Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +4 -3
- eval.txt +265 -0
- generation_config.json +1 -1
- model-00001-of-00007.safetensors +2 -2
- model-00002-of-00007.safetensors +2 -2
- model-00003-of-00007.safetensors +2 -2
- model-00004-of-00007.safetensors +2 -2
- model-00005-of-00007.safetensors +2 -2
- model-00006-of-00007.safetensors +2 -2
- model-00007-of-00007.safetensors +1 -1
- tokenizer.json +0 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
|
@@ -16,11 +16,12 @@
|
|
| 16 |
"num_hidden_layers": 60,
|
| 17 |
"num_key_value_heads": 4,
|
| 18 |
"rms_norm_eps": 1e-06,
|
|
|
|
| 19 |
"rope_theta": 1000000.0,
|
| 20 |
"sliding_window": null,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
-
"torch_dtype": "
|
| 23 |
-
"transformers_version": "4.
|
| 24 |
"use_cache": false,
|
| 25 |
"use_sliding_window": false,
|
| 26 |
"vocab_size": 152064
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/data/private/models/Rabbit-15B/checkpoint-2344",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
|
|
|
| 16 |
"num_hidden_layers": 60,
|
| 17 |
"num_key_value_heads": 4,
|
| 18 |
"rms_norm_eps": 1e-06,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
"rope_theta": 1000000.0,
|
| 21 |
"sliding_window": null,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.45.0",
|
| 25 |
"use_cache": false,
|
| 26 |
"use_sliding_window": false,
|
| 27 |
"vocab_size": 152064
|
eval.txt
ADDED
|
@@ -0,0 +1,265 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|Tasks|Version| Filter |n-shot| Metric | |Value | |Stderr|
|
| 2 |
+
|-----|------:|----------------|-----:|-----------|---|-----:|---|-----:|
|
| 3 |
+
|gsm8k| 3|flexible-extract| 5|exact_match|↑ |0.7854|± |0.0113|
|
| 4 |
+
| | |strict-match | 5|exact_match|↑ |0.7597|± |0.0118|
|
| 5 |
+
|
| 6 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 7 |
+
|---------|------:|------|-----:|--------|---|-----:|---|-----:|
|
| 8 |
+
|hellaswag| 1|none | 5|acc |↑ |0.5579|± |0.0050|
|
| 9 |
+
| | |none | 5|acc_norm|↑ |0.7380|± |0.0044|
|
| 10 |
+
|
| 11 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 12 |
+
|----------------|------:|------|-----:|--------|---|-----:|---|------|
|
| 13 |
+
|kobest_boolq | 1|none | 0|acc |↑ |0.9195|± |0.0073|
|
| 14 |
+
| | |none | 0|f1 |↑ |0.9195|± | N/A|
|
| 15 |
+
|kobest_copa | 1|none | 0|acc |↑ |0.6670|± |0.0149|
|
| 16 |
+
| | |none | 0|f1 |↑ |0.6664|± | N/A|
|
| 17 |
+
|kobest_hellaswag| 1|none | 0|acc |↑ |0.4380|± |0.0222|
|
| 18 |
+
| | |none | 0|acc_norm|↑ |0.5600|± |0.0222|
|
| 19 |
+
| | |none | 0|f1 |↑ |0.4349|± | N/A|
|
| 20 |
+
|kobest_sentineg | 1|none | 0|acc |↑ |0.6650|± |0.0237|
|
| 21 |
+
| | |none | 0|f1 |↑ |0.6233|± | N/A|
|
| 22 |
+
|kobest_wic | 1|none | 0|acc |↑ |0.6500|± |0.0134|
|
| 23 |
+
| | |none | 0|f1 |↑ |0.6479|± | N/A|
|
| 24 |
+
|
| 25 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 26 |
+
|----------------|------:|------|-----:|--------|---|-----:|---|------|
|
| 27 |
+
|kobest_boolq | 1|none | 5|acc |↑ |0.9145|± |0.0075|
|
| 28 |
+
