ScarletAce commited on
Commit
f43c1aa
1 Parent(s): 41d15a1

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 |0.3300|± |0.0210|
4
+ | | |none | 0|acc_norm|0.4340|± |0.0222|
5
+ |arc_challenge| 1|none | 0|acc |0.4693|± |0.0146|
6
+ | | |none | 0|acc_norm|0.4949|± |0.0146|
7
+ |arc_easy | 1|none | 0|acc |0.7870|± |0.0084|
8
+ | | |none | 0|acc_norm|0.7774|± |0.0085|
9
+ |winogrande | 1|none | 0|acc |0.7167|± |0.0127|
10
+ |hellaswag | 1|none | 0|acc |0.5975|± |0.0049|
11
+ | | |none | 0|acc_norm|0.7859|± |0.0041|
12
+ |piqa | 1|none | 0|acc |0.7824|± |0.0096|
13
+ | | |none | 0|acc_norm|0.7922|± |0.0095|
14
+ |boolq | 2|none | 0|acc |0.7985|± |0.0070|
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 |0.2880|± |0.0203|
4
+ | | |none | 0|acc_norm|0.3880|± |0.0218|
5
+ |arc_challenge| 1|none | 0|acc |0.4070|± |0.0144|
6
+ | | |none | 0|acc_norm|0.4394|± |0.0145|
7
+ |arc_easy | 1|none | 0|acc |0.7551|± |0.0088|
8
+ | | |none | 0|acc_norm|0.7327|± |0.0091|
9
+ |winogrande | 1|none | 0|acc |0.6598|± |0.0133|
10
+ |hellaswag | 1|none | 0|acc |0.5534|± |0.0050|
11
+ | | |none | 0|acc_norm|0.7392|± |0.0044|
12
+ |piqa | 1|none | 0|acc |0.7557|± |0.0100|
13
+ | | |none | 0|acc_norm|0.7715|± |0.0098|
14
+ |boolq | 2|none | 0|acc |0.7404|± |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 |0.2280|± |0.0188|
4
+ | | |none | 0|acc_norm|0.3420|± |0.0212|
5
+ |arc_challenge| 1|none | 0|acc |0.3746|± |0.0141|
6
+ | | |none | 0|acc_norm|0.3865|± |0.0142|
7
+ |arc_easy | 1|none | 0|acc |0.7172|± |0.0092|
8
+ | | |none | 0|acc_norm|0.6684|± |0.0097|
9
+ |winogrande | 1|none | 0|acc |0.5959|± |0.0138|
10
+ |hellaswag | 1|none | 0|acc |0.4990|± |0.0050|
11
+ | | |none | 0|acc_norm|0.6716|± |0.0047|
12
+ |piqa | 1|none | 0|acc |0.7242|± |0.0104|
13
+ | | |none | 0|acc_norm|0.7388|± |0.0102|
14
+ |boolq | 2|none | 0|acc |0.7064|± |0.0080|
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 |0.3240|± |0.0210|
4
+ | | |none | 0|acc_norm|0.4400|± |0.0222|
5
+ |arc_challenge| 1|none | 0|acc |0.4582|± |0.0146|
6
+ | | |none | 0|acc_norm|0.4940|± |0.0146|
7
+ |arc_easy | 1|none | 0|acc |0.7811|± |0.0085|
8
+ | | |none | 0|acc_norm|0.7740|± |0.0086|
9
+ |winogrande | 1|none | 0|acc |0.7245|± |0.0126|
10
+ |hellaswag | 1|none | 0|acc |0.5950|± |0.0049|
11
+ | | |none | 0|acc_norm|0.7812|± |0.0041|
12
+ |piqa | 1|none | 0|acc |0.7802|± |0.0097|
13
+ | | |none | 0|acc_norm|0.7927|± |0.0095|
14
+ |boolq | 2|none | 0|acc |0.8058|± |0.0069|
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 |0.3200|± |0.0209|
4
+ | | |none | 0|acc_norm|0.4320|± |0.0222|
5
+ |arc_challenge| 1|none | 0|acc |0.4701|± |0.0146|
6
+ | | |none | 0|acc_norm|0.4957|± |0.0146|
7
+ |arc_easy | 1|none | 0|acc |0.7837|± |0.0084|
8
+ | | |none | 0|acc_norm|0.7757|± |0.0086|
9
+ |winogrande | 1|none | 0|acc |0.7111|± |0.0127|
10
+ |hellaswag | 1|none | 0|acc |0.5935|± |0.0049|
11
+ | | |none | 0|acc_norm|0.7798|± |0.0041|
12
+ |piqa | 1|none | 0|acc |0.7824|± |0.0096|
13
+ | | |none | 0|acc_norm|0.7884|± |0.0095|
14
+ |boolq | 2|none | 0|acc |0.8034|± |0.0070|
