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 sha256:6e6a5aded8f7411f287fb24aa11cc860f0cee712a28e2e88592feb7750ca87d6
|
3 |
size 460928
|
trainer_log.jsonl
CHANGED
@@ -8157,3 +8157,45 @@
|
|
8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0006, "lr": 1.9632065447422463e-05, "epoch": 122.82534775888718, "percentage": 99.49, "elapsed_time": "4:51:12", "remaining_time": "0:01:30", "throughput": 3478.33, "total_tokens": 60774960}
|
8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0005, "lr": 1.8690637803880916e-05, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "4:51:14", "remaining_time": "0:01:27", "throughput": 3478.4, "total_tokens": 60782960}
|
8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.4524598121643066, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "4:51:21", "remaining_time": "0:01:27", "throughput": 3476.99, "total_tokens": 60782960}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 0.0006, "lr": 1.9632065447422463e-05, "epoch": 122.82534775888718, "percentage": 99.49, "elapsed_time": "4:51:12", "remaining_time": "0:01:30", "throughput": 3478.33, "total_tokens": 60774960}
|
8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.0005, "lr": 1.8690637803880916e-05, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "4:51:14", "remaining_time": "0:01:27", "throughput": 3478.4, "total_tokens": 60782960}
|
8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 1.4524598121643066, "epoch": 122.84080370942813, "percentage": 99.5, "elapsed_time": "4:51:21", "remaining_time": "0:01:27", "throughput": 3476.99, "total_tokens": 60782960}
|
8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 0.0005, "lr": 1.7772339163019123e-05, "epoch": 122.85625965996908, "percentage": 99.51, "elapsed_time": "4:51:25", "remaining_time": "0:01:25", "throughput": 3476.7, "total_tokens": 60790352}
|
8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.0005, "lr": 1.6877169666457138e-05, "epoch": 122.87171561051005, "percentage": 99.52, "elapsed_time": "4:51:27", "remaining_time": "0:01:23", "throughput": 3476.74, "total_tokens": 60797808}
|
8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.0008, "lr": 1.6005129452234532e-05, "epoch": 122.887171561051, "percentage": 99.54, "elapsed_time": "4:51:29", "remaining_time": "0:01:21", "throughput": 3476.8, "total_tokens": 60805808}
|
8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.0006, "lr": 1.5156218654843733e-05, "epoch": 122.90262751159196, "percentage": 99.55, "elapsed_time": "4:51:30", "remaining_time": "0:01:19", "throughput": 3476.85, "total_tokens": 60813552}
|
8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.0007, "lr": 1.4330437405196683e-05, "epoch": 122.91808346213293, "percentage": 99.56, "elapsed_time": "4:51:32", "remaining_time": "0:01:16", "throughput": 3476.9, "total_tokens": 60821200}
|
8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.0012, "lr": 1.352778583062486e-05, "epoch": 122.93353941267388, "percentage": 99.58, "elapsed_time": "4:51:34", "remaining_time": "0:01:14", "throughput": 3476.96, "total_tokens": 60829232}
|
8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.0016, "lr": 1.2748264054929237e-05, "epoch": 122.94899536321483, "percentage": 99.59, "elapsed_time": "4:51:36", "remaining_time": "0:01:12", "throughput": 3477.0, "total_tokens": 60836720}
|
8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.001, "lr": 1.1991872198297004e-05, "epoch": 122.9644513137558, "percentage": 99.6, "elapsed_time": "4:51:38", "remaining_time": "0:01:10", "throughput": 3477.06, "total_tokens": 60844656}
|
8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.0006, "lr": 1.1258610377384847e-05, "epoch": 122.97990726429676, "percentage": 99.61, "elapsed_time": "4:51:40", "remaining_time": "0:01:08", "throughput": 3477.11, "total_tokens": 60852336}
|
8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.0007, "lr": 1.0548478705268982e-05, "epoch": 122.99536321483771, "percentage": 99.62, "elapsed_time": "4:51:42", "remaining_time": "0:01:05", "throughput": 3477.22, "total_tokens": 60861072}
