RuidiChang commited on
Commit
0508a0c
·
verified ·
1 Parent(s): caa2a83

Sync missing vs SOURCE into TARGET under 'checkpoints' (batch 8, +50 files)

Browse files
Files changed (50) hide show
  1. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_3/final_betas.txt +24 -0
  2. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_3/test_metrics.txt +2 -0
  3. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_3/test_metrics_before.txt +2 -0
  4. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_sup/config.txt +6 -0
  5. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_sup/final_betas.pt +3 -0
  6. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_sup/final_betas.txt +24 -0
  7. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_sup/test_metrics_before.txt +2 -0
  8. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3/config.txt +6 -0
  9. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3/final_betas.pt +3 -0
  10. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3/final_betas.txt +24 -0
  11. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3/test_metrics.txt +2 -0
  12. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3/test_metrics_before.txt +2 -0
  13. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360/config.txt +6 -0
  14. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360/final_betas.pt +3 -0
  15. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360/final_betas.txt +24 -0
  16. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360/test_metrics.txt +2 -0
  17. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360/test_metrics_before.txt +2 -0
  18. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360_sup/config.txt +6 -0
  19. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360_sup/final_betas.pt +3 -0
  20. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360_sup/final_betas.txt +24 -0
  21. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360_sup/test_metrics_before.txt +2 -0
  22. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42/config.txt +6 -0
  23. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42/final_betas.pt +3 -0
  24. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42/final_betas.txt +24 -0
  25. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42/test_metrics.txt +2 -0
  26. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42/test_metrics_before.txt +2 -0
  27. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360/config.txt +6 -0
  28. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360/final_betas.pt +3 -0
  29. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360/final_betas.txt +24 -0
  30. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360/test_metrics.txt +2 -0
  31. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360/test_metrics_before.txt +2 -0
  32. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360_sup/config.txt +6 -0
  33. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360_sup/final_betas.pt +3 -0
  34. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360_sup/final_betas.txt +24 -0
  35. checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360_sup/test_metrics_before.txt +2 -0
  36. checkpoints/residual_beta_clutrr_qwen_train_correct_0/config.txt +6 -0
  37. checkpoints/residual_beta_clutrr_qwen_train_correct_0/final_betas.pt +3 -0
  38. checkpoints/residual_beta_clutrr_qwen_train_correct_0/final_betas.txt +24 -0
  39. checkpoints/residual_beta_clutrr_qwen_train_correct_0/test_metrics.txt +2 -0
  40. checkpoints/residual_beta_clutrr_qwen_train_correct_0/test_metrics_before.txt +2 -0
  41. checkpoints/residual_beta_clutrr_qwen_train_correct_1/config.txt +6 -0
  42. checkpoints/residual_beta_clutrr_qwen_train_correct_1/final_betas.pt +3 -0
