Commit
·
a9c8f45
1
Parent(s):
21871cb
Add res
Browse files- 4b284b84boscarv2seed3/evaluation/4b284b84boscarv2seed3_5_babi.json +22 -0
- 4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_0_babi.json +22 -0
- 4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_1_babi.json +22 -0
- 4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_2_babi.json +22 -0
- 4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_3_babi.json +22 -0
- 4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_4_babi.json +22 -0
- 4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_5_babi.json +22 -0
4b284b84boscarv2seed3/evaluation/4b284b84boscarv2seed3_5_babi.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"results": {
|
| 3 |
+
"babi": {
|
| 4 |
+
"em": 0.307,
|
| 5 |
+
"em_stderr": 0.00842262707724211
|
| 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-oscarseeds/4b284b84boscarv2seed3/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 |
+
}
|
4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_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-oscarseeds/4b284b84boscarv2seed4/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 |
+
}
|
4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_1_babi.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"results": {
|
| 3 |
+
"babi": {
|
| 4 |
+
"em": 0.07866666666666666,
|
| 5 |
+
"em_stderr": 0.004916041418507626
|
| 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-oscarseeds/4b284b84boscarv2seed4/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 |
+
}
|
4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_2_babi.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"results": {
|
| 3 |
+
"babi": {
|
| 4 |
+
"em": 0.176,
|
| 5 |
+
"em_stderr": 0.0069539522923415835
|
| 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-oscarseeds/4b284b84boscarv2seed4/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 |
+
}
|
4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_3_babi.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"results": {
|
| 3 |
+
"babi": {
|
| 4 |
+
"em": 0.24133333333333334,
|
| 5 |
+
"em_stderr": 0.007813505539008652
|
| 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-oscarseeds/4b284b84boscarv2seed4/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 |
+
}
|
4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_4_babi.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"results": {
|
| 3 |
+
"babi": {
|
| 4 |
+
"em": 0.2753333333333333,
|
| 5 |
+
"em_stderr": 0.008156621428058716
|
| 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-oscarseeds/4b284b84boscarv2seed4/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 |
+
}
|
4b284b84boscarv2seed4/evaluation/4b284b84boscarv2seed4_5_babi.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"results": {
|
| 3 |
+
"babi": {
|
| 4 |
+
"em": 0.29233333333333333,
|
| 5 |
+
"em_stderr": 0.008305490889254601
|
| 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-oscarseeds/4b284b84boscarv2seed4/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 |
+
}
|