 +8157,45 @@
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 318.3614457831325, "percentage": 99.49, "elapsed_time": "8:19:30", "remaining_time": "0:02:34", "throughput": 464.92, "total_tokens": 13934048}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "8:19:34", "remaining_time": "0:02:30", "throughput": 464.93, "total_tokens": 13935776}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 6.533459186553955, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "8:19:37", "remaining_time": "0:02:30", "throughput": 464.88, "total_tokens": 13935776}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 318.3614457831325, "percentage": 99.49, "elapsed_time": "8:19:30", "remaining_time": "0:02:34", "throughput": 464.92, "total_tokens": 13934048}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "8:19:34", "remaining_time": "0:02:30", "throughput": 464.93, "total_tokens": 13935776}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 6.533459186553955, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "8:19:37", "remaining_time": "0:02:30", "throughput": 464.88, "total_tokens": 13935776}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 318.44176706827307, "percentage": 99.51, "elapsed_time": "8:19:42", "remaining_time": "0:02:26", "throughput": 464.84, "total_tokens": 13937280}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 318.48192771084337, "percentage": 99.52, "elapsed_time": "8:19:46", "remaining_time": "0:02:23", "throughput": 464.85, "total_tokens": 13939088}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 318.52208835341366, "percentage": 99.54, "elapsed_time": "8:19:49", "remaining_time": "0:02:19", "throughput": 464.85, "total_tokens": 13940800}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 318.56224899598396, "percentage": 99.55, "elapsed_time": "8:19:53", "remaining_time": "0:02:15", "throughput": 464.85, "total_tokens": 13942400}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 318.6024096385542, "percentage": 99.56, "elapsed_time": "8:19:57", "remaining_time": "0:02:11", "throughput": 464.86, "total_tokens": 13944464}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 318.6425702811245, "percentage": 99.58, "elapsed_time": "8:20:00", "remaining_time": "0:02:08", "throughput": 464.86, "total_tokens": 13946160}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 2.1247106758215397e-09, "epoch": 318.6827309236948, "percentage": 99.59, "elapsed_time": "8:20:04", "remaining_time": "0:02:04", "throughput": 464.86, "total_tokens": 13947856}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 318.72289156626505, "percentage": 99.6, "elapsed_time": "8:20:08", "remaining_time": "0:02:00", "throughput": 464.86, "total_tokens": 13949488}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 318.76305220883535, "percentage": 99.61, "elapsed_time": "8:20:11", "remaining_time": "0:01:56", "throughput": 464.86, "total_tokens": 13951120}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 318.80321285140565, "percentage": 99.62, "elapsed_time": "8:20:15", "remaining_time": "0:01:52", "throughput": 464.85, "total_tokens": 13952656}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 318.8433734939759, "percentage": 99.64, "elapsed_time": "8:20:18", "remaining_time": "0:01:49", "throughput": 464.86, "total_tokens": 13954400}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 318.8835341365462, "percentage": 99.65, "elapsed_time": "8:20:22", "remaining_time": "0:01:45", "throughput": 464.86, "total_tokens": 13956224}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 318.9236947791165, "percentage": 99.66, "elapsed_time": "8:20:26", "remaining_time": "0:01:41", "throughput": 464.86, "total_tokens": 13957920}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 318.96385542168673, "percentage": 99.67, "elapsed_time": "8:20:29", "remaining_time": "0:01:37", "throughput": 464.87, "total_tokens": 13959792}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 319.0, "percentage": 99.69, "elapsed_time": "8:20:33", "remaining_time": "0:01:34", "throughput": 464.86, "total_tokens": 13961344}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 319.0401606425703, "percentage": 99.7, "elapsed_time": "8:20:37", "remaining_time": "0:01:30", "throughput": 464.86, "total_tokens": 13963136}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 319.08032128514054, "percentage": 99.71, "elapsed_time": "8:20:40", "remaining_time": "0:01:26", "throughput": 464.87, "total_tokens": 13964976}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 319.12048192771084, "percentage": 99.72, "elapsed_time": "8:20:44", "remaining_time": "0:01:22", "throughput": 464.87, "total_tokens": 13966656}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 