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": 0.167, "lr": 3.2720109079037443e-09, "epoch": 318.3614457831325, "percentage": 99.49, "elapsed_time": "3:58:54", "remaining_time": "0:01:13", "throughput": 972.07, "total_tokens": 13934048}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.1667, "lr": 3.1151063006468193e-09, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "3:58:56", "remaining_time": "0:01:12", "throughput": 972.07, "total_tokens": 13935776}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.5859531760215759, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "3:58:57", "remaining_time": "0:01:12", "throughput": 971.96, "total_tokens": 13935776}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.167, "lr": 3.2720109079037443e-09, "epoch": 318.3614457831325, "percentage": 99.49, "elapsed_time": "3:58:54", "remaining_time": "0:01:13", "throughput": 972.07, "total_tokens": 13934048}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.1667, "lr": 3.1151063006468193e-09, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "3:58:56", "remaining_time": "0:01:12", "throughput": 972.07, "total_tokens": 13935776}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.5859531760215759, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "3:58:57", "remaining_time": "0:01:12", "throughput": 971.96, "total_tokens": 13935776}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.1382, "lr": 2.962056527169854e-09, "epoch": 318.44176706827307, "percentage": 99.51, "elapsed_time": "3:59:01", "remaining_time": "0:01:10", "throughput": 971.85, "total_tokens": 13937280}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.1517, "lr": 2.8128616110761898e-09, "epoch": 318.48192771084337, "percentage": 99.52, "elapsed_time": "3:59:02", "remaining_time": "0:01:08", "throughput": 971.86, "total_tokens": 13939088}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.1625, "lr": 2.6675215753724223e-09, "epoch": 318.52208835341366, "percentage": 99.54, "elapsed_time": "3:59:04", "remaining_time": "0:01:06", "throughput": 971.86, "total_tokens": 13940800}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.1481, "lr": 2.5260364424739557e-09, "epoch": 318.56224899598396, "percentage": 99.55, "elapsed_time": "3:59:06", "remaining_time": "0:01:04", "throughput": 971.86, "total_tokens": 13942400}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.1946, "lr": 2.3884062341994475e-09, "epoch": 318.6024096385542, "percentage": 99.56, "elapsed_time": "3:59:07", "remaining_time": "0:01:03", "throughput": 971.88, "total_tokens": 13944464}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.2231, "lr": 2.25463097177081e-09, "epoch": 318.6425702811245, "percentage": 99.58, "elapsed_time": "3:59:09", "remaining_time": "0:01:01", "throughput": 971.89, "total_tokens": 13946160}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.1351, "lr": 2.1247106758215397e-09, "epoch": 318.6827309236948, "percentage": 99.59, "elapsed_time": "3:59:11", "remaining_time": "0:00:59", "throughput": 971.89, "total_tokens": 13947856}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.1801, "lr": 1.998645366382834e-09, "epoch": 318.72289156626505, "percentage": 99.6, "elapsed_time": "3:59:12", "remaining_time": "0:00:57", "throughput": 971.89, "total_tokens": 13949488}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.2099, "lr": 1.876435062897475e-09, "epoch": 318.76305220883535, "percentage": 99.61, "elapsed_time": "3:59:14", "remaining_time": "0:00:55", "throughput": 971.89, "total_tokens": 13951120}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.1703, "lr": 1.758079784211497e-09, "epoch": 318.80321285140565, "percentage": 99.62, "elapsed_time": "3:59:16", "remaining_time": "0:00:54", "throughput": 971.88, "total_tokens": 13952656}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.184, "lr": 1.6435795485797434e-09, "epoch": 318.8433734939759, "percentage": 99.64, "elapsed_time": "3:59:18", "remaining_time": "0:00:52", "throughput": 971.88, "total_tokens": 13954400}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.1294, "lr": 1.5329343736547596e-09, "epoch": 318.8835341365462, "percentage": 99.65, "elapsed_time": "3:59:19", "remaining_time": "0:00:50", "throughput": 971.89, "total_tokens": 13956224}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.1859, "lr": 1.4261442765006739e-09, "epoch": 318.9236947791165, "percentage": 99.66, "elapsed_time": "3:59:21", "remaining_time": "0:00:48", "throughput": 971.9, "total_tokens": 13957920}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.1565, "lr": 1.3232092735876445e-09, "epoch": 318.96385542168673, "percentage": 99.67, "elapsed_time": "3:59:23", "remaining_time": "0:00:46", "throughput": 971.91, "total_tokens": 13959792}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.1575, "lr": 1.2241293807918607e-09, "epoch": 319.0, "percentage": 99.69, "elapsed_time": "3:59:24", "remaining_time": "0:00:45", "throughput": 971.9, "total_tokens": 13961344}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.114, "lr": 1.128904613387216e-09, "epoch": 319.0401606425703, "percentage": 99.7, "elapsed_time": "3:59:26", "remaining_time": "0:00:43", "throughput": 971.9, "total_tokens": 13963136}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.1629, "lr": 1.0375349860591853e-09, "epoch": 319.08032128514054, "percentage": 99.71, "elapsed_time": "3:59:28", "remaining_time": "0:00:41", "throughput": 971.91, "total_tokens": 13964976}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.1816, "lr": 9.5002051290205e-10, "epoch": 319.12048192771084, "percentage": 99.72, "elapsed_time": "3:59:30", "remaining_time": "0:00:39", "throughput": 971.91, "total_tokens": 