rbelanec commited on
Commit
6d57e72
verified
1 Parent(s): 2aa7942

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 sha256:4b07274edff079aa87016d0679bb4ed059b19356ccedef584f07165e44814312
3
  size 1638528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b0496dcdb916798910222a840d16ef0400f808af4a844aa06ad3fddc71d8b2
3
  size 1638528
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": "9:58:27", "remaining_time": "0:03:04", "throughput": 2972.17, "total_tokens": 106724504}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 1.8690637803880916e-05, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "9:58:32", "remaining_time": "0:03:00", "throughput": 2972.19, "total_tokens": 106737720}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.7604958415031433, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "9:58:38", "remaining_time": "0:03:00", "throughput": 2971.66, "total_tokens": 106737720}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 1.9632065447422463e-05, "epoch": 282.2352941176471, "percentage": 99.49, "elapsed_time": "9:58:27", "remaining_time": "0:03:04", "throughput": 2972.17, "total_tokens": 106724504}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 1.8690637803880916e-05, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "9:58:32", "remaining_time": "0:03:00", "throughput": 2972.19, "total_tokens": 106737720}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.7604958415031433, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "9:58:38", "remaining_time": "0:03:00", "throughput": 2971.66, "total_tokens": 106737720}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 1.7772339163019123e-05, "epoch": 282.3065953654189, "percentage": 99.51, "elapsed_time": "9:58:43", "remaining_time": "0:02:55", "throughput": 2971.6, "total_tokens": 106750904}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 1.6877169666457138e-05, "epoch": 282.3422459893048, "percentage": 99.52, "elapsed_time": "9:58:48", "remaining_time": "0:02:51", "throughput": 2971.63, "total_tokens": 106765176}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 1.6005129452234532e-05, "epoch": 282.3778966131907, "percentage": 99.54, "elapsed_time": "9:58:52", "remaining_time": "0:02:46", "throughput": 2971.65, "total_tokens": 106778680}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 1.5156218654843733e-05, "epoch": 282.41354723707667, "percentage": 99.55, "elapsed_time": "9:58:56", "remaining_time": "0:02:42", "throughput": 2971.65, "total_tokens": 106791128}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 1.4330437405196683e-05, "epoch": 282.44919786096256, "percentage": 99.56, "elapsed_time": "9:59:00", "remaining_time": "0:02:37", "throughput": 2971.65, "total_tokens": 106803192}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 1.352778583062486e-05, "epoch": 282.4848484848485, "percentage": 99.58, "elapsed_time": "9:59:05", "remaining_time": "0:02:33", "throughput": 2971.68, "total_tokens": 106818200}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 1.2748264054929237e-05, "epoch": 282.5204991087344, "percentage": 99.59, "elapsed_time": "9:59:09", "remaining_time": "0:02:28", "throughput": 2971.71, "total_tokens": 106832248}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.1991872198297004e-05, "epoch": 282.5561497326203, "percentage": 99.6, "elapsed_time": "9:59:14", "remaining_time": "0:02:24", "throughput": 2971.73, "total_tokens": 106845816}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.1258610377384847e-05, "epoch": 282.5918003565062, "percentage": 99.61, "elapsed_time": "9:59:18", "remaining_time": "0:02:19", "throughput": 2971.76, "total_tokens": 106860088}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.0548478705268982e-05, "epoch": 282.62745098039215, "percentage": 99.62, "elapsed_time": "9:59:22", "remaining_time": "0:02:15", "throughput": 2971.76, "total_tokens": 106872856}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 9.86147729147846e-06, "epoch": 282.6631016042781, "percentage": 99.64, "elapsed_time": "9:59:27", "remaining_time": "0:02:10", "throughput": 2971.78, "total_tokens": 106886296}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 9.197606241928557e-06, "epoch": 282.698752228164, "percentage": 99.65, "elapsed_time": "9:59:31", "remaining_time": "0:02:06", "throughput": 2971.8, "total_tokens": 106900408}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 8.556865659004042e-06, "epoch": 282.7344028520499, "percentage": 99.66, "elapsed_time": "9:59:35", "remaining_time": "0:02:01", "throughput": 2971.82, "total_tokens": 106914040}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 7.939255641525867e-06, "epoch": 282.7700534759358, "percentage": 99.67, "elapsed_time": "9:59:40", "remaining_time": "0:01:57", "throughput": 2971.82, "total_tokens": 106926264}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 7.344776284751164e-06, "epoch": 282.80570409982175, "percentage": 99.69, "elapsed_time": "9:59:44", "remaining_time": "0:01:52", "throughput": 2971.81, "total_tokens": 106938168}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 6.773427680323296e-06, "epoch": 282.84135472370764, "percentage": 99.7, "elapsed_time": "9:59:48", "remaining_time": "0:01:48", "throughput": 2971.82, "total_tokens": 106951288}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 6.225209916355112e-06, "epoch": 282.8770053475936, "percentage": 99.71, "elapsed_time": "9:59:52", "remaining_time": "0:01:43", "throughput": 2971.85, "total_tokens": 106965624}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 5.7001230774123e-06, "epoch": 