Hugging Face's logo

datablations
/
lm1-4b2-84b-oscar-repetitions

Model card Files Community
Muennighoff commited on
Commit
173afca
•
1 Parent(s): 32baaa6

Add

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. 4b284b12boscar/evaluation/4b284b12boscar_0_babi.json +22 -0
  2. 4b284b12boscar/evaluation/4b284b12boscar_1_babi.json +22 -0
  3. 4b284b12boscar/evaluation/4b284b12boscar_2_babi.json +22 -0
  4. 4b284b12boscar/evaluation/4b284b12boscar_3_babi.json +22 -0
  5. 4b284b12boscar/evaluation/4b284b12boscar_4_babi.json +22 -0
  6. 4b284b12boscar/evaluation/4b284b12boscar_5_babi.json +22 -0
  7. 4b284b12boscar/transformers/merges.txt +0 -0
  8. 4b284b12boscar/transformers/tokenizer.json +0 -0
  9. 4b284b12boscar/transformers/vocab.json +3 -0
  10. 4b284b17boscar/evaluation/4b284b17boscar_0_babi.json +22 -0
  11. 4b284b17boscar/evaluation/4b284b17boscar_1_babi.json +22 -0
  12. 4b284b17boscar/evaluation/4b284b17boscar_2_babi.json +22 -0
  13. 4b284b17boscar/evaluation/4b284b17boscar_3_babi.json +22 -0
  14. 4b284b17boscar/evaluation/4b284b17boscar_4_babi.json +22 -0
  15. 4b284b17boscar/evaluation/4b284b17boscar_5_babi.json +22 -0
  16. 4b284b17boscar/transformers/merges.txt +0 -0
  17. 4b284b17boscar/transformers/tokenizer.json +0 -0
  18. 4b284b17boscar/transformers/vocab.json +3 -0
  19. 4b284b1b9oscar/evaluation/4b284b1b9oscar_0_babi.json +22 -0
  20. 4b284b1b9oscar/evaluation/4b284b1b9oscar_1_babi.json +22 -0
  21. 4b284b1b9oscar/evaluation/4b284b1b9oscar_2_babi.json +22 -0
  22. 4b284b1b9oscar/evaluation/4b284b1b9oscar_3_babi.json +22 -0
  23. 4b284b1b9oscar/evaluation/4b284b1b9oscar_4_babi.json +22 -0
  24. 4b284b1b9oscar/evaluation/4b284b1b9oscar_5_babi.json +22 -0
  25. 4b284b1b9oscar/transformers/merges.txt +0 -0
  26. 4b284b1b9oscar/transformers/tokenizer.json +0 -0
  27. 4b284b1b9oscar/transformers/vocab.json +3 -0
  28. 4b284b21boscar/evaluation/4b284b21boscar_0_babi.json +22 -0
  29. 4b284b21boscar/evaluation/4b284b21boscar_1_babi.json +22 -0
  30. 4b284b21boscar/evaluation/4b284b21boscar_2_babi.json +22 -0
  31. 4b284b21boscar/evaluation/4b284b21boscar_3_babi.json +22 -0
  32. 4b284b21boscar/evaluation/4b284b21boscar_4_babi.json +22 -0
  33. 4b284b21boscar/evaluation/4b284b21boscar_5_babi.json +22 -0
  34. 4b284b21boscar/transformers/merges.txt +0 -0
  35. 4b284b21boscar/transformers/tokenizer.json +0 -0
  36. 4b284b21boscar/transformers/vocab.json +3 -0
  37. 4b284b28boscar/evaluation/4b284b28boscar_0_babi.json +22 -0
  38. 4b284b28boscar/evaluation/4b284b28boscar_1_babi.json +22 -0
  39. 4b284b28boscar/evaluation/4b284b28boscar_2_babi.json +22 -0
  40. 4b284b28boscar/evaluation/4b284b28boscar_3_babi.json +22 -0
  41. 4b284b28boscar/evaluation/4b284b28boscar_4_babi.json +22 -0
  42. 4b284b28boscar/evaluation/4b284b28boscar_5_babi.json +22 -0
  43. 4b284b28boscar/transformers/merges.txt +0 -0
  44. 4b284b28boscar/transformers/tokenizer.json +0 -0
  45. 4b284b28boscar/transformers/vocab.json +3 -0
  46. 4b284b42boscar/evaluation/4b284b42boscar_0_babi.json +22 -0
  47. 4b284b42boscar/evaluation/4b284b42boscar_1_babi.json +22 -0
  48. 4b284b42boscar/evaluation/4b284b42boscar_2_babi.json +22 -0
  49. 4b284b42boscar/evaluation/4b284b42boscar_3_babi.json +22 -0
  50. 4b284b42boscar/evaluation/4b284b42boscar_4_babi.json +22 -0
4b284b12boscar/evaluation/4b284b12boscar_0_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.0,
5
+ "em_stderr": 0.0
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b12boscar/transformers",
14
+ "num_fewshot": 0,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b12boscar/evaluation/4b284b12boscar_1_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.09,
5
+ "em_stderr": 0.005225811232176943
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b12boscar/transformers",
14
+ "num_fewshot": 1,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b12boscar/evaluation/4b284b12boscar_2_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.17733333333333334,
5
+ "em_stderr": 0.006974593588588595
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b12boscar/transformers",
14
+ "num_fewshot": 2,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b12boscar/evaluation/4b284b12boscar_3_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.238,
5
+ "em_stderr": 0.00777638459605728
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b12boscar/transformers",
14
+ "num_fewshot": 3,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b12boscar/evaluation/4b284b12boscar_4_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.284,
5
+ "em_stderr": 0.008234314461136287
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b12boscar/transformers",
14
+ "num_fewshot": 4,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b12boscar/evaluation/4b284b12boscar_5_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.2956666666666667,
5
+ "em_stderr": 0.008333013220482667
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b12boscar/transformers",
14
+ "num_fewshot": 5,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b12boscar/transformers/merges.txt ADDED
File without changes
