rbelanec commited on
Commit
8ebda12
·
verified ·
1 Parent(s): a929e10

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": 4.0054, "lr": 3.2720109079037443e-09, "epoch": 698.1592920353983, "percentage": 99.49, "elapsed_time": "3:54:22", "remaining_time": "0:01:12", "throughput": 1607.2, "total_tokens": 22601024}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 3.1658, "lr": 3.1151063006468193e-09, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "3:54:24", "remaining_time": "0:01:10", "throughput": 1607.23, "total_tokens": 22604096}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 3.2396206855773926, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "3:54:25", "remaining_time": "0:01:10", "throughput": 1607.1, "total_tokens": 22604096}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8157
  {"current_steps": 39795, "total_steps": 40000, "loss": 4.0054, "lr": 3.2720109079037443e-09, "epoch": 698.1592920353983, "percentage": 99.49, "elapsed_time": "3:54:22", "remaining_time": "0:01:12", "throughput": 1607.2, "total_tokens": 22601024}
8158
  {"current_steps": 39800, "total_steps": 40000, "loss": 3.1658, "lr": 3.1151063006468193e-09, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "3:54:24", "remaining_time": "0:01:10", "throughput": 1607.23, "total_tokens": 22604096}
8159
  {"current_steps": 39800, "total_steps": 40000, "eval_loss": 3.2396206855773926, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "3:54:25", "remaining_time": "0:01:10", "throughput": 1607.1, "total_tokens": 22604096}
8160
+ {"current_steps": 39805, "total_steps": 40000, "loss": 3.1605, "lr": 2.962056527169854e-09, "epoch": 698.3362831858407, "percentage": 99.51, "elapsed_time": "3:54:28", "remaining_time": "0:01:08", "throughput": 1606.9, "total_tokens": 22607040}
8161
+ {"current_steps": 39810, "total_steps": 40000, "loss": 3.3124, "lr": 2.8128616110761898e-09, "epoch": 698.4247787610619, "percentage": 99.52, "elapsed_time": "3:54:30", "remaining_time": "0:01:07", "throughput": 1606.88, "total_tokens": 22609568}
8162
+ {"current_steps": 39815, "total_steps": 40000, "loss": 3.3526, "lr": 2.6675215753724223e-09, "epoch": 698.5132743362832, "percentage": 99.54, "elapsed_time": "3:54:32", "remaining_time": "0:01:05", "throughput": 1606.88, "total_tokens": 22612320}
8163
+ {"current_steps": 39820, "total_steps": 40000, "loss": 3.2821, "lr": 2.5260364424739557e-09, "epoch": 698.6017699115044, "percentage": 99.55, "elapsed_time": "3:54:33", "remaining_time": "0:01:03", "throughput": 1606.89, "total_tokens": 22615328}
8164
+ {"current_steps": 39825, "total_steps": 40000, "loss": 3.9491, "lr": 2.3884062341994475e-09, "epoch": 698.6902654867257, "percentage": 99.56, "elapsed_time": "3:54:35", "remaining_time": "0:01:01", "throughput": 1606.94, "total_tokens": 22618784}
8165
+ {"current_steps": 39830, "total_steps": 40000, "loss": 2.9556, "lr": 2.25463097177081e-09, "epoch": 698.7787610619469, "percentage": 99.58, "elapsed_time": "3:54:37", "remaining_time": "0:01:00", "throughput": 1606.93, "total_tokens": 22621376}
8166
+ {"current_steps": 39835, "total_steps": 40000, "loss": 2.9159, "lr": 2.1247106758215397e-09, "epoch": 698.8672566371681, "percentage": 99.59, "elapsed_time": "3:54:39", "remaining_time": "0:00:58", "throughput": 1606.92, "total_tokens": 22623936}
8167
+ {"current_steps": 39840, "total_steps": 40000, "loss": 3.1608, "lr": 1.998645366382834e-09, "epoch": 698.9557522123894, "percentage": 99.6, "elapsed_time": "3:54:40", "remaining_time": "0:00:56", "throughput": 1606.95, "total_tokens": 22627120}
8168
+ {"current_steps": 39845, "total_steps": 40000, "loss": 3.5056, "lr": 1.876435062897475e-09, "epoch": 699.0353982300885, "percentage": 99.61, "elapsed_time": "3:54:42", "remaining_time": "0:00:54", "throughput": 1606.91, "total_tokens": 22629960}
8169
+ {"current_steps": 39850, "total_steps": 40000, "loss": 2.8496, "lr": 1.758079784211497e-09, "epoch": 699.1238938053098, "percentage": 99.62, "elapsed_time": "3:54:44", "remaining_time": "0:00:53", "throughput": 1606.92, "total_tokens": 22632840}
