rbelanec commited on
Commit
a12ad1a
·
verified ·
1 Parent(s): 9e818a3

Training in progress, step 40000

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +41 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2bdb48fc82c4a5d536885fb297239a82bb6f2310da064a0fd63e8ef5312ffcb
3
  size 460928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f3ab82a86199196c8445208341faa207bca686ca2218429e7c110757d1e2e0b
3
  size 460928
trainer_log.jsonl CHANGED
@@ -8158,3 +8158,44 @@
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 1.8690637803880916e-05, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "2:21:57", "remaining_time": "0:00:42", "throughput": 2653.69, "total_tokens": 22604096}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.794979989528656, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "2:21:58", "remaining_time": "0:00:42", "throughput": 2653.4, "total_tokens": 22604096}
8160
  {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 1.7772339163019123e-05, "epoch": 698.3362831858407, "percentage": 99.51, "elapsed_time": "2:22:01", "remaining_time": "0:00:41", "throughput": 2652.91, "total_tokens": 22607040}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 1.8690637803880916e-05, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "2:21:57", "remaining_time": "0:00:42", "throughput": 2653.69, "total_tokens": 22604096}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.794979989528656, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "2:21:58", "remaining_time": "0:00:42", "throughput": 2653.4, "total_tokens": 22604096}
8160
  {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 1.7772339163019123e-05, "epoch": 698.3362831858407, "percentage": 99.51, "elapsed_time": "2:22:01", "remaining_time": "0:00:41", "throughput": 2652.91, "total_tokens": 22607040}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 1.6877169666457138e-05, "epoch": 698.4247787610619, "percentage": 99.52, "elapsed_time": "2:22:02", "remaining_time": "0:00:40", "throughput": 2652.89, "total_tokens": 22609568}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 1.6005129452234532e-05, "epoch": 698.5132743362832, "percentage": 99.54, "elapsed_time": "2:22:03", "remaining_time": "0:00:39", "throughput": 2652.91, "total_tokens": 22612320}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 1.5156218654843733e-05, "epoch": 698.6017699115044, "percentage": 99.55, "elapsed_time": "2:22:04", "remaining_time": "0:00:38", "throughput": 2652.95, "total_tokens": 22615328}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 1.4330437405196683e-05, "epoch": 698.6902654867257, "percentage": 99.56, "elapsed_time": "2:22:05", "remaining_time": "0:00:37", "throughput": 2653.05, "total_tokens": 22618784}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 1.352778583062486e-05, "epoch": 698.7787610619469, "percentage": 99.58, "elapsed_time": "2:22:06", "remaining_time": "0:00:36", "throughput": 2653.04, "total_tokens": 22621376}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 1.2748264054929237e-05, "epoch": 698.8672566371681, "percentage": 99.59, "elapsed_time": "2:22:07", "remaining_time": "0:00:35", "throughput": 2653.03, "total_tokens": 22623936}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.1991872198297004e-05, "epoch": 698.9557522123894, "percentage": 99.6, "elapsed_time": "2:22:08", "remaining_time": "0:00:34", "throughput": 2653.1, "total_tokens": 22627120}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.1258610377384847e-05, "epoch": 699.0353982300885, "percentage": 99.61, "elapsed_time": "2:22:09", "remaining_time": "0:00:33", "throughput": 2653.04, "total_tokens": 22629960}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.0548478705268982e-05, "epoch": 699.1238938053098, "percentage": 99.62, "elapsed_time": "2:22:10", "remaining_time": "0:00:32", "throughput": 2653.07, "total_tokens": 22632840}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 9.86147729147846e-06, "epoch": 699.212389380531, "percentage": 99.64, "elapsed_time": "2:22:11", "remaining_time": "0:00:31", "throughput": 2653.1, "total_tokens": 22635656}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 9.197606241928557e-06, "epoch": 699.3008849557522, "percentage": 99.65, "elapsed_time": "2:22:12", "remaining_time": "0:00:29", "throughput": 2653.14, "total_tokens": 22638632}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 8.556865659004042e-06, "epoch": 699.3893805309734, "percentage": 99.66, "elapsed_time": "2:22:13", "remaining_time": "0:00:28", "throughput": 2653.17, "total_tokens": 22641400}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 7.939255641525867e-06, "epoch": 699.4778761061947, "percentage": 99.67, "elapsed_time": "2:22:14", "remaining_time": "0:00:27", "throughput": 2653.19, "total_tokens": 22644264}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 7.344776284751164e-06, "epoch": 699.566371681416, "percentage": 99.69, "elapsed_time": "2:22:15", "remaining_time": "0:00:26", "throughput": 2653.23, "total_tokens": 22647128}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 6.773427680323296e-06, "epoch": 699.6548672566372, "percentage": 99.7, "elapsed_time": "2:22:16", "remaining_time": "0:00:25", "throughput": 2653.25, "total_tokens": 22649928}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 6.225209916355112e-06, "epoch": 699.7433628318585, "percentage": 99.71, "elapsed_time": "2:22:17", "remaining_time": "0:00:24", "throughput": 2653.28, "total_tokens": 22652840}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 