4b284b12boscar/transformers/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
4b284b12boscar/transformers/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196139668be63f3b5d6574427317ae82f612a97c5d1cdaf36ed2256dbf636783
3
+ size 1042301
4b284b17boscar/evaluation/4b284b17boscar_0_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.0,
5
+ "em_stderr": 0.0
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b17boscar/transformers",
14
+ "num_fewshot": 0,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b17boscar/evaluation/4b284b17boscar_1_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.10533333333333333,
5
+ "em_stderr": 0.005605641367924676
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b17boscar/transformers",
14
+ "num_fewshot": 1,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b17boscar/evaluation/4b284b17boscar_2_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.19666666666666666,
5
+ "em_stderr": 0.007258134962739362
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b17boscar/transformers",
14
+ "num_fewshot": 2,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b17boscar/evaluation/4b284b17boscar_3_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.26066666666666666,
5
+ "em_stderr": 0.008016312885357247
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b17boscar/transformers",
14
+ "num_fewshot": 3,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b17boscar/evaluation/4b284b17boscar_4_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.2886666666666667,
5
+ "em_stderr": 0.008274593466736098
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b17boscar/transformers",
14
+ "num_fewshot": 4,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b17boscar/evaluation/4b284b17boscar_5_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.2976666666666667,
5
+ "em_stderr": 0.008349270078537127
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b17boscar/transformers",
14
+ "num_fewshot": 5,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b17boscar/transformers/merges.txt ADDED
File without changes
4b284b17boscar/transformers/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
4b284b17boscar/transformers/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196139668be63f3b5d6574427317ae82f612a97c5d1cdaf36ed2256dbf636783
3
+ size 1042301
4b284b1b9oscar/evaluation/4b284b1b9oscar_0_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.0,
5
+ "em_stderr": 0.0
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b1b9oscar/transformers",
14
+ "num_fewshot": 0,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b1b9oscar/evaluation/4b284b1b9oscar_1_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.063,
5
+ "em_stderr": 0.004436615961187437
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b1b9oscar/transformers",
14
+ "num_fewshot": 1,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b1b9oscar/evaluation/4b284b1b9oscar_2_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.109,
5
+ "em_stderr": 0.005690676110814835
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b1b9oscar/transformers",
14
+ "num_fewshot": 2,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b1b9oscar/evaluation/4b284b1b9oscar_3_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.15,
5
+ "em_stderr": 0.0065202892106456705
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b1b9oscar/transformers",
14
+ "num_fewshot": 3,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b1b9oscar/evaluation/4b284b1b9oscar_4_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.17433333333333334,
5
+ "em_stderr": 0.006927943865929851
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b1b9oscar/transformers",
14
+ "num_fewshot": 4,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b1b9oscar/evaluation/4b284b1b9oscar_5_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.17066666666666666,
5
+ "em_stderr": 0.006869904199702395
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b1b9oscar/transformers",
14
+ "num_fewshot": 5,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b1b9oscar/transformers/merges.txt ADDED
File without changes
4b284b1b9oscar/transformers/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
4b284b1b9oscar/transformers/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196139668be63f3b5d6574427317ae82f612a97c5d1cdaf36ed2256dbf636783
3
+ size 1042301
4b284b21boscar/evaluation/4b284b21boscar_0_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.0,
5
+ "em_stderr": 0.0
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b21boscar/transformers",
14
+ "num_fewshot": 0,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b21boscar/evaluation/4b284b21boscar_1_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.07733333333333334,
5
+ "em_stderr": 0.004877727651134611
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b21boscar/transformers",
14
+ "num_fewshot": 1,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b21boscar/evaluation/4b284b21boscar_2_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.17133333333333334,
5
+ "em_stderr": 0.00688054174410001
