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": 1.1258, "lr": 3.2720109079037443e-09, "epoch": 698.1592920353983, "percentage": 99.49, "elapsed_time": "3:07:22", "remaining_time": "0:00:57", "throughput": 1961.31, "total_tokens": 22050120}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 1.0302, "lr": 3.1151063006468193e-09, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "3:07:23", "remaining_time": "0:00:56", "throughput": 1961.34, "total_tokens": 22053128}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.0310944318771362, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "3:07:24", "remaining_time": "0:00:56", "throughput": 1961.16, "total_tokens": 22053128}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 1.1258, "lr": 3.2720109079037443e-09, "epoch": 698.1592920353983, "percentage": 99.49, "elapsed_time": "3:07:22", "remaining_time": "0:00:57", "throughput": 1961.31, "total_tokens": 22050120}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 1.0302, "lr": 3.1151063006468193e-09, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "3:07:23", "remaining_time": "0:00:56", "throughput": 1961.34, "total_tokens": 22053128}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.0310944318771362, "epoch": 698.2477876106195, "percentage": 99.5, "elapsed_time": "3:07:24", "remaining_time": "0:00:56", "throughput": 1961.16, "total_tokens": 22053128}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.8212, "lr": 2.962056527169854e-09, "epoch": 698.3362831858407, "percentage": 99.51, "elapsed_time": "3:07:27", "remaining_time": "0:00:55", "throughput": 1960.99, "total_tokens": 22056024}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 1.1084, "lr": 2.8128616110761898e-09, "epoch": 698.4247787610619, "percentage": 99.52, "elapsed_time": "3:07:28", "remaining_time": "0:00:53", "throughput": 1960.97, "total_tokens": 22058504}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 1.0394, "lr": 2.6675215753724223e-09, "epoch": 698.5132743362832, "percentage": 99.54, "elapsed_time": "3:07:30", "remaining_time": "0:00:52", "throughput": 1960.97, "total_tokens": 22061176}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 1.1022, "lr": 2.5260364424739557e-09, "epoch": 698.6017699115044, "percentage": 99.55, "elapsed_time": "3:07:31", "remaining_time": "0:00:50", "throughput": 1960.98, "total_tokens": 22064072}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 1.1032, "lr": 2.3884062341994475e-09, "epoch": 698.6902654867257, "percentage": 99.56, "elapsed_time": "3:07:32", "remaining_time": "0:00:49", "throughput": 1961.03, "total_tokens": 22067400}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 1.1242, "lr": 2.25463097177081e-09, "epoch": 698.7787610619469, "percentage": 99.58, "elapsed_time": "3:07:34", "remaining_time": "0:00:48", "throughput": 1961.02, "total_tokens": 22069912}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 1.0822, "lr": 2.1247106758215397e-09, "epoch": 698.8672566371681, "percentage": 99.59, "elapsed_time": "3:07:35", "remaining_time": "0:00:46", "throughput": 1961.02, "total_tokens": 22072456}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 1.0733, "lr": 1.998645366382834e-09, "epoch": 698.9557522123894, "percentage": 99.6, "elapsed_time": "3:07:37", "remaining_time": "0:00:45", "throughput": 1961.04, "total_tokens": 22075560}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.9502, "lr": 1.876435062897475e-09, "epoch": 699.0353982300885, "percentage": 99.61, "elapsed_time": "3:07:38", "remaining_time": "0:00:43", "throughput": 1960.98, "total_tokens": 22078352}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.7858, "lr": 1.758079784211497e-09, "epoch": 699.1238938053098, "percentage": 99.62, "elapsed_time": "3:07:40", "remaining_time": "0:00:42", "throughput": 1960.99, "total_tokens": 22081216}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 1.1894, "lr": 1.6435795485797434e-09, "epoch": 699.212389380531, "percentage": 99.64, "elapsed_time": "3:07:41", "remaining_time": "0:00:40", "throughput": 1960.99, "total_tokens": 22083952}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 1.0199, "lr": 1.5329343736547596e-09, "epoch": 699.3008849557522, "percentage": 99.65, "elapsed_time": "3:07:42", "remaining_time": "0:00:39", "throughput": 1961.01, "total_tokens": 22086864}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 1.1236, "lr": 1.4261442765006739e-09, "epoch": 699.3893805309734, "percentage": 99.66, "elapsed_time": "3:07:44", "remaining_time": "0:00:38", "throughput": 1961.02, "total_tokens": 22089584}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 1.1375, "lr": 1.3232092735876445e-09, "epoch": 699.4778761061947, "percentage": 99.67, "elapsed_time": "3:07:45", "remaining_time": "0:00:36", "throughput": 1961.03, "total_tokens": 22092384}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 1.0768, "lr": 1.2241293807918607e-09, "epoch": 699.566371681416, "percentage": 99.69, "elapsed_time": "3:07:47", "remaining_time": "0:00:35", "throughput": 1961.04, "total_tokens": 22095152}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.9638, "lr": 1.128904613387216e-09, "epoch": 699.6548672566372, "percentage": 99.7, "elapsed_time": "3:07:48", "remaining_time": "0:00:33", "throughput": 1961.04, "total_tokens": 22097904}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.9703, "lr": 1.0375349860591853e-09, "epoch": 699.7433628318585, "percentage": 99.71, "elapsed_time": "3:07:49", "remaining_time": "0:00:32", "throughput": 1961.05, "total_tokens": 22100720}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 1.184, "lr": 9.5002051290205e-10, "epoch": 699.8318584070796, "percentage": 99.72, "elapsed_time": "3:07:51", "remaining_time": "0:00:31", "throughput": 1961.04, "total_tokens": 