Training in progress, step 40000
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +42 -0
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1074144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:552660bc996d7d672cab5e111e957120562704668238bb7a6993d5f34e8c25ac
|
| 3 |
size 1074144
|
trainer_log.jsonl
CHANGED
|
@@ -8157,3 +8157,45 @@
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 282.2352941176471, "percentage": 99.49, "elapsed_time": "10:00:35", "remaining_time": "0:03:05", "throughput": 2961.66, "total_tokens": 106724504}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "10:00:39", "remaining_time": "0:03:01", "throughput": 2961.67, "total_tokens": 106737720}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.4025973379611969, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "10:00:44", "remaining_time": "0:03:01", "throughput": 2961.29, "total_tokens": 106737720}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 3.2720109079037443e-09, "epoch": 282.2352941176471, "percentage": 99.49, "elapsed_time": "10:00:35", "remaining_time": "0:03:05", "throughput": 2961.66, "total_tokens": 106724504}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 3.1151063006468193e-09, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "10:00:39", "remaining_time": "0:03:01", "throughput": 2961.67, "total_tokens": 106737720}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.4025973379611969, "epoch": 282.27094474153296, "percentage": 99.5, "elapsed_time": "10:00:44", "remaining_time": "0:03:01", "throughput": 2961.29, "total_tokens": 106737720}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 2.962056527169854e-09, "epoch": 282.3065953654189, "percentage": 99.51, "elapsed_time": "10:00:49", "remaining_time": "0:02:56", "throughput": 2961.23, "total_tokens": 106750904}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 2.8128616110761898e-09, "epoch": 282.3422459893048, "percentage": 99.52, "elapsed_time": "10:00:54", "remaining_time": "0:02:52", "throughput": 2961.25, "total_tokens": 106765176}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 2.6675215753724223e-09, "epoch": 282.3778966131907, "percentage": 99.54, "elapsed_time": "10:00:58", "remaining_time": "0:02:47", "throughput": 2961.27, "total_tokens": 106778680}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 2.5260364424739557e-09, "epoch": 282.41354723707667, "percentage": 99.55, "elapsed_time": "10:01:02", "remaining_time": "0:02:43", "throughput": 2961.27, "total_tokens": 106791128}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 2.3884062341994475e-09, "epoch": 282.44919786096256, "percentage": 99.56, "elapsed_time": "10:01:06", "remaining_time": "0:02:38", "throughput": 2961.29, "total_tokens": 106803192}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 2.25463097177081e-09, "epoch": 282.4848484848485, "percentage": 99.58, "elapsed_time": "10:01:11", "remaining_time": "0:02:33", "throughput": 2961.31, "total_tokens": 106818200}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0, "lr": 2.1247106758215397e-09, "epoch": 282.5204991087344, "percentage": 99.59, "elapsed_time": "10:01:15", "remaining_time": "0:02:29", "throughput": 2961.33, "total_tokens": 106832248}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.998645366382834e-09, "epoch": 282.5561497326203, "percentage": 99.6, "elapsed_time": "10:01:20", "remaining_time": "0:02:24", "throughput": 2961.35, "total_tokens": 106845816}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.0, "lr": 1.876435062897475e-09, "epoch": 282.5918003565062, "percentage": 99.61, "elapsed_time": "10:01:24", "remaining_time": "0:02:20", "throughput": 2961.37, "total_tokens": 106860088}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.758079784211497e-09, "epoch": 282.62745098039215, "percentage": 99.62, "elapsed_time": "10:01:28", "remaining_time": "0:02:15", "throughput": 2961.39, "total_tokens": 106872856}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 1.6435795485797434e-09, "epoch": 282.6631016042781, "percentage": 99.64, "elapsed_time": "10:01:33", "remaining_time": "0:02:11", "throughput": 2961.4, "total_tokens": 106886296}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.0, "lr": 1.5329343736547596e-09, "epoch": 282.698752228164, "percentage": 99.65, "elapsed_time": "10:01:37", "remaining_time": "0:02:06", "throughput": 2961.42, "total_tokens": 106900408}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.0, "lr": 1.4261442765006739e-09, "epoch": 282.7344028520499, "percentage": 99.66, "elapsed_time": "10:01:42", "remaining_time": "0:02:02", "throughput": 2961.43, "total_tokens": 106914040}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 1.3232092735876445e-09, "epoch": 282.7700534759358, "percentage": 99.67, "elapsed_time": "10:01:46", "remaining_time": "0:01:57", "throughput": 2961.44, "total_tokens": 106926264}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 1.2241293807918607e-09, "epoch": 282.80570409982175, "percentage": 99.69, "elapsed_time": "10:01:50", "remaining_time": "0:01:53", "throughput": 2961.44, "total_tokens": 106938168}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 1.128904613387216e-09, "epoch": 282.84135472370764, "percentage": 99.7, "elapsed_time": "10:01:54", "remaining_time": "0:01:48", "throughput": 2961.46, "total_tokens": 106951288}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 1.0375349860591853e-09, "epoch": 282.8770053475936, "percentage": 99.71, "elapsed_time": "10:01:58", "remaining_time": "0:01:44", "throughput": 2961.48, "total_tokens": 106965624}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 9.5002051290205e-10, "epoch": 