Training in progress, step 540
Browse files
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5000000704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3736b4c0e87a998a04bd9ec0a7299fffc8542d92907606064eba20f16fd7a5df
|
3 |
size 5000000704
|
model-00002-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4857411192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82a57bc589d2e691f89c5f9d8226106a3d843a23203ba220b7a0b7849e04d785
|
3 |
size 4857411192
|
model-00003-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3921970888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efeb8683954a9be17e850297339f72909be6a7b4eb914c21d8c5d7497374d401
|
3 |
size 3921970888
|
trainer_log.jsonl
CHANGED
@@ -538,3 +538,39 @@
|
|
538 |
{"current_steps": 538, "total_steps": 9875, "loss": 1.0289, "lr": 5.445344129554656e-06, "epoch": 0.2724050632911392, "percentage": 5.45, "elapsed_time": "1:30:31", "remaining_time": "1 day, 2:11:05"}
|
539 |
{"current_steps": 539, "total_steps": 9875, "loss": 1.0893, "lr": 5.455465587044535e-06, "epoch": 0.2729113924050633, "percentage": 5.46, "elapsed_time": "1:30:33", "remaining_time": "1 day, 2:08:28"}
|
540 |
{"current_steps": 540, "total_steps": 9875, "loss": 1.1109, "lr": 5.465587044534414e-06, "epoch": 0.27341772151898736, "percentage": 5.47, "elapsed_time": "1:30:34", "remaining_time": "1 day, 2:05:51"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
538 |
{"current_steps": 538, "total_steps": 9875, "loss": 1.0289, "lr": 5.445344129554656e-06, "epoch": 0.2724050632911392, "percentage": 5.45, "elapsed_time": "1:30:31", "remaining_time": "1 day, 2:11:05"}
|
539 |
{"current_steps": 539, "total_steps": 9875, "loss": 1.0893, "lr": 5.455465587044535e-06, "epoch": 0.2729113924050633, "percentage": 5.46, "elapsed_time": "1:30:33", "remaining_time": "1 day, 2:08:28"}
|
540 |
{"current_steps": 540, "total_steps": 9875, "loss": 1.1109, "lr": 5.465587044534414e-06, "epoch": 0.27341772151898736, "percentage": 5.47, "elapsed_time": "1:30:34", "remaining_time": "1 day, 2:05:51"}
|
541 |
+
{"current_steps": 541, "total_steps": 9875, "loss": 1.012, "lr": 5.475708502024292e-06, "epoch": 0.2739240506329114, "percentage": 5.48, "elapsed_time": "1:31:55", "remaining_time": "1 day, 2:25:59"}
|
542 |
+
{"current_steps": 542, "total_steps": 9875, "loss": 1.0074, "lr": 5.485829959514171e-06, "epoch": 0.27443037974683543, "percentage": 5.49, "elapsed_time": "1:31:57", "remaining_time": "1 day, 2:23:20"}
|
543 |
+
{"current_steps": 543, "total_steps": 9875, "loss": 1.0505, "lr": 5.4959514170040495e-06, "epoch": 0.2749367088607595, "percentage": 5.5, "elapsed_time": "1:31:58", "remaining_time": "1 day, 2:20:43"}
|
544 |
+
{"current_steps": 544, "total_steps": 9875, "loss": 1.0963, "lr": 5.506072874493927e-06, "epoch": 0.27544303797468356, "percentage": 5.51, "elapsed_time": "1:32:00", "remaining_time": "1 day, 2:18:09"}
|
545 |
+
{"current_steps": 545, "total_steps": 9875, "loss": 1.0511, "lr": 5.516194331983806e-06, "epoch": 0.2759493670886076, "percentage": 5.52, "elapsed_time": "1:32:01", "remaining_time": "1 day, 2:15:32"}
|
546 |
+
{"current_steps": 546, "total_steps": 9875, "loss": 1.0176, "lr": 5.526315789473685e-06, "epoch": 0.27645569620253163, "percentage": 5.53, "elapsed_time": "1:32:03", "remaining_time": "1 day, 2:12:56"}
