rbelanec commited on
Commit
79e4627
·
verified ·
1 Parent(s): 94d5a44

Training in progress, step 40000

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +40 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3538c6d371af91484863df7496b569f942b882ac9ba4702a77412bb8bca3874a
3
  size 1638528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9055d98e9526c39b4b47b8d48ea6f616e642e427913fc945230169def2a07463
3
  size 1638528
trainer_log.jsonl CHANGED
@@ -8159,3 +8159,43 @@
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.5843693017959595, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "2:09:20", "remaining_time": "0:00:38", "throughput": 1374.11, "total_tokens": 10663840}
8160
  {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 1.7772339163019123e-05, "epoch": 442.27777777777777, "percentage": 99.51, "elapsed_time": "2:09:22", "remaining_time": "0:00:38", "throughput": 1373.94, "total_tokens": 10665136}
8161
  {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 1.6877169666457138e-05, "epoch": 442.3333333333333, "percentage": 99.52, "elapsed_time": "2:09:23", "remaining_time": "0:00:37", "throughput": 1373.95, "total_tokens": 10666480}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.5843693017959595, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "2:09:20", "remaining_time": "0:00:38", "throughput": 1374.11, "total_tokens": 10663840}
8160
  {"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 1.7772339163019123e-05, "epoch": 442.27777777777777, "percentage": 99.51, "elapsed_time": "2:09:22", "remaining_time": "0:00:38", "throughput": 1373.94, "total_tokens": 10665136}
8161
  {"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 1.6877169666457138e-05, "epoch": 442.3333333333333, "percentage": 99.52, "elapsed_time": "2:09:23", "remaining_time": "0:00:37", "throughput": 1373.95, "total_tokens": 10666480}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 1.6005129452234532e-05, "epoch": 442.3888888888889, "percentage": 99.54, "elapsed_time": "2:09:24", "remaining_time": "0:00:36", "throughput": 1373.97, "total_tokens": 10667840}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 1.5156218654843733e-05, "epoch": 442.44444444444446, "percentage": 99.55, "elapsed_time": "2:09:25", "remaining_time": "0:00:35", "throughput": 1373.98, "total_tokens": 10669184}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 1.4330437405196683e-05, "epoch": 442.5, "percentage": 99.56, "elapsed_time": "2:09:26", "remaining_time": "0:00:34", "throughput": 1373.99, "total_tokens": 10670496}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 1.352778583062486e-05, "epoch": 442.55555555555554, "percentage": 99.58, "elapsed_time": "2:09:26", "remaining_time": "0:00:33", "throughput": 1374.0, "total_tokens": 10671776}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 1.2748264054929237e-05, "epoch": 442.6111111111111, "percentage": 99.59, "elapsed_time": "2:09:27", "remaining_time": "0:00:32", "throughput": 1374.01, "total_tokens": 10673120}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.1991872198297004e-05, "epoch": 442.6666666666667, "percentage": 99.6, "elapsed_time": "2:09:28", "remaining_time": "0:00:31", "throughput": 1374.03, "total_tokens": 10674480}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.0003, "lr": 1.1258610377384847e-05, "epoch": 442.72222222222223, "percentage": 99.61, "elapsed_time": "2:09:29", "remaining_time": "0:00:30", "throughput": 1374.04, "total_tokens": 10675808}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.0548478705268982e-05, "epoch": 442.77777777777777, "percentage": 99.62, "elapsed_time": "2:09:30", "remaining_time": "0:00:29", "throughput": 1374.05, "total_tokens": 10677120}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.0001, "lr": 9.86147729147846e-06, "epoch": 442.8333333333333, "percentage": 99.64, "elapsed_time": "2:09:31", "remaining_time": "0:00:28", "throughput": 1374.06, "total_tokens": 10678448}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 9.197606241928557e-06, "epoch": 442.8888888888889, "percentage": 99.65, "elapsed_time": "2:09:32", "remaining_time": "0:00:27", "throughput": 1374.08, "total_tokens": 10679840}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 8.556865659004042e-06, "epoch": 442.94444444444446, "percentage": 99.66, "elapsed_time": "2:09:33", "remaining_time": "0:00:26", "throughput": 1374.09, "total_tokens": 10681216}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 7.939255641525867e-06, "epoch": 443.0, "percentage": 99.67, "elapsed_time": "2:09:34", "remaining_time": "0:00:25", "throughput": 1374.09, "total_tokens": 10682624}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 7.344776284751164e-06, "epoch": 443.05555555555554, "percentage": 99.69, "elapsed_time": "2:09:35", "remaining_time": "0:00:24", "throughput": 1374.06, "total_tokens": 10683920}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.0001, "lr": 6.773427680323296e-06, "epoch": 443.1111111111111, "percentage": 99.7, "elapsed_time": "2:09:36", "remaining_time": "0:00:23", "throughput": 1374.07, "total_tokens": 10685216}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 6.225209916355112e-06, "epoch": 443.1666666666667, "percentage": 99.71, "elapsed_time": "2:09:37", "remaining_time": "0:00:22", "throughput": 1374.09, "total_tokens": 10686576}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 5.7001230774123e-06, "epoch": 443.22222222222223, "percentage": 99.72, "elapsed_time": "2:09:38", "remaining_time": "0:00:21", "throughput": 