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": 0.4521, "lr": 3.2720109079037443e-09, "epoch": 1.273766084117534, "percentage": 99.49, "elapsed_time": "1 day, 12:37:36", "remaining_time": "0:11:19", "throughput": 459.28, "total_tokens": 60559376}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.5532, "lr": 3.1151063006468193e-09, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 12:37:39", "remaining_time": "0:11:02", "throughput": 459.33, "total_tokens": 60567296}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.4941261410713196, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 12:46:33", "remaining_time": "0:11:05", "throughput": 457.48, "total_tokens": 60567296}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.4521, "lr": 3.2720109079037443e-09, "epoch": 1.273766084117534, "percentage": 99.49, "elapsed_time": "1 day, 12:37:36", "remaining_time": "0:11:19", "throughput": 459.28, "total_tokens": 60559376}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.5532, "lr": 3.1151063006468193e-09, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 12:37:39", "remaining_time": "0:11:02", "throughput": 459.33, "total_tokens": 60567296}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.4941261410713196, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 12:46:33", "remaining_time": "0:11:05", "throughput": 457.48, "total_tokens": 60567296}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.7249, "lr": 2.962056527169854e-09, "epoch": 1.274086166058511, "percentage": 99.51, "elapsed_time": "1 day, 12:46:36", "remaining_time": "0:10:48", "throughput": 457.53, "total_tokens": 60574960}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.4993, "lr": 2.8128616110761898e-09, "epoch": 1.2742462070289995, "percentage": 99.52, "elapsed_time": "1 day, 12:46:38", "remaining_time": "0:10:31", "throughput": 457.58, "total_tokens": 60582544}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.4706, "lr": 2.6675215753724223e-09, "epoch": 1.274406247999488, "percentage": 99.54, "elapsed_time": "1 day, 12:46:41", "remaining_time": "0:10:15", "throughput": 457.62, "total_tokens": 60589536}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.5156, "lr": 2.5260364424739557e-09, "epoch": 1.2745662889699763, "percentage": 99.55, "elapsed_time": "1 day, 12:46:43", "remaining_time": "0:09:58", "throughput": 457.67, "total_tokens": 60597408}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.5791, "lr": 2.3884062341994475e-09, "epoch": 1.2747263299404648, "percentage": 99.56, "elapsed_time": "1 day, 12:46:46", "remaining_time": "0:09:41", "throughput": 457.72, "total_tokens": 60605056}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.4739, "lr": 2.25463097177081e-09, "epoch": 1.2748863709109532, "percentage": 99.58, "elapsed_time": "1 day, 12:46:48", "remaining_time": "0:09:25", "throughput": 457.77, "total_tokens": 60612912}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.3847, "lr": 2.1247106758215397e-09, "epoch": 1.2750464118814415, "percentage": 99.59, "elapsed_time": "1 day, 12:46:51", "remaining_time": "0:09:08", "throughput": 457.82, "total_tokens": 60620528}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.3403, "lr": 1.998645366382834e-09, "epoch": 1.27520645285193, "percentage": 99.6, "elapsed_time": "1 day, 12:46:53", "remaining_time": "0:08:51", "throughput": 457.87, "total_tokens": 60628464}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.61, "lr": 1.876435062897475e-09, "epoch": 1.2753664938224185, "percentage": 99.61, "elapsed_time": "1 day, 12:46:56", "remaining_time": "0:08:35", "throughput": 457.92, "total_tokens": 60636560}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.4145, "lr": 1.758079784211497e-09, "epoch": 1.275526534792907, "percentage": 99.62, "elapsed_time": "1 day, 12:46:59", "remaining_time": "0:08:18", "throughput": 457.97, "total_tokens": 60644256}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.3767, "lr": 1.6435795485797434e-09, "epoch": 1.2756865757633955, "percentage": 99.64, "elapsed_time": "1 day, 12:47:01", "remaining_time": "0:08:01", "throughput": 458.02, "total_tokens": 60651776}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.5245, "lr": 1.5329343736547596e-09, "epoch": 1.275846616733884, "percentage": 99.65, "elapsed_time": "1 day, 12:47:04", "remaining_time": "0:07:45", "throughput": 458.07, "total_tokens": 60659248}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.3565, "lr": 1.4261442765006739e-09, "epoch": 1.2760066577043723, "percentage": 99.66, "elapsed_time": "1 day, 12:47:06", "remaining_time": "0:07:28", "throughput": 458.11, "total_tokens": 60666448}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.4698, "lr": 1.3232092735876445e-09, "epoch": 1.2761666986748608, "percentage": 99.67, "elapsed_time": "1 day, 12:47:08", "remaining_time": "0:07:11", "throughput": 458.17, "total_tokens": 60674416}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.3379, "lr": 1.2241293807918607e-09, "epoch": 1.2763267396453493, "percentage": 99.69, "elapsed_time": "1 day, 12:47:11", "remaining_time": "0:06:55", "throughput": 458.22, "total_tokens": 60682288}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.5358, "lr": 1.128904613387216e-09, "epoch": 1.2764867806158375, "percentage": 99.7, "elapsed_time": "1 day, 12:47:14", "remaining_time": "0:06:38", "throughput": 458.27, "total_tokens": 60690736}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.486, "lr": 1.0375349860591853e-09, "epoch": 1.276646821586326, "percentage": 99.71, "elapsed_time": "1 day, 12:47:16", "remaining_time": "0:06:21", "throughput": 458.32, "total_tokens": 60698176}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.3751, "lr": 9.5002051290205e-10, "epoch": 1.2768068625568145, "percentage": 99.72, "elapsed_time": "1 day, 12:47:19", "remaining_time": "0:06:05", "throughput": 458.37, "total_tokens": 