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": 15.5161, "lr": 3.2720109079037443e-09, "epoch": 1.273766084117534, "percentage": 99.49, "elapsed_time": "20:58:40", "remaining_time": "0:06:29", "throughput": 724.58, "total_tokens": 54720384}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 14.5777, "lr": 3.1151063006468193e-09, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "20:58:41", "remaining_time": "0:06:19", "throughput": 724.66, "total_tokens": 54727600}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 15.15965461730957, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "21:03:56", "remaining_time": "0:06:21", "throughput": 721.65, "total_tokens": 54727600}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 15.5161, "lr": 3.2720109079037443e-09, "epoch": 1.273766084117534, "percentage": 99.49, "elapsed_time": "20:58:40", "remaining_time": "0:06:29", "throughput": 724.58, "total_tokens": 54720384}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 14.5777, "lr": 3.1151063006468193e-09, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "20:58:41", "remaining_time": "0:06:19", "throughput": 724.66, "total_tokens": 54727600}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 15.15965461730957, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "21:03:56", "remaining_time": "0:06:21", "throughput": 721.65, "total_tokens": 54727600}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 15.4644, "lr": 2.962056527169854e-09, "epoch": 1.274086166058511, "percentage": 99.51, "elapsed_time": "21:03:59", "remaining_time": "0:06:11", "throughput": 721.72, "total_tokens": 54734624}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 14.6175, "lr": 2.8128616110761898e-09, "epoch": 1.2742462070289995, "percentage": 99.52, "elapsed_time": "21:04:01", "remaining_time": "0:06:01", "throughput": 721.79, "total_tokens": 54741424}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 14.6334, "lr": 2.6675215753724223e-09, "epoch": 1.274406247999488, "percentage": 99.54, "elapsed_time": "21:04:02", "remaining_time": "0:05:52", "throughput": 721.86, "total_tokens": 54747760}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 16.0126, "lr": 2.5260364424739557e-09, "epoch": 1.2745662889699763, "percentage": 99.55, "elapsed_time": "21:04:04", "remaining_time": "0:05:42", "throughput": 721.94, "total_tokens": 54754880}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 16.4225, "lr": 2.3884062341994475e-09, "epoch": 1.2747263299404648, "percentage": 99.56, "elapsed_time": "21:04:06", "remaining_time": "0:05:33", "throughput": 722.01, "total_tokens": 54761840}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 14.7111, "lr": 2.25463097177081e-09, "epoch": 1.2748863709109532, "percentage": 99.58, "elapsed_time": "21:04:07", "remaining_time": "0:05:23", "throughput": 722.09, "total_tokens": 54768896}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 15.5967, "lr": 2.1247106758215397e-09, "epoch": 1.2750464118814415, "percentage": 99.59, "elapsed_time": "21:04:09", "remaining_time": "0:05:14", "throughput": 722.17, "total_tokens": 54775792}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 13.8975, "lr": 1.998645366382834e-09, "epoch": 1.27520645285193, "percentage": 99.6, "elapsed_time": "21:04:10", "remaining_time": "0:05:04", "throughput": 722.25, "total_tokens": 54783008}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 14.9323, "lr": 1.876435062897475e-09, "epoch": 1.2753664938224185, "percentage": 99.61, "elapsed_time": "21:04:12", "remaining_time": "0:04:55", "throughput": 722.33, "total_tokens": 54790336}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 15.6722, "lr": 1.758079784211497e-09, "epoch": 1.275526534792907, "percentage": 99.62, "elapsed_time": "21:04:14", "remaining_time": "0:04:45", "throughput": 722.4, "total_tokens": 54797264}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 14.0519, "lr": 1.6435795485797434e-09, "epoch": 1.2756865757633955, "percentage": 99.64, "elapsed_time": "21:04:15", "remaining_time": "0:04:35", "throughput": 722.47, "total_tokens": 54803952}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 15.1032, "lr": 1.5329343736547596e-09, "epoch": 1.275846616733884, "percentage": 99.65, "elapsed_time": "21:04:17", "remaining_time": "0:04:26", "throughput": 722.55, "total_tokens": 54810688}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 13.3863, "lr": 1.4261442765006739e-09, "epoch": 1.2760066577043723, "percentage": 99.66, "elapsed_time": "21:04:19", "remaining_time": "0:04:16", "throughput": 722.62, "total_tokens": 54817216}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 15.0804, "lr": 1.3232092735876445e-09, "epoch": 1.2761666986748608, "percentage": 99.67, "elapsed_time": "21:04:20", "remaining_time": "0:04:07", "throughput": 722.7, "total_tokens": 54824416}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 13.3413, "lr": 1.2241293807918607e-09, "epoch": 1.2763267396453493, "percentage": 99.69, "elapsed_time": "21:04:22", "remaining_time": "0:03:57", "throughput": 722.78, "total_tokens": 54831648}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 14.8093, "lr": 1.128904613387216e-09, "epoch": 1.2764867806158375, "percentage": 99.7, "elapsed_time": "21:04:23", "remaining_time": "0:03:48", "throughput": 722.86, "total_tokens": 54839168}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 16.1877, "lr": 1.0375349860591853e-09, "epoch": 1.276646821586326, "percentage": 99.71, "elapsed_time": "21:04:25", "remaining_time": "0:03:38", "throughput": 722.94, "total_tokens": 54845904}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 14.8408, "lr": 9.5002051290205e-10, "epoch": 1.2768068625568145, "percentage": 99.72, "elapsed_time": "21:04:27", "remaining_time": "0:03:29", "throughput": 