ScarletAce commited on
Commit
26d4600
1 Parent(s): e6d5ebe

Upload folder using huggingface_hub

Browse files
boolq,piqa,hellaswag,winogrande,arc_easy,arc_challenge,openbookqa_FP16.log ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
2
+ |-------------|------:|------|-----:|--------|-----:|---|-----:|
3
+ |openbookqa | 1|none | 0|acc |0.3180|± |0.0208|
4
+ | | |none | 0|acc_norm|0.4420|± |0.0222|
5
+ |arc_challenge| 1|none | 0|acc |0.4522|± |0.0145|
6
+ | | |none | 0|acc_norm|0.4684|± |0.0146|
7
+ |arc_easy | 1|none | 0|acc |0.7668|± |0.0087|
8
+ | | |none | 0|acc_norm|0.7538|± |0.0088|
9
+ |winogrande | 1|none | 0|acc |0.6985|± |0.0129|
10
+ |hellaswag | 1|none | 0|acc |0.5780|± |0.0049|
11
+ | | |none | 0|acc_norm|0.7669|± |0.0042|
12
+ |piqa | 1|none | 0|acc |0.7807|± |0.0097|
13
+ | | |none | 0|acc_norm|0.7938|± |0.0094|
14
+ |boolq | 2|none | 0|acc |0.7774|± |0.0073|
boolq,piqa,hellaswag,winogrande,arc_easy,arc_challenge,openbookqa_W4_A4_GPTQ.log ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
2
+ |-------------|------:|------|-----:|--------|-----:|---|-----:|
3
+ |openbookqa | 1|none | 0|acc |0.2820|± |0.0201|
4
+ | | |none | 0|acc_norm|0.4040|± |0.0220|
5
+ |arc_challenge| 1|none | 0|acc |0.3976|± |0.0143|
6
+ | | |none | 0|acc_norm|0.4215|± |0.0144|
7
+ |arc_easy | 1|none | 0|acc |0.7184|± |0.0092|
8
+ | | |none | 0|acc_norm|0.6772|± |0.0096|
9
+ |winogrande | 1|none | 0|acc |0.6409|± |0.0135|
10
+ |hellaswag | 1|none | 0|acc |0.5326|± |0.0050|
11
+ | | |none | 0|acc_norm|0.7181|± |0.0045|
12
+ |piqa | 1|none | 0|acc |0.7557|± |0.0100|
13
+ | | |none | 0|acc_norm|0.7622|± |0.0099|
14
+ |boolq | 2|none | 0|acc |0.7349|± |0.0077|
boolq,piqa,hellaswag,winogrande,arc_easy,arc_challenge,openbookqa_W4_A4_RTN.log ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
2
+ |-------------|------:|------|-----:|--------|-----:|---|-----:|
3
+ |openbookqa | 1|none | 0|acc |0.2060|± |0.0181|
4
+ | | |none | 0|acc_norm|0.3420|± |0.0212|
5
+ |arc_challenge| 1|none | 0|acc |0.3345|± |0.0138|
6
+ | | |none | 0|acc_norm|0.3498|± |0.0139|
7
+ |arc_easy | 1|none | 0|acc |0.6343|± |0.0099|
8
+ | | |none | 0|acc_norm|0.5833|± |0.0101|
9
+ |winogrande | 1|none | 0|acc |0.5691|± |0.0139|
10
+ |hellaswag | 1|none | 0|acc |0.4445|± |0.0050|
11
+ | | |none | 0|acc_norm|0.5966|± |0.0049|
12
+ |piqa | 1|none | 0|acc |0.6752|± |0.0109|
13
+ | | |none | 0|acc_norm|0.6768|± |0.0109|
14
+ |boolq | 2|none | 0|acc |0.6709|± |0.0082|
boolq,piqa,hellaswag,winogrande,arc_easy,arc_challenge,openbookqa_W6_A6_GPTQ.log ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
2
+ |-------------|------:|------|-----:|--------|-----:|---|-----:|
3
+ |openbookqa | 1|none | 0|acc |0.3080|± |0.0207|
4
+ | | |none | 0|acc_norm|0.4360|± |0.0222|
5
+ |arc_challenge| 1|none | 0|acc |0.4505|± |0.0145|
6
+ | | |none | 0|acc_norm|0.4727|± |0.0146|
7
+ |arc_easy | 1|none | 0|acc |0.7660|± |0.0087|
8
+ | | |none | 0|acc_norm|0.7479|± |0.0089|
9
+ |winogrande | 1|none | 0|acc |0.6851|± |0.0131|
10
+ |hellaswag | 1|none | 0|acc |0.5746|± |0.0049|
11
+ | | |none | 0|acc_norm|0.7630|± |0.0042|
12
+ |piqa | 1|none | 0|acc |0.7775|± |0.0097|
13
+ | | |none | 0|acc_norm|0.7911|± |0.0095|
14
+ |boolq | 2|none | 0|acc |0.7786|± |0.0073|