|
547 |
+
{"current_steps": 547, "total_steps": 9875, "loss": 1.1432, "lr": 5.536437246963563e-06, "epoch": 0.2769620253164557, "percentage": 5.54, "elapsed_time": "1:32:05", "remaining_time": "1 day, 2:10:20"}
|
548 |
+
{"current_steps": 548, "total_steps": 9875, "loss": 1.103, "lr": 5.546558704453442e-06, "epoch": 0.27746835443037976, "percentage": 5.55, "elapsed_time": "1:32:06", "remaining_time": "1 day, 2:07:46"}
|
549 |
+
{"current_steps": 549, "total_steps": 9875, "loss": 1.0837, "lr": 5.556680161943321e-06, "epoch": 0.2779746835443038, "percentage": 5.56, "elapsed_time": "1:32:08", "remaining_time": "1 day, 2:05:12"}
|
550 |
+
{"current_steps": 550, "total_steps": 9875, "loss": 1.0377, "lr": 5.566801619433199e-06, "epoch": 0.27848101265822783, "percentage": 5.57, "elapsed_time": "1:32:09", "remaining_time": "1 day, 2:02:38"}
|
551 |
+
{"current_steps": 551, "total_steps": 9875, "loss": 1.0458, "lr": 5.576923076923077e-06, "epoch": 0.2789873417721519, "percentage": 5.58, "elapsed_time": "1:33:13", "remaining_time": "1 day, 2:17:26"}
|
552 |
+
{"current_steps": 552, "total_steps": 9875, "loss": 0.9991, "lr": 5.5870445344129565e-06, "epoch": 0.27949367088607596, "percentage": 5.59, "elapsed_time": "1:33:14", "remaining_time": "1 day, 2:14:52"}
|
553 |
+
{"current_steps": 553, "total_steps": 9875, "loss": 1.0552, "lr": 5.597165991902834e-06, "epoch": 0.28, "percentage": 5.6, "elapsed_time": "1:33:16", "remaining_time": "1 day, 2:12:17"}
|
554 |
+
{"current_steps": 554, "total_steps": 9875, "loss": 1.0244, "lr": 5.6072874493927135e-06, "epoch": 0.28050632911392404, "percentage": 5.61, "elapsed_time": "1:33:17", "remaining_time": "1 day, 2:09:44"}
|
555 |
+
{"current_steps": 555, "total_steps": 9875, "loss": 1.0573, "lr": 5.617408906882592e-06, "epoch": 0.2810126582278481, "percentage": 5.62, "elapsed_time": "1:33:19", "remaining_time": "1 day, 2:07:11"}
|
556 |
+
{"current_steps": 556, "total_steps": 9875, "loss": 1.0382, "lr": 5.6275303643724695e-06, "epoch": 0.28151898734177216, "percentage": 5.63, "elapsed_time": "1:33:21", "remaining_time": "1 day, 2:04:39"}
|
557 |
+
{"current_steps": 557, "total_steps": 9875, "loss": 1.0395, "lr": 5.637651821862349e-06, "epoch": 0.28202531645569623, "percentage": 5.64, "elapsed_time": "1:33:22", "remaining_time": "1 day, 2:02:07"}
|
558 |
+
{"current_steps": 558, "total_steps": 9875, "loss": 1.0919, "lr": 5.6477732793522265e-06, "epoch": 0.28253164556962024, "percentage": 5.65, "elapsed_time": "1:33:24", "remaining_time": "1 day, 1:59:36"}
|
559 |
+
{"current_steps": 559, "total_steps": 9875, "loss": 1.0881, "lr": 5.657894736842106e-06, "epoch": 0.2830379746835443, "percentage": 5.66, "elapsed_time": "1:33:25", "remaining_time": "1 day, 1:57:05"}
|
560 |
+
{"current_steps": 560, "total_steps": 9875, "loss": 0.9783, "lr": 5.668016194331984e-06, "epoch": 0.28354430379746837, "percentage": 5.67, "elapsed_time": "1:33:27", "remaining_time": "1 day, 1:54:35"}
|
561 |
+
{"current_steps": 561, "total_steps": 9875, "loss": 0.966, "lr": 5.678137651821862e-06, "epoch": 0.28405063291139243, "percentage": 5.68, "elapsed_time": "1:34:41", "remaining_time": "1 day, 2:12:04"}
