hevok commited on
Commit
f2878cb
·
verified ·
1 Parent(s): bb04daf

Delete lm_evals

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T19-06-20.531501_lambada_openai.json +0 -27
  2. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T19-21-44.119690_hellaswag.json +0 -27
  3. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T19-23-17.145963_piqa.json +0 -27
  4. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T19-26-14.237824_arc_easy.json +0 -27
  5. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T19-27-50.078594_arc_challenge.json +0 -27
  6. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T20-26-56.754045_glue.json +0 -69
  7. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T20-27-55.978255_winogrande.json +0 -25
  8. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T20-29-37.701435_sciq.json +0 -27
  9. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T20-50-27.279294_mmlu.json +0 -330
  10. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T21-00-05.534236_lambada_multilingual.json +0 -55
  11. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T21-15-59.241658_pawsx.json +0 -60
  12. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T21-20-10.333493_xcopa.json +0 -80
  13. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-14T10-31-47.400032_xnli.json +0 -100
  14. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-14T10-48-34.071254_xstorycloze.json +0 -80
  15. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-14T10-51-40.216025_xwinograd.json +0 -55
  16. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-14T11-47-43.816593_mmlu.json +0 -330
  17. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T11-56-41.258584_lambada_openai.json +0 -27
  18. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T12-14-40.804741_hellaswag.json +0 -27
  19. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T12-16-12.146728_piqa.json +0 -27
  20. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T12-19-04.686563_arc_easy.json +0 -27
  21. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T12-20-40.573806_arc_challenge.json +0 -27
  22. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T13-19-33.146311_glue.json +0 -69
  23. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T13-20-31.009617_winogrande.json +0 -25
  24. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T13-22-11.575335_sciq.json +0 -27
  25. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T13-41-59.570521_mmlu.json +0 -330
  26. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T13-51-36.484339_lambada_multilingual.json +0 -55
  27. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T14-07-25.400235_pawsx.json +0 -60
  28. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T14-57-32.308002_xcopa.json +0 -80
  29. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T16-02-57.684170_xnli.json +0 -100
  30. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T16-19-00.595561_xstorycloze.json +0 -80
  31. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T16-21-46.468616_xwinograd.json +0 -55
  32. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T17-22-18.851434_mmlu.json +0 -330
  33. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T18-54-53.797865_lambada_openai_.json +0 -27
  34. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T09-57-49.932590_lambada_openai.json +0 -27
  35. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T10-13-21.086739_hellaswag.json +0 -27
  36. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T10-14-54.756945_piqa.json +0 -27
  37. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T10-17-57.209289_arc_easy.json +0 -27
  38. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T10-19-33.710789_arc_challenge.json +0 -27
  39. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T12-39-38.019272_xnli.json +0 -100
  40. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T12-56-32.162685_xstorycloze.json +0 -80
  41. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T12-59-30.016094_xwinograd.json +0 -55
  42. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T13-49-01.062852_mmlu.json +0 -330
  43. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T19-03-10.026654_glue.json +0 -69
  44. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T19-04-32.038053_winogrande.json +0 -25
  45. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T19-09-54.775610_sciq.json +0 -27
  46. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T19-31-43.872563_mmlu.json +0 -330
  47. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T20-07-36.031022_lambada_multilingual.json +0 -55
  48. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T20-24-29.617348_pawsx.json +0 -60
  49. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T20-29-15.015293_xcopa.json +0 -80
  50. lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_none/0.4.8_2025-03-14T11-51-55.842699_lambada_openai.json +0 -25
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T19-06-20.531501_lambada_openai.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "lambada_openai"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "lambada_openai": {
20
- "alias": "lambada_openai",
21
- "perplexity,none": 12.407350784089648,
22
- "perplexity_stderr,none": 0.37458781533549945,
23
- "acc,none": 0.48981176013972444,
24
- "acc_stderr,none": 0.006964531366864929
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T19-21-44.119690_hellaswag.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "hellaswag"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "hellaswag": {
20
- "alias": "hellaswag",
21
- "acc,none": 0.3467436765584545,
22
- "acc_stderr,none": 0.004749606196363352,
23
- "acc_norm,none": 0.4219279028082055,
24
- "acc_norm_stderr,none": 0.004928578106026366
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T19-23-17.145963_piqa.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "piqa"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "piqa": {
20
- "alias": "piqa",
21
- "acc,none": 0.6713819368879217,
22
- "acc_stderr,none": 0.010959127105167044,
23
- "acc_norm,none": 0.6637649619151251,
24
- "acc_norm_stderr,none": 0.01102234670897023
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T19-26-14.237824_arc_easy.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "arc_easy"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "arc_easy": {
20
- "alias": "arc_easy",
21
- "acc,none": 0.5660774410774411,
22
- "acc_stderr,none": 0.010169795770462104,
23
- "acc_norm,none": 0.4877946127946128,
24
- "acc_norm_stderr,none": 0.01025672623512901
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T19-27-50.078594_arc_challenge.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "arc_challenge"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "arc_challenge": {
20
- "alias": "arc_challenge",
21
- "acc,none": 0.2363481228668942,
22
- "acc_stderr,none": 0.012414960524301853,
23
- "acc_norm,none": 0.2764505119453925,
24
- "acc_norm_stderr,none": 0.013069662474252428
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T20-26-56.754045_glue.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "glue"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "cola": {
20
- "alias": "cola",
21
- "mcc,none": 0.0,
22
- "mcc_stderr,none": 0.0
23
- },
24
- "mnli": {
25
- "alias": "mnli",
26
- "acc,none": 0.31818644931227713,
27
- "acc_stderr,none": 0.004701653585969689
28
- },
29
- "mnli_mismatch": {
30
- "alias": "mnli_mismatch",
31
- "acc,none": 0.31834825061025224,
32
- "acc_stderr,none": 0.004698223389253123
33
- },
34
- "mrpc": {
35
- "alias": "mrpc",
36
- "acc,none": 0.31862745098039214,
37
- "acc_stderr,none": 0.023095996571841474,
38
- "f1,none": 0.027972027972027972,
39
- "f1_stderr,none": 0.013657795743166324
40
- },
41
- "qnli": {
42
- "alias": "qnli",
43
- "acc,none": 0.49203734211971445,
44
- "acc_stderr,none": 0.006764552590269392
45
- },
46
- "qqp": {
47
- "alias": "qqp",
48
- "acc,none": 0.4093742270591145,
49
- "acc_stderr,none": 0.0024455128327978796,
50
- "f1,none": 0.5085108572604713,
51
- "f1_stderr,none": 0.002764972824540013
52
- },
53
- "rte": {
54
- "alias": "rte",
55
- "acc,none": 0.5631768953068592,
56
- "acc_stderr,none": 0.029855247390314938
57
- },
58
- "sst2": {
59
- "alias": "sst2",
60
- "acc,none": 0.8188073394495413,
61
- "acc_stderr,none": 0.013051249343626403
62
- },
63
- "wnli": {
64
- "alias": "wnli",
65
- "acc,none": 0.4647887323943662,
66
- "acc_stderr,none": 0.05961305784972239
67
- }
68
- }
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T20-27-55.978255_winogrande.json DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "winogrande"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "winogrande": {
20
- "alias": "winogrande",
21
- "acc,none": 0.5256511444356748,
22
- "acc_stderr,none": 0.014033980956108558
23
- }
24
- }
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T20-29-37.701435_sciq.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "sciq"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "sciq": {
20
- "alias": "sciq",
21
- "acc,none": 0.862,
22
- "acc_stderr,none": 0.010912152632504417,
23
- "acc_norm,none": 0.79,
24
- "acc_norm_stderr,none": 0.012886662332274527
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T20-50-27.279294_mmlu.json DELETED
@@ -1,330 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "mmlu"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "mmlu": {
20
- "acc,none": 0.2577980344680245,
21
- "acc_stderr,none": 0.003687241789650295,
22
- "alias": "mmlu"
23
- },
24
- "mmlu_humanities": {
25
- "acc,none": 0.2459086078639745,
26
- "acc_stderr,none": 0.006272632557690886,
27
- "alias": " - humanities"
28
- },
29
- "mmlu_formal_logic": {
30
- "alias": " - formal_logic",
31
- "acc,none": 0.3333333333333333,
32
- "acc_stderr,none": 0.04216370213557836
33
- },
34
- "mmlu_high_school_european_history": {
35
- "alias": " - high_school_european_history",
36
- "acc,none": 0.3151515151515151,
37
- "acc_stderr,none": 0.0362773057502241
38
- },
39
- "mmlu_high_school_us_history": {
40
- "alias": " - high_school_us_history",
41
- "acc,none": 0.25,
42
- "acc_stderr,none": 0.03039153369274154
43
- },
44
- "mmlu_high_school_world_history": {
45
- "alias": " - high_school_world_history",
46
- "acc,none": 0.2742616033755274,
47
- "acc_stderr,none": 0.02904133351059801
48
- },
49
- "mmlu_international_law": {
50
- "alias": " - international_law",
51
- "acc,none": 0.2396694214876033,
52
- "acc_stderr,none": 0.03896878985070417
53
- },
54
- "mmlu_jurisprudence": {
55
- "alias": " - jurisprudence",
56
- "acc,none": 0.21296296296296297,
57
- "acc_stderr,none": 0.0395783547198098
58
- },
59
- "mmlu_logical_fallacies": {
60
- "alias": " - logical_fallacies",
61
- "acc,none": 0.2392638036809816,
62
- "acc_stderr,none": 0.03351953879521271
63
- },
64
- "mmlu_moral_disputes": {
65
- "alias": " - moral_disputes",
66
- "acc,none": 0.22832369942196531,
67
- "acc_stderr,none": 0.022598703804321635
68
- },
69
- "mmlu_moral_scenarios": {
70
- "alias": " - moral_scenarios",
71
- "acc,none": 0.2547486033519553,
72
- "acc_stderr,none": 0.014572650383409158
73
- },
74
- "mmlu_philosophy": {
75
- "alias": " - philosophy",
76
- "acc,none": 0.1832797427652733,
77
- "acc_stderr,none": 0.021974198848265805
78
- },
79
- "mmlu_prehistory": {
80
- "alias": " - prehistory",
81
- "acc,none": 0.21604938271604937,
82
- "acc_stderr,none": 0.022899162918445785
83
- },
84
- "mmlu_professional_law": {
85
- "alias": " - professional_law",
86
- "acc,none": 0.2503259452411995,
87
- "acc_stderr,none": 0.011064151027165441
88
- },
89
- "mmlu_world_religions": {
90
- "alias": " - world_religions",
91
- "acc,none": 0.2222222222222222,
92
- "acc_stderr,none": 0.031885780176863984
93
- },
94
- "mmlu_other": {
95
- "acc,none": 0.2581268104280657,
96
- "acc_stderr,none": 0.007836786127741097,
97
- "alias": " - other"
98
- },
99
- "mmlu_business_ethics": {
100
- "alias": " - business_ethics",
101
- "acc,none": 0.24,
102
- "acc_stderr,none": 0.04292346959909283
103
- },
104
- "mmlu_clinical_knowledge": {
105
- "alias": " - clinical_knowledge",
106
- "acc,none": 0.2943396226415094,
107
- "acc_stderr,none": 0.028049186315695245
108
- },
109
- "mmlu_college_medicine": {
110
- "alias": " - college_medicine",
111
- "acc,none": 0.2543352601156069,
112
- "acc_stderr,none": 0.0332055644308557
113
- },
114
- "mmlu_global_facts": {
115
- "alias": " - global_facts",
116
- "acc,none": 0.2,
117
- "acc_stderr,none": 0.04020151261036843
118
- },
119
- "mmlu_human_aging": {
120
- "alias": " - human_aging",
121
- "acc,none": 0.28699551569506726,
122
- "acc_stderr,none": 0.03036037971029195
123
- },
124
- "mmlu_management": {
125
- "alias": " - management",
126
- "acc,none": 0.33980582524271846,
127
- "acc_stderr,none": 0.046897659372781356
128
- },
129
- "mmlu_marketing": {
130
- "alias": " - marketing",
131
- "acc,none": 0.2606837606837607,
132
- "acc_stderr,none": 0.028760348956523414
133
- },
134
- "mmlu_medical_genetics": {
135
- "alias": " - medical_genetics",
136
- "acc,none": 0.22,
137
- "acc_stderr,none": 0.04163331998932269
138
- },
139
- "mmlu_miscellaneous": {
140
- "alias": " - miscellaneous",
141
- "acc,none": 0.21966794380587484,
142
- "acc_stderr,none": 0.014805384478371158
143
- },
144
- "mmlu_nutrition": {
145
- "alias": " - nutrition",
146
- "acc,none": 0.28104575163398693,
147
- "acc_stderr,none": 0.025738854797818705
148
- },
149
- "mmlu_professional_accounting": {
150
- "alias": " - professional_accounting",
151
- "acc,none": 0.25886524822695034,
152
- "acc_stderr,none": 0.026129572527180848
153
- },
154
- "mmlu_professional_medicine": {
155
- "alias": " - professional_medicine",
156
- "acc,none": 0.3235294117647059,
157
- "acc_stderr,none": 0.028418208619406794
158
- },
159
- "mmlu_virology": {
160
- "alias": " - virology",
161
- "acc,none": 0.21084337349397592,
