rbelanec commited on
Commit
edabc39
·
verified ·
1 Parent(s): e17c0ac

Training in progress, step 40000

Browse files
Files changed (1) hide show
  1. trainer_log.jsonl +42 -0
trainer_log.jsonl CHANGED
@@ -8157,3 +8157,45 @@
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.4566, "lr": 3.2720109079037443e-09, "epoch": 1.273766084117534, "percentage": 99.49, "elapsed_time": "1 day, 8:38:12", "remaining_time": "0:10:05", "throughput": 458.94, "total_tokens": 53921712}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.4209, "lr": 3.1151063006468193e-09, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 8:38:14", "remaining_time": "0:09:50", "throughput": 458.99, "total_tokens": 53928784}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.44395196437835693, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 8:46:34", "remaining_time": "0:09:52", "throughput": 457.04, "total_tokens": 53928784}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 0.4566, "lr": 3.2720109079037443e-09, "epoch": 1.273766084117534, "percentage": 99.49, "elapsed_time": "1 day, 8:38:12", "remaining_time": "0:10:05", "throughput": 458.94, "total_tokens": 53921712}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 0.4209, "lr": 3.1151063006468193e-09, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 8:38:14", "remaining_time": "0:09:50", "throughput": 458.99, "total_tokens": 53928784}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.44395196437835693, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 8:46:34", "remaining_time": "0:09:52", "throughput": 457.04, "total_tokens": 53928784}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 0.5255, "lr": 2.962056527169854e-09, "epoch": 1.274086166058511, "percentage": 99.51, "elapsed_time": "1 day, 8:46:38", "remaining_time": "0:09:38", "throughput": 457.09, "total_tokens": 53935552}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 0.3353, "lr": 2.8128616110761898e-09, "epoch": 1.2742462070289995, "percentage": 99.52, "elapsed_time": "1 day, 8:46:40", "remaining_time": "0:09:23", "throughput": 457.14, "total_tokens": 53942256}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 0.3467, "lr": 2.6675215753724223e-09, "epoch": 1.274406247999488, "percentage": 99.54, "elapsed_time": "1 day, 8:46:42", "remaining_time": "0:09:08", "throughput": 457.18, "total_tokens": 53948512}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 0.2884, "lr": 2.5260364424739557e-09, "epoch": 1.2745662889699763, "percentage": 99.55, "elapsed_time": "1 day, 8:46:45", "remaining_time": "0:08:53", "throughput": 457.23, "total_tokens": 53955520}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 0.4072, "lr": 2.3884062341994475e-09, "epoch": 1.2747263299404648, "percentage": 99.56, "elapsed_time": "1 day, 8:46:47", "remaining_time": "0:08:38", "throughput": 457.28, "total_tokens": 53962352}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 0.4422, "lr": 2.25463097177081e-09, "epoch": 1.2748863709109532, "percentage": 99.58, "elapsed_time": "1 day, 8:46:49", "remaining_time": "0:08:23", "throughput": 457.33, "total_tokens": 53969264}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 0.3812, "lr": 2.1247106758215397e-09, "epoch": 1.2750464118814415, "percentage": 99.59, "elapsed_time": "1 day, 8:46:51", "remaining_time": "0:08:08", "throughput": 457.38, "total_tokens": 53976032}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 0.2977, "lr": 1.998645366382834e-09, "epoch": 1.27520645285193, "percentage": 99.6, "elapsed_time": "1 day, 8:46:54", "remaining_time": "0:07:53", "throughput": 457.43, "total_tokens": 53982976}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 0.4371, "lr": 1.876435062897475e-09, "epoch": 1.2753664938224185, "percentage": 99.61, "elapsed_time": "1 day, 8:46:56", "remaining_time": "0:07:39", "throughput": 457.48, "total_tokens": 53990112}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 0.4302, "lr": 1.758079784211497e-09, "epoch": 1.275526534792907, "percentage": 