PhaaNe commited on
Commit
10a5284
·
verified ·
1 Parent(s): 9e5f341

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. ood-vifactcheck-visobert-source-source-00-s42-20260830T232831Z-f21e2f7e/model.safetensors +3 -0
  2. ood-vifactcheck-visobert-source-source-00-s43-20260831T010354Z-1a169064/model.safetensors +3 -0
  3. ood-vifactcheck-visobert-source-source-00-s44-20260831T024900Z-59e46264/model.safetensors +3 -0
  4. ood-vifactcheck-visobert-source-source-01-s42-20260830T234048Z-f21e2f7e/model.safetensors +3 -0
  5. ood-vifactcheck-visobert-source-source-01-s43-20260831T011628Z-1a169064/model.safetensors +3 -0
  6. ood-vifactcheck-visobert-source-source-01-s44-20260831T025631Z-59e46264/model.safetensors +3 -0
  7. ood-vifactcheck-visobert-source-source-02-s42-20260830T234935Z-f21e2f7e/model.safetensors +3 -0
  8. ood-vifactcheck-visobert-source-source-02-s43-20260831T012427Z-1a169064/model.safetensors +3 -0
  9. ood-vifactcheck-visobert-source-source-02-s44-20260831T030909Z-59e46264/model.safetensors +3 -0
  10. ood-vifactcheck-visobert-source-source-03-s42-20260830T235703Z-f21e2f7e/model.safetensors +3 -0
  11. ood-vifactcheck-visobert-source-source-03-s43-20260831T013703Z-1a169064/model.safetensors +3 -0
  12. ood-vifactcheck-visobert-source-source-03-s44-20260831T031636Z-59e46264/model.safetensors +3 -0
  13. ood-vifactcheck-visobert-source-source-04-s42-20260831T001152Z-f21e2f7e/model.safetensors +3 -0
  14. ood-vifactcheck-visobert-source-source-04-s42-20260831T001152Z-f21e2f7e/trainer/checkpoint-2112/special_tokens_map.json +15 -0
  15. ood-vifactcheck-visobert-source-source-04-s42-20260831T001152Z-f21e2f7e/trainer/checkpoint-2112/tokenizer.json +0 -0
  16. ood-vifactcheck-visobert-source-source-04-s42-20260831T001152Z-f21e2f7e/trainer/checkpoint-2112/trainer_state.json +763 -0
  17. ood-vifactcheck-visobert-source-source-04-s43-20260831T014836Z-1a169064/model.safetensors +3 -0
  18. ood-vifactcheck-visobert-source-source-04-s44-20260831T032410Z-59e46264/model.safetensors +3 -0
  19. ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/model.safetensors +3 -0
  20. ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-1440/special_tokens_map.json +15 -0
  21. ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-1440/tokenizer.json +0 -0
  22. ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-1440/tokenizer_config.json +56 -0
  23. ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-1440/trainer_state.json +530 -0
  24. ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-900/special_tokens_map.json +15 -0
  25. ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-900/tokenizer.json +0 -0
  26. ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-900/tokenizer_config.json +56 -0
  27. ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-900/trainer_state.json +350 -0
  28. ood-vifactcheck-visobert-source-source-05-s43-20260831T020453Z-1a169064/model.safetensors +3 -0
  29. ood-vifactcheck-visobert-source-source-05-s44-20260831T033516Z-59e46264/model.safetensors +3 -0
  30. ood-vifactcheck-visobert-source-source-06-s42-20260831T003231Z-f21e2f7e/model.safetensors +3 -0
  31. ood-vifactcheck-visobert-source-source-06-s42-20260831T003231Z-f21e2f7e/trainer/checkpoint-1480/special_tokens_map.json +15 -0
  32. ood-vifactcheck-visobert-source-source-06-s42-20260831T003231Z-f21e2f7e/trainer/checkpoint-1480/tokenizer_config.json +56 -0
  33. ood-vifactcheck-visobert-source-source-06-s43-20260831T021725Z-1a169064/model.safetensors +3 -0
  34. ood-vifactcheck-visobert-source-source-06-s44-20260831T034444Z-59e46264/model.safetensors +3 -0
  35. ood-vifactcheck-visobert-source-source-06-s44-20260831T034444Z-59e46264/trainer/checkpoint-1295/tokenizer.json +0 -0
  36. ood-vifactcheck-visobert-source-source-07-s42-20260831T004433Z-f21e2f7e/model.safetensors +3 -0
  37. ood-vifactcheck-visobert-source-source-07-s43-20260831T023232Z-1a169064/model.safetensors +3 -0
  38. ood-vifactcheck-visobert-source-source-07-s44-20260831T035525Z-59e46264/model.safetensors +3 -0
  39. ood-vifactcheck-visobert-source-source-08-s42-20260831T005402Z-f21e2f7e/model.safetensors +3 -0
  40. ood-vifactcheck-visobert-source-source-08-s43-20260831T024013Z-1a169064/model.safetensors +3 -0
  41. ood-vifactcheck-visobert-source-source-08-s44-20260831T040503Z-59e46264/model.safetensors +3 -0
  42. ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/model.safetensors +3 -0
  43. ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/model.safetensors +3 -0
  44. ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/optimizer.pt +3 -0
  45. ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/rng_state.pth +3 -0
  46. ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/scheduler.pt +3 -0
  47. ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/sentencepiece.bpe.model +3 -0
  48. ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/training_args.bin +3 -0
  49. ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1683/model.safetensors +3 -0
  50. ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1683/rng_state.pth +3 -0
ood-vifactcheck-visobert-source-source-00-s42-20260830T232831Z-f21e2f7e/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1084cabbe19a487328a8fee661c29f42223dfac7941775e07529256c8b1ac0a6
3
+ size 390297060
ood-vifactcheck-visobert-source-source-00-s43-20260831T010354Z-1a169064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b917231821cc7192e52413055d0026c9c43faa6b626763aeb61eb30d8a65d23
3
+ size 390297060
ood-vifactcheck-visobert-source-source-00-s44-20260831T024900Z-59e46264/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:febda7e3af4c6ba0098370b66137eef43eceb01176bf0767357a06425d3899d6
3
+ size 390297060
ood-vifactcheck-visobert-source-source-01-s42-20260830T234048Z-f21e2f7e/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b81d16fc7dab02226373376abedb0a35595d1106efc9373261a3e4764d0060c2
3
+ size 390297060
ood-vifactcheck-visobert-source-source-01-s43-20260831T011628Z-1a169064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6473e395cfc34c8f680dcc658f18fd13940d874a8f3d886ff13aa61b557c6cbb
3
+ size 390297060
ood-vifactcheck-visobert-source-source-01-s44-20260831T025631Z-59e46264/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b4059a592a2f86322782fa0bfcf84f3dce84f84e2019ee21029eaa97668a39
3
+ size 390297060
ood-vifactcheck-visobert-source-source-02-s42-20260830T234935Z-f21e2f7e/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d38f6ac1cd2b54093f8695b3a534144bd923cfd724d7540ac3afca7c7309772
3
+ size 390297060
ood-vifactcheck-visobert-source-source-02-s43-20260831T012427Z-1a169064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22104ec8b0f2e1b4e8b0ef1e7af9ebe09ad4cf0380afc4896cade801f9dadff1
3
+ size 390297060
ood-vifactcheck-visobert-source-source-02-s44-20260831T030909Z-59e46264/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640f4504ad725880c681b752d8a3848abd549d67fc796c3a33947a5dd2cdec11
3
+ size 390297060