|
8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.0005, "lr": 9.86147729147846e-06, "epoch": 123.00927357032458, "percentage": 99.64, "elapsed_time": "4:51:45", "remaining_time": "0:01:03", "throughput": 3477.15, "total_tokens": 60867632}
|
8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.0008, "lr": 9.197606241928557e-06, "epoch": 123.02472952086553, "percentage": 99.65, "elapsed_time": "4:51:47", "remaining_time": "0:01:01", "throughput": 3477.17, "total_tokens": 60874832}
|
8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.0015, "lr": 8.556865659004042e-06, "epoch": 123.04018547140649, "percentage": 99.66, "elapsed_time": "4:51:48", "remaining_time": "0:00:59", "throughput": 3477.22, "total_tokens": 60882512}
|
8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.0007, "lr": 7.939255641525867e-06, "epoch": 123.05564142194746, "percentage": 99.67, "elapsed_time": "4:51:50", "remaining_time": "0:00:57", "throughput": 3477.25, "total_tokens": 60890000}
|
8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.0007, "lr": 7.344776284751164e-06, "epoch": 123.07109737248841, "percentage": 99.69, "elapsed_time": "4:51:52", "remaining_time": "0:00:54", "throughput": 3477.3, "total_tokens": 60897680}
|
8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.0009, "lr": 6.773427680323296e-06, "epoch": 123.08655332302936, "percentage": 99.7, "elapsed_time": "4:51:54", "remaining_time": "0:00:52", "throughput": 3477.36, "total_tokens": 60905648}
|
8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.0007, "lr": 6.225209916355112e-06, "epoch": 123.10200927357033, "percentage": 99.71, "elapsed_time": "4:51:56", "remaining_time": "0:00:50", "throughput": 3477.39, "total_tokens": 60913008}
|
8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.001, "lr": 5.7001230774123e-06, "epoch": 123.11746522411129, "percentage": 99.72, "elapsed_time": "4:51:58", "remaining_time": "0:00:48", "throughput": 3477.43, "total_tokens": 60920432}
|
8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.0006, "lr": 5.198167244446772e-06, "epoch": 123.13292117465224, "percentage": 99.74, "elapsed_time": "4:52:00", "remaining_time": "0:00:46", "throughput": 3477.47, "total_tokens": 60928144}
|
8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.0006, "lr": 4.71934249487993e-06, "epoch": 123.14837712519319, "percentage": 99.75, "elapsed_time": "4:52:02", "remaining_time": "0:00:43", "throughput": 3477.53, "total_tokens": 60936016}
|
8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.0009, "lr": 4.2636489025527075e-06, "epoch": 123.16383307573416, "percentage": 99.76, "elapsed_time": "4:52:04", "remaining_time": "0:00:41", "throughput": 3477.58, "total_tokens": 60943632}
|
8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.0006, "lr": 3.831086537742223e-06, "epoch": 123.17928902627511, "percentage": 99.78, "elapsed_time": "4:52:06", "remaining_time": "0:00:39", "throughput": 3477.61, "total_tokens": 60951120}
|
8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.0005, "lr": 3.4216554671451236e-06, "epoch": 123.19474497681607, "percentage": 99.79, "elapsed_time": "4:52:08", "remaining_time": "0:00:37", "throughput": 3477.65, "total_tokens": 60958576}
|
8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.0006, "lr": 3.035355753894242e-06, "epoch": 123.21020092735704, "percentage": 99.8, "elapsed_time": "4:52:10", "remaining_time": "0:00:35", "throughput": 3477.69, "total_tokens": 60966224}
|
8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.0007, "lr": 2.6721874575752477e-06, "epoch": 123.22565687789799, "percentage": 99.81, "elapsed_time": "4:52:12", "remaining_time": "0:00:32", "throughput": 3477.73, "total_tokens": 60973744}
|
8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.0009, "lr": 2.3321506341933418e-06, "epoch": 123.24111282843894, "percentage": 99.83, "elapsed_time": "4:52:14", "remaining_time": "0:00:30", "throughput": 3477.75, "total_tokens": 60980944}
