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": 1.0131, "lr": 3.2720109079037443e-09, "epoch": 6.4918835141528675, "percentage": 99.49, "elapsed_time": "13:50:27", "remaining_time": "0:04:16", "throughput": 1513.06, "total_tokens": 75392208}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.8366, "lr": 3.1151063006468193e-09, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "13:50:30", "remaining_time": "0:04:10", "throughput": 1513.17, "total_tokens": 75402576}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.9413630962371826, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "13:52:41", "remaining_time": "0:04:11", "throughput": 1509.21, "total_tokens": 75402576}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 1.0131, "lr": 3.2720109079037443e-09, "epoch": 6.4918835141528675, "percentage": 99.49, "elapsed_time": "13:50:27", "remaining_time": "0:04:16", "throughput": 1513.06, "total_tokens": 75392208}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.8366, "lr": 3.1151063006468193e-09, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "13:50:30", "remaining_time": "0:04:10", "throughput": 1513.17, "total_tokens": 75402576}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.9413630962371826, "epoch": 6.492699241373685, "percentage": 99.5, "elapsed_time": "13:52:41", "remaining_time": "0:04:11", "throughput": 1509.21, "total_tokens": 75402576}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 1.3058, "lr": 2.962056527169854e-09, "epoch": 6.493514968594502, "percentage": 99.51, "elapsed_time": "13:52:46", "remaining_time": "0:04:04", "throughput": 1509.26, "total_tokens": 75412160}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.6739, "lr": 2.8128616110761898e-09, "epoch": 6.49433069581532, "percentage": 99.52, "elapsed_time": "13:52:49", "remaining_time": "0:03:58", "throughput": 1509.36, "total_tokens": 75421648}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.8845, "lr": 2.6675215753724223e-09, "epoch": 6.495146423036137, "percentage": 99.54, "elapsed_time": "13:52:52", "remaining_time": "0:03:52", "throughput": 1509.48, "total_tokens": 75432032}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.7729, "lr": 2.5260364424739557e-09, "epoch": 6.495962150256954, "percentage": 99.55, "elapsed_time": "13:52:55", "remaining_time": "0:03:45", "throughput": 1509.58, "total_tokens": 75441760}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 1.1028, "lr": 2.3884062341994475e-09, "epoch": 6.496777877477771, "percentage": 99.56, "elapsed_time": "13:52:58", "remaining_time": "0:03:39", "throughput": 1509.68, "total_tokens": 75451104}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.8374, "lr": 2.25463097177081e-09, "epoch": 6.497593604698589, "percentage": 99.58, "elapsed_time": "13:53:00", "remaining_time": "0:03:33", "throughput": 1509.76, "total_tokens": 75458992}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 1.1631, "lr": 2.1247106758215397e-09, "epoch": 6.498409331919406, "percentage": 99.59, "elapsed_time": "13:53:03", "remaining_time": "0:03:27", "throughput": 1509.84, "total_tokens": 75466768}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.9555, "lr": 1.998645366382834e-09, "epoch": 6.499225059140223, "percentage": 99.6, "elapsed_time": "13:53:06", "remaining_time": "0:03:20", "throughput": 1509.95, "total_tokens": 75477344}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 1.1337, "lr": 1.876435062897475e-09, "epoch": 6.5000407863610405, "percentage": 99.61, "elapsed_time": "13:53:09", "remaining_time": "0:03:14", "throughput": 1510.06, "total_tokens": 75488112}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.775, "lr": 1.758079784211497e-09, "epoch": 6.500856513581859, "percentage": 99.62, "elapsed_time": "13:53:12", "remaining_time": "0:03:08", "throughput": 1510.16, "total_tokens": 75497344}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.6639, "lr": 1.6435795485797434e-09, "epoch": 6.501672240802676, "percentage": 99.64, "elapsed_time": "13:53:15", "remaining_time": "0:03:01", "throughput": 1510.26, "total_tokens": 75506928}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.9531, "lr": 1.5329343736547596e-09, "epoch": 6.502487968023493, "percentage": 99.65, "elapsed_time": "13:53:18", "remaining_time": "0:02:55", "throughput": 1510.36, "total_tokens": 75516624}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.6144, "lr": 1.4261442765006739e-09, "epoch": 6.50330369524431, "percentage": 99.66, "elapsed_time": "13:53:21", "remaining_time": "0:02:49", "throughput": 1510.46, "total_tokens": 75525952}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.9699, "lr": 1.3232092735876445e-09, "epoch": 6.504119422465128, "percentage": 99.67, "elapsed_time": "13:53:24", "remaining_time": "0:02:43", "throughput": 1510.57, "total_tokens": 75535680}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.8793, "lr": 1.2241293807918607e-09, "epoch": 6.504935149685945, "percentage": 99.69, "elapsed_time": "13:53:27", "remaining_time": "0:02:36", "throughput": 1510.66, "total_tokens": 75544816}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.8509, "lr": 1.128904613387216e-09, "epoch": 6.505750876906762, "percentage": 99.7, "elapsed_time": "13:53:31", "remaining_time": "0:02:30", "throughput": 1510.77, "total_tokens": 75555120}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.9835, "lr": 1.0375349860591853e-09, "epoch": 6.506566604127579, "percentage": 99.71, "elapsed_time": "13:53:34", "remaining_time": "0:02:24", "throughput": 1510.88, "total_tokens": 75565568}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.6353, "lr": 9.5002051290205e-10, "epoch": 6.507382331348397, "percentage": 99.72, "elapsed_time": "13:53:36", "remaining_time": "0:02:17", "throughput": 1510.96, "total_tokens": 