boolq,piqa,hellaswag,winogrande,arc_easy,arc_challenge,openbookqa_W6_A6_RTN.log ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
2
+ |-------------|------:|------|-----:|--------|-----:|---|-----:|
3
+ |openbookqa | 1|none | 0|acc |0.3300|± |0.0210|
4
+ | | |none | 0|acc_norm|0.4400|± |0.0222|
5
+ |arc_challenge| 1|none | 0|acc |0.4565|± |0.0146|
6
+ | | |none | 0|acc_norm|0.4718|± |0.0146|
7
+ |arc_easy | 1|none | 0|acc |0.7656|± |0.0087|
8
+ | | |none | 0|acc_norm|0.7517|± |0.0089|
9
+ |winogrande | 1|none | 0|acc |0.7040|± |0.0128|
10
+ |hellaswag | 1|none | 0|acc |0.5745|± |0.0049|
11
+ | | |none | 0|acc_norm|0.7648|± |0.0042|
12
+ |piqa | 1|none | 0|acc |0.7835|± |0.0096|
13
+ | | |none | 0|acc_norm|0.7905|± |0.0095|
14
+ |boolq | 2|none | 0|acc |0.7740|± |0.0073|
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/project/vislangmod/Llama-2-7b-hf/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.41.2",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.9,
8
+ "top_p": 0.6,
9
+ "transformers_version": "4.41.2"
10
+ }
mmlu_FP16.log ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
2
+ |---------------------------------------|-------|------|-----:|------|-----:|---|-----:|
3
+ |mmlu |N/A |none | 0|acc |0.4155|± |0.0041|
4
+ | - humanities |N/A |none | 0|acc |0.3892|± |0.0069|
5
+ | - formal_logic | 0|none | 0|acc |0.3571|± |0.0429|
6
+ | - high_school_european_history | 0|none | 0|acc |0.6061|± |0.0382|
7
+ | - high_school_us_history | 0|none | 0|acc |0.4755|± |0.0351|
8
+ | - high_school_world_history | 0|none | 0|acc |0.5992|± |0.0319|
9
+ | - international_law | 0|none | 0|acc |0.5950|± |0.0448|
10
+ | - jurisprudence | 0|none | 0|acc |0.4722|± |0.0483|
11
+ | - logical_fallacies | 0|none | 0|acc |0.4969|± |0.0393|
12
+ | - moral_disputes | 0|none | 0|acc |0.4104|± |0.0265|
13
+ | - moral_scenarios | 0|none | 0|acc |0.2413|± |0.0143|
14
+ | - philosophy | 0|none | 0|acc |0.5177|± |0.0284|
15
+ | - prehistory | 0|none | 0|acc |0.4414|± |0.0276|
16
+ | - professional_law | 0|none | 0|acc |0.3149|± |0.0119|
17
+ | - world_religions | 0|none | 0|acc |0.5731|± |0.0379|
18
+ | - other |N/A |none | 0|acc |0.4689|± |0.0089|
19
+ | - business_ethics | 0|none | 0|acc |0.4200|± |0.0496|
20
+ | - clinical_knowledge | 0|none | 0|acc |0.4755|± |0.0307|
21
+ | - college_medicine | 0|none | 0|acc |0.4393|± |0.0378|
22
+ | - global_facts | 0|none | 0|acc |0.3000|± |0.0461|
23
+ | - human_aging | 0|none | 0|acc |0.4081|± |0.0330|
24
+ | - management | 0|none | 0|acc |0.4272|± |0.0490|
25
+ | - marketing | 0|none | 0|acc |0.6239|± |0.0317|
26
+ | - medical_genetics | 0|none | 0|acc |0.5200|± |0.0502|
27
+ | - miscellaneous | 0|none | 0|acc |0.5364|± |0.0178|
28
+ | - nutrition | 0|none | 0|acc |0.4542|± |0.0285|
29
+ | - professional_accounting | 0|none | 0|acc |0.3582|± |0.0286|
30
+ | - professional_medicine | 0|none | 0|acc |0.4743|± |0.0303|
31
+ | - virology | 0|none | 0|acc |0.3675|± |0.0375|
32
+ | - social_sciences |N/A |none | 0|acc |0.4651|± |0.0089|
33
+ | - econometrics | 0|none | 0|acc |0.1930|± |0.0371|
34
+ | - high_school_geography | 0|none | 0|acc |0.4596|± |0.0355|
35
+ | - high_school_government_and_politics| 0|none | 0|acc |0.5596|± |0.0358|
36
+ | - high_school_macroeconomics | 0|none | 0|acc |0.3821|± |0.0246|