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/project/vislangmod/Llama-2-13b-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": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 40,
18
+ "num_hidden_layers": 40,
19
+ "num_key_value_heads": 40,
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 |0.4857|± |0.0041|
4
+ | - humanities |N/A |none | 0|acc |0.4612|± |0.0069|
5
+ | - formal_logic | 0|none | 0|acc |0.2937|± |0.0407|
6
+ | - high_school_european_history | 0|none | 0|acc |0.6364|± |0.0376|
7
+ | - high_school_us_history | 0|none | 0|acc |0.6765|± |0.0328|
8
+ | - high_school_world_history | 0|none | 0|acc |0.6540|± |0.0310|
9
+ | - international_law | 0|none | 0|acc |0.6529|± |0.0435|
10
+ | - jurisprudence | 0|none | 0|acc |0.5741|± |0.0478|
11
+ | - logical_fallacies | 0|none | 0|acc |0.5031|± |0.0393|
12
+ | - moral_disputes | 0|none | 0|acc |0.5029|± |0.0269|
13
+ | - moral_scenarios | 0|none | 0|acc |0.2503|± |0.0145|
14
+ | - philosophy | 0|none | 0|acc |0.6206|± |0.0276|
15
+ | - prehistory | 0|none | 0|acc |0.5957|± |0.0273|
16
+ | - professional_law | 0|none | 0|acc |0.3950|± |0.0125|
17
+ | - world_religions | 0|none | 0|acc |0.7135|± |0.0347|
18
+ | - other |N/A |none | 0|acc |0.5423|± |0.0087|
19
+ | - business_ethics | 0|none | 0|acc |0.5100|± |0.0502|
20
+ | - clinical_knowledge | 0|none | 0|acc |0.4528|± |0.0306|
21
+ | - college_medicine | 0|none | 0|acc |0.4509|± |0.0379|
22
+ | - global_facts | 0|none | 0|acc |0.3200|± |0.0469|
23
+ | - human_aging | 0|none | 0|acc |0.5561|± |0.0333|
24
+ | - management | 0|none | 0|acc |0.6408|± |0.0475|
25
+ | - marketing | 0|none | 0|acc |0.7094|± |0.0297|
26
+ | - medical_genetics | 0|none | 0|acc |0.5100|± |0.0502|
27
+ | - miscellaneous | 0|none | 0|acc |0.6692|± |0.0168|
28
+ | - nutrition | 0|none | 0|acc |0.5163|± |0.0286|
29
+ | - professional_accounting | 0|none | 0|acc |0.3865|± |0.0290|
30
+ | - professional_medicine | 0|none | 0|acc |0.4963|± |0.0304|
31
+ | - virology | 0|none | 0|acc |0.4277|± |0.0385|
32
+ | - social_sciences |N/A |none | 0|acc |0.5626|± |0.0088|
33
+ | - econometrics | 0|none | 0|acc |0.2018|± |0.0378|
34
+ | - high_school_geography | 0|none | 0|acc |0.5707|± |0.0353|
35
+ | - high_school_government_and_politics| 0|none | 0|acc |0.6736|± |0.0338|
36
+ | - high_school_macroeconomics | 0|none | 0|acc |0.4923|± |0.0253|
37
+ | - high_school_microeconomics | 0|none | 0|acc |0.5000|± |0.0325|
38
+ | - high_school_psychology | 0|none | 0|acc |0.6312|± |0.0207|
39
+ | - human_sexuality | 0|none | 0|acc |0.6183|± |0.0426|
40
+ | - professional_psychology | 0|none | 0|acc |0.5049|± |0.0202|
41
+ | - public_relations | 0|none | 0|acc |0.5636|± |0.0475|
42
+ | - security_studies | 0|none | 0|acc |0.6041|± |0.0313|
43
+ | - sociology | 0|none | 0|acc |0.6915|± |0.0327|
44
+ | - us_foreign_policy | 0|none | 0|acc |0.7100|± |0.0456|
45
+ | - stem |N/A |none | 0|acc |0.3914|± |0.0085|
46
+ | - abstract_algebra | 0|none | 0|acc |0.2900|± |0.0456|
47
+ | - anatomy | 0|none | 0|acc |0.4741|± |0.0431|
48
+ | - astronomy | 0|none | 0|acc |0.5263|± |0.0406|
49
+ | - college_biology | 0|none | 0|acc |0.4653|± |0.0417|
50
+ | - college_chemistry | 0|none | 0|acc |0.3800|± |0.0488|
