Training in progress, step 40000
Browse files- trainer_log.jsonl +42 -0
trainer_log.jsonl
CHANGED
|
@@ -8157,3 +8157,45 @@
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.1317, "lr": 3.2720109079037443e-09, "epoch": 82.73388773388774, "percentage": 99.49, "elapsed_time": "8:11:14", "remaining_time": "0:02:31", "throughput": 1054.92, "total_tokens": 31093384}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.106, "lr": 3.1151063006468193e-09, "epoch": 82.74428274428274, "percentage": 99.5, "elapsed_time": "8:11:18", "remaining_time": "0:02:28", "throughput": 1054.93, "total_tokens": 31097352}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.13433800637722015, "epoch": 82.74428274428274, "percentage": 99.5, "elapsed_time": "8:11:28", "remaining_time": "0:02:28", "throughput": 1054.57, "total_tokens": 31097352}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.1317, "lr": 3.2720109079037443e-09, "epoch": 82.73388773388774, "percentage": 99.49, "elapsed_time": "8:11:14", "remaining_time": "0:02:31", "throughput": 1054.92, "total_tokens": 31093384}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.106, "lr": 3.1151063006468193e-09, "epoch": 82.74428274428274, "percentage": 99.5, "elapsed_time": "8:11:18", "remaining_time": "0:02:28", "throughput": 1054.93, "total_tokens": 31097352}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.13433800637722015, "epoch": 82.74428274428274, "percentage": 99.5, "elapsed_time": "8:11:28", "remaining_time": "0:02:28", "throughput": 1054.57, "total_tokens": 31097352}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.1492, "lr": 2.962056527169854e-09, "epoch": 82.75467775467776, "percentage": 99.51, "elapsed_time": "8:11:33", "remaining_time": "0:02:24", "throughput": 1054.52, "total_tokens": 31101288}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.1066, "lr": 2.8128616110761898e-09, "epoch": 82.76507276507276, "percentage": 99.52, "elapsed_time": "8:11:36", "remaining_time": "0:02:20", "throughput": 1054.53, "total_tokens": 31105096}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0944, "lr": 2.6675215753724223e-09, "epoch": 82.77546777546777, "percentage": 99.54, "elapsed_time": "8:11:39", "remaining_time": "0:02:17", "throughput": 1054.54, "total_tokens": 31108872}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.116, "lr": 2.5260364424739557e-09, "epoch": 82.78586278586279, "percentage": 99.55, "elapsed_time": "8:11:43", "remaining_time": "0:02:13", "throughput": 1054.55, "total_tokens": 31112744}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.1029, "lr": 2.3884062341994475e-09, "epoch": 82.79625779625779, "percentage": 99.56, "elapsed_time": "8:11:46", "remaining_time": "0:02:09", "throughput": 1054.56, "total_tokens": 31116712}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.1167, "lr": 2.25463097177081e-09, "epoch": 82.8066528066528, "percentage": 99.58, "elapsed_time": "8:11:50", "remaining_time": "0:02:05", "throughput": 1054.57, "total_tokens": 31120648}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.1264, "lr": 2.1247106758215397e-09, "epoch": 82.81704781704782, "percentage": 99.59, "elapsed_time": "8:11:53", "remaining_time": "0:02:02", "throughput": 1054.59, "total_tokens": 31124648}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.1142, "lr": 1.998645366382834e-09, "epoch": 82.82744282744282, "percentage": 99.6, "elapsed_time": "8:11:56", "remaining_time": "0:01:58", "throughput": 1054.6, "total_tokens": 31128584}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.1283, "lr": 1.876435062897475e-09, "epoch": 82.83783783783784, "percentage": 99.61, "elapsed_time": "8:12:00", "remaining_time": "0:01:54", "throughput": 1054.62, "total_tokens": 31132680}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0929, "lr": 1.758079784211497e-09, "epoch": 82.84823284823285, "percentage": 