162
- "acc_stderr,none": 0.031755547866299194
163
- },
164
- "mmlu_social_sciences": {
165
- "acc,none": 0.2612934676633084,
166
- "acc_stderr,none": 0.007931489440202161,
167
- "alias": " - social sciences"
168
- },
169
- "mmlu_econometrics": {
170
- "alias": " - econometrics",
171
- "acc,none": 0.23684210526315788,
172
- "acc_stderr,none": 0.039994238792813344
173
- },
174
- "mmlu_high_school_geography": {
175
- "alias": " - high_school_geography",
176
- "acc,none": 0.2878787878787879,
177
- "acc_stderr,none": 0.03225883512300992
178
- },
179
- "mmlu_high_school_government_and_politics": {
180
- "alias": " - high_school_government_and_politics",
181
- "acc,none": 0.25906735751295334,
182
- "acc_stderr,none": 0.0316187791793541
183
- },
184
- "mmlu_high_school_macroeconomics": {
185
- "alias": " - high_school_macroeconomics",
186
- "acc,none": 0.26153846153846155,
187
- "acc_stderr,none": 0.022282141204204426
188
- },
189
- "mmlu_high_school_microeconomics": {
190
- "alias": " - high_school_microeconomics",
191
- "acc,none": 0.2857142857142857,
192
- "acc_stderr,none": 0.029344572500634335
193
- },
194
- "mmlu_high_school_psychology": {
195
- "alias": " - high_school_psychology",
196
- "acc,none": 0.25504587155963304,
197
- "acc_stderr,none": 0.018688500856535832
198
- },
199
- "mmlu_human_sexuality": {
200
- "alias": " - human_sexuality",
201
- "acc,none": 0.2748091603053435,
202
- "acc_stderr,none": 0.03915345408847836
203
- },
204
- "mmlu_professional_psychology": {
205
- "alias": " - professional_psychology",
206
- "acc,none": 0.25980392156862747,
207
- "acc_stderr,none": 0.017740899509177795
208
- },
209
- "mmlu_public_relations": {
210
- "alias": " - public_relations",
211
- "acc,none": 0.2636363636363636,
212
- "acc_stderr,none": 0.04220224692971987
213
- },
214
- "mmlu_security_studies": {
215
- "alias": " - security_studies",
216
- "acc,none": 0.24081632653061225,
217
- "acc_stderr,none": 0.027372942201788163
218
- },
219
- "mmlu_sociology": {
220
- "alias": " - sociology",
221
- "acc,none": 0.2736318407960199,
222
- "acc_stderr,none": 0.031524391865554016
223
- },
224
- "mmlu_us_foreign_policy": {
225
- "alias": " - us_foreign_policy",
226
- "acc,none": 0.23,
227
- "acc_stderr,none": 0.04229525846816505
228
- },
229
- "mmlu_stem": {
230
- "acc,none": 0.2718046305106248,
231
- "acc_stderr,none": 0.00790588931133328,
232
- "alias": " - stem"
233
- },
234
- "mmlu_abstract_algebra": {
235
- "alias": " - abstract_algebra",
236
- "acc,none": 0.22,
237
- "acc_stderr,none": 0.04163331998932269
238
- },
239
- "mmlu_anatomy": {
240
- "alias": " - anatomy",
241
- "acc,none": 0.2222222222222222,
242
- "acc_stderr,none": 0.03591444084196969
243
- },
244
- "mmlu_astronomy": {
245
- "alias": " - astronomy",
246
- "acc,none": 0.27631578947368424,
247
- "acc_stderr,none": 0.03639057569952924
248
- },
249
- "mmlu_college_biology": {
250
- "alias": " - college_biology",
251
- "acc,none": 0.2569444444444444,
252
- "acc_stderr,none": 0.03653946969442099
253
- },
254
- "mmlu_college_chemistry": {
255
- "alias": " - college_chemistry",
256
- "acc,none": 0.36,
257
- "acc_stderr,none": 0.04824181513244218
258
- },
259
- "mmlu_college_computer_science": {
260
- "alias": " - college_computer_science",
261
- "acc,none": 0.27,
262
- "acc_stderr,none": 0.04461960433384741
263
- },
264
- "mmlu_college_mathematics": {
265
- "alias": " - college_mathematics",
266
- "acc,none": 0.3,
267
- "acc_stderr,none": 0.046056618647183814
268
- },
269
- "mmlu_college_physics": {
270
- "alias": " - college_physics",
271
- "acc,none": 0.3431372549019608,
272
- "acc_stderr,none": 0.047240073523838896
273
- },
274
- "mmlu_computer_security": {
275
- "alias": " - computer_security",
276
- "acc,none": 0.23,
277
- "acc_stderr,none": 0.04229525846816506
278
- },
279
- "mmlu_conceptual_physics": {
280
- "alias": " - conceptual_physics",
281
- "acc,none": 0.20851063829787234,
282
- "acc_stderr,none": 0.026556982117838725
283
- },
284
- "mmlu_electrical_engineering": {
285
- "alias": " - electrical_engineering",
286
- "acc,none": 0.2,
287
- "acc_stderr,none": 0.033333333333333284
288
- },
289
- "mmlu_elementary_mathematics": {
290
- "alias": " - elementary_mathematics",
291
- "acc,none": 0.2724867724867725,
292
- "acc_stderr,none": 0.022930973071633356
293
- },
294
- "mmlu_high_school_biology": {
295
- "alias": " - high_school_biology",
296
- "acc,none": 0.2903225806451613,
297
- "acc_stderr,none": 0.025822106119415898
298
- },
299
- "mmlu_high_school_chemistry": {
300
- "alias": " - high_school_chemistry",
301
- "acc,none": 0.2561576354679803,
302
- "acc_stderr,none": 0.030712730070982592
303
- },
304
- "mmlu_high_school_computer_science": {
305
- "alias": " - high_school_computer_science",
306
- "acc,none": 0.23,
307
- "acc_stderr,none": 0.04229525846816508
308
- },
309
- "mmlu_high_school_mathematics": {
310
- "alias": " - high_school_mathematics",
311
- "acc,none": 0.3,
312
- "acc_stderr,none": 0.027940457136228416
313
- },
314
- "mmlu_high_school_physics": {
315
- "alias": " - high_school_physics",
316
- "acc,none": 0.2781456953642384,
317
- "acc_stderr,none": 0.03658603262763743
318
- },
319
- "mmlu_high_school_statistics": {
320
- "alias": " - high_school_statistics",
321
- "acc,none": 0.36574074074074076,
322
- "acc_stderr,none": 0.032847388576472056
323
- },
324
- "mmlu_machine_learning": {
325
- "alias": " - machine_learning",
326
- "acc,none": 0.24107142857142858,
327
- "acc_stderr,none": 0.04059867246952687
328
- }
329
- }
330
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T21-00-05.534236_lambada_multilingual.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "lambada_multilingual"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "lambada_openai_mt_de": {
20
- "alias": "lambada_openai_mt_de",
21
- "perplexity,none": 217.60668191767158,
22
- "perplexity_stderr,none": 13.386879667864363,
23
- "acc,none": 0.24238307781874635,
24
- "acc_stderr,none": 0.00597018864415414
25
- },
26
- "lambada_openai_mt_en": {
27
- "alias": "lambada_openai_mt_en",
28
- "perplexity,none": 12.40735077022245,
29
- "perplexity_stderr,none": 0.37458781378621286,
30
- "acc,none": 0.48981176013972444,
31
- "acc_stderr,none": 0.006964531366864929
32
- },
33
- "lambada_openai_mt_es": {
34
- "alias": "lambada_openai_mt_es",
35
- "perplexity,none": 266.1166411896921,
36
- "perplexity_stderr,none": 15.92044089608634,
37
- "acc,none": 0.2501455462837182,
38
- "acc_stderr,none": 0.006033883877757193
39
- },
40
- "lambada_openai_mt_fr": {
41
- "alias": "lambada_openai_mt_fr",
42
- "perplexity,none": 128.38541768361372,
43
- "perplexity_stderr,none": 7.512376165987988,
44
- "acc,none": 0.31476809625460894,
45
- "acc_stderr,none": 0.0064703267662255814
46
- },
47
- "lambada_openai_mt_it": {
48
- "alias": "lambada_openai_mt_it",
49
- "perplexity,none": 209.98639759161097,
50
- "perplexity_stderr,none": 13.315525534037729,
51
- "acc,none": 0.2850766543760916,
52
- "acc_stderr,none": 0.006289594388741717
53
- }
54
- }
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T21-15-59.241658_pawsx.json DELETED
@@ -1,60 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "pawsx"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "pawsx": {
20
- "acc,none": 0.4645714285714286,
21
- "acc_stderr,none": 0.004212978865599906,
22
- "alias": "pawsx"
23
- },
24
- "paws_de": {
25
- "alias": " - paws_de",
26
- "acc,none": 0.4535,
27
- "acc_stderr,none": 0.011134669525078671
28
- },
29
- "paws_en": {
30
- "alias": " - paws_en",
31
- "acc,none": 0.466,
32
- "acc_stderr,none": 0.01115725065242577
33
- },
34
- "paws_es": {
35
- "alias": " - paws_es",
36
- "acc,none": 0.508,
37
- "acc_stderr,none": 0.01118170448803001
38
- },
39
- "paws_fr": {
40
- "alias": " - paws_fr",
41
- "acc,none": 0.4715,
42
- "acc_stderr,none": 0.011164954236428791
43
- },
44
- "paws_ja": {
45
- "alias": " - paws_ja",
46
- "acc,none": 0.4455,
47
- "acc_stderr,none": 0.011116504096687392
48
- },
49
- "paws_ko": {
50
- "alias": " - paws_ko",
51
- "acc,none": 0.4555,
52
- "acc_stderr,none": 0.011138757154883975
53
- },
54
- "paws_zh": {
55
- "alias": " - paws_zh",
56
- "acc,none": 0.452,
57
- "acc_stderr,none": 0.01113148485052578
58
- }
59
- }
60
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-13T21-20-10.333493_xcopa.json DELETED
@@ -1,80 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xcopa"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xcopa": {
20
- "acc,none": 0.5296363636363637,
21
- "acc_stderr,none": 0.006732007807068195,
22
- "alias": "xcopa"
23
- },
24
- "xcopa_et": {
25
- "alias": " - xcopa_et",
26
- "acc,none": 0.496,
27
- "acc_stderr,none": 0.02238235778196214
28
- },
29
- "xcopa_ht": {
30
- "alias": " - xcopa_ht",
31
- "acc,none": 0.526,
32
- "acc_stderr,none": 0.02235279165091416
33
- },
34
- "xcopa_id": {
35
- "alias": " - xcopa_id",
36
- "acc,none": 0.56,
37
- "acc_stderr,none": 0.02222133153414303
38
- },
39
- "xcopa_it": {
40
- "alias": " - xcopa_it",
41
- "acc,none": 0.524,
42
- "acc_stderr,none": 0.022357273881016403
43
- },
44
- "xcopa_qu": {
45
- "alias": " - xcopa_qu",
46
- "acc,none": 0.5,
47
- "acc_stderr,none": 0.022383074051792257
48
- },
49
- "xcopa_sw": {
50
- "alias": " - xcopa_sw",
51
- "acc,none": 0.528,
52
- "acc_stderr,none": 0.022347949832668093
53
- },
54
- "xcopa_ta": {
55
- "alias": " - xcopa_ta",
56
- "acc,none": 0.534,
57
- "acc_stderr,none": 0.02233126442325838
58
- },
59
- "xcopa_th": {
60
- "alias": " - xcopa_th",
61
- "acc,none": 0.554,
62
- "acc_stderr,none": 0.022252153078595897
63
- },
64
- "xcopa_tr": {
65
- "alias": " - xcopa_tr",
66
- "acc,none": 0.524,
67
- "acc_stderr,none": 0.0223572738810164
68
- },
69
- "xcopa_vi": {
70
- "alias": " - xcopa_vi",
71
- "acc,none": 0.532,
72
- "acc_stderr,none": 0.022337186479044296
73
- },
74
- "xcopa_zh": {
75
- "alias": " - xcopa_zh",
76
- "acc,none": 0.548,
77
- "acc_stderr,none": 0.02227969410784342
78
- }
79
- }
80
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-14T10-31-47.400032_xnli.json DELETED
@@ -1,100 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xnli"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xnli": {
20
- "acc,none": 0.3738152610441767,
21
- "acc_stderr,none": 0.0024958379883944465,
22
- "alias": "xnli"
23
- },
24
- "xnli_ar": {
25
- "alias": " - xnli_ar",
26
- "acc,none": 0.3385542168674699,
27
- "acc_stderr,none": 0.009485250208516881
28
- },
29
- "xnli_bg": {
30
- "alias": " - xnli_bg",
31
- "acc,none": 0.3646586345381526,
32
- "acc_stderr,none": 0.009647934990250467
33
- },
34
- "xnli_de": {
35
- "alias": " - xnli_de",
36
- "acc,none": 0.41405622489959837,
37
- "acc_stderr,none": 0.009872910116421196
38
- },
39
- "xnli_el": {
40
- "alias": " - xnli_el",
41
- "acc,none": 0.3417670682730924,
42
- "acc_stderr,none": 0.009506977398287627
43
- },
44
- "xnli_en": {
45
- "alias": " - xnli_en",
46
- "acc,none": 0.4682730923694779,
47
- "acc_stderr,none": 0.010001876146466708
48
- },
49
- "xnli_es": {
50
- "alias": " - xnli_es",
51
- "acc,none": 0.37751004016064255,
52
- "acc_stderr,none": 0.009716681793584016
53
- },
54
- "xnli_fr": {
55
- "alias": " - xnli_fr",
56
- "acc,none": 0.42610441767068274,
57
- "acc_stderr,none": 0.00991201637745908
58
- },
59
- "xnli_hi": {
60
- "alias": " - xnli_hi",
61
- "acc,none": 0.3542168674698795,
62
- "acc_stderr,none": 0.009586620142951845
63
- },
64
- "xnli_ru": {
65
- "alias": " - xnli_ru",
66
- "acc,none": 0.42289156626506025,
67
- "acc_stderr,none": 0.009902179034797433
68
- },
69
- "xnli_sw": {
70
- "alias": " - xnli_sw",
71
- "acc,none": 0.351004016064257,
72
- "acc_stderr,none": 0.0095667538348033
73
- },
74
- "xnli_th": {
75
- "alias": " - xnli_th",
76
- "acc,none": 0.3485943775100402,
77
- "acc_stderr,none": 0.009551542053301817
78
- },
79
- "xnli_tr": {
80
- "alias": " - xnli_tr",
81
- "acc,none": 0.3550200803212851,
82
- "acc_stderr,none": 0.009591512730974291
83
- },
84
- "xnli_ur": {
85
- "alias": " - xnli_ur",
86
- "acc,none": 0.336144578313253,
87
- "acc_stderr,none": 0.009468634669293527
88
- },
89
- "xnli_vi": {
90
- "alias": " - xnli_vi",
91
- "acc,none": 0.37028112449799194,
92
- "acc_stderr,none": 0.009678915409840288
93
- },
94
- "xnli_zh": {
95
- "alias": " - xnli_zh",
96
- "acc,none": 0.3381526104417671,
97
- "acc_stderr,none": 0.009482500057981024
98
- }
99
- }
100
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-14T10-48-34.071254_xstorycloze.json DELETED
@@ -1,80 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xstorycloze"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xstorycloze": {
20
- "acc,none": 0.5253594849888695,
21
- "acc_stderr,none": 0.0038631877983218758,
22
- "alias": "xstorycloze"
23
- },
24
- "xstorycloze_ar": {
25
- "alias": " - xstorycloze_ar",
26
- "acc,none": 0.47650562541363334,
27
- "acc_stderr,none": 0.012852912530051752
28
- },
29
- "xstorycloze_en": {
30
- "alias": " - xstorycloze_en",
31
- "acc,none": 0.6307081403044341,
32
- "acc_stderr,none": 0.01241968588127358
33
- },
34
- "xstorycloze_es": {
35
- "alias": " - xstorycloze_es",
36
- "acc,none": 0.5433487756452681,
37
- "acc_stderr,none": 0.01281867645248196
38
- },
39
- "xstorycloze_eu": {
40
- "alias": " - xstorycloze_eu",
41
- "acc,none": 0.5201853077432164,
42
- "acc_stderr,none": 0.012856635706498292
43
- },
44
- "xstorycloze_hi": {
45
- "alias": " - xstorycloze_hi",
46
- "acc,none": 0.5129053606882858,
47
- "acc_stderr,none": 0.012862838605728474
48
- },
49
- "xstorycloze_id": {
50
- "alias": " - xstorycloze_id",
51
- "acc,none": 0.5069490403706155,
52
- "acc_stderr,none": 0.01286588257096072
53
- },
54
- "xstorycloze_my": {
55
- "alias": " - xstorycloze_my",
56
- "acc,none": 0.5016545334215751,
57
- "acc_stderr,none": 0.012867054869163341
58
- },
59
- "xstorycloze_ru": {
60
- "alias": " - xstorycloze_ru",
61
- "acc,none": 0.5155526141628061,
62
- "acc_stderr,none": 0.012860899111470784