5.7001230774123e-06, "epoch": 699.8318584070796, "percentage": 99.72, "elapsed_time": "2:22:18", "remaining_time": "0:00:23", "throughput": 2653.28, "total_tokens": 22655384}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 5.198167244446772e-06, "epoch": 699.9203539823009, "percentage": 99.74, "elapsed_time": "2:22:19", "remaining_time": "0:00:22", "throughput": 2653.3, "total_tokens": 22658232}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 4.71934249487993e-06, "epoch": 700.0, "percentage": 99.75, "elapsed_time": "2:22:20", "remaining_time": "0:00:21", "throughput": 2653.25, "total_tokens": 22660488}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 4.2636489025527075e-06, "epoch": 700.0884955752213, "percentage": 99.76, "elapsed_time": "2:22:21", "remaining_time": "0:00:20", "throughput": 2653.21, "total_tokens": 22663336}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 3.831086537742223e-06, "epoch": 700.1769911504425, "percentage": 99.78, "elapsed_time": "2:22:22", "remaining_time": "0:00:19", "throughput": 2653.23, "total_tokens": 22666120}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 3.4216554671451236e-06, "epoch": 700.2654867256637, "percentage": 99.79, "elapsed_time": "2:22:23", "remaining_time": "0:00:18", "throughput": 2653.22, "total_tokens": 22668648}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 3.035355753894242e-06, "epoch": 700.3539823008849, "percentage": 99.8, "elapsed_time": "2:22:24", "remaining_time": "0:00:17", "throughput": 2653.25, "total_tokens": 22671464}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 2.6721874575752477e-06, "epoch": 700.4424778761062, "percentage": 99.81, "elapsed_time": "2:22:25", "remaining_time": "0:00:16", "throughput": 2653.28, "total_tokens": 22674360}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 2.3321506341933418e-06, "epoch": 700.5309734513274, "percentage": 99.83, "elapsed_time": "2:22:26", "remaining_time": "0:00:14", "throughput": 2653.34, "total_tokens": 22677432}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 2.0152453361732546e-06, "epoch": 700.6194690265487, "percentage": 99.84, "elapsed_time": "2:22:27", "remaining_time": "0:00:13", "throughput": 2653.37, "total_tokens": 22680296}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 1.7214716123925554e-06, "epoch": 700.70796460177, "percentage": 99.85, "elapsed_time": "2:22:28", "remaining_time": "0:00:12", "throughput": 2653.42, "total_tokens": 22683304}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 1.4508295081649968e-06, "epoch": 700.7964601769911, "percentage": 99.86, "elapsed_time": "2:22:29", "remaining_time": "0:00:11", "throughput": 2653.49, "total_tokens": 22686520}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 1.2033190652238623e-06, "epoch": 700.8849557522124, "percentage": 99.88, "elapsed_time": "2:22:30", "remaining_time": "0:00:10", "throughput": 2653.5, "total_tokens": 22689240}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 9.78940321721966e-07, "epoch": 700.9734513274336, "percentage": 99.89, "elapsed_time": "2:22:31", "remaining_time": "0:00:09", "throughput": 2653.61, "total_tokens": 22692696}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 7.776933122816132e-07, "epoch": 701.0530973451328, "percentage": 99.9, "elapsed_time": "2:22:32", "remaining_time": "0:00:08", "throughput": 2653.47, "total_tokens": 22694888}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 5.99578067927986e-07, "epoch": 701.141592920354, "percentage": 99.91, "elapsed_time": "2:22:33", "remaining_time": "0:00:07", "throughput": 2653.55, "total_tokens": 22698120}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 4.445946161224512e-07, "epoch": 701.2300884955753, "percentage": 99.92, "elapsed_time": "2:22:34", "remaining_time": "0:00:06", "throughput": 2653.58, "total_tokens": 22701000}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 3.127429807792126e-07, "epoch": 701.3185840707964, "percentage": 99.94, "elapsed_time": "2:22:35", "remaining_time": "0:00:05", "throughput": 2653.68, "total_tokens": 22704392}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 2.040231822320049e-07, "epoch": 701.4070796460177, "percentage": 99.95, "elapsed_time": "2:22:36", "remaining_time": "0:00:04", "throughput": 2653.69, "total_tokens": 22707096}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.1843523723409354e-07, "epoch": 701.4955752212389, "percentage": 99.96, "elapsed_time": "2:22:37", "remaining_time": "0:00:03", "throughput": 2653.75, "total_tokens": 22710184}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 5.597915897492811e-08, "epoch": 701.5840707964602, "percentage": 99.98, "elapsed_time": "2:22:38", "remaining_time": "0:00:02", "throughput": 2653.8, "total_tokens": 22713240}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 1.6654957113448885e-08, "epoch": 701.6725663716815, "percentage": 99.99, "elapsed_time": "2:22:39", "remaining_time": "0:00:01", "throughput": 2653.81, "total_tokens": 22715928}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 4.626377114735902e-10, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "2:22:40", "remaining_time": "0:00:00", "throughput": 2653.79, "total_tokens": 22718312}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.8050469756126404, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "2:22:41", "remaining_time": "0:00:00", "throughput": 2653.49, "total_tokens": 22718312}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "2:22:43", "remaining_time": "0:00:00", "throughput": 2652.98, "total_tokens": 22718312}