Hugging Face's logo

Spaces:
BramVanroy
/
open_dutch_llm_leaderboard
Running

App Files Community
2
Bram Vanroy commited on
Commit
6087d40
•
1 Parent(s): 559e4ba

remove hellaswag

Browse files

following this bug https://github.com/laiviet/lm-evaluation-harness/issues/3. Will re-test with corrected 10-shot.

Files changed (7) hide show
  1. evals/hellaswag/hellaswag_nl_Llama-2-7b-chat-hf.json +0 -23
  2. evals/hellaswag/hellaswag_nl_Llama-2-7b-hf.json +0 -23
  3. evals/hellaswag/hellaswag_nl_Mistral-7B-v0.1.json +0 -23
  4. evals/hellaswag/hellaswag_nl_Orca-2-7b.json +0 -23
  5. evals/hellaswag/hellaswag_nl_gpt2-large-dutch.json +0 -23
  6. evals/hellaswag/hellaswag_nl_gpt2-medium-dutch.json +0 -23
  7. evals/hellaswag/hellaswag_nl_neural-chat-7b-v3-1.json +0 -23
evals/hellaswag/hellaswag_nl_Llama-2-7b-chat-hf.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "results": {
3
- "hellaswag_nl": {
4
- "acc": 0.3838100377765785,
5
- "acc_stderr": 0.005052614927289456,
6
- "acc_norm": 0.4819212088505127,
7
- "acc_norm_stderr": 0.005191425828002782
8
- }
9
- },
10
- "versions": {
11
- "hellaswag_nl": 1
12
- },
13
- "config": {
14
- "model": "hf-auto",
15
- "model_args": "pretrained=meta-llama/Llama-2-7b-chat-hf,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
16
- "batch_size": "auto",
17
- "device": "cuda",
18
- "no_cache": false,
19
- "limit": null,
20
- "bootstrap_iters": 100000,
21
- "description_dict": {}
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evals/hellaswag/hellaswag_nl_Llama-2-7b-hf.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "results": {
3
- "hellaswag_nl": {
4
- "acc": 0.386184565569347,
5
- "acc_stderr": 0.00505844561828187,
6
- "acc_norm": 0.4957366432811657,
7
- "acc_norm_stderr": 0.0051946338704556266
8
- }
9
- },
10
- "versions": {
11
- "hellaswag_nl": 1
12
- },
13
- "config": {
14
- "model": "hf-auto",
15
- "model_args": "pretrained=meta-llama/Llama-2-7b-hf,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
16
- "batch_size": "auto",
17
- "device": "cuda",
18
- "no_cache": false,
19
- "limit": null,
20
- "bootstrap_iters": 100000,
21
- "description_dict": {}
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evals/hellaswag/hellaswag_nl_Mistral-7B-v0.1.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "results": {
3
- "hellaswag_nl": {
4
- "acc": 0.4336751214247167,
5
- "acc_stderr": 0.0051489159372014965,
6
- "acc_norm": 0.5662169454937939,
7
- "acc_norm_stderr": 0.005149065890785751
8
- }
9
- },
10
- "versions": {
11
- "hellaswag_nl": 1
12
- },
13
- "config": {
14
- "model": "hf-auto",
15
- "model_args": "pretrained=mistralai/Mistral-7B-v0.1,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
16
- "batch_size": "auto",
17
- "device": "cuda",
18
- "no_cache": false,
19
- "limit": null,
20
- "bootstrap_iters": 100000,
21
- "description_dict": {}
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evals/hellaswag/hellaswag_nl_Orca-2-7b.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "results": {
3
- "hellaswag_nl": {
4
- "acc": 0.38456556934700487,
5
- "acc_stderr": 0.005054483938257531,
6
- "acc_norm": 0.48041014570966,
7
- "acc_norm_stderr": 0.005190834031799853
8
- }
9
- },
10
- "versions": {
11
- "hellaswag_nl": 1
12
- },
13
- "config": {
14
- "model": "hf-auto",
15
- "model_args": "pretrained=microsoft/Orca-2-7b,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
16
- "batch_size": "auto",
17
- "device": "cuda",
18
- "no_cache": false,
19
- "limit": null,
20
- "bootstrap_iters": 100000,
21
- "description_dict": {}
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evals/hellaswag/hellaswag_nl_gpt2-large-dutch.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "results": {
3
- "hellaswag_nl": {
4
- "acc": 0.3043712898003238,
5
- "acc_stderr": 0.004780698091128437,
6
- "acc_norm": 0.34279546681057743,
7
- "acc_norm_stderr": 0.004931380767300367
8
- }
9
- },
10
- "versions": {
11
- "hellaswag_nl": 1
12
- },
13
- "config": {
14
- "model": "hf-auto",
15
- "model_args": "pretrained=yhavinga/gpt2-large-dutch,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
16
- "batch_size": "auto",
17
- "device": "cuda",
18
- "no_cache": false,
19
- "limit": null,
20
- "bootstrap_iters": 100000,
21
- "description_dict": {}
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evals/hellaswag/hellaswag_nl_gpt2-medium-dutch.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "results": {
3
- "hellaswag_nl": {
4
- "acc": 0.31246627091203455,
5
- "acc_stderr": 0.004815587775923881,
6
- "acc_norm": 0.36438208310847275,
7
- "acc_norm_stderr": 0.00500008398696681
8
- }
9
- },
10
- "versions": {
11
- "hellaswag_nl": 1
12
- },
13
- "config": {
14
- "model": "hf-auto",
15
- "model_args": "pretrained=yhavinga/gpt2-medium-dutch,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
16
- "batch_size": "auto",
17
- "device": "cuda",
18
- "no_cache": false,
19
- "limit": null,
20
- "bootstrap_iters": 100000,
21
- "description_dict": {}
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
evals/hellaswag/hellaswag_nl_neural-chat-7b-v3-1.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "results": {
3
- "hellaswag_nl": {
4
- "acc": 0.44069077172153265,
5
- "acc_stderr": 0.0051581467942195215,
6
- "acc_norm": 0.5429033998920669,
7
- "acc_norm_stderr": 0.005175663147811796
8
- }
9
- },
10
- "versions": {
11
- "hellaswag_nl": 1
12
- },
13
- "config": {
14
- "model": "hf-auto",
15
- "model_args": "pretrained=Intel/neural-chat-7b-v3-1,use_accelerate=True,device_map_option=auto,dtype=bfloat16,load_in_8bit=True",
16
- "batch_size": "auto",
17
- "device": "cuda",
18
- "no_cache": false,
19
- "limit": null,
20
- "bootstrap_iters": 100000,
21
- "description_dict": {}
22
- }
23
- }