Training in progress, step 40000
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +41 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 18124968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b8ba704f4490502ddb358e38f792e37db67665952e9820511b19f6742e59536
|
| 3 |
size 18124968
|
trainer_log.jsonl
CHANGED
|
@@ -8158,3 +8158,44 @@
|
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "4:48:44", "remaining_time": "0:01:27", "throughput": 643.27, "total_tokens": 11144688}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.2725274562835693, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "4:48:46", "remaining_time": "0:01:27", "throughput": 643.22, "total_tokens": 11144688}
|
| 8160 |
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 442.27777777777777, "percentage": 99.51, "elapsed_time": "4:48:50", "remaining_time": "0:01:24", "throughput": 643.15, "total_tokens": 11146048}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "4:48:44", "remaining_time": "0:01:27", "throughput": 643.27, "total_tokens": 11144688}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.2725274562835693, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "4:48:46", "remaining_time": "0:01:27", "throughput": 643.22, "total_tokens": 11144688}
|
| 8160 |
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 442.27777777777777, "percentage": 99.51, "elapsed_time": "4:48:50", "remaining_time": "0:01:24", "throughput": 643.15, "total_tokens": 11146048}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 442.3333333333333, "percentage": 99.52, "elapsed_time": "4:48:52", "remaining_time": "0:01:22", "throughput": 643.15, "total_tokens": 11147488}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 442.3888888888889, "percentage": 99.54, "elapsed_time": "4:48:54", "remaining_time": "0:01:20", "throughput": 643.16, "total_tokens": 11148912}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 442.44444444444446, "percentage": 99.55, "elapsed_time": "4:48:56", "remaining_time": "0:01:18", "throughput": 643.16, "total_tokens": 11150288}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 442.5, "percentage": 99.56, "elapsed_time": "4:48:58", "remaining_time": "0:01:16", "throughput": 643.16, "total_tokens": 11151664}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 442.55555555555554, "percentage": 99.58, "elapsed_time": "4:49:00", "remaining_time": "0:01:14", "throughput": 643.16, "total_tokens": 11152992}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 2.1247106758215397e-09, "epoch": 442.6111111111111, "percentage": 99.59, "elapsed_time": "4:49:02", "remaining_time": "0:01:11", "throughput": 643.17, "total_tokens": 11154416}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 442.6666666666667, "percentage": 99.6, "elapsed_time": "4:49:04", "remaining_time": "0:01:09", "throughput": 643.17, "total_tokens": 11155824}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 442.72222222222223, "percentage": 99.61, "elapsed_time": "4:49:07", "remaining_time": "0:01:07", "throughput": 643.18, "total_tokens": 11157216}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 442.77777777777777, "percentage": 99.62, "elapsed_time": "4:49:09", "remaining_time": "0:01:05", "throughput": 643.18, "total_tokens": 11158624}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 442.8333333333333, "percentage": 99.64, "elapsed_time": "4:49:11", "remaining_time": "0:01:03", "throughput": 643.18, "total_tokens": 11160000}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 442.8888888888889, "percentage": 99.65, "elapsed_time": "4:49:13", "remaining_time": "0:01:00", "throughput": 643.19, "total_tokens": 11161456}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 442.94444444444446, "percentage": 99.66, "elapsed_time": "4:49:15", "remaining_time": "0:00:58", "throughput": 643.2, "total_tokens": 11162896}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 443.0, "percentage": 99.67, "elapsed_time": "4:49:17", "remaining_time": "0:00:56", "throughput": 643.2, "total_tokens": 11164336}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 443.05555555555554, "percentage": 99.69, "elapsed_time": "4:49:19", "remaining_time": "0:00:54", "throughput": 643.19, "total_tokens": 11165712}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 443.1111111111111, "percentage": 99.7, "elapsed_time": "4:49:21", "remaining_time": "0:00:52", "throughput": 643.2, "total_tokens": 11167104}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 443.1666666666667, "percentage": 99.71, "elapsed_time": "4:49:23", "remaining_time": "0:00:50", "throughput": 643.21, "total_tokens": 11168560}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 443.22222222222223, "percentage": 