ood-vifactcheck-visobert-source-source-03-s42-20260830T235703Z-f21e2f7e/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fc89a2cbb0a761176f6891e0ce15dbab910d93c74d1e9b9ee4141502a3e2ce
3
+ size 390297060
ood-vifactcheck-visobert-source-source-03-s43-20260831T013703Z-1a169064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9526beabcef79cce9f98aab7028cb96bb1d49ff116c921d490ff0b6a9b1e3ebc
3
+ size 390297060
ood-vifactcheck-visobert-source-source-03-s44-20260831T031636Z-59e46264/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a334bf3fb2fba97430c4f924e65a003b12828ce8582f330e7459a05b38035d
3
+ size 390297060
ood-vifactcheck-visobert-source-source-04-s42-20260831T001152Z-f21e2f7e/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9826caa10b4f8177525d9d997bc787903b4cac625d0a1f010467c9f6986cf7f4
3
+ size 390297060
ood-vifactcheck-visobert-source-source-04-s42-20260831T001152Z-f21e2f7e/trainer/checkpoint-2112/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
ood-vifactcheck-visobert-source-source-04-s42-20260831T001152Z-f21e2f7e/trainer/checkpoint-2112/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ood-vifactcheck-visobert-source-source-04-s42-20260831T001152Z-f21e2f7e/trainer/checkpoint-2112/trainer_state.json ADDED
@@ -0,0 +1,763 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1584,
3
+ "best_metric": 0.5827959365470929,
4
+ "best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-vifactcheck-visobert-source-source-04-s42-20260831T001152Z-f21e2f7e/trainer/checkpoint-1584",
5
+ "epoch": 12.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2112,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.14245014245014245,
14
+ "grad_norm": 22.647480010986328,
15
+ "learning_rate": 1.3636363636363636e-06,
16
+ "loss": 4.6969,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.2849002849002849,
21
+ "grad_norm": 25.382366180419922,
22
+ "learning_rate": 2.784090909090909e-06,
23
+ "loss": 4.5328,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.42735042735042733,
28
+ "grad_norm": 29.886882781982422,
29
+ "learning_rate": 4.204545454545455e-06,
30
+ "loss": 4.4957,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.5698005698005698,
35
+ "grad_norm": 27.658693313598633,
36
+ "learning_rate": 5.625e-06,
37
+ "loss": 4.4721,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.7122507122507122,
42
+ "grad_norm": 19.12157440185547,
43
+ "learning_rate": 7.045454545454546e-06,
44
+ "loss": 4.377,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.8547008547008547,
49
+ "grad_norm": 17.77869987487793,
50
+ "learning_rate": 8.465909090909091e-06,
51
+ "loss": 4.3755,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.9971509971509972,
56
+ "grad_norm": 57.97350311279297,
57
+ "learning_rate": 9.886363636363637e-06,
58
+ "loss": 4.3975,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 1.0,
63
+ "eval_accuracy": 0.4281567489114659,
64
+ "eval_loss": 1.068101406097412,
65
+ "eval_macro_f1": 0.41701292397097306,
66
+ "eval_runtime": 1.3598,
67
+ "eval_samples_per_second": 506.706,
68
+ "eval_steps_per_second": 32.359,
69
+ "eval_weighted_f1": 0.416564605324622,
70
+ "step": 176
71
+ },
72
+ {
73
+ "epoch": 1.1367521367521367,
74
+ "grad_norm": 26.81343650817871,
75
+ "learning_rate": 1.1306818181818183e-05,
76
+ "loss": 4.1715,
77
+ "step": 200
78
+ },
79
+ {
80
+ "epoch": 1.2792022792022792,
81
+ "grad_norm": 31.017099380493164,
82
+ "learning_rate": 1.2727272727272728e-05,
83
+ "loss": 4.3255,
84
+ "step": 225
85
+ },
86
+ {
87
+ "epoch": 1.4216524216524218,
88
+ "grad_norm": 31.356576919555664,
89
+ "learning_rate": 1.4147727272727274e-05,
90
+ "loss": 4.2753,
91
+ "step": 250
92
+ },
93
+ {
94
+ "epoch": 1.564102564102564,
95
+ "grad_norm": 40.33323669433594,
96
+ "learning_rate": 1.5568181818181822e-05,
97
+ "loss": 4.2271,
98
+ "step": 275
99
+ },
100
+ {
101
+ "epoch": 1.7065527065527064,
102
+ "grad_norm": 23.7972412109375,
103
+ "learning_rate": 1.6988636363636368e-05,
104
+ "loss": 4.2389,
105
+ "step": 300
106
+ },
107
+ {
108
+ "epoch": 1.849002849002849,
109
+ "grad_norm": 39.20664978027344,
110
+ "learning_rate": 1.840909090909091e-05,
111
+ "loss": 4.3281,
112
+ "step": 325
113
+ },
114
+ {
115
+ "epoch": 1.9914529914529915,
116
+ "grad_norm": 37.309452056884766,
117
+ "learning_rate": 1.9829545454545456e-05,
118
+ "loss": 4.2745,
119
+ "step": 350
120
+ },
121
+ {
122
+ "epoch": 2.0,
123
+ "eval_accuracy": 0.45573294629898403,
124
+ "eval_loss": 1.0810412168502808,
125
+ "eval_macro_f1": 0.3707354177879669,
126
+ "eval_runtime": 1.4696,
127
+ "eval_samples_per_second": 468.849,
128
+ "eval_steps_per_second": 29.941,
129
+ "eval_weighted_f1": 0.3757687195315277,
130
+ "step": 352
131
+ },
132
+ {
133
+ "epoch": 2.131054131054131,
134
+ "grad_norm": 18.360013961791992,
135
+ "learning_rate": 1.9861111111111114e-05,
136
+ "loss": 3.8592,
137
+ "step": 375
138
+ },
139
+ {
140
+ "epoch": 2.2735042735042734,
141
+ "grad_norm": 19.811275482177734,
142
+ "learning_rate": 1.9703282828282832e-05,
143
+ "loss": 3.8411,
144
+ "step": 400
145
+ },
146
+ {
147
+ "epoch": 2.415954415954416,
148
+ "grad_norm": 22.7065486907959,
149
+ "learning_rate": 1.9545454545454546e-05,
150
+ "loss": 3.6747,
151
+ "step": 425
152
+ },
153
+ {
154
+ "epoch": 2.5584045584045585,
155
+ "grad_norm": 46.72457504272461,
156
+ "learning_rate": 1.9387626262626263e-05,
157
+ "loss": 3.6057,
158
+ "step": 450
159
+ },
160
+ {
161
+ "epoch": 2.700854700854701,
162
+ "grad_norm": 27.52411651611328,
163
+ "learning_rate": 1.922979797979798e-05,
164
+ "loss": 3.5957,
165
+ "step": 475
166
+ },
167
+ {
168
+ "epoch": 2.8433048433048436,
169
+ "grad_norm": 43.00493240356445,
170
+ "learning_rate": 1.90719696969697e-05,
171
+ "loss": 3.5362,
172
+ "step": 500
173
+ },
174
+ {
175
+ "epoch": 2.9857549857549857,
176
+ "grad_norm": 22.293670654296875,
177
+ "learning_rate": 1.8914141414141416e-05,
178
+ "loss": 3.666,
179
+ "step": 525
180
+ },
181
+ {
182
+ "epoch": 3.0,
183
+ "eval_accuracy": 0.5195936139332366,
184
+ "eval_loss": 0.9567133784294128,
185
+ "eval_macro_f1": 0.5007173131879014,
186
+ "eval_runtime": 1.6699,
187
+ "eval_samples_per_second": 412.591,
188
+ "eval_steps_per_second": 26.348,
189
+ "eval_weighted_f1": 0.5030444563452333,
190
+ "step": 528
191
+ },
192
+ {
193
+ "epoch": 3.1253561253561255,
194
+ "grad_norm": 53.87973403930664,
195
+ "learning_rate": 1.8756313131313133e-05,
196
+ "loss": 3.1279,
197
+ "step": 550
198
+ },
199
+ {
200
+ "epoch": 3.267806267806268,
201
+ "grad_norm": 32.13964080810547,
202
+ "learning_rate": 1.859848484848485e-05,
203
+ "loss": 2.7206,
204
+ "step": 575
205
+ },
206
+ {
207
+ "epoch": 3.41025641025641,
208
+ "grad_norm": 33.29050064086914,
209
+ "learning_rate": 1.844065656565657e-05,
210
+ "loss": 2.7132,
211
+ "step": 600
212
+ },
213
+ {
214
+ "epoch": 3.5527065527065527,
215
+ "grad_norm": 76.17159271240234,
216
+ "learning_rate": 1.8282828282828286e-05,
217
+ "loss": 2.8156,
218
+ "step": 625
219
+ },
220
+ {
221
+ "epoch": 3.695156695156695,
222
+ "grad_norm": 28.67092514038086,
223
+ "learning_rate": 1.8125e-05,
