Update README.md
Browse files
README.md
CHANGED
@@ -77,6 +77,8 @@ We evaluate Polyglot-Ko-3.8B on [KOBEST dataset](https://arxiv.org/abs/2204.0454
|
|
77 |
|
78 |
The following tables show the results when the number of few-shot examples differ. You can reproduce these results using the [polyglot branch of lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/polyglot) and the following scripts. For a fair comparison, all models were run under the same conditions and using the same prompts. In the tables, `n` refers to the number of few-shot examples.
|
79 |
|
|
|
|
|
80 |
```console
|
81 |
python main.py \
|
82 |
--model gpt2 \
|
@@ -90,31 +92,76 @@ python main.py \
|
|
90 |
|
91 |
### COPA (F1)
|
92 |
|
93 |
-
| Model | params | n=0
|
94 |
|----------------------------------------------------------------------------------------------|--------|--------|--------|---------|---------|
|
95 |
| [skt/ko-gpt-trinity-1.2B-v0.5](https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5) | 1.2B | 0.6696 | 0.6477 | 0.6419 | 0.6514 |
|
96 |
| [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt) | 6.0B | 0.7345 | 0.7287 | 0.7277 | 0.7479 |
|
97 |
| [facebook/xglm-7.5B](https://huggingface.co/facebook/xglm-7.5B) | 7.5B | 0.6723 | 0.6731 | 0.6769 | 0.7119 |
|
98 |
| [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) | 1.3B | 0.7196 | 0.7193 | 0.7204 | 0.7206 |
|
99 |
-
| **[EleutherAI/polyglot-ko-3.8b](https://huggingface.co/EleutherAI/polyglot-ko-3.8b) (this)** | **3.8B**
|
100 |
| [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) | 5.8B | 0.7745 | 0.7676 | 0.7775 | 0.7887 |
|
101 |
| [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) | 12.8B | 0.7937 | 0.8108 | 0.8037 | 0.8369 |
|
102 |
|
103 |
-
<img src="https://
|
104 |
|
105 |
### HellaSwag (F1)
|
106 |
|
107 |
-
| Model
|
108 |
-
|
109 |
-
| [skt/ko-gpt-trinity-1.2B-v0.5](https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5)
|
110 |
-
| [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt)
|
111 |
-
| [facebook/xglm-7.5B](https://huggingface.co/facebook/xglm-7.5B)
|
112 |
-
| [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b)
|
113 |
-
| **[EleutherAI/polyglot-ko-3.8b](https://huggingface.co/EleutherAI/polyglot-ko-3.8b) (this)**
|
114 |
-
| [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b)
|
115 |
-
| [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b)
|
116 |
-
|
117 |
-
<img src="https://
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
118 |
|
119 |
## Limitations and Biases
|
120 |
|
|
|
77 |
|
78 |
The following tables show the results when the number of few-shot examples differ. You can reproduce these results using the [polyglot branch of lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/polyglot) and the following scripts. For a fair comparison, all models were run under the same conditions and using the same prompts. In the tables, `n` refers to the number of few-shot examples.
|
79 |
|
80 |
+
In case of WiC dataset, all models show random performance.
|
81 |
+
|
82 |
```console
|
83 |
python main.py \
|
84 |
--model gpt2 \
|
|
|
92 |
|
93 |
### COPA (F1)
|
94 |
|
95 |
+
| Model | params | n=0 | n=5 | n=10 | n=50 |
|
96 |
|----------------------------------------------------------------------------------------------|--------|--------|--------|---------|---------|
|
97 |
| [skt/ko-gpt-trinity-1.2B-v0.5](https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5) | 1.2B | 0.6696 | 0.6477 | 0.6419 | 0.6514 |
|
98 |
| [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt) | 6.0B | 0.7345 | 0.7287 | 0.7277 | 0.7479 |
|
99 |
| [facebook/xglm-7.5B](https://huggingface.co/facebook/xglm-7.5B) | 7.5B | 0.6723 | 0.6731 | 0.6769 | 0.7119 |
|
100 |
| [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) | 1.3B | 0.7196 | 0.7193 | 0.7204 | 0.7206 |
|
101 |
+
| **[EleutherAI/polyglot-ko-3.8b](https://huggingface.co/EleutherAI/polyglot-ko-3.8b) (this)** | **3.8B** | **0.7595** | **0.7608** | **0.7638** | **0.7788** |
|
102 |
| [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) | 5.8B | 0.7745 | 0.7676 | 0.7775 | 0.7887 |
|
103 |
| [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) | 12.8B | 0.7937 | 0.8108 | 0.8037 | 0.8369 |
|
104 |
|
105 |
+
<img src="https://github.com/EleutherAI/polyglot/assets/19511788/d5b49364-aed5-4467-bae2-5a322c8e2ceb" width="800px">
|
106 |
|
107 |
### HellaSwag (F1)
|
108 |
|
109 |
+
| Model | params | n=0 | n=5 | n=10 | n=50 |
|
110 |
+
|----------------------------------------------------------------------------------------------|--------|--------|--------|---------|---------|
|
111 |
+
| [skt/ko-gpt-trinity-1.2B-v0.5](https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5) | 1.2B | 0.5243 | 0.5272 | 0.5166 | 0.5352 |
|
112 |
+
