rbelanec commited on
Commit
9d092a7
verified
1 Parent(s): 02454f7

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 sha256:62611ed7ac4e34612bde00a6df2b460325df673c4c925d6b64df06cdb04465b7
3
  size 1638528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c26c7a619b7c1ed086b88e6a4e6bffd7a20dfde1834944f545874a05e11ba292
3
  size 1638528
trainer_log.jsonl CHANGED
@@ -8157,3 +8157,45 @@
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.3806, "lr": 1.9632065447422463e-05, "epoch": 18.762376237623762, "percentage": 99.49, "elapsed_time": "5:27:19", "remaining_time": "0:01:41", "throughput": 1879.18, "total_tokens": 36905440}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.3315, "lr": 1.8690637803880916e-05, "epoch": 18.764733616218766, "percentage": 99.5, "elapsed_time": "5:27:20", "remaining_time": "0:01:38", "throughput": 1879.27, "total_tokens": 36910256}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.3283248841762543, "epoch": 18.764733616218766, "percentage": 99.5, "elapsed_time": "5:27:54", "remaining_time": "0:01:38", "throughput": 1876.06, "total_tokens": 36910256}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.3806, "lr": 1.9632065447422463e-05, "epoch": 18.762376237623762, "percentage": 99.49, "elapsed_time": "5:27:19", "remaining_time": "0:01:41", "throughput": 1879.18, "total_tokens": 36905440}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.3315, "lr": 1.8690637803880916e-05, "epoch": 18.764733616218766, "percentage": 99.5, "elapsed_time": "5:27:20", "remaining_time": "0:01:38", "throughput": 1879.27, "total_tokens": 36910256}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.3283248841762543, "epoch": 18.764733616218766, "percentage": 99.5, "elapsed_time": "5:27:54", "remaining_time": "0:01:38", "throughput": 1876.06, "total_tokens": 36910256}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.3009, "lr": 1.7772339163019123e-05, "epoch": 18.767090994813767, "percentage": 99.51, "elapsed_time": "5:27:56", "remaining_time": "0:01:36", "throughput": 1876.03, "total_tokens": 36914608}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.3276, "lr": 1.6877169666457138e-05, "epoch": 18.76944837340877, "percentage": 99.52, "elapsed_time": "5:27:58", "remaining_time": "0:01:33", "throughput": 1876.1, "total_tokens": 36918928}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.3168, "lr": 1.6005129452234532e-05, "epoch": 18.77180575200377, "percentage": 99.54, "elapsed_time": "5:28:00", "remaining_time": "0:01:31", "throughput": 1876.18, "total_tokens": 36923520}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.3335, "lr": 1.5156218654843733e-05, "epoch": 18.774163130598772, "percentage": 99.55, "elapsed_time": "5:28:02", "remaining_time": "0:01:28", "throughput": 1876.33, "total_tokens": 36929904}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.3293, "lr": 1.4330437405196683e-05, "epoch": 18.776520509193777, "percentage": 99.56, "elapsed_time": "5:28:03", "remaining_time": "0:01:26", "throughput": 1876.39, "total_tokens": 36933840}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.2867, "lr": 1.352778583062486e-05, "epoch": 18.778877887788777, "percentage": 99.58, "elapsed_time": "5:28:05", "remaining_time": "0:01:24", "throughput": 1876.47, "total_tokens": 36938416}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.2814, "lr": 1.2748264054929237e-05, "epoch": 18.78123526638378, "percentage": 99.59, "elapsed_time": "5:28:06", "remaining_time": "0:01:21", "throughput": 1876.55, "total_tokens": 36943136}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.3216, "lr": 1.1991872198297004e-05, "epoch": 18.783592644978782, "percentage": 99.6, "elapsed_time": "5:28:08", "remaining_time": "0:01:19", "throughput": 1876.64, "total_tokens": 36948224}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.3174, "lr": 1.1258610377384847e-05, "epoch": 18.785950023573786, "percentage": 99.61, "elapsed_time": "5:28:10", "remaining_time": "0:01:16", "throughput": 