51
+ | - college_computer_science | 0|none | 0|acc |0.4300|± |0.0498|
52
+ | - college_mathematics | 0|none | 0|acc |0.3300|± |0.0473|
53
+ | - college_physics | 0|none | 0|acc |0.2647|± |0.0439|
54
+ | - computer_security | 0|none | 0|acc |0.6600|± |0.0476|
55
+ | - conceptual_physics | 0|none | 0|acc |0.3319|± |0.0308|
56
+ | - electrical_engineering | 0|none | 0|acc |0.4552|± |0.0415|
57
+ | - elementary_mathematics | 0|none | 0|acc |0.3069|± |0.0238|
58
+ | - high_school_biology | 0|none | 0|acc |0.5645|± |0.0282|
59
+ | - high_school_chemistry | 0|none | 0|acc |0.3842|± |0.0342|
60
+ | - high_school_computer_science | 0|none | 0|acc |0.4700|± |0.0502|
61
+ | - high_school_mathematics | 0|none | 0|acc |0.3000|± |0.0279|
62
+ | - high_school_physics | 0|none | 0|acc |0.2252|± |0.0341|
63
+ | - high_school_statistics | 0|none | 0|acc |0.3796|± |0.0331|
64
+ | - machine_learning | 0|none | 0|acc |0.2679|± |0.0420|
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 |0.3892|± |0.0040|
4
+ | - humanities |N/A |none | 0|acc |0.3766|± |0.0069|
5
+ | - formal_logic | 0|none | 0|acc |0.2857|± |0.0404|
6
+ | - high_school_european_history | 0|none | 0|acc |0.4909|± |0.0390|
7
+ | - high_school_us_history | 0|none | 0|acc |0.5196|± |0.0351|
8
+ | - high_school_world_history | 0|none | 0|acc |0.5105|± |0.0325|
9
+ | - international_law | 0|none | 0|acc |0.6364|± |0.0439|
10
+ | - jurisprudence | 0|none | 0|acc |0.4074|± |0.0475|
11
+ | - logical_fallacies | 0|none | 0|acc |0.4356|± |0.0390|
12
+ | - moral_disputes | 0|none | 0|acc |0.4104|± |0.0265|
13
+ | - moral_scenarios | 0|none | 0|acc |0.2436|± |0.0144|
14
+ | - philosophy | 0|none | 0|acc |0.4277|± |0.0281|
15
+ | - prehistory | 0|none | 0|acc |0.4444|± |0.0276|
16
+ | - professional_law | 0|none | 0|acc |0.3259|± |0.0120|
17
+ | - world_religions | 0|none | 0|acc |0.5789|± |0.0379|
18
+ | - other |N/A |none | 0|acc |0.4232|± |0.0088|
19
+ | - business_ethics | 0|none | 0|acc |0.4000|± |0.0492|
20
+ | - clinical_knowledge | 0|none | 0|acc |0.3811|± |0.0299|
21
+ | - college_medicine | 0|none | 0|acc |0.3410|± |0.0361|
22
+ | - global_facts | 0|none | 0|acc |0.2700|± |0.0446|
23
+ | - human_aging | 0|none | 0|acc |0.4081|± |0.0330|
24
+ | - management | 0|none | 0|acc |0.4951|± |0.0495|
25
+ | - marketing | 0|none | 0|acc |0.5726|± |0.0324|
26
+ | - medical_genetics | 0|none | 0|acc |0.3600|± |0.0482|
27
+ | - miscellaneous | 0|none | 0|acc |0.5096|± |0.0179|
28
+ | - nutrition | 0|none | 0|acc |0.4346|± |0.0284|
29
+ | - professional_accounting | 0|none | 0|acc |0.2979|± |0.0273|
30
+ | - professional_medicine | 0|none | 0|acc |0.3456|± |0.0289|
31
+ | - virology | 0|none | 0|acc |0.3976|± |0.0381|
32
+ | - social_sciences |N/A |none | 0|acc |0.4374|± |0.0089|
33
+ | - econometrics | 0|none | 0|acc |0.2456|± |0.0405|
34
+ | - high_school_geography | 0|none | 0|acc |0.3788|± |0.0346|
35
+ | - high_school_government_and_politics| 0|none | 0|acc |0.5648|± |0.0358|
36
+ | - high_school_macroeconomics | 0|none | 0|acc |0.4000|± |0.0248|
37
+ | - high_school_microeconomics | 0|none | 0|acc |0.3487|± |0.0310|
38
