rbelanec commited on
Commit
9a9f9e4
verified
1 Parent(s): f05535a

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:b5d34a56cc489163ede17027d5ba19bed2bba07db5eb4dccebeccece9bf22e6e
3
  size 460928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adc2e005471996bf661bf837b26ed6ce948abda3fd08dd87ce01062ef333fb01
3
  size 460928
trainer_log.jsonl CHANGED
@@ -8158,3 +8158,44 @@
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.4841, "lr": 1.8690637803880916e-05, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "20:40:47", "remaining_time": "0:06:14", "throughput": 735.12, "total_tokens": 54727600}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.49426430463790894, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "20:46:19", "remaining_time": "0:06:15", "throughput": 731.85, "total_tokens": 54727600}
8160
  {"current_steps": 39805, "total_steps": 40000, "loss": 0.5417, "lr": 1.7772339163019123e-05, "epoch": 1.274086166058511, "percentage": 99.51, "elapsed_time": "20:46:22", "remaining_time": "0:06:06", "throughput": 731.92, "total_tokens": 54734624}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.4841, "lr": 1.8690637803880916e-05, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "20:40:47", "remaining_time": "0:06:14", "throughput": 735.12, "total_tokens": 54727600}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.49426430463790894, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "20:46:19", "remaining_time": "0:06:15", "throughput": 731.85, "total_tokens": 54727600}
8160
  {"current_steps": 39805, "total_steps": 40000, "loss": 0.5417, "lr": 1.7772339163019123e-05, "epoch": 1.274086166058511, "percentage": 99.51, "elapsed_time": "20:46:22", "remaining_time": "0:06:06", "throughput": 731.92, "total_tokens": 54734624}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.3511, "lr": 1.6877169666457138e-05, "epoch": 1.2742462070289995, "percentage": 99.52, "elapsed_time": "20:46:23", "remaining_time": "0:05:56", "throughput": 732.0, "total_tokens": 54741424}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.4041, "lr": 1.6005129452234532e-05, "epoch": 1.274406247999488, "percentage": 99.54, "elapsed_time": "20:46:24", "remaining_time": "0:05:47", "throughput": 732.07, "total_tokens": 54747760}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.3814, "lr": 1.5156218654843733e-05, "epoch": 1.2745662889699763, "percentage": 99.55, "elapsed_time": "20:46:25", "remaining_time": "0:05:38", "throughput": 732.16, "total_tokens": 54754880}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.5959, "lr": 1.4330437405196683e-05, "epoch": 1.2747263299404648, "percentage": 99.56, "elapsed_time": "20:46:26", "remaining_time": "0:05:28", "throughput": 732.24, "total_tokens": 54761840}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.5163, "lr": 1.352778583062486e-05, "epoch": 1.2748863709109532, "percentage": 99.58, "elapsed_time": "20:46:27", "remaining_time": "0:05:19", "throughput": 732.32, "total_tokens": 54768896}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.5016, "lr": 1.2748264054929237e-05, "epoch": 1.2750464118814415, "percentage": 99.59, "elapsed_time": "20:46:28", "remaining_time": "0:05:09", "throughput": 732.41, "total_tokens": 54775792}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.5304, "lr": 1.1991872198297004e-05, "epoch": 1.27520645285193, "percentage": 99.6, "elapsed_time": "20:46:29", "remaining_time": "0:05:00", "throughput": 732.49, "total_tokens": 54783008}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.4474, "lr": 1.1258610377384847e-05, "epoch": 1.2753664938224185, "percentage": 99.61, "elapsed_time": "20:46:30", "remaining_time": "0:04:50", "throughput": 732.58, "total_tokens": 54790336}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.4915, "lr": 1.0548478705268982e-05, "epoch": 1.275526534792907, "percentage": 99.62, "elapsed_time": "20:46:31", "remaining_time": "0:04:41", "throughput": 732.66, "total_tokens": 54797264}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.6021, "lr": 9.86147729147846e-06, "epoch": 1.2756865757633955, "percentage": 99.64, "elapsed_time": "20:46:33", "remaining_time": "0:04:32", "throughput": 732.74, "total_tokens": 54803952}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.5051, "lr": 9.197606241928557e-06, "epoch": 1.275846616733884, "percentage": 99.65, "elapsed_time": "20:46:34", "remaining_time": "0:04:22", "throughput": 732.82, "total_tokens": 54810688}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.3728, "lr": 8.556865659004042e-06, "epoch": 1.2760066577043723, "percentage": 99.66, "elapsed_time": "20:46:35", "remaining_time": "0:04:13", "throughput": 732.9, "total_tokens": 54817216}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.5634, "lr": 7.939255641525867e-06, "epoch": 1.2761666986748608, "percentage": 99.67, "elapsed_time": "20:46:36", "remaining_time": "0:04:03", "throughput": 732.98, "total_tokens": 54824416}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.3852, "lr": 7.344776284751164e-06, "epoch": 1.2763267396453493, "percentage": 99.69, "elapsed_time": "20:46:37", "remaining_time": "0:03:54", "throughput": 733.07, "total_tokens": 54831648}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.4774, "lr": 6.773427680323296e-06, "epoch": 1.2764867806158375, "percentage": 99.7, "elapsed_time": "20:46:38", "remaining_time": "0:03:45", "throughput": 733.16, "total_tokens": 54839168}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.3739, "lr": 6.225209916355112e-06, "epoch": 1.276646821586326, "percentage": 99.71, "elapsed_time": "20:46:39", "remaining_time": "0:03:35", "throughput": 733.24, "total_tokens": 54845904}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.4063, "lr": 5.7001230774123e-06, "epoch": 1.2768068625568145, "percentage": 