rbelanec commited on
Commit
bfd0aec
verified
1 Parent(s): 425e1a7

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 sha256:85715259257542d2d0b83a9929e62e8939943da92f181672c06c86d1052c4c9b
3
  size 498936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86665f1da5240fdaa4bf9ddcb19dd1570b2b61e88e031f8b5059041ed9f17f6c
3
  size 498936
trainer_log.jsonl CHANGED
@@ -8157,3 +8157,45 @@
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0284, "lr": 3.2720109079037443e-09, "epoch": 282.2352941176471, "percentage": 99.49, "elapsed_time": "7:10:14", "remaining_time": "0:02:12", "throughput": 3935.74, "total_tokens": 101597328}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0456, "lr": 3.1151063006468193e-09, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "7:10:17", "remaining_time": "0:02:09", "throughput": 3935.76, "total_tokens": 101609904}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.11810856312513351, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "7:10:20", "remaining_time": "0:02:09", "throughput": 3935.27, "total_tokens": 101609904}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0284, "lr": 3.2720109079037443e-09, "epoch": 282.2352941176471, "percentage": 99.49, "elapsed_time": "7:10:14", "remaining_time": "0:02:12", "throughput": 3935.74, "total_tokens": 101597328}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0456, "lr": 3.1151063006468193e-09, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "7:10:17", "remaining_time": "0:02:09", "throughput": 3935.76, "total_tokens": 101609904}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.11810856312513351, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "7:10:20", "remaining_time": "0:02:09", "throughput": 3935.27, "total_tokens": 101609904}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.03, "lr": 2.962056527169854e-09, "epoch": 282.3065953654189, "percentage": 99.51, "elapsed_time": "7:10:25", "remaining_time": "0:02:06", "throughput": 3935.02, "total_tokens": 101622480}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0515, "lr": 2.8128616110761898e-09, "epoch": 282.3422459893048, "percentage": 99.52, "elapsed_time": "7:10:28", "remaining_time": "0:02:03", "throughput": 3935.06, "total_tokens": 101635984}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0278, "lr": 2.6675215753724223e-09, "epoch": 282.3778966131907, "percentage": 99.54, "elapsed_time": "7:10:31", "remaining_time": "0:02:00", "throughput": 3935.08, "total_tokens": 101648752}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.02, "lr": 2.5260364424739557e-09, "epoch": 282.41354723707667, "percentage": 99.55, "elapsed_time": "7:10:34", "remaining_time": "0:01:56", "throughput": 3935.07, "total_tokens": 101660752}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0412, "lr": 2.3884062341994475e-09, "epoch": 282.44919786096256, "percentage": 99.56, "elapsed_time": "7:10:37", "remaining_time": "0:01:53", "throughput": 3935.05, "total_tokens": 101672368}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0681, "lr": 2.25463097177081e-09, "epoch": 282.4848484848485, "percentage": 99.58, "elapsed_time": "7:10:40", "remaining_time": "0:01:50", "throughput": 3935.12, "total_tokens": 101686512}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.036, "lr": 2.1247106758215397e-09, "epoch": 282.5204991087344, "percentage": 99.59, "elapsed_time": "7:10:43", "remaining_time": "0:01:47", "throughput": 3935.16, "total_tokens": 101699984}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0226, "lr": 1.998645366382834e-09, "epoch": 282.5561497326203, "percentage": 99.6, "elapsed_time": "7:10:47", "remaining_time": "0:01:43", "throughput": 3935.18, "total_tokens": 101712720}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0342, "lr": 1.876435062897475e-09, "epoch": 282.5918003565062, "percentage": 99.61, "elapsed_time": "7:10:50", "remaining_time": "0:01:40", "throughput": 3935.23, "total_tokens": 101726224}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0322, "lr": 1.758079784211497e-09, "epoch": 282.62745098039215, "percentage": 99.62, "elapsed_time": "7:10:53", "remaining_time": "0:01:37", "throughput": 3935.23, "total_tokens": 101738416}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0261, "lr": 1.6435795485797434e-09, "epoch": 282.6631016042781, "percentage": 99.64, "elapsed_time": "7:10:56", "remaining_time": "0:01:34", "throughput": 3935.25, "total_tokens": 101751152}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0438, "lr": 1.5329343736547596e-09, "epoch": 282.698752228164, "percentage": 99.65, "elapsed_time": "7:10:59", "remaining_time": "0:01:30", "throughput": 3935.29, "total_tokens": 101764496}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0262, "lr": 1.4261442765006739e-09, "epoch": 282.7344028520499, "percentage": 99.66, "elapsed_time": "7:11:02", "remaining_time": "0:01:27", "throughput": 3935.32, "total_tokens": 101777648}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0464, "lr": 1.3232092735876445e-09, "epoch": 282.7700534759358, "percentage": 99.67, "elapsed_time": "7:11:05", "remaining_time": "0:01:24", "throughput": 3935.3, "total_tokens": 101789232}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0293, "lr": 1.2241293807918607e-09, "epoch": 282.80570409982175, "percentage": 99.69, "elapsed_time": "7:11:08", "remaining_time": "0:01:21", "throughput": 3935.27, "total_tokens": 101800688}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0376, "lr": 1.128904613387216e-09, "epoch": 282.84135472370764, "percentage": 99.7, "elapsed_time": "7:11:11", "remaining_time": "0:01:17", "throughput": 3935.28, "total_tokens": 101813296}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0479, "lr": 1.0375349860591853e-09, "epoch": 282.8770053475936, "percentage": 99.71, "elapsed_time": "7:11:15", "remaining_time": "0:01:14", "throughput": 3935.33, "total_tokens": 