63
- },
64
- "xstorycloze_sw": {
65
- "alias": " - xstorycloze_sw",
66
- "acc,none": 0.49636002647253474,
67
- "acc_stderr,none": 0.01286678434828923
68
- },
69
- "xstorycloze_te": {
70
- "alias": " - xstorycloze_te",
71
- "acc,none": 0.5360688285903376,
72
- "acc_stderr,none": 0.012833602406620017
73
- },
74
- "xstorycloze_zh": {
75
- "alias": " - xstorycloze_zh",
76
- "acc,none": 0.5387160820648577,
77
- "acc_stderr,none": 0.012828493353271535
78
- }
79
- }
80
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-14T10-51-40.216025_xwinograd.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xwinograd"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xwinograd": {
20
- "acc,none": 0.640143852551135,
21
- "acc_stderr,none": 0.007122015764479138,
22
- "alias": "xwinograd"
23
- },
24
- "xwinograd_en": {
25
- "alias": " - xwinograd_en",
26
- "acc,none": 0.7002150537634408,
27
- "acc_stderr,none": 0.00950391558599881
28
- },
29
- "xwinograd_fr": {
30
- "alias": " - xwinograd_fr",
31
- "acc,none": 0.6144578313253012,
32
- "acc_stderr,none": 0.0537495779731939
33
- },
34
- "xwinograd_jp": {
35
- "alias": " - xwinograd_jp",
36
- "acc,none": 0.5464025026068822,
37
- "acc_stderr,none": 0.016084549821364785
38
- },
39
- "xwinograd_pt": {
40
- "alias": " - xwinograd_pt",
41
- "acc,none": 0.5247148288973384,
42
- "acc_stderr,none": 0.030852343325490784
43
- },
44
- "xwinograd_ru": {
45
- "alias": " - xwinograd_ru",
46
- "acc,none": 0.5650793650793651,
47
- "acc_stderr,none": 0.027976598287184684
48
- },
49
- "xwinograd_zh": {
50
- "alias": " - xwinograd_zh",
51
- "acc,none": 0.6527777777777778,
52
- "acc_stderr,none": 0.021227675707409237
53
- }
54
- }
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_0/0.4.8_2025-03-14T11-47-43.816593_mmlu.json DELETED
@@ -1,330 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "mmlu"
5
- ],
6
- "num_fewshot": 5,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 0,
11
- "pad_token_ids": [
12
- 0
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "mmlu": {
20
- "acc,none": 0.2577980344680245,
21
- "acc_stderr,none": 0.003687241789650295,
22
- "alias": "mmlu"
23
- },
24
- "mmlu_humanities": {
25
- "acc,none": 0.2459086078639745,
26
- "acc_stderr,none": 0.006272632557690886,
27
- "alias": " - humanities"
28
- },
29
- "mmlu_formal_logic": {
30
- "alias": " - formal_logic",
31
- "acc,none": 0.3333333333333333,
32
- "acc_stderr,none": 0.04216370213557836
33
- },
34
- "mmlu_high_school_european_history": {
35
- "alias": " - high_school_european_history",
36
- "acc,none": 0.3151515151515151,
37
- "acc_stderr,none": 0.0362773057502241
38
- },
39
- "mmlu_high_school_us_history": {
40
- "alias": " - high_school_us_history",
41
- "acc,none": 0.25,
42
- "acc_stderr,none": 0.03039153369274154
43
- },
44
- "mmlu_high_school_world_history": {
45
- "alias": " - high_school_world_history",
46
- "acc,none": 0.2742616033755274,
47
- "acc_stderr,none": 0.02904133351059801
48
- },
49
- "mmlu_international_law": {
50
- "alias": " - international_law",
51
- "acc,none": 0.2396694214876033,
52
- "acc_stderr,none": 0.03896878985070417
53
- },
54
- "mmlu_jurisprudence": {
55
- "alias": " - jurisprudence",
56
- "acc,none": 0.21296296296296297,
57
- "acc_stderr,none": 0.0395783547198098
58
- },
59
- "mmlu_logical_fallacies": {
60
- "alias": " - logical_fallacies",
61
- "acc,none": 0.2392638036809816,
62
- "acc_stderr,none": 0.03351953879521271
63
- },
64
- "mmlu_moral_disputes": {
65
- "alias": " - moral_disputes",
66
- "acc,none": 0.22832369942196531,
67
- "acc_stderr,none": 0.022598703804321635
68
- },
69
- "mmlu_moral_scenarios": {
70
- "alias": " - moral_scenarios",
71
- "acc,none": 0.2547486033519553,
72
- "acc_stderr,none": 0.014572650383409158
73
- },
74
- "mmlu_philosophy": {
75
- "alias": " - philosophy",
76
- "acc,none": 0.1832797427652733,
77
- "acc_stderr,none": 0.021974198848265805
78
- },
79
- "mmlu_prehistory": {
80
- "alias": " - prehistory",
81
- "acc,none": 0.21604938271604937,
82
- "acc_stderr,none": 0.022899162918445785
83
- },
84
- "mmlu_professional_law": {
85
- "alias": " - professional_law",
86
- "acc,none": 0.2503259452411995,
87
- "acc_stderr,none": 0.011064151027165441
88
- },
89
- "mmlu_world_religions": {
90
- "alias": " - world_religions",
91
- "acc,none": 0.2222222222222222,
92
- "acc_stderr,none": 0.031885780176863984
93
- },
94
- "mmlu_other": {
95
- "acc,none": 0.2581268104280657,
96
- "acc_stderr,none": 0.007836786127741097,
97
- "alias": " - other"
98
- },
99
- "mmlu_business_ethics": {
100
- "alias": " - business_ethics",
101
- "acc,none": 0.24,
102
- "acc_stderr,none": 0.04292346959909283
103
- },
104
- "mmlu_clinical_knowledge": {
105
- "alias": " - clinical_knowledge",
106
- "acc,none": 0.2943396226415094,
107
- "acc_stderr,none": 0.028049186315695245
108
- },
109
- "mmlu_college_medicine": {
110
- "alias": " - college_medicine",
111
- "acc,none": 0.2543352601156069,
112
- "acc_stderr,none": 0.0332055644308557
113
- },
114
- "mmlu_global_facts": {
115
- "alias": " - global_facts",
116
- "acc,none": 0.2,
117
- "acc_stderr,none": 0.04020151261036843
118
- },
119
- "mmlu_human_aging": {
120
- "alias": " - human_aging",
121
- "acc,none": 0.28699551569506726,
122
- "acc_stderr,none": 0.03036037971029195
123
- },
124
- "mmlu_management": {
125
- "alias": " - management",
126
- "acc,none": 0.33980582524271846,
127
- "acc_stderr,none": 0.046897659372781356
128
- },
129
- "mmlu_marketing": {
130
- "alias": " - marketing",
131
- "acc,none": 0.2606837606837607,
132
- "acc_stderr,none": 0.028760348956523414
133
- },
134
- "mmlu_medical_genetics": {
135
- "alias": " - medical_genetics",
136
- "acc,none": 0.22,
137
- "acc_stderr,none": 0.04163331998932269
138
- },
139
- "mmlu_miscellaneous": {
140
- "alias": " - miscellaneous",
141
- "acc,none": 0.21966794380587484,
142
- "acc_stderr,none": 0.014805384478371158
143
- },
144
- "mmlu_nutrition": {
145
- "alias": " - nutrition",
146
- "acc,none": 0.28104575163398693,
147
- "acc_stderr,none": 0.025738854797818705
148
- },
149
- "mmlu_professional_accounting": {
150
- "alias": " - professional_accounting",
151
- "acc,none": 0.25886524822695034,
152
- "acc_stderr,none": 0.026129572527180848
153
- },
154
- "mmlu_professional_medicine": {
155
- "alias": " - professional_medicine",
156
- "acc,none": 0.3235294117647059,
157
- "acc_stderr,none": 0.028418208619406794
158
- },
159
- "mmlu_virology": {
160
- "alias": " - virology",
161
- "acc,none": 0.21084337349397592,
162
- "acc_stderr,none": 0.031755547866299194
163
- },
164
- "mmlu_social_sciences": {
165
- "acc,none": 0.2612934676633084,
166
- "acc_stderr,none": 0.007931489440202161,
167
- "alias": " - social sciences"
168
- },
169
- "mmlu_econometrics": {
170
- "alias": " - econometrics",
171
- "acc,none": 0.23684210526315788,
172
- "acc_stderr,none": 0.039994238792813344
173
- },
174
- "mmlu_high_school_geography": {
175
- "alias": " - high_school_geography",
176
- "acc,none": 0.2878787878787879,
177
- "acc_stderr,none": 0.03225883512300992
178
- },
179
- "mmlu_high_school_government_and_politics": {
180
- "alias": " - high_school_government_and_politics",
181
- "acc,none": 0.25906735751295334,
182
- "acc_stderr,none": 0.0316187791793541
183
- },
184
- "mmlu_high_school_macroeconomics": {
185
- "alias": " - high_school_macroeconomics",
186
- "acc,none": 0.26153846153846155,
187
- "acc_stderr,none": 0.022282141204204426
188
- },
189
- "mmlu_high_school_microeconomics": {
190
- "alias": " - high_school_microeconomics",
191
- "acc,none": 0.2857142857142857,
192
- "acc_stderr,none": 0.029344572500634335
193
- },
194
- "mmlu_high_school_psychology": {
195
- "alias": " - high_school_psychology",
196
- "acc,none": 0.25504587155963304,
197
- "acc_stderr,none": 0.018688500856535832
198
- },
199
- "mmlu_human_sexuality": {
200
- "alias": " - human_sexuality",
201
- "acc,none": 0.2748091603053435,
202
- "acc_stderr,none": 0.03915345408847836
203
- },
204
- "mmlu_professional_psychology": {
205
- "alias": " - professional_psychology",
206
- "acc,none": 0.25980392156862747,
207
- "acc_stderr,none": 0.017740899509177795
208
- },
209
- "mmlu_public_relations": {
210
- "alias": " - public_relations",
211
- "acc,none": 0.2636363636363636,
212
- "acc_stderr,none": 0.04220224692971987
213
- },
214
- "mmlu_security_studies": {
215
- "alias": " - security_studies",
216
- "acc,none": 0.24081632653061225,
217
- "acc_stderr,none": 0.027372942201788163
218
- },
219
- "mmlu_sociology": {
220
- "alias": " - sociology",
221
- "acc,none": 0.2736318407960199,
222
- "acc_stderr,none": 0.031524391865554016
223
- },
224
- "mmlu_us_foreign_policy": {
225
- "alias": " - us_foreign_policy",
226
- "acc,none": 0.23,
227
- "acc_stderr,none": 0.04229525846816505
228
- },
229
- "mmlu_stem": {
230
- "acc,none": 0.2718046305106248,
231
- "acc_stderr,none": 0.00790588931133328,
232
- "alias": " - stem"
233
- },
234
- "mmlu_abstract_algebra": {
235
- "alias": " - abstract_algebra",
236
- "acc,none": 0.22,
237
- "acc_stderr,none": 0.04163331998932269
238
- },
239
- "mmlu_anatomy": {
240
- "alias": " - anatomy",
241
- "acc,none": 0.2222222222222222,
242
- "acc_stderr,none": 0.03591444084196969
243
- },
244
- "mmlu_astronomy": {
245
- "alias": " - astronomy",
246
- "acc,none": 0.27631578947368424,
247
- "acc_stderr,none": 0.03639057569952924
248
- },
249
- "mmlu_college_biology": {
250
- "alias": " - college_biology",
251
- "acc,none": 0.2569444444444444,
252
- "acc_stderr,none": 0.03653946969442099
253
- },
254
- "mmlu_college_chemistry": {
255
- "alias": " - college_chemistry",
256
- "acc,none": 0.36,
257
- "acc_stderr,none": 0.04824181513244218
258
- },
259
- "mmlu_college_computer_science": {
260
- "alias": " - college_computer_science",
261
- "acc,none": 0.27,
262
- "acc_stderr,none": 0.04461960433384741
263
- },
264
- "mmlu_college_mathematics": {
265
- "alias": " - college_mathematics",
266
- "acc,none": 0.3,
267
- "acc_stderr,none": 0.046056618647183814
268
- },
269
- "mmlu_college_physics": {
270
- "alias": " - college_physics",
271
- "acc,none": 0.3431372549019608,
272
- "acc_stderr,none": 0.047240073523838896
273
- },
274
- "mmlu_computer_security": {
275
- "alias": " - computer_security",
276
- "acc,none": 0.23,
277
- "acc_stderr,none": 0.04229525846816506
278
- },
279
- "mmlu_conceptual_physics": {
280
- "alias": " - conceptual_physics",
281
- "acc,none": 0.20851063829787234,
282
- "acc_stderr,none": 0.026556982117838725
283
- },
284
- "mmlu_electrical_engineering": {
285
- "alias": " - electrical_engineering",
286
- "acc,none": 0.2,
287
- "acc_stderr,none": 0.033333333333333284
288
- },
289
- "mmlu_elementary_mathematics": {
290
- "alias": " - elementary_mathematics",
291
- "acc,none": 0.2724867724867725,
292
- "acc_stderr,none": 0.022930973071633356
293
- },
294
- "mmlu_high_school_biology": {
295
- "alias": " - high_school_biology",
296
- "acc,none": 0.2903225806451613,
297
- "acc_stderr,none": 0.025822106119415898
298
- },
299
- "mmlu_high_school_chemistry": {
300
- "alias": " - high_school_chemistry",
301
- "acc,none": 0.2561576354679803,
302
- "acc_stderr,none": 0.030712730070982592
303
- },
304
- "mmlu_high_school_computer_science": {
305
- "alias": " - high_school_computer_science",
306
- "acc,none": 0.23,
307
- "acc_stderr,none": 0.04229525846816508
308
- },
309
- "mmlu_high_school_mathematics": {
310
- "alias": " - high_school_mathematics",
311
- "acc,none": 0.3,
312
- "acc_stderr,none": 0.027940457136228416
313
- },
314
- "mmlu_high_school_physics": {
315
- "alias": " - high_school_physics",
316
- "acc,none": 0.2781456953642384,
317
- "acc_stderr,none": 0.03658603262763743
318
- },
319
- "mmlu_high_school_statistics": {
320
- "alias": " - high_school_statistics",
321
- "acc,none": 0.36574074074074076,
322
- "acc_stderr,none": 0.032847388576472056
323
- },
324
- "mmlu_machine_learning": {
325
- "alias": " - machine_learning",
326
- "acc,none": 0.24107142857142858,
327
- "acc_stderr,none": 0.04059867246952687
328
- }
329
- }
330
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T11-56-41.258584_lambada_openai.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "lambada_openai"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "lambada_openai": {
20
- "alias": "lambada_openai",
21
- "perplexity,none": 12.642543091460501,
22
- "perplexity_stderr,none": 0.38123879021241674,
23
- "acc,none": 0.4814671065398797,
24
- "acc_stderr,none": 0.006961190829726007
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T12-14-40.804741_hellaswag.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "hellaswag"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "hellaswag": {
20
- "alias": "hellaswag",
21
- "acc,none": 0.34475204142601074,
22
- "acc_stderr,none": 0.00474316003427116,
23
- "acc_norm,none": 0.4213304122684724,
24
- "acc_norm_stderr,none": 0.0049276318064775575
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T12-16-12.146728_piqa.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "piqa"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "piqa": {
20
- "alias": "piqa",
21
- "acc,none": 0.6730141458106638,
22
- "acc_stderr,none": 0.010945157126978227,
23
- "acc_norm,none": 0.6653971708378672,
24
- "acc_norm_stderr,none": 0.011009071725162503
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T12-19-04.686563_arc_easy.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "arc_easy"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "arc_easy": {
20
- "alias": "arc_easy",
21
- "acc,none": 0.593013468013468,
22
- "acc_stderr,none": 0.010080695355466593,
23
- "acc_norm,none": 0.5437710437710438,
24
- "acc_norm_stderr,none": 0.010220394383722018
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T12-20-40.573806_arc_challenge.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "arc_challenge"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "arc_challenge": {
20
