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": 0.2682, "lr": 3.2720109079037443e-09, "epoch": 442.1666666666667, "percentage": 99.49, "elapsed_time": "3:04:44", "remaining_time": "0:00:57", "throughput": 961.94, "total_tokens": 10662480}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.2206, "lr": 3.1151063006468193e-09, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "3:04:45", "remaining_time": "0:00:55", "throughput": 961.95, "total_tokens": 10663840}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.24173478782176971, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "3:04:46", "remaining_time": "0:00:55", "throughput": 961.86, "total_tokens": 10663840}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.2682, "lr": 3.2720109079037443e-09, "epoch": 442.1666666666667, "percentage": 99.49, "elapsed_time": "3:04:44", "remaining_time": "0:00:57", "throughput": 961.94, "total_tokens": 10662480}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.2206, "lr": 3.1151063006468193e-09, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "3:04:45", "remaining_time": "0:00:55", "throughput": 961.95, "total_tokens": 10663840}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.24173478782176971, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "3:04:46", "remaining_time": "0:00:55", "throughput": 961.86, "total_tokens": 10663840}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.2883, "lr": 2.962056527169854e-09, "epoch": 442.27777777777777, "percentage": 99.51, "elapsed_time": "3:04:49", "remaining_time": "0:00:54", "throughput": 961.77, "total_tokens": 10665136}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.2407, "lr": 2.8128616110761898e-09, "epoch": 442.3333333333333, "percentage": 99.52, "elapsed_time": "3:04:50", "remaining_time": "0:00:52", "throughput": 961.78, "total_tokens": 10666480}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.1666, "lr": 2.6675215753724223e-09, "epoch": 442.3888888888889, "percentage": 99.54, "elapsed_time": "3:04:51", "remaining_time": "0:00:51", "throughput": 961.79, "total_tokens": 10667840}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.2852, "lr": 2.5260364424739557e-09, "epoch": 442.44444444444446, "percentage": 99.55, "elapsed_time": "3:04:52", "remaining_time": "0:00:50", "throughput": 961.8, "total_tokens": 10669184}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.1558, "lr": 2.3884062341994475e-09, "epoch": 442.5, "percentage": 99.56, "elapsed_time": "3:04:54", "remaining_time": "0:00:48", "throughput": 961.8, "total_tokens": 10670496}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.2358, "lr": 2.25463097177081e-09, "epoch": 442.55555555555554, "percentage": 99.58, "elapsed_time": "3:04:55", "remaining_time": "0:00:47", "throughput": 961.81, "total_tokens": 10671776}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.1655, "lr": 2.1247106758215397e-09, "epoch": 442.6111111111111, "percentage": 99.59, "elapsed_time": "3:04:56", "remaining_time": "0:00:45", "throughput": 961.81, "total_tokens": 10673120}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.2041, "lr": 1.998645366382834e-09, "epoch": 442.6666666666667, "percentage": 99.6, "elapsed_time": "3:04:58", "remaining_time": "0:00:44", "throughput": 961.82, "total_tokens": 10674480}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.2796, "lr": 1.876435062897475e-09, "epoch": 442.72222222222223, "percentage": 99.61, "elapsed_time": "3:04:59", "remaining_time": "0:00:43", "throughput": 961.83, "total_tokens": 10675808}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.2779, "lr": 1.758079784211497e-09, "epoch": 442.77777777777777, "percentage": 99.62, "elapsed_time": "3:05:00", "remaining_time": "0:00:41", "throughput": 961.83, "total_tokens": 10677120}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.3313, "lr": 1.6435795485797434e-09, "epoch": 442.8333333333333, "percentage": 99.64, "elapsed_time": "3:05:02", "remaining_time": "0:00:40", "throughput": 961.84, "total_tokens": 10678448}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.2443, "lr": 1.5329343736547596e-09, "epoch": 442.8888888888889, "percentage": 99.65, "elapsed_time": "3:05:03", "remaining_time": "0:00:38", "throughput": 961.85, "total_tokens": 10679840}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.1738, "lr": 1.4261442765006739e-09, "epoch": 442.94444444444446, "percentage": 99.66, "elapsed_time": "3:05:04", "remaining_time": "0:00:37", "throughput": 961.86, "total_tokens": 10681216}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.3165, "lr": 1.3232092735876445e-09, "epoch": 443.0, "percentage": 99.67, "elapsed_time": "3:05:06", "remaining_time": "0:00:36", "throughput": 961.86, "total_tokens": 10682624}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.2619, "lr": 1.2241293807918607e-09, "epoch": 443.05555555555554, "percentage": 99.69, "elapsed_time": "3:05:07", "remaining_time": "0:00:34", "throughput": 961.84, "total_tokens": 10683920}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.2807, "lr": 1.128904613387216e-09, "epoch": 443.1111111111111, "percentage": 99.7, "elapsed_time": "3:05:09", "remaining_time": "0:00:33", "throughput": 961.85, "total_tokens": 10685216}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.2018, "lr": 1.0375349860591853e-09, "epoch": 443.1666666666667, "percentage": 99.71, "elapsed_time": "3:05:10", "remaining_time": "0:00:32", "throughput": 961.86, "total_tokens": 10686576}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.2265, "lr": 9.5002051290205e-10, "epoch": 443.22222222222223, "percentage": 99.72, "elapsed_time": "3:05:11", "remaining_time": "0:00:30", "throughput": 