rbelanec commited on
Commit
45e442b
verified
1 Parent(s): 40e4694

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 sha256:9d6b86ed6b6f45e54a059bf835433228902439e250a95b7cf859495eb1f9d9c6
3
  size 18124968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:712ec196ee73a1ed103904bd14c0003d4f36f067930fab5ccbda47e2a52e2cbc
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": 282.2352941176471, "percentage": 99.49, "elapsed_time": "9:27:13", "remaining_time": "0:02:55", "throughput": 2985.19, "total_tokens": 101597328}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "9:27:17", "remaining_time": "0:02:51", "throughput": 2985.2, "total_tokens": 101609904}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.642926037311554, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "9:27:21", "remaining_time": "0:02:51", "throughput": 2984.85, "total_tokens": 101609904}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 282.2352941176471, "percentage": 99.49, "elapsed_time": "9:27:13", "remaining_time": "0:02:55", "throughput": 2985.19, "total_tokens": 101597328}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "9:27:17", "remaining_time": "0:02:51", "throughput": 2985.2, "total_tokens": 101609904}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.642926037311554, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "9:27:21", "remaining_time": "0:02:51", "throughput": 2984.85, "total_tokens": 101609904}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 282.3065953654189, "percentage": 99.51, "elapsed_time": "9:27:27", "remaining_time": "0:02:46", "throughput": 2984.7, "total_tokens": 101622480}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 282.3422459893048, "percentage": 99.52, "elapsed_time": "9:27:31", "remaining_time": "0:02:42", "throughput": 2984.73, "total_tokens": 101635984}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 282.3778966131907, "percentage": 99.54, "elapsed_time": "9:27:36", "remaining_time": "0:02:38", "throughput": 2984.75, "total_tokens": 101648752}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 282.41354723707667, "percentage": 99.55, "elapsed_time": "9:27:40", "remaining_time": "0:02:33", "throughput": 2984.74, "total_tokens": 101660752}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 282.44919786096256, "percentage": 99.56, "elapsed_time": "9:27:44", "remaining_time": "0:02:29", "throughput": 2984.72, "total_tokens": 101672368}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 282.4848484848485, "percentage": 99.58, "elapsed_time": "9:27:48", "remaining_time": "0:02:25", "throughput": 2984.77, "total_tokens": 101686512}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 2.1247106758215397e-09, "epoch": 282.5204991087344, "percentage": 99.59, "elapsed_time": "9:27:52", "remaining_time": "0:02:21", "throughput": 2984.81, "total_tokens": 101699984}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 282.5561497326203, "percentage": 99.6, "elapsed_time": "9:27:56", "remaining_time": "0:02:16", "throughput": 2984.82, "total_tokens": 101712720}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 282.5918003565062, "percentage": 99.61, "elapsed_time": "9:28:00", "remaining_time": "0:02:12", "throughput": 2984.86, "total_tokens": 101726224}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 282.62745098039215, "percentage": 99.62, "elapsed_time": "9:28:04", "remaining_time": "0:02:08", "throughput": 2984.85, "total_tokens": 101738416}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 282.6631016042781, "percentage": 99.64, "elapsed_time": "9:28:09", "remaining_time": "0:02:04", "throughput": 2984.87, "total_tokens": 101751152}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 282.698752228164, "percentage": 99.65, "elapsed_time": "9:28:13", "remaining_time": "0:01:59", "throughput": 2984.9, "total_tokens": 101764496}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 282.7344028520499, "percentage": 99.66, "elapsed_time": "9:28:17", "remaining_time": "0:01:55", "throughput": 2984.92, "total_tokens": 101777648}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 282.7700534759358, "percentage": 99.67, "elapsed_time": "9:28:21", "remaining_time": "0:01:51", "throughput": 2984.9, "total_tokens": 101789232}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 282.80570409982175, "percentage": 99.69, "elapsed_time": "9:28:25", "remaining_time": "0:01:46", "throughput": 2984.87, "total_tokens": 101800688}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 282.84135472370764, "percentage": 99.7, "elapsed_time": "9:28:29", "remaining_time": "0:01:42", "throughput": 2984.88, "total_tokens": 101813296}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 282.8770053475936, "percentage": 99.71, "elapsed_time": "9:28:33", "remaining_time": "0:01:38", "throughput": 2984.92, "total_tokens": 101826960}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 