  43. checkpoints/residual_beta_clutrr_qwen_train_correct_1/final_betas.txt +24 -0
  44. checkpoints/residual_beta_clutrr_qwen_train_correct_1/test_metrics.txt +2 -0
  45. checkpoints/residual_beta_clutrr_qwen_train_correct_1/test_metrics_before.txt +2 -0
  46. checkpoints/residual_beta_clutrr_qwen_train_correct_2/config.txt +6 -0
  47. checkpoints/residual_beta_clutrr_qwen_train_correct_2/final_betas.pt +3 -0
  48. checkpoints/residual_beta_clutrr_qwen_train_correct_2/final_betas.txt +24 -0
  49. checkpoints/residual_beta_clutrr_qwen_train_correct_2/test_metrics.txt +2 -0
  50. checkpoints/residual_beta_clutrr_qwen_train_correct_2/test_metrics_before.txt +2 -0
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_3/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 1.000145
2
+ Layer 1: 1.000036
3
+ Layer 2: 1.000149
4
+ Layer 3: 1.000094
5
+ Layer 4: 0.999870
6
+ Layer 5: 0.999861
7
+ Layer 6: 0.999875
8
+ Layer 7: 1.000146
9
+ Layer 8: 1.000150
10
+ Layer 9: 0.999893
11
+ Layer 10: 0.999871
12
+ Layer 11: 0.999842
13
+ Layer 12: 0.999854
14
+ Layer 13: 1.000133
15
+ Layer 14: 1.000068
16
+ Layer 15: 0.999898
17
+ Layer 16: 0.999968
18
+ Layer 17: 1.000151
19
+ Layer 18: 1.000115
20
+ Layer 19: 1.000005
21
+ Layer 20: 0.999844
22
+ Layer 21: 1.000114
23
+ Layer 22: 0.999857
24
+ Layer 23: 1.000054
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_3/test_metrics.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 5.4055
2
+ Test Accuracy: 0.3555
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_3/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 5.4091
2
+ Test Accuracy: 0.3555
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_sup/config.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epochs: 3
2
+ batch_size: 16
3
+ lr: 5e-06
4
+ seed: 2
5
+ checkpoint_dir: checkpoints/clutrr_qwen/checkpoint-360
6
+ output_dir: checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_sup
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_sup/final_betas.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702ca6cc5b6bf7824f1ea40b18f0af7ca33a0c79df223b526bbbf42a38dc8c26
3
+ size 1264
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_sup/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 1.002641
2
+ Layer 1: 1.002353
3
+ Layer 2: 1.002844
4
+ Layer 3: 1.000317
5
+ Layer 4: 0.997070
6
+ Layer 5: 0.999512
7
+ Layer 6: 0.997561
8
+ Layer 7: 1.000414
9
+ Layer 8: 1.001451
10
+ Layer 9: 0.997695
11
+ Layer 10: 1.000184
12
+ Layer 11: 0.997263
13
+ Layer 12: 0.997811
14
+ Layer 13: 1.000659
15
+ Layer 14: 1.001217
16
+ Layer 15: 0.998634
17
+ Layer 16: 1.001653
18
+ Layer 17: 1.002702
19
+ Layer 18: 0.997795
20
+ Layer 19: 0.999280
21
+ Layer 20: 0.997102
22
+ Layer 21: 0.999309
23
+ Layer 22: 0.997789
24
+ Layer 23: 1.001823
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_2_360_sup/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 3.3787
2
+ Test Accuracy: 0.4416
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3/config.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epochs: 3
2
+ batch_size: 16
3
+ lr: 5e-06
4
+ seed: 3
5
+ checkpoint_dir: checkpoints/clutrr_qwen/checkpoint-360
6
+ output_dir: checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3/final_betas.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7351bc60199955ac270856bfd0b9c4097ecaaae373e5eed7546f86d4a68db7ed
3
+ size 1264
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 1.000280
2
+ Layer 1: 1.000347
3
+ Layer 2: 1.000030
4
+ Layer 3: 1.000340
5
+ Layer 4: 0.999968
6
+ Layer 5: 0.999866
7
+ Layer 6: 0.999796
8
+ Layer 7: 1.000170
9
+ Layer 8: 1.000072
10
+ Layer 9: 0.999831
11
+ Layer 10: 0.999759
12
+ Layer 11: 0.999608
13
+ Layer 12: 0.999649
14
+ Layer 13: 0.999954
15
+ Layer 14: 0.999963
16
+ Layer 15: 0.999632
17
+ Layer 16: 1.000385
