rbelanec commited on
Commit
9ccbce1
verified
1 Parent(s): 8dbd6c5

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 sha256:29357c69ef6b55c752e9898f1acb751ac4f4861ab9d642508c7d052540cbf175
3
  size 460928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aa3ec29a9fe40c1544317973e4ded0ab1cee54d5a2f9f9241c5f2cf138762d5
3
  size 460928
trainer_log.jsonl CHANGED
@@ -8157,3 +8157,45 @@
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 1.9632065447422463e-05, "epoch": 282.2352941176471, "percentage": 99.49, "elapsed_time": "4:50:54", "remaining_time": "0:01:29", "throughput": 5820.74, "total_tokens": 101597328}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 1.8690637803880916e-05, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "4:50:56", "remaining_time": "0:01:27", "throughput": 5820.78, "total_tokens": 101609904}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.7435283064842224, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "4:50:59", "remaining_time": "0:01:27", "throughput": 5819.68, "total_tokens": 101609904}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 1.9632065447422463e-05, "epoch": 282.2352941176471, "percentage": 99.49, "elapsed_time": "4:50:54", "remaining_time": "0:01:29", "throughput": 5820.74, "total_tokens": 101597328}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 1.8690637803880916e-05, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "4:50:56", "remaining_time": "0:01:27", "throughput": 5820.78, "total_tokens": 101609904}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.7435283064842224, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "4:50:59", "remaining_time": "0:01:27", "throughput": 5819.68, "total_tokens": 101609904}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 1.7772339163019123e-05, "epoch": 282.3065953654189, "percentage": 99.51, "elapsed_time": "4:51:03", "remaining_time": "0:01:25", "throughput": 5819.2, "total_tokens": 101622480}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 1.6877169666457138e-05, "epoch": 282.3422459893048, "percentage": 99.52, "elapsed_time": "4:51:05", "remaining_time": "0:01:23", "throughput": 5819.27, "total_tokens": 101635984}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 1.6005129452234532e-05, "epoch": 282.3778966131907, "percentage": 99.54, "elapsed_time": "4:51:07", "remaining_time": "0:01:21", "throughput": 5819.31, "total_tokens": 101648752}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 1.5156218654843733e-05, "epoch": 282.41354723707667, "percentage": 99.55, "elapsed_time": "4:51:09", "remaining_time": "0:01:18", "throughput": 5819.33, "total_tokens": 101660752}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 1.4330437405196683e-05, "epoch": 282.44919786096256, "percentage": 99.56, "elapsed_time": "4:51:11", "remaining_time": "0:01:16", "throughput": 5819.32, "total_tokens": 101672368}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 1.352778583062486e-05, "epoch": 282.4848484848485, "percentage": 99.58, "elapsed_time": "4:51:13", "remaining_time": "0:01:14", "throughput": 5819.42, "total_tokens": 101686512}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 1.2748264054929237e-05, "epoch": 282.5204991087344, "percentage": 99.59, "elapsed_time": "4:51:15", "remaining_time": "0:01:12", "throughput": 5819.49, "total_tokens": 101699984}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.1991872198297004e-05, "epoch": 282.5561497326203, "percentage": 99.6, "elapsed_time": "4:51:17", "remaining_time": "0:01:10", "throughput": 5819.53, "total_tokens": 101712720}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.1258610377384847e-05, "epoch": 282.5918003565062, "percentage": 99.61, "elapsed_time": "4:51:19", "remaining_time": "0:01:07", "throughput": 5819.62, "total_tokens": 101726224}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.0548478705268982e-05, "epoch": 282.62745098039215, "percentage": 99.62, "elapsed_time": "4:51:21", "remaining_time": "0:01:05", "throughput": 5819.64, "total_tokens": 101738416}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 9.86147729147846e-06, "epoch": 282.6631016042781, "percentage": 99.64, "elapsed_time": "4:51:23", "remaining_time": "0:01:03", "throughput": 5819.68, "total_tokens": 101751152}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 9.197606241928557e-06, "epoch": 282.698752228164, "percentage": 99.65, "elapsed_time": "4:51:26", "remaining_time": "0:01:01", "throughput": 5819.75, "total_tokens": 101764496}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 8.556865659004042e-06, "epoch": 282.7344028520499, "percentage": 99.66, "elapsed_time": "4:51:28", "remaining_time": "0:00:59", "throughput": 5819.81, "total_tokens": 101777648}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 7.939255641525867e-06, "epoch": 282.7700534759358, "percentage": 99.67, "elapsed_time": "4:51:30", "remaining_time": "0:00:57", "throughput": 5819.79, "total_tokens": 101789232}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 7.344776284751164e-06, "epoch": 282.80570409982175, "percentage": 99.69, "elapsed_time": "4:51:32", "remaining_time": "0:00:54", "throughput": 5819.78, "total_tokens": 101800688}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 6.773427680323296e-06, "epoch": 282.84135472370764, "percentage": 99.7, "elapsed_time": "4:51:34", "remaining_time": "0:00:52", "throughput": 5819.82, "total_tokens": 101813296}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 6.225209916355112e-06, "epoch": 282.8770053475936, "percentage": 99.71, "elapsed_time": "4:51:36", "remaining_time": "0:00:50", "throughput": 5819.9, "total_tokens": 