| [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt) | 6.0B | 0.5590 | 0.5833 | 0.5828 | 0.5907 |
|
113 |
+
| [facebook/xglm-7.5B](https://huggingface.co/facebook/xglm-7.5B) | 7.5B | 0.5665 | 0.5689 | 0.5565 | 0.5622 |
|
114 |
+
| [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) | 1.3B | 0.5247 | 0.5260 | 0.5278 | 0.5427 |
|
115 |
+
| **[EleutherAI/polyglot-ko-3.8b](https://huggingface.co/EleutherAI/polyglot-ko-3.8b) (this)** | **3.8B** | **0.5707** | **0.5830** | **0.5670** | **0.5787** |
|
116 |
+
| [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) | 5.8B | 0.5976 | 0.5998 | 0.5979 | 0.6208 |
|
117 |
+
| [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) | 12.8B | 0.5954 | 0.6306 | 0.6098 | 0.6118 |
|
118 |
+
|
119 |
+
<img src="https://github.com/EleutherAI/polyglot/assets/19511788/5acb60ac-161a-4ab3-a296-db4442e08b7f" width="800px">
|
120 |
+
|
121 |
+
### BoolQ (F1)
|
122 |
+
|
123 |
+
| Model | params | n=0 | n=5 | n=10 | n=50 |
|
124 |
+
|----------------------------------------------------------------------------------------------|--------|--------|--------|---------|---------|
|
125 |
+
| [skt/ko-gpt-trinity-1.2B-v0.5](https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5) | 1.2B | 0.3356 | 0.4014 | 0.3640 | 0.3560 |
|
126 |
+
| [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt) | 6.0B | 0.4514 | 0.5981 | 0.5499 | 0.5202 |
|
127 |
+
| [facebook/xglm-7.5B](https://huggingface.co/facebook/xglm-7.5B) | 7.5B | 0.4464 | 0.3324 | 0.3324 | 0.3324 |
|
128 |
+
| [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) | 1.3B | 0.3552 | 0.4751 | 0.4109 | 0.4038 |
|
129 |
+
| **[EleutherAI/polyglot-ko-3.8b](https://huggingface.co/EleutherAI/polyglot-ko-3.8b) (this)** | **3.8B** | **0.4320** | **0.5263** | **0.4930** | **0.4038** |
|
130 |
+
| [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) | 5.8B | 0.4356 | 0.5698 | 0.5187 | 0.5236 |
|
131 |
+
| [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) | 12.8B | 0.4818 | 0.6041 | 0.6289 | 0.6448 |
|
132 |
+
|
133 |
+
|
134 |
+
<img src="https://github.com/EleutherAI/polyglot/assets/19511788/b74c23c0-01f3-4b68-9e10-a48e9aa052ab" width="800px">
|
135 |
+
|
136 |
+
### SentiNeg (F1)
|
137 |
+
|
138 |
+
| Model | params | n=0 | n=5 | n=10 | n=50 |
|
139 |
+
|----------------------------------------------------------------------------------------------|--------|--------|--------|---------|---------|
|
140 |
+
| [skt/ko-gpt-trinity-1.2B-v0.5](https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5) | 1.2B | 0.6065 | 0.6878 | 0.7280 | 0.8413 |
|
141 |
+
| [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt) | 6.0B | 0.3747 | 0.8942 | 0.9294 | 0.9698 |
|
142 |
+
| [facebook/xglm-7.5B](https://huggingface.co/facebook/xglm-7.5B) | 7.5B | 0.3578 | 0.4471 | 0.3964 | 0.5271 |
|
143 |
+
| [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) | 1.3B | 0.6790 | 0.6257 | 0.5514 | 0.7851 |
|
144 |
+
| **[EleutherAI/polyglot-ko-3.8b](https://huggingface.co/EleutherAI/polyglot-ko-3.8b) (this)** | **3.8B** | **0.4858** | **0.7950** | **0.7320** | **0.7851** |
|
145 |
+
| [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) | 5.8B | 0.3394 | 0.8841 | 0.8808 | 0.9521 |
|
146 |
+
| [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) | 12.8B | 0.9117 | 0.9015 | 0.9345 | 0.9723 |
|
147 |
+
|
148 |
+
|
149 |
+
<img src="https://github.com/EleutherAI/polyglot/assets/19511788/95b56b19-d349-4b70-9ff9-94a5560f89ee" width="800px">
|
150 |
+
|
151 |
+
### WiC (F1)
|
152 |
+
|
153 |
+
| Model | params | n=0 | n=5 | n=10 | n=50 |
|
154 |
+
|----------------------------------------------------------------------------------------------|--------|--------|--------|---------|---------|
|
155 |
+
| [skt/ko-gpt-trinity-1.2B-v0.5](https://huggingface.co/skt/ko-gpt-trinity-1.2B-v0.5) | 1.2B | 0.3290 | 0.4313 | 0.4001 | 0.3621 |
|
156 |
+
| [kakaobrain/kogpt](https://huggingface.co/kakaobrain/kogpt) | 6.0B | 0.3526 | 0.4775 | 0.4358 | 0.4061 |
|
157 |
+
| [facebook/xglm-7.5B](https://huggingface.co/facebook/xglm-7.5B) | 7.5B | 0.3280 | 0.4903 | 0.4945 | 0.3656 |
|
158 |
+
| [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) | 1.3B | 0.3297 | 0.4850 | 0.4650 | 0.3290 |
|
159 |
+
| **[EleutherAI/polyglot-ko-3.8b](https://huggingface.co/EleutherAI/polyglot-ko-3.8b) (this)** | **3.8B** | **0.3390** | **0.4944** | **0.4203** | **0.3835** |
|
160 |
+
| [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) | 5.8B | 0.3913 | 0.4688 | 0.4189 | 0.3910 |
|
161 |
+
| [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) | 12.8B | 0.3985 | 0.3683 | 0.3307 | 0.3273 |
|
162 |
+
|
163 |
+
|
164 |
+
<img src="https://github.com/EleutherAI/polyglot/assets/19511788/4de4a4c3-d7ac-4e04-8b0c-0d533fe88294" width="800px">
|
165 |
|
166 |
## Limitations and Biases
|
167 |
|