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": 0.1676, "lr": 3.2720109079037443e-09, "epoch": 122.82534775888718, "percentage": 99.49, "elapsed_time": "7:17:50", "remaining_time": "0:02:15", "throughput": 2316.73, "total_tokens": 60862384}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.1807, "lr": 3.1151063006468193e-09, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "7:17:53", "remaining_time": "0:02:12", "throughput": 2316.76, "total_tokens": 60870320}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.2583099603652954, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "7:18:00", "remaining_time": "0:02:12", "throughput": 2316.16, "total_tokens": 60870320}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.1676, "lr": 3.2720109079037443e-09, "epoch": 122.82534775888718, "percentage": 99.49, "elapsed_time": "7:17:50", "remaining_time": "0:02:15", "throughput": 2316.73, "total_tokens": 60862384}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.1807, "lr": 3.1151063006468193e-09, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "7:17:53", "remaining_time": "0:02:12", "throughput": 2316.76, "total_tokens": 60870320}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.2583099603652954, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "7:18:00", "remaining_time": "0:02:12", "throughput": 2316.16, "total_tokens": 60870320}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.166, "lr": 2.962056527169854e-09, "epoch": 122.85625965996908, "percentage": 99.51, "elapsed_time": "7:18:04", "remaining_time": "0:02:08", "throughput": 2316.1, "total_tokens": 60877680}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.2171, "lr": 2.8128616110761898e-09, "epoch": 122.87171561051005, "percentage": 99.52, "elapsed_time": "7:18:07", "remaining_time": "0:02:05", "throughput": 2316.12, "total_tokens": 60885200}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.2304, "lr": 2.6675215753724223e-09, "epoch": 122.887171561051, "percentage": 99.54, "elapsed_time": "7:18:10", "remaining_time": "0:02:02", "throughput": 2316.14, "total_tokens": 60893360}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.1696, "lr": 2.5260364424739557e-09, "epoch": 122.90262751159196, "percentage": 99.55, "elapsed_time": "7:18:13", "remaining_time": "0:01:58", "throughput": 2316.17, "total_tokens": 60901200}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.1994, "lr": 2.3884062341994475e-09, "epoch": 122.91808346213293, "percentage": 99.56, "elapsed_time": "7:18:17", "remaining_time": "0:01:55", "throughput": 2316.19, "total_tokens": 60908912}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.1892, "lr": 2.25463097177081e-09, "epoch": 122.93353941267388, "percentage": 99.58, "elapsed_time": "7:18:20", "remaining_time": "0:01:52", "throughput": 2316.21, "total_tokens": 60916912}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.2085, "lr": 2.1247106758215397e-09, "epoch": 122.94899536321483, "percentage": 99.59, "elapsed_time": "7:18:23", "remaining_time": "0:01:48", "throughput": 2316.22, "total_tokens": 60924336}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.2567, "lr": 1.998645366382834e-09, "epoch": 122.9644513137558, "percentage": 99.6, "elapsed_time": "7:18:26", "remaining_time": "0:01:45", "throughput": 2316.25, "total_tokens": 60932336}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.1607, "lr": 1.876435062897475e-09, "epoch": 122.97990726429676, "percentage": 99.61, "elapsed_time": "7:18:29", "remaining_time": "0:01:42", "throughput": 2316.26, "total_tokens": 60939760}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.1796, "lr": 1.758079784211497e-09, "epoch": 122.99536321483771, "percentage": 99.62, "elapsed_time": "7:18:32", "remaining_time": "0:01:39", "throughput": 2316.31, "total_tokens": 60948560}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.1797, "lr": 1.6435795485797434e-09, "epoch": 123.00927357032458, "percentage": 99.64, "elapsed_time": "7:18:35", "remaining_time": "0:01:35", "throughput": 2316.29, "total_tokens": 60955168}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.1785, "lr": 1.5329343736547596e-09, "epoch": 123.02472952086553, "percentage": 99.65, "elapsed_time": "7:18:38", "remaining_time": "0:01:32", "throughput": 2316.29, "total_tokens": 60962368}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.2031, "lr": 1.4261442765006739e-09, "epoch": 123.04018547140649, "percentage": 99.66, "elapsed_time": "7:18:42", "remaining_time": "0:01:29", "throughput": 2316.31, "total_tokens": 60970016}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.2284, "lr": 1.3232092735876445e-09, "epoch": 123.05564142194746, "percentage": 99.67, "elapsed_time": "7:18:45", "remaining_time": "0:01:25", "throughput": 2316.33, "total_tokens": 60977440}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.1943, "lr": 1.2241293807918607e-09, "epoch": 123.07109737248841, "percentage": 99.69, "elapsed_time": "7:18:48", "remaining_time": "0:01:22", "throughput": 2316.34, "total_tokens": 60985184}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.173, "lr": 1.128904613387216e-09, "epoch": 123.08655332302936, "percentage": 99.7, "elapsed_time": "7:18:51", "remaining_time": "0:01:19", "throughput": 2316.36, "total_tokens": 60992896}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.1845, "lr": 1.0375349860591853e-09, "epoch": 123.10200927357033, "percentage": 99.71, "elapsed_time": "7:18:54", "remaining_time": "0:01:15", "throughput": 2316.37, "total_tokens": 61000256}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.2225, "lr": 9.5002051290205e-10, "epoch": 123.11746522411129, "percentage": 99.72, "elapsed_time": "7:18:57", "remaining_time": "0:01:12", "throughput": 