rbelanec commited on
Commit
dd29c71
verified
1 Parent(s): d91a13a

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:fe4d2c2a2ad4d5be81b2bc0e82aadf15b2a926ad2d302d5c5e344877ed7f02a8
3
  size 18124968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e84af10c28f0f2066b1416fcaf8d99454665ecb6a64ac747f80a3a620cad849
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": 10.502837534644318, "percentage": 99.49, "elapsed_time": "14:11:53", "remaining_time": "0:04:23", "throughput": 704.22, "total_tokens": 35994880}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 10.504157318199816, "percentage": 99.5, "elapsed_time": "14:11:57", "remaining_time": "0:04:16", "throughput": 704.26, "total_tokens": 35999840}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.21051521599292755, "epoch": 10.504157318199816, "percentage": 99.5, "elapsed_time": "14:13:26", "remaining_time": "0:04:17", "throughput": 703.03, "total_tokens": 35999840}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 10.502837534644318, "percentage": 99.49, "elapsed_time": "14:11:53", "remaining_time": "0:04:23", "throughput": 704.22, "total_tokens": 35994880}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 10.504157318199816, "percentage": 99.5, "elapsed_time": "14:11:57", "remaining_time": "0:04:16", "throughput": 704.26, "total_tokens": 35999840}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.21051521599292755, "epoch": 10.504157318199816, "percentage": 99.5, "elapsed_time": "14:13:26", "remaining_time": "0:04:17", "throughput": 703.03, "total_tokens": 35999840}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 10.505477101755313, "percentage": 99.51, "elapsed_time": "14:13:34", "remaining_time": "0:04:10", "throughput": 703.01, "total_tokens": 36004288}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0006, "lr": 2.8128616110761898e-09, "epoch": 10.50679688531081, "percentage": 99.52, "elapsed_time": "14:13:38", "remaining_time": "0:04:04", "throughput": 703.04, "total_tokens": 36008672}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0071, "lr": 2.6675215753724223e-09, "epoch": 10.508116668866306, "percentage": 99.54, "elapsed_time": "14:13:42", "remaining_time": "0:03:58", "throughput": 703.08, "total_tokens": 36013312}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 10.509436452421802, "percentage": 99.55, "elapsed_time": "14:13:46", "remaining_time": "0:03:51", "throughput": 703.11, "total_tokens": 36017824}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 10.5107562359773, "percentage": 99.56, "elapsed_time": "14:13:50", "remaining_time": "0:03:45", "throughput": 703.14, "total_tokens": 36022496}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 10.512076019532797, "percentage": 99.58, "elapsed_time": "14:13:54", "remaining_time": "0:03:38", "throughput": 703.18, "total_tokens": 36027168}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 2.1247106758215397e-09, "epoch": 10.513395803088294, "percentage": 99.59, "elapsed_time": "14:13:59", "remaining_time": "0:03:32", "throughput": 703.21, "total_tokens": 36031648}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 10.51471558664379, "percentage": 99.6, "elapsed_time": "14:14:03", "remaining_time": "0:03:25", "throughput": 703.23, "total_tokens": 36035936}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 10.516035370199287, "percentage": 99.61, "elapsed_time": "14:14:07", "remaining_time": "0:03:19", "throughput": 703.27, "total_tokens": 36040480}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 10.517355153754785, "percentage": 99.62, "elapsed_time": "14:14:11", "remaining_time": "0:03:12", "throughput": 703.29, "total_tokens": 36044896}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 10.518674937310282, "percentage": 99.64, "elapsed_time": "14:14:15", "remaining_time": "0:03:06", "throughput": 703.32, "total_tokens": 36049344}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 10.519994720865778, "percentage": 99.65, "elapsed_time": "14:14:19", "remaining_time": "0:03:00", "throughput": 703.35, "total_tokens": 36053792}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 10.521314504421275, "percentage": 99.66, "elapsed_time": "14:14:23", "remaining_time": "0:02:53", "throughput": 703.38, "total_tokens": 36058272}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 10.522634287976771, "percentage": 99.67, "elapsed_time": "14:14:28", "remaining_time": "0:02:47", "throughput": 703.42, "total_tokens": 36062880}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0001, "lr": 1.2241293807918607e-09, "epoch": 10.523954071532268, "percentage": 99.69, "elapsed_time": "14:14:32", "remaining_time": "0:02:40", "throughput": 703.45, "total_tokens": 36067488}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 10.525273855087766, "percentage": 99.7, "elapsed_time": "14:14:36", "remaining_time": "0:02:34", "throughput": 703.48, "total_tokens": 36072064}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 10.526593638643263, "percentage": 99.71, "elapsed_time": "14:14:40", "remaining_time": "0:02:27", "throughput": 703.51, "total_tokens": 36076480}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 