- "alias": "arc_challenge",
21
- "acc,none": 0.2551194539249147,
22
- "acc_stderr,none": 0.0127390386952021,
23
- "acc_norm,none": 0.2909556313993174,
24
- "acc_norm_stderr,none": 0.013273077865907593
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T13-19-33.146311_glue.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "glue"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "cola": {
20
- "alias": "cola",
21
- "mcc,none": 0.0,
22
- "mcc_stderr,none": 0.0
23
- },
24
- "mnli": {
25
- "alias": "mnli",
26
- "acc,none": 0.31900152827305145,
27
- "acc_stderr,none": 0.00470485695337838
28
- },
29
- "mnli_mismatch": {
30
- "alias": "mnli_mismatch",
31
- "acc,none": 0.31682262001627337,
32
- "acc_stderr,none": 0.0046921942364258435
33
- },
34
- "mrpc": {
35
- "alias": "mrpc",
36
- "acc,none": 0.3799019607843137,
37
- "acc_stderr,none": 0.024058510831539842,
38
- "f1,none": 0.24925816023738873,
39
- "f1_stderr,none": 0.031299043218421745
40
- },
41
- "qnli": {
42
- "alias": "qnli",
43
- "acc,none": 0.48892549881017755,
44
- "acc_stderr,none": 0.006763750866374647
45
- },
46
- "qqp": {
47
- "alias": "qqp",
48
- "acc,none": 0.4644076181053673,
49
- "acc_stderr,none": 0.002480392237462389,
50
- "f1,none": 0.46043057908900625,
51
- "f1_stderr,none": 0.0030958101543491746
52
- },
53
- "rte": {
54
- "alias": "rte",
55
- "acc,none": 0.5523465703971119,
56
- "acc_stderr,none": 0.02993107036293953
57
- },
58
- "sst2": {
59
- "alias": "sst2",
60
- "acc,none": 0.801605504587156,
61
- "acc_stderr,none": 0.013512511513295078
62
- },
63
- "wnli": {
64
- "alias": "wnli",
65
- "acc,none": 0.5211267605633803,
66
- "acc_stderr,none": 0.05970805879899504
67
- }
68
- }
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T13-20-31.009617_winogrande.json DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "winogrande"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "winogrande": {
20
- "alias": "winogrande",
21
- "acc,none": 0.5272296764009471,
22
- "acc_stderr,none": 0.014031631629827698
23
- }
24
- }
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T13-22-11.575335_sciq.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "sciq"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "sciq": {
20
- "alias": "sciq",
21
- "acc,none": 0.863,
22
- "acc_stderr,none": 0.010878848714333299,
23
- "acc_norm,none": 0.81,
24
- "acc_norm_stderr,none": 0.012411851354816324
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T13-41-59.570521_mmlu.json DELETED
@@ -1,330 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "mmlu"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "mmlu": {
20
- "acc,none": 0.25409485828229594,
21
- "acc_stderr,none": 0.003673285974361475,
22
- "alias": "mmlu"
23
- },
24
- "mmlu_humanities": {
25
- "acc,none": 0.2454835281615303,
26
- "acc_stderr,none": 0.006269554905683639,
27
- "alias": " - humanities"
28
- },
29
- "mmlu_formal_logic": {
30
- "alias": " - formal_logic",
31
- "acc,none": 0.3412698412698413,
32
- "acc_stderr,none": 0.04240799327574924
33
- },
34
- "mmlu_high_school_european_history": {
35
- "alias": " - high_school_european_history",
36
- "acc,none": 0.3151515151515151,
37
- "acc_stderr,none": 0.0362773057502241
38
- },
39
- "mmlu_high_school_us_history": {
40
- "alias": " - high_school_us_history",
41
- "acc,none": 0.24509803921568626,
42
- "acc_stderr,none": 0.030190282453501943
43
- },
44
- "mmlu_high_school_world_history": {
45
- "alias": " - high_school_world_history",
46
- "acc,none": 0.2742616033755274,
47
- "acc_stderr,none": 0.02904133351059801
48
- },
49
- "mmlu_international_law": {
50
- "alias": " - international_law",
51
- "acc,none": 0.23140495867768596,
52
- "acc_stderr,none": 0.03849856098794088
53
- },
54
- "mmlu_jurisprudence": {
55
- "alias": " - jurisprudence",
56
- "acc,none": 0.21296296296296297,
57
- "acc_stderr,none": 0.039578354719809805
58
- },
59
- "mmlu_logical_fallacies": {
60
- "alias": " - logical_fallacies",
61
- "acc,none": 0.26380368098159507,
62
- "acc_stderr,none": 0.03462419931615624
63
- },
64
- "mmlu_moral_disputes": {
65
- "alias": " - moral_disputes",
66
- "acc,none": 0.2398843930635838,
67
- "acc_stderr,none": 0.022989592543123567
68
- },
69
- "mmlu_moral_scenarios": {
70
- "alias": " - moral_scenarios",
71
- "acc,none": 0.24581005586592178,
72
- "acc_stderr,none": 0.01440029642922559
73
- },
74
- "mmlu_philosophy": {
75
- "alias": " - philosophy",
76
- "acc,none": 0.1864951768488746,
77
- "acc_stderr,none": 0.022122439772480764
78
- },
79
- "mmlu_prehistory": {
80
- "alias": " - prehistory",
81
- "acc,none": 0.2191358024691358,
82
- "acc_stderr,none": 0.023016705640262175
83
- },
84
- "mmlu_professional_law": {
85
- "alias": " - professional_law",
86
- "acc,none": 0.24771838331160365,
87
- "acc_stderr,none": 0.011025499291443735
88
- },
89
- "mmlu_world_religions": {
90
- "alias": " - world_religions",
91
- "acc,none": 0.22807017543859648,
92
- "acc_stderr,none": 0.03218093795602357
93
- },
94
- "mmlu_other": {
95
- "acc,none": 0.25523012552301255,
96
- "acc_stderr,none": 0.00781936823628676,
97
- "alias": " - other"
98
- },
99
- "mmlu_business_ethics": {
100
- "alias": " - business_ethics",
101
- "acc,none": 0.22,
102
- "acc_stderr,none": 0.04163331998932269
103
- },
104
- "mmlu_clinical_knowledge": {
105
- "alias": " - clinical_knowledge",
106
- "acc,none": 0.26037735849056604,
107
- "acc_stderr,none": 0.02700876609070809
108
- },
109
- "mmlu_college_medicine": {
110
- "alias": " - college_medicine",
111
- "acc,none": 0.24277456647398843,
112
- "acc_stderr,none": 0.0326926380614177
113
- },
114
- "mmlu_global_facts": {
115
- "alias": " - global_facts",
116
- "acc,none": 0.22,
117
- "acc_stderr,none": 0.0416333199893227
118
- },
119
- "mmlu_human_aging": {
120
- "alias": " - human_aging",
121
- "acc,none": 0.32286995515695066,
122
- "acc_stderr,none": 0.03138147637575498
123
- },
124
- "mmlu_management": {
125
- "alias": " - management",
126
- "acc,none": 0.2912621359223301,
127
- "acc_stderr,none": 0.04498676320572924
128
- },
129
- "mmlu_marketing": {
130
- "alias": " - marketing",
131
- "acc,none": 0.2863247863247863,
132
- "acc_stderr,none": 0.029614323690456648
133
- },
134
- "mmlu_medical_genetics": {
135
- "alias": " - medical_genetics",
136
- "acc,none": 0.24,
137
- "acc_stderr,none": 0.04292346959909283
138
- },
139
- "mmlu_miscellaneous": {
140
- "alias": " - miscellaneous",
141
- "acc,none": 0.23371647509578544,
142
- "acc_stderr,none": 0.015133383278988832
143
- },
144
- "mmlu_nutrition": {
145
- "alias": " - nutrition",
146
- "acc,none": 0.23529411764705882,
147
- "acc_stderr,none": 0.024288619466046116
148
- },
149
- "mmlu_professional_accounting": {
150
- "alias": " - professional_accounting",
151
- "acc,none": 0.2553191489361702,
152
- "acc_stderr,none": 0.02601199293090201
153
- },
154
- "mmlu_professional_medicine": {
155
- "alias": " - professional_medicine",
156
- "acc,none": 0.2977941176470588,
157
- "acc_stderr,none": 0.027778298701545443
158
- },
159
- "mmlu_virology": {
160
- "alias": " - virology",
161
- "acc,none": 0.22289156626506024,
162
- "acc_stderr,none": 0.03240004825594688
163
- },
164
- "mmlu_social_sciences": {
165
- "acc,none": 0.25901852453688656,
166
- "acc_stderr,none": 0.007907951917759793,
167
- "alias": " - social sciences"
168
- },
169
- "mmlu_econometrics": {
170
- "alias": " - econometrics",
171
- "acc,none": 0.2719298245614035,
172
- "acc_stderr,none": 0.041857744240220575
173
- },
174
- "mmlu_high_school_geography": {
175
- "alias": " - high_school_geography",
176
- "acc,none": 0.2828282828282828,
177
- "acc_stderr,none": 0.032087795587867514
178
- },
179
- "mmlu_high_school_government_and_politics": {
180
- "alias": " - high_school_government_and_politics",
181
- "acc,none": 0.26424870466321243,
182
- "acc_stderr,none": 0.03182155050916647
183
- },
184
- "mmlu_high_school_macroeconomics": {
185
- "alias": " - high_school_macroeconomics",
186
- "acc,none": 0.25384615384615383,
187
- "acc_stderr,none": 0.022066054378726253
188
- },
189
- "mmlu_high_school_microeconomics": {
190
- "alias": " - high_school_microeconomics",
191
- "acc,none": 0.2689075630252101,
192
- "acc_stderr,none": 0.028801392193631276
193
- },
194
- "mmlu_high_school_psychology": {
195
- "alias": " - high_school_psychology",
196
- "acc,none": 0.24403669724770644,
197
- "acc_stderr,none": 0.018415286351416406
198
- },
199
- "mmlu_human_sexuality": {
200
- "alias": " - human_sexuality",
201
- "acc,none": 0.2900763358778626,
202
- "acc_stderr,none": 0.03980066246467765
203
- },
204
- "mmlu_professional_psychology": {
205
- "alias": " - professional_psychology",
206
- "acc,none": 0.26143790849673204,
207
- "acc_stderr,none": 0.017776947157528027
208
- },
209
- "mmlu_public_relations": {
210
- "alias": " - public_relations",
211
- "acc,none": 0.22727272727272727,
212
- "acc_stderr,none": 0.04013964554072774
213
- },
214
- "mmlu_security_studies": {
215
- "alias": " - security_studies",
216
- "acc,none": 0.24489795918367346,
217
- "acc_stderr,none": 0.027529637440174923
218
- },
219
- "mmlu_sociology": {
220
- "alias": " - sociology",
221
- "acc,none": 0.2835820895522388,
222
- "acc_stderr,none": 0.03187187537919797
223
- },
224
- "mmlu_us_foreign_policy": {
225
- "alias": " - us_foreign_policy",
226
- "acc,none": 0.23,
227
- "acc_stderr,none": 0.042295258468165065
228
- },
229
- "mmlu_stem": {
230
- "acc,none": 0.26102124960355216,
231
- "acc_stderr,none": 0.007821062178349759,
232
- "alias": " - stem"
233
- },
234
- "mmlu_abstract_algebra": {
235
- "alias": " - abstract_algebra",
236
- "acc,none": 0.19,
237
- "acc_stderr,none": 0.039427724440366234
238
- },
239
- "mmlu_anatomy": {
240
- "alias": " - anatomy",
241
- "acc,none": 0.21481481481481482,
242
- "acc_stderr,none": 0.035478541985608236
243
- },
244
- "mmlu_astronomy": {
245
- "alias": " - astronomy",
246
- "acc,none": 0.2894736842105263,
247
- "acc_stderr,none": 0.036906779861372814
248
- },
249
- "mmlu_college_biology": {
250
- "alias": " - college_biology",
251
- "acc,none": 0.2361111111111111,
252
- "acc_stderr,none": 0.03551446610810826
253
- },
254
- "mmlu_college_chemistry": {
255
- "alias": " - college_chemistry",
256
- "acc,none": 0.34,
257
- "acc_stderr,none": 0.047609522856952365
258
- },
259
- "mmlu_college_computer_science": {
260
- "alias": " - college_computer_science",
261
- "acc,none": 0.28,
262
- "acc_stderr,none": 0.04512608598542128
263
- },
264
- "mmlu_college_mathematics": {
265
- "alias": " - college_mathematics",
266
- "acc,none": 0.25,
267
- "acc_stderr,none": 0.04351941398892446
268
- },
269
- "mmlu_college_physics": {
270
- "alias": " - college_physics",
271
- "acc,none": 0.28431372549019607,
272
- "acc_stderr,none": 0.04488482852329017
273
- },
274
- "mmlu_computer_security": {
275
- "alias": " - computer_security",
276
- "acc,none": 0.24,
277
- "acc_stderr,none": 0.042923469599092816
278
- },
279
- "mmlu_conceptual_physics": {
280
- "alias": " - conceptual_physics",
281
- "acc,none": 0.2170212765957447,
282
- "acc_stderr,none": 0.02694748312149622
283
- },
284
- "mmlu_electrical_engineering": {
285
- "alias": " - electrical_engineering",
286
- "acc,none": 0.2206896551724138,
287
- "acc_stderr,none": 0.03455930201924813
288
- },
289
- "mmlu_elementary_mathematics": {
290
- "alias": " - elementary_mathematics",
291
- "acc,none": 0.2671957671957672,
292
- "acc_stderr,none": 0.022789673145776575
293
- },
294
- "mmlu_high_school_biology": {
295
- "alias": " - high_school_biology",
296
- "acc,none": 0.2806451612903226,
297
- "acc_stderr,none": 0.025560604721022888
298
- },
299
- "mmlu_high_school_chemistry": {
300
- "alias": " - high_school_chemistry",
301
- "acc,none": 0.2561576354679803,
302
- "acc_stderr,none": 0.030712730070982592
303
- },
304
- "mmlu_high_school_computer_science": {
305
- "alias": " - high_school_computer_science",
306
- "acc,none": 0.24,
307
- "acc_stderr,none": 0.04292346959909282
308
- },
309
- "mmlu_high_school_mathematics": {
310
- "alias": " - high_school_mathematics",
311
- "acc,none": 0.2740740740740741,
312
- "acc_stderr,none": 0.027195934804085622
313
- },
314
- "mmlu_high_school_physics": {
315
- "alias": " - high_school_physics",
316
- "acc,none": 0.24503311258278146,
317
- "acc_stderr,none": 0.03511807571804726
318
- },
319
- "mmlu_high_school_statistics": {
320
- "alias": " - high_school_statistics",
321
- "acc,none": 0.3287037037037037,
322
- "acc_stderr,none": 0.03203614084670058
323
- },
324
- "mmlu_machine_learning": {
325
- "alias": " - machine_learning",
326
- "acc,none": 0.25,
327
- "acc_stderr,none": 0.04109974682633932
328
- }
329
- }
330
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T13-51-36.484339_lambada_multilingual.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "lambada_multilingual"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "lambada_openai_mt_de": {
20
- "alias": "lambada_openai_mt_de",
21
- "perplexity,none": 212.25983991266492,
22
- "perplexity_stderr,none": 13.036191156227552,
23
- "acc,none": 0.2456821269163594,
24
- "acc_stderr,none": 0.0059975800540142
25
- },
26
- "lambada_openai_mt_en": {
27
- "alias": "lambada_openai_mt_en",
28
- "perplexity,none": 12.64254308002806,
29
- "perplexity_stderr,none": 0.3812387886051039,
30
- "acc,none": 0.4814671065398797,
31
- "acc_stderr,none": 0.006961190829726007
32
- },
33
- "lambada_openai_mt_es": {
34
- "alias": "lambada_openai_mt_es",
35
- "perplexity,none": 266.87295366430163,
36
- "perplexity_stderr,none": 15.932942020346013,
37
- "acc,none": 0.2536386570929556,
38
- "acc_stderr,none": 0.006061698956508257
39
- },
40
- "lambada_openai_mt_fr": {
41
- "alias": "lambada_openai_mt_fr",
42
- "perplexity,none": 129.37466016136514,
43
- "perplexity_stderr,none": 7.571204962328844,
44
- "acc,none": 0.31593246652435475,
45
- "acc_stderr,none": 0.0064767732277837935
46
- },
47
- "lambada_openai_mt_it": {
48