282.9126559714795, "percentage": 99.72, "elapsed_time": "10:02:03", "remaining_time": "0:01:39", "throughput": 2961.49, "total_tokens": 106979832}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 8.663612074077954e-10, "epoch": 282.9483065953654, "percentage": 99.74, "elapsed_time": "10:02:07", "remaining_time": "0:01:35", "throughput": 2961.5, "total_tokens": 106993112}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 7.865570824799884e-10, "epoch": 282.98395721925135, "percentage": 99.75, "elapsed_time": "10:02:11", "remaining_time": "0:01:30", "throughput": 2961.51, "total_tokens": 107005432}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 7.106081504254514e-10, "epoch": 283.01426024955435, "percentage": 99.76, "elapsed_time": "10:02:16", "remaining_time": "0:01:26", "throughput": 2961.49, "total_tokens": 107016656}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 6.385144229570372e-10, "epoch": 283.0499108734403, "percentage": 99.78, "elapsed_time": "10:02:20", "remaining_time": "0:01:21", "throughput": 2961.51, "total_tokens": 107030992}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 5.70275911190854e-10, "epoch": 283.0855614973262, "percentage": 99.79, "elapsed_time": "10:02:25", "remaining_time": "0:01:16", "throughput": 2961.53, "total_tokens": 107044688}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 5.058926256490403e-10, "epoch": 283.1212121212121, "percentage": 99.8, "elapsed_time": "10:02:29", "remaining_time": "0:01:12", "throughput": 2961.54, "total_tokens": 107056976}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 4.4536457626254134e-10, "epoch": 283.15686274509807, "percentage": 99.81, "elapsed_time": "10:02:33", "remaining_time": "0:01:07", "throughput": 2961.55, "total_tokens": 107071376}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 3.88691772365557e-10, "epoch": 283.19251336898395, "percentage": 99.83, "elapsed_time": "10:02:37", "remaining_time": "0:01:03", "throughput": 2961.56, "total_tokens": 107084080}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 3.358742226955425e-10, "epoch": 283.2281639928699, "percentage": 99.84, "elapsed_time": "10:02:42", "remaining_time": "0:00:58", "throughput": 2961.58, "total_tokens": 107097616}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 2.8691193539875925e-10, "epoch": 283.2638146167558, "percentage": 99.85, "elapsed_time": "10:02:46", "remaining_time": "0:00:54", "throughput": 2961.59, "total_tokens": 107111760}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 2.418049180274995e-10, "epoch": 283.2994652406417, "percentage": 99.86, "elapsed_time": "10:02:51", "remaining_time": "0:00:49", "throughput": 2961.61, "total_tokens": 107125328}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 2.005531775373104e-10, "epoch": 283.3351158645276, "percentage": 99.88, "elapsed_time": "10:02:55", "remaining_time": "0:00:45", "throughput": 2961.62, "total_tokens": 107137840}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 1.6315672028699435e-10, "epoch": 283.37076648841355, "percentage": 99.89, "elapsed_time": "10:03:00", "remaining_time": "0:00:40", "throughput": 2961.63, "total_tokens": 107151920}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.0, "lr": 1.2961555204693555e-10, "epoch": 283.4064171122995, "percentage": 99.9, "elapsed_time": "10:03:04", "remaining_time": "0:00:36", "throughput": 2961.65, "total_tokens": 107165712}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 9.992967798799768e-11, "epoch": 283.4420677361854, "percentage": 99.91, "elapsed_time": "10:03:09", "remaining_time": "0:00:31", "throughput": 2961.66, "total_tokens": 107180304}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 7.409910268707521e-11, "epoch": 283.4777183600713, "percentage": 99.92, "elapsed_time": "10:03:13", "remaining_time": "0:00:27", "throughput": 2961.68, "total_tokens": 107193776}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0, "lr": 5.212383012986877e-11, "epoch": 283.5133689839572, "percentage": 99.94, "elapsed_time": "10:03:17", "remaining_time": "0:00:22", "throughput": 2961.69, "total_tokens": 107206512}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 3.400386370533415e-11, "epoch": 283.54901960784315, "percentage": 99.95, "elapsed_time": "10:03:22", "remaining_time": "0:00:18", "throughput": 2961.7, "total_tokens": 107219440}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.9739206205682258e-11, "epoch": 283.58467023172904, "percentage": 99.96, "elapsed_time": "10:03:26", "remaining_time": "0:00:13", "throughput": 2961.7, "total_tokens": 107231504}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 9.329859829154685e-12, "epoch": 283.620320855615, "percentage": 99.98, "elapsed_time": "10:03:30", "remaining_time": "0:00:09", "throughput": 2961.72, "total_tokens": 107245488}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 2.7758261855748148e-12, "epoch": 283.65597147950086, "percentage": 99.99, "elapsed_time": "10:03:35", "remaining_time": "0:00:04", "throughput": 2961.75, "total_tokens": 107260144}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 7.710628524559838e-14, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "10:03:39", "remaining_time": "0:00:00", "throughput": 2961.76, "total_tokens": 107274480}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.4114895164966583, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "10:03:44", "remaining_time": "0:00:00", "throughput": 2961.39, "total_tokens": 107274480}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 283.6916221033868, "percentage": 100.0, "elapsed_time": "10:03:45", "remaining_time": "0:00:00", "throughput": 2961.32, "total_tokens": 107274480}
|