2316.39, "total_tokens": 61007616}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.1582, "lr": 8.663612074077954e-10, "epoch": 123.13292117465224, "percentage": 99.74, "elapsed_time": "7:19:00", "remaining_time": "0:01:09", "throughput": 2316.4, "total_tokens": 61015360}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.1954, "lr": 7.865570824799884e-10, "epoch": 123.14837712519319, "percentage": 99.75, "elapsed_time": "7:19:03", "remaining_time": "0:01:06", "throughput": 2316.43, "total_tokens": 61023232}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.2257, "lr": 7.106081504254514e-10, "epoch": 123.16383307573416, "percentage": 99.76, "elapsed_time": "7:19:06", "remaining_time": "0:01:02", "throughput": 2316.45, "total_tokens": 61030880}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.1679, "lr": 6.385144229570372e-10, "epoch": 123.17928902627511, "percentage": 99.78, "elapsed_time": "7:19:09", "remaining_time": "0:00:59", "throughput": 2316.46, "total_tokens": 61038400}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.1756, "lr": 5.70275911190854e-10, "epoch": 123.19474497681607, "percentage": 99.79, "elapsed_time": "7:19:12", "remaining_time": "0:00:56", "throughput": 2316.48, "total_tokens": 61045952}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.1588, "lr": 5.058926256490403e-10, "epoch": 123.21020092735704, "percentage": 99.8, "elapsed_time": "7:19:16", "remaining_time": "0:00:52", "throughput": 2316.5, "total_tokens": 61053664}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.2287, "lr": 4.4536457626254134e-10, "epoch": 123.22565687789799, "percentage": 99.81, "elapsed_time": "7:19:19", "remaining_time": "0:00:49", "throughput": 2316.51, "total_tokens": 61061184}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.2312, "lr": 3.88691772365557e-10, "epoch": 123.24111282843894, "percentage": 99.83, "elapsed_time": "7:19:22", "remaining_time": "0:00:46", "throughput": 2316.51, "total_tokens": 61068288}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.172, "lr": 3.358742226955425e-10, "epoch": 123.25656877897991, "percentage": 99.84, "elapsed_time": "7:19:25", "remaining_time": "0:00:42", "throughput": 2316.54, "total_tokens": 61076096}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.1786, "lr": 2.8691193539875925e-10, "epoch": 123.27202472952087, "percentage": 99.85, "elapsed_time": "7:19:28", "remaining_time": "0:00:39", "throughput": 2316.55, "total_tokens": 61083520}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.2214, "lr": 2.418049180274995e-10, "epoch": 123.28748068006182, "percentage": 99.86, "elapsed_time": "7:19:31", "remaining_time": "0:00:36", "throughput": 2316.55, "total_tokens": 61090592}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.213, "lr": 2.005531775373104e-10, "epoch": 123.30293663060279, "percentage": 99.88, "elapsed_time": "7:19:34", "remaining_time": "0:00:33", "throughput": 2316.56, "total_tokens": 61098016}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.203, "lr": 1.6315672028699435e-10, "epoch": 123.31839258114374, "percentage": 99.89, "elapsed_time": "7:19:37", "remaining_time": "0:00:29", "throughput": 2316.58, "total_tokens": 61105568}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.1874, "lr": 1.2961555204693555e-10, "epoch": 123.3338485316847, "percentage": 99.9, "elapsed_time": "7:19:40", "remaining_time": "0:00:26", "throughput": 2316.59, "total_tokens": 61112992}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.1921, "lr": 9.992967798799768e-11, "epoch": 123.34930448222566, "percentage": 99.91, "elapsed_time": "7:19:43", "remaining_time": "0:00:23", "throughput": 2316.61, "total_tokens": 61120416}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.1936, "lr": 7.409910268707521e-11, "epoch": 123.36476043276662, "percentage": 99.92, "elapsed_time": "7:19:46", "remaining_time": "0:00:19", "throughput": 2316.64, "total_tokens": 61128480}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.1628, "lr": 5.212383012986877e-11, "epoch": 123.38021638330757, "percentage": 99.94, "elapsed_time": "7:19:49", "remaining_time": "0:00:16", "throughput": 2316.68, "total_tokens": 61137056}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.2592, "lr": 3.400386370533415e-11, "epoch": 123.39567233384854, "percentage": 99.95, "elapsed_time": "7:19:53", "remaining_time": "0:00:13", "throughput": 2316.71, "total_tokens": 61145344}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.1915, "lr": 1.9739206205682258e-11, "epoch": 123.41112828438949, "percentage": 99.96, "elapsed_time": "7:19:56", "remaining_time": "0:00:09", "throughput": 2316.75, "total_tokens": 61153888}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.1654, "lr": 9.329859829154685e-12, "epoch": 123.42658423493044, "percentage": 99.98, "elapsed_time": "7:19:59", "remaining_time": "0:00:06", "throughput": 2316.78, "total_tokens": 61161888}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.1922, "lr": 2.7758261855748148e-12, "epoch": 123.44204018547141, "percentage": 99.99, "elapsed_time": "7:20:02", "remaining_time": "0:00:03", "throughput": 2316.81, "total_tokens": 61169728}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.1913, "lr": 7.710628524559838e-14, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "7:20:05", "remaining_time": "0:00:00", "throughput": 2316.82, "total_tokens": 61177152}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.2583099603652954, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "7:20:12", "remaining_time": "0:00:00", "throughput": 2316.22, "total_tokens": 61177152}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "7:20:13", "remaining_time": "0:00:00", "throughput": 2316.15, "total_tokens": 61177152}
|