+ | - high_school_psychology | 0|none | 0|acc |0.4771|± |0.0214|
39
+ | - human_sexuality | 0|none | 0|acc |0.4656|± |0.0437|
40
+ | - professional_psychology | 0|none | 0|acc |0.4134|± |0.0199|
41
+ | - public_relations | 0|none | 0|acc |0.4455|± |0.0476|
42
+ | - security_studies | 0|none | 0|acc |0.4367|± |0.0318|
43
+ | - sociology | 0|none | 0|acc |0.5224|± |0.0353|
44
+ | - us_foreign_policy | 0|none | 0|acc |0.6000|± |0.0492|
45
+ | - stem |N/A |none | 0|acc |0.3273|± |0.0082|
46
+ | - abstract_algebra | 0|none | 0|acc |0.2300|± |0.0423|
47
+ | - anatomy | 0|none | 0|acc |0.4000|± |0.0423|
48
+ | - astronomy | 0|none | 0|acc |0.4605|± |0.0406|
49
+ | - college_biology | 0|none | 0|acc |0.3611|± |0.0402|
50
+ | - college_chemistry | 0|none | 0|acc |0.2600|± |0.0441|
51
+ | - college_computer_science | 0|none | 0|acc |0.3700|± |0.0485|
52
+ | - college_mathematics | 0|none | 0|acc |0.2300|± |0.0423|
53
+ | - college_physics | 0|none | 0|acc |0.2157|± |0.0409|
54
+ | - computer_security | 0|none | 0|acc |0.5200|± |0.0502|
55
+ | - conceptual_physics | 0|none | 0|acc |0.3362|± |0.0309|
56
+ | - electrical_engineering | 0|none | 0|acc |0.3862|± |0.0406|
57
+ | - elementary_mathematics | 0|none | 0|acc |0.2884|± |0.0233|
58
+ | - high_school_biology | 0|none | 0|acc |0.4645|± |0.0284|
59
+ | - high_school_chemistry | 0|none | 0|acc |0.2709|± |0.0313|
60
+ | - high_school_computer_science | 0|none | 0|acc |0.3600|± |0.0482|
61
+ | - high_school_mathematics | 0|none | 0|acc |0.2556|± |0.0266|
62
+ | - high_school_physics | 0|none | 0|acc |0.2318|± |0.0345|
63
+ | - high_school_statistics | 0|none | 0|acc |0.2407|± |0.0292|
64
+ | - machine_learning | 0|none | 0|acc |0.3393|± |0.0449|
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 |0.3051|± |0.0039|
4
+ | - humanities |N/A |none | 0|acc |0.2891|± |0.0066|
5
+ | - formal_logic | 0|none | 0|acc |0.3095|± |0.0413|
6
+ | - high_school_european_history | 0|none | 0|acc |0.2061|± |0.0316|
7
+ | - high_school_us_history | 0|none | 0|acc |0.4118|± |0.0345|
8
+ | - high_school_world_history | 0|none | 0|acc |0.3586|± |0.0312|
9
+ | - international_law | 0|none | 0|acc |0.3471|± |0.0435|
10
+ | - jurisprudence | 0|none | 0|acc |0.3611|± |0.0464|
11
+ | - logical_fallacies | 0|none | 0|acc |0.2147|± |0.0323|
12
+ | - moral_disputes | 0|none | 0|acc |0.3150|± |0.0250|
13
+ | - moral_scenarios | 0|none | 0|acc |0.2324|± |0.0141|
14
+ | - philosophy | 0|none | 0|acc |0.3376|± |0.0269|
15
+ | - prehistory | 0|none | 0|acc |0.3302|± |0.0262|
16
+ | - professional_law | 0|none | 0|acc |0.2679|± |0.0113|
17
+ | - world_religions | 0|none | 0|acc |0.3626|± |0.0369|
18
+ | - other |N/A |none | 0|acc |0.3251|± |0.0084|
19
+ | - business_ethics | 0|none | 0|acc |0.3200|± |0.0469|
20
+ | - clinical_knowledge | 0|none | 0|acc |0.3170|± |0.0286|
21
+ | - college_medicine | 0|none | 0|acc |0.3295|± |0.0358|
22
+ | - global_facts | 0|none | 0|acc |0.2100|± |0.0409|
23
+ | - human_aging | 0|none | 0|acc |0.2735|± |0.0299|
24
+ | - management | 0|none | 0|acc |0.4078|± |0.0487|
25
+ | - marketing | 0|none | 0|acc |0.3547|± |0.0313|
26