99.72, "elapsed_time": "4:49:25", "remaining_time": "0:00:47", "throughput": 643.21, "total_tokens": 11169968}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 443.27777777777777, "percentage": 99.74, "elapsed_time": "4:49:28", "remaining_time": "0:00:45", "throughput": 643.21, "total_tokens": 11171376}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 443.3333333333333, "percentage": 99.75, "elapsed_time": "4:49:30", "remaining_time": "0:00:43", "throughput": 643.22, "total_tokens": 11172768}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 443.3888888888889, "percentage": 99.76, "elapsed_time": "4:49:32", "remaining_time": "0:00:41", "throughput": 643.22, "total_tokens": 11174160}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 443.44444444444446, "percentage": 99.78, "elapsed_time": "4:49:34", "remaining_time": "0:00:39", "throughput": 643.23, "total_tokens": 11175584}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 443.5, "percentage": 99.79, "elapsed_time": "4:49:36", "remaining_time": "0:00:37", "throughput": 643.23, "total_tokens": 11176928}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 443.55555555555554, "percentage": 99.8, "elapsed_time": "4:49:38", "remaining_time": "0:00:34", "throughput": 643.23, "total_tokens": 11178304}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 443.6111111111111, "percentage": 99.81, "elapsed_time": "4:49:40", "remaining_time": "0:00:32", "throughput": 643.24, "total_tokens": 11179728}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 443.6666666666667, "percentage": 99.83, "elapsed_time": "4:49:42", "remaining_time": "0:00:30", "throughput": 643.24, "total_tokens": 11181104}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 443.72222222222223, "percentage": 99.84, "elapsed_time": "4:49:44", "remaining_time": "0:00:28", "throughput": 643.25, "total_tokens": 11182512}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 443.77777777777777, "percentage": 99.85, "elapsed_time": "4:49:46", "remaining_time": "0:00:26", "throughput": 643.25, "total_tokens": 11183952}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 443.8333333333333, "percentage": 99.86, "elapsed_time": "4:49:48", "remaining_time": "0:00:23", "throughput": 643.26, "total_tokens": 11185344}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 443.8888888888889, "percentage": 99.88, "elapsed_time": "4:49:50", "remaining_time": "0:00:21", "throughput": 643.26, "total_tokens": 11186752}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 443.94444444444446, "percentage": 99.89, "elapsed_time": "4:49:52", "remaining_time": "0:00:19", "throughput": 643.27, "total_tokens": 11188176}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 1.2961555204693555e-10, "epoch": 444.0, "percentage": 99.9, "elapsed_time": "4:49:54", "remaining_time": "0:00:17", "throughput": 643.26, "total_tokens": 11189552}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 444.05555555555554, "percentage": 99.91, "elapsed_time": "4:49:57", "remaining_time": "0:00:15", "throughput": 643.26, "total_tokens": 11190960}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 444.1111111111111, "percentage": 99.92, "elapsed_time": "4:49:59", "remaining_time": "0:00:13", "throughput": 643.26, "total_tokens": 11192368}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 5.212383012986877e-11, "epoch": 444.1666666666667, "percentage": 99.94, "elapsed_time": "4:50:01", "remaining_time": "0:00:10", "throughput": 643.27, "total_tokens": 11193776}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 444.22222222222223, "percentage": 99.95, "elapsed_time": "4:50:03", "remaining_time": "0:00:08", "throughput": 643.28, "total_tokens": 11195216}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 444.27777777777777, "percentage": 99.96, "elapsed_time": "4:50:05", "remaining_time": "0:00:06", "throughput": 643.28, "total_tokens": 11196624}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 444.3333333333333, "percentage": 99.98, "elapsed_time": "4:50:07", "remaining_time": "0:00:04", "throughput": 643.28, "total_tokens": 11198032}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 444.3888888888889, "percentage": 99.99, "elapsed_time": "4:50:09", "remaining_time": "0:00:02", "throughput": 643.29, "total_tokens": 11199424}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "4:50:11", "remaining_time": "0:00:00", "throughput": 643.29, "total_tokens": 11200800}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 1.2688204050064087, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "4:50:13", "remaining_time": "0:00:00", "throughput": 643.24, "total_tokens": 11200800}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "4:50:15", "remaining_time": "0:00:00", "throughput": 643.17, "total_tokens": 11200800}
|