99.72, "elapsed_time": "20:46:40", "remaining_time": "0:03:26", "throughput": 733.32, "total_tokens": 54852784}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.5106, "lr": 5.198167244446772e-06, "epoch": 1.276966903527303, "percentage": 99.74, "elapsed_time": "20:46:41", "remaining_time": "0:03:16", "throughput": 733.4, "total_tokens": 54859440}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.6145, "lr": 4.71934249487993e-06, "epoch": 1.2771269444977915, "percentage": 99.75, "elapsed_time": "20:46:42", "remaining_time": "0:03:07", "throughput": 733.49, "total_tokens": 54866608}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.444, "lr": 4.2636489025527075e-06, "epoch": 1.27728698546828, "percentage": 99.76, "elapsed_time": "20:46:43", "remaining_time": "0:02:58", "throughput": 733.56, "total_tokens": 54873104}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.3843, "lr": 3.831086537742223e-06, "epoch": 1.2774470264387683, "percentage": 99.78, "elapsed_time": "20:46:44", "remaining_time": "0:02:48", "throughput": 733.64, "total_tokens": 54879648}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.3684, "lr": 3.4216554671451236e-06, "epoch": 1.2776070674092568, "percentage": 99.79, "elapsed_time": "20:46:45", "remaining_time": "0:02:39", "throughput": 733.72, "total_tokens": 54886688}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.3599, "lr": 3.035355753894242e-06, "epoch": 1.2777671083797453, "percentage": 99.8, "elapsed_time": "20:46:46", "remaining_time": "0:02:29", "throughput": 733.8, "total_tokens": 54893328}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.5776, "lr": 2.6721874575752477e-06, "epoch": 1.2779271493502335, "percentage": 99.81, "elapsed_time": "20:46:47", "remaining_time": "0:02:20", "throughput": 733.88, "total_tokens": 54899984}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.5556, "lr": 2.3321506341933418e-06, "epoch": 1.278087190320722, "percentage": 99.83, "elapsed_time": "20:46:48", "remaining_time": "0:02:11", "throughput": 733.96, "total_tokens": 54906832}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.3766, "lr": 2.0152453361732546e-06, "epoch": 1.2782472312912105, "percentage": 99.84, "elapsed_time": "20:46:49", "remaining_time": "0:02:01", "throughput": 734.04, "total_tokens": 54913632}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.5157, "lr": 1.7214716123925554e-06, "epoch": 1.278407272261699, "percentage": 99.85, "elapsed_time": "20:46:50", "remaining_time": "0:01:52", "throughput": 734.13, "total_tokens": 54920528}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.5987, "lr": 1.4508295081649968e-06, "epoch": 1.2785673132321875, "percentage": 99.86, "elapsed_time": "20:46:51", "remaining_time": "0:01:43", "throughput": 734.21, "total_tokens": 54927584}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.5308, "lr": 1.2033190652238623e-06, "epoch": 1.2787273542026758, "percentage": 99.88, "elapsed_time": "20:46:52", "remaining_time": "0:01:33", "throughput": 734.29, "total_tokens": 54934240}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.5319, "lr": 9.78940321721966e-07, "epoch": 1.2788873951731643, "percentage": 99.89, "elapsed_time": "20:46:53", "remaining_time": "0:01:24", "throughput": 734.37, "total_tokens": 54941232}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.3879, "lr": 7.776933122816132e-07, "epoch": 1.2790474361436528, "percentage": 99.9, "elapsed_time": "20:46:54", "remaining_time": "0:01:14", "throughput": 734.45, "total_tokens": 54947808}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.5018, "lr": 5.99578067927986e-07, "epoch": 1.2792074771141413, "percentage": 99.91, "elapsed_time": "20:46:55", "remaining_time": "0:01:05", "throughput": 734.53, "total_tokens": 54954704}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.471, "lr": 4.445946161224512e-07, "epoch": 1.2793675180846296, "percentage": 99.92, "elapsed_time": "20:46:57", "remaining_time": "0:00:56", "throughput": 734.61, "total_tokens": 54961680}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.5018, "lr": 3.127429807792126e-07, "epoch": 1.279527559055118, "percentage": 99.94, "elapsed_time": "20:46:58", "remaining_time": "0:00:46", "throughput": 734.7, "total_tokens": 54968656}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.4346, "lr": 2.040231822320049e-07, "epoch": 1.2796876000256066, "percentage": 99.95, "elapsed_time": "20:46:59", "remaining_time": "0:00:37", "throughput": 734.77, "total_tokens": 54975280}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.4366, "lr": 1.1843523723409354e-07, "epoch": 1.279847640996095, "percentage": 99.96, "elapsed_time": "20:47:00", "remaining_time": "0:00:28", "throughput": 734.85, "total_tokens": 54982032}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.3981, "lr": 5.597915897492811e-08, "epoch": 1.2800076819665835, "percentage": 99.98, "elapsed_time": "20:47:01", "remaining_time": "0:00:18", "throughput": 734.93, "total_tokens": 54988688}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.3084, "lr": 1.6654957113448885e-08, "epoch": 1.2801677229370718, "percentage": 99.99, "elapsed_time": "20:47:02", "remaining_time": "0:00:09", "throughput": 735.01, "total_tokens": 54995344}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.4098, "lr": 4.626377114735902e-10, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "20:47:03", "remaining_time": "0:00:00", "throughput": 735.09, "total_tokens": 55002224}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.49421823024749756, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "20:52:35", "remaining_time": "0:00:00", "throughput": 731.84, "total_tokens": 55002224}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "20:52:37", "remaining_time": "0:00:00", "throughput": 731.83, "total_tokens": 55002224}