+ | - medical_genetics | 0|none | 0|acc |0.3400|± |0.0476|
27
+ | - miscellaneous | 0|none | 0|acc |0.3257|± |0.0168|
28
+ | - nutrition | 0|none | 0|acc |0.3268|± |0.0269|
29
+ | - professional_accounting | 0|none | 0|acc |0.2660|± |0.0264|
30
+ | - professional_medicine | 0|none | 0|acc |0.3603|± |0.0292|
31
+ | - virology | 0|none | 0|acc |0.4096|± |0.0383|
32
+ | - social_sciences |N/A |none | 0|acc |0.3315|± |0.0084|
33
+ | - econometrics | 0|none | 0|acc |0.2368|± |0.0400|
34
+ | - high_school_geography | 0|none | 0|acc |0.3232|± |0.0333|
35
+ | - high_school_government_and_politics| 0|none | 0|acc |0.3472|± |0.0344|
36
+ | - high_school_macroeconomics | 0|none | 0|acc |0.3231|± |0.0237|
37
+ | - high_school_microeconomics | 0|none | 0|acc |0.2647|± |0.0287|
38
+ | - high_school_psychology | 0|none | 0|acc |0.3541|± |0.0205|
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 |0.3182|± |0.0446|
42
+ | - security_studies | 0|none | 0|acc |0.3551|± |0.0306|
43
+ | - sociology | 0|none | 0|acc |0.4328|± |0.0350|
44
+ | - us_foreign_policy | 0|none | 0|acc |0.4700|± |0.0502|
45
+ | - stem |N/A |none | 0|acc |0.2835|± |0.0080|
46
+ | - abstract_algebra | 0|none | 0|acc |0.2100|± |0.0409|
47
+ | - anatomy | 0|none | 0|acc |0.3333|± |0.0407|
48
+ | - astronomy | 0|none | 0|acc |0.3289|± |0.0382|
49
+ | - college_biology | 0|none | 0|acc |0.3403|± |0.0396|
50
+ | - college_chemistry | 0|none | 0|acc |0.3600|± |0.0482|
51
+ | - college_computer_science | 0|none | 0|acc |0.2900|± |0.0456|
52
+ | - college_mathematics | 0|none | 0|acc |0.2600|± |0.0441|
53
+ | - college_physics | 0|none | 0|acc |0.2647|± |0.0439|
54
+ | - computer_security | 0|none | 0|acc |0.3000|± |0.0461|
55
+ | - conceptual_physics | 0|none | 0|acc |0.3234|± |0.0306|
56
+ | - electrical_engineering | 0|none | 0|acc |0.2897|± |0.0378|
57
+ | - elementary_mathematics | 0|none | 0|acc |0.2698|± |0.0229|
58
+ | - high_school_biology | 0|none | 0|acc |0.3032|± |0.0261|
59
+ | - high_school_chemistry | 0|none | 0|acc |0.1823|± |0.0272|
60
+ | - high_school_computer_science | 0|none | 0|acc |0.2300|± |0.0423|
61
+ | - high_school_mathematics | 0|none | 0|acc |0.2519|± |0.0265|
62
+ | - high_school_physics | 0|none | 0|acc |0.2450|± |0.0351|
63
+ | - high_school_statistics | 0|none | 0|acc |0.3333|± |0.0321|
64
+ | - machine_learning | 0|none | 0|acc |0.2679|± |0.0420|
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 |0.4794|± |0.0041|
4
+ | - humanities |N/A |none | 0|acc |0.4555|± |0.0069|
5
+ | - formal_logic | 0|none | 0|acc |0.2857|± |0.0404|
6
+ | - high_school_european_history | 0|none | 0|acc |0.6182|± |0.0379|
7
+ | - high_school_us_history | 0|none | 0|acc |0.6863|± |0.0326|
8
+ | - high_school_world_history | 0|none | 0|acc |0.6456|± |0.0311|
9
+ | - international_law | 0|none | 0|acc |0.6364|± |0.0439|
10
+ | - jurisprudence | 0|none | 0|acc |0.6019|± |0.0473|
11
+ | - logical_fallacies | 0|none | 0|acc |0.5092|± |0.0393|
12
+ | - moral_disputes | 0|none | 0|acc |0.4682|± |0.0269|
13
+ | - moral_scenarios | 0|none | 0|acc |0.2492|± |0.0145|
14
+ | - philosophy | 0|none | 0|acc |0.5949|± |0.0279|
15
