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 460928
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e03ec03327f46c144a1f1bb7a08252ab399ae7bc70f6414b01bce374bb82a24a
|
| 3 |
size 460928
|
trainer_log.jsonl
CHANGED
|
@@ -8157,3 +8157,45 @@
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0137, "lr": 1.9632065447422463e-05, "epoch": 10.502837534644318, "percentage": 99.49, "elapsed_time": "8:38:10", "remaining_time": "0:02:40", "throughput": 1157.74, "total_tokens": 35994880}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0159, "lr": 1.8690637803880916e-05, "epoch": 10.504157318199816, "percentage": 99.5, "elapsed_time": "8:38:12", "remaining_time": "0:02:36", "throughput": 1157.83, "total_tokens": 35999840}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.1114056259393692, "epoch": 10.504157318199816, "percentage": 99.5, "elapsed_time": "8:39:28", "remaining_time": "0:02:36", "throughput": 1155.01, "total_tokens": 35999840}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0137, "lr": 1.9632065447422463e-05, "epoch": 10.502837534644318, "percentage": 99.49, "elapsed_time": "8:38:10", "remaining_time": "0:02:40", "throughput": 1157.74, "total_tokens": 35994880}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0159, "lr": 1.8690637803880916e-05, "epoch": 10.504157318199816, "percentage": 99.5, "elapsed_time": "8:38:12", "remaining_time": "0:02:36", "throughput": 1157.83, "total_tokens": 35999840}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.1114056259393692, "epoch": 10.504157318199816, "percentage": 99.5, "elapsed_time": "8:39:28", "remaining_time": "0:02:36", "throughput": 1155.01, "total_tokens": 35999840}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0065, "lr": 1.7772339163019123e-05, "epoch": 10.505477101755313, "percentage": 99.51, "elapsed_time": "8:39:32", "remaining_time": "0:02:32", "throughput": 1155.02, "total_tokens": 36004288}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.0121, "lr": 1.6877169666457138e-05, "epoch": 10.50679688531081, "percentage": 99.52, "elapsed_time": "8:39:34", "remaining_time": "0:02:28", "throughput": 1155.08, "total_tokens": 36008672}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0146, "lr": 1.6005129452234532e-05, "epoch": 10.508116668866306, "percentage": 99.54, "elapsed_time": "8:39:36", "remaining_time": "0:02:24", "throughput": 1155.16, "total_tokens": 36013312}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0092, "lr": 1.5156218654843733e-05, "epoch": 10.509436452421802, "percentage": 99.55, "elapsed_time": "8:39:38", "remaining_time": "0:02:20", "throughput": 1155.23, "total_tokens": 36017824}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0114, "lr": 1.4330437405196683e-05, "epoch": 10.5107562359773, "percentage": 99.56, "elapsed_time": "8:39:39", "remaining_time": "0:02:17", "throughput": 1155.31, "total_tokens": 36022496}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.0107, "lr": 1.352778583062486e-05, "epoch": 10.512076019532797, "percentage": 99.58, "elapsed_time": "8:39:41", "remaining_time": "0:02:13", "throughput": 1155.38, "total_tokens": 36027168}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0082, "lr": 1.2748264054929237e-05, "epoch": 10.513395803088294, "percentage": 99.59, "elapsed_time": "8:39:43", "remaining_time": "0:02:09", "throughput": 1155.46, "total_tokens": 36031648}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.0109, "lr": 1.1991872198297004e-05, "epoch": 10.51471558664379, "percentage": 99.6, "elapsed_time": "8:39:45", "remaining_time": "0:02:05", "throughput": 1155.52, "total_tokens": 36035936}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.0032, "lr": 1.1258610377384847e-05, "epoch": 10.516035370199287, "percentage": 99.61, "elapsed_time": "8:39:47", "remaining_time": "0:02:01", "throughput": 1155.59, "total_tokens": 36040480}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.012, "lr": 