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 1638528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fa099a59fe26630e3fbdf284c9cc9afdb889a5f5c46aa1e617178910e85a950
|
| 3 |
size 1638528
|
trainer_log.jsonl
CHANGED
|
@@ -8157,3 +8157,45 @@
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 1.9632065447422463e-05, "epoch": 122.82534775888718, "percentage": 99.49, "elapsed_time": "8:04:00", "remaining_time": "0:02:29", "throughput": 1866.71, "total_tokens": 54210272}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 1.8690637803880916e-05, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "8:04:03", "remaining_time": "0:02:25", "throughput": 1866.74, "total_tokens": 54217344}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 2.1381330490112305, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "8:04:15", "remaining_time": "0:02:26", "throughput": 1866.01, "total_tokens": 54217344}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0, "lr": 1.9632065447422463e-05, "epoch": 122.82534775888718, "percentage": 99.49, "elapsed_time": "8:04:00", "remaining_time": "0:02:29", "throughput": 1866.71, "total_tokens": 54210272}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0, "lr": 1.8690637803880916e-05, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "8:04:03", "remaining_time": "0:02:25", "throughput": 1866.74, "total_tokens": 54217344}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 2.1381330490112305, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "8:04:15", "remaining_time": "0:02:26", "throughput": 1866.01, "total_tokens": 54217344}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0, "lr": 1.7772339163019123e-05, "epoch": 122.85625965996908, "percentage": 99.51, "elapsed_time": "8:04:19", "remaining_time": "0:02:22", "throughput": 1865.97, "total_tokens": 54224032}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.0, "lr": 1.6877169666457138e-05, "epoch": 122.87171561051005, "percentage": 99.52, "elapsed_time": "8:04:22", "remaining_time": "0:02:18", "throughput": 1865.99, "total_tokens": 54230592}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0, "lr": 1.6005129452234532e-05, "epoch": 122.887171561051, "percentage": 99.54, "elapsed_time": "8:04:26", "remaining_time": "0:02:15", "throughput": 1866.01, "total_tokens": 54237856}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0, "lr": 1.5156218654843733e-05, "epoch": 122.90262751159196, "percentage": 99.55, "elapsed_time": "8:04:29", "remaining_time": "0:02:11", "throughput": 1866.03, "total_tokens": 54244800}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0, "lr": 1.4330437405196683e-05, "epoch": 122.91808346213293, "percentage": 99.56, "elapsed_time": "8:04:32", "remaining_time": "0:02:07", "throughput": 1866.05, "total_tokens": 54251776}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.0, "lr": 1.352778583062486e-05, "epoch": 122.93353941267388, "percentage": 99.58, "elapsed_time": "8:04:36", "remaining_time": "0:02:04", "throughput": 1866.08, "total_tokens": 54258912}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0012, "lr": 1.2748264054929237e-05, "epoch": 122.94899536321483, "percentage": 99.59, "elapsed_time": "8:04:39", "remaining_time": "0:02:00", "throughput": 1866.09, "total_tokens": 54265440}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.0, "lr": 1.1991872198297004e-05, "epoch": 122.9644513137558, "percentage": 99.6, "elapsed_time": "8:04:43", "remaining_time": "0:01:56", "throughput": 1866.12, "total_tokens": 54272608}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.0012, "lr": 1.1258610377384847e-05, "epoch": 122.97990726429676, "percentage": 99.61, "elapsed_time": "8:04:46", "remaining_time": "0:01:53", "throughput": 1866.14, "total_tokens": 54279200}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0, "lr": 1.0548478705268982e-05, "epoch": 122.99536321483771, "percentage": 99.62, "elapsed_time": "8:04:49", "remaining_time": "0:01:49", "throughput": 1866.18, "total_tokens": 54286944}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.0, "lr": 9.86147729147846e-06, "epoch": 123.00927357032458, "percentage": 99.64, "elapsed_time": "8:04:53", "remaining_time": "0:01:45", "throughput": 1866.17, "total_tokens": 54292800}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.0013, "lr": 9.197606241928557e-06, "epoch": 123.02472952086553, "percentage": 99.65, "elapsed_time": "8:04:56", "remaining_time": "0:01:42", "throughput": 1866.18, "total_tokens": 54299200}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.0013, "lr": 8.556865659004042e-06, "epoch": 123.04018547140649, "percentage": 99.66, "elapsed_time": "8:04:59", "remaining_time": "0:01:38", "throughput": 1866.2, "total_tokens": 54306112}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.0, "lr": 7.939255641525867e-06, "epoch": 123.05564142194746, "percentage": 99.67, "elapsed_time": "8:05:03", "remaining_time": "0:01:34", "throughput": 1866.22, "total_tokens": 54312704}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.0, "lr": 7.344776284751164e-06, "epoch": 123.07109737248841, "percentage": 99.69, "elapsed_time": "8:05:06", "remaining_time": "0:01:31", "throughput": 1866.24, "total_tokens": 54319712}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.0, "lr": 6.773427680323296e-06, "epoch": 123.08655332302936, "percentage": 99.7, "elapsed_time": "8:05:09", "remaining_time": "0:01:27", "throughput": 1866.26, "total_tokens": 54326624}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0, "lr": 6.225209916355112e-06, "epoch": 123.10200927357033, "percentage": 99.71, "elapsed_time": "8:05:13", "remaining_time": "0:01:23", "throughput": 1866.27, "total_tokens": 54333184}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.0, "lr": 5.7001230774123e-06, "epoch": 