+ | - prehistory | 0|none | 0|acc |0.6049|± |0.0272|
16
+ | - professional_law | 0|none | 0|acc |0.3911|± |0.0125|
17
+ | - world_religions | 0|none | 0|acc |0.7076|± |0.0349|
18
+ | - other |N/A |none | 0|acc |0.5372|± |0.0088|
19
+ | - business_ethics | 0|none | 0|acc |0.5200|± |0.0502|
20
+ | - clinical_knowledge | 0|none | 0|acc |0.4302|± |0.0305|
21
+ | - college_medicine | 0|none | 0|acc |0.4451|± |0.0379|
22
+ | - global_facts | 0|none | 0|acc |0.3300|± |0.0473|
23
+ | - human_aging | 0|none | 0|acc |0.5650|± |0.0333|
24
+ | - management | 0|none | 0|acc |0.6214|± |0.0480|
25
+ | - marketing | 0|none | 0|acc |0.6966|± |0.0301|
26
+ | - medical_genetics | 0|none | 0|acc |0.5000|± |0.0503|
27
+ | - miscellaneous | 0|none | 0|acc |0.6539|± |0.0170|
28
+ | - nutrition | 0|none | 0|acc |0.4967|± |0.0286|
29
+ | - professional_accounting | 0|none | 0|acc |0.4043|± |0.0293|
30
+ | - professional_medicine | 0|none | 0|acc |0.5110|± |0.0304|
31
+ | - virology | 0|none | 0|acc |0.4398|± |0.0386|
32
+ | - social_sciences |N/A |none | 0|acc |0.5522|± |0.0088|
33
+ | - econometrics | 0|none | 0|acc |0.2105|± |0.0384|
34
+ | - high_school_geography | 0|none | 0|acc |0.5455|± |0.0355|
35
+ | - high_school_government_and_politics| 0|none | 0|acc |0.7047|± |0.0329|
36
+ | - high_school_macroeconomics | 0|none | 0|acc |0.4615|± |0.0253|
37
+ | - high_school_microeconomics | 0|none | 0|acc |0.4874|± |0.0325|
38
+ | - high_school_psychology | 0|none | 0|acc |0.6275|± |0.0207|
39
+ | - human_sexuality | 0|none | 0|acc |0.5954|± |0.0430|
40
+ | - professional_psychology | 0|none | 0|acc |0.5033|± |0.0202|
41
+ | - public_relations | 0|none | 0|acc |0.5273|± |0.0478|
42
+ | - security_studies | 0|none | 0|acc |0.5837|± |0.0316|
43
+ | - sociology | 0|none | 0|acc |0.6716|± |0.0332|
44
+ | - us_foreign_policy | 0|none | 0|acc |0.7100|± |0.0456|
45
+ | - stem |N/A |none | 0|acc |0.3873|± |0.0085|
46
+ | - abstract_algebra | 0|none | 0|acc |0.2700|± |0.0446|
47
+ | - anatomy | 0|none | 0|acc |0.4667|± |0.0431|
48
+ | - astronomy | 0|none | 0|acc |0.5000|± |0.0407|
49
+ | - college_biology | 0|none | 0|acc |0.4931|± |0.0418|
50
+ | - college_chemistry | 0|none | 0|acc |0.4000|± |0.0492|
51
+ | - college_computer_science | 0|none | 0|acc |0.4200|± |0.0496|
52
+ | - college_mathematics | 0|none | 0|acc |0.2800|± |0.0451|
53
+ | - college_physics | 0|none | 0|acc |0.3039|± |0.0458|
54
+ | - computer_security | 0|none | 0|acc |0.6400|± |0.0482|
55
+ | - conceptual_physics | 0|none | 0|acc |0.3702|± |0.0316|
56
+ | - electrical_engineering | 0|none | 0|acc |0.4828|± |0.0416|
57
+ | - elementary_mathematics | 0|none | 0|acc |0.2910|± |0.0234|
58
+ | - high_school_biology | 0|none | 0|acc |0.5710|± |0.0282|
59
+ | - high_school_chemistry | 0|none | 0|acc |0.3498|± |0.0336|
60
+ | - high_school_computer_science | 0|none | 0|acc |0.4300|± |0.0498|
61
+ | - high_school_mathematics | 0|none | 0|acc |0.2593|± |0.0267|
62
+ | - high_school_physics | 0|none | 0|acc |0.2781|± |0.0366|
63
+ | - high_school_statistics | 0|none | 0|acc |0.3657|± |0.0328|
64
+ | - machine_learning | 0|none | 0|acc |0.2679|± |0.0420|