37
+ | - high_school_microeconomics | 0|none | 0|acc |0.3571|± |0.0311|
38
+ | - high_school_psychology | 0|none | 0|acc |0.5468|± |0.0213|
39
+ | - human_sexuality | 0|none | 0|acc |0.5115|± |0.0438|
40
+ | - professional_psychology | 0|none | 0|acc |0.4412|± |0.0201|
41
+ | - public_relations | 0|none | 0|acc |0.4273|± |0.0474|
42
+ | - security_studies | 0|none | 0|acc |0.4571|± |0.0319|
43
+ | - sociology | 0|none | 0|acc |0.5871|± |0.0348|
44
+ | - us_foreign_policy | 0|none | 0|acc |0.6400|± |0.0482|
45
+ | - stem |N/A |none | 0|acc |0.3536|± |0.0084|
46
+ | - abstract_algebra | 0|none | 0|acc |0.2700|± |0.0446|
47
+ | - anatomy | 0|none | 0|acc |0.4370|± |0.0428|
48
+ | - astronomy | 0|none | 0|acc |0.4342|± |0.0403|
49
+ | - college_biology | 0|none | 0|acc |0.4028|± |0.0410|
50
+ | - college_chemistry | 0|none | 0|acc |0.3900|± |0.0490|
51
+ | - college_computer_science | 0|none | 0|acc |0.3700|± |0.0485|
52
+ | - college_mathematics | 0|none | 0|acc |0.3800|± |0.0488|
53
+ | - college_physics | 0|none | 0|acc |0.2843|± |0.0449|
54
+ | - computer_security | 0|none | 0|acc |0.5200|± |0.0502|
55
+ | - conceptual_physics | 0|none | 0|acc |0.3532|± |0.0312|
56
+ | - electrical_engineering | 0|none | 0|acc |0.3931|± |0.0407|
57
+ | - elementary_mathematics | 0|none | 0|acc |0.2725|± |0.0229|
58
+ | - high_school_biology | 0|none | 0|acc |0.4484|± |0.0283|
59
+ | - high_school_chemistry | 0|none | 0|acc |0.3300|± |0.0331|
60
+ | - high_school_computer_science | 0|none | 0|acc |0.3900|± |0.0490|
61
+ | - high_school_mathematics | 0|none | 0|acc |0.2481|± |0.0263|
62
+ | - high_school_physics | 0|none | 0|acc |0.2980|± |0.0373|
63
+ | - high_school_statistics | 0|none | 0|acc |0.3056|± |0.0314|
64
+ | - machine_learning | 0|none | 0|acc |0.3929|± |0.0464|
mmlu_W4_A4_GPTQ.log ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
2
+ |---------------------------------------|-------|------|-----:|------|-----:|---|-----:|
3
+ |mmlu |N/A |none | 0|acc |0.3097|± |0.0039|
4
+ | - humanities |N/A |none | 0|acc |0.3007|± |0.0066|
5
+ | - formal_logic | 0|none | 0|acc |0.2857|± |0.0404|
6
+ | - high_school_european_history | 0|none | 0|acc |0.3515|± |0.0373|
7
+ | - high_school_us_history | 0|none | 0|acc |0.3676|± |0.0338|
8
+ | - high_school_world_history | 0|none | 0|acc |0.4219|± |0.0321|
9
+ | - international_law | 0|none | 0|acc |0.3554|± |0.0437|
10
+ | - jurisprudence | 0|none | 0|acc |0.3056|± |0.0445|
11
+ | - logical_fallacies | 0|none | 0|acc |0.2761|± |0.0351|
12
+ | - moral_disputes | 0|none | 0|acc |0.2948|± |0.0245|
13
+ | - moral_scenarios | 0|none | 0|acc |0.2190|± |0.0138|
14
+ | - philosophy | 0|none | 0|acc |0.3408|± |0.0269|
15
+ | - prehistory | 0|none | 0|acc |0.3333|± |0.0262|
16
+ | - professional_law | 0|none | 0|acc |0.2901|± |0.0116|
17
+ | - world_religions | 0|none | 0|acc |0.3977|± |0.0375|
18
+ | - other |N/A |none | 0|acc |0.3296|± |0.0084|
19
+ | - business_ethics | 0|none | 0|acc |0.3500|± |0.0479|
20
+ | - clinical_knowledge | 0|none | 0|acc |0.3472|± |0.0293|
21
+ | - college_medicine | 0|none | 0|acc |0.2717|± |0.0339|
22
+ | - global_facts | 0|none | 0|acc |0.2600|± |0.0441|
23
+ | - human_aging | 0|none | 0|acc |0.2691|± |0.0298|
24