10.52791342219876, "percentage": 99.72, "elapsed_time": "14:14:44", "remaining_time": "0:02:21", "throughput": 703.55, "total_tokens": 36081184}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 10.529233205754256, "percentage": 99.74, "elapsed_time": "14:14:48", "remaining_time": "0:02:14", "throughput": 703.58, "total_tokens": 36085696}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 10.530552989309752, "percentage": 99.75, "elapsed_time": "14:14:52", "remaining_time": "0:02:08", "throughput": 703.61, "total_tokens": 36090016}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0001, "lr": 7.106081504254514e-10, "epoch": 10.53187277286525, "percentage": 99.76, "elapsed_time": "14:14:57", "remaining_time": "0:02:02", "throughput": 703.63, "total_tokens": 36094368}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 10.533192556420747, "percentage": 99.78, "elapsed_time": "14:15:01", "remaining_time": "0:01:55", "throughput": 703.67, "total_tokens": 36099008}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 10.534512339976244, "percentage": 99.79, "elapsed_time": "14:15:05", "remaining_time": "0:01:49", "throughput": 703.7, "total_tokens": 36103584}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 10.53583212353174, "percentage": 99.8, "elapsed_time": "14:15:09", "remaining_time": "0:01:42", "throughput": 703.73, "total_tokens": 36108000}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 10.537151907087237, "percentage": 99.81, "elapsed_time": "14:15:13", "remaining_time": "0:01:36", "throughput": 703.77, "total_tokens": 36112768}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0001, "lr": 3.88691772365557e-10, "epoch": 10.538471690642735, "percentage": 99.83, "elapsed_time": "14:15:17", "remaining_time": "0:01:29", "throughput": 703.8, "total_tokens": 36117440}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0001, "lr": 3.358742226955425e-10, "epoch": 10.539791474198232, "percentage": 99.84, "elapsed_time": "14:15:21", "remaining_time": "0:01:23", "throughput": 703.83, "total_tokens": 36121856}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 10.541111257753728, "percentage": 99.85, "elapsed_time": "14:15:26", "remaining_time": "0:01:17", "throughput": 703.86, "total_tokens": 36126304}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 10.542431041309225, "percentage": 99.86, "elapsed_time": "14:15:30", "remaining_time": "0:01:10", "throughput": 703.89, "total_tokens": 36130688}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 10.543750824864722, "percentage": 99.88, "elapsed_time": "14:15:34", "remaining_time": "0:01:04", "throughput": 703.92, "total_tokens": 36135424}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 10.545070608420218, "percentage": 99.89, "elapsed_time": "14:15:38", "remaining_time": "0:00:57", "throughput": 703.95, "total_tokens": 36139776}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0004, "lr": 1.2961555204693555e-10, "epoch": 10.546390391975716, "percentage": 99.9, "elapsed_time": "14:15:42", "remaining_time": "0:00:51", "throughput": 703.99, "total_tokens": 36144864}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0003, "lr": 9.992967798799768e-11, "epoch": 10.547710175531213, "percentage": 99.91, "elapsed_time": "14:15:46", "remaining_time": "0:00:44", "throughput": 704.03, "total_tokens": 36149536}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 10.54902995908671, "percentage": 99.92, "elapsed_time": "14:15:50", "remaining_time": "0:00:38", "throughput": 704.06, "total_tokens": 36154304}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 5.212383012986877e-11, "epoch": 10.550349742642206, "percentage": 99.94, "elapsed_time": "14:15:54", "remaining_time": "0:00:32", "throughput": 704.09, "total_tokens": 36158656}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 10.551669526197703, "percentage": 99.95, "elapsed_time": "14:15:59", "remaining_time": "0:00:25", "throughput": 704.12, "total_tokens": 36163136}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 10.552989309753201, "percentage": 99.96, "elapsed_time": "14:16:03", "remaining_time": "0:00:19", "throughput": 704.15, "total_tokens": 36167456}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 10.554309093308698, "percentage": 99.98, "elapsed_time": "14:16:07", "remaining_time": "0:00:12", "throughput": 704.18, "total_tokens": 36171968}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 10.555628876864194, "percentage": 99.99, "elapsed_time": "14:16:11", "remaining_time": "0:00:06", "throughput": 704.21, "total_tokens": 36176544}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 10.55694866041969, "percentage": 100.0, "elapsed_time": "14:16:15", "remaining_time": "0:00:00", "throughput": 704.25, "total_tokens": 36181120}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.21107575297355652, "epoch": 10.55694866041969, "percentage": 100.0, "elapsed_time": "14:17:44", "remaining_time": "0:00:00", "throughput": 703.02, "total_tokens": 36181120}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 10.55694866041969, "percentage": 100.0, "elapsed_time": "14:17:46", "remaining_time": "0:00:00", "throughput": 703.0, "total_tokens": 36181120}