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 |0.4765|± |0.0041|
4
+ | - humanities |N/A |none | 0|acc |0.4499|± |0.0069|
5
+ | - formal_logic | 0|none | 0|acc |0.2857|± |0.0404|
6
+ | - high_school_european_history | 0|none | 0|acc |0.6545|± |0.0371|
7
+ | - high_school_us_history | 0|none | 0|acc |0.6520|± |0.0334|
8
+ | - high_school_world_history | 0|none | 0|acc |0.6582|± |0.0309|
9
+ | - international_law | 0|none | 0|acc |0.6198|± |0.0443|
10
+ | - jurisprudence | 0|none | 0|acc |0.5278|± |0.0483|
11
+ | - logical_fallacies | 0|none | 0|acc |0.4847|± |0.0393|
12
+ | - moral_disputes | 0|none | 0|acc |0.5000|± |0.0269|
13
+ | - moral_scenarios | 0|none | 0|acc |0.2380|± |0.0142|
14
+ | - philosophy | 0|none | 0|acc |0.5916|± |0.0279|
15
+ | - prehistory | 0|none | 0|acc |0.5741|± |0.0275|
16
+ | - professional_law | 0|none | 0|acc |0.3931|± |0.0125|
17
+ | - world_religions | 0|none | 0|acc |0.6667|± |0.0362|
18
+ | - other |N/A |none | 0|acc |0.5291|± |0.0087|
19
+ | - business_ethics | 0|none | 0|acc |0.5400|± |0.0501|
20
+ | - clinical_knowledge | 0|none | 0|acc |0.4340|± |0.0305|
21
+ | - college_medicine | 0|none | 0|acc |0.4624|± |0.0380|
22
+ | - global_facts | 0|none | 0|acc |0.2800|± |0.0451|
23
+ | - human_aging | 0|none | 0|acc |0.5112|± |0.0335|
24
+ | - management | 0|none | 0|acc |0.6505|± |0.0472|
25
+ | - marketing | 0|none | 0|acc |0.6923|± |0.0302|
26
+ | - medical_genetics | 0|none | 0|acc |0.5100|± |0.0502|
27
+ | - miscellaneous | 0|none | 0|acc |0.6501|± |0.0171|
28
+ | - nutrition | 0|none | 0|acc |0.5000|± |0.0286|
29
+ | - professional_accounting | 0|none | 0|acc |0.3546|± |0.0285|
30
+ | - professional_medicine | 0|none | 0|acc |0.5037|± |0.0304|
31
+ | - virology | 0|none | 0|acc |0.4458|± |0.0387|
32
+ | - social_sciences |N/A |none | 0|acc |0.5518|± |0.0088|
33
+ | - econometrics | 0|none | 0|acc |0.2456|± |0.0405|
34
+ | - high_school_geography | 0|none | 0|acc |0.5606|± |0.0354|
35
+ | - high_school_government_and_politics| 0|none | 0|acc |0.6839|± |0.0336|
36
+ | - high_school_macroeconomics | 0|none | 0|acc |0.4692|± |0.0253|
37
+ | - high_school_microeconomics | 0|none | 0|acc |0.5042|± |0.0325|
38
+ | - high_school_psychology | 0|none | 0|acc |0.6073|± |0.0209|
39
+ | - human_sexuality | 0|none | 0|acc |0.6107|± |0.0428|
40
+ | - professional_psychology | 0|none | 0|acc |0.4951|± |0.0202|
41
+ | - public_relations | 0|none | 0|acc |0.5364|± |0.0478|
42
+ | - security_studies | 0|none | 0|acc |0.5959|± |0.0314|
43
+ | - sociology | 0|none | 0|acc |0.6617|± |0.0335|
44
+ | - us_foreign_policy | 0|none | 0|acc |0.7200|± |0.0451|
45
+ | - stem |N/A |none | 0|acc |0.3907|± |0.0085|
46
+ | - abstract_algebra | 0|none | 0|acc |0.2900|± |0.0456|
47
+ | - anatomy | 0|none | 0|acc |0.4889|± |0.0432|
48
+ | - astronomy | 0|none | 0|acc |0.5132|± |0.0407|
49
+ | - college_biology | 0|none | 0|acc |0.4792|± |0.0418|
50
+ | - college_chemistry | 0|none | 0|acc |0.3700|± |0.0485|
51
+ | - college_computer_science | 0|none | 0|acc |0.4200|± |0.0496|
52
+ | - college_mathematics | 0|none | 0|acc |0.3500|± |0.0479|
53
+ | - college_physics | 0|none | 0|acc |0.2941|± |0.0453|