1876.76, "total_tokens": 36953872}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.3217, "lr": 1.0548478705268982e-05, "epoch": 18.788307402168787, "percentage": 99.62, "elapsed_time": "5:28:11", "remaining_time": "0:01:14", "throughput": 1876.83, "total_tokens": 36958032}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.3144, "lr": 9.86147729147846e-06, "epoch": 18.79066478076379, "percentage": 99.64, "elapsed_time": "5:28:13", "remaining_time": "0:01:11", "throughput": 1876.88, "total_tokens": 36961760}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.2808, "lr": 9.197606241928557e-06, "epoch": 18.79302215935879, "percentage": 99.65, "elapsed_time": "5:28:14", "remaining_time": "0:01:09", "throughput": 1876.91, "total_tokens": 36965136}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.3354, "lr": 8.556865659004042e-06, "epoch": 18.795379537953796, "percentage": 99.66, "elapsed_time": "5:28:16", "remaining_time": "0:01:06", "throughput": 1876.99, "total_tokens": 36969840}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.3325, "lr": 7.939255641525867e-06, "epoch": 18.797736916548796, "percentage": 99.67, "elapsed_time": "5:28:17", "remaining_time": "0:01:04", "throughput": 1877.06, "total_tokens": 36974336}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.305, "lr": 7.344776284751164e-06, "epoch": 18.8000942951438, "percentage": 99.69, "elapsed_time": "5:28:19", "remaining_time": "0:01:01", "throughput": 1877.13, "total_tokens": 36978752}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.2663, "lr": 6.773427680323296e-06, "epoch": 18.8024516737388, "percentage": 99.7, "elapsed_time": "5:28:21", "remaining_time": "0:00:59", "throughput": 1877.25, "total_tokens": 36984416}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.315, "lr": 6.225209916355112e-06, "epoch": 18.804809052333805, "percentage": 99.71, "elapsed_time": "5:28:22", "remaining_time": "0:00:56", "throughput": 1877.31, "total_tokens": 36988512}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.3538, "lr": 5.7001230774123e-06, "epoch": 18.807166430928806, "percentage": 99.72, "elapsed_time": "5:28:24", "remaining_time": "0:00:54", "throughput": 1877.38, "total_tokens": 36993024}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.3711, "lr": 5.198167244446772e-06, "epoch": 18.80952380952381, "percentage": 99.74, "elapsed_time": "5:28:26", "remaining_time": "0:00:51", "throughput": 1877.49, "total_tokens": 36998448}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.3227, "lr": 4.71934249487993e-06, "epoch": 18.81188118811881, "percentage": 99.75, "elapsed_time": "5:28:27", "remaining_time": "0:00:49", "throughput": 1877.6, "total_tokens": 37003600}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.3114, "lr": 4.2636489025527075e-06, "epoch": 18.814238566713815, "percentage": 99.76, "elapsed_time": "5:28:29", "remaining_time": "0:00:46", "throughput": 1877.67, "total_tokens": 37008000}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.3193, "lr": 3.831086537742223e-06, "epoch": 18.816595945308816, "percentage": 99.78, "elapsed_time": "5:28:31", "remaining_time": "0:00:44", "throughput": 1877.76, "total_tokens": 37012608}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.3755, "lr": 3.4216554671451236e-06, "epoch": 18.81895332390382, "percentage": 99.79, "elapsed_time": "5:28:32", "remaining_time": "0:00:41", "throughput": 1877.84, "total_tokens": 37017408}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.363, "lr": 3.035355753894242e-06, "epoch": 18.82131070249882, "percentage": 99.8, "elapsed_time": "5:28:34", "remaining_time": "0:00:39", "throughput": 1877.9, "total_tokens": 37021616}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.3028, "lr": 2.6721874575752477e-06, "epoch": 18.823668081093825, "percentage": 99.81, "elapsed_time": "5:28:35", "remaining_time": "0:00:37", "throughput": 1877.99, "total_tokens": 37026480}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.3195, "lr": 