18
+ Layer 17: 1.000405
19
+ Layer 18: 0.999651
20
+ Layer 19: 0.999895
21
+ Layer 20: 0.999615
22
+ Layer 21: 0.999842
23
+ Layer 22: 0.999970
24
+ Layer 23: 1.000411
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3/test_metrics.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 5.2828
2
+ Test Accuracy: 0.2901
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 5.2859
2
+ Test Accuracy: 0.2891
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360/config.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epochs: 5
2
+ batch_size: 16
3
+ lr: 5e-06
4
+ seed: 3
5
+ checkpoint_dir: checkpoints/clutrr_qwen/checkpoint-360
6
+ output_dir: checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360/final_betas.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59dc8c1905ffa29340db7b006b8c4931ecd690fec67d35c7bc8b9992dab69dd9
3
+ size 1264
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 1.000036
2
+ Layer 1: 1.000023
3
+ Layer 2: 1.000035
4
+ Layer 3: 1.000011
5
+ Layer 4: 0.999971
6
+ Layer 5: 0.999968
7
+ Layer 6: 0.999965
8
+ Layer 7: 1.000037
9
+ Layer 8: 1.000037
10
+ Layer 9: 1.000000
11
+ Layer 10: 0.999966
12
+ Layer 11: 0.999961
13
+ Layer 12: 0.999961
14
+ Layer 13: 1.000018
15
+ Layer 14: 1.000028
16
+ Layer 15: 0.999976
17
+ Layer 16: 0.999993
18
+ Layer 17: 1.000039
19
+ Layer 18: 1.000025
20
+ Layer 19: 1.000008
21
+ Layer 20: 0.999960
22
+ Layer 21: 1.000034
23
+ Layer 22: 0.999964
24
+ Layer 23: 1.000021
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360/test_metrics.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 5.4082
2
+ Test Accuracy: 0.3555
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 5.4091
2
+ Test Accuracy: 0.3555
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360_sup/config.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epochs: 3
2
+ batch_size: 16
3
+ lr: 5e-06
4
+ seed: 3
5
+ checkpoint_dir: checkpoints/clutrr_qwen/checkpoint-360
6
+ output_dir: checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360_sup
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360_sup/final_betas.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aec21d1f677119dde9ce17a75ad146359654317f9c352945c1cc30155bffd9a
3
+ size 1264
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360_sup/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 1.002601
2
+ Layer 1: 1.002335
3
+ Layer 2: 1.002811
4
+ Layer 3: 1.000285
5
+ Layer 4: 0.997043
6
+ Layer 5: 0.999547
7
+ Layer 6: 0.997493
8
+ Layer 7: 1.000441
9
+ Layer 8: 1.001439
10
+ Layer 9: 0.997551
11
+ Layer 10: 1.000194
12
+ Layer 11: 0.997314
13
+ Layer 12: 0.997855
14
+ Layer 13: 1.000679
15
+ Layer 14: 1.001223
16
+ Layer 15: 0.998667
17
+ Layer 16: 1.001642
18
+ Layer 17: 1.002723
19
+ Layer 18: 0.997815
20
+ Layer 19: 0.999206
21
+ Layer 20: 0.996983
22
+ Layer 21: 0.999292
23
+ Layer 22: 0.997923
24
+ Layer 23: 1.001815
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_3_360_sup/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 3.3787
2
+ Test Accuracy: 0.4416
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42/config.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epochs: 3
2
+ batch_size: 16
3
+ lr: 5e-06
4
+ seed: 42
5
+ checkpoint_dir: checkpoints/clutrr_qwen/checkpoint-360
6
+ output_dir: checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42/final_betas.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebd49f17f798b5bc699b0261b725ac64f224485a41e254de3c75c3f2706314da
3
+ size 1264
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 1.000341
2
+ Layer 1: 1.000379
3
+ Layer 2: 1.000056
4
+ Layer 3: 1.000324
5
+ Layer 4: 0.999946
6
+ Layer 5: 0.999853
7
+ Layer 6: 0.999776
8
+ Layer 7: 1.000202
9
+ Layer 8: 1.000089
10
+ Layer 9: 0.999790
11
+ Layer 10: 0.999805