54
+ | - computer_security | 0|none | 0|acc |0.6200|± |0.0488|
55
+ | - conceptual_physics | 0|none | 0|acc |0.3106|± |0.0303|
56
+ | - electrical_engineering | 0|none | 0|acc |0.4621|± |0.0415|
57
+ | - elementary_mathematics | 0|none | 0|acc |0.3148|± |0.0239|
58
+ | - high_school_biology | 0|none | 0|acc |0.5581|± |0.0283|
59
+ | - high_school_chemistry | 0|none | 0|acc |0.3153|± |0.0327|
60
+ | - high_school_computer_science | 0|none | 0|acc |0.4700|± |0.0502|
61
+ | - high_school_mathematics | 0|none | 0|acc |0.2704|± |0.0271|
62
+ | - high_school_physics | 0|none | 0|acc |0.2583|± |0.0357|
63
+ | - high_school_statistics | 0|none | 0|acc |0.3981|± |0.0334|
64
+ | - machine_learning | 0|none | 0|acc |0.3839|± |0.0462|
pytorch_model-00001-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34899312119642f0f76b9ee62530b019054ec714e494c3ef52e64bc5c20f12f
3
+ size 1947867050
pytorch_model-00002-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0aeafc2e7b7cc6d21c4aa91759a01e711eca47af17ac83966eec4703f783d7d
3
+ size 1903351962
pytorch_model-00003-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda3984bedd07b1d4517b193ee3b6dc5ad7d3bf09e4fbdfffd6158e47f86edad
3
+ size 1903351962
pytorch_model-00004-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e0bed05a1a994b2640f688195dbfd1a9884ccb58ca97443a0245e2a184d4be
3
+ size 1903352026
pytorch_model-00005-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f799df4c33c06af54254c5c18c27d6f5759902b4682ce6c135c925086e050757
3
+ size 1903352154
pytorch_model-00006-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aead492ea253babdd6afc50173b97fd93eb39f601633f91c75894dca21e36b7
3
+ size 1903352154
pytorch_model-00007-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e39eef10730837dc4c7f594df71f277d2a7695156110ada7642339ac6fb09e
3
+ size 1903352154
pytorch_model-00008-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b86f7821996f6f4fabcc6816a4974284128121069c3211611d59a7acbb66297
3
+ size 1903352154
pytorch_model-00009-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d46cab153ca34b03605442e60a5a4551dfc69172a387e9b738f33e1f3ec32417
3
+ size 1903352154
pytorch_model-00010-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0899930a38f0d6470924d263bba608b5da22637254aaf66fc3a6b9ac33259fa
3
+ size 1903352154
pytorch_model-00011-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46130265eefb3e286aded205209aa0e60657e1aecc3a35141c3be2f02a80a088
3
+ size 1903352154
pytorch_model-00012-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96d35d3cf34cd58f567bd59aca4ace6deb76ae204b92ed53c646eb18da38673b
3
+ size 1903352154
pytorch_model-00013-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cfc206e7ae460d93d1edc053a9d67503eec7a20b1f2d6fe9bba8aa7a613e9d7
3
+ size 1903352154
pytorch_model-00014-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46dd577203909db1affe17179cdbafc4e2687723b820413d7229ef56cdfa54b
3
+ size 1245308948
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:b990405cae244b69eec5ffb8dad2eced6f03031735f7a75b63b35f1507434917
3
+ size 26033472938
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
+ }