|
562 |
+
{"current_steps": 562, "total_steps": 9875, "loss": 1.1139, "lr": 5.688259109311741e-06, "epoch": 0.28455696202531644, "percentage": 5.69, "elapsed_time": "1:34:42", "remaining_time": "1 day, 2:09:32"}
|
563 |
+
{"current_steps": 563, "total_steps": 9875, "loss": 1.0297, "lr": 5.6983805668016205e-06, "epoch": 0.2850632911392405, "percentage": 5.7, "elapsed_time": "1:34:44", "remaining_time": "1 day, 2:07:01"}
|
564 |
+
{"current_steps": 564, "total_steps": 9875, "loss": 1.0144, "lr": 5.708502024291498e-06, "epoch": 0.28556962025316457, "percentage": 5.71, "elapsed_time": "1:34:46", "remaining_time": "1 day, 2:04:30"}
|
565 |
+
{"current_steps": 565, "total_steps": 9875, "loss": 1.1488, "lr": 5.718623481781377e-06, "epoch": 0.28607594936708863, "percentage": 5.72, "elapsed_time": "1:34:47", "remaining_time": "1 day, 2:02:00"}
|
566 |
+
{"current_steps": 566, "total_steps": 9875, "loss": 0.9193, "lr": 5.728744939271256e-06, "epoch": 0.28658227848101264, "percentage": 5.73, "elapsed_time": "1:34:49", "remaining_time": "1 day, 1:59:31"}
|
567 |
+
{"current_steps": 567, "total_steps": 9875, "loss": 1.1477, "lr": 5.7388663967611335e-06, "epoch": 0.2870886075949367, "percentage": 5.74, "elapsed_time": "1:34:50", "remaining_time": "1 day, 1:57:01"}
|
568 |
+
{"current_steps": 568, "total_steps": 9875, "loss": 0.9613, "lr": 5.748987854251013e-06, "epoch": 0.28759493670886077, "percentage": 5.75, "elapsed_time": "1:34:52", "remaining_time": "1 day, 1:54:33"}
|
569 |
+
{"current_steps": 569, "total_steps": 9875, "loss": 1.0533, "lr": 5.759109311740891e-06, "epoch": 0.28810126582278484, "percentage": 5.76, "elapsed_time": "1:34:53", "remaining_time": "1 day, 1:52:05"}
|
570 |
+
{"current_steps": 570, "total_steps": 9875, "loss": 1.0252, "lr": 5.769230769230769e-06, "epoch": 0.28860759493670884, "percentage": 5.77, "elapsed_time": "1:34:55", "remaining_time": "1 day, 1:49:38"}
|
571 |
+
{"current_steps": 571, "total_steps": 9875, "loss": 1.0884, "lr": 5.779352226720648e-06, "epoch": 0.2891139240506329, "percentage": 5.78, "elapsed_time": "1:36:15", "remaining_time": "1 day, 2:08:33"}
|
572 |
+
{"current_steps": 572, "total_steps": 9875, "loss": 1.0181, "lr": 5.789473684210527e-06, "epoch": 0.289620253164557, "percentage": 5.79, "elapsed_time": "1:36:17", "remaining_time": "1 day, 2:06:04"}
|
573 |
+
{"current_steps": 573, "total_steps": 9875, "loss": 1.0633, "lr": 5.799595141700405e-06, "epoch": 0.29012658227848104, "percentage": 5.8, "elapsed_time": "1:36:19", "remaining_time": "1 day, 2:03:36"}
|
574 |
+
{"current_steps": 574, "total_steps": 9875, "loss": 1.0394, "lr": 5.809716599190284e-06, "epoch": 0.29063291139240505, "percentage": 5.81, "elapsed_time": "1:36:20", "remaining_time": "1 day, 2:01:08"}
|
575 |
+
{"current_steps": 575, "total_steps": 9875, "loss": 0.9718, "lr": 5.819838056680163e-06, "epoch": 0.2911392405063291, "percentage": 5.82, "elapsed_time": "1:36:22", "remaining_time": "1 day, 1:58:41"}
|
576 |
+
{"current_steps": 576, "total_steps": 9875, "loss": 1.0125, "lr": 5.8299595141700406e-06, "epoch": 0.2916455696202532, "percentage": 5.83, "elapsed_time": "1:36:23", "remaining_time": "1 day, 1:56:14"}
|