12
+ Layer 11: 0.999627
13
+ Layer 12: 0.999643
14
+ Layer 13: 0.999951
15
+ Layer 14: 0.999973
16
+ Layer 15: 0.999626
17
+ Layer 16: 1.000381
18
+ Layer 17: 1.000414
19
+ Layer 18: 0.999654
20
+ Layer 19: 0.999867
21
+ Layer 20: 0.999608
22
+ Layer 21: 0.999833
23
+ Layer 22: 0.999911
24
+ Layer 23: 1.000409
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42/test_metrics.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 5.2827
2
+ Test Accuracy: 0.2901
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 5.2859
2
+ Test Accuracy: 0.2891
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360/config.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epochs: 5
2
+ batch_size: 16
3
+ lr: 5e-06
4
+ seed: 42
5
+ checkpoint_dir: checkpoints/clutrr_qwen/checkpoint-360
6
+ output_dir: checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360/final_betas.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23180348fdcd28d1bacacdbd497d12120126260a443c44c109f3e90e44672026
3
+ size 1264
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 1.000038
2
+ Layer 1: 0.999994
3
+ Layer 2: 1.000038
4
+ Layer 3: 1.000029
5
+ Layer 4: 0.999978
6
+ Layer 5: 0.999961
7
+ Layer 6: 0.999961
8
+ Layer 7: 1.000038
9
+ Layer 8: 1.000036
10
+ Layer 9: 0.999968
11
+ Layer 10: 0.999965
12
+ Layer 11: 0.999962
13
+ Layer 12: 0.999962
14
+ Layer 13: 1.000035
15
+ Layer 14: 1.000034
16
+ Layer 15: 0.999966
17
+ Layer 16: 0.999980
18
+ Layer 17: 1.000038
19
+ Layer 18: 1.000031
20
+ Layer 19: 1.000018
21
+ Layer 20: 0.999960
22
+ Layer 21: 1.000034
23
+ Layer 22: 0.999965
24
+ Layer 23: 1.000026
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360/test_metrics.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 5.4082
2
+ Test Accuracy: 0.3555
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 5.4091
2
+ Test Accuracy: 0.3555
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360_sup/config.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epochs: 3
2
+ batch_size: 16
3
+ lr: 5e-06
4
+ seed: 42
5
+ checkpoint_dir: checkpoints/clutrr_qwen/checkpoint-360
6
+ output_dir: checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360_sup
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360_sup/final_betas.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38cbebe7b5cde3d0a3bb984cfef58ce86385c5aaf6bee8c47d28742af025e675
3
+ size 1264
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360_sup/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 1.002718
2
+ Layer 1: 1.002307
3
+ Layer 2: 1.002795
4
+ Layer 3: 1.000264
5
+ Layer 4: 0.997024
6
+ Layer 5: 0.999576
7
+ Layer 6: 0.997403
8
+ Layer 7: 1.000390
9
+ Layer 8: 1.001439
10
+ Layer 9: 0.997656
11
+ Layer 10: 1.000182
12
+ Layer 11: 0.997294
13
+ Layer 12: 0.997795
14
+ Layer 13: 1.000618
15
+ Layer 14: 1.001209
16
+ Layer 15: 0.998720
17
+ Layer 16: 1.001593
18
+ Layer 17: 1.002653
19
+ Layer 18: 0.997688
20
+ Layer 19: 0.999232
21
+ Layer 20: 0.997043
22
+ Layer 21: 0.999295
23
+ Layer 22: 0.997869
24
+ Layer 23: 1.001814
checkpoints/residual_beta_clutrr_qwen_test_ood_correct_42_360_sup/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 3.3787
2
+ Test Accuracy: 0.4416
checkpoints/residual_beta_clutrr_qwen_train_correct_0/config.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epochs: 5
2
+ batch_size: 16
3
+ lr: 5e-06
4
+ seed: 0
5
+ checkpoint_dir: checkpoints/clutrr_qwen/checkpoint-360
6
+ output_dir: checkpoints/residual_beta_clutrr_qwen_train_correct_0
checkpoints/residual_beta_clutrr_qwen_train_correct_0/final_betas.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6df6758347b2de2fcf8e4c90d0173c2bfd77524a88b36efa511bb03a366efb1
3
+ size 1264
checkpoints/residual_beta_clutrr_qwen_train_correct_0/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 0.999937