- "alias": "lambada_openai_mt_it",
49
- "perplexity,none": 209.52126390403453,
50
- "perplexity_stderr,none": 13.299710278444714,
51
- "acc,none": 0.2856588395109645,
52
- "acc_stderr,none": 0.00629344939005611
53
- }
54
- }
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T14-07-25.400235_pawsx.json DELETED
@@ -1,60 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "pawsx"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "pawsx": {
20
- "acc,none": 0.4612857142857143,
21
- "acc_stderr,none": 0.004212518419096327,
22
- "alias": "pawsx"
23
- },
24
- "paws_de": {
25
- "alias": " - paws_de",
26
- "acc,none": 0.451,
27
- "acc_stderr,none": 0.011129305041886329
28
- },
29
- "paws_en": {
30
- "alias": " - paws_en",
31
- "acc,none": 0.4705,
32
- "acc_stderr,none": 0.011163654804511655
33
- },
34
- "paws_es": {
35
- "alias": " - paws_es",
36
- "acc,none": 0.4885,
37
- "acc_stderr,none": 0.011180177690296084
38
- },
39
- "paws_fr": {
40
- "alias": " - paws_fr",
41
- "acc,none": 0.4585,
42
- "acc_stderr,none": 0.011144549137930344
43
- },
44
- "paws_ja": {
45
- "alias": " - paws_ja",
46
- "acc,none": 0.4415,
47
- "acc_stderr,none": 0.011106329288974695
48
- },
49
- "paws_ko": {
50
- "alias": " - paws_ko",
51
- "acc,none": 0.459,
52
- "acc_stderr,none": 0.011145474902641254
53
- },
54
- "paws_zh": {
55
- "alias": " - paws_zh",
56
- "acc,none": 0.46,
57
- "acc_stderr,none": 0.01114729254418001
58
- }
59
- }
60
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T14-57-32.308002_xcopa.json DELETED
@@ -1,80 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xcopa"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xcopa": {
20
- "acc,none": 0.5330909090909091,
21
- "acc_stderr,none": 0.0067289909324144215,
22
- "alias": "xcopa"
23
- },
24
- "xcopa_et": {
25
- "alias": " - xcopa_et",
26
- "acc,none": 0.496,
27
- "acc_stderr,none": 0.02238235778196214
28
- },
29
- "xcopa_ht": {
30
- "alias": " - xcopa_ht",
31
- "acc,none": 0.544,
32
- "acc_stderr,none": 0.022296238348407053
33
- },
34
- "xcopa_id": {
35
- "alias": " - xcopa_id",
36
- "acc,none": 0.556,
37
- "acc_stderr,none": 0.022242244375731024
38
- },
39
- "xcopa_it": {
40
- "alias": " - xcopa_it",
41
- "acc,none": 0.532,
42
- "acc_stderr,none": 0.022337186479044292
43
- },
44
- "xcopa_qu": {
45
- "alias": " - xcopa_qu",
46
- "acc,none": 0.502,
47
- "acc_stderr,none": 0.022382894986483524
48
- },
49
- "xcopa_sw": {
50
- "alias": " - xcopa_sw",
51
- "acc,none": 0.528,
52
- "acc_stderr,none": 0.022347949832668093
53
- },
54
- "xcopa_ta": {
55
- "alias": " - xcopa_ta",
56
- "acc,none": 0.538,
57
- "acc_stderr,none": 0.022318338119870523
58
- },
59
- "xcopa_th": {
60
- "alias": " - xcopa_th",
61
- "acc,none": 0.56,
62
- "acc_stderr,none": 0.022221331534143015
63
- },
64
- "xcopa_tr": {
65
- "alias": " - xcopa_tr",
66
- "acc,none": 0.526,
67
- "acc_stderr,none": 0.022352791650914167
68
- },
69
- "xcopa_vi": {
70
- "alias": " - xcopa_vi",
71
- "acc,none": 0.534,
72
- "acc_stderr,none": 0.022331264423258383
73
- },
74
- "xcopa_zh": {
75
- "alias": " - xcopa_zh",
76
- "acc,none": 0.548,
77
- "acc_stderr,none": 0.02227969410784342
78
- }
79
- }
80
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T16-02-57.684170_xnli.json DELETED
@@ -1,100 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xnli"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xnli": {
20
- "acc,none": 0.37566265060240966,
21
- "acc_stderr,none": 0.0024964839295963676,
22
- "alias": "xnli"
23
- },
24
- "xnli_ar": {
25
- "alias": " - xnli_ar",
26
- "acc,none": 0.3405622489959839,
27
- "acc_stderr,none": 0.009498886690274442
28
- },
29
- "xnli_bg": {
30
- "alias": " - xnli_bg",
31
- "acc,none": 0.37269076305220883,
32
- "acc_stderr,none": 0.009691761259693463
33
- },
34
- "xnli_de": {
35
- "alias": " - xnli_de",
36
- "acc,none": 0.41686746987951806,
37
- "acc_stderr,none": 0.009882576606533236
38
- },
39
- "xnli_el": {
40
- "alias": " - xnli_el",
41
- "acc,none": 0.3369477911646586,
42
- "acc_stderr,none": 0.009474203778757712
43
- },
44
- "xnli_en": {
45
- "alias": " - xnli_en",
46
- "acc,none": 0.4827309236947791,
47
- "acc_stderr,none": 0.010016093498409703
48
- },
49
- "xnli_es": {
50
- "alias": " - xnli_es",
51
- "acc,none": 0.3815261044176707,
52
- "acc_stderr,none": 0.00973666813309817
53
- },
54
- "xnli_fr": {
55
- "alias": " - xnli_fr",
56
- "acc,none": 0.42730923694779116,
57
- "acc_stderr,none": 0.009915595034908124
58
- },
59
- "xnli_hi": {
60
- "alias": " - xnli_hi",
61
- "acc,none": 0.3514056224899598,
62
- "acc_stderr,none": 0.00956926307982396
63
- },
64
- "xnli_ru": {
65
- "alias": " - xnli_ru",
66
- "acc,none": 0.43333333333333335,
67
- "acc_stderr,none": 0.009932588282324236
68
- },
69
- "xnli_sw": {
70
- "alias": " - xnli_sw",
71
- "acc,none": 0.3465863453815261,
72
- "acc_stderr,none": 0.009538660220459
73
- },
74
- "xnli_th": {
75
- "alias": " - xnli_th",
76
- "acc,none": 0.3397590361445783,
77
- "acc_stderr,none": 0.009493454925438249
78
- },
79
- "xnli_tr": {
80
- "alias": " - xnli_tr",
81
- "acc,none": 0.3598393574297189,
82
- "acc_stderr,none": 0.009620250217765997
83
- },
84
- "xnli_ur": {
85
- "alias": " - xnli_ur",
86
- "acc,none": 0.3345381526104418,
87
- "acc_stderr,none": 0.009457404390939166
88
- },
89
- "xnli_vi": {
90
- "alias": " - xnli_vi",
91
- "acc,none": 0.3690763052208835,
92
- "acc_stderr,none": 0.00967239564447043
93
- },
94
- "xnli_zh": {
95
- "alias": " - xnli_zh",
96
- "acc,none": 0.3417670682730924,
97
- "acc_stderr,none": 0.009506977398287621
98
- }
99
- }
100
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T16-19-00.595561_xstorycloze.json DELETED
@@ -1,80 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xstorycloze"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xstorycloze": {
20
- "acc,none": 0.5257204740990313,
21
- "acc_stderr,none": 0.003863789045312555,
22
- "alias": "xstorycloze"
23
- },
24
- "xstorycloze_ar": {
25
- "alias": " - xstorycloze_ar",
26
- "acc,none": 0.4818001323626737,
27
- "acc_stderr,none": 0.012858598401831848
28
- },
29
- "xstorycloze_en": {
30
- "alias": " - xstorycloze_en",
31
- "acc,none": 0.6293845135671741,
32
- "acc_stderr,none": 0.012428861084065903
33
- },
34
- "xstorycloze_es": {
35
- "alias": " - xstorycloze_es",
36
- "acc,none": 0.5400397088021178,
37
- "acc_stderr,none": 0.012825802370083987
38
- },
39
- "xstorycloze_eu": {
40
- "alias": " - xstorycloze_eu",
41
- "acc,none": 0.5201853077432164,
42
- "acc_stderr,none": 0.012856635706498292
43
- },
44
- "xstorycloze_hi": {
45
- "alias": " - xstorycloze_hi",
46
- "acc,none": 0.514890800794176,
47
- "acc_stderr,none": 0.012861417842074004
48
- },
49
- "xstorycloze_id": {
50
- "alias": " - xstorycloze_id",
51
- "acc,none": 0.5069490403706155,
52
- "acc_stderr,none": 0.012865882570960722
53
- },
54
- "xstorycloze_my": {
55
- "alias": " - xstorycloze_my",
56
- "acc,none": 0.5029781601588352,
57
- "acc_stderr,none": 0.012866897066011233
58
- },
59
- "xstorycloze_ru": {
60
- "alias": " - xstorycloze_ru",
61
- "acc,none": 0.5129053606882858,
62
- "acc_stderr,none": 0.012862838605728476
63
- },
64
- "xstorycloze_sw": {
65
- "alias": " - xstorycloze_sw",
66
- "acc,none": 0.4990072799470549,
67
- "acc_stderr,none": 0.012867099955422926
68
- },
69
- "xstorycloze_te": {
70
- "alias": " - xstorycloze_te",
71
- "acc,none": 0.5340833884844474,
72
- "acc_stderr,none": 0.012837195610619434
73
- },
74
- "xstorycloze_zh": {
75
- "alias": " - xstorycloze_zh",
76
- "acc,none": 0.5407015221707479,
77
- "acc_stderr,none": 0.012824422739625578
78
- }
79
- }
80
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T16-21-46.468616_xwinograd.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xwinograd"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xwinograd": {
20
- "acc,none": 0.6414924702180266,
21
- "acc_stderr,none": 0.007097604851218048,
22
- "alias": "xwinograd"
23
- },
24
- "xwinograd_en": {
25
- "alias": " - xwinograd_en",
26
- "acc,none": 0.7088172043010753,
27
- "acc_stderr,none": 0.009423927122193903
28
- },
29
- "xwinograd_fr": {
30
- "alias": " - xwinograd_fr",
31
- "acc,none": 0.6144578313253012,
32
- "acc_stderr,none": 0.0537495779731939
33
- },
34
- "xwinograd_jp": {
35
- "alias": " - xwinograd_jp",
36
- "acc,none": 0.5338894681960376,
37
- "acc_stderr,none": 0.016117117806017902
38
- },
39
- "xwinograd_pt": {
40
- "alias": " - xwinograd_pt",
41
- "acc,none": 0.532319391634981,
42
- "acc_stderr,none": 0.030825503526303782
43
- },
44
- "xwinograd_ru": {
45
- "alias": " - xwinograd_ru",
46
- "acc,none": 0.5523809523809524,
47
- "acc_stderr,none": 0.0280613656383537
48
- },
49
- "xwinograd_zh": {
50
- "alias": " - xwinograd_zh",
51
- "acc,none": 0.6527777777777778,
52
- "acc_stderr,none": 0.021227675707409233
53
- }
54
- }
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T17-22-18.851434_mmlu.json DELETED
@@ -1,330 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "mmlu"
5
- ],
6
- "num_fewshot": 5,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "mmlu": {
20
- "acc,none": 0.25409485828229594,
21
- "acc_stderr,none": 0.003673285974361475,
22
- "alias": "mmlu"
23
- },
24
- "mmlu_humanities": {
25
- "acc,none": 0.2454835281615303,
26
- "acc_stderr,none": 0.006269554905683639,
27
- "alias": " - humanities"
28
- },
29
- "mmlu_formal_logic": {
30
- "alias": " - formal_logic",
31
- "acc,none": 0.3412698412698413,
32
- "acc_stderr,none": 0.04240799327574924
33
- },
34
- "mmlu_high_school_european_history": {
35
- "alias": " - high_school_european_history",
36
- "acc,none": 0.3151515151515151,
37
- "acc_stderr,none": 0.0362773057502241
38
- },
39
- "mmlu_high_school_us_history": {
40
- "alias": " - high_school_us_history",
41
- "acc,none": 0.24509803921568626,
42
- "acc_stderr,none": 0.030190282453501943
43
- },
44
- "mmlu_high_school_world_history": {
45
- "alias": " - high_school_world_history",
46
- "acc,none": 0.2742616033755274,
47
- "acc_stderr,none": 0.02904133351059801
48
- },
49
- "mmlu_international_law": {
50
- "alias": " - international_law",
51
- "acc,none": 0.23140495867768596,
52
- "acc_stderr,none": 0.03849856098794088
53
- },
54
- "mmlu_jurisprudence": {
55
- "alias": " - jurisprudence",
56
- "acc,none": 0.21296296296296297,
57
- "acc_stderr,none": 0.039578354719809805
58
- },
59
- "mmlu_logical_fallacies": {
60
- "alias": " - logical_fallacies",
61
- "acc,none": 0.26380368098159507,
62
- "acc_stderr,none": 0.03462419931615624
63
- },
64
- "mmlu_moral_disputes": {
65
- "alias": " - moral_disputes",
66
- "acc,none": 0.2398843930635838,
67
- "acc_stderr,none": 0.022989592543123567
68
- },
69
- "mmlu_moral_scenarios": {
70
- "alias": " - moral_scenarios",
71
- "acc,none": 0.24581005586592178,
72
- "acc_stderr,none": 0.01440029642922559
73
- },
74
- "mmlu_philosophy": {
75
- "alias": " - philosophy",
76
- "acc,none": 0.1864951768488746,
77
- "acc_stderr,none": 0.022122439772480764
78
- },
79
- "mmlu_prehistory": {
80
- "alias": " - prehistory",
81
- "acc,none": 0.2191358024691358,
82
- "acc_stderr,none": 0.023016705640262175
83
- },
84
- "mmlu_professional_law": {
85
- "alias": " - professional_law",
86
- "acc,none": 0.24771838331160365,
87
- "acc_stderr,none": 0.011025499291443735
88
- },
89
- "mmlu_world_religions": {
90
- "alias": " - world_religions",
91
- "acc,none": 0.22807017543859648,
92
- "acc_stderr,none": 0.03218093795602357
93
- },
94
- "mmlu_other": {
95
- "acc,none": 0.25523012552301255,
96
- "acc_stderr,none": 0.00781936823628676,
97
- "alias": " - other"
98
- },
99
- "mmlu_business_ethics": {
100
- "alias": " - business_ethics",
101
- "acc,none": 0.22,
102
- "acc_stderr,none": 0.04163331998932269
103
- },
104
- "mmlu_clinical_knowledge": {
105
- "alias": " - clinical_knowledge",
106
- "acc,none": 0.26037735849056604,
107
- "acc_stderr,none": 0.02700876609070809
108
- },
109
- "mmlu_college_medicine": {
110
- "alias": " - college_medicine",
111
- "acc,none": 0.24277456647398843,
112
- "acc_stderr,none": 0.0326926380614177
113
- },
114
- "mmlu_global_facts": {
115
- "alias": " - global_facts",
116
- "acc,none": 0.22,
117
- "acc_stderr,none": 0.0416333199893227
118
- },
119
- "mmlu_human_aging": {
120
- "alias": " - human_aging",
121
- "acc,none": 0.32286995515695066,
122
- "acc_stderr,none": 0.03138147637575498
123
- },
124
- "mmlu_management": {
125
- "alias": " - management",
126
- "acc,none": 0.2912621359223301,
127
- "acc_stderr,none": 0.04498676320572924
128
- },
129
- "mmlu_marketing": {
130
- "alias": " - marketing",
131
- "acc,none": 0.2863247863247863,
132
- "acc_stderr,none": 0.029614323690456648
133
- },
134
- "mmlu_medical_genetics": {
135
- "alias": " - medical_genetics",
136
- "acc,none": 0.24,
137
- "acc_stderr,none": 0.04292346959909283
138
- },
139
- "mmlu_miscellaneous": {
140
- "alias": " - miscellaneous",
141
- "acc,none": 0.23371647509578544,
142
- "acc_stderr,none": 0.015133383278988832
143
- },
144
- "mmlu_nutrition": {
145
- "alias": " - nutrition",
146
- "acc,none": 0.23529411764705882,
147
- "acc_stderr,none": 0.024288619466046116
148
- },
149
- "mmlu_professional_accounting": {
150
- "alias": " - professional_accounting",
151
- "acc,none": 0.2553191489361702,
152
- "acc_stderr,none": 0.02601199293090201
153
- },
154
- "mmlu_professional_medicine": {
155
- "alias": " - professional_medicine",
156
- "acc,none": 0.2977941176470588,
157
- "acc_stderr,none": 0.027778298701545443
158
- },
159
- "mmlu_virology": {
160
- "alias": " - virology",
161
- "acc,none": 0.22289156626506024,
162
- "acc_stderr,none": 0.03240004825594688
163
- },
164
- "mmlu_social_sciences": {
165
- "acc,none": 0.25901852453688656,
166
- "acc_stderr,none": 0.007907951917759795,
167
- "alias": " - social sciences"
168
- },
169
- "mmlu_econometrics": {
170
- "alias": " - econometrics",
171
- "acc,none": 0.2719298245614035,
172
- "acc_stderr,none": 0.041857744240220575
173
- },
174
- "mmlu_high_school_geography": {
175