224
+ "loss": 2.6867,
225
+ "step": 650
226
+ },
227
+ {
228
+ "epoch": 3.8376068376068377,
229
+ "grad_norm": 39.83797836303711,
230
+ "learning_rate": 1.7967171717171718e-05,
231
+ "loss": 2.7785,
232
+ "step": 675
233
+ },
234
+ {
235
+ "epoch": 3.98005698005698,
236
+ "grad_norm": 67.78004455566406,
237
+ "learning_rate": 1.7809343434343435e-05,
238
+ "loss": 2.8467,
239
+ "step": 700
240
+ },
241
+ {
242
+ "epoch": 4.0,
243
+ "eval_accuracy": 0.5239477503628447,
244
+ "eval_loss": 1.0697739124298096,
245
+ "eval_macro_f1": 0.5041346579802543,
246
+ "eval_runtime": 1.3567,
247
+ "eval_samples_per_second": 507.839,
248
+ "eval_steps_per_second": 32.431,
249
+ "eval_weighted_f1": 0.5067010462199292,
250
+ "step": 704
251
+ },
252
+ {
253
+ "epoch": 4.119658119658119,
254
+ "grad_norm": 29.25116729736328,
255
+ "learning_rate": 1.7651515151515153e-05,
256
+ "loss": 1.9684,
257
+ "step": 725
258
+ },
259
+ {
260
+ "epoch": 4.262108262108262,
261
+ "grad_norm": 138.7740478515625,
262
+ "learning_rate": 1.749368686868687e-05,
263
+ "loss": 1.8833,
264
+ "step": 750
265
+ },
266
+ {
267
+ "epoch": 4.404558404558404,
268
+ "grad_norm": 43.61983108520508,
269
+ "learning_rate": 1.7335858585858588e-05,
270
+ "loss": 2.0275,
271
+ "step": 775
272
+ },
273
+ {
274
+ "epoch": 4.547008547008547,
275
+ "grad_norm": 43.14507293701172,
276
+ "learning_rate": 1.7178030303030305e-05,
277
+ "loss": 1.9386,
278
+ "step": 800
279
+ },
280
+ {
281
+ "epoch": 4.689458689458689,
282
+ "grad_norm": 67.69963836669922,
283
+ "learning_rate": 1.7020202020202023e-05,
284
+ "loss": 1.6151,
285
+ "step": 825
286
+ },
287
+ {
288
+ "epoch": 4.831908831908832,
289
+ "grad_norm": 54.038822174072266,
290
+ "learning_rate": 1.6862373737373737e-05,
291
+ "loss": 1.7144,
292
+ "step": 850
293
+ },
294
+ {
295
+ "epoch": 4.9743589743589745,
296
+ "grad_norm": 68.24846649169922,
297
+ "learning_rate": 1.6704545454545454e-05,
298
+ "loss": 1.9561,
299
+ "step": 875
300
+ },
301
+ {
302
+ "epoch": 5.0,
303
+ "eval_accuracy": 0.5660377358490566,
304
+ "eval_loss": 1.1763917207717896,
305
+ "eval_macro_f1": 0.5619178548450664,
306
+ "eval_runtime": 1.5814,
307
+ "eval_samples_per_second": 435.694,
308
+ "eval_steps_per_second": 27.824,
309
+ "eval_weighted_f1": 0.5624988377140542,
310
+ "step": 880
311
+ },
312
+ {
313
+ "epoch": 5.113960113960114,
314
+ "grad_norm": 53.75267028808594,
315
+ "learning_rate": 1.6546717171717172e-05,
316
+ "loss": 1.2223,
317
+ "step": 900
318
+ },
319
+ {
320
+ "epoch": 5.256410256410256,
321
+ "grad_norm": 74.08851623535156,
322
+ "learning_rate": 1.638888888888889e-05,
323
+ "loss": 1.141,
324
+ "step": 925
325
+ },
326
+ {
327
+ "epoch": 5.398860398860399,
328
+ "grad_norm": 45.42808151245117,
329
+ "learning_rate": 1.6231060606060607e-05,
330
+ "loss": 1.0914,
331
+ "step": 950
332
+ },
333
+ {
334
+ "epoch": 5.5413105413105415,
335
+ "grad_norm": 51.34950637817383,
336
+ "learning_rate": 1.6073232323232324e-05,
337
+ "loss": 0.9795,
338
+ "step": 975
339
+ },
340
+ {
341
+ "epoch": 5.683760683760684,
342
+ "grad_norm": 73.9638442993164,
343
+ "learning_rate": 1.5915404040404042e-05,
344
+ "loss": 1.0929,
345
+ "step": 1000
346
+ },
347
+ {
348
+ "epoch": 5.8262108262108265,
349
+ "grad_norm": 41.8527717590332,
350
+ "learning_rate": 1.575757575757576e-05,
351
+ "loss": 1.1185,
352
+ "step": 1025
353
+ },
354
+ {
355
+ "epoch": 5.968660968660968,
356
+ "grad_norm": 109.64105224609375,
357
+ "learning_rate": 1.5599747474747477e-05,
358
+ "loss": 0.9814,
359
+ "step": 1050
360
+ },
361
+ {
362
+ "epoch": 6.0,
363
+ "eval_accuracy": 0.5529753265602322,
364
+ "eval_loss": 1.7165353298187256,
365
+ "eval_macro_f1": 0.5448369193384395,
366
+ "eval_runtime": 1.3346,
367
+ "eval_samples_per_second": 516.259,
368
+ "eval_steps_per_second": 32.969,
369
+ "eval_weighted_f1": 0.5464179491770302,
370
+ "step": 1056
371
+ },
372
+ {
373
+ "epoch": 6.1082621082621085,
374
+ "grad_norm": 57.110198974609375,
375
+ "learning_rate": 1.544191919191919e-05,
376
+ "loss": 0.811,
377
+ "step": 1075
378
+ },
379
+ {
380
+ "epoch": 6.250712250712251,
381
+ "grad_norm": 56.78047561645508,
382
+ "learning_rate": 1.528409090909091e-05,
383
+ "loss": 0.4878,
384
+ "step": 1100
385
+ },
386
+ {
387
+ "epoch": 6.3931623931623935,
388
+ "grad_norm": 53.50935745239258,
389
+ "learning_rate": 1.5126262626262626e-05,
390
+ "loss": 0.7522,
391
+ "step": 1125
392
+ },
393
+ {
394
+ "epoch": 6.535612535612536,
395
+ "grad_norm": 14.805171966552734,
396
+ "learning_rate": 1.4968434343434344e-05,
397
+ "loss": 0.619,
398
+ "step": 1150
399
+ },
400
+ {
401
+ "epoch": 6.678062678062678,
402
+ "grad_norm": 75.20733642578125,
403
+ "learning_rate": 1.4810606060606061e-05,
404
+ "loss": 0.5579,
405
+ "step": 1175
406
+ },
407
+ {
408
+ "epoch": 6.82051282051282,
409
+ "grad_norm": 46.543548583984375,
410
+ "learning_rate": 1.4652777777777779e-05,
411
+ "loss": 0.6341,
412
+ "step": 1200
413
+ },
414
+ {
415
+ "epoch": 6.962962962962963,
416
+ "grad_norm": 97.66300201416016,
417
+ "learning_rate": 1.4494949494949494e-05,
418
+ "loss": 0.6457,
419
+ "step": 1225
420
+ },
421
+ {
422
+ "epoch": 7.0,
423
+ "eval_accuracy": 0.5703918722786647,
424
+ "eval_loss": 1.898086667060852,
425
+ "eval_macro_f1": 0.5672731392573087,
426
+ "eval_runtime": 1.7464,
427
+ "eval_samples_per_second": 394.522,
428
+ "eval_steps_per_second": 25.194,
429
+ "eval_weighted_f1": 0.5682004750295354,
430
+ "step": 1232
431
+ },
432
+ {
433
+ "epoch": 7.102564102564102,
434
+ "grad_norm": 46.35641098022461,
435
+ "learning_rate": 1.4337121212121212e-05,
436
+ "loss": 0.4373,
437
+ "step": 1250
438
+ },
439
+ {
440
+ "epoch": 7.245014245014245,
441
+ "grad_norm": 36.77285385131836,
442
+ "learning_rate": 1.4179292929292931e-05,
443
+ "loss": 0.2564,
444
+ "step": 1275
445
+ },
446
+ {
447
+ "epoch": 7.387464387464387,
448
+ "grad_norm": 105.87223815917969,
449
+ "learning_rate": 1.4021464646464649e-05,
450
+ "loss": 0.5362,
451
+ "step": 1300
452
+ },
453
+ {
454
+ "epoch": 7.52991452991453,
455
+ "grad_norm": 10.142257690429688,
456
+ "learning_rate": 1.3863636363636366e-05,
457
+ "loss": 0.2968,
458
+ "step": 1325
459
+ },
460
+ {
461
+ "epoch": 7.672364672364672,
462
+ "grad_norm": 7.8140692710876465,
463
+ "learning_rate": 1.3705808080808084e-05,
464
+ "loss": 0.4024,
465
+ "step": 1350
466
+ },
467
+ {
468
+ "epoch": 7.814814814814815,
469
+ "grad_norm": 99.27178192138672,
470
+ "learning_rate": 1.35479797979798e-05,
471
+ "loss": 0.2586,
472
+ "step": 1375
473
+ },
474
+ {
475
+ "epoch": 7.957264957264957,
476
+ "grad_norm": 84.80584716796875,
477
+ "learning_rate": 1.3390151515151517e-05,
478
+ "loss": 0.4128,
479
+ "step": 1400
480
+ },
481
+ {
482
+ "epoch": 8.0,
483
+ "eval_accuracy": 0.579100145137881,
484
+ "eval_loss": 2.4165353775024414,
485
+ "eval_macro_f1": 0.5730352518211279,
486
+ "eval_runtime": 1.4796,
487
+ "eval_samples_per_second": 465.668,
488
+ "eval_steps_per_second": 29.738,
489
+ "eval_weighted_f1": 0.5730396492373024,
490
+ "step": 1408
491
+ },