282.9126559714795, "percentage": 99.72, "elapsed_time": "9:59:57", "remaining_time": "0:01:39", "throughput": 2971.88, "total_tokens": 106979832}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 5.198167244446772e-06, "epoch": 282.9483065953654, "percentage": 99.74, "elapsed_time": "10:00:01", "remaining_time": "0:01:34", "throughput": 2971.9, "total_tokens": 106993112}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 4.71934249487993e-06, "epoch": 282.98395721925135, "percentage": 99.75, "elapsed_time": "10:00:05", "remaining_time": "0:01:30", "throughput": 2971.89, "total_tokens": 107005432}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 4.2636489025527075e-06, "epoch": 283.01426024955435, "percentage": 99.76, "elapsed_time": "10:00:09", "remaining_time": "0:01:25", "throughput": 2971.88, "total_tokens": 107016656}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 3.831086537742223e-06, "epoch": 283.0499108734403, "percentage": 99.78, "elapsed_time": "10:00:14", "remaining_time": "0:01:21", "throughput": 2971.91, "total_tokens": 107030992}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 3.4216554671451236e-06, "epoch": 283.0855614973262, "percentage": 99.79, "elapsed_time": "10:00:18", "remaining_time": "0:01:16", "throughput": 2971.93, "total_tokens": 107044688}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 3.035355753894242e-06, "epoch": 283.1212121212121, "percentage": 99.8, "elapsed_time": "10:00:22", "remaining_time": "0:01:12", "throughput": 2971.93, "total_tokens": 107056976}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 2.6721874575752477e-06, "epoch": 283.15686274509807, "percentage": 99.81, "elapsed_time": "10:00:27", "remaining_time": "0:01:07", "throughput": 2971.96, "total_tokens": 107071376}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 2.3321506341933418e-06, "epoch": 283.19251336898395, "percentage": 99.83, "elapsed_time": "10:00:31", "remaining_time": "0:01:03", "throughput": 2971.97, "total_tokens": 107084080}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 2.0152453361732546e-06, "epoch": 283.2281639928699, "percentage": 99.84, "elapsed_time": "10:00:35", "remaining_time": "0:00:58", "throughput": 2971.98, "total_tokens": 107097616}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 1.7214716123925554e-06, "epoch": 283.2638146167558, "percentage": 99.85, "elapsed_time": "10:00:40", "remaining_time": "0:00:54", "throughput": 2972.01, "total_tokens": 107111760}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 1.4508295081649968e-06, "epoch": 283.2994652406417, "percentage": 99.86, "elapsed_time": "10:00:44", "remaining_time": "0:00:49", "throughput": 2972.03, "total_tokens": 107125328}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 1.2033190652238623e-06, "epoch": 283.3351158645276, "percentage": 99.88, "elapsed_time": "10:00:48", "remaining_time": "0:00:45", "throughput": 2972.03, "total_tokens": 107137840}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 9.78940321721966e-07, "epoch": 283.37076648841355, "percentage": 99.89, "elapsed_time": "10:00:53", "remaining_time": "0:00:40", "throughput": 2972.06, "total_tokens": 107151920}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 7.776933122816132e-07, "epoch": 283.4064171122995, "percentage": 99.9, "elapsed_time": "10:00:57", "remaining_time": "0:00:36", "throughput": 2972.08, "total_tokens": 107165712}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 5.99578067927986e-07, "epoch": 283.4420677361854, "percentage": 99.91, "elapsed_time": "10:01:02", "remaining_time": "0:00:31", "throughput": 2972.11, "total_tokens": 107180304}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 4.445946161224512e-07, "epoch": 283.4777183600713, "percentage": 99.92, "elapsed_time": "10:01:06", "remaining_time": "0:00:27", "throughput": 2972.13, "total_tokens": 107193776}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 3.127429807792126e-07, "epoch": 283.5133689839572, "percentage": 99.94, "elapsed_time": "10:01:10", "remaining_time": "0:00:22", "throughput": 2972.13, "total_tokens": 107206512}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 2.040231822320049e-07, "epoch": 283.54901960784315, "percentage": 99.95, "elapsed_time": "10:01:14", "remaining_time": "0:00:18", "throughput": 2972.14, "total_tokens": 107219440}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.1843523723409354e-07, "epoch": 283.58467023172904, "percentage": 99.96, "elapsed_time": "10:01:18", "remaining_time": "0:00:13", "throughput": 2972.14, "total_tokens": 107231504}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 5.597915897492811e-08, "epoch": 283.620320855615, "percentage": 99.98, "elapsed_time": "10:01:23", "remaining_time": "0:00:09", "throughput": 2972.16, "total_tokens": 107245488}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 1.6654957113448885e-08, "epoch": 283.65597147950086, "percentage": 99.99, "elapsed_time": "10:01:27", "remaining_time": "0:00:04", "throughput": 2972.19, "total_tokens": 107260144}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 4.626377114735902e-10, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "10:01:32", "remaining_time": "0:00:00", "throughput": 2972.22, "total_tokens": 107274480}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.7574778199195862, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "10:01:38", "remaining_time": "0:00:00", "throughput": 2971.7, "total_tokens": 107274480}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "10:01:39", "remaining_time": "0:00:00", "throughput": 2971.64, "total_tokens": 107274480}