1.0548478705268982e-05, "epoch": 10.517355153754785, "percentage": 99.62, "elapsed_time": "8:39:49", "remaining_time": "0:01:57", "throughput": 1155.66, "total_tokens": 36044896}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.0069, "lr": 9.86147729147846e-06, "epoch": 10.518674937310282, "percentage": 99.64, "elapsed_time": "8:39:51", "remaining_time": "0:01:53", "throughput": 1155.73, "total_tokens": 36049344}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.011, "lr": 9.197606241928557e-06, "epoch": 10.519994720865778, "percentage": 99.65, "elapsed_time": "8:39:53", "remaining_time": "0:01:49", "throughput": 1155.8, "total_tokens": 36053792}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.0057, "lr": 8.556865659004042e-06, "epoch": 10.521314504421275, "percentage": 99.66, "elapsed_time": "8:39:55", "remaining_time": "0:01:45", "throughput": 1155.87, "total_tokens": 36058272}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.0203, "lr": 7.939255641525867e-06, "epoch": 10.522634287976771, "percentage": 99.67, "elapsed_time": "8:39:57", "remaining_time": "0:01:41", "throughput": 1155.95, "total_tokens": 36062880}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.0168, "lr": 7.344776284751164e-06, "epoch": 10.523954071532268, "percentage": 99.69, "elapsed_time": "8:39:59", "remaining_time": "0:01:37", "throughput": 1156.02, "total_tokens": 36067488}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.0043, "lr": 6.773427680323296e-06, "epoch": 10.525273855087766, "percentage": 99.7, "elapsed_time": "8:40:01", "remaining_time": "0:01:33", "throughput": 1156.1, "total_tokens": 36072064}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0181, "lr": 6.225209916355112e-06, "epoch": 10.526593638643263, "percentage": 99.71, "elapsed_time": "8:40:03", "remaining_time": "0:01:29", "throughput": 1156.16, "total_tokens": 36076480}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.0154, "lr": 5.7001230774123e-06, "epoch": 10.52791342219876, "percentage": 99.72, "elapsed_time": "8:40:05", "remaining_time": "0:01:26", "throughput": 1156.24, "total_tokens": 36081184}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.0188, "lr": 5.198167244446772e-06, "epoch": 10.529233205754256, "percentage": 99.74, "elapsed_time": "8:40:07", "remaining_time": "0:01:22", "throughput": 1156.31, "total_tokens": 36085696}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.0049, "lr": 4.71934249487993e-06, "epoch": 10.530552989309752, "percentage": 99.75, "elapsed_time": "8:40:09", "remaining_time": "0:01:18", "throughput": 1156.38, "total_tokens": 36090016}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0275, "lr": 4.2636489025527075e-06, "epoch": 10.53187277286525, "percentage": 99.76, "elapsed_time": "8:40:11", "remaining_time": "0:01:14", "throughput": 1156.45, "total_tokens": 36094368}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0087, "lr": 3.831086537742223e-06, "epoch": 10.533192556420747, "percentage": 99.78, "elapsed_time": "8:40:13", "remaining_time": "0:01:10", "throughput": 1156.52, "total_tokens": 36099008}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.0079, "lr": 3.4216554671451236e-06, "epoch": 10.534512339976244, "percentage": 99.79, "elapsed_time": "8:40:15", "remaining_time": "0:01:06", "throughput": 1156.59, "total_tokens": 36103584}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0123, "lr": 3.035355753894242e-06, "epoch": 10.53583212353174, "percentage": 99.8, "elapsed_time": "8:40:17", "remaining_time": "0:01:02", "throughput": 1156.66, "total_tokens": 36108000}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0062, "lr": 2.6721874575752477e-06, "epoch": 10.537151907087237, "percentage": 99.81, "elapsed_time": "8:40:19", "remaining_time": "0:00:58", "throughput": 1156.74, "total_tokens": 36112768}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0059, "lr": 2.3321506341933418e-06, "epoch": 10.538471690642735, "percentage": 