101826960}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0394, "lr": 9.5002051290205e-10, "epoch": 282.9126559714795, "percentage": 99.72, "elapsed_time": "7:11:18", "remaining_time": "0:01:11", "throughput": 3935.38, "total_tokens": 101840464}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0221, "lr": 8.663612074077954e-10, "epoch": 282.9483065953654, "percentage": 99.74, "elapsed_time": "7:11:21", "remaining_time": "0:01:08", "throughput": 3935.4, "total_tokens": 101853200}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0301, "lr": 7.865570824799884e-10, "epoch": 282.98395721925135, "percentage": 99.75, "elapsed_time": "7:11:24", "remaining_time": "0:01:04", "throughput": 3935.38, "total_tokens": 101864944}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0289, "lr": 7.106081504254514e-10, "epoch": 283.01426024955435, "percentage": 99.76, "elapsed_time": "7:11:27", "remaining_time": "0:01:01", "throughput": 3935.32, "total_tokens": 101875688}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0344, "lr": 6.385144229570372e-10, "epoch": 283.0499108734403, "percentage": 99.78, "elapsed_time": "7:11:30", "remaining_time": "0:00:58", "throughput": 3935.38, "total_tokens": 101889576}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0409, "lr": 5.70275911190854e-10, "epoch": 283.0855614973262, "percentage": 99.79, "elapsed_time": "7:11:33", "remaining_time": "0:00:55", "throughput": 3935.41, "total_tokens": 101902504}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0359, "lr": 5.058926256490403e-10, "epoch": 283.1212121212121, "percentage": 99.8, "elapsed_time": "7:11:36", "remaining_time": "0:00:51", "throughput": 3935.39, "total_tokens": 101914184}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.043, "lr": 4.4536457626254134e-10, "epoch": 283.15686274509807, "percentage": 99.81, "elapsed_time": "7:11:39", "remaining_time": "0:00:48", "throughput": 3935.44, "total_tokens": 101927848}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0243, "lr": 3.88691772365557e-10, "epoch": 283.19251336898395, "percentage": 99.83, "elapsed_time": "7:11:43", "remaining_time": "0:00:45", "throughput": 3935.45, "total_tokens": 101940232}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0288, "lr": 3.358742226955425e-10, "epoch": 283.2281639928699, "percentage": 99.84, "elapsed_time": "7:11:46", "remaining_time": "0:00:42", "throughput": 3935.47, "total_tokens": 101953032}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0514, "lr": 2.8691193539875925e-10, "epoch": 283.2638146167558, "percentage": 99.85, "elapsed_time": "7:11:49", "remaining_time": "0:00:38", "throughput": 3935.51, "total_tokens": 101966408}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0324, "lr": 2.418049180274995e-10, "epoch": 283.2994652406417, "percentage": 99.86, "elapsed_time": "7:11:52", "remaining_time": "0:00:35", "throughput": 3935.54, "total_tokens": 101979368}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0519, "lr": 2.005531775373104e-10, "epoch": 283.3351158645276, "percentage": 99.88, "elapsed_time": "7:11:55", "remaining_time": "0:00:32", "throughput": 3935.52, "total_tokens": 101991080}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0266, "lr": 1.6315672028699435e-10, "epoch": 283.37076648841355, "percentage": 99.89, "elapsed_time": "7:11:58", "remaining_time": "0:00:29", "throughput": 3935.56, "total_tokens": 102004424}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0321, "lr": 1.2961555204693555e-10, "epoch": 283.4064171122995, "percentage": 99.9, "elapsed_time": "7:12:01", "remaining_time": "0:00:25", "throughput": 3935.59, "total_tokens": 102017480}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0415, "lr": 9.992967798799768e-11, "epoch": 283.4420677361854, "percentage": 99.91, "elapsed_time": "7:12:04", "remaining_time": "0:00:22", "throughput": 3935.65, "total_tokens": 102031400}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0326, "lr": 7.409910268707521e-11, "epoch": 283.4777183600713, "percentage": 99.92, "elapsed_time": "7:12:08", "remaining_time": "0:00:19", "throughput": 3935.68, "total_tokens": 102044392}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0408, "lr": 5.212383012986877e-11, "epoch": 283.5133689839572, "percentage": 99.94, "elapsed_time": "7:12:11", "remaining_time": "0:00:16", "throughput": 3935.68, "total_tokens": 102056648}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0393, "lr": 3.400386370533415e-11, "epoch": 283.54901960784315, "percentage": 99.95, "elapsed_time": "7:12:14", "remaining_time": "0:00:12", "throughput": 3935.69, "total_tokens": 102068968}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0424, "lr": 1.9739206205682258e-11, "epoch": 283.58467023172904, "percentage": 99.96, "elapsed_time": "7:12:17", "remaining_time": "0:00:09", "throughput": 3935.66, "total_tokens": 102080520}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0423, "lr": 9.329859829154685e-12, "epoch": 283.620320855615, "percentage": 99.98, "elapsed_time": "7:12:20", "remaining_time": "0:00:06", "throughput": 3935.7, "total_tokens": 102093736}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0338, "lr": 2.7758261855748148e-12, "epoch": 283.65597147950086, "percentage": 99.99, "elapsed_time": "7:12:23", "remaining_time": "0:00:03", "throughput": 3935.76, "total_tokens": 102107592}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.026, "lr": 7.710628524559838e-14, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "7:12:26", "remaining_time": "0:00:00", "throughput": 3935.8, "total_tokens": 102120968}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.11833836138248444, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "7:12:29", "remaining_time": "0:00:00", "throughput": 3935.32, "total_tokens": 102120968}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "7:12:31", "remaining_time": "0:00:00", "throughput": 3935.07, "total_tokens": 102120968}