60705744}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.5697, "lr": 8.663612074077954e-10, "epoch": 1.276966903527303, "percentage": 99.74, "elapsed_time": "1 day, 12:47:21", "remaining_time": "0:05:48", "throughput": 458.41, "total_tokens": 60713024}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.4348, "lr": 7.865570824799884e-10, "epoch": 1.2771269444977915, "percentage": 99.75, "elapsed_time": "1 day, 12:47:24", "remaining_time": "0:05:31", "throughput": 458.46, "total_tokens": 60720928}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.3818, "lr": 7.106081504254514e-10, "epoch": 1.27728698546828, "percentage": 99.76, "elapsed_time": "1 day, 12:47:26", "remaining_time": "0:05:15", "throughput": 458.51, "total_tokens": 60728192}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.3227, "lr": 6.385144229570372e-10, "epoch": 1.2774470264387683, "percentage": 99.78, "elapsed_time": "1 day, 12:47:28", "remaining_time": "0:04:58", "throughput": 458.56, "total_tokens": 60735520}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.499, "lr": 5.70275911190854e-10, "epoch": 1.2776070674092568, "percentage": 99.79, "elapsed_time": "1 day, 12:47:31", "remaining_time": "0:04:42", "throughput": 458.61, "total_tokens": 60743168}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.4142, "lr": 5.058926256490403e-10, "epoch": 1.2777671083797453, "percentage": 99.8, "elapsed_time": "1 day, 12:47:33", "remaining_time": "0:04:25", "throughput": 458.65, "total_tokens": 60750496}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.3717, "lr": 4.4536457626254134e-10, "epoch": 1.2779271493502335, "percentage": 99.81, "elapsed_time": "1 day, 12:47:36", "remaining_time": "0:04:08", "throughput": 458.7, "total_tokens": 60757872}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.5995, "lr": 3.88691772365557e-10, "epoch": 1.278087190320722, "percentage": 99.83, "elapsed_time": "1 day, 12:47:38", "remaining_time": "0:03:52", "throughput": 458.75, "total_tokens": 60765376}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.3923, "lr": 3.358742226955425e-10, "epoch": 1.2782472312912105, "percentage": 99.84, "elapsed_time": "1 day, 12:47:40", "remaining_time": "0:03:35", "throughput": 458.8, "total_tokens": 60772912}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.6435, "lr": 2.8691193539875925e-10, "epoch": 1.278407272261699, "percentage": 99.85, "elapsed_time": "1 day, 12:47:43", "remaining_time": "0:03:18", "throughput": 458.85, "total_tokens": 60780528}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.572, "lr": 2.418049180274995e-10, "epoch": 1.2785673132321875, "percentage": 99.86, "elapsed_time": "1 day, 12:47:45", "remaining_time": "0:03:02", "throughput": 458.9, "total_tokens": 60788272}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.5002, "lr": 2.005531775373104e-10, "epoch": 1.2787273542026758, "percentage": 99.88, "elapsed_time": "1 day, 12:47:48", "remaining_time": "0:02:45", "throughput": 458.94, "total_tokens": 60795648}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.6333, "lr": 1.6315672028699435e-10, "epoch": 1.2788873951731643, "percentage": 99.89, "elapsed_time": "1 day, 12:47:50", "remaining_time": "0:02:29", "throughput": 458.99, "total_tokens": 60803360}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.4447, "lr": 1.2961555204693555e-10, "epoch": 1.2790474361436528, "percentage": 99.9, "elapsed_time": "1 day, 12:47:53", "remaining_time": "0:02:12", "throughput": 459.04, "total_tokens": 60810480}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.4968, "lr": 9.992967798799768e-11, "epoch": 1.2792074771141413, "percentage": 99.91, "elapsed_time": "1 day, 12:47:55", "remaining_time": "0:01:56", "throughput": 459.09, "total_tokens": 60818128}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.4906, "lr": 7.409910268707521e-11, "epoch": 1.2793675180846296, "percentage": 99.92, "elapsed_time": "1 day, 12:47:58", "remaining_time": "0:01:39", "throughput": 459.14, "total_tokens": 60825888}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.4819, "lr": 5.212383012986877e-11, "epoch": 1.279527559055118, "percentage": 99.94, "elapsed_time": "1 day, 12:48:00", "remaining_time": "0:01:22", "throughput": 459.19, "total_tokens": 60833536}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.547, "lr": 3.400386370533415e-11, "epoch": 1.2796876000256066, "percentage": 99.95, "elapsed_time": "1 day, 12:48:03", "remaining_time": "0:01:06", "throughput": 459.23, "total_tokens": 60840864}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.386, "lr": 1.9739206205682258e-11, "epoch": 1.279847640996095, "percentage": 99.96, "elapsed_time": "1 day, 12:48:05", "remaining_time": "0:00:49", "throughput": 459.28, "total_tokens": 60848336}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.4371, "lr": 9.329859829154685e-12, "epoch": 1.2800076819665835, "percentage": 99.98, "elapsed_time": "1 day, 12:48:07", "remaining_time": "0:00:33", "throughput": 459.33, "total_tokens": 60855632}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.3467, "lr": 2.7758261855748148e-12, "epoch": 1.2801677229370718, "percentage": 99.99, "elapsed_time": "1 day, 12:48:10", "remaining_time": "0:00:16", "throughput": 459.38, "total_tokens": 60862976}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.4226, "lr": 7.710628524559838e-14, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "1 day, 12:48:12", "remaining_time": "0:00:00", "throughput": 459.43, "total_tokens": 60870656}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.4941261410713196, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "1 day, 12:57:06", "remaining_time": "0:00:00", "throughput": 457.58, "total_tokens": 60870656}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "1 day, 12:57:07", "remaining_time": "0:00:00", "throughput": 457.58, "total_tokens": 60870656}
|