|
8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.0006, "lr": 2.0152453361732546e-06, "epoch": 123.25656877897991, "percentage": 99.84, "elapsed_time": "4:52:16", "remaining_time": "0:00:28", "throughput": 3477.8, "total_tokens": 60988752}
|
8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.0008, "lr": 1.7214716123925554e-06, "epoch": 123.27202472952087, "percentage": 99.85, "elapsed_time": "4:52:18", "remaining_time": "0:00:26", "throughput": 3477.83, "total_tokens": 60996112}
|
8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.0005, "lr": 1.4508295081649968e-06, "epoch": 123.28748068006182, "percentage": 99.86, "elapsed_time": "4:52:20", "remaining_time": "0:00:24", "throughput": 3477.85, "total_tokens": 61003312}
|
8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.0009, "lr": 1.2033190652238623e-06, "epoch": 123.30293663060279, "percentage": 99.88, "elapsed_time": "4:52:22", "remaining_time": "0:00:21", "throughput": 3477.88, "total_tokens": 61010736}
|
8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.0006, "lr": 9.78940321721966e-07, "epoch": 123.31839258114374, "percentage": 99.89, "elapsed_time": "4:52:24", "remaining_time": "0:00:19", "throughput": 3477.92, "total_tokens": 61018256}
|
8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.0014, "lr": 7.776933122816132e-07, "epoch": 123.3338485316847, "percentage": 99.9, "elapsed_time": "4:52:26", "remaining_time": "0:00:17", "throughput": 3477.95, "total_tokens": 61025648}
|
8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.0008, "lr": 5.99578067927986e-07, "epoch": 123.34930448222566, "percentage": 99.91, "elapsed_time": "4:52:28", "remaining_time": "0:00:15", "throughput": 3477.99, "total_tokens": 61033136}
|
8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.0009, "lr": 4.445946161224512e-07, "epoch": 123.36476043276662, "percentage": 99.92, "elapsed_time": "4:52:30", "remaining_time": "0:00:13", "throughput": 3478.06, "total_tokens": 61041168}
|
8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.0012, "lr": 3.127429807792126e-07, "epoch": 123.38021638330757, "percentage": 99.94, "elapsed_time": "4:52:32", "remaining_time": "0:00:10", "throughput": 3478.14, "total_tokens": 61049584}
|
8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.0011, "lr": 2.040231822320049e-07, "epoch": 123.39567233384854, "percentage": 99.95, "elapsed_time": "4:52:34", "remaining_time": "0:00:08", "throughput": 3478.21, "total_tokens": 61057584}
|
8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.0006, "lr": 1.1843523723409354e-07, "epoch": 123.41112828438949, "percentage": 99.96, "elapsed_time": "4:52:36", "remaining_time": "0:00:06", "throughput": 3478.3, "total_tokens": 61066064}
|
8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.0005, "lr": 5.597915897492811e-08, "epoch": 123.42658423493044, "percentage": 99.98, "elapsed_time": "4:52:38", "remaining_time": "0:00:04", "throughput": 3478.36, "total_tokens": 61073936}
|
8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.0006, "lr": 1.6654957113448885e-08, "epoch": 123.44204018547141, "percentage": 99.99, "elapsed_time": "4:52:40", "remaining_time": "0:00:02", "throughput": 3478.42, "total_tokens": 61081840}
|
8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.0006, "lr": 4.626377114735902e-10, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "4:52:42", "remaining_time": "0:00:00", "throughput": 3478.45, "total_tokens": 61089232}
|
8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 1.4482582807540894, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "4:52:49", "remaining_time": "0:00:00", "throughput": 3477.05, "total_tokens": 61089232}
|
8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 123.45749613601237, "percentage": 100.0, "elapsed_time": "4:52:50", "remaining_time": "0:00:00", "throughput": 3476.74, "total_tokens": 61089232}
|