99.62, "elapsed_time": "1 day, 8:46:58", "remaining_time": "0:07:24", "throughput": 457.53, "total_tokens": 53996960}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 0.5152, "lr": 1.6435795485797434e-09, "epoch": 1.2756865757633955, "percentage": 99.64, "elapsed_time": "1 day, 8:47:01", "remaining_time": "0:07:09", "throughput": 457.58, "total_tokens": 54003616}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 0.6194, "lr": 1.5329343736547596e-09, "epoch": 1.275846616733884, "percentage": 99.65, "elapsed_time": "1 day, 8:47:03", "remaining_time": "0:06:54", "throughput": 457.62, "total_tokens": 54010320}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 0.3193, "lr": 1.4261442765006739e-09, "epoch": 1.2760066577043723, "percentage": 99.66, "elapsed_time": "1 day, 8:47:05", "remaining_time": "0:06:39", "throughput": 457.67, "total_tokens": 54016752}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 0.5354, "lr": 1.3232092735876445e-09, "epoch": 1.2761666986748608, "percentage": 99.67, "elapsed_time": "1 day, 8:47:07", "remaining_time": "0:06:24", "throughput": 457.72, "total_tokens": 54023792}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 0.3291, "lr": 1.2241293807918607e-09, "epoch": 1.2763267396453493, "percentage": 99.69, "elapsed_time": "1 day, 8:47:10", "remaining_time": "0:06:10", "throughput": 457.77, "total_tokens": 54030800}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 0.4874, "lr": 1.128904613387216e-09, "epoch": 1.2764867806158375, "percentage": 99.7, "elapsed_time": "1 day, 8:47:12", "remaining_time": "0:05:55", "throughput": 457.83, "total_tokens": 54038272}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 0.6306, "lr": 1.0375349860591853e-09, "epoch": 1.276646821586326, "percentage": 99.71, "elapsed_time": "1 day, 8:47:14", "remaining_time": "0:05:40", "throughput": 457.87, "total_tokens": 54044944}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 0.2892, "lr": 9.5002051290205e-10, "epoch": 1.2768068625568145, "percentage": 99.72, "elapsed_time": "1 day, 8:47:17", "remaining_time": "0:05:25", "throughput": 457.92, "total_tokens": 54051744}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 0.3713, "lr": 8.663612074077954e-10, "epoch": 1.276966903527303, "percentage": 99.74, "elapsed_time": "1 day, 8:47:19", "remaining_time": "0:05:10", "throughput": 457.97, "total_tokens": 54058176}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 0.5137, "lr": 7.865570824799884e-10, "epoch": 1.2771269444977915, "percentage": 99.75, "elapsed_time": "1 day, 8:47:21", "remaining_time": "0:04:55", "throughput": 458.02, "total_tokens": 54065248}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 0.4038, "lr": 7.106081504254514e-10, "epoch": 1.27728698546828, "percentage": 99.76, "elapsed_time": "1 day, 8:47:23", "remaining_time": "0:04:41", "throughput": 458.06, "total_tokens": 54071648}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 0.316, "lr": 6.385144229570372e-10, "epoch": 1.2774470264387683, "percentage": 99.78, "elapsed_time": "1 day, 8:47:25", "remaining_time": "0:04:26", "throughput": 458.11, "total_tokens": 54078176}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 0.4233, "lr": 5.70275911190854e-10, "epoch": 1.2776070674092568, "percentage": 99.79, "elapsed_time": "1 day, 8:47:28", "remaining_time": "0:04:11", "throughput": 458.16, "total_tokens": 54084912}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 0.4325, "lr": 5.058926256490403e-10, "epoch": 1.2777671083797453, "percentage": 99.8, "elapsed_time": "1 day, 8:47:30", "remaining_time": "0:03:56", "throughput": 458.21, "total_tokens": 54091424}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 0.4069, "lr": 4.4536457626254134e-10, "epoch": 1.2779271493502335, "percentage": 99.81, "elapsed_time": "1 day, 8:47:32", "remaining_time": "0:03:41", "throughput": 458.25, "total_tokens": 54098000}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 0.4892, "lr": 3.88691772365557e-10, "epoch": 