492
+ {
493
+ "epoch": 8.096866096866098,
494
+ "grad_norm": 20.056537628173828,
495
+ "learning_rate": 1.3232323232323234e-05,
496
+ "loss": 0.4127,
497
+ "step": 1425
498
+ },
499
+ {
500
+ "epoch": 8.239316239316238,
501
+ "grad_norm": 54.585140228271484,
502
+ "learning_rate": 1.3074494949494952e-05,
503
+ "loss": 0.2561,
504
+ "step": 1450
505
+ },
506
+ {
507
+ "epoch": 8.381766381766381,
508
+ "grad_norm": 24.0261287689209,
509
+ "learning_rate": 1.2916666666666668e-05,
510
+ "loss": 0.2442,
511
+ "step": 1475
512
+ },
513
+ {
514
+ "epoch": 8.524216524216524,
515
+ "grad_norm": 121.47981262207031,
516
+ "learning_rate": 1.2758838383838385e-05,
517
+ "loss": 0.2792,
518
+ "step": 1500
519
+ },
520
+ {
521
+ "epoch": 8.666666666666666,
522
+ "grad_norm": 7.25212287902832,
523
+ "learning_rate": 1.2601010101010103e-05,
524
+ "loss": 0.3819,
525
+ "step": 1525
526
+ },
527
+ {
528
+ "epoch": 8.809116809116809,
529
+ "grad_norm": 2.060002326965332,
530
+ "learning_rate": 1.244318181818182e-05,
531
+ "loss": 0.2825,
532
+ "step": 1550
533
+ },
534
+ {
535
+ "epoch": 8.951566951566951,
536
+ "grad_norm": 25.59327507019043,
537
+ "learning_rate": 1.2285353535353536e-05,
538
+ "loss": 0.1745,
539
+ "step": 1575
540
+ },
541
+ {
542
+ "epoch": 9.0,
543
+ "eval_accuracy": 0.5863570391872278,
544
+ "eval_loss": 2.7472100257873535,
545
+ "eval_macro_f1": 0.5827959365470929,
546
+ "eval_runtime": 1.3505,
547
+ "eval_samples_per_second": 510.197,
548
+ "eval_steps_per_second": 32.582,
549
+ "eval_weighted_f1": 0.5833044385279388,
550
+ "step": 1584
551
+ },
552
+ {
553
+ "epoch": 9.091168091168091,
554
+ "grad_norm": 1.2540035247802734,
555
+ "learning_rate": 1.2127525252525254e-05,
556
+ "loss": 0.1561,
557
+ "step": 1600
558
+ },
559
+ {
560
+ "epoch": 9.233618233618234,
561
+ "grad_norm": 0.644784688949585,
562
+ "learning_rate": 1.1969696969696971e-05,
563
+ "loss": 0.2235,
564
+ "step": 1625
565
+ },
566
+ {
567
+ "epoch": 9.376068376068377,
568
+ "grad_norm": 35.13825607299805,
569
+ "learning_rate": 1.1811868686868689e-05,
570
+ "loss": 0.2002,
571
+ "step": 1650
572
+ },
573
+ {
574
+ "epoch": 9.518518518518519,
575
+ "grad_norm": 113.64639282226562,
576
+ "learning_rate": 1.1654040404040406e-05,
577
+ "loss": 0.3835,
578
+ "step": 1675
579
+ },
580
+ {
581
+ "epoch": 9.660968660968662,
582
+ "grad_norm": 6.9370646476745605,
583
+ "learning_rate": 1.1496212121212122e-05,
584
+ "loss": 0.1197,
585
+ "step": 1700
586
+ },
587
+ {
588
+ "epoch": 9.803418803418804,
589
+ "grad_norm": 1.7939224243164062,
590
+ "learning_rate": 1.133838383838384e-05,
591
+ "loss": 0.3838,
592
+ "step": 1725
593
+ },
594
+ {
595
+ "epoch": 9.945868945868947,
596
+ "grad_norm": 62.85049819946289,
597
+ "learning_rate": 1.1180555555555557e-05,
598
+ "loss": 0.1329,
599
+ "step": 1750
600
+ },
601
+ {
602
+ "epoch": 10.0,
603
+ "eval_accuracy": 0.5689404934687954,
604
+ "eval_loss": 3.035370349884033,
605
+ "eval_macro_f1": 0.5618373265259172,
606
+ "eval_runtime": 1.3952,
607
+ "eval_samples_per_second": 493.844,
608
+ "eval_steps_per_second": 31.537,
609
+ "eval_weighted_f1": 0.5619748013807669,
610
+ "step": 1760
611
+ },
612
+ {
613
+ "epoch": 10.085470085470085,
614
+ "grad_norm": 111.22190856933594,
615
+ "learning_rate": 1.1022727272727275e-05,
616
+ "loss": 0.1885,
617
+ "step": 1775
618
+ },
619
+ {
620
+ "epoch": 10.227920227920228,
621
+ "grad_norm": 38.88776397705078,
622
+ "learning_rate": 1.086489898989899e-05,
623
+ "loss": 0.1017,
624
+ "step": 1800
625
+ },
626
+ {
627
+ "epoch": 10.37037037037037,
628
+ "grad_norm": 103.15046691894531,
629
+ "learning_rate": 1.0707070707070708e-05,
630
+ "loss": 0.1179,
631
+ "step": 1825
632
+ },
633
+ {
634
+ "epoch": 10.512820512820513,
635
+ "grad_norm": 0.7128024697303772,
636
+ "learning_rate": 1.0549242424242425e-05,
637
+ "loss": 0.1103,
638
+ "step": 1850
639
+ },
640
+ {
641
+ "epoch": 10.655270655270655,
642
+ "grad_norm": 4.258548259735107,
643
+ "learning_rate": 1.0391414141414143e-05,
644
+ "loss": 0.1594,
645
+ "step": 1875
646
+ },
647
+ {
648
+ "epoch": 10.797720797720798,
649
+ "grad_norm": 22.149688720703125,
650
+ "learning_rate": 1.0233585858585859e-05,
651
+ "loss": 0.1657,
652
+ "step": 1900
653
+ },
654
+ {
655
+ "epoch": 10.94017094017094,
656
+ "grad_norm": 133.43955993652344,
657
+ "learning_rate": 1.0075757575757576e-05,
658
+ "loss": 0.0928,
659
+ "step": 1925
660
+ },
661
+ {
662
+ "epoch": 11.0,
663
+ "eval_accuracy": 0.5602322206095791,
664
+ "eval_loss": 3.5120935440063477,
665
+ "eval_macro_f1": 0.5604230704352063,
666
+ "eval_runtime": 1.4318,
667
+ "eval_samples_per_second": 481.213,
668
+ "eval_steps_per_second": 30.731,
669
+ "eval_weighted_f1": 0.5609388408435853,
670
+ "step": 1936
671
+ },
672
+ {
673
+ "epoch": 11.079772079772079,
674
+ "grad_norm": 35.31703567504883,
675
+ "learning_rate": 9.917929292929294e-06,
676
+ "loss": 0.0628,
677
+ "step": 1950
678
+ },
679
+ {
680
+ "epoch": 11.222222222222221,
681
+ "grad_norm": 80.0780029296875,
682
+ "learning_rate": 9.760101010101011e-06,
683
+ "loss": 0.1374,
684
+ "step": 1975
685
+ },
686
+ {
687
+ "epoch": 11.364672364672364,
688
+ "grad_norm": 129.75169372558594,
689
+ "learning_rate": 9.602272727272727e-06,
690
+ "loss": 0.0809,
691
+ "step": 2000
692
+ },
693
+ {
694
+ "epoch": 11.507122507122507,
695
+ "grad_norm": 0.19092045724391937,
696
+ "learning_rate": 9.444444444444445e-06,
697
+ "loss": 0.1343,
698
+ "step": 2025
699
+ },
700
+ {
701
+ "epoch": 11.649572649572649,
702
+ "grad_norm": 80.83219146728516,
703
+ "learning_rate": 9.286616161616162e-06,
704
+ "loss": 0.1421,
705
+ "step": 2050
706
+ },
707
+ {
708
+ "epoch": 11.792022792022792,
709
+ "grad_norm": 1.9926334619522095,
710
+ "learning_rate": 9.12878787878788e-06,
711
+ "loss": 0.082,
712
+ "step": 2075
713
+ },
714
+ {
715
+ "epoch": 11.934472934472934,
716
+ "grad_norm": 0.286663681268692,
717
+ "learning_rate": 8.970959595959597e-06,
718
+ "loss": 0.1033,
719
+ "step": 2100
720
+ },
721
+ {
722
+ "epoch": 12.0,
723
+ "eval_accuracy": 0.5747460087082729,
724
+ "eval_loss": 3.7466416358947754,
725
+ "eval_macro_f1": 0.5682897048750707,
726
+ "eval_runtime": 1.5813,
727
+ "eval_samples_per_second": 435.716,
728
+ "eval_steps_per_second": 27.825,
729
+ "eval_weighted_f1": 0.5687016960761164,
730
+ "step": 2112
731
+ }
732
+ ],
733
+ "logging_steps": 25,
734
+ "max_steps": 3520,
735
+ "num_input_tokens_seen": 0,
736
+ "num_train_epochs": 20,
737
+ "save_steps": 500,
738
+ "stateful_callbacks": {
739
+ "EarlyStoppingCallback": {
740
+ "args": {
741
+ "early_stopping_patience": 3,
742
+ "early_stopping_threshold": 0.0
743
+ },
744
+ "attributes": {
745
+ "early_stopping_patience_counter": 3
746
+ }
747
+ },
748
+ "TrainerControl": {
749
+ "args": {
750
+ "should_epoch_stop": false,
751
+ "should_evaluate": false,
752
+ "should_log": false,
753
+ "should_save": true,
754
+ "should_training_stop": true
755
+ },
756
+ "attributes": {}
757
+ }
758
+ },
759
+ "total_flos": 0.0,
760
+ "train_batch_size": 8,
761
+ "trial_name": null,