123.11746522411129, "percentage": 99.72, "elapsed_time": "8:05:16", "remaining_time": "0:01:20", "throughput": 1866.29, "total_tokens": 54339712}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.0, "lr": 5.198167244446772e-06, "epoch": 123.13292117465224, "percentage": 99.74, "elapsed_time": "8:05:19", "remaining_time": "0:01:16", "throughput": 1866.31, "total_tokens": 54346560}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.0, "lr": 4.71934249487993e-06, "epoch": 123.14837712519319, "percentage": 99.75, "elapsed_time": "8:05:23", "remaining_time": "0:01:12", "throughput": 1866.34, "total_tokens": 54353728}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0, "lr": 4.2636489025527075e-06, "epoch": 123.16383307573416, "percentage": 99.76, "elapsed_time": "8:05:26", "remaining_time": "0:01:09", "throughput": 1866.36, "total_tokens": 54360512}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0, "lr": 3.831086537742223e-06, "epoch": 123.17928902627511, "percentage": 99.78, "elapsed_time": "8:05:29", "remaining_time": "0:01:05", "throughput": 1866.38, "total_tokens": 54367264}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.0, "lr": 3.4216554671451236e-06, "epoch": 123.19474497681607, "percentage": 99.79, "elapsed_time": "8:05:33", "remaining_time": "0:01:02", "throughput": 1866.39, "total_tokens": 54373824}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0, "lr": 3.035355753894242e-06, "epoch": 123.21020092735704, "percentage": 99.8, "elapsed_time": "8:05:36", "remaining_time": "0:00:58", "throughput": 1866.41, "total_tokens": 54380640}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0, "lr": 2.6721874575752477e-06, "epoch": 123.22565687789799, "percentage": 99.81, "elapsed_time": "8:05:39", "remaining_time": "0:00:54", "throughput": 1866.42, "total_tokens": 54387328}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0, "lr": 2.3321506341933418e-06, "epoch": 123.24111282843894, "percentage": 99.83, "elapsed_time": "8:05:43", "remaining_time": "0:00:51", "throughput": 1866.43, "total_tokens": 54393760}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0, "lr": 2.0152453361732546e-06, "epoch": 123.25656877897991, "percentage": 99.84, "elapsed_time": "8:05:46", "remaining_time": "0:00:47", "throughput": 1866.45, "total_tokens": 54400480}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0, "lr": 1.7214716123925554e-06, "epoch": 123.27202472952087, "percentage": 99.85, "elapsed_time": "8:05:49", "remaining_time": "0:00:43", "throughput": 1866.47, "total_tokens": 54407040}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0, "lr": 1.4508295081649968e-06, "epoch": 123.28748068006182, "percentage": 99.86, "elapsed_time": "8:05:52", "remaining_time": "0:00:40", "throughput": 1866.48, "total_tokens": 54413472}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0, "lr": 1.2033190652238623e-06, "epoch": 123.30293663060279, "percentage": 99.88, "elapsed_time": "8:05:56", "remaining_time": "0:00:36", "throughput": 1866.5, "total_tokens": 54420064}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.0, "lr": 9.78940321721966e-07, "epoch": 123.31839258114374, "percentage": 99.89, "elapsed_time": "8:05:59", "remaining_time": "0:00:32", "throughput": 1866.52, "total_tokens": 54426752}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.0012, "lr": 7.776933122816132e-07, "epoch": 123.3338485316847, "percentage": 99.9, "elapsed_time": "8:06:02", "remaining_time": "0:00:29", "throughput": 1866.53, "total_tokens": 54433344}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.0, "lr": 5.99578067927986e-07, "epoch": 123.34930448222566, "percentage": 99.91, "elapsed_time": "8:06:06", "remaining_time": "0:00:25", "throughput": 1866.55, "total_tokens": 54440000}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0, "lr": 4.445946161224512e-07, "epoch": 123.36476043276662, "percentage": 99.92, "elapsed_time": "8:06:09", "remaining_time": "0:00:21", "throughput": 1866.58, "total_tokens": 54447232}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0011, "lr": 3.127429807792126e-07, "epoch": 123.38021638330757, "percentage": 99.94, "elapsed_time": "8:06:13", "remaining_time": "0:00:18", "throughput": 1866.61, "total_tokens": 54454752}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.0, "lr": 2.040231822320049e-07, "epoch": 123.39567233384854, "percentage": 99.95, "elapsed_time": "8:06:16", "remaining_time": "0:00:14", "throughput": 1866.64, "total_tokens": 54461952}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0, "lr": 1.1843523723409354e-07, "epoch": 123.41112828438949, "percentage": 99.96, "elapsed_time": "8:06:19", "remaining_time": "0:00:10", "throughput": 1866.68, "total_tokens": 54469504}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.0, "lr": 5.597915897492811e-08, "epoch": 123.42658423493044, "percentage": 99.98, "elapsed_time": "8:06:23", "remaining_time": "0:00:07", "throughput": 1866.7, "total_tokens": 54476608}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0, "lr": 1.6654957113448885e-08, "epoch": 123.44204018547141, "percentage": 99.99, "elapsed_time": "8:06:26", "remaining_time": "0:00:03", "throughput": 1866.73, "total_tokens": 54483712}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0, "lr": 4.626377114735902e-10, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "8:06:30", "remaining_time": "0:00:00", "throughput": 1866.75, "total_tokens": 54490336}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 2.137033700942993, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "8:06:41", "remaining_time": "0:00:00", "throughput": 1866.02, "total_tokens": 54490336}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "8:06:42", "remaining_time": "0:00:00", "throughput": 1865.96, "total_tokens": 54490336}
|