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:fb47f250022e78db8e0e1d4adf3574ece66b04f63a8b5f1356744d901df6e2f5
|
| 3 |
size 1638528
|
trainer_log.jsonl
CHANGED
|
@@ -8158,3 +8158,44 @@
|
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.3461, "lr": 1.8690637803880916e-05, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "2:16:04", "remaining_time": "0:00:41", "throughput": 1666.72, "total_tokens": 13608768}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.4369497299194336, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "2:16:06", "remaining_time": "0:00:41", "throughput": 1666.39, "total_tokens": 13608768}
|
| 8160 |
{"current_steps": 39805, "total_steps": 40000, "loss": 0.3405, "lr": 1.7772339163019123e-05, "epoch": 318.44176706827307, "percentage": 99.51, "elapsed_time": "2:16:08", "remaining_time": "0:00:40", "throughput": 1666.24, "total_tokens": 13610240}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 0.3461, "lr": 1.8690637803880916e-05, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "2:16:04", "remaining_time": "0:00:41", "throughput": 1666.72, "total_tokens": 13608768}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 0.4369497299194336, "epoch": 318.4016064257028, "percentage": 99.5, "elapsed_time": "2:16:06", "remaining_time": "0:00:41", "throughput": 1666.39, "total_tokens": 13608768}
|
| 8160 |
{"current_steps": 39805, "total_steps": 40000, "loss": 0.3405, "lr": 1.7772339163019123e-05, "epoch": 318.44176706827307, "percentage": 99.51, "elapsed_time": "2:16:08", "remaining_time": "0:00:40", "throughput": 1666.24, "total_tokens": 13610240}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 0.3501, "lr": 1.6877169666457138e-05, "epoch": 318.48192771084337, "percentage": 99.52, "elapsed_time": "2:16:09", "remaining_time": "0:00:38", "throughput": 1666.25, "total_tokens": 13611936}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 0.3294, "lr": 1.6005129452234532e-05, "epoch": 318.52208835341366, "percentage": 99.54, "elapsed_time": "2:16:10", "remaining_time": "0:00:37", "throughput": 1666.27, "total_tokens": 13613648}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 0.3611, "lr": 1.5156218654843733e-05, "epoch": 318.56224899598396, "percentage": 99.55, "elapsed_time": "2:16:11", "remaining_time": "0:00:36", "throughput": 1666.27, "total_tokens": 13615200}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 0.3516, "lr": 1.4330437405196683e-05, "epoch": 318.6024096385542, "percentage": 99.56, "elapsed_time": "2:16:12", "remaining_time": "0:00:35", "throughput": 1666.31, "total_tokens": 13617264}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 0.3543, "lr": 1.352778583062486e-05, "epoch": 318.6425702811245, "percentage": 99.58, "elapsed_time": "2:16:13", "remaining_time": "0:00:34", "throughput": 1666.32, "total_tokens": 13618928}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 0.3381, "lr": 1.2748264054929237e-05, "epoch": 318.6827309236948, "percentage": 99.59, "elapsed_time": "2:16:14", "remaining_time": "0:00:33", "throughput": 1666.32, "total_tokens": 13620576}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 0.2965, "lr": 1.1991872198297004e-05, "epoch": 318.72289156626505, "percentage": 99.6, "elapsed_time": "2:16:14", "remaining_time": "0:00:32", "throughput": 1666.33, "total_tokens": 13622176}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 0.3437, "lr": 1.1258610377384847e-05, "epoch": 318.76305220883535, "percentage": 99.61, "elapsed_time": "2:16:15", "remaining_time": "0:00:31", "throughput": 1666.33, "total_tokens": 13623744}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 0.3193, "lr": 1.0548478705268982e-05, "epoch": 318.80321285140565, "percentage": 99.62, "elapsed_time": "2:16:16", "remaining_time": "0:00:30", "throughput": 1666.34, "total_tokens": 