961.87, "total_tokens": 10687936}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.196, "lr": 8.663612074077954e-10, "epoch": 443.27777777777777, "percentage": 99.74, "elapsed_time": "3:05:12", "remaining_time": "0:00:29", "throughput": 961.87, "total_tokens": 10689280}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.2889, "lr": 7.865570824799884e-10, "epoch": 443.3333333333333, "percentage": 99.75, "elapsed_time": "3:05:14", "remaining_time": "0:00:27", "throughput": 961.88, "total_tokens": 10690656}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.2141, "lr": 7.106081504254514e-10, "epoch": 443.3888888888889, "percentage": 99.76, "elapsed_time": "3:05:15", "remaining_time": "0:00:26", "throughput": 961.89, "total_tokens": 10691984}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.1348, "lr": 6.385144229570372e-10, "epoch": 443.44444444444446, "percentage": 99.78, "elapsed_time": "3:05:16", "remaining_time": "0:00:25", "throughput": 961.9, "total_tokens": 10693360}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.2768, "lr": 5.70275911190854e-10, "epoch": 443.5, "percentage": 99.79, "elapsed_time": "3:05:18", "remaining_time": "0:00:23", "throughput": 961.91, "total_tokens": 10694672}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.2011, "lr": 5.058926256490403e-10, "epoch": 443.55555555555554, "percentage": 99.8, "elapsed_time": "3:05:19", "remaining_time": "0:00:22", "throughput": 961.91, "total_tokens": 10695984}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.1896, "lr": 4.4536457626254134e-10, "epoch": 443.6111111111111, "percentage": 99.81, "elapsed_time": "3:05:20", "remaining_time": "0:00:20", "throughput": 961.92, "total_tokens": 10697360}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.3572, "lr": 3.88691772365557e-10, "epoch": 443.6666666666667, "percentage": 99.83, "elapsed_time": "3:05:22", "remaining_time": "0:00:19", "throughput": 961.93, "total_tokens": 10698688}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.2174, "lr": 3.358742226955425e-10, "epoch": 443.72222222222223, "percentage": 99.84, "elapsed_time": "3:05:23", "remaining_time": "0:00:18", "throughput": 961.94, "total_tokens": 10700048}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.2199, "lr": 2.8691193539875925e-10, "epoch": 443.77777777777777, "percentage": 99.85, "elapsed_time": "3:05:24", "remaining_time": "0:00:16", "throughput": 961.94, "total_tokens": 10701392}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.1866, "lr": 2.418049180274995e-10, "epoch": 443.8333333333333, "percentage": 99.86, "elapsed_time": "3:05:26", "remaining_time": "0:00:15", "throughput": 961.95, "total_tokens": 10702704}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.2783, "lr": 2.005531775373104e-10, "epoch": 443.8888888888889, "percentage": 99.88, "elapsed_time": "3:05:27", "remaining_time": "0:00:13", "throughput": 961.96, "total_tokens": 10704048}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.3541, "lr": 1.6315672028699435e-10, "epoch": 443.94444444444446, "percentage": 99.89, "elapsed_time": "3:05:28", "remaining_time": "0:00:12", "throughput": 961.97, "total_tokens": 10705408}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.2852, "lr": 1.2961555204693555e-10, "epoch": 444.0, "percentage": 99.9, "elapsed_time": "3:05:30", "remaining_time": "0:00:11", "throughput": 961.96, "total_tokens": 10706768}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.1936, "lr": 9.992967798799768e-11, "epoch": 444.05555555555554, "percentage": 99.91, "elapsed_time": "3:05:31", "remaining_time": "0:00:09", "throughput": 961.94, "total_tokens": 10708096}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.1815, "lr": 7.409910268707521e-11, "epoch": 444.1111111111111, "percentage": 99.92, "elapsed_time": "3:05:33", "remaining_time": "0:00:08", "throughput": 961.95, "total_tokens": 10709424}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.1466, "lr": 5.212383012986877e-11, "epoch": 444.1666666666667, "percentage": 99.94, "elapsed_time": "3:05:34", "remaining_time": "0:00:06", "throughput": 961.96, "total_tokens": 10710768}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.3258, "lr": 3.400386370533415e-11, "epoch": 444.22222222222223, "percentage": 99.95, "elapsed_time": "3:05:35", "remaining_time": "0:00:05", "throughput": 961.97, "total_tokens": 10712128}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.2089, "lr": 1.9739206205682258e-11, "epoch": 444.27777777777777, "percentage": 99.96, "elapsed_time": "3:05:36", "remaining_time": "0:00:04", "throughput": 961.97, "total_tokens": 10713472}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.2581, "lr": 9.329859829154685e-12, "epoch": 444.3333333333333, "percentage": 99.98, "elapsed_time": "3:05:38", "remaining_time": "0:00:02", "throughput": 961.98, "total_tokens": 10714816}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.2285, "lr": 2.7758261855748148e-12, "epoch": 444.3888888888889, "percentage": 99.99, "elapsed_time": "3:05:39", "remaining_time": "0:00:01", "throughput": 961.98, "total_tokens": 10716112}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.269, "lr": 7.710628524559838e-14, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "3:05:40", "remaining_time": "0:00:00", "throughput": 961.99, "total_tokens": 10717440}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.24173478782176971, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "3:05:41", "remaining_time": "0:00:00", "throughput": 961.9, "total_tokens": 10717440}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "3:05:42", "remaining_time": "0:00:00", "throughput": 961.81, "total_tokens": 10717440}
|