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b21boscar/transformers",
14
+ "num_fewshot": 2,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b21boscar/evaluation/4b284b21boscar_3_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.23266666666666666,
5
+ "em_stderr": 0.0077156209448852224
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b21boscar/transformers",
14
+ "num_fewshot": 3,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b21boscar/evaluation/4b284b21boscar_4_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.2816666666666667,
5
+ "em_stderr": 0.00821376936537552
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b21boscar/transformers",
14
+ "num_fewshot": 4,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b21boscar/evaluation/4b284b21boscar_5_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.29933333333333334,
5
+ "em_stderr": 0.008362671486299168
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b21boscar/transformers",
14
+ "num_fewshot": 5,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b21boscar/transformers/merges.txt ADDED
File without changes
4b284b21boscar/transformers/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
4b284b21boscar/transformers/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196139668be63f3b5d6574427317ae82f612a97c5d1cdaf36ed2256dbf636783
3
+ size 1042301
4b284b28boscar/evaluation/4b284b28boscar_0_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.0,
5
+ "em_stderr": 0.0
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b28boscar/transformers",
14
+ "num_fewshot": 0,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b28boscar/evaluation/4b284b28boscar_1_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.101,
5
+ "em_stderr": 0.005502401791504982
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b28boscar/transformers",
14
+ "num_fewshot": 1,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b28boscar/evaluation/4b284b28boscar_2_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.215,
5
+ "em_stderr": 0.007501805940179963
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b28boscar/transformers",
14
+ "num_fewshot": 2,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b28boscar/evaluation/4b284b28boscar_3_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.26966666666666667,
5
+ "em_stderr": 0.008103748644869114
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b28boscar/transformers",
14
+ "num_fewshot": 3,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b28boscar/evaluation/4b284b28boscar_4_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.307,
5
+ "em_stderr": 0.008422627077242112
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b28boscar/transformers",
14
+ "num_fewshot": 4,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b28boscar/evaluation/4b284b28boscar_5_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.31166666666666665,
5
+ "em_stderr": 0.008457779251186945
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b28boscar/transformers",
14
+ "num_fewshot": 5,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b28boscar/transformers/merges.txt ADDED
File without changes
4b284b28boscar/transformers/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
4b284b28boscar/transformers/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:196139668be63f3b5d6574427317ae82f612a97c5d1cdaf36ed2256dbf636783
3
+ size 1042301
4b284b42boscar/evaluation/4b284b42boscar_0_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.0,
5
+ "em_stderr": 0.0
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b42boscar/transformers",
14
+ "num_fewshot": 0,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b42boscar/evaluation/4b284b42boscar_1_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.09566666666666666,
5
+ "em_stderr": 0.005371014905852756
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b42boscar/transformers",
14
+ "num_fewshot": 1,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b42boscar/evaluation/4b284b42boscar_2_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.183,
5
+ "em_stderr": 0.007060709445418449
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b42boscar/transformers",
14
+ "num_fewshot": 2,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b42boscar/evaluation/4b284b42boscar_3_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.231,
5
+ "em_stderr": 0.007696281196011626
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b42boscar/transformers",
14
+ "num_fewshot": 3,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }
4b284b42boscar/evaluation/4b284b42boscar_4_babi.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "babi": {
4
+ "em": 0.274,
5
+ "em_stderr": 0.008144329931718155
6
+ }
7
+ },
8
+ "versions": {
9
+ "babi": 0
10
+ },
11
+ "config": {
12
+ "model": "gpt2",
13
+ "model_args": "pretrained=/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/lm1-4b2-84b-oscar-repetitions/4b284b42boscar/transformers",
14
+ "num_fewshot": 4,
15
+ "batch_size": null,
16
+ "device": null,
17
+ "no_cache": true,
18
+ "limit": 3000,
19
+ "bootstrap_iters": 100000,
20
+ "description_dict": {}
21
+ }
22
+ }