99.83, "elapsed_time": "8:40:21", "remaining_time": "0:00:54", "throughput": 1156.82, "total_tokens": 36117440}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0107, "lr": 2.0152453361732546e-06, "epoch": 10.539791474198232, "percentage": 99.84, "elapsed_time": "8:40:23", "remaining_time": "0:00:50", "throughput": 1156.89, "total_tokens": 36121856}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0182, "lr": 1.7214716123925554e-06, "epoch": 10.541111257753728, "percentage": 99.85, "elapsed_time": "8:40:25", "remaining_time": "0:00:46", "throughput": 1156.96, "total_tokens": 36126304}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0232, "lr": 1.4508295081649968e-06, "epoch": 10.542431041309225, "percentage": 99.86, "elapsed_time": "8:40:27", "remaining_time": "0:00:42", "throughput": 1157.03, "total_tokens": 36130688}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0077, "lr": 1.2033190652238623e-06, "epoch": 10.543750824864722, "percentage": 99.88, "elapsed_time": "8:40:29", "remaining_time": "0:00:39", "throughput": 1157.11, "total_tokens": 36135424}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.0106, "lr": 9.78940321721966e-07, "epoch": 10.545070608420218, "percentage": 99.89, "elapsed_time": "8:40:31", "remaining_time": "0:00:35", "throughput": 1157.17, "total_tokens": 36139776}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.0085, "lr": 7.776933122816132e-07, "epoch": 10.546390391975716, "percentage": 99.9, "elapsed_time": "8:40:33", "remaining_time": "0:00:31", "throughput": 1157.26, "total_tokens": 36144864}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.0098, "lr": 5.99578067927986e-07, "epoch": 10.547710175531213, "percentage": 99.91, "elapsed_time": "8:40:35", "remaining_time": "0:00:27", "throughput": 1157.34, "total_tokens": 36149536}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0077, "lr": 4.445946161224512e-07, "epoch": 10.54902995908671, "percentage": 99.92, "elapsed_time": "8:40:37", "remaining_time": "0:00:23", "throughput": 1157.42, "total_tokens": 36154304}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0163, "lr": 3.127429807792126e-07, "epoch": 10.550349742642206, "percentage": 99.94, "elapsed_time": "8:40:38", "remaining_time": "0:00:19", "throughput": 1157.48, "total_tokens": 36158656}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.0049, "lr": 2.040231822320049e-07, "epoch": 10.551669526197703, "percentage": 99.95, "elapsed_time": "8:40:40", "remaining_time": "0:00:15", "throughput": 1157.56, "total_tokens": 36163136}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0072, "lr": 1.1843523723409354e-07, "epoch": 10.552989309753201, "percentage": 99.96, "elapsed_time": "8:40:42", "remaining_time": "0:00:11", "throughput": 1157.62, "total_tokens": 36167456}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.0072, "lr": 5.597915897492811e-08, "epoch": 10.554309093308698, "percentage": 99.98, "elapsed_time": "8:40:44", "remaining_time": "0:00:07", "throughput": 1157.69, "total_tokens": 36171968}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0103, "lr": 1.6654957113448885e-08, "epoch": 10.555628876864194, "percentage": 99.99, "elapsed_time": "8:40:46", "remaining_time": "0:00:03", "throughput": 1157.77, "total_tokens": 36176544}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0205, "lr": 4.626377114735902e-10, "epoch": 10.55694866041969, "percentage": 100.0, "elapsed_time": "8:40:48", "remaining_time": "0:00:00", "throughput": 1157.84, "total_tokens": 36181120}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.11209341138601303, "epoch": 10.55694866041969, "percentage": 100.0, "elapsed_time": "8:42:04", "remaining_time": "0:00:00", "throughput": 1155.03, "total_tokens": 36181120}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 10.55694866041969, "percentage": 100.0, "elapsed_time": "8:42:06", "remaining_time": "0:00:00", "throughput": 1154.96, "total_tokens": 36181120}
|