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 1638528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f92bc1dfd0342e7f73da0c95a479de407a5ad9740cc05250b376acef3f98b962
|
| 3 |
size 1638528
|
trainer_log.jsonl
CHANGED
|
@@ -8158,3 +8158,44 @@
|
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0002, "lr": 1.8690637803880916e-05, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "2:07:11", "remaining_time": "0:00:38", "throughput": 1461.14, "total_tokens": 11150400}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.1250280141830444, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "2:07:12", "remaining_time": "0:00:38", "throughput": 1460.89, "total_tokens": 11150400}
|
| 8160 |
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0002, "lr": 1.7772339163019123e-05, "epoch": 442.27777777777777, "percentage": 99.51, "elapsed_time": "2:07:14", "remaining_time": "0:00:37", "throughput": 1460.76, "total_tokens": 11151792}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0002, "lr": 1.8690637803880916e-05, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "2:07:11", "remaining_time": "0:00:38", "throughput": 1461.14, "total_tokens": 11150400}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.1250280141830444, "epoch": 442.22222222222223, "percentage": 99.5, "elapsed_time": "2:07:12", "remaining_time": "0:00:38", "throughput": 1460.89, "total_tokens": 11150400}
|
| 8160 |
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0002, "lr": 1.7772339163019123e-05, "epoch": 442.27777777777777, "percentage": 99.51, "elapsed_time": "2:07:14", "remaining_time": "0:00:37", "throughput": 1460.76, "total_tokens": 11151792}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.0002, "lr": 1.6877169666457138e-05, "epoch": 442.3333333333333, "percentage": 99.52, "elapsed_time": "2:07:15", "remaining_time": "0:00:36", "throughput": 1460.77, "total_tokens": 11153232}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0002, "lr": 1.6005129452234532e-05, "epoch": 442.3888888888889, "percentage": 99.54, "elapsed_time": "2:07:16", "remaining_time": "0:00:35", "throughput": 1460.78, "total_tokens": 11154624}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0003, "lr": 1.5156218654843733e-05, "epoch": 442.44444444444446, "percentage": 99.55, "elapsed_time": "2:07:16", "remaining_time": "0:00:34", "throughput": 1460.8, "total_tokens": 11156016}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0001, "lr": 1.4330437405196683e-05, "epoch": 442.5, "percentage": 99.56, "elapsed_time": "2:07:17", "remaining_time": "0:00:33", "throughput": 1460.81, "total_tokens": 11157392}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.0001, "lr": 1.352778583062486e-05, "epoch": 442.55555555555554, "percentage": 99.58, "elapsed_time": "2:07:18", "remaining_time": "0:00:32", "throughput": 1460.82, "total_tokens": 11158704}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0002, "lr": 1.2748264054929237e-05, "epoch": 442.6111111111111, "percentage": 99.59, "elapsed_time": "2:07:19", "remaining_time": "0:00:31", "throughput": 1460.83, "total_tokens": 11160112}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.0002, "lr": 1.1991872198297004e-05, "epoch": 442.6666666666667, "percentage": 99.6, "elapsed_time": "2:07:20", "remaining_time": "0:00:30", "throughput": 1460.85, "total_tokens": 11161520}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.0002, "lr": 1.1258610377384847e-05, "epoch": 442.72222222222223, "percentage": 99.61, "elapsed_time": "2:07:21", "remaining_time": "0:00:29", "throughput": 1460.86, "total_tokens": 11162912}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0002, "lr": 1.0548478705268982e-05, "epoch": 442.77777777777777, "percentage": 99.62, "elapsed_time": "2:07:22", "remaining_time": "0:00:28", "throughput": 1460.88, "total_tokens": 11164320}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.0003, "lr": 9.86147729147846e-06, "epoch": 442.8333333333333, "percentage": 99.64, "elapsed_time": "2:07:23", "remaining_time": "0:00:27", "throughput": 1460.9, "total_tokens": 11165712}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.0002, "lr": 9.197606241928557e-06, "epoch": 442.8888888888889, "percentage": 99.65, "elapsed_time": "2:07:23", "remaining_time": "0:00:26", "throughput": 1460.92, "total_tokens": 11167168}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.0003, "lr": 8.556865659004042e-06, "epoch": 442.94444444444446, "percentage": 99.66, "elapsed_time": "2:07:24", "remaining_time": "0:00:25", "throughput": 1460.94, "total_tokens": 11168608}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.0002, "lr": 7.939255641525867e-06, "epoch": 443.0, "percentage": 99.67, "elapsed_time": "2:07:25", "remaining_time": "0:00:24", "throughput": 1460.93, "total_tokens": 11170064}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.0002, "lr": 7.344776284751164e-06, "epoch": 443.05555555555554, "percentage": 99.69, "elapsed_time": "2:07:27", "remaining_time": "0:00:23", "throughput": 1460.88, "total_tokens": 11171456}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.0001, "lr": 6.773427680323296e-06, "epoch": 443.1111111111111, "percentage": 99.7, "elapsed_time": "2:07:27", "remaining_time": "0:00:23", "throughput": 1460.9, "total_tokens": 11172832}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0003, "lr": 6.225209916355112e-06, "epoch": 443.1666666666667, "percentage": 99.71, "elapsed_time": "2:07:28", "remaining_time": "0:00:22", "throughput": 1460.92, "total_tokens": 11174288}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.0002, "lr": 5.7001230774123e-06, "epoch": 443.22222222222223, "percentage": 99.72, "elapsed_time": "2:07:29", "remaining_time": "0:00:21", "throughput": 