762
+ "trial_params": null
763
+ }
ood-vifactcheck-visobert-source-source-04-s43-20260831T014836Z-1a169064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eda61907fc3caac514e5a0547be9e7dafc76d75aee519e2ce16b96e26cb3ea1
3
+ size 390297060
ood-vifactcheck-visobert-source-source-04-s44-20260831T032410Z-59e46264/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896bc7d72e87dd904a243ca9b29330fc96a7f981bdcd96fc93701bf1e65a5201
3
+ size 390297060
ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:030009374c0d8a05e0329c49664adc7f7440614e6bf066fc458e636dafe5f539
3
+ size 390297060
ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-1440/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-1440/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-1440/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "15001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-1440/trainer_state.json ADDED
@@ -0,0 +1,530 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 900,
3
+ "best_metric": 0.5820708900600206,
4
+ "best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-900",
5
+ "epoch": 8.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1440,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1388888888888889,
14
+ "grad_norm": 24.826852798461914,
15
+ "learning_rate": 1.3333333333333334e-06,
16
+ "loss": 4.6608,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.2777777777777778,
21
+ "grad_norm": 24.02608299255371,
22
+ "learning_rate": 2.7222222222222224e-06,
23
+ "loss": 4.5105,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.4166666666666667,
28
+ "grad_norm": 19.22039794921875,
29
+ "learning_rate": 4.111111111111111e-06,
30
+ "loss": 4.4833,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.5555555555555556,
35
+ "grad_norm": 23.38973045349121,
36
+ "learning_rate": 5.500000000000001e-06,
37
+ "loss": 4.4073,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.6944444444444444,
42
+ "grad_norm": 17.526378631591797,
43
+ "learning_rate": 6.88888888888889e-06,
44
+ "loss": 4.4816,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.8333333333333334,
49
+ "grad_norm": 17.242778778076172,
50
+ "learning_rate": 8.277777777777778e-06,
51
+ "loss": 4.4028,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.9722222222222222,
56
+ "grad_norm": 21.158187866210938,
57
+ "learning_rate": 9.666666666666667e-06,
58
+ "loss": 4.4702,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 1.0,
63
+ "eval_accuracy": 0.48507462686567165,
64
+ "eval_loss": 1.0395435094833374,
65
+ "eval_macro_f1": 0.48157349896480334,
66
+ "eval_runtime": 1.3823,
67
+ "eval_samples_per_second": 484.705,
68
+ "eval_steps_per_second": 30.384,
69
+ "eval_weighted_f1": 0.48171286425017773,
70
+ "step": 180
71
+ },
72
+ {
73
+ "epoch": 1.1111111111111112,
74
+ "grad_norm": 37.203067779541016,
75
+ "learning_rate": 1.1055555555555557e-05,
76
+ "loss": 4.2792,
77
+ "step": 200
78
+ },
79
+ {
80
+ "epoch": 1.25,
81
+ "grad_norm": 32.83223342895508,
82
+ "learning_rate": 1.2444444444444446e-05,
83
+ "loss": 4.1883,
84
+ "step": 225
85
+ },
86
+ {
87
+ "epoch": 1.3888888888888888,
88
+ "grad_norm": 17.162460327148438,
89
+ "learning_rate": 1.3833333333333334e-05,
90
+ "loss": 4.2907,
91
+ "step": 250
92
+ },
93
+ {
94
+ "epoch": 1.5277777777777777,
95
+ "grad_norm": 27.619388580322266,
96
+ "learning_rate": 1.5222222222222223e-05,
97
+ "loss": 4.3111,
98
+ "step": 275
99
+ },
100
+ {
101
+ "epoch": 1.6666666666666665,
102
+ "grad_norm": 27.325172424316406,
103
+ "learning_rate": 1.6611111111111113e-05,
104
+ "loss": 4.2018,
105
+ "step": 300
106
+ },
107
+ {
108
+ "epoch": 1.8055555555555556,
109
+ "grad_norm": 21.307151794433594,
110
+ "learning_rate": 1.8e-05,
111
+ "loss": 4.1696,
112
+ "step": 325
113
+ },
114
+ {
115
+ "epoch": 1.9444444444444444,
116
+ "grad_norm": 15.286060333251953,
117
+ "learning_rate": 1.938888888888889e-05,
118
+ "loss": 4.2193,
119
+ "step": 350
120
+ },
121
+ {
122
+ "epoch": 2.0,
123
+ "eval_accuracy": 0.4791044776119403,
124
+ "eval_loss": 1.0072804689407349,
125
+ "eval_macro_f1": 0.44860799046491584,
126
+ "eval_runtime": 1.4456,
127
+ "eval_samples_per_second": 463.46,
128
+ "eval_steps_per_second": 29.053,
129
+ "eval_weighted_f1": 0.44815622546829526,
130
+ "step": 360
131
+ },
132
+ {
133
+ "epoch": 2.0833333333333335,
134
+ "grad_norm": 26.641504287719727,
135
+ "learning_rate": 1.991358024691358e-05,
136
+ "loss": 3.9302,
137
+ "step": 375
138
+ },
139
+ {
140
+ "epoch": 2.2222222222222223,
141
+ "grad_norm": 21.551965713500977,
142
+ "learning_rate": 1.975925925925926e-05,
143
+ "loss": 3.8501,
144
+ "step": 400
145
+ },
146
+ {
147
+ "epoch": 2.361111111111111,
148
+ "grad_norm": 41.141807556152344,
149
+ "learning_rate": 1.960493827160494e-05,
150
+ "loss": 3.7357,
151
+ "step": 425
152
+ },
153
+ {
154
+ "epoch": 2.5,
155
+ "grad_norm": 29.060522079467773,
156
+ "learning_rate": 1.945061728395062e-05,
157
+ "loss": 3.69,
158
+ "step": 450
159
+ },
160
+ {
161
+ "epoch": 2.638888888888889,
162
+ "grad_norm": 57.155418395996094,
163
+ "learning_rate": 1.92962962962963e-05,
164
+ "loss": 3.5694,
165
+ "step": 475
166
+ },
167
+ {
168
+ "epoch": 2.7777777777777777,
169
+ "grad_norm": 22.63286018371582,
170
+ "learning_rate": 1.914197530864198e-05,
171
+ "loss": 3.7485,
172
+ "step": 500
173
+ },
174
+ {
175
+ "epoch": 2.9166666666666665,
176
+ "grad_norm": 23.279579162597656,
177
+ "learning_rate": 1.8987654320987657e-05,
178
+ "loss": 3.5465,
179
+ "step": 525
180
+ },
181
+ {
182
+ "epoch": 3.0,
183
+ "eval_accuracy": 0.5552238805970149,
184
+ "eval_loss": 0.9134945869445801,
185
+ "eval_macro_f1": 0.545440723371018,
186
+ "eval_runtime": 1.3629,
187
+ "eval_samples_per_second": 491.606,
188
+ "eval_steps_per_second": 30.817,
189
+ "eval_weighted_f1": 0.5444931386875956,
190
+ "step": 540
191
+ },
192
+ {
193
+ "epoch": 3.0555555555555554,
194
+ "grad_norm": 36.72185516357422,
195
+ "learning_rate": 1.8833333333333335e-05,
196
+ "loss": 3.4629,
197
+ "step": 550
198
+ },
199
+ {
200
+ "epoch": 3.1944444444444446,
201
+ "grad_norm": 31.557235717773438,
202
+ "learning_rate": 1.8679012345679013e-05,
203
+ "loss": 2.8424,
204
+ "step": 575
205
+ },
206
+ {
207
+ "epoch": 3.3333333333333335,
208
+ "grad_norm": 62.97331237792969,
209
+ "learning_rate": 1.8524691358024694e-05,
210
+ "loss": 2.9011,
211
+ "step": 600
212
+ },
213
+ {
214
+ "epoch": 3.4722222222222223,
215
+ "grad_norm": 42.78829574584961,
216
+ "learning_rate": 1.837037037037037e-05,
217
+ "loss": 2.7434,
218
+ "step": 625
219
+ },
220
+ {
221
+ "epoch": 3.611111111111111,
222
+ "grad_norm": 37.28730010986328,
223
+ "learning_rate": 1.821604938271605e-05,
224
+ "loss": 2.8436,
225
+ "step": 650
226
+ },
227
+ {
228
+ "epoch": 3.75,
229
+ "grad_norm": 52.72061538696289,
230
+ "learning_rate": 1.806172839506173e-05,
231
+ "loss": 2.8424,
232
+ "step": 675
233
+ },
234
+ {
235
+ "epoch": 3.888888888888889,
236
+ "grad_norm": 33.707733154296875,
237
+ "learning_rate": 1.7907407407407408e-05,
238
+ "loss": 3.0866,
239