282.9126559714795, "percentage": 99.72, "elapsed_time": "9:28:37", "remaining_time": "0:01:34", "throughput": 2984.96, "total_tokens": 101840464}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 282.9483065953654, "percentage": 99.74, "elapsed_time": "9:28:41", "remaining_time": "0:01:29", "throughput": 2984.97, "total_tokens": 101853200}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 282.98395721925135, "percentage": 99.75, "elapsed_time": "9:28:46", "remaining_time": "0:01:25", "throughput": 2984.96, "total_tokens": 101864944}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 283.01426024955435, "percentage": 99.76, "elapsed_time": "9:28:50", "remaining_time": "0:01:21", "throughput": 2984.93, "total_tokens": 101875688}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 283.0499108734403, "percentage": 99.78, "elapsed_time": "9:28:54", "remaining_time": "0:01:16", "throughput": 2984.97, "total_tokens": 101889576}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 283.0855614973262, "percentage": 99.79, "elapsed_time": "9:28:58", "remaining_time": "0:01:12", "throughput": 2984.99, "total_tokens": 101902504}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 283.1212121212121, "percentage": 99.8, "elapsed_time": "9:29:02", "remaining_time": "0:01:08", "throughput": 2984.97, "total_tokens": 101914184}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 283.15686274509807, "percentage": 99.81, "elapsed_time": "9:29:06", "remaining_time": "0:01:04", "throughput": 2985.01, "total_tokens": 101927848}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 283.19251336898395, "percentage": 99.83, "elapsed_time": "9:29:10", "remaining_time": "0:00:59", "throughput": 2985.01, "total_tokens": 101940232}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 283.2281639928699, "percentage": 99.84, "elapsed_time": "9:29:14", "remaining_time": "0:00:55", "throughput": 2985.03, "total_tokens": 101953032}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 283.2638146167558, "percentage": 99.85, "elapsed_time": "9:29:18", "remaining_time": "0:00:51", "throughput": 2985.06, "total_tokens": 101966408}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 283.2994652406417, "percentage": 99.86, "elapsed_time": "9:29:23", "remaining_time": "0:00:47", "throughput": 2985.08, "total_tokens": 101979368}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 283.3351158645276, "percentage": 99.88, "elapsed_time": "9:29:27", "remaining_time": "0:00:42", "throughput": 2985.07, "total_tokens": 101991080}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 283.37076648841355, "percentage": 99.89, "elapsed_time": "9:29:31", "remaining_time": "0:00:38", "throughput": 2985.1, "total_tokens": 102004424}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 1.2961555204693555e-10, "epoch": 283.4064171122995, "percentage": 99.9, "elapsed_time": "9:29:35", "remaining_time": "0:00:34", "throughput": 2985.12, "total_tokens": 102017480}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 283.4420677361854, "percentage": 99.91, "elapsed_time": "9:29:39", "remaining_time": "0:00:29", "throughput": 2985.17, "total_tokens": 102031400}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 283.4777183600713, "percentage": 99.92, "elapsed_time": "9:29:43", "remaining_time": "0:00:25", "throughput": 2985.19, "total_tokens": 102044392}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 5.212383012986877e-11, "epoch": 283.5133689839572, "percentage": 99.94, "elapsed_time": "9:29:47", "remaining_time": "0:00:21", "throughput": 2985.19, "total_tokens": 102056648}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 283.54901960784315, "percentage": 99.95, "elapsed_time": "9:29:51", "remaining_time": "0:00:17", "throughput": 2985.19, "total_tokens": 102068968}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 283.58467023172904, "percentage": 99.96, "elapsed_time": "9:29:55", "remaining_time": "0:00:12", "throughput": 2985.17, "total_tokens": 102080520}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 283.620320855615, "percentage": 99.98, "elapsed_time": "9:30:00", "remaining_time": "0:00:08", "throughput": 2985.2, "total_tokens": 102093736}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 283.65597147950086, "percentage": 99.99, "elapsed_time": "9:30:04", "remaining_time": "0:00:04", "throughput": 2985.24, "total_tokens": 102107592}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "9:30:08", "remaining_time": "0:00:00", "throughput": 2985.27, "total_tokens": 102120968}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.6471313238143921, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "9:30:12", "remaining_time": "0:00:00", "throughput": 2984.93, "total_tokens": 102120968}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "9:30:14", "remaining_time": "0:00:00", "throughput": 2984.69, "total_tokens": 102120968}