Update README
Browse files
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: mit
|
|
| 4 |
|
| 5 |
| 配置 | GSM8K | SVAMP | GSM8K-hard | MultiArith |
|
| 6 |
| ------------------------ | -----------------: | ---------------: | ----------------: | ----------------: |
|
|
|
|
| 7 |
| eval_full_s0.0015_a0.0002 | 73.84% | 81.33% | 36.62% | 99.44% |
|
| 8 |
| eval_full_s0.0015_a0.00025 | 73.16% | 83.00% | 37.45% | 97.22% |
|
| 9 |
| **avg_full** | 73.50% | 82.17% | 37.04% | 98.50% |
|
|
@@ -18,4 +19,6 @@ license: mit
|
|
| 18 |
| eval_r16_s0.0225_a0.005 | 75.82% | 85.67% | 39.12% | 98.89% |
|
| 19 |
| eval_r16_s0.0225_a0.0025 | 74.83% | 85.00% | 37.83% | 96.67% |
|
| 20 |
| eval_r16_s0.0225_a0.0035 | 75.66% | 83.67% | 38.89% | 98.33% |
|
| 21 |
-
| **avg_r16** | 75.44% | **84.78%** | **38.61%** | 97.96% |
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
| 配置 | GSM8K | SVAMP | GSM8K-hard | MultiArith |
|
| 6 |
| ------------------------ | -----------------: | ---------------: | ----------------: | ----------------: |
|
| 7 |
+
| **zero_shot** | 74.15% | 81.00% | 35.86% | 99.44% |
|
| 8 |
| eval_full_s0.0015_a0.0002 | 73.84% | 81.33% | 36.62% | 99.44% |
|
| 9 |
| eval_full_s0.0015_a0.00025 | 73.16% | 83.00% | 37.45% | 97.22% |
|
| 10 |
| **avg_full** | 73.50% | 82.17% | 37.04% | 98.50% |
|
|
|
|
| 19 |
| eval_r16_s0.0225_a0.005 | 75.82% | 85.67% | 39.12% | 98.89% |
|
| 20 |
| eval_r16_s0.0225_a0.0025 | 74.83% | 85.00% | 37.83% | 96.67% |
|
| 21 |
| eval_r16_s0.0225_a0.0035 | 75.66% | 83.67% | 38.89% | 98.33% |
|
| 22 |
+
| **avg_r16** | 75.44% | **84.78%** | **38.61%** | 97.96% |
|
| 23 |
+
| eval_r64_s0.01_a0.0025 | 77.03% | 83.33% | 36.62% | 96.11% |
|
| 24 |
+
| eval_r64_s0.0085_a0.0025 | 75.59% | 84.33% | 37.68% | 96.11% |
|