+ | - management | 0|none | 0|acc |0.3107|± |0.0458|
25
+ | - marketing | 0|none | 0|acc |0.4103|± |0.0322|
26
+ | - medical_genetics | 0|none | 0|acc |0.2800|± |0.0451|
27
+ | - miscellaneous | 0|none | 0|acc |0.3563|± |0.0171|
28
+ | - nutrition | 0|none | 0|acc |0.3497|± |0.0273|
29
+ | - professional_accounting | 0|none | 0|acc |0.2872|± |0.0270|
30
+ | - professional_medicine | 0|none | 0|acc |0.3676|± |0.0293|
31
+ | - virology | 0|none | 0|acc |0.2470|± |0.0336|
32
+ | - social_sciences |N/A |none | 0|acc |0.3195|± |0.0084|
33
+ | - econometrics | 0|none | 0|acc |0.2456|± |0.0405|
34
+ | - high_school_geography | 0|none | 0|acc |0.3182|± |0.0332|
35
+ | - high_school_government_and_politics| 0|none | 0|acc |0.3627|± |0.0347|
36
+ | - high_school_macroeconomics | 0|none | 0|acc |0.3026|± |0.0233|
37
+ | - high_school_microeconomics | 0|none | 0|acc |0.2395|± |0.0277|
38
+ | - high_school_psychology | 0|none | 0|acc |0.3193|± |0.0200|
39
+ | - human_sexuality | 0|none | 0|acc |0.3969|± |0.0429|
40
+ | - professional_psychology | 0|none | 0|acc |0.2810|± |0.0182|
41
+ | - public_relations | 0|none | 0|acc |0.3273|± |0.0449|
42
+ | - security_studies | 0|none | 0|acc |0.3306|± |0.0301|
43
+ | - sociology | 0|none | 0|acc |0.4378|± |0.0351|
44
+ | - us_foreign_policy | 0|none | 0|acc |0.4400|± |0.0499|
45
+ | - stem |N/A |none | 0|acc |0.2940|± |0.0081|
46
+ | - abstract_algebra | 0|none | 0|acc |0.2400|± |0.0429|
47
+ | - anatomy | 0|none | 0|acc |0.3556|± |0.0414|
48
+ | - astronomy | 0|none | 0|acc |0.3487|± |0.0388|
49
+ | - college_biology | 0|none | 0|acc |0.3542|± |0.0400|
50
+ | - college_chemistry | 0|none | 0|acc |0.2600|± |0.0441|
51
+ | - college_computer_science | 0|none | 0|acc |0.3300|± |0.0473|
52
+ | - college_mathematics | 0|none | 0|acc |0.3000|± |0.0461|
53
+ | - college_physics | 0|none | 0|acc |0.2059|± |0.0402|
54
+ | - computer_security | 0|none | 0|acc |0.3700|± |0.0485|
55
+ | - conceptual_physics | 0|none | 0|acc |0.2511|± |0.0283|
56
+ | - electrical_engineering | 0|none | 0|acc |0.3034|± |0.0383|
57
+ | - elementary_mathematics | 0|none | 0|acc |0.2328|± |0.0218|
58
+ | - high_school_biology | 0|none | 0|acc |0.3548|± |0.0272|
59
+ | - high_school_chemistry | 0|none | 0|acc |0.2365|± |0.0299|
60
+ | - high_school_computer_science | 0|none | 0|acc |0.3100|± |0.0465|
61
+ | - high_school_mathematics | 0|none | 0|acc |0.2926|± |0.0277|
62
+ | - high_school_physics | 0|none | 0|acc |0.3113|± |0.0378|
63
+ | - high_school_statistics | 0|none | 0|acc |0.3056|± |0.0314|
64
+ | - machine_learning | 0|none | 0|acc |0.2857|± |0.0429|
mmlu_W4_A4_RTN.log ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
2
+ |---------------------------------------|-------|------|-----:|------|-----:|---|-----:|
3
+ |mmlu |N/A |none | 0|acc |0.2578|± |0.0037|
4
+ | - humanities |N/A |none | 0|acc |0.2465|± |0.0063|
5
+ | - formal_logic | 0|none | 0|acc |0.2857|± |0.0404|
6
+ | - high_school_european_history | 0|none | 0|acc |0.2424|± |0.0335|
7
+ | - high_school_us_history | 0|none | 0|acc |0.2255|± |0.0293|
8
+ | - high_school_world_history | 0|none | 0|acc |0.2489|± |0.0281|
9
+ | - international_law | 0|none | 0|acc |0.1983|± |0.0364|
10
+ | - jurisprudence | 0|none | 0|acc |0.2685|± |0.0428|
11