75573360}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 1.7346, "lr": 8.663612074077954e-10, "epoch": 6.5081980585692145, "percentage": 99.74, "elapsed_time": "13:53:39", "remaining_time": "0:02:11", "throughput": 1511.06, "total_tokens": 75582720}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.8606, "lr": 7.865570824799884e-10, "epoch": 6.509013785790032, "percentage": 99.75, "elapsed_time": "13:53:42", "remaining_time": "0:02:05", "throughput": 1511.16, "total_tokens": 75592496}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 1.2528, "lr": 7.106081504254514e-10, "epoch": 6.50982951301085, "percentage": 99.76, "elapsed_time": "13:53:45", "remaining_time": "0:01:59", "throughput": 1511.26, "total_tokens": 75602064}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.7687, "lr": 6.385144229570372e-10, "epoch": 6.510645240231667, "percentage": 99.78, "elapsed_time": "13:53:48", "remaining_time": "0:01:52", "throughput": 1511.36, "total_tokens": 75611456}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.6788, "lr": 5.70275911190854e-10, "epoch": 6.511460967452484, "percentage": 99.79, "elapsed_time": "13:53:51", "remaining_time": "0:01:46", "throughput": 1511.45, "total_tokens": 75619840}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.8855, "lr": 5.058926256490403e-10, "epoch": 6.512276694673301, "percentage": 99.8, "elapsed_time": "13:53:54", "remaining_time": "0:01:40", "throughput": 1511.54, "total_tokens": 75628864}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.8453, "lr": 4.4536457626254134e-10, "epoch": 6.513092421894118, "percentage": 99.81, "elapsed_time": "13:53:57", "remaining_time": "0:01:33", "throughput": 1511.63, "total_tokens": 75637728}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.7255, "lr": 3.88691772365557e-10, "epoch": 6.513908149114936, "percentage": 99.83, "elapsed_time": "13:54:00", "remaining_time": "0:01:27", "throughput": 1511.73, "total_tokens": 75647120}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.8234, "lr": 3.358742226955425e-10, "epoch": 6.514723876335753, "percentage": 99.84, "elapsed_time": "13:54:03", "remaining_time": "0:01:21", "throughput": 1511.82, "total_tokens": 75656224}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 1.2348, "lr": 2.8691193539875925e-10, "epoch": 6.5155396035565705, "percentage": 99.85, "elapsed_time": "13:54:06", "remaining_time": "0:01:15", "throughput": 1511.92, "total_tokens": 75665648}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 1.0813, "lr": 2.418049180274995e-10, "epoch": 6.5163553307773885, "percentage": 99.86, "elapsed_time": "13:54:09", "remaining_time": "0:01:08", "throughput": 1512.02, "total_tokens": 75675488}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 1.0512, "lr": 2.005531775373104e-10, "epoch": 6.517171057998206, "percentage": 99.88, "elapsed_time": "13:54:12", "remaining_time": "0:01:02", "throughput": 1512.11, "total_tokens": 75684480}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.9147, "lr": 1.6315672028699435e-10, "epoch": 6.517986785219023, "percentage": 99.89, "elapsed_time": "13:54:15", "remaining_time": "0:00:56", "throughput": 1512.21, "total_tokens": 75693952}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.974, "lr": 1.2961555204693555e-10, "epoch": 6.51880251243984, "percentage": 99.9, "elapsed_time": "13:54:18", "remaining_time": "0:00:50", "throughput": 1512.32, "total_tokens": 75703808}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 1.2351, "lr": 9.992967798799768e-11, "epoch": 6.519618239660657, "percentage": 99.91, "elapsed_time": "13:54:21", "remaining_time": "0:00:43", "throughput": 1512.41, "total_tokens": 75712960}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 1.0167, "lr": 7.409910268707521e-11, "epoch": 6.520433966881475, "percentage": 99.92, "elapsed_time": "13:54:24", "remaining_time": "0:00:37", "throughput": 1512.52, "total_tokens": 75722928}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.6303, "lr": 5.212383012986877e-11, "epoch": 6.521249694102292, "percentage": 99.94, "elapsed_time": "13:54:26", "remaining_time": "0:00:31", "throughput": 1512.59, "total_tokens": 75730560}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.9082, "lr": 3.400386370533415e-11, "epoch": 6.522065421323109, "percentage": 99.95, "elapsed_time": "13:54:29", "remaining_time": "0:00:25", "throughput": 1512.68, "total_tokens": 75739568}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.8388, "lr": 1.9739206205682258e-11, "epoch": 6.522881148543927, "percentage": 99.96, "elapsed_time": "13:54:32", "remaining_time": "0:00:18", "throughput": 1512.79, "total_tokens": 75749696}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 1.338, "lr": 9.329859829154685e-12, "epoch": 6.523696875764744, "percentage": 99.98, "elapsed_time": "13:54:35", "remaining_time": "0:00:12", "throughput": 1512.9, "total_tokens": 75759696}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 1.2552, "lr": 2.7758261855748148e-12, "epoch": 6.524512602985562, "percentage": 99.99, "elapsed_time": "13:54:38", "remaining_time": "0:00:06", "throughput": 1513.0, "total_tokens": 75769312}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.8005, "lr": 7.710628524559838e-14, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "13:54:41", "remaining_time": "0:00:00", "throughput": 1513.1, "total_tokens": 75778784}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.9413630962371826, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "13:56:52", "remaining_time": "0:00:00", "throughput": 1509.16, "total_tokens": 75778784}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 6.525328330206379, "percentage": 100.0, "elapsed_time": "13:56:53", "remaining_time": "0:00:00", "throughput": 1509.13, "total_tokens": 75778784}
|