+ "step": 700
240
+ },
241
+ {
242
+ "epoch": 4.0,
243
+ "eval_accuracy": 0.582089552238806,
244
+ "eval_loss": 0.8941500186920166,
245
+ "eval_macro_f1": 0.5803242075928376,
246
+ "eval_runtime": 1.4191,
247
+ "eval_samples_per_second": 472.137,
248
+ "eval_steps_per_second": 29.597,
249
+ "eval_weighted_f1": 0.5801379238657683,
250
+ "step": 720
251
+ },
252
+ {
253
+ "epoch": 4.027777777777778,
254
+ "grad_norm": 43.675987243652344,
255
+ "learning_rate": 1.775308641975309e-05,
256
+ "loss": 2.6387,
257
+ "step": 725
258
+ },
259
+ {
260
+ "epoch": 4.166666666666667,
261
+ "grad_norm": 39.623165130615234,
262
+ "learning_rate": 1.7598765432098767e-05,
263
+ "loss": 1.9852,
264
+ "step": 750
265
+ },
266
+ {
267
+ "epoch": 4.305555555555555,
268
+ "grad_norm": 45.12331008911133,
269
+ "learning_rate": 1.7444444444444448e-05,
270
+ "loss": 1.9036,
271
+ "step": 775
272
+ },
273
+ {
274
+ "epoch": 4.444444444444445,
275
+ "grad_norm": 54.73080825805664,
276
+ "learning_rate": 1.7290123456790125e-05,
277
+ "loss": 1.8365,
278
+ "step": 800
279
+ },
280
+ {
281
+ "epoch": 4.583333333333333,
282
+ "grad_norm": 84.51736450195312,
283
+ "learning_rate": 1.7135802469135806e-05,
284
+ "loss": 1.9016,
285
+ "step": 825
286
+ },
287
+ {
288
+ "epoch": 4.722222222222222,
289
+ "grad_norm": 39.228389739990234,
290
+ "learning_rate": 1.6981481481481484e-05,
291
+ "loss": 1.9351,
292
+ "step": 850
293
+ },
294
+ {
295
+ "epoch": 4.861111111111111,
296
+ "grad_norm": 33.56704330444336,
297
+ "learning_rate": 1.6827160493827162e-05,
298
+ "loss": 1.5536,
299
+ "step": 875
300
+ },
301
+ {
302
+ "epoch": 5.0,
303
+ "grad_norm": 57.18074035644531,
304
+ "learning_rate": 1.667283950617284e-05,
305
+ "loss": 2.0261,
306
+ "step": 900
307
+ },
308
+ {
309
+ "epoch": 5.0,
310
+ "eval_accuracy": 0.5791044776119403,
311
+ "eval_loss": 1.0985665321350098,
312
+ "eval_macro_f1": 0.5820708900600206,
313
+ "eval_runtime": 1.4123,
314
+ "eval_samples_per_second": 474.416,
315
+ "eval_steps_per_second": 29.74,
316
+ "eval_weighted_f1": 0.5818792704789624,
317
+ "step": 900
318
+ },
319
+ {
320
+ "epoch": 5.138888888888889,
321
+ "grad_norm": 46.81850814819336,
322
+ "learning_rate": 1.651851851851852e-05,
323
+ "loss": 1.061,
324
+ "step": 925
325
+ },
326
+ {
327
+ "epoch": 5.277777777777778,
328
+ "grad_norm": 39.9931640625,
329
+ "learning_rate": 1.6364197530864198e-05,
330
+ "loss": 0.9309,
331
+ "step": 950
332
+ },
333
+ {
334
+ "epoch": 5.416666666666667,
335
+ "grad_norm": 43.532955169677734,
336
+ "learning_rate": 1.6209876543209876e-05,
337
+ "loss": 1.0138,
338
+ "step": 975
339
+ },
340
+ {
341
+ "epoch": 5.555555555555555,
342
+ "grad_norm": 72.61285400390625,
343
+ "learning_rate": 1.6055555555555557e-05,
344
+ "loss": 0.9342,
345
+ "step": 1000
346
+ },
347
+ {
348
+ "epoch": 5.694444444444445,
349
+ "grad_norm": 76.93058013916016,
350
+ "learning_rate": 1.5901234567901235e-05,
351
+ "loss": 1.0929,
352
+ "step": 1025
353
+ },
354
+ {
355
+ "epoch": 5.833333333333333,
356
+ "grad_norm": 43.552799224853516,
357
+ "learning_rate": 1.5746913580246916e-05,
358
+ "loss": 1.1078,
359
+ "step": 1050
360
+ },
361
+ {
362
+ "epoch": 5.972222222222222,
363
+ "grad_norm": 51.12466049194336,
364
+ "learning_rate": 1.5592592592592593e-05,
365
+ "loss": 0.9255,
366
+ "step": 1075
367
+ },
368
+ {
369
+ "epoch": 6.0,
370
+ "eval_accuracy": 0.5850746268656717,
371
+ "eval_loss": 1.3756561279296875,
372
+ "eval_macro_f1": 0.5802423525934683,
373
+ "eval_runtime": 1.3476,
374
+ "eval_samples_per_second": 497.174,
375
+ "eval_steps_per_second": 31.166,
376
+ "eval_weighted_f1": 0.5808070994223503,
377
+ "step": 1080
378
+ },
379
+ {
380
+ "epoch": 6.111111111111111,
381
+ "grad_norm": 61.43894577026367,
382
+ "learning_rate": 1.5438271604938274e-05,
383
+ "loss": 0.8839,
384
+ "step": 1100
385
+ },
386
+ {
387
+ "epoch": 6.25,
388
+ "grad_norm": 65.20443725585938,
389
+ "learning_rate": 1.5283950617283952e-05,
390
+ "loss": 0.5466,
391
+ "step": 1125
392
+ },
393
+ {
394
+ "epoch": 6.388888888888889,
395
+ "grad_norm": 58.19245147705078,
396
+ "learning_rate": 1.5129629629629632e-05,
397
+ "loss": 0.4801,
398
+ "step": 1150
399
+ },
400
+ {
401
+ "epoch": 6.527777777777778,
402
+ "grad_norm": 34.7457160949707,
403
+ "learning_rate": 1.4975308641975311e-05,
404
+ "loss": 0.4932,
405
+ "step": 1175
406
+ },
407
+ {
408
+ "epoch": 6.666666666666667,
409
+ "grad_norm": 80.92588806152344,
410
+ "learning_rate": 1.4820987654320989e-05,
411
+ "loss": 0.7618,
412
+ "step": 1200
413
+ },
414
+ {
415
+ "epoch": 6.805555555555555,
416
+ "grad_norm": 34.988346099853516,
417
+ "learning_rate": 1.4666666666666666e-05,
418
+ "loss": 0.6381,
419
+ "step": 1225
420
+ },
421
+ {
422
+ "epoch": 6.944444444444445,
423
+ "grad_norm": 42.942352294921875,
424
+ "learning_rate": 1.4512345679012347e-05,
425
+ "loss": 0.5206,
426
+ "step": 1250
427
+ },
428
+ {
429
+ "epoch": 7.0,
430
+ "eval_accuracy": 0.5462686567164179,
431
+ "eval_loss": 2.1072909832000732,
432
+ "eval_macro_f1": 0.5372260981559058,
433
+ "eval_runtime": 1.5196,
434
+ "eval_samples_per_second": 440.919,
435
+ "eval_steps_per_second": 27.64,
436
+ "eval_weighted_f1": 0.5388465226019322,
437
+ "step": 1260
438
+ },
439
+ {
440
+ "epoch": 7.083333333333333,
441
+ "grad_norm": 26.077503204345703,
442
+ "learning_rate": 1.4358024691358025e-05,
443
+ "loss": 0.4734,
444
+ "step": 1275
445
+ },
446
+ {
447
+ "epoch": 7.222222222222222,
448
+ "grad_norm": 115.0558090209961,
449
+ "learning_rate": 1.4203703703703704e-05,
450
+ "loss": 0.2917,
451
+ "step": 1300
452
+ },
453
+ {
454
+ "epoch": 7.361111111111111,
455
+ "grad_norm": 6.695279121398926,
456
+ "learning_rate": 1.4049382716049384e-05,
457
+ "loss": 0.3978,
458
+ "step": 1325
459
+ },
460
+ {
461
+ "epoch": 7.5,
462
+ "grad_norm": 134.19117736816406,
463
+ "learning_rate": 1.3895061728395063e-05,
464
+ "loss": 0.4411,
465
+ "step": 1350
466
+ },
467
+ {
468
+ "epoch": 7.638888888888889,
469
+ "grad_norm": 64.8404541015625,
470
+ "learning_rate": 1.3740740740740741e-05,
471
+ "loss": 0.3344,
472
+ "step": 1375
473
+ },
474
+ {
475
+ "epoch": 7.777777777777778,
476
+ "grad_norm": 46.805789947509766,
477
+ "learning_rate": 1.3586419753086422e-05,
478
+ "loss": 0.3393,
479
+ "step": 1400
480
+ },
481
+ {
482
+ "epoch": 7.916666666666667,
483
+ "grad_norm": 5.838100433349609,
484
+ "learning_rate": 1.34320987654321e-05,
485
+ "loss": 0.4422,
486
+ "step": 1425
487
+ },
488
+ {
489
+ "epoch": 8.0,
490
+ "eval_accuracy": 0.5507462686567164,
491
+ "eval_loss": 2.24959397315979,
492
+ "eval_macro_f1": 0.548423284909714,
493
+ "eval_runtime": 1.3223,
494
+ "eval_samples_per_second": 506.684,
495
+ "eval_steps_per_second": 31.762,
496
+ "eval_weighted_f1": 0.5493094451388693,
497
+ "step": 1440
498
+ }
499
+ ],
500
+ "logging_steps": 25,
501
+ "max_steps": 3600,
502
+ "num_input_tokens_seen": 0,
503
+ "num_train_epochs": 20,
504
+ "save_steps": 500,
505
+ "stateful_callbacks": {
506
+ "EarlyStoppingCallback": {
507
+ "args": {
508
+ "early_stopping_patience": 3,