+ | - logical_fallacies | 0|none | 0|acc |0.2515|± |0.0341|
12
+ | - moral_disputes | 0|none | 0|acc |0.2630|± |0.0237|
13
+ | - moral_scenarios | 0|none | 0|acc |0.2335|± |0.0141|
14
+ | - philosophy | 0|none | 0|acc |0.2122|± |0.0232|
15
+ | - prehistory | 0|none | 0|acc |0.2377|± |0.0237|
16
+ | - professional_law | 0|none | 0|acc |0.2640|± |0.0113|
17
+ | - world_religions | 0|none | 0|acc |0.2164|± |0.0316|
18
+ | - other |N/A |none | 0|acc |0.2617|± |0.0079|
19
+ | - business_ethics | 0|none | 0|acc |0.2300|± |0.0423|
20
+ | - clinical_knowledge | 0|none | 0|acc |0.3019|± |0.0283|
21
+ | - college_medicine | 0|none | 0|acc |0.3179|± |0.0355|
22
+ | - global_facts | 0|none | 0|acc |0.1800|± |0.0386|
23
+ | - human_aging | 0|none | 0|acc |0.1794|± |0.0257|
24
+ | - management | 0|none | 0|acc |0.3107|± |0.0458|
25
+ | - marketing | 0|none | 0|acc |0.2863|± |0.0296|
26
+ | - medical_genetics | 0|none | 0|acc |0.2900|± |0.0456|
27
+ | - miscellaneous | 0|none | 0|acc |0.2401|± |0.0153|
28
+ | - nutrition | 0|none | 0|acc |0.2843|± |0.0258|
29
+ | - professional_accounting | 0|none | 0|acc |0.2872|± |0.0270|
30
+ | - professional_medicine | 0|none | 0|acc |0.2831|± |0.0274|
31
+ | - virology | 0|none | 0|acc |0.2169|± |0.0321|
32
+ | - social_sciences |N/A |none | 0|acc |0.2720|± |0.0080|
33
+ | - econometrics | 0|none | 0|acc |0.2193|± |0.0389|
34
+ | - high_school_geography | 0|none | 0|acc |0.3030|± |0.0327|
35
+ | - high_school_government_and_politics| 0|none | 0|acc |0.2798|± |0.0324|
36
+ | - high_school_macroeconomics | 0|none | 0|acc |0.3385|± |0.0240|
37
+ | - high_school_microeconomics | 0|none | 0|acc |0.2983|± |0.0297|
38
+ | - high_school_psychology | 0|none | 0|acc |0.2807|± |0.0193|
39
+ | - human_sexuality | 0|none | 0|acc |0.2595|± |0.0384|
40
+ | - professional_psychology | 0|none | 0|acc |0.2288|± |0.0170|
41
+ | - public_relations | 0|none | 0|acc |0.2273|± |0.0401|
42
+ | - security_studies | 0|none | 0|acc |0.2571|± |0.0280|
43
+ | - sociology | 0|none | 0|acc |0.2388|± |0.0301|
44
+ | - us_foreign_policy | 0|none | 0|acc |0.3200|± |0.0469|
45
+ | - stem |N/A |none | 0|acc |0.2569|± |0.0078|
46
+ | - abstract_algebra | 0|none | 0|acc |0.1900|± |0.0394|
47
+ | - anatomy | 0|none | 0|acc |0.2444|± |0.0371|
48
+ | - astronomy | 0|none | 0|acc |0.2105|± |0.0332|
49
+ | - college_biology | 0|none | 0|acc |0.2917|± |0.0380|
50
+ | - college_chemistry | 0|none | 0|acc |0.3200|± |0.0469|
51
+ | - college_computer_science | 0|none | 0|acc |0.2900|± |0.0456|
52
+ | - college_mathematics | 0|none | 0|acc |0.2400|± |0.0429|
53
+ | - college_physics | 0|none | 0|acc |0.2549|± |0.0434|
54
+ | - computer_security | 0|none | 0|acc |0.2700|± |0.0446|
55
+ | - conceptual_physics | 0|none | 0|acc |0.2766|± |0.0292|
56
+ | - electrical_engineering | 0|none | 0|acc |0.2414|± |0.0357|
57
+ | - elementary_mathematics | 0|none | 0|acc |0.2619|± |0.0226|
58
+ | - high_school_biology | 0|none | 0|acc |0.2710|± |0.0253|
59
+ | - high_school_chemistry | 0|none | 0|acc |0.2167|± |0.0290|
60
+ | - high_school_computer_science | 0|none | 0|acc |0.2100|± |0.0409|
61
+ | - high_school_mathematics | 0|none | 0|acc |0.2407|± |0.0261|
62
+ | - high_school_physics | 0|none | 0|acc |0.2715|± |0.0363|
63