22103184}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 1.0703, "lr": 8.663612074077954e-10, "epoch": 699.9203539823009, "percentage": 99.74, "elapsed_time": "3:07:52", "remaining_time": "0:00:29", "throughput": 1961.04, "total_tokens": 22105936}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 1.3927, "lr": 7.865570824799884e-10, "epoch": 700.0, "percentage": 99.75, "elapsed_time": "3:07:53", "remaining_time": "0:00:28", "throughput": 1960.99, "total_tokens": 22108104}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 1.2332, "lr": 7.106081504254514e-10, "epoch": 700.0884955752213, "percentage": 99.76, "elapsed_time": "3:07:55", "remaining_time": "0:00:26", "throughput": 1960.93, "total_tokens": 22110856}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 1.1341, "lr": 6.385144229570372e-10, "epoch": 700.1769911504425, "percentage": 99.78, "elapsed_time": "3:07:57", "remaining_time": "0:00:25", "throughput": 1960.95, "total_tokens": 22113608}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 1.0557, "lr": 5.70275911190854e-10, "epoch": 700.2654867256637, "percentage": 99.79, "elapsed_time": "3:07:58", "remaining_time": "0:00:24", "throughput": 1960.93, "total_tokens": 22116072}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.9841, "lr": 5.058926256490403e-10, "epoch": 700.3539823008849, "percentage": 99.8, "elapsed_time": "3:07:59", "remaining_time": "0:00:22", "throughput": 1960.95, "total_tokens": 22118840}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 1.0484, "lr": 4.4536457626254134e-10, "epoch": 700.4424778761062, "percentage": 99.81, "elapsed_time": "3:08:01", "remaining_time": "0:00:21", "throughput": 1960.96, "total_tokens": 22121640}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.8099, "lr": 3.88691772365557e-10, "epoch": 700.5309734513274, "percentage": 99.83, "elapsed_time": "3:08:02", "remaining_time": "0:00:19", "throughput": 1960.97, "total_tokens": 22124568}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 1.0403, "lr": 3.358742226955425e-10, "epoch": 700.6194690265487, "percentage": 99.84, "elapsed_time": "3:08:03", "remaining_time": "0:00:18", "throughput": 1960.98, "total_tokens": 22127400}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.9812, "lr": 2.8691193539875925e-10, "epoch": 700.70796460177, "percentage": 99.85, "elapsed_time": "3:08:05", "remaining_time": "0:00:16", "throughput": 1961.01, "total_tokens": 22130328}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 1.0974, "lr": 2.418049180274995e-10, "epoch": 700.7964601769911, "percentage": 99.86, "elapsed_time": "3:08:06", "remaining_time": "0:00:15", "throughput": 1961.05, "total_tokens": 22133512}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 1.1063, "lr": 2.005531775373104e-10, "epoch": 700.8849557522124, "percentage": 99.88, "elapsed_time": "3:08:07", "remaining_time": "0:00:14", "throughput": 1961.05, "total_tokens": 22136136}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 1.1024, "lr": 1.6315672028699435e-10, "epoch": 700.9734513274336, "percentage": 99.89, "elapsed_time": "3:08:09", "remaining_time": "0:00:12", "throughput": 1961.1, "total_tokens": 22139512}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.9561, "lr": 1.2961555204693555e-10, "epoch": 701.0530973451328, "percentage": 99.9, "elapsed_time": "3:08:11", "remaining_time": "0:00:11", "throughput": 1960.99, "total_tokens": 22141648}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.9276, "lr": 9.992967798799768e-11, "epoch": 701.141592920354, "percentage": 99.91, "elapsed_time": "3:08:12", "remaining_time": "0:00:09", "throughput": 1961.02, "total_tokens": 22144800}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 1.1954, "lr": 7.409910268707521e-11, "epoch": 701.2300884955753, "percentage": 99.92, "elapsed_time": "3:08:13", "remaining_time": "0:00:08", "throughput": 1961.03, "total_tokens": 22147616}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 1.1826, "lr": 5.212383012986877e-11, "epoch": 701.3185840707964, "percentage": 99.94, "elapsed_time": "3:08:15", "remaining_time": "0:00:07", "throughput": 1961.08, "total_tokens": 22150912}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 1.0434, "lr": 3.400386370533415e-11, "epoch": 701.4070796460177, "percentage": 99.95, "elapsed_time": "3:08:16", "remaining_time": "0:00:05", "throughput": 1961.08, "total_tokens": 22153504}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 1.0067, "lr": 1.9739206205682258e-11, "epoch": 701.4955752212389, "percentage": 99.96, "elapsed_time": "3:08:18", "remaining_time": "0:00:04", "throughput": 1961.1, "total_tokens": 22156544}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 1.0387, "lr": 9.329859829154685e-12, "epoch": 701.5840707964602, "percentage": 99.98, "elapsed_time": "3:08:19", "remaining_time": "0:00:02", "throughput": 1961.12, "total_tokens": 22159536}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 1.06, "lr": 2.7758261855748148e-12, "epoch": 701.6725663716815, "percentage": 99.99, "elapsed_time": "3:08:20", "remaining_time": "0:00:01", "throughput": 1961.11, "total_tokens": 22162128}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.9108, "lr": 7.710628524559838e-14, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "3:08:22", "remaining_time": "0:00:00", "throughput": 1961.09, "total_tokens": 22164464}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 1.0310944318771362, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "3:08:23", "remaining_time": "0:00:00", "throughput": 1960.91, "total_tokens": 22164464}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 701.7610619469026, "percentage": 100.0, "elapsed_time": "3:08:24", "remaining_time": "0:00:00", "throughput": 1960.71, "total_tokens": 22164464}
|