319.16064257028114, "percentage": 99.74, "elapsed_time": "8:20:47", "remaining_time": "0:01:19", "throughput": 464.86, "total_tokens": 13968192}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 319.2008032128514, "percentage": 99.75, "elapsed_time": "8:20:51", "remaining_time": "0:01:15", "throughput": 464.87, "total_tokens": 13969920}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 319.2409638554217, "percentage": 99.76, "elapsed_time": "8:20:55", "remaining_time": "0:01:11", "throughput": 464.88, "total_tokens": 13971920}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 319.281124497992, "percentage": 99.78, "elapsed_time": "8:20:58", "remaining_time": "0:01:07", "throughput": 464.88, "total_tokens": 13973584}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 319.3212851405622, "percentage": 99.79, "elapsed_time": "8:21:02", "remaining_time": "0:01:04", "throughput": 464.88, "total_tokens": 13975360}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 319.3614457831325, "percentage": 99.8, "elapsed_time": "8:21:06", "remaining_time": "0:01:00", "throughput": 464.88, "total_tokens": 13977072}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 319.4016064257028, "percentage": 99.81, "elapsed_time": "8:21:09", "remaining_time": "0:00:56", "throughput": 464.88, "total_tokens": 13978800}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 319.44176706827307, "percentage": 99.83, "elapsed_time": "8:21:13", "remaining_time": "0:00:52", "throughput": 464.88, "total_tokens": 13980448}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 319.48192771084337, "percentage": 99.84, "elapsed_time": "8:21:16", "remaining_time": "0:00:48", "throughput": 464.88, "total_tokens": 13982096}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 319.52208835341366, "percentage": 99.85, "elapsed_time": "8:21:20", "remaining_time": "0:00:45", "throughput": 464.88, "total_tokens": 13983952}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 319.56224899598396, "percentage": 99.86, "elapsed_time": "8:21:24", "remaining_time": "0:00:41", "throughput": 464.89, "total_tokens": 13985808}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 319.6024096385542, "percentage": 99.88, "elapsed_time": "8:21:27", "remaining_time": "0:00:37", "throughput": 464.89, "total_tokens": 13987504}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 319.6425702811245, "percentage": 99.89, "elapsed_time": "8:21:31", "remaining_time": "0:00:33", "throughput": 464.89, "total_tokens": 13989200}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 1.2961555204693555e-10, "epoch": 319.6827309236948, "percentage": 99.9, "elapsed_time": "8:21:34", "remaining_time": "0:00:30", "throughput": 464.9, "total_tokens": 13991088}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 319.72289156626505, "percentage": 99.91, "elapsed_time": "8:21:38", "remaining_time": "0:00:26", "throughput": 464.91, "total_tokens": 13993184}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 319.76305220883535, "percentage": 99.92, "elapsed_time": "8:21:42", "remaining_time": "0:00:22", "throughput": 464.91, "total_tokens": 13994800}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 5.212383012986877e-11, "epoch": 319.80321285140565, "percentage": 99.94, "elapsed_time": "8:21:45", "remaining_time": "0:00:18", "throughput": 464.92, "total_tokens": 13996688}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 319.8433734939759, "percentage": 99.95, "elapsed_time": "8:21:48", "remaining_time": "0:00:15", "throughput": 464.93, "total_tokens": 13998368}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 319.8835341365462, "percentage": 99.96, "elapsed_time": "8:21:52", "remaining_time": "0:00:11", "throughput": 464.93, "total_tokens": 14000176}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 319.9236947791165, "percentage": 99.98, "elapsed_time": "8:21:55", "remaining_time": "0:00:07", "throughput": 464.93, "total_tokens": 14001856}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 319.96385542168673, "percentage": 99.99, "elapsed_time": "8:21:59", "remaining_time": "0:00:03", "throughput": 464.93, "total_tokens": 14003616}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 320.0, "percentage": 100.0, "elapsed_time": "8:22:02", "remaining_time": "0:00:00", "throughput": 464.93, "total_tokens": 14005200}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 6.535747528076172, "epoch": 320.0, "percentage": 100.0, "elapsed_time": "8:22:06", "remaining_time": "0:00:00", "throughput": 464.89, "total_tokens": 14005200}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 320.0, "percentage": 100.0, "elapsed_time": "8:22:08", "remaining_time": "0:00:00", "throughput": 464.85, "total_tokens": 14005200}