99.62, "elapsed_time": "8:12:03", "remaining_time": "0:01:51", "throughput": 1054.63, "total_tokens": 31136584}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.1044, "lr": 1.6435795485797434e-09, "epoch": 82.85862785862786, "percentage": 99.64, "elapsed_time": "8:12:07", "remaining_time": "0:01:47", "throughput": 1054.63, "total_tokens": 31140392}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.1051, "lr": 1.5329343736547596e-09, "epoch": 82.86902286902287, "percentage": 99.65, "elapsed_time": "8:12:10", "remaining_time": "0:01:43", "throughput": 1054.65, "total_tokens": 31144360}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.1284, "lr": 1.4261442765006739e-09, "epoch": 82.87941787941789, "percentage": 99.66, "elapsed_time": "8:12:13", "remaining_time": "0:01:40", "throughput": 1054.66, "total_tokens": 31148264}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.1016, "lr": 1.3232092735876445e-09, "epoch": 82.88981288981289, "percentage": 99.67, "elapsed_time": "8:12:17", "remaining_time": "0:01:36", "throughput": 1054.66, "total_tokens": 31152008}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.1047, "lr": 1.2241293807918607e-09, "epoch": 82.9002079002079, "percentage": 99.69, "elapsed_time": "8:12:20", "remaining_time": "0:01:32", "throughput": 1054.67, "total_tokens": 31155816}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.1053, "lr": 1.128904613387216e-09, "epoch": 82.9106029106029, "percentage": 99.7, "elapsed_time": "8:12:24", "remaining_time": "0:01:28", "throughput": 1054.68, "total_tokens": 31159592}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.1402, "lr": 1.0375349860591853e-09, "epoch": 82.92099792099792, "percentage": 99.71, "elapsed_time": "8:12:27", "remaining_time": "0:01:25", "throughput": 1054.69, "total_tokens": 31163528}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.1594, "lr": 9.5002051290205e-10, "epoch": 82.93139293139293, "percentage": 99.72, "elapsed_time": "8:12:30", "remaining_time": "0:01:21", "throughput": 1054.7, "total_tokens": 31167464}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.1356, "lr": 8.663612074077954e-10, "epoch": 82.94178794178794, "percentage": 99.74, "elapsed_time": "8:12:34", "remaining_time": "0:01:17", "throughput": 1054.72, "total_tokens": 31171496}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.114, "lr": 7.865570824799884e-10, "epoch": 82.95218295218295, "percentage": 99.75, "elapsed_time": "8:12:37", "remaining_time": "0:01:14", "throughput": 1054.72, "total_tokens": 31175272}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.105, "lr": 7.106081504254514e-10, "epoch": 82.96257796257797, "percentage": 99.76, "elapsed_time": "8:12:41", "remaining_time": "0:01:10", "throughput": 1054.73, "total_tokens": 31178952}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0934, "lr": 6.385144229570372e-10, "epoch": 82.97297297297297, "percentage": 99.78, "elapsed_time": "8:12:44", "remaining_time": "0:01:06", "throughput": 1054.74, "total_tokens": 31182952}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.1007, "lr": 5.70275911190854e-10, "epoch": 82.98336798336798, "percentage": 99.79, "elapsed_time": "8:12:47", "remaining_time": "0:01:02", "throughput": 1054.75, "total_tokens": 31186888}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0926, "lr": 5.058926256490403e-10, "epoch": 82.993762993763, "percentage": 99.8, "elapsed_time": "8:12:51", "remaining_time": "0:00:59", "throughput": 1054.76, "total_tokens": 31190792}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0995, "lr": 4.4536457626254134e-10, "epoch": 83.004158004158, "percentage": 99.81, "elapsed_time": "8:12:55", "remaining_time": "0:00:55", "throughput": 1054.76, "total_tokens": 31194744}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.105, "lr": 3.88691772365557e-10, "epoch": 83.01455301455302, "percentage": 99.83, "elapsed_time": "8:12:58", "remaining_time": "0:00:51", "throughput": 