1.278087190320722, "percentage": 99.83, "elapsed_time": "1 day, 8:47:34", "remaining_time": "0:03:26", "throughput": 458.3, "total_tokens": 54104816}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 0.4008, "lr": 3.358742226955425e-10, "epoch": 1.2782472312912105, "percentage": 99.84, "elapsed_time": "1 day, 8:47:37", "remaining_time": "0:03:12", "throughput": 458.35, "total_tokens": 54111488}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 0.5212, "lr": 2.8691193539875925e-10, "epoch": 1.278407272261699, "percentage": 99.85, "elapsed_time": "1 day, 8:47:39", "remaining_time": "0:02:57", "throughput": 458.4, "total_tokens": 54118352}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 0.4056, "lr": 2.418049180274995e-10, "epoch": 1.2785673132321875, "percentage": 99.86, "elapsed_time": "1 day, 8:47:41", "remaining_time": "0:02:42", "throughput": 458.45, "total_tokens": 54125232}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 0.56, "lr": 2.005531775373104e-10, "epoch": 1.2787273542026758, "percentage": 99.88, "elapsed_time": "1 day, 8:47:43", "remaining_time": "0:02:27", "throughput": 458.5, "total_tokens": 54131792}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 0.4518, "lr": 1.6315672028699435e-10, "epoch": 1.2788873951731643, "percentage": 99.89, "elapsed_time": "1 day, 8:47:46", "remaining_time": "0:02:12", "throughput": 458.55, "total_tokens": 54138736}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 0.3408, "lr": 1.2961555204693555e-10, "epoch": 1.2790474361436528, "percentage": 99.9, "elapsed_time": "1 day, 8:47:48", "remaining_time": "0:01:58", "throughput": 458.59, "total_tokens": 54145120}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 0.4988, "lr": 9.992967798799768e-11, "epoch": 1.2792074771141413, "percentage": 99.91, "elapsed_time": "1 day, 8:47:50", "remaining_time": "0:01:43", "throughput": 458.64, "total_tokens": 54151872}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 0.3944, "lr": 7.409910268707521e-11, "epoch": 1.2793675180846296, "percentage": 99.92, "elapsed_time": "1 day, 8:47:52", "remaining_time": "0:01:28", "throughput": 458.69, "total_tokens": 54158800}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 0.5413, "lr": 5.212383012986877e-11, "epoch": 1.279527559055118, "percentage": 99.94, "elapsed_time": "1 day, 8:47:55", "remaining_time": "0:01:13", "throughput": 458.74, "total_tokens": 54165648}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 0.4645, "lr": 3.400386370533415e-11, "epoch": 1.2796876000256066, "percentage": 99.95, "elapsed_time": "1 day, 8:47:57", "remaining_time": "0:00:59", "throughput": 458.79, "total_tokens": 54172192}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 0.3328, "lr": 1.9739206205682258e-11, "epoch": 1.279847640996095, "percentage": 99.96, "elapsed_time": "1 day, 8:47:59", "remaining_time": "0:00:44", "throughput": 458.83, "total_tokens": 54178880}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 0.4789, "lr": 9.329859829154685e-12, "epoch": 1.2800076819665835, "percentage": 99.98, "elapsed_time": "1 day, 8:48:01", "remaining_time": "0:00:29", "throughput": 458.88, "total_tokens": 54185392}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 0.3449, "lr": 2.7758261855748148e-12, "epoch": 1.2801677229370718, "percentage": 99.99, "elapsed_time": "1 day, 8:48:03", "remaining_time": "0:00:14", "throughput": 458.93, "total_tokens": 54192000}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 0.3773, "lr": 7.710628524559838e-14, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "1 day, 8:48:06", "remaining_time": "0:00:00", "throughput": 458.98, "total_tokens": 54198768}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.44395196437835693, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "1 day, 8:56:26", "remaining_time": "0:00:00", "throughput": 457.04, "total_tokens": 54198768}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "1 day, 8:56:27", "remaining_time": "0:00:00", "throughput": 457.04, "total_tokens": 54198768}