+ | - high_school_statistics | 0|none | 0|acc |0.2731|± |0.0304|
64
+ | - machine_learning | 0|none | 0|acc |0.2946|± |0.0433|
mmlu_W6_A6_GPTQ.log ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
2
+ |---------------------------------------|-------|------|-----:|------|-----:|---|-----:|
3
+ |mmlu |N/A |none | 0|acc |0.4082|± |0.0041|
4
+ | - humanities |N/A |none | 0|acc |0.3783|± |0.0069|
5
+ | - formal_logic | 0|none | 0|acc |0.3333|± |0.0422|
6
+ | - high_school_european_history | 0|none | 0|acc |0.5818|± |0.0385|
7
+ | - high_school_us_history | 0|none | 0|acc |0.4804|± |0.0351|
8
+ | - high_school_world_history | 0|none | 0|acc |0.5781|± |0.0321|
9
+ | - international_law | 0|none | 0|acc |0.5372|± |0.0455|
10
+ | - jurisprudence | 0|none | 0|acc |0.4352|± |0.0479|
11
+ | - logical_fallacies | 0|none | 0|acc |0.4785|± |0.0392|
12
+ | - moral_disputes | 0|none | 0|acc |0.4017|± |0.0264|
13
+ | - moral_scenarios | 0|none | 0|acc |0.2413|± |0.0143|
14
+ | - philosophy | 0|none | 0|acc |0.4952|± |0.0284|
15
+ | - prehistory | 0|none | 0|acc |0.4321|± |0.0276|
16
+ | - professional_law | 0|none | 0|acc |0.3031|± |0.0117|
17
+ | - world_religions | 0|none | 0|acc |0.6023|± |0.0375|
18
+ | - other |N/A |none | 0|acc |0.4606|± |0.0089|
19
+ | - business_ethics | 0|none | 0|acc |0.4700|± |0.0502|
20
+ | - clinical_knowledge | 0|none | 0|acc |0.4717|± |0.0307|
21
+ | - college_medicine | 0|none | 0|acc |0.4509|± |0.0379|
22
+ | - global_facts | 0|none | 0|acc |0.3000|± |0.0461|
23
+ | - human_aging | 0|none | 0|acc |0.3946|± |0.0328|
24
+ | - management | 0|none | 0|acc |0.4369|± |0.0491|
25
+ | - marketing | 0|none | 0|acc |0.5940|± |0.0322|
26
+ | - medical_genetics | 0|none | 0|acc |0.5000|± |0.0503|
27
+ | - miscellaneous | 0|none | 0|acc |0.5223|± |0.0179|
28
+ | - nutrition | 0|none | 0|acc |0.4444|± |0.0285|
29
+ | - professional_accounting | 0|none | 0|acc |0.3794|± |0.0289|
30
+ | - professional_medicine | 0|none | 0|acc |0.4228|± |0.0300|
31
+ | - virology | 0|none | 0|acc |0.3735|± |0.0377|
32
+ | - social_sciences |N/A |none | 0|acc |0.4621|± |0.0089|
33
+ | - econometrics | 0|none | 0|acc |0.2105|± |0.0384|
34
+ | - high_school_geography | 0|none | 0|acc |0.4545|± |0.0355|
35
+ | - high_school_government_and_politics| 0|none | 0|acc |0.5440|± |0.0359|
36
+ | - high_school_macroeconomics | 0|none | 0|acc |0.3872|± |0.0247|
37
+ | - high_school_microeconomics | 0|none | 0|acc |0.3529|± |0.0310|
38
+ | - high_school_psychology | 0|none | 0|acc |0.5468|± |0.0213|
39
+ | - human_sexuality | 0|none | 0|acc |0.5115|± |0.0438|
40
+ | - professional_psychology | 0|none | 0|acc |0.4297|± |0.0200|
41
+ | - public_relations | 0|none | 0|acc |0.4273|± |0.0474|
42
+ | - security_studies | 0|none | 0|acc |0.4571|± |0.0319|
43
+ | - sociology | 0|none | 0|acc |0.5920|± |0.0348|
44
+ | - us_foreign_policy | 0|none | 0|acc |0.6200|± |0.0488|
45
+ | - stem |N/A |none | 0|acc |0.3486|± |0.0084|
46
+ | - abstract_algebra | 0|none | 0|acc |0.2800|± |0.0451|
47
+ | - anatomy | 0|none | 0|acc |0.4148|± |0.0426|
48
+ | - astronomy | 0|none | 0|acc |0.4079|± |0.0400|
49
+ | - college_biology | 0|none | 0|acc |0.4583|± |0.0417|
50
+ | - college_chemistry | 0|none | 0|acc |0.3500|± |0.0479|
51
+ | - college_computer_science | 0|none | 0|acc |0.3200|± |0.0469|
