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 sha256:736629ff5be66b0e4e54bfabccdc81b329c642d532320383a2bb131c4dfaf5ba
|
3 |
size 460928
|
trainer_log.jsonl
CHANGED
@@ -8157,3 +8157,45 @@
|
|
8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.072, "lr": 1.9632065447422463e-05, "epoch": 1.94442137150954, "percentage": 99.49, "elapsed_time": "1 day, 2:28:09", "remaining_time": "0:08:10", "throughput": 541.41, "total_tokens": 51590464}
|
8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0663, "lr": 1.8690637803880916e-05, "epoch": 1.9446656731732344, "percentage": 99.5, "elapsed_time": "1 day, 2:28:11", "remaining_time": "0:07:58", "throughput": 541.46, "total_tokens": 51597120}
|
8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.08352842926979065, "epoch": 1.9446656731732344, "percentage": 99.5, "elapsed_time": "1 day, 2:34:54", "remaining_time": "0:08:00", "throughput": 539.19, "total_tokens": 51597120}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.072, "lr": 1.9632065447422463e-05, "epoch": 1.94442137150954, "percentage": 99.49, "elapsed_time": "1 day, 2:28:09", "remaining_time": "0:08:10", "throughput": 541.41, "total_tokens": 51590464}
|
8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0663, "lr": 1.8690637803880916e-05, "epoch": 1.9446656731732344, "percentage": 99.5, "elapsed_time": "1 day, 2:28:11", "remaining_time": "0:07:58", "throughput": 541.46, "total_tokens": 51597120}
|
8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.08352842926979065, "epoch": 1.9446656731732344, "percentage": 99.5, "elapsed_time": "1 day, 2:34:54", "remaining_time": "0:08:00", "throughput": 539.19, "total_tokens": 51597120}
|
8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.094, "lr": 1.7772339163019123e-05, "epoch": 1.9449099748369285, "percentage": 99.51, "elapsed_time": "1 day, 2:34:58", "remaining_time": "0:07:48", "throughput": 539.24, "total_tokens": 51604032}
|
8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.0687, "lr": 1.6877169666457138e-05, "epoch": 1.945154276500623, "percentage": 99.52, "elapsed_time": "1 day, 2:35:00", "remaining_time": "0:07:36", "throughput": 539.29, "total_tokens": 51610464}
|
8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0829, "lr": 1.6005129452234532e-05, "epoch": 1.9453985781643173, "percentage": 99.54, "elapsed_time": "1 day, 2:35:01", "remaining_time": "0:07:24", "throughput": 539.35, "total_tokens": 51616928}
|
8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0924, "lr": 1.5156218654843733e-05, "epoch": 1.9456428798280117, "percentage": 99.55, "elapsed_time": "1 day, 2:35:03", "remaining_time": "0:07:12", "throughput": 539.41, "total_tokens": 51623520}
|
8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0877, "lr": 1.4330437405196683e-05, "epoch": 1.945887181491706, "percentage": 99.56, "elapsed_time": "1 day, 2:35:05", "remaining_time": "0:07:00", "throughput": 539.47, "total_tokens": 51630240}
|
8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.1067, "lr": 1.352778583062486e-05, "epoch": 1.9461314831554004, "percentage": 99.58, "elapsed_time": "1 day, 2:35:07", "remaining_time": "0:06:48", "throughput": 539.53, "total_tokens": 51637152}
|
8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0802, "lr": 1.2748264054929237e-05, "epoch": 1.9463757848190946, "percentage": 99.59, "elapsed_time": "1 day, 2:35:09", "remaining_time": "0:06:36", "throughput": 539.59, "total_tokens": 51643648}
|
8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.098, "lr": 1.1991872198297004e-05, "epoch": 1.946620086482789, "percentage": 99.6, "elapsed_time": "1 day, 2:35:11", "remaining_time": "0:06:24", "throughput": 539.65, "total_tokens": 51650272}
|
8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.1195, "lr": 1.1258610377384847e-05, "epoch": 1.9468643881464833, "percentage": 99.61, "elapsed_time": "1 day, 2:35:13", "remaining_time": "0:06:12", "throughput": 539.71, "total_tokens": 51657024}
|