1054.77, "total_tokens": 31198648}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.1412, "lr": 3.358742226955425e-10, "epoch": 83.02494802494803, "percentage": 99.84, "elapsed_time": "8:13:02", "remaining_time": "0:00:48", "throughput": 1054.78, "total_tokens": 31202584}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.1164, "lr": 2.8691193539875925e-10, "epoch": 83.03534303534303, "percentage": 99.85, "elapsed_time": "8:13:05", "remaining_time": "0:00:44", "throughput": 1054.79, "total_tokens": 31206360}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0978, "lr": 2.418049180274995e-10, "epoch": 83.04573804573805, "percentage": 99.86, "elapsed_time": "8:13:08", "remaining_time": "0:00:40", "throughput": 1054.8, "total_tokens": 31210296}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0986, "lr": 2.005531775373104e-10, "epoch": 83.05613305613305, "percentage": 99.88, "elapsed_time": "8:13:12", "remaining_time": "0:00:37", "throughput": 1054.81, "total_tokens": 31214136}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.1086, "lr": 1.6315672028699435e-10, "epoch": 83.06652806652806, "percentage": 99.89, "elapsed_time": "8:13:15", "remaining_time": "0:00:33", "throughput": 1054.81, "total_tokens": 31217912}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.088, "lr": 1.2961555204693555e-10, "epoch": 83.07692307692308, "percentage": 99.9, "elapsed_time": "8:13:19", "remaining_time": "0:00:29", "throughput": 1054.83, "total_tokens": 31221848}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.1501, "lr": 9.992967798799768e-11, "epoch": 83.08731808731808, "percentage": 99.91, "elapsed_time": "8:13:22", "remaining_time": "0:00:25", "throughput": 1054.83, "total_tokens": 31225688}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.1108, "lr": 7.409910268707521e-11, "epoch": 83.0977130977131, "percentage": 99.92, "elapsed_time": "8:13:25", "remaining_time": "0:00:22", "throughput": 1054.85, "total_tokens": 31229688}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0968, "lr": 5.212383012986877e-11, "epoch": 83.10810810810811, "percentage": 99.94, "elapsed_time": "8:13:29", "remaining_time": "0:00:18", "throughput": 1054.86, "total_tokens": 31233624}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.1272, "lr": 3.400386370533415e-11, "epoch": 83.11850311850311, "percentage": 99.95, "elapsed_time": "8:13:32", "remaining_time": "0:00:14", "throughput": 1054.87, "total_tokens": 31237624}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.1246, "lr": 1.9739206205682258e-11, "epoch": 83.12889812889813, "percentage": 99.96, "elapsed_time": "8:13:36", "remaining_time": "0:00:11", "throughput": 1054.89, "total_tokens": 31241560}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.1328, "lr": 9.329859829154685e-12, "epoch": 83.13929313929314, "percentage": 99.98, "elapsed_time": "8:13:39", "remaining_time": "0:00:07", "throughput": 1054.9, "total_tokens": 31245464}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.1307, "lr": 2.7758261855748148e-12, "epoch": 83.14968814968815, "percentage": 99.99, "elapsed_time": "8:13:42", "remaining_time": "0:00:03", "throughput": 1054.91, "total_tokens": 31249336}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.1271, "lr": 7.710628524559838e-14, "epoch": 83.16008316008316, "percentage": 100.0, "elapsed_time": "8:13:46", "remaining_time": "0:00:00", "throughput": 1054.92, "total_tokens": 31253176}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.13433800637722015, "epoch": 83.16008316008316, "percentage": 100.0, "elapsed_time": "8:13:56", "remaining_time": "0:00:00", "throughput": 1054.56, "total_tokens": 31253176}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 83.16008316008316, "percentage": 100.0, "elapsed_time": "8:13:57", "remaining_time": "0:00:00", "throughput": 1054.5, "total_tokens": 31253176}
|