52
+ | - college_mathematics | 0|none | 0|acc |0.3100|± |0.0465|
53
+ | - college_physics | 0|none | 0|acc |0.3137|± |0.0462|
54
+ | - computer_security | 0|none | 0|acc |0.5200|± |0.0502|
55
+ | - conceptual_physics | 0|none | 0|acc |0.3489|± |0.0312|
56
+ | - electrical_engineering | 0|none | 0|acc |0.3655|± |0.0401|
57
+ | - elementary_mathematics | 0|none | 0|acc |0.2725|± |0.0229|
58
+ | - high_school_biology | 0|none | 0|acc |0.4581|± |0.0283|
59
+ | - high_school_chemistry | 0|none | 0|acc |0.3399|± |0.0333|
60
+ | - high_school_computer_science | 0|none | 0|acc |0.4100|± |0.0494|
61
+ | - high_school_mathematics | 0|none | 0|acc |0.2407|± |0.0261|
62
+ | - high_school_physics | 0|none | 0|acc |0.2914|± |0.0371|
63
+ | - high_school_statistics | 0|none | 0|acc |0.2870|± |0.0309|
64
+ | - machine_learning | 0|none | 0|acc |0.3929|± |0.0464|
mmlu_W6_A6_RTN.log ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | Tasks |Version|Filter|n-shot|Metric|Value | |Stderr|
2
+ |---------------------------------------|-------|------|-----:|------|-----:|---|-----:|
3
+ |mmlu |N/A |none | 0|acc |0.4052|± |0.0041|
4
+ | - humanities |N/A |none | 0|acc |0.3815|± |0.0069|
5
+ | - formal_logic | 0|none | 0|acc |0.3651|± |0.0431|
6
+ | - high_school_european_history | 0|none | 0|acc |0.5636|± |0.0387|
7
+ | - high_school_us_history | 0|none | 0|acc |0.4804|± |0.0351|
8
+ | - high_school_world_history | 0|none | 0|acc |0.5527|± |0.0324|
9
+ | - international_law | 0|none | 0|acc |0.5537|± |0.0454|
10
+ | - jurisprudence | 0|none | 0|acc |0.4907|± |0.0483|
11
+ | - logical_fallacies | 0|none | 0|acc |0.4540|± |0.0391|
12
+ | - moral_disputes | 0|none | 0|acc |0.3988|± |0.0264|
13
+ | - moral_scenarios | 0|none | 0|acc |0.2447|± |0.0144|
14
+ | - philosophy | 0|none | 0|acc |0.5048|± |0.0284|
15
+ | - prehistory | 0|none | 0|acc |0.4414|± |0.0276|
16
+ | - professional_law | 0|none | 0|acc |0.3110|± |0.0118|
17
+ | - world_religions | 0|none | 0|acc |0.5789|± |0.0379|
18
+ | - other |N/A |none | 0|acc |0.4538|± |0.0089|
19
+ | - business_ethics | 0|none | 0|acc |0.4100|± |0.0494|
20
+ | - clinical_knowledge | 0|none | 0|acc |0.4491|± |0.0306|
21
+ | - college_medicine | 0|none | 0|acc |0.4393|± |0.0378|
22
+ | - global_facts | 0|none | 0|acc |0.2700|± |0.0446|
23
+ | - human_aging | 0|none | 0|acc |0.3812|± |0.0326|
24
+ | - management | 0|none | 0|acc |0.4660|± |0.0494|
25
+ | - marketing | 0|none | 0|acc |0.5855|± |0.0323|
26
+ | - medical_genetics | 0|none | 0|acc |0.4800|± |0.0502|
27
+ | - miscellaneous | 0|none | 0|acc |0.5198|± |0.0179|
28
+ | - nutrition | 0|none | 0|acc |0.4542|± |0.0285|
29
+ | - professional_accounting | 0|none | 0|acc |0.3369|± |0.0282|
30
+ | - professional_medicine | 0|none | 0|acc |0.4559|± |0.0303|
31
+ | - virology | 0|none | 0|acc |0.3855|± |0.0379|
32
+ | - social_sciences |N/A |none | 0|acc |0.4469|± |0.0088|
33
+ | - econometrics | 0|none | 0|acc |0.2368|± |0.0400|
34
+ | - high_school_geography | 0|none | 0|acc |0.4242|± |0.0352|
35
+ | - high_school_government_and_politics| 0|none | 0|acc |0.5959|± |0.0354|
36
+ | - high_school_macroeconomics | 0|none | 0|acc |0.3795|± |0.0246|
37
+ | - high_school_microeconomics | 0|none | 0|acc |0.3529|± |0.0310|
