Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
3cd9673
•
1 Parent(s): 3ed4a41

Training in progress, step 55000

Browse files
Files changed (10) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scaler.pt +1 -1
  8. last-checkpoint/scheduler.pt +1 -1
  9. last-checkpoint/trainer_state.json +62 -2
  10. pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:585dc16d735672778f127a50a104f1dd435dd6961982b55a3048c7509e1a0606
3
  size 402587859
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d29c5cd8302f025539b519369f38710bd60a484f6040f6e6fd4ef126527e62c
3
  size 402587859
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3b7ae155a06728642638731f6de2c2f5afc3e981ea2fdb85c38fb6a64b25b0c
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8175eb7aabe29b20ae38e8721bcad6b96bf56fb83040d029289a7b2b4bdffd
3
  size 201355195
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c214fb929216c2b57a561db0a033cee82210e2640667cbc8b9831673fb9add6b
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3828b49e984f94b8de98c57402e14e2b06028ba92bbe503825e54ba102f5e8c6
3
  size 14503
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44ecb07ac2162f527064f2737413d021caa039db7ccee830bdf0538ff05d4093
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e5996ed29725601ba19223eb8bddf8ddb108344f54331ee084dc716ce0fb97
3
  size 14503
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a5ac6e08b327e2d192624409abaa145fec824a1b1c826ed5c288c5e1790e3b9
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f1beb224cc84fef2658e7f28686099ea3a58b55973b5b4fda4130dad690eda9
3
  size 14503
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50af050c43186589343af9bb992fc787c0a783d8c2b49498b7c1931805c39e02
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e8e45049980835f8d0790e3bb91cd80a327d90ff90145a257ee1e39800e9cb2
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e2dbdff4ea032b46d21433a227047ff3118604187bcfab711dfc4fa85bb0b8c
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32b5fdb733a605d87af51fdd387ceec9f49ad656b2ebd6ccfb7e2575b9b2fe96
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b02d21f408cca9174ccc2664126f6b167a3474ba9d60c95500be18ad93c90a5
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69ebd792f9481284cd3db527c14e931aa8fdfefc23b7bb13c9b2a45f83d116bf
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.851063829787234,
5
- "global_step": 50000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -606,6 +606,66 @@
606
  "learning_rate": 0.00014657626627801257,
607
  "loss": 0.3638,
608
  "step": 50000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
609
  }
610
  ],
611
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9361702127659575,
5
+ "global_step": 55000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
606
  "learning_rate": 0.00014657626627801257,
607
  "loss": 0.3638,
608
  "step": 50000
609
+ },
610
+ {
611
+ "epoch": 0.86,
612
+ "learning_rate": 0.0001465080038033494,
613
+ "loss": 0.3634,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 0.87,
618
+ "learning_rate": 0.00014643908492153906,
619
+ "loss": 0.3634,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 0.88,
624
+ "learning_rate": 0.00014636978991651827,
625
+ "loss": 0.3632,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 0.89,
630
+ "learning_rate": 0.00014629956288627466,
631
+ "loss": 0.3633,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 0.89,
636
+ "learning_rate": 0.00014622868150611156,
637
+ "loss": 0.3627,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 0.9,
642
+ "learning_rate": 0.00014615714647559958,
643
+ "loss": 0.3627,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 0.91,
648
+ "learning_rate": 0.00014608495850076063,
649
+ "loss": 0.3625,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 0.92,
654
+ "learning_rate": 0.00014601211829406085,
655
+ "loss": 0.3622,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 0.93,
660
+ "learning_rate": 0.00014593862657440366,
661
+ "loss": 0.3619,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 0.94,
666
+ "learning_rate": 0.0001458644840671227,
667
+ "loss": 0.3617,
668
+ "step": 55000
669
  }
670
  ],
671
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3b7ae155a06728642638731f6de2c2f5afc3e981ea2fdb85c38fb6a64b25b0c
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8175eb7aabe29b20ae38e8721bcad6b96bf56fb83040d029289a7b2b4bdffd
3
  size 201355195