8170
+ {"current_steps": 39855, "total_steps": 40000, "loss": 3.8849, "lr": 1.6435795485797434e-09, "epoch": 699.212389380531, "percentage": 99.64, "elapsed_time": "3:54:46", "remaining_time": "0:00:51", "throughput": 1606.92, "total_tokens": 22635656}
8171
+ {"current_steps": 39860, "total_steps": 40000, "loss": 3.3479, "lr": 1.5329343736547596e-09, "epoch": 699.3008849557522, "percentage": 99.65, "elapsed_time": "3:54:48", "remaining_time": "0:00:49", "throughput": 1606.93, "total_tokens": 22638632}
8172
+ {"current_steps": 39865, "total_steps": 40000, "loss": 3.1947, "lr": 1.4261442765006739e-09, "epoch": 699.3893805309734, "percentage": 99.66, "elapsed_time": "3:54:49", "remaining_time": "0:00:47", "throughput": 1606.93, "total_tokens": 22641400}
8173
+ {"current_steps": 39870, "total_steps": 40000, "loss": 3.2287, "lr": 1.3232092735876445e-09, "epoch": 699.4778761061947, "percentage": 99.67, "elapsed_time": "3:54:51", "remaining_time": "0:00:45", "throughput": 1606.94, "total_tokens": 22644264}
8174
+ {"current_steps": 39875, "total_steps": 40000, "loss": 3.2848, "lr": 1.2241293807918607e-09, "epoch": 699.566371681416, "percentage": 99.69, "elapsed_time": "3:54:53", "remaining_time": "0:00:44", "throughput": 1606.95, "total_tokens": 22647128}
8175
+ {"current_steps": 39880, "total_steps": 40000, "loss": 3.7001, "lr": 1.128904613387216e-09, "epoch": 699.6548672566372, "percentage": 99.7, "elapsed_time": "3:54:55", "remaining_time": "0:00:42", "throughput": 1606.95, "total_tokens": 22649928}
8176
+ {"current_steps": 39885, "total_steps": 40000, "loss": 3.4504, "lr": 1.0375349860591853e-09, "epoch": 699.7433628318585, "percentage": 99.71, "elapsed_time": "3:54:56", "remaining_time": "0:00:40", "throughput": 1606.96, "total_tokens": 22652840}
8177
+ {"current_steps": 39890, "total_steps": 40000, "loss": 3.2756, "lr": 9.5002051290205e-10, "epoch": 699.8318584070796, "percentage": 99.72, "elapsed_time": "3:54:58", "remaining_time": "0:00:38", "throughput": 1606.94, "total_tokens": 22655384}
8178
+ {"current_steps": 39895, "total_steps": 40000, "loss": 3.9052, "lr": 8.663612074077954e-10, "epoch": 699.9203539823009, "percentage": 99.74, "elapsed_time": "3:55:00", "remaining_time": "0:00:37", "throughput": 1606.95, "total_tokens": 22658232}
8179
+ {"current_steps": 39900, "total_steps": 40000, "loss": 4.196, "lr": 7.865570824799884e-10, "epoch": 700.0, "percentage": 99.75, "elapsed_time": "3:55:01", "remaining_time": "0:00:35", "throughput": 1606.91, "total_tokens": 22660488}
8180
+ {"current_steps": 39905, "total_steps": 40000, "loss": 3.0424, "lr": 7.106081504254514e-10, "epoch": 700.0884955752213, "percentage": 99.76, "elapsed_time": "3:55:03", "remaining_time": "0:00:33", "throughput": 1606.88, "total_tokens": 22663336}
8181
+ {"current_steps": 39910, "total_steps": 40000, "loss": 3.5692, "lr": 6.385144229570372e-10, "epoch": 700.1769911504425, "percentage": 99.78, "elapsed_time": "3:55:05", "remaining_time": "0:00:31", "throughput": 1606.88, "total_tokens": 22666120}
8182
+ {"current_steps": 39915, "total_steps": 40000, "loss": 3.5741, "lr": 5.70275911190854e-10, "epoch": 700.2654867256637, "percentage": 99.79, "elapsed_time": "3:55:07", "remaining_time": "0:00:30", "throughput": 1606.86, "total_tokens": 22668648}
8183
+ {"current_steps": 39920, "total_steps": 40000, "loss": 3.6275, "lr": 5.058926256490403e-10, "epoch": 700.3539823008849, "percentage": 99.8, "elapsed_time": "3:55:09", "remaining_time": "0:00:28", "throughput": 1606.87, "total_tokens": 22671464}
8184
+ {"current_steps": 39925, "total_steps": 40000, "loss": 3.1527, "lr": 4.4536457626254134e-10, "epoch": 700.4424778761062, "percentage": 99.81, "elapsed_time": "3:55:10", "remaining_time": "0:00:26", "throughput": 1606.88, "total_tokens": 22674360}
8185
+ {"current_steps": 39930, "total_steps": 40000, "loss": 3.3957, "lr": 3.88691772365557e-10, "epoch": 700.5309734513274, "percentage": 99.83, "elapsed_time": "3:55:12", "remaining_time": "0:00:24", "throughput": 1606.9, "total_tokens": 22677432}