509
+ "early_stopping_threshold": 0.0
510
+ },
511
+ "attributes": {
512
+ "early_stopping_patience_counter": 3
513
+ }
514
+ },
515
+ "TrainerControl": {
516
+ "args": {
517
+ "should_epoch_stop": false,
518
+ "should_evaluate": false,
519
+ "should_log": false,
520
+ "should_save": true,
521
+ "should_training_stop": true
522
+ },
523
+ "attributes": {}
524
+ }
525
+ },
526
+ "total_flos": 0.0,
527
+ "train_batch_size": 8,
528
+ "trial_name": null,
529
+ "trial_params": null
530
+ }
ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-900/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-900/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-900/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "15001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-900/trainer_state.json ADDED
@@ -0,0 +1,350 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 900,
3
+ "best_metric": 0.5820708900600206,
4
+ "best_model_checkpoint": "/root/VNEncoder/results/checkpoints/ood-vifactcheck-visobert-source-source-05-s42-20260831T002403Z-f21e2f7e/trainer/checkpoint-900",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 900,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1388888888888889,
14
+ "grad_norm": 24.826852798461914,
15
+ "learning_rate": 1.3333333333333334e-06,
16
+ "loss": 4.6608,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.2777777777777778,
21
+ "grad_norm": 24.02608299255371,
22
+ "learning_rate": 2.7222222222222224e-06,
23
+ "loss": 4.5105,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.4166666666666667,
28
+ "grad_norm": 19.22039794921875,
29
+ "learning_rate": 4.111111111111111e-06,
30
+ "loss": 4.4833,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.5555555555555556,
35
+ "grad_norm": 23.38973045349121,
36
+ "learning_rate": 5.500000000000001e-06,
37
+ "loss": 4.4073,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.6944444444444444,
42
+ "grad_norm": 17.526378631591797,
43
+ "learning_rate": 6.88888888888889e-06,
44
+ "loss": 4.4816,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 0.8333333333333334,
49
+ "grad_norm": 17.242778778076172,
50
+ "learning_rate": 8.277777777777778e-06,
51
+ "loss": 4.4028,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 0.9722222222222222,
56
+ "grad_norm": 21.158187866210938,
57
+ "learning_rate": 9.666666666666667e-06,
58
+ "loss": 4.4702,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 1.0,
63
+ "eval_accuracy": 0.48507462686567165,
64
+ "eval_loss": 1.0395435094833374,
65
+ "eval_macro_f1": 0.48157349896480334,
66
+ "eval_runtime": 1.3823,
67
+ "eval_samples_per_second": 484.705,
68
+ "eval_steps_per_second": 30.384,
69
+ "eval_weighted_f1": 0.48171286425017773,
70
+ "step": 180
71
+ },
72
+ {
73
+ "epoch": 1.1111111111111112,
74
+ "grad_norm": 37.203067779541016,
75
+ "learning_rate": 1.1055555555555557e-05,
76
+ "loss": 4.2792,
77
+ "step": 200
78
+ },
79
+ {
80
+ "epoch": 1.25,
81
+ "grad_norm": 32.83223342895508,
82
+ "learning_rate": 1.2444444444444446e-05,
83
+ "loss": 4.1883,
84
+ "step": 225
85
+ },
86
+ {
87
+ "epoch": 1.3888888888888888,
88
+ "grad_norm": 17.162460327148438,
89
+ "learning_rate": 1.3833333333333334e-05,
90
+ "loss": 4.2907,
91
+ "step": 250
92
+ },
93
+ {
94
+ "epoch": 1.5277777777777777,
95
+ "grad_norm": 27.619388580322266,
96
+ "learning_rate": 1.5222222222222223e-05,
97
+ "loss": 4.3111,
98
+ "step": 275
99
+ },
100
+ {
101
+ "epoch": 1.6666666666666665,
102
+ "grad_norm": 27.325172424316406,
103
+ "learning_rate": 1.6611111111111113e-05,
104
+ "loss": 4.2018,
105
+ "step": 300
106
+ },
107
+ {
108
+ "epoch": 1.8055555555555556,
109
+ "grad_norm": 21.307151794433594,
110
+ "learning_rate": 1.8e-05,
111
+ "loss": 4.1696,
112
+ "step": 325
113
+ },
114
+ {
115
+ "epoch": 1.9444444444444444,
116
+ "grad_norm": 15.286060333251953,
117
+ "learning_rate": 1.938888888888889e-05,
118
+ "loss": 4.2193,
119
+ "step": 350
120
+ },
121
+ {
122
+ "epoch": 2.0,
123
+ "eval_accuracy": 0.4791044776119403,
124
+ "eval_loss": 1.0072804689407349,
125
+ "eval_macro_f1": 0.44860799046491584,
126
+ "eval_runtime": 1.4456,
127
+ "eval_samples_per_second": 463.46,
128
+ "eval_steps_per_second": 29.053,
129
+ "eval_weighted_f1": 0.44815622546829526,
130
+ "step": 360
131
+ },
132
+ {
133
+ "epoch": 2.0833333333333335,
134
+ "grad_norm": 26.641504287719727,
135
+ "learning_rate": 1.991358024691358e-05,
136
+ "loss": 3.9302,
137
+ "step": 375
138
+ },
139
+ {
140
+ "epoch": 2.2222222222222223,
141
+ "grad_norm": 21.551965713500977,
142
+ "learning_rate": 1.975925925925926e-05,
143
+ "loss": 3.8501,
144
+ "step": 400
145
+ },
146
+ {
147
+ "epoch": 2.361111111111111,
148
+ "grad_norm": 41.141807556152344,
149
+ "learning_rate": 1.960493827160494e-05,
150
+ "loss": 3.7357,
151
+ "step": 425
152
+ },
153
+ {
154
+ "epoch": 2.5,
155
+ "grad_norm": 29.060522079467773,
156
+ "learning_rate": 1.945061728395062e-05,
157
+ "loss": 3.69,
158
+ "step": 450
159
+ },
160
+ {
161
+ "epoch": 2.638888888888889,
162
+ "grad_norm": 57.155418395996094,
163
+ "learning_rate": 1.92962962962963e-05,
164
+ "loss": 3.5694,
165
+ "step": 475
166
+ },
167
+ {
168
+ "epoch": 2.7777777777777777,
169
+ "grad_norm": 22.63286018371582,
170
+ "learning_rate": 1.914197530864198e-05,
171
+ "loss": 3.7485,
172
+ "step": 500
173
+ },
174
+ {
175
+ "epoch": 2.9166666666666665,
176
+ "grad_norm": 23.279579162597656,
177
+ "learning_rate": 1.8987654320987657e-05,
178
+ "loss": 3.5465,
179
+ "step": 525
180
+ },
181
+ {
182
+ "epoch": 3.0,
183
+ "eval_accuracy": 0.5552238805970149,
184
+ "eval_loss": 0.9134945869445801,
185
+ "eval_macro_f1": 0.545440723371018,
186
+ "eval_runtime": 1.3629,
187
+ "eval_samples_per_second": 491.606,
188
+ "eval_steps_per_second": 30.817,
189
+ "eval_weighted_f1": 0.5444931386875956,
190
+ "step": 540
191
+ },
192
+ {
193
+ "epoch": 3.0555555555555554,
194
+ "grad_norm": 36.72185516357422,
195
+ "learning_rate": 1.8833333333333335e-05,
196
+ "loss": 3.4629,
197
+ "step": 550
198
+ },
199
+ {
200
+ "epoch": 3.1944444444444446,
201
+ "grad_norm": 31.557235717773438,
202
+ "learning_rate": 1.8679012345679013e-05,
203
+ "loss": 2.8424,
204
+ "step": 575
205
+ },
206
+ {
207
+ "epoch": 3.3333333333333335,
208
+ "grad_norm": 62.97331237792969,
209
+ "learning_rate": 1.8524691358024694e-05,
210
+ "loss": 2.9011,
211
+ "step": 600
212
+ },
213
+ {
214
+ "epoch": 3.4722222222222223,
215
+ "grad_norm": 42.78829574584961,
216
+ "learning_rate": 1.837037037037037e-05,
217
+ "loss": 2.7434,
218
+ "step": 625
219
+ },
220
+ {
221
+ "epoch": 3.611111111111111,
222
+ "grad_norm": 37.28730010986328,
223
+ "learning_rate": 1.821604938271605e-05,
224
+ "loss": 2.8436,
225
+ "step": 650
226
+ },
227
+ {
228
+ "epoch": 3.75,
229
+ "grad_norm": 52.72061538696289,
230
+ "learning_rate": 1.806172839506173e-05,
231
+ "loss": 2.8424,
232
+ "step": 675
233
+ },
234
+ {
235
+ "epoch": 3.888888888888889,
236
+ "grad_norm": 33.707733154296875,
237
+ "learning_rate": 1.7907407407407408e-05,
238
+ "loss": 3.0866,
239
+ "step": 700
240
+ },