| | |none | 5|f1 |↑ |0.9145|± | N/A|
|
| 29 |
+
|kobest_copa | 1|none | 5|acc |↑ |0.7050|± |0.0144|
|
| 30 |
+
| | |none | 5|f1 |↑ |0.7045|± | N/A|
|
| 31 |
+
|kobest_hellaswag| 1|none | 5|acc |↑ |0.4600|± |0.0223|
|
| 32 |
+
| | |none | 5|acc_norm|↑ |0.5540|± |0.0223|
|
| 33 |
+
| | |none | 5|f1 |↑ |0.4564|± | N/A|
|
| 34 |
+
|kobest_sentineg | 1|none | 5|acc |↑ |0.9496|± |0.0110|
|
| 35 |
+
| | |none | 5|f1 |↑ |0.9496|± | N/A|
|
| 36 |
+
|kobest_wic | 1|none | 5|acc |↑ |0.7294|± |0.0125|
|
| 37 |
+
| | |none | 5|f1 |↑ |0.7258|± | N/A|
|
| 38 |
+
|
| 39 |
+
| Tasks |Version| Filter |n-shot| Metric | |Value | |Stderr|
|
| 40 |
+
|------------------------------------------------------------|------:|----------|-----:|-----------|---|-----:|---|-----:|
|
| 41 |
+
|kmmlu_direct_accounting | 2|none | 5|exact_match|↑ |0.5200|± |0.0502|
|
| 42 |
+
|kmmlu_direct_agricultural_sciences | 2|none | 5|exact_match|↑ |0.3700|± |0.0153|
|
| 43 |
+
|kmmlu_direct_aviation_engineering_and_maintenance | 2|none | 5|exact_match|↑ |0.4630|± |0.0158|
|
| 44 |
+
|kmmlu_direct_biology | 2|none | 5|exact_match|↑ |0.3680|± |0.0153|
|
| 45 |
+
|kmmlu_direct_chemical_engineering | 2|none | 5|exact_match|↑ |0.4700|± |0.0158|
|
| 46 |
+
|kmmlu_direct_chemistry | 2|none | 5|exact_match|↑ |0.4733|± |0.0204|
|
| 47 |
+
|kmmlu_direct_civil_engineering | 2|none | 5|exact_match|↑ |0.3630|± |0.0152|
|
| 48 |
+
|kmmlu_direct_computer_science | 2|none | 5|exact_match|↑ |0.7320|± |0.0140|
|
| 49 |
+
|kmmlu_direct_construction | 2|none | 5|exact_match|↑ |0.3620|± |0.0152|
|
| 50 |
+
|kmmlu_direct_criminal_law | 2|none | 5|exact_match|↑ |0.4050|± |0.0348|
|
| 51 |
+
|kmmlu_direct_ecology | 2|none | 5|exact_match|↑ |0.4860|± |0.0158|
|
| 52 |
+
|kmmlu_direct_economics | 2|none | 5|exact_match|↑ |0.6077|± |0.0430|
|
| 53 |
+
|kmmlu_direct_education | 2|none | 5|exact_match|↑ |0.7100|± |0.0456|
|
| 54 |
+
|kmmlu_direct_electrical_engineering | 2|none | 5|exact_match|↑ |0.3210|± |0.0148|
|
| 55 |
+
|kmmlu_direct_electronics_engineering | 2|none | 5|exact_match|↑ |0.5450|± |0.0158|
|
| 56 |
+
|kmmlu_direct_energy_management | 2|none | 5|exact_match|↑ |0.3920|± |0.0154|
|
| 57 |
+
|kmmlu_direct_environmental_science | 2|none | 5|exact_match|↑ |0.3090|± |0.0146|
|
| 58 |
+
|kmmlu_direct_fashion | 2|none | 5|exact_match|↑ |0.4800|± |0.0158|
|
| 59 |
+
|kmmlu_direct_food_processing | 2|none | 5|exact_match|↑ |0.4400|± |0.0157|
|
| 60 |
+
|kmmlu_direct_gas_technology_and_engineering | 2|none | 5|exact_match|↑ |0.3590|± |0.0152|
|
| 61 |
+
|kmmlu_direct_geomatics | 2|none | 5|exact_match|↑ |0.3890|± |0.0154|
|
| 62 |
+
|kmmlu_direct_health | 2|none | 5|exact_match|↑ |0.6200|± |0.0488|
|
| 63 |
+
|kmmlu_direct_industrial_engineer | 2|none | 5|exact_match|↑ |0.4780|± |0.0158|
|
| 64 |
+
|kmmlu_direct_information_technology | 2|none | 5|exact_match|↑ |0.7130|± |0.0143|
|
| 65 |
+
|kmmlu_direct_interior_architecture_and_design | 2|none | 5|exact_match|↑ |0.5970|± |0.0155|
|
| 66 |
+
|kmmlu_direct_korean_history | 2|none | 5|exact_match|↑ |0.3500|± |0.0479|
|
| 67 |
+
|kmmlu_direct_law | 2|none | 5|exact_match|↑ |0.4640|± |0.0158|
|
| 68 |
+
|kmmlu_direct_machine_design_and_manufacturing | 2|none | 5|exact_match|↑ |0.4800|± |0.0158|
|
| 69 |
+
|kmmlu_direct_management | 2|none | 5|exact_match|↑ |0.6190|± |0.0154|
|
| 70 |
+
|kmmlu_direct_maritime_engineering | 2|none | 5|exact_match|↑ |0.4750|± |0.0204|
|
| 71 |
+
|kmmlu_direct_marketing | 2|none | 5|exact_match|↑ |0.8010|± |0.0126|
|
| 72 |
+
|kmmlu_direct_materials_engineering | 2|none | 5|exact_match|↑ |0.4960|± |0.0158|
|
| 73 |
+
|kmmlu_direct_math | 2|none | 5|exact_match|↑ |0.3600|± |0.0278|
|
| 74 |
+
|kmmlu_direct_mechanical_engineering | 2|none | 5|exact_match|↑ |0.3960|± |0.0155|
|
| 75 |
+
|kmmlu_direct_nondestructive_testing | 2|none | 5|exact_match|↑ |0.4500|± |0.0157|
|
| 76 |
+
|kmmlu_direct_patent | 2|none | 5|exact_match|↑ |0.4000|± |0.0492|
|
| 77 |
+
|kmmlu_direct_political_science_and_sociology | 2|none | 5|exact_match|↑ |0.5600|± |0.0287|
|
| 78 |
+
|kmmlu_direct_psychology | 2|none | 5|exact_match|↑ |0.4790|± |0.0158|
|
| 79 |
+
|kmmlu_direct_public_safety | 2|none | 5|exact_match|↑ |0.3710|± |0.0153|
|
| 80 |
+
|kmmlu_direct_railway_and_automotive_engineering | 2|none | 5|exact_match|↑ |0.3520|± |0.0151|
|
| 81 |
+
|kmmlu_direct_real_estate | 2|none | 5|exact_match|↑ |0.4750|± |0.0354|
|
| 82 |
+
|kmmlu_direct_refrigerating_machinery | 2|none | 5|exact_match|↑ |0.3710|± |0.0153|
|
| 83 |
+
|kmmlu_direct_social_welfare | 2|none | 5|exact_match|↑ |0.6170|± |0.0154|
|
| 84 |
+
|kmmlu_direct_taxation | 2|none | 5|exact_match|↑ |0.3950|± |0.0347|
|
| 85 |
+
|kmmlu_direct_telecommunications_and_wireless_technology | 2|none | 5|exact_match|↑ |0.6150|± |0.0154|
|
| 86 |
+
|kmmlu_hard_accounting | 2|none | 5|acc |↑ |0.2826|± |0.0671|
|
| 87 |
+
| | |none | 5|acc_norm |↑ |0.2826|± |0.0671|
|
| 88 |
+
|kmmlu_hard_agricultural_sciences | 2|none | 5|acc |↑ |0.1400|± |0.0349|
|
| 89 |
+
| | |none | 5|acc_norm |↑ |0.1400|± |0.0349|
|
| 90 |
+
|kmmlu_hard_aviation_engineering_and_maintenance | 2|none | 5|acc |↑ |0.2200|± |0.0416|
|
| 91 |
+
| | |none | 5|acc_norm |↑ |0.2200|± |0.0416|
|
| 92 |
+
|kmmlu_hard_biology | 2|none | 5|acc |↑ |0.1800|± |0.0386|
|
| 93 |
+
| | |none | 5|acc_norm |↑ |0.1800|± |0.0386|
|
| 94 |
+
|kmmlu_hard_chemical_engineering | 2|none | 5|acc |↑ |0.1500|± |0.0359|
|
| 95 |
+
| | |none | 5|acc_norm |↑ |0.1500|± |0.0359|
|
| 96 |
+
|kmmlu_hard_chemistry | 2|none | 5|acc |↑ |0.3000|± |0.0461|
|
| 97 |
+
| | |none | 5|acc_norm |↑ |0.3000|± |0.0461|
|
| 98 |
+
|kmmlu_hard_civil_engineering | 2|none | 5|acc |↑ |0.1800|± |0.0386|
|
| 99 |
+
| | |none | 5|acc_norm |↑ |0.1800|± |0.0386|
|
| 100 |
+
|kmmlu_hard_computer_science | 2|none | 5|acc |↑ |0.2400|± |0.0429|
|
| 101 |
+
| | |none | 5|acc_norm |↑ |0.2400|± |0.0429|
|
| 102 |
+
|kmmlu_hard_construction | 2|none | 5|acc |↑ |0.1800|± |0.0386|
|
| 103 |
+
| | |none | 5|acc_norm |↑ |0.1800|± |0.0386|
|
| 104 |
+
|kmmlu_hard_cot_accounting | 2|get-answer| 5|exact_match|↑ |0.2391|± |0.0636|
|
| 105 |
+
|kmmlu_hard_cot_agricultural_sciences | 2|get-answer| 5|exact_match|↑ |0.0900|± |0.0288|
|
| 106 |
+
|kmmlu_hard_cot_aviation_engineering_and_maintenance | 2|get-answer| 5|exact_match|↑ |0.2800|± |0.0451|
|
| 107 |
+
|kmmlu_hard_cot_biology | 2|get-answer| 5|exact_match|↑ |0.1200|± |0.0327|
|
| 108 |
+
|kmmlu_hard_cot_chemical_engineering | 2|get-answer| 5|exact_match|↑ |0.2100|± |0.0409|
|
| 109 |
+
|kmmlu_hard_cot_chemistry | 2|get-answer| 5|exact_match|↑ |0.3100|± |0.0465|
|
| 110 |
+
|kmmlu_hard_cot_civil_engineering | 2|get-answer| 5|exact_match|↑ |0.2400|± |0.0429|
|
| 111 |
+
|kmmlu_hard_cot_computer_science | 2|get-answer| 5|exact_match|↑ |0.2300|± |0.0423|
|
| 112 |
+
|kmmlu_hard_cot_construction | 2|get-answer| 5|exact_match|↑ |0.2100|± |0.0409|
|
| 113 |
+
|kmmlu_hard_cot_criminal_law | 2|get-answer| 5|exact_match|↑ |0.1100|± |0.0314|
|
| 114 |
+
|kmmlu_hard_cot_ecology | 2|get-answer| 5|exact_match|↑ |0.1300|± |0.0338|
|
| 115 |
+
|kmmlu_hard_cot_economics | 2|get-answer| 5|exact_match|↑ |0.1429|± |0.0546|
|
| 116 |
+
|kmmlu_hard_cot_education | 2|get-answer| 5|exact_match|↑ |0.0435|± |0.0435|
|
| 117 |
+
|kmmlu_hard_cot_electrical_engineering | 2|get-answer| 5|exact_match|↑ |0.2200|± |0.0416|
|
| 118 |
+
|kmmlu_hard_cot_electronics_engineering | 2|get-answer| 5|exact_match|↑ |0.3500|± |0.0479|
|
| 119 |
+
|kmmlu_hard_cot_energy_management | 2|get-answer| 5|exact_match|↑ |0.3300|± |0.0473|
|
| 120 |
+
|kmmlu_hard_cot_environmental_science | 2|get-answer| 5|exact_match|↑ |0.1500|± |0.0359|
|
| 121 |
+
|kmmlu_hard_cot_fashion | 2|get-answer| 5|exact_match|↑ |0.2200|± |0.0416|
|
| 122 |
+
|kmmlu_hard_cot_food_processing | 2|get-answer| 5|exact_match|↑ |0.2100|± |0.0409|
|
| 123 |
+
|kmmlu_hard_cot_gas_technology_and_engineering | 2|get-answer| 5|exact_match|↑ |0.3200|± |0.0469|
|
| 124 |
+
|kmmlu_hard_cot_geomatics | 2|get-answer| 5|exact_match|↑ |0.1900|± |0.0394|
|
| 125 |
+
|kmmlu_hard_cot_health | 2|get-answer| 5|exact_match|↑ |0.2609|± |0.0936|
|
| 126 |
+
|kmmlu_hard_cot_industrial_engineer | 2|get-answer| 5|exact_match|↑ |0.1300|± |0.0338|
|
| 127 |
+
|kmmlu_hard_cot_information_technology | 2|get-answer| 5|exact_match|↑ |0.3600|± |0.0482|
|
| 128 |
+
|kmmlu_hard_cot_interior_architecture_and_design | 2|get-answer| 5|exact_match|↑ |0.1600|± |0.0368|
|
| 129 |
+
|kmmlu_hard_cot_korean_history | 2|get-answer| 5|exact_match|↑ |0.1364|± |0.0523|
|
| 130 |
+
|kmmlu_hard_cot_law | 2|get-answer| 5|exact_match|↑ |0.1500|± |0.0359|
|
| 131 |
+
|kmmlu_hard_cot_machine_design_and_manufacturing | 2|get-answer| 5|exact_match|↑ |0.3000|± |0.0461|
|
| 132 |
+
|kmmlu_hard_cot_management | 2|get-answer| 5|exact_match|↑ |0.1900|± |0.0394|
|
| 133 |
+
|kmmlu_hard_cot_maritime_engineering | 2|get-answer| 5|exact_match|↑ |0.2000|± |0.0402|
|
| 134 |
+
|kmmlu_hard_cot_marketing | 2|get-answer| 5|exact_match|↑ |0.2000|± |0.0402|
|
| 135 |
+
|kmmlu_hard_cot_materials_engineering | 2|get-answer| 5|exact_match|↑ |0.1500|± |0.0359|
|
| 136 |
+
|kmmlu_hard_cot_math | 2|get-answer| 5|exact_match|↑ |0.3600|± |0.0482|
|
| 137 |
+
|kmmlu_hard_cot_mechanical_engineering | 2|get-answer| 5|exact_match|↑ |0.2600|± |0.0441|
|
| 138 |
+
|kmmlu_hard_cot_nondestructive_testing | 2|get-answer| 5|exact_match|↑ |0.3000|± |0.0461|
|
| 139 |
+
|kmmlu_hard_cot_patent | 2|get-answer| 5|exact_match|↑ |0.2549|± |0.0616|
|
| 140 |
+
|kmmlu_hard_cot_political_science_and_sociology | 2|get-answer| 5|exact_match|↑ |0.0889|± |0.0302|
|
| 141 |
+
|kmmlu_hard_cot_psychology | 2|get-answer| 5|exact_match|↑ |0.1300|± |0.0338|
|
| 142 |
+
|kmmlu_hard_cot_public_safety | 2|get-answer| 5|exact_match|↑ |0.1700|± |0.0378|
|
| 143 |
+
|kmmlu_hard_cot_railway_and_automotive_engineering | 2|get-answer| 5|exact_match|↑ |0.1700|± |0.0378|
|
| 144 |
+
|kmmlu_hard_cot_real_estate | 2|get-answer| 5|exact_match|↑ |0.2472|± |0.0460|
|
| 145 |
+
|kmmlu_hard_cot_refrigerating_machinery | 2|get-answer| 5|exact_match|↑ |0.3000|± |0.0461|
|
| 146 |
+
|kmmlu_hard_cot_social_welfare | 2|get-answer| 5|exact_match|↑ |0.3700|± |0.0485|
|
| 147 |
+
|kmmlu_hard_cot_taxation | 2|get-answer| 5|exact_match|↑ |0.1979|± |0.0409|
|
| 148 |
+
|kmmlu_hard_cot_telecommunications_and_wireless_technology | 2|get-answer| 5|exact_match|↑ |0.2900|± |0.0456|
|
| 149 |
+
|kmmlu_hard_criminal_law | 2|none | 5|acc |↑ |0.2400|± |0.0429|
|
| 150 |
+
| | |none | 5|acc_norm |↑ |0.2400|± |0.0429|
|
| 151 |
+
|kmmlu_hard_direct_accounting | 2|none | 5|exact_match|↑ |0.3043|± |0.0686|
|
| 152 |
+
|kmmlu_hard_direct_agricultural_sciences | 2|none | 5|exact_match|↑ |0.1400|± |0.0349|
|
| 153 |
+
|kmmlu_hard_direct_aviation_engineering_and_maintenance | 2|none | 5|exact_match|↑ |0.2200|± |0.0416|
|
| 154 |
+
|kmmlu_hard_direct_biology | 2|none | 5|exact_match|↑ |0.1900|± |0.0394|
|
| 155 |
+
|kmmlu_hard_direct_chemical_engineering | 2|none | 5|exact_match|↑ |0.1600|± |0.0368|
|
| 156 |
+
|kmmlu_hard_direct_chemistry | 2|none | 5|exact_match|↑ |0.2900|± |0.0456|
|
| 157 |
+
|kmmlu_hard_direct_civil_engineering | 2|none | 5|exact_match|↑ |0.1800|± |0.0386|
|
| 158 |
+
|kmmlu_hard_direct_computer_science | 2|none | 5|exact_match|↑ |0.2400|± |0.0429|
|
| 159 |
+
|kmmlu_hard_direct_construction | 2|none | 5|exact_match|↑ |0.1700|± |0.0378|
|
| 160 |
+
|kmmlu_hard_direct_criminal_law | 2|none | 5|exact_match|↑ |0.2400|± |0.0429|
|
| 161 |
+
|kmmlu_hard_direct_ecology | 2|none | 5|exact_match|↑ |0.1500|± |0.0359|
|
| 162 |
+
|kmmlu_hard_direct_economics | 2|none | 5|exact_match|↑ |0.2857|± |0.0706|
|
| 163 |
+
|kmmlu_hard_direct_education | 2|none | 5|exact_match|↑ |0.3478|± |0.1015|
|
| 164 |
+
|kmmlu_hard_direct_electrical_engineering | 2|none | 5|exact_match|↑ |0.1700|± |0.0378|
|
| 165 |
+
|kmmlu_hard_direct_electronics_engineering | 2|none | 5|exact_match|↑ |0.2500|± |0.0435|
|
| 166 |
+
|kmmlu_hard_direct_energy_management | 2|none | 5|exact_match|↑ |0.2100|± |0.0409|
|
| 167 |
+
|kmmlu_hard_direct_environmental_science | 2|none | 5|exact_match|↑ |0.2000|± |0.0402|
|
| 168 |
+
|kmmlu_hard_direct_fashion | 2|none | 5|exact_match|↑ |0.2300|± |0.0423|
|
| 169 |
+
|kmmlu_hard_direct_food_processing | 2|none | 5|exact_match|↑ |0.1800|± |0.0386|
|
| 170 |
+
|kmmlu_hard_direct_gas_technology_and_engineering | 2|none | 5|exact_match|↑ |0.1100|± |0.0314|
|
| 171 |
+
|kmmlu_hard_direct_geomatics | 2|none | 5|exact_match|↑ |0.2200|± |0.0416|
|
| 172 |
+
|kmmlu_hard_direct_health | 2|none | 5|exact_match|↑ |0.1739|± |0.0808|
|
| 173 |
+
|kmmlu_hard_direct_industrial_engineer | 2|none | 5|exact_match|↑ |0.1900|± |0.0394|
|
| 174 |
+
|kmmlu_hard_direct_information_technology | 2|none | 5|exact_match|↑ |0.3200|± |0.0469|
|
| 175 |
+
|kmmlu_hard_direct_interior_architecture_and_design | 2|none | 5|exact_match|↑ |0.2100|± |0.0409|
|
| 176 |
+
|kmmlu_hard_direct_korean_history | 2|none | 5|exact_match|↑ |0.1591|± |0.0558|
|
| 177 |
+
|kmmlu_hard_direct_law | 2|none | 5|exact_match|↑ |0.1700|± |0.0378|
|
| 178 |
+
|kmmlu_hard_direct_machine_design_and_manufacturing | 2|none | 5|exact_match|↑ |0.1700|± |0.0378|
|
| 179 |
+
|kmmlu_hard_direct_management | 2|none | 5|exact_match|↑ |0.3100|± |0.0465|
|
| 180 |
+
|kmmlu_hard_direct_maritime_engineering | 2|none | 5|exact_match|↑ |0.2300|± |0.0423|
|
| 181 |
+
|kmmlu_hard_direct_marketing | 2|none | 5|exact_match|↑ |0.3300|± |0.0473|
|
| 182 |
+
|kmmlu_hard_direct_materials_engineering | 2|none | 5|exact_match|↑ |0.1700|± |0.0378|
|
| 183 |
+
|kmmlu_hard_direct_math | 2|none | 5|exact_match|↑ |0.3100|± |0.0465|
|
| 184 |
+
|kmmlu_hard_direct_mechanical_engineering | 2|none | 5|exact_match|↑ |0.1700|± |0.0378|
|
| 185 |
+
|kmmlu_hard_direct_nondestructive_testing | 2|none | 5|exact_match|↑ |0.1300|± |0.0338|
|
| 186 |
+
|kmmlu_hard_direct_patent | 2|none | 5|exact_match|↑ |0.3137|± |0.0656|
|
| 187 |
+
|kmmlu_hard_direct_political_science_and_sociology | 2|none | 5|exact_match|↑ |0.2444|± |0.0456|
|
| 188 |
+
|kmmlu_hard_direct_psychology | 2|none | 5|exact_match|↑ |0.2600|± |0.0441|
|
| 189 |
+
|kmmlu_hard_direct_public_safety | 2|none | 5|exact_match|↑ |0.1500|± |0.0359|
|
| 190 |
+
|kmmlu_hard_direct_railway_and_automotive_engineering | 2|none | 5|exact_match|↑ |0.1800|± |0.0386|
|
| 191 |
+
|kmmlu_hard_direct_real_estate | 2|none | 5|exact_match|↑ |0.2247|± |0.0445|
|
| 192 |
+
|kmmlu_hard_direct_refrigerating_machinery | 2|none | 5|exact_match|↑ |0.1800|± |0.0386|
|
| 193 |
+
|kmmlu_hard_direct_social_welfare | 2|none | 5|exact_match|↑ |0.3100|± |0.0465|
|
| 194 |
+
|kmmlu_hard_direct_taxation | 2|none | 5|exact_match|↑ |0.1979|± |0.0409|
|
| 195 |
+
|kmmlu_hard_direct_telecommunications_and_wireless_technology| 2|none | 5|exact_match|↑ |0.2500|± |0.0435|
|
| 196 |
+
|kmmlu_hard_ecology | 2|none | 5|acc |↑ |0.1400|± |0.0349|
|
| 197 |
+
| | |none | 5|acc_norm |↑ |0.1400|± |0.0349|
|
| 198 |
+
|kmmlu_hard_economics | 2|none | 5|acc |↑ |0.2857|± |0.0706|
|
| 199 |
+
| | |none | 5|acc_norm |↑ |0.2857|± |0.0706|
|
| 200 |
+
|kmmlu_hard_education | 2|none | 5|acc |↑ |0.3478|± |0.1015|
|
| 201 |
+
| | |none | 5|acc_norm |↑ |0.3478|± |0.1015|
|
| 202 |
+
|kmmlu_hard_electrical_engineering | 2|none | 5|acc |↑ |0.1600|± |0.0368|
|
| 203 |
+
| | |none | 5|acc_norm |↑ |0.1600|± |0.0368|
|
| 204 |
+
|kmmlu_hard_electronics_engineering | 2|none | 5|acc |↑ |0.2500|± |0.0435|
|
| 205 |
+
| | |none | 5|acc_norm |↑ |0.2500|± |0.0435|
|
| 206 |
+
|kmmlu_hard_energy_management | 2|none | 5|acc |↑ |0.2100|± |0.0409|
|
| 207 |
+
| | |none | 5|acc_norm |↑ |0.2100|± |0.0409|
|
| 208 |
+
|kmmlu_hard_environmental_science | 2|none | 5|acc |↑ |0.2000|± |0.0402|
|
| 209 |
+
| | |none | 5|acc_norm |↑ |0.2000|± |0.0402|
|
| 210 |
+
|kmmlu_hard_fashion | 2|none | 5|acc |↑ |0.2100|± |0.0409|
|
| 211 |
+
| | |none | 5|acc_norm |↑ |0.2100|± |0.0409|
|
| 212 |
+
|kmmlu_hard_food_processing | 2|none | 5|acc |↑ |0.1800|± |0.0386|
|
| 213 |
+
| | |none | 5|acc_norm |↑ |0.1800|± |0.0386|
|
| 214 |
+
|kmmlu_hard_gas_technology_and_engineering | 2|none | 5|acc |↑ |0.1100|± |0.0314|
|
| 215 |
+
| | |none | 5|acc_norm |↑ |0.1100|± |0.0314|
|
| 216 |
+
|kmmlu_hard_geomatics | 2|none | 5|acc |↑ |0.2200|± |0.0416|
|
| 217 |
+
| | |none | 5|acc_norm |↑ |0.2200|± |0.0416|
|
| 218 |
+
|kmmlu_hard_health | 2|none | 5|acc |↑ |0.2174|± |0.0879|
|
| 219 |
+
| | |none | 5|acc_norm |↑ |0.2174|± |0.0879|
|
| 220 |
+
|kmmlu_hard_industrial_engineer | 2|none | 5|acc |↑ |0.1900|± |0.0394|
|
| 221 |
+
| | |none | 5|acc_norm |↑ |0.1900|± |0.0394|
|
| 222 |
+
|kmmlu_hard_information_technology | 2|none | 5|acc |↑ |0.3200|± |0.0469|
|
| 223 |
+
| | |none | 5|acc_norm |↑ |0.3200|± |0.0469|
|
| 224 |
+
|kmmlu_hard_interior_architecture_and_design | 2|none | 5|acc |↑ |0.2100|± |0.0409|
|
| 225 |
+
| | |none | 5|acc_norm |↑ |0.2100|± |0.0409|
|
| 226 |
+
|kmmlu_hard_korean_history | 2|none | 5|acc |↑ |0.1591|± |0.0558|
|
| 227 |
+
| | |none | 5|acc_norm |↑ |0.1591|± |0.0558|
|
| 228 |
+
|kmmlu_hard_law | 2|none | 5|acc |↑ |0.1700|± |0.0378|
|
| 229 |
+
| | |none | 5|acc_norm |↑ |0.1700|± |0.0378|
|
| 230 |
+
|kmmlu_hard_machine_design_and_manufacturing | 2|none | 5|acc |↑ |0.1700|± |0.0378|
|
| 231 |
+
| | |none | 5|acc_norm |↑ |0.1700|± |0.0378|
|
| 232 |
+
|kmmlu_hard_management | 2|none | 5|acc |↑ |0.3100|± |0.0465|
|
| 233 |
+
| | |none | 5|acc_norm |↑ |0.3100|± |0.0465|
|
| 234 |
+
|kmmlu_hard_maritime_engineering | 2|none | 5|acc |↑ |0.2300|± |0.0423|
|
| 235 |
+
| | |none | 5|acc_norm |↑ |0.2300|± |0.0423|
|
| 236 |
+
|kmmlu_hard_marketing | 2|none | 5|acc |↑ |0.3200|± |0.0469|
|
| 237 |
+
| | |none | 5|acc_norm |↑ |0.3200|± |0.0469|
|
| 238 |
+
|kmmlu_hard_materials_engineering | 2|none | 5|acc |↑ |0.1900|± |0.0394|
|
| 239 |
+
| | |none | 5|acc_norm |↑ |0.1900|± |0.0394|
|
| 240 |
+
|kmmlu_hard_math | 2|none | 5|acc |↑ |0.3100|± |0.0465|
|
| 241 |
+
| | |none | 5|acc_norm |↑ |0.3100|± |0.0465|
|
| 242 |
+
|kmmlu_hard_mechanical_engineering | 2|none | 5|acc |↑ |0.1700|± |0.0378|
|
| 243 |
+
| | |none | 5|acc_norm |↑ |0.1700|± |0.0378|
|
| 244 |
+
|kmmlu_hard_nondestructive_testing | 2|none | 5|acc |↑ |0.1300|± |0.0338|
|
| 245 |
+
| | |none | 5|acc_norm |↑ |0.1300|± |0.0338|
|
| 246 |
+
|kmmlu_hard_patent | 2|none | 5|acc |↑ |0.2941|± |0.0644|
|
| 247 |
+
| | |none | 5|acc_norm |↑ |0.2941|± |0.0644|
|
| 248 |
+
|kmmlu_hard_political_science_and_sociology | 2|none | 5|acc |↑ |0.2667|± |0.0469|
|
| 249 |
+
| | |none | 5|acc_norm |↑ |0.2667|± |0.0469|
|
| 250 |
+
|kmmlu_hard_psychology | 2|none | 5|acc |↑ |0.2700|± |0.0446|
|
| 251 |
+
| | |none | 5|acc_norm |↑ |0.2700|± |0.0446|
|
| 252 |
+
|kmmlu_hard_public_safety | 2|none | 5|acc |↑ |0.1400|± |0.0349|
|
| 253 |
+
| | |none | 5|acc_norm |↑ |0.1400|± |0.0349|
|
| 254 |
+
|kmmlu_hard_railway_and_automotive_engineering | 2|none | 5|acc |↑ |0.1700|± |0.0378|
|
| 255 |
+
| | |none | 5|acc_norm |↑ |0.1700|± |0.0378|
|
| 256 |
+
|kmmlu_hard_real_estate | 2|none | 5|acc |↑ |0.2135|± |0.0437|
|
| 257 |
+
| | |none | 5|acc_norm |↑ |0.2135|± |0.0437|
|
| 258 |
+
|kmmlu_hard_refrigerating_machinery | 2|none | 5|acc |↑ |0.2000|± |0.0402|
|
| 259 |
+
| | |none | 5|acc_norm |↑ |0.2000|± |0.0402|
|
| 260 |
+
|kmmlu_hard_social_welfare | 2|none | 5|acc |↑ |0.3200|± |0.0469|
|
| 261 |
+
| | |none | 5|acc_norm |↑ |0.3200|± |0.0469|
|
| 262 |
+
|kmmlu_hard_taxation | 2|none | 5|acc |↑ |0.2083|± |0.0417|
|
| 263 |
+
| | |none | 5|acc_norm |↑ |0.2083|± |0.0417|
|
| 264 |
+
|kmmlu_hard_telecommunications_and_wireless_technology | 2|none | 5|acc |↑ |0.2600|± |0.0441|
|
| 265 |
+
| | |none | 5|acc_norm |↑ |0.2600|± |0.0441|
|
generation_config.json
CHANGED
|
@@ -2,6 +2,6 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"do_sample": true,
|
| 4 |
"eos_token_id": 151645,
|
| 5 |
-
"transformers_version": "4.
|
| 6 |
"use_cache": false
|
| 7 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"do_sample": true,
|
| 4 |
"eos_token_id": 151645,
|
| 5 |
+
"transformers_version": "4.45.0",
|
| 6 |
"use_cache": false
|
| 7 |
}
|
model-00001-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75efef28bbffbf631709659a8d0b3cf1e2f77e169dc93c8e6d63d72d9d7095af
|
| 3 |
+
size 4877660776
|
model-00002-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:922caa4ea6c1d9b759338b8fd660655feac066efc89e3b3ed1b9703e1ef48d87
|
| 3 |
+
size 4932751008
|
model-00003-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3319912206086ca4a97ce31464152c9be37d688f40950064f92f53b34dc584d2
|
| 3 |
+
size 4991495888
|
model-00004-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e949a2be58e0966bfb76da4995a7f03e09e4141871c3a16702bc45a3ddc10d7f
|
| 3 |
+
size 4991495888
|
model-00005-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1df52907001c545ae2f4d49a1888f0e26f4bf034880eaf0d4a5ec24c514b6bf2
|
| 3 |
+
size 4932751040
|
model-00006-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8bc5fae0f95564d05dcb266a681fcf3075e755ac226eef8b23db421bc63b09b
|
| 3 |
+
size 4330865200
|
model-00007-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bac53e858731549045ae820fbecc57ee0b3164efbf5498b91f6cc3159d985d62
|
| 3 |
size 1089994880
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:beecd5cf471eeee302d693ba0ec908a4207debddd428e720f1ccc457271682d6
|
| 3 |
+
size 8120
|