8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0853, "lr": 1.0548478705268982e-05, "epoch": 1.9471086898101775, "percentage": 99.62, "elapsed_time": "1 day, 2:35:15", "remaining_time": "0:06:00", "throughput": 539.76, "total_tokens": 51663424}
|
8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.0634, "lr": 9.86147729147846e-06, "epoch": 1.9473529914738719, "percentage": 99.64, "elapsed_time": "1 day, 2:35:17", "remaining_time": "0:05:48", "throughput": 539.82, "total_tokens": 51669824}
|
8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.0862, "lr": 9.197606241928557e-06, "epoch": 1.9475972931375662, "percentage": 99.65, "elapsed_time": "1 day, 2:35:19", "remaining_time": "0:05:36", "throughput": 539.88, "total_tokens": 51676448}
|
8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.0802, "lr": 8.556865659004042e-06, "epoch": 1.9478415948012606, "percentage": 99.66, "elapsed_time": "1 day, 2:35:21", "remaining_time": "0:05:24", "throughput": 539.94, "total_tokens": 51683328}
|
8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.0697, "lr": 7.939255641525867e-06, "epoch": 1.948085896464955, "percentage": 99.67, "elapsed_time": "1 day, 2:35:23", "remaining_time": "0:05:12", "throughput": 539.99, "total_tokens": 51689248}
|
8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.1147, "lr": 7.344776284751164e-06, "epoch": 1.9483301981286494, "percentage": 99.69, "elapsed_time": "1 day, 2:35:24", "remaining_time": "0:05:00", "throughput": 540.05, "total_tokens": 51695968}
|
8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.055, "lr": 6.773427680323296e-06, "epoch": 1.9485744997923435, "percentage": 99.7, "elapsed_time": "1 day, 2:35:26", "remaining_time": "0:04:48", "throughput": 540.11, "total_tokens": 51702816}
|
8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0933, "lr": 6.225209916355112e-06, "epoch": 1.948818801456038, "percentage": 99.71, "elapsed_time": "1 day, 2:35:28", "remaining_time": "0:04:36", "throughput": 540.16, "total_tokens": 51709184}
|
8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.0884, "lr": 5.7001230774123e-06, "epoch": 1.9490631031197323, "percentage": 99.72, "elapsed_time": "1 day, 2:35:30", "remaining_time": "0:04:23", "throughput": 540.22, "total_tokens": 51715904}
|
8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.1167, "lr": 5.198167244446772e-06, "epoch": 1.9493074047834265, "percentage": 99.74, "elapsed_time": "1 day, 2:35:32", "remaining_time": "0:04:11", "throughput": 540.28, "total_tokens": 51722016}
|
8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.0694, "lr": 4.71934249487993e-06, "epoch": 1.9495517064471208, "percentage": 99.75, "elapsed_time": "1 day, 2:35:34", "remaining_time": "0:03:59", "throughput": 540.33, "total_tokens": 51728128}
|
8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0759, "lr": 4.2636489025527075e-06, "epoch": 1.9497960081108152, "percentage": 99.76, "elapsed_time": "1 day, 2:35:36", "remaining_time": "0:03:47", "throughput": 540.38, "total_tokens": 51734368}
|
8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0773, "lr": 3.831086537742223e-06, "epoch": 1.9500403097745096, "percentage": 99.78, "elapsed_time": "1 day, 2:35:38", "remaining_time": "0:03:35", "throughput": 540.44, "total_tokens": 51740768}
|
8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.1004, "lr": 3.4216554671451236e-06, "epoch": 1.950284611438204, "percentage": 99.79, "elapsed_time": "1 day, 2:35:40", "remaining_time": "0:03:23", "throughput": 540.5, "total_tokens": 51748000}
|
8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.078, "lr": 3.035355753894242e-06, "epoch": 1.9505289131018984, "percentage": 99.8, "elapsed_time": "1 day, 2:35:42", "remaining_time": "0:03:11", "throughput": 540.56, "total_tokens": 51754432}
|
8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0724, "lr": 2.6721874575752477e-06, "epoch": 1.9507732147655925, "percentage": 99.81, "elapsed_time": "1 day, 2:35:44", "remaining_time": "0:02:59", "throughput": 540.62, "total_tokens": 51761120}
|
8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0877, "lr": 2.3321506341933418e-06, "epoch": 1.951017516429287, "percentage": 99.83, "elapsed_time": "1 day, 2:35:46", "remaining_time": "0:02:47", "throughput": 540.68, "total_tokens": 51767712}