- "alias": " - high_school_geography",
176
- "acc,none": 0.2828282828282828,
177
- "acc_stderr,none": 0.032087795587867514
178
- },
179
- "mmlu_high_school_government_and_politics": {
180
- "alias": " - high_school_government_and_politics",
181
- "acc,none": 0.26424870466321243,
182
- "acc_stderr,none": 0.03182155050916647
183
- },
184
- "mmlu_high_school_macroeconomics": {
185
- "alias": " - high_school_macroeconomics",
186
- "acc,none": 0.25384615384615383,
187
- "acc_stderr,none": 0.022066054378726253
188
- },
189
- "mmlu_high_school_microeconomics": {
190
- "alias": " - high_school_microeconomics",
191
- "acc,none": 0.2689075630252101,
192
- "acc_stderr,none": 0.028801392193631276
193
- },
194
- "mmlu_high_school_psychology": {
195
- "alias": " - high_school_psychology",
196
- "acc,none": 0.24403669724770644,
197
- "acc_stderr,none": 0.018415286351416406
198
- },
199
- "mmlu_human_sexuality": {
200
- "alias": " - human_sexuality",
201
- "acc,none": 0.2900763358778626,
202
- "acc_stderr,none": 0.03980066246467765
203
- },
204
- "mmlu_professional_psychology": {
205
- "alias": " - professional_psychology",
206
- "acc,none": 0.26143790849673204,
207
- "acc_stderr,none": 0.017776947157528027
208
- },
209
- "mmlu_public_relations": {
210
- "alias": " - public_relations",
211
- "acc,none": 0.22727272727272727,
212
- "acc_stderr,none": 0.04013964554072774
213
- },
214
- "mmlu_security_studies": {
215
- "alias": " - security_studies",
216
- "acc,none": 0.24489795918367346,
217
- "acc_stderr,none": 0.027529637440174923
218
- },
219
- "mmlu_sociology": {
220
- "alias": " - sociology",
221
- "acc,none": 0.2835820895522388,
222
- "acc_stderr,none": 0.03187187537919797
223
- },
224
- "mmlu_us_foreign_policy": {
225
- "alias": " - us_foreign_policy",
226
- "acc,none": 0.23,
227
- "acc_stderr,none": 0.042295258468165065
228
- },
229
- "mmlu_stem": {
230
- "acc,none": 0.26102124960355216,
231
- "acc_stderr,none": 0.007821062178349759,
232
- "alias": " - stem"
233
- },
234
- "mmlu_abstract_algebra": {
235
- "alias": " - abstract_algebra",
236
- "acc,none": 0.19,
237
- "acc_stderr,none": 0.039427724440366234
238
- },
239
- "mmlu_anatomy": {
240
- "alias": " - anatomy",
241
- "acc,none": 0.21481481481481482,
242
- "acc_stderr,none": 0.035478541985608236
243
- },
244
- "mmlu_astronomy": {
245
- "alias": " - astronomy",
246
- "acc,none": 0.2894736842105263,
247
- "acc_stderr,none": 0.036906779861372814
248
- },
249
- "mmlu_college_biology": {
250
- "alias": " - college_biology",
251
- "acc,none": 0.2361111111111111,
252
- "acc_stderr,none": 0.03551446610810826
253
- },
254
- "mmlu_college_chemistry": {
255
- "alias": " - college_chemistry",
256
- "acc,none": 0.34,
257
- "acc_stderr,none": 0.047609522856952365
258
- },
259
- "mmlu_college_computer_science": {
260
- "alias": " - college_computer_science",
261
- "acc,none": 0.28,
262
- "acc_stderr,none": 0.04512608598542128
263
- },
264
- "mmlu_college_mathematics": {
265
- "alias": " - college_mathematics",
266
- "acc,none": 0.25,
267
- "acc_stderr,none": 0.04351941398892446
268
- },
269
- "mmlu_college_physics": {
270
- "alias": " - college_physics",
271
- "acc,none": 0.28431372549019607,
272
- "acc_stderr,none": 0.04488482852329017
273
- },
274
- "mmlu_computer_security": {
275
- "alias": " - computer_security",
276
- "acc,none": 0.24,
277
- "acc_stderr,none": 0.042923469599092816
278
- },
279
- "mmlu_conceptual_physics": {
280
- "alias": " - conceptual_physics",
281
- "acc,none": 0.2170212765957447,
282
- "acc_stderr,none": 0.02694748312149622
283
- },
284
- "mmlu_electrical_engineering": {
285
- "alias": " - electrical_engineering",
286
- "acc,none": 0.2206896551724138,
287
- "acc_stderr,none": 0.03455930201924813
288
- },
289
- "mmlu_elementary_mathematics": {
290
- "alias": " - elementary_mathematics",
291
- "acc,none": 0.2671957671957672,
292
- "acc_stderr,none": 0.022789673145776575
293
- },
294
- "mmlu_high_school_biology": {
295
- "alias": " - high_school_biology",
296
- "acc,none": 0.2806451612903226,
297
- "acc_stderr,none": 0.025560604721022888
298
- },
299
- "mmlu_high_school_chemistry": {
300
- "alias": " - high_school_chemistry",
301
- "acc,none": 0.2561576354679803,
302
- "acc_stderr,none": 0.030712730070982592
303
- },
304
- "mmlu_high_school_computer_science": {
305
- "alias": " - high_school_computer_science",
306
- "acc,none": 0.24,
307
- "acc_stderr,none": 0.04292346959909282
308
- },
309
- "mmlu_high_school_mathematics": {
310
- "alias": " - high_school_mathematics",
311
- "acc,none": 0.2740740740740741,
312
- "acc_stderr,none": 0.027195934804085622
313
- },
314
- "mmlu_high_school_physics": {
315
- "alias": " - high_school_physics",
316
- "acc,none": 0.24503311258278146,
317
- "acc_stderr,none": 0.03511807571804726
318
- },
319
- "mmlu_high_school_statistics": {
320
- "alias": " - high_school_statistics",
321
- "acc,none": 0.3287037037037037,
322
- "acc_stderr,none": 0.03203614084670058
323
- },
324
- "mmlu_machine_learning": {
325
- "alias": " - machine_learning",
326
- "acc,none": 0.25,
327
- "acc_stderr,none": 0.04109974682633932
328
- }
329
- }
330
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_11/0.4.8_2025-03-13T18-54-53.797865_lambada_openai_.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "lambada_openai"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": 11,
11
- "pad_token_ids": [
12
- 11
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "lambada_openai": {
20
- "alias": "lambada_openai",
21
- "perplexity,none": 12.642543877737143,
22
- "perplexity_stderr,none": 0.3812387951513916,
23
- "acc,none": 0.4814671065398797,
24
- "acc_stderr,none": 0.006961190829726007
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T09-57-49.932590_lambada_openai.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "lambada_openai"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "lambada_openai": {
20
- "alias": "lambada_openai",
21
- "perplexity,none": 12.62972464596384,
22
- "perplexity_stderr,none": 0.3806139731054351,
23
- "acc,none": 0.48282553852124976,
24
- "acc_stderr,none": 0.006961867045185065
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T10-13-21.086739_hellaswag.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "hellaswag"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "hellaswag": {
20
- "alias": "hellaswag",
21
- "acc,none": 0.3451503684524995,
22
- "acc_stderr,none": 0.004744456628455124,
23
- "acc_norm,none": 0.4197371041625174,
24
- "acc_norm_stderr,none": 0.004925072159723834
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T10-14-54.756945_piqa.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "piqa"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "piqa": {
20
- "alias": "piqa",
21
- "acc,none": 0.6735582154515778,
22
- "acc_stderr,none": 0.010940467046177306,
23
- "acc_norm,none": 0.6664853101196954,
24
- "acc_norm_stderr,none": 0.011000139592184566
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T10-17-57.209289_arc_easy.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "arc_easy"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "arc_easy": {
20
- "alias": "arc_easy",
21
- "acc,none": 0.5854377104377104,
22
- "acc_stderr,none": 0.010108889212447767,
23
- "acc_norm,none": 0.5420875420875421,
24
- "acc_norm_stderr,none": 0.010223371342195895
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T10-19-33.710789_arc_challenge.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "arc_challenge"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "arc_challenge": {
20
- "alias": "arc_challenge",
21
- "acc,none": 0.2551194539249147,
22
- "acc_stderr,none": 0.012739038695202102,
23
- "acc_norm,none": 0.2935153583617747,
24
- "acc_norm_stderr,none": 0.013307250444941113
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T12-39-38.019272_xnli.json DELETED
@@ -1,100 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xnli"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xnli": {
20
- "acc,none": 0.3731191432396252,
21
- "acc_stderr,none": 0.0024949681237011402,
22
- "alias": "xnli"
23
- },
24
- "xnli_ar": {
25
- "alias": " - xnli_ar",
26
- "acc,none": 0.3373493975903614,
27
- "acc_stderr,none": 0.009476976849778591
28
- },
29
- "xnli_bg": {
30
- "alias": " - xnli_bg",
31
- "acc,none": 0.3682730923694779,
32
- "acc_stderr,none": 0.009668013178998446
33
- },
34
- "xnli_de": {
35
- "alias": " - xnli_de",
36
- "acc,none": 0.40602409638554215,
37
- "acc_stderr,none": 0.00984346200738422
38
- },
39
- "xnli_el": {
40
- "alias": " - xnli_el",
41
- "acc,none": 0.3369477911646586,
42
- "acc_stderr,none": 0.009474203778757713
43
- },
44
- "xnli_en": {
45
- "alias": " - xnli_en",
46
- "acc,none": 0.4674698795180723,
47
- "acc_stderr,none": 0.010000839483876027
48
- },
49
- "xnli_es": {
50
- "alias": " - xnli_es",
51
- "acc,none": 0.3923694779116466,
52
- "acc_stderr,none": 0.009787120838990105
53
- },
54
- "xnli_fr": {
55
- "alias": " - xnli_fr",
56
- "acc,none": 0.42208835341365464,
57
- "acc_stderr,none": 0.009899652714895416
58
- },
59
- "xnli_hi": {
60
- "alias": " - xnli_hi",
61
- "acc,none": 0.351004016064257,
62
- "acc_stderr,none": 0.009566753834803288
63
- },
64
- "xnli_ru": {
65
- "alias": " - xnli_ru",
66
- "acc,none": 0.42208835341365464,
67
- "acc_stderr,none": 0.009899652714895424
68
- },
69
- "xnli_sw": {
70
- "alias": " - xnli_sw",
71
- "acc,none": 0.3481927710843373,
72
- "acc_stderr,none": 0.009548980649153391
73
- },
74
- "xnli_th": {
75
- "alias": " - xnli_th",
76
- "acc,none": 0.35180722891566263,
77
- "acc_stderr,none": 0.009571764897113621
78
- },
79
- "xnli_tr": {
80
- "alias": " - xnli_tr",
81
- "acc,none": 0.35180722891566263,
82
- "acc_stderr,none": 0.009571764897113625
83
- },
84
- "xnli_ur": {
85
- "alias": " - xnli_ur",
86
- "acc,none": 0.3349397590361446,
87
- "acc_stderr,none": 0.009460223484996469
88
- },
89
- "xnli_vi": {
90
- "alias": " - xnli_vi",
91
- "acc,none": 0.3674698795180723,
92
- "acc_stderr,none": 0.009663601903728034
93
- },
94
- "xnli_zh": {
95
- "alias": " - xnli_zh",
96
- "acc,none": 0.3389558232931727,
97
- "acc_stderr,none": 0.009487992732201522
98
- }
99
- }
100
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T12-56-32.162685_xstorycloze.json DELETED
@@ -1,80 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xstorycloze"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xstorycloze": {
20
- "acc,none": 0.5243366825100776,
21
- "acc_stderr,none": 0.0038648541830817408,
22
- "alias": "xstorycloze"
23
- },
24
- "xstorycloze_ar": {
25
- "alias": " - xstorycloze_ar",
26
- "acc,none": 0.4824619457313038,
27
- "acc_stderr,none": 0.012859207453266304
28
- },
29
- "xstorycloze_en": {
30
- "alias": " - xstorycloze_en",
31
- "acc,none": 0.6260754467240238,
32
- "acc_stderr,none": 0.012451361842944465
33
- },
34
- "xstorycloze_es": {
35
- "alias": " - xstorycloze_es",
36
- "acc,none": 0.5367306419589676,
37
- "acc_stderr,none": 0.012832359240206969
38
- },
39
- "xstorycloze_eu": {
40
- "alias": " - xstorycloze_eu",
41
- "acc,none": 0.5195234943745863,
42
- "acc_stderr,none": 0.01285731253183686
43
- },
44
- "xstorycloze_hi": {
45
- "alias": " - xstorycloze_hi",
46
- "acc,none": 0.514228987425546,
47
- "acc_stderr,none": 0.012861913999596129
48
- },
49
- "xstorycloze_id": {
50
- "alias": " - xstorycloze_id",
51
- "acc,none": 0.5049636002647253,
52
- "acc_stderr,none": 0.012866491277589943
53
- },
54
- "xstorycloze_my": {
55
- "alias": " - xstorycloze_my",
56
- "acc,none": 0.5036399735274653,
57
- "acc_stderr,none": 0.01286678434828923
58
- },
59
- "xstorycloze_ru": {
60
- "alias": " - xstorycloze_ru",
61
- "acc,none": 0.5122435473196558,
62
- "acc_stderr,none": 0.012863267059205548
63
- },
64
- "xstorycloze_sw": {
65
- "alias": " - xstorycloze_sw",
66
- "acc,none": 0.49702183984116477,
67
- "acc_stderr,none": 0.012866897066011233
68
- },
69
- "xstorycloze_te": {
70
- "alias": " - xstorycloze_te",
71
- "acc,none": 0.5340833884844474,
72
- "acc_stderr,none": 0.012837195610619434
73
- },
74
- "xstorycloze_zh": {
75
- "alias": " - xstorycloze_zh",
76
- "acc,none": 0.5367306419589676,
77
- "acc_stderr,none": 0.01283235924020697
78
- }
79
- }
80
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T12-59-30.016094_xwinograd.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xwinograd"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xwinograd": {
20
- "acc,none": 0.6439649359406608,
21
- "acc_stderr,none": 0.007096653855893872,
22
- "alias": "xwinograd"
23
- },
24
- "xwinograd_en": {
25
- "alias": " - xwinograd_en",
26
- "acc,none": 0.7066666666666667,
27
- "acc_stderr,none": 0.00944430382490117
28
- },
29
- "xwinograd_fr": {
30
- "alias": " - xwinograd_fr",
31
- "acc,none": 0.6626506024096386,
32
- "acc_stderr,none": 0.052212602620321284
33
- },
34
- "xwinograd_jp": {
35
- "alias": " - xwinograd_jp",
36
- "acc,none": 0.5380604796663191,
37
- "acc_stderr,none": 0.016107396603808045
38
- },
39
- "xwinograd_pt": {
40
- "alias": " - xwinograd_pt",
41
- "acc,none": 0.5513307984790875,
42
- "acc_stderr,none": 0.030726890349707915
43
- },
44
- "xwinograd_ru": {
45
- "alias": " - xwinograd_ru",
46
- "acc,none": 0.5587301587301587,
47
- "acc_stderr,none": 0.02802130493237513
48
- },
49
- "xwinograd_zh": {
50
- "alias": " - xwinograd_zh",
51
- "acc,none": 0.6547619047619048,
52
- "acc_stderr,none": 0.021199082505488055
53
- }
54
- }
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T13-49-01.062852_mmlu.json DELETED
@@ -1,330 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "mmlu"
5
- ],
6
- "num_fewshot": 5,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "mmlu": {
20
- "acc,none": 0.2547357926221336,
21
- "acc_stderr,none": 0.0036750666019376636,
22
- "alias": "mmlu"
23
- },
24
- "mmlu_humanities": {
25
- "acc,none": 0.2454835281615303,
26
- "acc_stderr,none": 0.006267346149858851,
27
- "alias": " - humanities"
28