13966656}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.1672, "lr": 8.663612074077954e-10, "epoch": 319.16064257028114, "percentage": 99.74, "elapsed_time": "3:59:32", "remaining_time": "0:00:37", "throughput": 971.9, "total_tokens": 13968192}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.1488, "lr": 7.865570824799884e-10, "epoch": 319.2008032128514, "percentage": 99.75, "elapsed_time": "3:59:33", "remaining_time": "0:00:36", "throughput": 971.91, "total_tokens": 13969920}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.1622, "lr": 7.106081504254514e-10, "epoch": 319.2409638554217, "percentage": 99.76, "elapsed_time": "3:59:35", "remaining_time": "0:00:34", "throughput": 971.93, "total_tokens": 13971920}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.1838, "lr": 6.385144229570372e-10, "epoch": 319.281124497992, "percentage": 99.78, "elapsed_time": "3:59:37", "remaining_time": "0:00:32", "throughput": 971.93, "total_tokens": 13973584}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.1925, "lr": 5.70275911190854e-10, "epoch": 319.3212851405622, "percentage": 99.79, "elapsed_time": "3:59:38", "remaining_time": "0:00:30", "throughput": 971.94, "total_tokens": 13975360}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.1781, "lr": 5.058926256490403e-10, "epoch": 319.3614457831325, "percentage": 99.8, "elapsed_time": "3:59:40", "remaining_time": "0:00:28", "throughput": 971.94, "total_tokens": 13977072}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.1405, "lr": 4.4536457626254134e-10, "epoch": 319.4016064257028, "percentage": 99.81, "elapsed_time": "3:59:42", "remaining_time": "0:00:27", "throughput": 971.95, "total_tokens": 13978800}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.1176, "lr": 3.88691772365557e-10, "epoch": 319.44176706827307, "percentage": 99.83, "elapsed_time": "3:59:43", "remaining_time": "0:00:25", "throughput": 971.95, "total_tokens": 13980448}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.1405, "lr": 3.358742226955425e-10, "epoch": 319.48192771084337, "percentage": 99.84, "elapsed_time": "3:59:45", "remaining_time": "0:00:23", "throughput": 971.94, "total_tokens": 13982096}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.1812, "lr": 2.8691193539875925e-10, "epoch": 319.52208835341366, "percentage": 99.85, "elapsed_time": "3:59:47", "remaining_time": "0:00:21", "throughput": 971.96, "total_tokens": 13983952}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.1929, "lr": 2.418049180274995e-10, "epoch": 319.56224899598396, "percentage": 99.86, "elapsed_time": "3:59:49", "remaining_time": "0:00:19", "throughput": 971.97, "total_tokens": 13985808}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.1345, "lr": 2.005531775373104e-10, "epoch": 319.6024096385542, "percentage": 99.88, "elapsed_time": "3:59:50", "remaining_time": "0:00:18", "throughput": 971.97, "total_tokens": 13987504}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.1362, "lr": 1.6315672028699435e-10, "epoch": 319.6425702811245, "percentage": 99.89, "elapsed_time": "3:59:52", "remaining_time": "0:00:16", "throughput": 971.98, "total_tokens": 13989200}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.1693, "lr": 1.2961555204693555e-10, "epoch": 319.6827309236948, "percentage": 99.9, "elapsed_time": "3:59:54", "remaining_time": "0:00:14", "throughput": 971.99, "total_tokens": 13991088}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.1801, "lr": 9.992967798799768e-11, "epoch": 319.72289156626505, "percentage": 99.91, "elapsed_time": "3:59:55", "remaining_time": "0:00:12", "throughput": 972.02, "total_tokens": 13993184}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.1939, "lr": 7.409910268707521e-11, "epoch": 319.76305220883535, "percentage": 99.92, "elapsed_time": "3:59:57", "remaining_time": "0:00:10", "throughput": 972.02, "total_tokens": 13994800}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.1748, "lr": 5.212383012986877e-11, "epoch": 319.80321285140565, "percentage": 99.94, "elapsed_time": "3:59:59", "remaining_time": "0:00:09", "throughput": 972.03, "total_tokens": 13996688}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.129, "lr": 3.400386370533415e-11, "epoch": 319.8433734939759, "percentage": 99.95, "elapsed_time": "4:00:01", "remaining_time": "0:00:07", "throughput": 972.03, "total_tokens": 13998368}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.1684, "lr": 1.9739206205682258e-11, "epoch": 319.8835341365462, "percentage": 99.96, "elapsed_time": "4:00:02", "remaining_time": "0:00:05", "throughput": 972.04, "total_tokens": 14000176}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.1522, "lr": 9.329859829154685e-12, "epoch": 319.9236947791165, "percentage": 99.98, "elapsed_time": "4:00:04", "remaining_time": "0:00:03", "throughput": 972.04, "total_tokens": 14001856}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.2182, "lr": 2.7758261855748148e-12, "epoch": 319.96385542168673, "percentage": 99.99, "elapsed_time": "4:00:06", "remaining_time": "0:00:01", "throughput": 972.05, "total_tokens": 14003616}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.198, "lr": 7.710628524559838e-14, "epoch": 320.0, "percentage": 100.0, "elapsed_time": "4:00:07", "remaining_time": "0:00:00", "throughput": 972.05, "total_tokens": 14005200}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.5859531760215759, "epoch": 320.0, "percentage": 100.0, "elapsed_time": "4:00:09", "remaining_time": "0:00:00", "throughput": 971.94, "total_tokens": 14005200}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 320.0, "percentage": 100.0, "elapsed_time": "4:00:11", "remaining_time": "0:00:00", "throughput": 971.81, "total_tokens": 14005200}
|