2
+ Layer 1: 1.000578
3
+ Layer 2: 0.999976
4
+ Layer 3: 0.999662
5
+ Layer 4: 0.999473
6
+ Layer 5: 0.999782
7
+ Layer 6: 0.999490
8
+ Layer 7: 0.999664
9
+ Layer 8: 1.000263
10
+ Layer 9: 0.999968
11
+ Layer 10: 0.999135
12
+ Layer 11: 1.000500
13
+ Layer 12: 0.999715
14
+ Layer 13: 1.000203
15
+ Layer 14: 0.998853
16
+ Layer 15: 0.999448
17
+ Layer 16: 1.000437
18
+ Layer 17: 0.999553
19
+ Layer 18: 0.999548
20
+ Layer 19: 1.000105
21
+ Layer 20: 1.000069
22
+ Layer 21: 0.999188
23
+ Layer 22: 1.000004
24
+ Layer 23: 1.000252
checkpoints/residual_beta_clutrr_qwen_train_correct_0/test_metrics.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 0.0344
2
+ Test Accuracy: 0.9904
checkpoints/residual_beta_clutrr_qwen_train_correct_0/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 0.0344
2
+ Test Accuracy: 0.9903
checkpoints/residual_beta_clutrr_qwen_train_correct_1/config.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epochs: 5
2
+ batch_size: 16
3
+ lr: 5e-06
4
+ seed: 1
5
+ checkpoint_dir: checkpoints/clutrr_qwen/checkpoint-360
6
+ output_dir: checkpoints/residual_beta_clutrr_qwen_train_correct_1
checkpoints/residual_beta_clutrr_qwen_train_correct_1/final_betas.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30d05e9ea7d815bda294c28f9f75ab4442afc31fda0a357d33b6ecedc3988ac6
3
+ size 1264
checkpoints/residual_beta_clutrr_qwen_train_correct_1/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 0.999943
2
+ Layer 1: 1.000539
3
+ Layer 2: 1.000001
4
+ Layer 3: 0.999699
5
+ Layer 4: 0.999437
6
+ Layer 5: 0.999752
7
+ Layer 6: 0.999466
8
+ Layer 7: 0.999700
9
+ Layer 8: 1.000283
10
+ Layer 9: 0.999923
11
+ Layer 10: 0.999160
12
+ Layer 11: 1.000561
13
+ Layer 12: 0.999707
14
+ Layer 13: 1.000170
15
+ Layer 14: 0.998928
16
+ Layer 15: 0.999428
17
+ Layer 16: 1.000384
18
+ Layer 17: 0.999649
19
+ Layer 18: 0.999508
20
+ Layer 19: 1.000103
21
+ Layer 20: 1.000079
22
+ Layer 21: 0.999237
23
+ Layer 22: 0.999985
24
+ Layer 23: 1.000261
checkpoints/residual_beta_clutrr_qwen_train_correct_1/test_metrics.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 0.0344
2
+ Test Accuracy: 0.9904
checkpoints/residual_beta_clutrr_qwen_train_correct_1/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 0.0344
2
+ Test Accuracy: 0.9903
checkpoints/residual_beta_clutrr_qwen_train_correct_2/config.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epochs: 5
2
+ batch_size: 16
3
+ lr: 5e-06
4
+ seed: 2
5
+ checkpoint_dir: checkpoints/clutrr_qwen/checkpoint-360
6
+ output_dir: checkpoints/residual_beta_clutrr_qwen_train_correct_2
checkpoints/residual_beta_clutrr_qwen_train_correct_2/final_betas.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f2df33216d87dcb2b572cdb588d260a0f24ffd8e2f0f1388dbf59662d223291
3
+ size 1264
checkpoints/residual_beta_clutrr_qwen_train_correct_2/final_betas.txt ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Layer 0: 0.999950
2
+ Layer 1: 1.000561
3
+ Layer 2: 0.999992
4
+ Layer 3: 0.999692
5
+ Layer 4: 0.999499
6
+ Layer 5: 0.999717
7
+ Layer 6: 0.999415
8
+ Layer 7: 0.999687
9
+ Layer 8: 1.000277
10
+ Layer 9: 0.999916
11
+ Layer 10: 0.999232
12
+ Layer 11: 1.000572
13
+ Layer 12: 0.999707
14
+ Layer 13: 1.000171
15
+ Layer 14: 0.998923
16
+ Layer 15: 0.999370
17
+ Layer 16: 1.000451
18
+ Layer 17: 0.999624
19
+ Layer 18: 0.999540
20
+ Layer 19: 1.000095
21
+ Layer 20: 1.000082
22
+ Layer 21: 0.999218
23
+ Layer 22: 0.999989
24
+ Layer 23: 1.000250
checkpoints/residual_beta_clutrr_qwen_train_correct_2/test_metrics.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 0.0344
2
+ Test Accuracy: 0.9904
checkpoints/residual_beta_clutrr_qwen_train_correct_2/test_metrics_before.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ Test Loss: 0.0344
2
+ Test Accuracy: 0.9903