723.01, "total_tokens": 54852784}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 15.2268, "lr": 8.663612074077954e-10, "epoch": 1.276966903527303, "percentage": 99.74, "elapsed_time": "21:04:28", "remaining_time": "0:03:19", "throughput": 723.08, "total_tokens": 54859440}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 14.3592, "lr": 7.865570824799884e-10, "epoch": 1.2771269444977915, "percentage": 99.75, "elapsed_time": "21:04:30", "remaining_time": "0:03:10", "throughput": 723.16, "total_tokens": 54866608}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 15.6708, "lr": 7.106081504254514e-10, "epoch": 1.27728698546828, "percentage": 99.76, "elapsed_time": "21:04:32", "remaining_time": "0:03:00", "throughput": 723.23, "total_tokens": 54873104}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 15.1862, "lr": 6.385144229570372e-10, "epoch": 1.2774470264387683, "percentage": 99.78, "elapsed_time": "21:04:33", "remaining_time": "0:02:51", "throughput": 723.3, "total_tokens": 54879648}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 14.0016, "lr": 5.70275911190854e-10, "epoch": 1.2776070674092568, "percentage": 99.79, "elapsed_time": "21:04:35", "remaining_time": "0:02:41", "throughput": 723.38, "total_tokens": 54886688}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 15.637, "lr": 5.058926256490403e-10, "epoch": 1.2777671083797453, "percentage": 99.8, "elapsed_time": "21:04:36", "remaining_time": "0:02:32", "throughput": 723.45, "total_tokens": 54893328}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 13.4268, "lr": 4.4536457626254134e-10, "epoch": 1.2779271493502335, "percentage": 99.81, "elapsed_time": "21:04:38", "remaining_time": "0:02:22", "throughput": 723.52, "total_tokens": 54899984}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 15.1463, "lr": 3.88691772365557e-10, "epoch": 1.278087190320722, "percentage": 99.83, "elapsed_time": "21:04:40", "remaining_time": "0:02:13", "throughput": 723.6, "total_tokens": 54906832}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 14.6905, "lr": 3.358742226955425e-10, "epoch": 1.2782472312912105, "percentage": 99.84, "elapsed_time": "21:04:41", "remaining_time": "0:02:03", "throughput": 723.67, "total_tokens": 54913632}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 16.8609, "lr": 2.8691193539875925e-10, "epoch": 1.278407272261699, "percentage": 99.85, "elapsed_time": "21:04:43", "remaining_time": "0:01:53", "throughput": 723.75, "total_tokens": 54920528}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 15.9361, "lr": 2.418049180274995e-10, "epoch": 1.2785673132321875, "percentage": 99.86, "elapsed_time": "21:04:45", "remaining_time": "0:01:44", "throughput": 723.83, "total_tokens": 54927584}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 16.1678, "lr": 2.005531775373104e-10, "epoch": 1.2787273542026758, "percentage": 99.88, "elapsed_time": "21:04:46", "remaining_time": "0:01:34", "throughput": 723.9, "total_tokens": 54934240}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 16.6017, "lr": 1.6315672028699435e-10, "epoch": 1.2788873951731643, "percentage": 99.89, "elapsed_time": "21:04:48", "remaining_time": "0:01:25", "throughput": 723.97, "total_tokens": 54941232}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 16.7286, "lr": 1.2961555204693555e-10, "epoch": 1.2790474361436528, "percentage": 99.9, "elapsed_time": "21:04:49", "remaining_time": "0:01:15", "throughput": 724.05, "total_tokens": 54947808}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 15.2419, "lr": 9.992967798799768e-11, "epoch": 1.2792074771141413, "percentage": 99.91, "elapsed_time": "21:04:51", "remaining_time": "0:01:06", "throughput": 724.12, "total_tokens": 54954704}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 16.0448, "lr": 7.409910268707521e-11, "epoch": 1.2793675180846296, "percentage": 99.92, "elapsed_time": "21:04:53", "remaining_time": "0:00:56", "throughput": 724.2, "total_tokens": 54961680}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 12.645, "lr": 5.212383012986877e-11, "epoch": 1.279527559055118, "percentage": 99.94, "elapsed_time": "21:04:54", "remaining_time": "0:00:47", "throughput": 724.27, "total_tokens": 54968656}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 14.6829, "lr": 3.400386370533415e-11, "epoch": 1.2796876000256066, "percentage": 99.95, "elapsed_time": "21:04:56", "remaining_time": "0:00:37", "throughput": 724.35, "total_tokens": 54975280}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 14.6238, "lr": 1.9739206205682258e-11, "epoch": 1.279847640996095, "percentage": 99.96, "elapsed_time": "21:04:58", "remaining_time": "0:00:28", "throughput": 724.42, "total_tokens": 54982032}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 16.5385, "lr": 9.329859829154685e-12, "epoch": 1.2800076819665835, "percentage": 99.98, "elapsed_time": "21:04:59", "remaining_time": "0:00:18", "throughput": 724.49, "total_tokens": 54988688}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 13.4798, "lr": 2.7758261855748148e-12, "epoch": 1.2801677229370718, "percentage": 99.99, "elapsed_time": "21:05:01", "remaining_time": "0:00:09", "throughput": 724.56, "total_tokens": 54995344}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 16.7093, "lr": 7.710628524559838e-14, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "21:05:02", "remaining_time": "0:00:00", "throughput": 724.64, "total_tokens": 55002224}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 15.15965461730957, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "21:10:17", "remaining_time": "0:00:00", "throughput": 721.65, "total_tokens": 55002224}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "21:10:19", "remaining_time": "0:00:00", "throughput": 721.63, "total_tokens": 55002224}
|