1374.1, "total_tokens": 10687936}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 5.198167244446772e-06, "epoch": 443.27777777777777, "percentage": 99.74, "elapsed_time": "2:09:39", "remaining_time": "0:00:20", "throughput": 1374.12, "total_tokens": 10689280}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.0001, "lr": 4.71934249487993e-06, "epoch": 443.3333333333333, "percentage": 99.75, "elapsed_time": "2:09:39", "remaining_time": "0:00:19", "throughput": 1374.13, "total_tokens": 10690656}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 4.2636489025527075e-06, "epoch": 443.3888888888889, "percentage": 99.76, "elapsed_time": "2:09:40", "remaining_time": "0:00:18", "throughput": 1374.15, "total_tokens": 10691984}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.0001, "lr": 3.831086537742223e-06, "epoch": 443.44444444444446, "percentage": 99.78, "elapsed_time": "2:09:41", "remaining_time": "0:00:17", "throughput": 1374.16, "total_tokens": 10693360}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 3.4216554671451236e-06, "epoch": 443.5, "percentage": 99.79, "elapsed_time": "2:09:42", "remaining_time": "0:00:16", "throughput": 1374.17, "total_tokens": 10694672}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 3.035355753894242e-06, "epoch": 443.55555555555554, "percentage": 99.8, "elapsed_time": "2:09:43", "remaining_time": "0:00:15", "throughput": 1374.18, "total_tokens": 10695984}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 2.6721874575752477e-06, "epoch": 443.6111111111111, "percentage": 99.81, "elapsed_time": "2:09:44", "remaining_time": "0:00:14", "throughput": 1374.2, "total_tokens": 10697360}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 2.3321506341933418e-06, "epoch": 443.6666666666667, "percentage": 99.83, "elapsed_time": "2:09:45", "remaining_time": "0:00:13", "throughput": 1374.21, "total_tokens": 10698688}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.0001, "lr": 2.0152453361732546e-06, "epoch": 443.72222222222223, "percentage": 99.84, "elapsed_time": "2:09:46", "remaining_time": "0:00:12", "throughput": 1374.23, "total_tokens": 10700048}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 1.7214716123925554e-06, "epoch": 443.77777777777777, "percentage": 99.85, "elapsed_time": "2:09:47", "remaining_time": "0:00:11", "throughput": 1374.24, "total_tokens": 10701392}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.0003, "lr": 1.4508295081649968e-06, "epoch": 443.8333333333333, "percentage": 99.86, "elapsed_time": "2:09:48", "remaining_time": "0:00:10", "throughput": 1374.25, "total_tokens": 10702704}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 1.2033190652238623e-06, "epoch": 443.8888888888889, "percentage": 99.88, "elapsed_time": "2:09:48", "remaining_time": "0:00:09", "throughput": 1374.26, "total_tokens": 10704048}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 9.78940321721966e-07, "epoch": 443.94444444444446, "percentage": 99.89, "elapsed_time": "2:09:49", "remaining_time": "0:00:08", "throughput": 1374.28, "total_tokens": 10705408}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 7.776933122816132e-07, "epoch": 444.0, "percentage": 99.9, "elapsed_time": "2:09:50", "remaining_time": "0:00:07", "throughput": 1374.27, "total_tokens": 10706768}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 5.99578067927986e-07, "epoch": 444.05555555555554, "percentage": 99.91, "elapsed_time": "2:09:51", "remaining_time": "0:00:06", "throughput": 1374.25, "total_tokens": 10708096}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 4.445946161224512e-07, "epoch": 444.1111111111111, "percentage": 99.92, "elapsed_time": "2:09:52", "remaining_time": "0:00:05", "throughput": 1374.26, "total_tokens": 10709424}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 3.127429807792126e-07, "epoch": 444.1666666666667, "percentage": 99.94, "elapsed_time": "2:09:53", "remaining_time": "0:00:04", "throughput": 1374.27, "total_tokens": 10710768}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 2.040231822320049e-07, "epoch": 444.22222222222223, "percentage": 99.95, "elapsed_time": "2:09:54", "remaining_time": "0:00:03", "throughput": 1374.29, "total_tokens": 10712128}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.1843523723409354e-07, "epoch": 444.27777777777777, "percentage": 99.96, "elapsed_time": "2:09:55", "remaining_time": "0:00:02", "throughput": 1374.25, "total_tokens": 10713472}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 5.597915897492811e-08, "epoch": 444.3333333333333, "percentage": 99.98, "elapsed_time": "2:09:56", "remaining_time": "0:00:01", "throughput": 1374.27, "total_tokens": 10714816}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 1.6654957113448885e-08, "epoch": 444.3888888888889, "percentage": 99.99, "elapsed_time": "2:09:57", "remaining_time": "0:00:00", "throughput": 1374.27, "total_tokens": 10716112}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.0001, "lr": 4.626377114735902e-10, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "2:09:58", "remaining_time": "0:00:00", "throughput": 1374.29, "total_tokens": 10717440}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 1.584324836730957, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "2:09:59", "remaining_time": "0:00:00", "throughput": 1374.08, "total_tokens": 10717440}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "2:10:00", "remaining_time": "0:00:00", "throughput": 1373.9, "total_tokens": 10717440}