241
+ {
242
+ "epoch": 4.0,
243
+ "eval_accuracy": 0.582089552238806,
244
+ "eval_loss": 0.8941500186920166,
245
+ "eval_macro_f1": 0.5803242075928376,
246
+ "eval_runtime": 1.4191,
247
+ "eval_samples_per_second": 472.137,
248
+ "eval_steps_per_second": 29.597,
249
+ "eval_weighted_f1": 0.5801379238657683,
250
+ "step": 720
251
+ },
252
+ {
253
+ "epoch": 4.027777777777778,
254
+ "grad_norm": 43.675987243652344,
255
+ "learning_rate": 1.775308641975309e-05,
256
+ "loss": 2.6387,
257
+ "step": 725
258
+ },
259
+ {
260
+ "epoch": 4.166666666666667,
261
+ "grad_norm": 39.623165130615234,
262
+ "learning_rate": 1.7598765432098767e-05,
263
+ "loss": 1.9852,
264
+ "step": 750
265
+ },
266
+ {
267
+ "epoch": 4.305555555555555,
268
+ "grad_norm": 45.12331008911133,
269
+ "learning_rate": 1.7444444444444448e-05,
270
+ "loss": 1.9036,
271
+ "step": 775
272
+ },
273
+ {
274
+ "epoch": 4.444444444444445,
275
+ "grad_norm": 54.73080825805664,
276
+ "learning_rate": 1.7290123456790125e-05,
277
+ "loss": 1.8365,
278
+ "step": 800
279
+ },
280
+ {
281
+ "epoch": 4.583333333333333,
282
+ "grad_norm": 84.51736450195312,
283
+ "learning_rate": 1.7135802469135806e-05,
284
+ "loss": 1.9016,
285
+ "step": 825
286
+ },
287
+ {
288
+ "epoch": 4.722222222222222,
289
+ "grad_norm": 39.228389739990234,
290
+ "learning_rate": 1.6981481481481484e-05,
291
+ "loss": 1.9351,
292
+ "step": 850
293
+ },
294
+ {
295
+ "epoch": 4.861111111111111,
296
+ "grad_norm": 33.56704330444336,
297
+ "learning_rate": 1.6827160493827162e-05,
298
+ "loss": 1.5536,
299
+ "step": 875
300
+ },
301
+ {
302
+ "epoch": 5.0,
303
+ "grad_norm": 57.18074035644531,
304
+ "learning_rate": 1.667283950617284e-05,
305
+ "loss": 2.0261,
306
+ "step": 900
307
+ },
308
+ {
309
+ "epoch": 5.0,
310
+ "eval_accuracy": 0.5791044776119403,
311
+ "eval_loss": 1.0985665321350098,
312
+ "eval_macro_f1": 0.5820708900600206,
313
+ "eval_runtime": 1.4123,
314
+ "eval_samples_per_second": 474.416,
315
+ "eval_steps_per_second": 29.74,
316
+ "eval_weighted_f1": 0.5818792704789624,
317
+ "step": 900
318
+ }
319
+ ],
320
+ "logging_steps": 25,
321
+ "max_steps": 3600,
322
+ "num_input_tokens_seen": 0,
323
+ "num_train_epochs": 20,
324
+ "save_steps": 500,
325
+ "stateful_callbacks": {
326
+ "EarlyStoppingCallback": {
327
+ "args": {
328
+ "early_stopping_patience": 3,
329
+ "early_stopping_threshold": 0.0
330
+ },
331
+ "attributes": {
332
+ "early_stopping_patience_counter": 0
333
+ }
334
+ },
335
+ "TrainerControl": {
336
+ "args": {
337
+ "should_epoch_stop": false,
338
+ "should_evaluate": false,
339
+ "should_log": false,
340
+ "should_save": true,
341
+ "should_training_stop": false
342
+ },
343
+ "attributes": {}
344
+ }
345
+ },
346
+ "total_flos": 0.0,
347
+ "train_batch_size": 8,
348
+ "trial_name": null,
349
+ "trial_params": null
350
+ }
ood-vifactcheck-visobert-source-source-05-s43-20260831T020453Z-1a169064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7504a9f97a47c627458665f264d9593eade01b0919f0434d7e9c9a3739d04b04
3
+ size 390297060
ood-vifactcheck-visobert-source-source-05-s44-20260831T033516Z-59e46264/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10447b10d4480c2508c62607d1e84d042492ac2fe3595481c13d5e8c4d0d88a7
3
+ size 390297060
ood-vifactcheck-visobert-source-source-06-s42-20260831T003231Z-f21e2f7e/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d976b9e788271da5b413241cfad6eac1068b8e9e7c290605059305dd5b0db7bd
3
+ size 390297060
ood-vifactcheck-visobert-source-source-06-s42-20260831T003231Z-f21e2f7e/trainer/checkpoint-1480/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
ood-vifactcheck-visobert-source-source-06-s42-20260831T003231Z-f21e2f7e/trainer/checkpoint-1480/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "15001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
ood-vifactcheck-visobert-source-source-06-s43-20260831T021725Z-1a169064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:625b974e4a57d7e7c8db1a9698eebb7a0f6b7eec57c115010ff577ffe264e4dc
3
+ size 390297060
ood-vifactcheck-visobert-source-source-06-s44-20260831T034444Z-59e46264/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e18a826021a192a4ab7d2e6f320f3c3f3a6114d979b4c8a870b6295be2449c
3
+ size 390297060
ood-vifactcheck-visobert-source-source-06-s44-20260831T034444Z-59e46264/trainer/checkpoint-1295/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ood-vifactcheck-visobert-source-source-07-s42-20260831T004433Z-f21e2f7e/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e66d0db3a84f978e553851e757b26de1c6fa64dc57dcd0c84b85dfcdf2debbdf
3
+ size 390297060
ood-vifactcheck-visobert-source-source-07-s43-20260831T023232Z-1a169064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4ecaea9c322eafd25a22819736fa2370c625da4744a5b03673d30d4879f027
3
+ size 390297060
ood-vifactcheck-visobert-source-source-07-s44-20260831T035525Z-59e46264/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e6ce9b0ee8450d9c30062fe41d37f16f3aefa64c401f12b8ec80a2f60a43494
3
+ size 390297060
ood-vifactcheck-visobert-source-source-08-s42-20260831T005402Z-f21e2f7e/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67cd73038ee0926baae21336e052da705ca3d14ece38cc8b0fcff226f76e60b1
3
+ size 390297060
ood-vifactcheck-visobert-source-source-08-s43-20260831T024013Z-1a169064/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:162e3dc5aaaddc4c41b80d18d99474bc4b195b7a1e2e6ad6afa6b6a0fc0278e4
3
+ size 390297060
ood-vifactcheck-visobert-source-source-08-s44-20260831T040503Z-59e46264/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c654711cdb668f839919defdccb17fc53676b7c1b0110bd18974524ea29943b9
3
+ size 390297060
ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a29d77659bae673f8996e10f2b76e6dd2a3dbf307cd03d4e8ae8d71018240ae
3
+ size 390297060
ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c9f80cb20e3b4a6807bc77835720f9c8542d4eb18ce12288f47f4f91852c98
3
+ size 390297092
ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe654f8c5bc4cc7e7a71db9aa915850bfc31535e1edfcac5af8e2e18e52f2e88
3
+ size 775987770
ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec421a6084ff87c2bbd27871a78c9cc2498c8f4da8ae09a185a3dcfbf8ff0ed4
3
+ size 14244
ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7291c94528e6bb2695d0bcb1ff62cea02337b1bf749755fff28373265711e3
3
+ size 1064
ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02aaf05cda4db99e86b7c76eba6258867ce4d043da0fed19c87a7d46c8b53a65
3
+ size 470732
ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1122/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e93262ce99a4d62ae9b98d81f060a67c7ef34ab6c6dc5b5358e74ca7c3cfd0d8
3
+ size 5624
ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1683/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08c8f3213a0ff295a6c120ae25b2822fa0126f30202b3d42ade3dd56df3a1a6a
3
+ size 390297092
ood-vifactcheck-visobert-topic-domain-00-s42-20260830T141709Z-f21e2f7e/trainer/checkpoint-1683/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e595dd113ce1ecfc2747fbe0305892f66073d3150cb8cd3383ff7bc79ed608
3
+ size 14244