13625280}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 0.3239, "lr": 9.86147729147846e-06, "epoch": 318.8433734939759, "percentage": 99.64, "elapsed_time": "2:16:17", "remaining_time": "0:00:29", "throughput": 1666.36, "total_tokens": 13626976}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 0.3456, "lr": 9.197606241928557e-06, "epoch": 318.8835341365462, "percentage": 99.65, "elapsed_time": "2:16:18", "remaining_time": "0:00:28", "throughput": 1666.38, "total_tokens": 13628768}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 0.3483, "lr": 8.556865659004042e-06, "epoch": 318.9236947791165, "percentage": 99.66, "elapsed_time": "2:16:19", "remaining_time": "0:00:27", "throughput": 1666.38, "total_tokens": 13630464}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 0.3083, "lr": 7.939255641525867e-06, "epoch": 318.96385542168673, "percentage": 99.67, "elapsed_time": "2:16:20", "remaining_time": "0:00:26", "throughput": 1666.41, "total_tokens": 13632304}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 0.3277, "lr": 7.344776284751164e-06, "epoch": 319.0, "percentage": 99.69, "elapsed_time": "2:16:21", "remaining_time": "0:00:25", "throughput": 1666.39, "total_tokens": 13633808}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 0.3441, "lr": 6.773427680323296e-06, "epoch": 319.0401606425703, "percentage": 99.7, "elapsed_time": "2:16:22", "remaining_time": "0:00:24", "throughput": 1666.36, "total_tokens": 13635568}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 0.3583, "lr": 6.225209916355112e-06, "epoch": 319.08032128514054, "percentage": 99.71, "elapsed_time": "2:16:23", "remaining_time": "0:00:23", "throughput": 1666.38, "total_tokens": 13637344}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 0.3562, "lr": 5.7001230774123e-06, "epoch": 319.12048192771084, "percentage": 99.72, "elapsed_time": "2:16:24", "remaining_time": "0:00:22", "throughput": 1666.38, "total_tokens": 13638992}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 0.36, "lr": 5.198167244446772e-06, "epoch": 319.16064257028114, "percentage": 99.74, "elapsed_time": "2:16:25", "remaining_time": "0:00:21", "throughput": 1666.38, "total_tokens": 13640480}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 0.3271, "lr": 4.71934249487993e-06, "epoch": 319.2008032128514, "percentage": 99.75, "elapsed_time": "2:16:26", "remaining_time": "0:00:20", "throughput": 1666.4, "total_tokens": 13642176}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 0.3548, "lr": 4.2636489025527075e-06, "epoch": 319.2409638554217, "percentage": 99.76, "elapsed_time": "2:16:27", "remaining_time": "0:00:19", "throughput": 1666.44, "total_tokens": 13644176}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 0.3673, "lr": 3.831086537742223e-06, "epoch": 319.281124497992, "percentage": 99.78, "elapsed_time": "2:16:28", "remaining_time": "0:00:18", "throughput": 1666.45, "total_tokens": 13645840}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 0.2902, "lr": 3.4216554671451236e-06, "epoch": 319.3212851405622, "percentage": 99.79, "elapsed_time": "2:16:29", "remaining_time": "0:00:17", "throughput": 1666.46, "total_tokens": 13647536}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 0.3435, "lr": 3.035355753894242e-06, "epoch": 319.3614457831325, "percentage": 99.8, "elapsed_time": "2:16:30", "remaining_time": "0:00:16", "throughput": 1666.47, "total_tokens": 13649168}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 0.3281, "lr": 2.6721874575752477e-06, "epoch": 319.4016064257028, "percentage": 99.81, "elapsed_time": "2:16:31", "remaining_time": "0:00:15", "throughput": 1666.49, "total_tokens": 13650880}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 0.3334, "lr": 2.3321506341933418e-06, "epoch": 319.44176706827307, "percentage": 99.83, "elapsed_time": "2:16:32", "remaining_time": "0:00:14", "throughput": 