1460.93, "total_tokens": 11175664}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.0002, "lr": 5.198167244446772e-06, "epoch": 443.27777777777777, "percentage": 99.74, "elapsed_time": "2:07:30", "remaining_time": "0:00:20", "throughput": 1460.95, "total_tokens": 11177056}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.0003, "lr": 4.71934249487993e-06, "epoch": 443.3333333333333, "percentage": 99.75, "elapsed_time": "2:07:31", "remaining_time": "0:00:19", "throughput": 1460.97, "total_tokens": 11178480}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0003, "lr": 4.2636489025527075e-06, "epoch": 443.3888888888889, "percentage": 99.76, "elapsed_time": "2:07:32", "remaining_time": "0:00:18", "throughput": 1460.98, "total_tokens": 11179856}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0002, "lr": 3.831086537742223e-06, "epoch": 443.44444444444446, "percentage": 99.78, "elapsed_time": "2:07:33", "remaining_time": "0:00:17", "throughput": 1461.0, "total_tokens": 11181264}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.0001, "lr": 3.4216554671451236e-06, "epoch": 443.5, "percentage": 99.79, "elapsed_time": "2:07:34", "remaining_time": "0:00:16", "throughput": 1461.01, "total_tokens": 11182624}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0002, "lr": 3.035355753894242e-06, "epoch": 443.55555555555554, "percentage": 99.8, "elapsed_time": "2:07:34", "remaining_time": "0:00:15", "throughput": 1461.03, "total_tokens": 11184032}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0003, "lr": 2.6721874575752477e-06, "epoch": 443.6111111111111, "percentage": 99.81, "elapsed_time": "2:07:35", "remaining_time": "0:00:14", "throughput": 1461.05, "total_tokens": 11185440}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0002, "lr": 2.3321506341933418e-06, "epoch": 443.6666666666667, "percentage": 99.83, "elapsed_time": "2:07:36", "remaining_time": "0:00:13", "throughput": 1461.06, "total_tokens": 11186816}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0003, "lr": 2.0152453361732546e-06, "epoch": 443.72222222222223, "percentage": 99.84, "elapsed_time": "2:07:37", "remaining_time": "0:00:12", "throughput": 1461.08, "total_tokens": 11188224}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0002, "lr": 1.7214716123925554e-06, "epoch": 443.77777777777777, "percentage": 99.85, "elapsed_time": "2:07:38", "remaining_time": "0:00:11", "throughput": 1461.1, "total_tokens": 11189664}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0002, "lr": 1.4508295081649968e-06, "epoch": 443.8333333333333, "percentage": 99.86, "elapsed_time": "2:07:39", "remaining_time": "0:00:10", "throughput": 1461.12, "total_tokens": 11191072}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0001, "lr": 1.2033190652238623e-06, "epoch": 443.8888888888889, "percentage": 99.88, "elapsed_time": "2:07:40", "remaining_time": "0:00:09", "throughput": 1461.14, "total_tokens": 11192480}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.0002, "lr": 9.78940321721966e-07, "epoch": 443.94444444444446, "percentage": 99.89, "elapsed_time": "2:07:40", "remaining_time": "0:00:08", "throughput": 1461.15, "total_tokens": 11193888}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.0002, "lr": 7.776933122816132e-07, "epoch": 444.0, "percentage": 99.9, "elapsed_time": "2:07:42", "remaining_time": "0:00:07", "throughput": 1461.13, "total_tokens": 11195264}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.0002, "lr": 5.99578067927986e-07, "epoch": 444.05555555555554, "percentage": 99.91, "elapsed_time": "2:07:43", "remaining_time": "0:00:06", "throughput": 1461.08, "total_tokens": 11196624}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0001, "lr": 4.445946161224512e-07, "epoch": 444.1111111111111, "percentage": 99.92, "elapsed_time": "2:07:44", "remaining_time": "0:00:05", "throughput": 1461.09, "total_tokens": 11198016}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0003, "lr": 3.127429807792126e-07, "epoch": 444.1666666666667, "percentage": 99.94, "elapsed_time": "2:07:45", "remaining_time": "0:00:04", "throughput": 1461.11, "total_tokens": 11199440}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.0002, "lr": 2.040231822320049e-07, "epoch": 444.22222222222223, "percentage": 99.95, "elapsed_time": "2:07:45", "remaining_time": "0:00:03", "throughput": 1461.13, "total_tokens": 11200880}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0001, "lr": 1.1843523723409354e-07, "epoch": 444.27777777777777, "percentage": 99.96, "elapsed_time": "2:07:46", "remaining_time": "0:00:02", "throughput": 1461.15, "total_tokens": 11202304}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.0001, "lr": 5.597915897492811e-08, "epoch": 444.3333333333333, "percentage": 99.98, "elapsed_time": "2:07:47", "remaining_time": "0:00:01", "throughput": 1461.17, "total_tokens": 11203696}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0002, "lr": 1.6654957113448885e-08, "epoch": 444.3888888888889, "percentage": 99.99, "elapsed_time": "2:07:48", "remaining_time": "0:00:00", "throughput": 1461.18, "total_tokens": 11205088}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0003, "lr": 4.626377114735902e-10, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "2:07:49", "remaining_time": "0:00:00", "throughput": 1461.2, "total_tokens": 11206480}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 1.1277180910110474, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "2:07:50", "remaining_time": "0:00:00", "throughput": 1460.95, "total_tokens": 11206480}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 444.44444444444446, "percentage": 100.0, "elapsed_time": "2:07:51", "remaining_time": "0:00:00", "throughput": 1460.75, "total_tokens": 11206480}
|