8186
+ {"current_steps": 39935, "total_steps": 40000, "loss": 3.5256, "lr": 3.358742226955425e-10, "epoch": 700.6194690265487, "percentage": 99.84, "elapsed_time": "3:55:14", "remaining_time": "0:00:22", "throughput": 1606.91, "total_tokens": 22680296}
8187
+ {"current_steps": 39940, "total_steps": 40000, "loss": 2.8995, "lr": 2.8691193539875925e-10, "epoch": 700.70796460177, "percentage": 99.85, "elapsed_time": "3:55:15", "remaining_time": "0:00:21", "throughput": 1606.92, "total_tokens": 22683304}
8188
+ {"current_steps": 39945, "total_steps": 40000, "loss": 3.4827, "lr": 2.418049180274995e-10, "epoch": 700.7964601769911, "percentage": 99.86, "elapsed_time": "3:55:17", "remaining_time": "0:00:19", "throughput": 1606.95, "total_tokens": 22686520}
8189
+ {"current_steps": 39950, "total_steps": 40000, "loss": 3.549, "lr": 2.005531775373104e-10, "epoch": 700.8849557522124, "percentage": 99.88, "elapsed_time": "3:55:19", "remaining_time": "0:00:17", "throughput": 1606.95, "total_tokens": 22689240}
8190
+ {"current_steps": 39955, "total_steps": 40000, "loss": 3.3329, "lr": 1.6315672028699435e-10, "epoch": 700.9734513274336, "percentage": 99.89, "elapsed_time": "3:55:21", "remaining_time": "0:00:15", "throughput": 1607.0, "total_tokens": 22692696}
8191
+ {"current_steps": 39960, "total_steps": 40000, "loss": 3.4901, "lr": 1.2961555204693555e-10, "epoch": 701.0530973451328, "percentage": 99.9, "elapsed_time": "3:55:23", "remaining_time": "0:00:14", "throughput": 1606.92, "total_tokens": 22694888}
8192
+ {"current_steps": 39965, "total_steps": 40000, "loss": 3.4907, "lr": 9.992967798799768e-11, "epoch": 701.141592920354, "percentage": 99.91, "elapsed_time": "3:55:24", "remaining_time": "0:00:12", "throughput": 1606.95, "total_tokens": 22698120}
8193
+ {"current_steps": 39970, "total_steps": 40000, "loss": 3.2959, "lr": 7.409910268707521e-11, "epoch": 701.2300884955753, "percentage": 99.92, "elapsed_time": "3:55:26", "remaining_time": "0:00:10", "throughput": 1606.96, "total_tokens": 22701000}
8194
+ {"current_steps": 39975, "total_steps": 40000, "loss": 3.6865, "lr": 5.212383012986877e-11, "epoch": 701.3185840707964, "percentage": 99.94, "elapsed_time": "3:55:28", "remaining_time": "0:00:08", "throughput": 1607.0, "total_tokens": 22704392}
8195
+ {"current_steps": 39980, "total_steps": 40000, "loss": 3.3385, "lr": 3.400386370533415e-11, "epoch": 701.4070796460177, "percentage": 99.95, "elapsed_time": "3:55:30", "remaining_time": "0:00:07", "throughput": 1606.99, "total_tokens": 22707096}
8196
+ {"current_steps": 39985, "total_steps": 40000, "loss": 3.5564, "lr": 1.9739206205682258e-11, "epoch": 701.4955752212389, "percentage": 99.96, "elapsed_time": "3:55:31", "remaining_time": "0:00:05", "throughput": 1607.02, "total_tokens": 22710184}
8197
+ {"current_steps": 39990, "total_steps": 40000, "loss": 3.3046, "lr": 9.329859829154685e-12, "epoch": 701.5840707964602, "percentage": 99.98, "elapsed_time": "3:55:33", "remaining_time": "0:00:03", "throughput": 1607.04, "total_tokens": 22713240}
8198
+ {"current_steps": 39995, "total_steps": 40000, "loss": 3.2232, "lr": 2.7758261855748148e-12, "epoch": 701.6725663716815, "percentage": 99.99, "elapsed_time": "3:55:35", "remaining_time": "0:00:01", "throughput": 1607.03, "total_tokens": 22715928}
8199
+ {"current_steps": 40000, "total_steps": 40000, "loss": 3.1903, "lr": 7.710628524559838e-14, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "3:55:37", "remaining_time": "0:00:00", "throughput": 1607.0, "total_tokens": 22718312}
8200
+ {"current_steps": 40000, "total_steps": 40000, "eval_loss": 3.2396206855773926, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "3:55:38", "remaining_time": "0:00:00", "throughput": 1606.88, "total_tokens": 22718312}
8201
+ {"current_steps": 40000, "total_steps": 40000, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "3:55:39", "remaining_time": "0:00:00", "throughput": 1606.67, "total_tokens": 22718312}