1666.49, "total_tokens": 13652464}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 0.3087, "lr": 2.0152453361732546e-06, "epoch": 319.48192771084337, "percentage": 99.84, "elapsed_time": "2:16:33", "remaining_time": "0:00:13", "throughput": 1666.5, "total_tokens": 13654064}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 0.3682, "lr": 1.7214716123925554e-06, "epoch": 319.52208835341366, "percentage": 99.85, "elapsed_time": "2:16:34", "remaining_time": "0:00:12", "throughput": 1666.52, "total_tokens": 13655872}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 0.3301, "lr": 1.4508295081649968e-06, "epoch": 319.56224899598396, "percentage": 99.86, "elapsed_time": "2:16:35", "remaining_time": "0:00:11", "throughput": 1666.54, "total_tokens": 13657680}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 0.3357, "lr": 1.2033190652238623e-06, "epoch": 319.6024096385542, "percentage": 99.88, "elapsed_time": "2:16:36", "remaining_time": "0:00:10", "throughput": 1666.55, "total_tokens": 13659312}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 0.3298, "lr": 9.78940321721966e-07, "epoch": 319.6425702811245, "percentage": 99.89, "elapsed_time": "2:16:37", "remaining_time": "0:00:09", "throughput": 1666.56, "total_tokens": 13660976}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 0.3205, "lr": 7.776933122816132e-07, "epoch": 319.6827309236948, "percentage": 99.9, "elapsed_time": "2:16:38", "remaining_time": "0:00:08", "throughput": 1666.59, "total_tokens": 13662848}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 0.3602, "lr": 5.99578067927986e-07, "epoch": 319.72289156626505, "percentage": 99.91, "elapsed_time": "2:16:39", "remaining_time": "0:00:07", "throughput": 1666.63, "total_tokens": 13664896}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 0.3735, "lr": 4.445946161224512e-07, "epoch": 319.76305220883535, "percentage": 99.92, "elapsed_time": "2:16:40", "remaining_time": "0:00:06", "throughput": 1666.62, "total_tokens": 13666464}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 0.3183, "lr": 3.127429807792126e-07, "epoch": 319.80321285140565, "percentage": 99.94, "elapsed_time": "2:16:41", "remaining_time": "0:00:05", "throughput": 1666.65, "total_tokens": 13668320}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 0.3174, "lr": 2.040231822320049e-07, "epoch": 319.8433734939759, "percentage": 99.95, "elapsed_time": "2:16:41", "remaining_time": "0:00:04", "throughput": 1666.66, "total_tokens": 13669920}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 0.3402, "lr": 1.1843523723409354e-07, "epoch": 319.8835341365462, "percentage": 99.96, "elapsed_time": "2:16:42", "remaining_time": "0:00:03", "throughput": 1666.68, "total_tokens": 13671664}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 0.3049, "lr": 5.597915897492811e-08, "epoch": 319.9236947791165, "percentage": 99.98, "elapsed_time": "2:16:43", "remaining_time": "0:00:02", "throughput": 1666.69, "total_tokens": 13673296}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 0.3189, "lr": 1.6654957113448885e-08, "epoch": 319.96385542168673, "percentage": 99.99, "elapsed_time": "2:16:44", "remaining_time": "0:00:01", "throughput": 1666.71, "total_tokens": 13675056}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 0.319, "lr": 4.626377114735902e-10, "epoch": 320.0, "percentage": 100.0, "elapsed_time": "2:16:45", "remaining_time": "0:00:00", "throughput": 1666.69, "total_tokens": 13676608}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 0.43265536427497864, "epoch": 320.0, "percentage": 100.0, "elapsed_time": "2:16:47", "remaining_time": "0:00:00", "throughput": 1666.36, "total_tokens": 13676608}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 320.0, "percentage": 100.0, "elapsed_time": "2:16:48", "remaining_time": "0:00:00", "throughput": 1666.16, "total_tokens": 13676608}
|