- },
29
- "mmlu_formal_logic": {
30
- "alias": " - formal_logic",
31
- "acc,none": 0.3412698412698413,
32
- "acc_stderr,none": 0.04240799327574925
33
- },
34
- "mmlu_high_school_european_history": {
35
- "alias": " - high_school_european_history",
36
- "acc,none": 0.3151515151515151,
37
- "acc_stderr,none": 0.0362773057502241
38
- },
39
- "mmlu_high_school_us_history": {
40
- "alias": " - high_school_us_history",
41
- "acc,none": 0.24509803921568626,
42
- "acc_stderr,none": 0.03019028245350194
43
- },
44
- "mmlu_high_school_world_history": {
45
- "alias": " - high_school_world_history",
46
- "acc,none": 0.29535864978902954,
47
- "acc_stderr,none": 0.02969633871342286
48
- },
49
- "mmlu_international_law": {
50
- "alias": " - international_law",
51
- "acc,none": 0.2644628099173554,
52
- "acc_stderr,none": 0.04026187527591206
53
- },
54
- "mmlu_jurisprudence": {
55
- "alias": " - jurisprudence",
56
- "acc,none": 0.2222222222222222,
57
- "acc_stderr,none": 0.0401910747255735
58
- },
59
- "mmlu_logical_fallacies": {
60
- "alias": " - logical_fallacies",
61
- "acc,none": 0.24539877300613497,
62
- "acc_stderr,none": 0.03380939813943354
63
- },
64
- "mmlu_moral_disputes": {
65
- "alias": " - moral_disputes",
66
- "acc,none": 0.23410404624277456,
67
- "acc_stderr,none": 0.022797110278071128
68
- },
69
- "mmlu_moral_scenarios": {
70
- "alias": " - moral_scenarios",
71
- "acc,none": 0.2435754189944134,
72
- "acc_stderr,none": 0.014355911964767864
73
- },
74
- "mmlu_philosophy": {
75
- "alias": " - philosophy",
76
- "acc,none": 0.18006430868167203,
77
- "acc_stderr,none": 0.02182342285774495
78
- },
79
- "mmlu_prehistory": {
80
- "alias": " - prehistory",
81
- "acc,none": 0.21604938271604937,
82
- "acc_stderr,none": 0.022899162918445785
83
- },
84
- "mmlu_professional_law": {
85
- "alias": " - professional_law",
86
- "acc,none": 0.2470664928292047,
87
- "acc_stderr,none": 0.011015752255279338
88
- },
89
- "mmlu_world_religions": {
90
- "alias": " - world_religions",
91
- "acc,none": 0.23391812865497075,
92
- "acc_stderr,none": 0.03246721765117827
93
- },
94
- "mmlu_other": {
95
- "acc,none": 0.2603797875764403,
96
- "acc_stderr,none": 0.007871165717920162,
97
- "alias": " - other"
98
- },
99
- "mmlu_business_ethics": {
100
- "alias": " - business_ethics",
101
- "acc,none": 0.23,
102
- "acc_stderr,none": 0.04229525846816505
103
- },
104
- "mmlu_clinical_knowledge": {
105
- "alias": " - clinical_knowledge",
106
- "acc,none": 0.2830188679245283,
107
- "acc_stderr,none": 0.027724236492700904
108
- },
109
- "mmlu_college_medicine": {
110
- "alias": " - college_medicine",
111
- "acc,none": 0.24277456647398843,
112
- "acc_stderr,none": 0.0326926380614177
113
- },
114
- "mmlu_global_facts": {
115
- "alias": " - global_facts",
116
- "acc,none": 0.2,
117
- "acc_stderr,none": 0.04020151261036843
118
- },
119
- "mmlu_human_aging": {
120
- "alias": " - human_aging",
121
- "acc,none": 0.31390134529147984,
122
- "acc_stderr,none": 0.031146796482972465
123
- },
124
- "mmlu_management": {
125
- "alias": " - management",
126
- "acc,none": 0.2912621359223301,
127
- "acc_stderr,none": 0.04498676320572924
128
- },
129
- "mmlu_marketing": {
130
- "alias": " - marketing",
131
- "acc,none": 0.29914529914529914,
132
- "acc_stderr,none": 0.029996951858349483
133
- },
134
- "mmlu_medical_genetics": {
135
- "alias": " - medical_genetics",
136
- "acc,none": 0.22,
137
- "acc_stderr,none": 0.04163331998932269
138
- },
139
- "mmlu_miscellaneous": {
140
- "alias": " - miscellaneous",
141
- "acc,none": 0.23754789272030652,
142
- "acc_stderr,none": 0.015218733046150195
143
- },
144
- "mmlu_nutrition": {
145
- "alias": " - nutrition",
146
- "acc,none": 0.27124183006535946,
147
- "acc_stderr,none": 0.025457756696667864
148
- },
149
- "mmlu_professional_accounting": {
150
- "alias": " - professional_accounting",
151
- "acc,none": 0.25177304964539005,
152
- "acc_stderr,none": 0.025892151156709405
153
- },
154
- "mmlu_professional_medicine": {
155
- "alias": " - professional_medicine",
156
- "acc,none": 0.29044117647058826,
157
- "acc_stderr,none": 0.027576468622740526
158
- },
159
- "mmlu_virology": {
160
- "alias": " - virology",
161
- "acc,none": 0.2289156626506024,
162
- "acc_stderr,none": 0.03270745277352477
163
- },
164
- "mmlu_social_sciences": {
165
- "acc,none": 0.2577185570360741,
166
- "acc_stderr,none": 0.007892283265392744,
167
- "alias": " - social sciences"
168
- },
169
- "mmlu_econometrics": {
170
- "alias": " - econometrics",
171
- "acc,none": 0.2543859649122807,
172
- "acc_stderr,none": 0.040969851398436716
173
- },
174
- "mmlu_high_school_geography": {
175
- "alias": " - high_school_geography",
176
- "acc,none": 0.2727272727272727,
177
- "acc_stderr,none": 0.03173071239071724
178
- },
179
- "mmlu_high_school_government_and_politics": {
180
- "alias": " - high_school_government_and_politics",
181
- "acc,none": 0.27461139896373055,
182
- "acc_stderr,none": 0.03221024508041154
183
- },
184
- "mmlu_high_school_macroeconomics": {
185
- "alias": " - high_school_macroeconomics",
186
- "acc,none": 0.2512820512820513,
187
- "acc_stderr,none": 0.021992016662370564
188
- },
189
- "mmlu_high_school_microeconomics": {
190
- "alias": " - high_school_microeconomics",
191
- "acc,none": 0.2605042016806723,
192
- "acc_stderr,none": 0.028510251512341937
193
- },
194
- "mmlu_high_school_psychology": {
195
- "alias": " - high_school_psychology",
196
- "acc,none": 0.24403669724770644,
197
- "acc_stderr,none": 0.018415286351416413
198
- },
199
- "mmlu_human_sexuality": {
200
- "alias": " - human_sexuality",
201
- "acc,none": 0.26717557251908397,
202
- "acc_stderr,none": 0.038808483010823944
203
- },
204
- "mmlu_professional_psychology": {
205
- "alias": " - professional_psychology",
206
- "acc,none": 0.2696078431372549,
207
- "acc_stderr,none": 0.017952449196987862
208
- },
209
- "mmlu_public_relations": {
210
- "alias": " - public_relations",
211
- "acc,none": 0.22727272727272727,
212
- "acc_stderr,none": 0.04013964554072775
213
- },
214
- "mmlu_security_studies": {
215
- "alias": " - security_studies",
216
- "acc,none": 0.22448979591836735,
217
- "acc_stderr,none": 0.02671143055553841
218
- },
219
- "mmlu_sociology": {
220
- "alias": " - sociology",
221
- "acc,none": 0.3034825870646766,
222
- "acc_stderr,none": 0.032510068164586174
223
- },
224
- "mmlu_us_foreign_policy": {
225
- "alias": " - us_foreign_policy",
226
- "acc,none": 0.23,
227
- "acc_stderr,none": 0.04229525846816506
228
- },
229
- "mmlu_stem": {
230
- "acc,none": 0.260069774817634,
231
- "acc_stderr,none": 0.0078061861482534595,
232
- "alias": " - stem"
233
- },
234
- "mmlu_abstract_algebra": {
235
- "alias": " - abstract_algebra",
236
- "acc,none": 0.2,
237
- "acc_stderr,none": 0.04020151261036845
238
- },
239
- "mmlu_anatomy": {
240
- "alias": " - anatomy",
241
- "acc,none": 0.2074074074074074,
242
- "acc_stderr,none": 0.03502553170678318
243
- },
244
- "mmlu_astronomy": {
245
- "alias": " - astronomy",
246
- "acc,none": 0.27631578947368424,
247
- "acc_stderr,none": 0.03639057569952925
248
- },
249
- "mmlu_college_biology": {
250
- "alias": " - college_biology",
251
- "acc,none": 0.24305555555555555,
252
- "acc_stderr,none": 0.03586879280080342
253
- },
254
- "mmlu_college_chemistry": {
255
- "alias": " - college_chemistry",
256
- "acc,none": 0.35,
257
- "acc_stderr,none": 0.047937248544110196
258
- },
259
- "mmlu_college_computer_science": {
260
- "alias": " - college_computer_science",
261
- "acc,none": 0.29,
262
- "acc_stderr,none": 0.04560480215720684
263
- },
264
- "mmlu_college_mathematics": {
265
- "alias": " - college_mathematics",
266
- "acc,none": 0.26,
267
- "acc_stderr,none": 0.0440844002276808
268
- },
269
- "mmlu_college_physics": {
270
- "alias": " - college_physics",
271
- "acc,none": 0.3333333333333333,
272
- "acc_stderr,none": 0.04690650298201943
273
- },
274
- "mmlu_computer_security": {
275
- "alias": " - computer_security",
276
- "acc,none": 0.22,
277
- "acc_stderr,none": 0.04163331998932269
278
- },
279
- "mmlu_conceptual_physics": {
280
- "alias": " - conceptual_physics",
281
- "acc,none": 0.2170212765957447,
282
- "acc_stderr,none": 0.02694748312149622
283
- },
284
- "mmlu_electrical_engineering": {
285
- "alias": " - electrical_engineering",
286
- "acc,none": 0.19310344827586207,
287
- "acc_stderr,none": 0.032894455221274
288
- },
289
- "mmlu_elementary_mathematics": {
290
- "alias": " - elementary_mathematics",
291
- "acc,none": 0.2566137566137566,
292
- "acc_stderr,none": 0.022494510767503154
293
- },
294
- "mmlu_high_school_biology": {
295
- "alias": " - high_school_biology",
296
- "acc,none": 0.2870967741935484,
297
- "acc_stderr,none": 0.025736542745594525
298
- },
299
- "mmlu_high_school_chemistry": {
300
- "alias": " - high_school_chemistry",
301
- "acc,none": 0.2512315270935961,
302
- "acc_stderr,none": 0.030516530732694436
303
- },
304
- "mmlu_high_school_computer_science": {
305
- "alias": " - high_school_computer_science",
306
- "acc,none": 0.24,
307
- "acc_stderr,none": 0.04292346959909283
308
- },
309
- "mmlu_high_school_mathematics": {
310
- "alias": " - high_school_mathematics",
311
- "acc,none": 0.27037037037037037,
312
- "acc_stderr,none": 0.027080372815145658
313
- },
314
- "mmlu_high_school_physics": {
315
- "alias": " - high_school_physics",
316
- "acc,none": 0.2582781456953642,
317
- "acc_stderr,none": 0.035737053147634576
318
- },
319
- "mmlu_high_school_statistics": {
320
- "alias": " - high_school_statistics",
321
- "acc,none": 0.3194444444444444,
322
- "acc_stderr,none": 0.03179876342176851
323
- },
324
- "mmlu_machine_learning": {
325
- "alias": " - machine_learning",
326
- "acc,none": 0.25,
327
- "acc_stderr,none": 0.04109974682633932
328
- }
329
- }
330
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T19-03-10.026654_glue.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "glue"
5
- ],
6
- "num_fewshot": 5,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "cola": {
20
- "alias": "cola",
21
- "mcc,none": -0.08703457213373123,
22
- "mcc_stderr,none": 0.030163539085824434
23
- },
24
- "mnli": {
25
- "alias": "mnli",
26
- "acc,none": 0.3307182883341824,
27
- "acc_stderr,none": 0.0047490917271714875
28
- },
29
- "mnli_mismatch": {
30
- "alias": "mnli_mismatch",
31
- "acc,none": 0.3360455655004068,
32
- "acc_stderr,none": 0.004763973908606825
33
- },
34
- "mrpc": {
35
- "alias": "mrpc",
36
- "acc,none": 0.4019607843137255,
37
- "acc_stderr,none": 0.024302976642371528,
38
- "f1,none": 0.34759358288770054,
39
- "f1_stderr,none": 0.0313439979522004
40
- },
41
- "qnli": {
42
- "alias": "qnli",
43
- "acc,none": 0.4962474830679114,
44
- "acc_stderr,none": 0.006765220016415222
45
- },
46
- "qqp": {
47
- "alias": "qqp",
48
- "acc,none": 0.5283452881523621,
49
- "acc_stderr,none": 0.002482701510086862,
50
- "f1,none": 0.41103252308737687,
51
- "f1_stderr,none": 0.0034173131749060475
52
- },
53
- "rte": {
54
- "alias": "rte",
55
- "acc,none": 0.48736462093862815,
56
- "acc_stderr,none": 0.030086851767188564
57
- },
58
- "sst2": {
59
- "alias": "sst2",
60
- "acc,none": 0.6284403669724771,
61
- "acc_stderr,none": 0.016373337800737308
62
- },
63
- "wnli": {
64
- "alias": "wnli",
65
- "acc,none": 0.5774647887323944,
66
- "acc_stderr,none": 0.05903984205682581
67
- }
68
- }
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T19-04-32.038053_winogrande.json DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "winogrande"
5
- ],
6
- "num_fewshot": 5,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "winogrande": {
20
- "alias": "winogrande",
21
- "acc,none": 0.5374901341752171,
22
- "acc_stderr,none": 0.014012928183336573
23
- }
24
- }
25
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T19-09-54.775610_sciq.json DELETED
@@ -1,27 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "sciq"
5
- ],
6
- "num_fewshot": 5,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "sciq": {
20
- "alias": "sciq",
21
- "acc,none": 0.92,
22
- "acc_stderr,none": 0.00858333697775365,
23
- "acc_norm,none": 0.908,
24
- "acc_norm_stderr,none": 0.00914437639315114
25
- }
26
- }
27
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T19-31-43.872563_mmlu.json DELETED
@@ -1,330 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "mmlu"
5
- ],
6
- "num_fewshot": 5,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "mmlu": {
20
- "acc,none": 0.2547357926221336,
21
- "acc_stderr,none": 0.0036750666019376636,
22
- "alias": "mmlu"
23
- },
24
- "mmlu_humanities": {
25
- "acc,none": 0.2454835281615303,
26
- "acc_stderr,none": 0.006267346149858851,
27
- "alias": " - humanities"
28
- },
29
- "mmlu_formal_logic": {
30
- "alias": " - formal_logic",
31
- "acc,none": 0.3412698412698413,
32
- "acc_stderr,none": 0.04240799327574925
33
- },
34
- "mmlu_high_school_european_history": {
35
- "alias": " - high_school_european_history",
36
- "acc,none": 0.3151515151515151,
37
- "acc_stderr,none": 0.0362773057502241
38
- },
39
- "mmlu_high_school_us_history": {
40
- "alias": " - high_school_us_history",
41
- "acc,none": 0.24509803921568626,
42
- "acc_stderr,none": 0.03019028245350194
43
- },
44
- "mmlu_high_school_world_history": {
45
- "alias": " - high_school_world_history",
46
- "acc,none": 0.29535864978902954,
47
- "acc_stderr,none": 0.02969633871342286
48
- },
49
- "mmlu_international_law": {
50
- "alias": " - international_law",
51
- "acc,none": 0.2644628099173554,
52
- "acc_stderr,none": 0.04026187527591206
53
- },
54
- "mmlu_jurisprudence": {
55
- "alias": " - jurisprudence",
56
- "acc,none": 0.2222222222222222,
57
- "acc_stderr,none": 0.0401910747255735
58
- },
59
- "mmlu_logical_fallacies": {
60
- "alias": " - logical_fallacies",
61
- "acc,none": 0.24539877300613497,
62
- "acc_stderr,none": 0.03380939813943354
63
- },
64
- "mmlu_moral_disputes": {
65
- "alias": " - moral_disputes",
66
- "acc,none": 0.23410404624277456,
67
- "acc_stderr,none": 0.022797110278071128