2.3321506341933418e-06, "epoch": 18.826025459688825, "percentage": 99.83, "elapsed_time": "5:28:37", "remaining_time": "0:00:34", "throughput": 1878.08, "total_tokens": 37031408}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.3534, "lr": 2.0152453361732546e-06, "epoch": 18.82838283828383, "percentage": 99.84, "elapsed_time": "5:28:39", "remaining_time": "0:00:32", "throughput": 1878.16, "total_tokens": 37035920}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.3344, "lr": 1.7214716123925554e-06, "epoch": 18.83074021687883, "percentage": 99.85, "elapsed_time": "5:28:40", "remaining_time": "0:00:29", "throughput": 1878.21, "total_tokens": 37039696}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.3248, "lr": 1.4508295081649968e-06, "epoch": 18.833097595473834, "percentage": 99.86, "elapsed_time": "5:28:42", "remaining_time": "0:00:27", "throughput": 1878.29, "total_tokens": 37044208}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.3386, "lr": 1.2033190652238623e-06, "epoch": 18.835454974068835, "percentage": 99.88, "elapsed_time": "5:28:43", "remaining_time": "0:00:24", "throughput": 1878.38, "total_tokens": 37049168}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.3599, "lr": 9.78940321721966e-07, "epoch": 18.83781235266384, "percentage": 99.89, "elapsed_time": "5:28:45", "remaining_time": "0:00:22", "throughput": 1878.46, "total_tokens": 37053712}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.3222, "lr": 7.776933122816132e-07, "epoch": 18.84016973125884, "percentage": 99.9, "elapsed_time": "5:28:47", "remaining_time": "0:00:19", "throughput": 1878.55, "total_tokens": 37058592}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.3024, "lr": 5.99578067927986e-07, "epoch": 18.842527109853844, "percentage": 99.91, "elapsed_time": "5:28:48", "remaining_time": "0:00:17", "throughput": 1878.64, "total_tokens": 37063312}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.3202, "lr": 4.445946161224512e-07, "epoch": 18.844884488448844, "percentage": 99.92, "elapsed_time": "5:28:50", "remaining_time": "0:00:14", "throughput": 1878.73, "total_tokens": 37068192}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.3578, "lr": 3.127429807792126e-07, "epoch": 18.84724186704385, "percentage": 99.94, "elapsed_time": "5:28:52", "remaining_time": "0:00:12", "throughput": 1878.85, "total_tokens": 37074112}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.3563, "lr": 2.040231822320049e-07, "epoch": 18.84959924563885, "percentage": 99.95, "elapsed_time": "5:28:53", "remaining_time": "0:00:09", "throughput": 1878.96, "total_tokens": 37079376}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.314, "lr": 1.1843523723409354e-07, "epoch": 18.851956624233853, "percentage": 99.96, "elapsed_time": "5:28:55", "remaining_time": "0:00:07", "throughput": 1879.03, "total_tokens": 37083760}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.3603, "lr": 5.597915897492811e-08, "epoch": 18.854314002828854, "percentage": 99.98, "elapsed_time": "5:28:57", "remaining_time": "0:00:04", "throughput": 1879.13, "total_tokens": 37088688}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.3479, "lr": 1.6654957113448885e-08, "epoch": 18.85667138142386, "percentage": 99.99, "elapsed_time": "5:28:58", "remaining_time": "0:00:02", "throughput": 1879.21, "total_tokens": 37092992}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.3403, "lr": 4.626377114735902e-10, "epoch": 18.85902876001886, "percentage": 100.0, "elapsed_time": "5:29:00", "remaining_time": "0:00:00", "throughput": 1879.28, "total_tokens": 37097424}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.3285662531852722, "epoch": 18.85902876001886, "percentage": 100.0, "elapsed_time": "5:29:33", "remaining_time": "0:00:00", "throughput": 1876.09, "total_tokens": 37097424}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 18.85902876001886, "percentage": 100.0, "elapsed_time": "5:29:34", "remaining_time": "0:00:00", "throughput": 1876.0, "total_tokens": 37097424}