38
+ | - high_school_psychology | 0|none | 0|acc |0.5284|± |0.0214|
39
+ | - human_sexuality | 0|none | 0|acc |0.4809|± |0.0438|
40
+ | - professional_psychology | 0|none | 0|acc |0.3824|± |0.0197|
41
+ | - public_relations | 0|none | 0|acc |0.3818|± |0.0465|
42
+ | - security_studies | 0|none | 0|acc |0.4735|± |0.0320|
43
+ | - sociology | 0|none | 0|acc |0.5821|± |0.0349|
44
+ | - us_foreign_policy | 0|none | 0|acc |0.5700|± |0.0498|
45
+ | - stem |N/A |none | 0|acc |0.3520|± |0.0084|
46
+ | - abstract_algebra | 0|none | 0|acc |0.2800|± |0.0451|
47
+ | - anatomy | 0|none | 0|acc |0.4444|± |0.0429|
48
+ | - astronomy | 0|none | 0|acc |0.4408|± |0.0404|
49
+ | - college_biology | 0|none | 0|acc |0.4097|± |0.0411|
50
+ | - college_chemistry | 0|none | 0|acc |0.4300|± |0.0498|
51
+ | - college_computer_science | 0|none | 0|acc |0.3800|± |0.0488|
52
+ | - college_mathematics | 0|none | 0|acc |0.3500|± |0.0479|
53
+ | - college_physics | 0|none | 0|acc |0.3039|± |0.0458|
54
+ | - computer_security | 0|none | 0|acc |0.4600|± |0.0501|
55
+ | - conceptual_physics | 0|none | 0|acc |0.3660|± |0.0315|
56
+ | - electrical_engineering | 0|none | 0|acc |0.4069|± |0.0409|
57
+ | - elementary_mathematics | 0|none | 0|acc |0.2540|± |0.0224|
58
+ | - high_school_biology | 0|none | 0|acc |0.4161|± |0.0280|
59
+ | - high_school_chemistry | 0|none | 0|acc |0.3054|± |0.0324|
60
+ | - high_school_computer_science | 0|none | 0|acc |0.4000|± |0.0492|
61
+ | - high_school_mathematics | 0|none | 0|acc |0.2444|± |0.0262|
62
+ | - high_school_physics | 0|none | 0|acc |0.3311|± |0.0384|
63
+ | - high_school_statistics | 0|none | 0|acc |0.3287|± |0.0320|
64
+ | - machine_learning | 0|none | 0|acc |0.3929|± |0.0464|
pytorch_model-00001-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7694178cbf14607c312ba7572ef99f88e859758cecaad96b1ce81d5a81510b39
3
+ size 1982192024
pytorch_model-00002-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e233d91ff0f0eddb44a41c7487cd11672b0099486af1e2e407764b2f058b310
3
+ size 1990664269
pytorch_model-00003-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:275b78c072f2b3a8553f7ad55da198758952f20fc3d7d559bb03feb05672e0d1
3
+ size 1990664461
pytorch_model-00004-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0886ebc9108755b48b9941d36d691419ff59424a3215705bf7ec75f366fb06de
3
+ size 1990664525
pytorch_model-00005-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f4b39f4f90a3533dbbc6ed829fd64baa4152f9c1aae14385984c6f654df904
3
+ size 1933964948
pytorch_model-00006-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f97398b5cd4738a9acccf4c65b2635174018cfa9c9e3bec8be397a70ef4619ed
3
+ size 1934041485
pytorch_model-00007-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc063ac614fbeeb4080840366d11a4d99fafaf7ecd47f65563efff17a1d8ca1
3
+ size 1657124277
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
rotate_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:055e614cbf9b87e63f7b81e4182b5b1fd0beef53a0ee71868aa9f1ee97afae4f
3
+ size 13479370546
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\n' }}{% endif %}{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "padding_side": "left",
38
+ "sp_model_kwargs": {},
39
+ "split_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }