Piotr Zalewski commited on
Commit
fe7acc7
1 Parent(s): fffa65a

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (7137661e27a9a686e604685d7555d52f97f56da2)

Files changed (1) hide show
  1. README.md +112 -3
README.md CHANGED
@@ -1,7 +1,4 @@
1
  ---
2
- base_model: meta-llama/Llama-3.2-3B-Instruct
3
- datasets:
4
- - KingNish/reasoning-base-20k
5
  language:
6
  - en
7
  license: llama3.2
@@ -13,6 +10,104 @@ tags:
13
  - sft
14
  - reasoning
15
  - llama-3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  ---
17
 
18
  # Model Description
@@ -63,3 +158,17 @@ print("ANSWER: " + response_output)
63
  This Llama model was trained faster than [Unsloth](https://github.com/unslothai/unsloth) using [custom training code](https://www.kaggle.com/code/piotr25691/distributed-llama-training-with-2xt4).
64
 
65
  Visit https://www.kaggle.com/code/piotr25691/distributed-llama-training-with-2xt4 to find out how you can finetune your models using BOTH of the Kaggle provided GPUs.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
 
 
 
2
  language:
3
  - en
4
  license: llama3.2
 
10
  - sft
11
  - reasoning
12
  - llama-3
13
+ base_model: meta-llama/Llama-3.2-3B-Instruct
14
+ datasets:
15
+ - KingNish/reasoning-base-20k
16
+ model-index:
17
+ - name: thea-c-3b-25r
18
+ results:
19
+ - task:
20
+ type: text-generation
21
+ name: Text Generation
22
+ dataset:
23
+ name: IFEval (0-Shot)
24
+ type: HuggingFaceH4/ifeval
25
+ args:
26
+ num_few_shot: 0
27
+ metrics:
28
+ - type: inst_level_strict_acc and prompt_level_strict_acc
29
+ value: 74.02
30
+ name: strict accuracy
31
+ source:
32
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
33
+ name: Open LLM Leaderboard
34
+ - task:
35
+ type: text-generation
36
+ name: Text Generation
37
+ dataset:
38
+ name: BBH (3-Shot)
39
+ type: BBH
40
+ args:
41
+ num_few_shot: 3
42
+ metrics:
43
+ - type: acc_norm
44
+ value: 22.77
45
+ name: normalized accuracy
46
+ source:
47
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
48
+ name: Open LLM Leaderboard
49
+ - task:
50
+ type: text-generation
51
+ name: Text Generation
52
+ dataset:
53
+ name: MATH Lvl 5 (4-Shot)
54
+ type: hendrycks/competition_math
55
+ args:
56
+ num_few_shot: 4
57
+ metrics:
58
+ - type: exact_match
59
+ value: 13.37
60
+ name: exact match
61
+ source:
62
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
63
+ name: Open LLM Leaderboard
64
+ - task:
65
+ type: text-generation
66
+ name: Text Generation
67
+ dataset:
68
+ name: GPQA (0-shot)
69
+ type: Idavidrein/gpqa
70
+ args:
71
+ num_few_shot: 0
72
+ metrics:
73
+ - type: acc_norm
74
+ value: 2.01
75
+ name: acc_norm
76
+ source:
77
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
78
+ name: Open LLM Leaderboard
79
+ - task:
80
+ type: text-generation
81
+ name: Text Generation
82
+ dataset:
83
+ name: MuSR (0-shot)
84
+ type: TAUR-Lab/MuSR
85
+ args:
86
+ num_few_shot: 0
87
+ metrics:
88
+ - type: acc_norm
89
+ value: 1.27
90
+ name: acc_norm
91
+ source:
92
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
93
+ name: Open LLM Leaderboard
94
+ - task:
95
+ type: text-generation
96
+ name: Text Generation
97
+ dataset:
98
+ name: MMLU-PRO (5-shot)
99
+ type: TIGER-Lab/MMLU-Pro
100
+ config: main
101
+ split: test
102
+ args:
103
+ num_few_shot: 5
104
+ metrics:
105
+ - type: acc
106
+ value: 24.2
107
+ name: accuracy
108
+ source:
109
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
110
+ name: Open LLM Leaderboard
111
  ---
112
 
113
  # Model Description
 
158
  This Llama model was trained faster than [Unsloth](https://github.com/unslothai/unsloth) using [custom training code](https://www.kaggle.com/code/piotr25691/distributed-llama-training-with-2xt4).
159
 
160
  Visit https://www.kaggle.com/code/piotr25691/distributed-llama-training-with-2xt4 to find out how you can finetune your models using BOTH of the Kaggle provided GPUs.
161
+
162
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
163
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_piotr25691__thea-c-3b-25r)
164
+
165
+ | Metric |Value|
166
+ |-------------------|----:|
167
+ |Avg. |22.94|
168
+ |IFEval (0-Shot) |74.02|
169
+ |BBH (3-Shot) |22.77|
170
+ |MATH Lvl 5 (4-Shot)|13.37|
171
+ |GPQA (0-shot) | 2.01|
172
+ |MuSR (0-shot) | 1.27|
173
+ |MMLU-PRO (5-shot) |24.20|
174
+