68
- },
69
- "mmlu_moral_scenarios": {
70
- "alias": " - moral_scenarios",
71
- "acc,none": 0.2435754189944134,
72
- "acc_stderr,none": 0.014355911964767864
73
- },
74
- "mmlu_philosophy": {
75
- "alias": " - philosophy",
76
- "acc,none": 0.18006430868167203,
77
- "acc_stderr,none": 0.02182342285774495
78
- },
79
- "mmlu_prehistory": {
80
- "alias": " - prehistory",
81
- "acc,none": 0.21604938271604937,
82
- "acc_stderr,none": 0.022899162918445785
83
- },
84
- "mmlu_professional_law": {
85
- "alias": " - professional_law",
86
- "acc,none": 0.2470664928292047,
87
- "acc_stderr,none": 0.011015752255279338
88
- },
89
- "mmlu_world_religions": {
90
- "alias": " - world_religions",
91
- "acc,none": 0.23391812865497075,
92
- "acc_stderr,none": 0.03246721765117827
93
- },
94
- "mmlu_other": {
95
- "acc,none": 0.2603797875764403,
96
- "acc_stderr,none": 0.007871165717920162,
97
- "alias": " - other"
98
- },
99
- "mmlu_business_ethics": {
100
- "alias": " - business_ethics",
101
- "acc,none": 0.23,
102
- "acc_stderr,none": 0.04229525846816505
103
- },
104
- "mmlu_clinical_knowledge": {
105
- "alias": " - clinical_knowledge",
106
- "acc,none": 0.2830188679245283,
107
- "acc_stderr,none": 0.027724236492700904
108
- },
109
- "mmlu_college_medicine": {
110
- "alias": " - college_medicine",
111
- "acc,none": 0.24277456647398843,
112
- "acc_stderr,none": 0.0326926380614177
113
- },
114
- "mmlu_global_facts": {
115
- "alias": " - global_facts",
116
- "acc,none": 0.2,
117
- "acc_stderr,none": 0.04020151261036843
118
- },
119
- "mmlu_human_aging": {
120
- "alias": " - human_aging",
121
- "acc,none": 0.31390134529147984,
122
- "acc_stderr,none": 0.031146796482972465
123
- },
124
- "mmlu_management": {
125
- "alias": " - management",
126
- "acc,none": 0.2912621359223301,
127
- "acc_stderr,none": 0.04498676320572924
128
- },
129
- "mmlu_marketing": {
130
- "alias": " - marketing",
131
- "acc,none": 0.29914529914529914,
132
- "acc_stderr,none": 0.029996951858349483
133
- },
134
- "mmlu_medical_genetics": {
135
- "alias": " - medical_genetics",
136
- "acc,none": 0.22,
137
- "acc_stderr,none": 0.04163331998932269
138
- },
139
- "mmlu_miscellaneous": {
140
- "alias": " - miscellaneous",
141
- "acc,none": 0.23754789272030652,
142
- "acc_stderr,none": 0.015218733046150195
143
- },
144
- "mmlu_nutrition": {
145
- "alias": " - nutrition",
146
- "acc,none": 0.27124183006535946,
147
- "acc_stderr,none": 0.025457756696667864
148
- },
149
- "mmlu_professional_accounting": {
150
- "alias": " - professional_accounting",
151
- "acc,none": 0.25177304964539005,
152
- "acc_stderr,none": 0.025892151156709405
153
- },
154
- "mmlu_professional_medicine": {
155
- "alias": " - professional_medicine",
156
- "acc,none": 0.29044117647058826,
157
- "acc_stderr,none": 0.027576468622740526
158
- },
159
- "mmlu_virology": {
160
- "alias": " - virology",
161
- "acc,none": 0.2289156626506024,
162
- "acc_stderr,none": 0.03270745277352477
163
- },
164
- "mmlu_social_sciences": {
165
- "acc,none": 0.2577185570360741,
166
- "acc_stderr,none": 0.007892283265392744,
167
- "alias": " - social sciences"
168
- },
169
- "mmlu_econometrics": {
170
- "alias": " - econometrics",
171
- "acc,none": 0.2543859649122807,
172
- "acc_stderr,none": 0.040969851398436716
173
- },
174
- "mmlu_high_school_geography": {
175
- "alias": " - high_school_geography",
176
- "acc,none": 0.2727272727272727,
177
- "acc_stderr,none": 0.03173071239071724
178
- },
179
- "mmlu_high_school_government_and_politics": {
180
- "alias": " - high_school_government_and_politics",
181
- "acc,none": 0.27461139896373055,
182
- "acc_stderr,none": 0.03221024508041154
183
- },
184
- "mmlu_high_school_macroeconomics": {
185
- "alias": " - high_school_macroeconomics",
186
- "acc,none": 0.2512820512820513,
187
- "acc_stderr,none": 0.021992016662370564
188
- },
189
- "mmlu_high_school_microeconomics": {
190
- "alias": " - high_school_microeconomics",
191
- "acc,none": 0.2605042016806723,
192
- "acc_stderr,none": 0.028510251512341937
193
- },
194
- "mmlu_high_school_psychology": {
195
- "alias": " - high_school_psychology",
196
- "acc,none": 0.24403669724770644,
197
- "acc_stderr,none": 0.018415286351416413
198
- },
199
- "mmlu_human_sexuality": {
200
- "alias": " - human_sexuality",
201
- "acc,none": 0.26717557251908397,
202
- "acc_stderr,none": 0.038808483010823944
203
- },
204
- "mmlu_professional_psychology": {
205
- "alias": " - professional_psychology",
206
- "acc,none": 0.2696078431372549,
207
- "acc_stderr,none": 0.017952449196987862
208
- },
209
- "mmlu_public_relations": {
210
- "alias": " - public_relations",
211
- "acc,none": 0.22727272727272727,
212
- "acc_stderr,none": 0.04013964554072775
213
- },
214
- "mmlu_security_studies": {
215
- "alias": " - security_studies",
216
- "acc,none": 0.22448979591836735,
217
- "acc_stderr,none": 0.02671143055553841
218
- },
219
- "mmlu_sociology": {
220
- "alias": " - sociology",
221
- "acc,none": 0.3034825870646766,
222
- "acc_stderr,none": 0.032510068164586174
223
- },
224
- "mmlu_us_foreign_policy": {
225
- "alias": " - us_foreign_policy",
226
- "acc,none": 0.23,
227
- "acc_stderr,none": 0.04229525846816506
228
- },
229
- "mmlu_stem": {
230
- "acc,none": 0.260069774817634,
231
- "acc_stderr,none": 0.0078061861482534595,
232
- "alias": " - stem"
233
- },
234
- "mmlu_abstract_algebra": {
235
- "alias": " - abstract_algebra",
236
- "acc,none": 0.2,
237
- "acc_stderr,none": 0.04020151261036845
238
- },
239
- "mmlu_anatomy": {
240
- "alias": " - anatomy",
241
- "acc,none": 0.2074074074074074,
242
- "acc_stderr,none": 0.03502553170678318
243
- },
244
- "mmlu_astronomy": {
245
- "alias": " - astronomy",
246
- "acc,none": 0.27631578947368424,
247
- "acc_stderr,none": 0.03639057569952925
248
- },
249
- "mmlu_college_biology": {
250
- "alias": " - college_biology",
251
- "acc,none": 0.24305555555555555,
252
- "acc_stderr,none": 0.03586879280080342
253
- },
254
- "mmlu_college_chemistry": {
255
- "alias": " - college_chemistry",
256
- "acc,none": 0.35,
257
- "acc_stderr,none": 0.047937248544110196
258
- },
259
- "mmlu_college_computer_science": {
260
- "alias": " - college_computer_science",
261
- "acc,none": 0.29,
262
- "acc_stderr,none": 0.04560480215720684
263
- },
264
- "mmlu_college_mathematics": {
265
- "alias": " - college_mathematics",
266
- "acc,none": 0.26,
267
- "acc_stderr,none": 0.0440844002276808
268
- },
269
- "mmlu_college_physics": {
270
- "alias": " - college_physics",
271
- "acc,none": 0.3333333333333333,
272
- "acc_stderr,none": 0.04690650298201943
273
- },
274
- "mmlu_computer_security": {
275
- "alias": " - computer_security",
276
- "acc,none": 0.22,
277
- "acc_stderr,none": 0.04163331998932269
278
- },
279
- "mmlu_conceptual_physics": {
280
- "alias": " - conceptual_physics",
281
- "acc,none": 0.2170212765957447,
282
- "acc_stderr,none": 0.02694748312149622
283
- },
284
- "mmlu_electrical_engineering": {
285
- "alias": " - electrical_engineering",
286
- "acc,none": 0.19310344827586207,
287
- "acc_stderr,none": 0.032894455221274
288
- },
289
- "mmlu_elementary_mathematics": {
290
- "alias": " - elementary_mathematics",
291
- "acc,none": 0.2566137566137566,
292
- "acc_stderr,none": 0.022494510767503154
293
- },
294
- "mmlu_high_school_biology": {
295
- "alias": " - high_school_biology",
296
- "acc,none": 0.2870967741935484,
297
- "acc_stderr,none": 0.025736542745594525
298
- },
299
- "mmlu_high_school_chemistry": {
300
- "alias": " - high_school_chemistry",
301
- "acc,none": 0.2512315270935961,
302
- "acc_stderr,none": 0.030516530732694436
303
- },
304
- "mmlu_high_school_computer_science": {
305
- "alias": " - high_school_computer_science",
306
- "acc,none": 0.24,
307
- "acc_stderr,none": 0.04292346959909283
308
- },
309
- "mmlu_high_school_mathematics": {
310
- "alias": " - high_school_mathematics",
311
- "acc,none": 0.27037037037037037,
312
- "acc_stderr,none": 0.027080372815145658
313
- },
314
- "mmlu_high_school_physics": {
315
- "alias": " - high_school_physics",
316
- "acc,none": 0.2582781456953642,
317
- "acc_stderr,none": 0.035737053147634576
318
- },
319
- "mmlu_high_school_statistics": {
320
- "alias": " - high_school_statistics",
321
- "acc,none": 0.3194444444444444,
322
- "acc_stderr,none": 0.03179876342176851
323
- },
324
- "mmlu_machine_learning": {
325
- "alias": " - machine_learning",
326
- "acc,none": 0.25,
327
- "acc_stderr,none": 0.04109974682633932
328
- }
329
- }
330
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T20-07-36.031022_lambada_multilingual.json DELETED
@@ -1,55 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "lambada_multilingual"
5
- ],
6
- "num_fewshot": 5,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "lambada_openai_mt_de": {
20
- "alias": "lambada_openai_mt_de",
21
- "perplexity,none": 267.28408723088717,
22
- "perplexity_stderr,none": 16.35740283931253,
23
- "acc,none": 0.20958664855424025,
24
- "acc_stderr,none": 0.005670495539426846
25
- },
26
- "lambada_openai_mt_en": {
27
- "alias": "lambada_openai_mt_en",
28
- "perplexity,none": 21.37572561784123,
29
- "perplexity_stderr,none": 0.6808300296181946,
30
- "acc,none": 0.38676499126722297,
31
- "acc_stderr,none": 0.006784988579985175
32
- },
33
- "lambada_openai_mt_es": {
34
- "alias": "lambada_openai_mt_es",
35
- "perplexity,none": 370.8411076274339,
36
- "perplexity_stderr,none": 21.595221630946366,
37
- "acc,none": 0.21424412963322337,
38
- "acc_stderr,none": 0.005716238694447705
39
- },
40
- "lambada_openai_mt_fr": {
41
- "alias": "lambada_openai_mt_fr",
42
- "perplexity,none": 196.3477203013756,
43
- "perplexity_stderr,none": 11.305248298408568,
44
- "acc,none": 0.2450999417814865,
45
- "acc_stderr,none": 0.005992780988422183
46
- },
47
- "lambada_openai_mt_it": {
48
- "alias": "lambada_openai_mt_it",
49
- "perplexity,none": 323.19218684985276,
50
- "perplexity_stderr,none": 20.29110209885659,
51
- "acc,none": 0.2109450805356103,
52
- "acc_stderr,none": 0.005683951840704777
53
- }
54
- }
55
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T20-24-29.617348_pawsx.json DELETED
@@ -1,60 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "pawsx"
5
- ],
6
- "num_fewshot": 5,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "pawsx": {
20
- "acc,none": 0.46485714285714286,
21
- "acc_stderr,none": 0.004213340523157351,
22
- "alias": "pawsx"
23
- },
24
- "paws_de": {
25
- "alias": " - paws_de",
26
- "acc,none": 0.4565,
27
- "acc_stderr,none": 0.011140733053371418
28
- },
29
- "paws_en": {
30
- "alias": " - paws_en",
31
- "acc,none": 0.48,
32
- "acc_stderr,none": 0.011174185930778313
33
- },
34
- "paws_es": {
35
- "alias": " - paws_es",
36
- "acc,none": 0.503,
37
- "acc_stderr,none": 0.011182934722804556
38
- },
39
- "paws_fr": {
40
- "alias": " - paws_fr",
41
- "acc,none": 0.467,
42
- "acc_stderr,none": 0.011158752568250661
43
- },
44
- "paws_ja": {
45
- "alias": " - paws_ja",
46
- "acc,none": 0.448,
47
- "acc_stderr,none": 0.01112249319745629
48
- },
49
- "paws_ko": {
50
- "alias": " - paws_ko",
51
- "acc,none": 0.4515,
52
- "acc_stderr,none": 0.011130400617630763
53
- },
54
- "paws_zh": {
55
- "alias": " - paws_zh",
56
- "acc,none": 0.448,
57
- "acc_stderr,none": 0.01112249319745629
58
- }
59
- }
60
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_261/0.4.8_2025-03-15T20-29-15.015293_xcopa.json DELETED
@@ -1,80 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "xcopa"
5
- ],
6
- "num_fewshot": 5,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [
12
- 261
13
- ],
14
- "stop_token_ids": [
15
- 11,
16
- 261
17
- ],
18
- "results": {
19
- "xcopa": {
20
- "acc,none": 0.5294545454545454,
21
- "acc_stderr,none": 0.00673238666638665,
22
- "alias": "xcopa"
23
- },
24
- "xcopa_et": {
25
- "alias": " - xcopa_et",
26
- "acc,none": 0.496,
27
- "acc_stderr,none": 0.02238235778196214
28
- },
29
- "xcopa_ht": {
30
- "alias": " - xcopa_ht",
31
- "acc,none": 0.528,
32
- "acc_stderr,none": 0.02234794983266809
33
- },
34
- "xcopa_id": {
35
- "alias": " - xcopa_id",
36
- "acc,none": 0.546,
37
- "acc_stderr,none": 0.02228814759117695
38
- },
39
- "xcopa_it": {
40
- "alias": " - xcopa_it",
41
- "acc,none": 0.526,
42
- "acc_stderr,none": 0.02235279165091416
43
- },
44
- "xcopa_qu": {
45
- "alias": " - xcopa_qu",
46
- "acc,none": 0.5,
47
- "acc_stderr,none": 0.022383074051792257
48
- },
49
- "xcopa_sw": {
50
- "alias": " - xcopa_sw",
51
- "acc,none": 0.528,
52
- "acc_stderr,none": 0.022347949832668093
53
- },
54
- "xcopa_ta": {
55
- "alias": " - xcopa_ta",
56
- "acc,none": 0.532,
57
- "acc_stderr,none": 0.0223371864790443
58
- },
59
- "xcopa_th": {
60
- "alias": " - xcopa_th",
61
- "acc,none": 0.566,
62
- "acc_stderr,none": 0.02218721580302901
63
- },
64
- "xcopa_tr": {
65
- "alias": " - xcopa_tr",
66
- "acc,none": 0.526,
67
- "acc_stderr,none": 0.022352791650914167
68
- },
69
- "xcopa_vi": {
70
- "alias": " - xcopa_vi",
71
- "acc,none": 0.538,
72
- "acc_stderr,none": 0.022318338119870527
73
- },
74
- "xcopa_zh": {
75
- "alias": " - xcopa_zh",
76
- "acc,none": 0.538,
77
- "acc_stderr,none": 0.02231833811987053
78
- }
79
- }
80
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
lm_evals/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096/pad_none/0.4.8_2025-03-14T11-51-55.842699_lambada_openai.json DELETED
@@ -1,25 +0,0 @@
1
- {
2
- "model": "/models/RWKV-x070-World-0.1B-v2.8-20241210-ctx4096",
3
- "tasks": [
4
- "lambada_openai"
5
- ],
6
- "num_fewshot": 0,
7
- "lm_eval_version": "0.4.8",
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "custom_prefix_token_id": null,
11
- "pad_token_ids": [],
12
- "stop_token_ids": [
13
- 11,
14
- 261
15
- ],
16
- "results": {
17
- "lambada_openai": {
18
- "alias": "lambada_openai",
19
- "perplexity,none": 14.00703003680488,
20
- "perplexity_stderr,none": 0.4392984349795351,
21
- "acc,none": 0.4737046380749078,
22
- "acc_stderr,none": 0.006956337791536673
23
- }
24
- }
25
- }