101826960}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 5.7001230774123e-06, "epoch": 282.9126559714795, "percentage": 99.72, "elapsed_time": "4:51:38", "remaining_time": "0:00:48", "throughput": 5819.98, "total_tokens": 101840464}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 5.198167244446772e-06, "epoch": 282.9483065953654, "percentage": 99.74, "elapsed_time": "4:51:40", "remaining_time": "0:00:46", "throughput": 5820.02, "total_tokens": 101853200}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 4.71934249487993e-06, "epoch": 282.98395721925135, "percentage": 99.75, "elapsed_time": "4:51:42", "remaining_time": "0:00:43", "throughput": 5820.02, "total_tokens": 101864944}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 4.2636489025527075e-06, "epoch": 283.01426024955435, "percentage": 99.76, "elapsed_time": "4:51:44", "remaining_time": "0:00:41", "throughput": 5819.94, "total_tokens": 101875688}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 3.831086537742223e-06, "epoch": 283.0499108734403, "percentage": 99.78, "elapsed_time": "4:51:46", "remaining_time": "0:00:39", "throughput": 5820.03, "total_tokens": 101889576}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 3.4216554671451236e-06, "epoch": 283.0855614973262, "percentage": 99.79, "elapsed_time": "4:51:48", "remaining_time": "0:00:37", "throughput": 5820.09, "total_tokens": 101902504}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 3.035355753894242e-06, "epoch": 283.1212121212121, "percentage": 99.8, "elapsed_time": "4:51:50", "remaining_time": "0:00:35", "throughput": 5820.09, "total_tokens": 101914184}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 2.6721874575752477e-06, "epoch": 283.15686274509807, "percentage": 99.81, "elapsed_time": "4:51:52", "remaining_time": "0:00:32", "throughput": 5820.17, "total_tokens": 101927848}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 2.3321506341933418e-06, "epoch": 283.19251336898395, "percentage": 99.83, "elapsed_time": "4:51:54", "remaining_time": "0:00:30", "throughput": 5820.2, "total_tokens": 101940232}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 2.0152453361732546e-06, "epoch": 283.2281639928699, "percentage": 99.84, "elapsed_time": "4:51:56", "remaining_time": "0:00:28", "throughput": 5820.24, "total_tokens": 101953032}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 1.7214716123925554e-06, "epoch": 283.2638146167558, "percentage": 99.85, "elapsed_time": "4:51:59", "remaining_time": "0:00:26", "throughput": 5820.31, "total_tokens": 101966408}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 1.4508295081649968e-06, "epoch": 283.2994652406417, "percentage": 99.86, "elapsed_time": "4:52:01", "remaining_time": "0:00:24", "throughput": 5820.37, "total_tokens": 101979368}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 1.2033190652238623e-06, "epoch": 283.3351158645276, "percentage": 99.88, "elapsed_time": "4:52:03", "remaining_time": "0:00:21", "throughput": 5820.36, "total_tokens": 101991080}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 9.78940321721966e-07, "epoch": 283.37076648841355, "percentage": 99.89, "elapsed_time": "4:52:05", "remaining_time": "0:00:19", "throughput": 5820.43, "total_tokens": 102004424}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 7.776933122816132e-07, "epoch": 283.4064171122995, "percentage": 99.9, "elapsed_time": "4:52:07", "remaining_time": "0:00:17", "throughput": 5820.48, "total_tokens": 102017480}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 5.99578067927986e-07, "epoch": 283.4420677361854, "percentage": 99.91, "elapsed_time": "4:52:09", "remaining_time": "0:00:15", "throughput": 5820.58, "total_tokens": 102031400}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 4.445946161224512e-07, "epoch": 283.4777183600713, "percentage": 99.92, "elapsed_time": "4:52:11", "remaining_time": "0:00:13", "throughput": 5820.64, "total_tokens": 102044392}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 3.127429807792126e-07, "epoch": 283.5133689839572, "percentage": 99.94, "elapsed_time": "4:52:13", "remaining_time": "0:00:10", "throughput": 5820.66, "total_tokens": 102056648}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 2.040231822320049e-07, "epoch": 283.54901960784315, "percentage": 99.95, "elapsed_time": "4:52:15", "remaining_time": "0:00:08", "throughput": 5820.68, "total_tokens": 102068968}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.1843523723409354e-07, "epoch": 283.58467023172904, "percentage": 99.96, "elapsed_time": "4:52:17", "remaining_time": "0:00:06", "throughput": 5820.67, "total_tokens": 102080520}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 5.597915897492811e-08, "epoch": 283.620320855615, "percentage": 99.98, "elapsed_time": "4:52:19", "remaining_time": "0:00:04", "throughput": 5820.73, "total_tokens": 102093736}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 1.6654957113448885e-08, "epoch": 283.65597147950086, "percentage": 99.99, "elapsed_time": "4:52:21", "remaining_time": "0:00:02", "throughput": 5820.83, "total_tokens": 102107592}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 4.626377114735902e-10, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "4:52:23", "remaining_time": "0:00:00", "throughput": 5820.89, "total_tokens": 102120968}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.7422819137573242, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "4:52:27", "remaining_time": "0:00:00", "throughput": 5819.81, "total_tokens": 102120968}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "4:52:28", "remaining_time": "0:00:00", "throughput": 5819.3, "total_tokens": 102120968}