|
8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0735, "lr": 2.0152453361732546e-06, "epoch": 1.951261818092981, "percentage": 99.84, "elapsed_time": "1 day, 2:35:47", "remaining_time": "0:02:35", "throughput": 540.73, "total_tokens": 51773824}
|
8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0753, "lr": 1.7214716123925554e-06, "epoch": 1.9515061197566754, "percentage": 99.85, "elapsed_time": "1 day, 2:35:49", "remaining_time": "0:02:23", "throughput": 540.78, "total_tokens": 51780064}
|
8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0831, "lr": 1.4508295081649968e-06, "epoch": 1.9517504214203698, "percentage": 99.86, "elapsed_time": "1 day, 2:35:51", "remaining_time": "0:02:11", "throughput": 540.84, "total_tokens": 51786752}
|
8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0903, "lr": 1.2033190652238623e-06, "epoch": 1.9519947230840642, "percentage": 99.88, "elapsed_time": "1 day, 2:35:53", "remaining_time": "0:01:59", "throughput": 540.9, "total_tokens": 51793056}
|
8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.0906, "lr": 9.78940321721966e-07, "epoch": 1.9522390247477586, "percentage": 99.89, "elapsed_time": "1 day, 2:35:55", "remaining_time": "0:01:47", "throughput": 540.96, "total_tokens": 51799552}
|
8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.0659, "lr": 7.776933122816132e-07, "epoch": 1.952483326411453, "percentage": 99.9, "elapsed_time": "1 day, 2:35:57", "remaining_time": "0:01:35", "throughput": 541.01, "total_tokens": 51805824}
|
8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.0938, "lr": 5.99578067927986e-07, "epoch": 1.9527276280751473, "percentage": 99.91, "elapsed_time": "1 day, 2:35:59", "remaining_time": "0:01:23", "throughput": 541.07, "total_tokens": 51812544}
|
8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0606, "lr": 4.445946161224512e-07, "epoch": 1.9529719297388415, "percentage": 99.92, "elapsed_time": "1 day, 2:36:01", "remaining_time": "0:01:11", "throughput": 541.13, "total_tokens": 51819520}
|
8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0719, "lr": 3.127429807792126e-07, "epoch": 1.9532162314025359, "percentage": 99.94, "elapsed_time": "1 day, 2:36:03", "remaining_time": "0:00:59", "throughput": 541.19, "total_tokens": 51826336}
|
8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.081, "lr": 2.040231822320049e-07, "epoch": 1.95346053306623, "percentage": 99.95, "elapsed_time": "1 day, 2:36:05", "remaining_time": "0:00:47", "throughput": 541.25, "total_tokens": 51833216}
|
8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0891, "lr": 1.1843523723409354e-07, "epoch": 1.9537048347299244, "percentage": 99.96, "elapsed_time": "1 day, 2:36:07", "remaining_time": "0:00:35", "throughput": 541.31, "total_tokens": 51840096}
|
8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.0682, "lr": 5.597915897492811e-08, "epoch": 1.9539491363936188, "percentage": 99.98, "elapsed_time": "1 day, 2:36:09", "remaining_time": "0:00:23", "throughput": 541.37, "total_tokens": 51846688}
|
8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0871, "lr": 1.6654957113448885e-08, "epoch": 1.9541934380573132, "percentage": 99.99, "elapsed_time": "1 day, 2:36:11", "remaining_time": "0:00:11", "throughput": 541.42, "total_tokens": 51852640}
|
8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0783, "lr": 4.626377114735902e-10, "epoch": 1.9544377397210075, "percentage": 100.0, "elapsed_time": "1 day, 2:36:13", "remaining_time": "0:00:00", "throughput": 541.48, "total_tokens": 51858816}
|
8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.08348309993743896, "epoch": 1.9544377397210075, "percentage": 100.0, "elapsed_time": "1 day, 2:42:55", "remaining_time": "0:00:00", "throughput": 539.21, "total_tokens": 51858816}
|
8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 1.9544377397210075, "percentage": 100.0, "elapsed_time": "1 day, 2:42:57", "remaining_time": "0:00:00", "throughput": 539.2, "total_tokens": 51858816}
|