End of training
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -50,205 +50,235 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:-----:|:---------------:|
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
-
| 0.
|
| 134 |
-
| 0.
|
| 135 |
-
| 0.
|
| 136 |
-
| 0.
|
| 137 |
-
| 0.
|
| 138 |
-
| 0.
|
| 139 |
-
| 0.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
| 145 |
-
| 0.
|
| 146 |
-
| 0.
|
| 147 |
-
| 0.
|
| 148 |
-
| 0.
|
| 149 |
-
| 0.
|
| 150 |
-
| 0.
|
| 151 |
-
| 0.
|
| 152 |
-
| 0.
|
| 153 |
-
| 0.
|
| 154 |
-
| 0.
|
| 155 |
-
| 0.1707 | 2.
|
| 156 |
-
| 0.
|
| 157 |
-
| 0.
|
| 158 |
-
| 0.
|
| 159 |
-
| 0.
|
| 160 |
-
| 0.
|
| 161 |
-
| 0.
|
| 162 |
-
| 0.
|
| 163 |
-
| 0.
|
| 164 |
-
| 0.
|
| 165 |
-
| 0.
|
| 166 |
-
| 0.
|
| 167 |
-
| 0.
|
| 168 |
-
| 0.
|
| 169 |
-
| 0.
|
| 170 |
-
| 0.
|
| 171 |
-
| 0.
|
| 172 |
-
| 0.
|
| 173 |
-
| 0.
|
| 174 |
-
| 0.
|
| 175 |
-
| 0.
|
| 176 |
-
| 0.
|
| 177 |
-
| 0.
|
| 178 |
-
| 0.
|
| 179 |
-
| 0.
|
| 180 |
-
| 0.
|
| 181 |
-
| 0.
|
| 182 |
-
| 0.
|
| 183 |
-
| 0.
|
| 184 |
-
| 0.
|
| 185 |
-
| 0.
|
| 186 |
-
| 0.
|
| 187 |
-
| 0.
|
| 188 |
-
| 0.
|
| 189 |
-
| 0.
|
| 190 |
-
| 0.
|
| 191 |
-
| 0.
|
| 192 |
-
| 0.
|
| 193 |
-
| 0.
|
| 194 |
-
| 0.
|
| 195 |
-
| 0.
|
| 196 |
-
| 0.
|
| 197 |
-
| 0.
|
| 198 |
-
| 0.
|
| 199 |
-
| 0.
|
| 200 |
-
| 0.
|
| 201 |
-
| 0.
|
| 202 |
-
| 0.
|
| 203 |
-
| 0.
|
| 204 |
-
| 0.
|
| 205 |
-
| 0.
|
| 206 |
-
| 0.
|
| 207 |
-
| 0.
|
| 208 |
-
| 0.
|
| 209 |
-
| 0.
|
| 210 |
-
| 0.
|
| 211 |
-
| 0.
|
| 212 |
-
| 0.
|
| 213 |
-
| 0.
|
| 214 |
-
| 0.
|
| 215 |
-
| 0.
|
| 216 |
-
| 0.
|
| 217 |
-
| 0.
|
| 218 |
-
| 0.
|
| 219 |
-
| 0.
|
| 220 |
-
| 0.
|
| 221 |
-
| 0.
|
| 222 |
-
| 0.
|
| 223 |
-
| 0.
|
| 224 |
-
| 0.
|
| 225 |
-
| 0.
|
| 226 |
-
| 0.
|
| 227 |
-
| 0.
|
| 228 |
-
| 0.
|
| 229 |
-
| 0.
|
| 230 |
-
| 0.
|
| 231 |
-
| 0.
|
| 232 |
-
| 0.
|
| 233 |
-
| 0.
|
| 234 |
-
| 0.
|
| 235 |
-
| 0.
|
| 236 |
-
| 0.
|
| 237 |
-
| 0.
|
| 238 |
-
| 0.
|
| 239 |
-
| 0.
|
| 240 |
-
| 0.
|
| 241 |
-
| 0.
|
| 242 |
-
| 0.
|
| 243 |
-
| 0.
|
| 244 |
-
| 0.
|
| 245 |
-
| 0.
|
| 246 |
-
| 0.
|
| 247 |
-
| 0.
|
| 248 |
-
| 0.
|
| 249 |
-
| 0.
|
| 250 |
-
| 0.
|
| 251 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
|
| 253 |
|
| 254 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2878
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:-----:|:---------------:|
|
| 53 |
+
| 0.2463 | 1.65 | 8000 | 0.2803 |
|
| 54 |
+
| 0.2618 | 1.66 | 8050 | 0.2798 |
|
| 55 |
+
| 0.2549 | 1.67 | 8100 | 0.2802 |
|
| 56 |
+
| 0.2396 | 1.68 | 8150 | 0.2786 |
|
| 57 |
+
| 0.2349 | 1.69 | 8200 | 0.2778 |
|
| 58 |
+
| 0.2312 | 1.7 | 8250 | 0.2787 |
|
| 59 |
+
| 0.2541 | 1.71 | 8300 | 0.2779 |
|
| 60 |
+
| 0.2596 | 1.72 | 8350 | 0.2765 |
|
| 61 |
+
| 0.2341 | 1.73 | 8400 | 0.2763 |
|
| 62 |
+
| 0.2706 | 1.74 | 8450 | 0.2760 |
|
| 63 |
+
| 0.2453 | 1.75 | 8500 | 0.2765 |
|
| 64 |
+
| 0.2324 | 1.76 | 8550 | 0.2758 |
|
| 65 |
+
| 0.276 | 1.77 | 8600 | 0.2740 |
|
| 66 |
+
| 0.2688 | 1.78 | 8650 | 0.2739 |
|
| 67 |
+
| 0.2462 | 1.79 | 8700 | 0.2766 |
|
| 68 |
+
| 0.2741 | 1.8 | 8750 | 0.2740 |
|
| 69 |
+
| 0.2457 | 1.81 | 8800 | 0.2740 |
|
| 70 |
+
| 0.265 | 1.82 | 8850 | 0.2732 |
|
| 71 |
+
| 0.2451 | 1.83 | 8900 | 0.2733 |
|
| 72 |
+
| 0.2169 | 1.84 | 8950 | 0.2728 |
|
| 73 |
+
| 0.2415 | 1.85 | 9000 | 0.2728 |
|
| 74 |
+
| 0.2338 | 1.86 | 9050 | 0.2737 |
|
| 75 |
+
| 0.2293 | 1.87 | 9100 | 0.2740 |
|
| 76 |
+
| 0.2235 | 1.88 | 9150 | 0.2722 |
|
| 77 |
+
| 0.2773 | 1.89 | 9200 | 0.2721 |
|
| 78 |
+
| 0.2544 | 1.9 | 9250 | 0.2709 |
|
| 79 |
+
| 0.2474 | 1.91 | 9300 | 0.2706 |
|
| 80 |
+
| 0.2461 | 1.92 | 9350 | 0.2704 |
|
| 81 |
+
| 0.2716 | 1.93 | 9400 | 0.2693 |
|
| 82 |
+
| 0.2773 | 1.94 | 9450 | 0.2695 |
|
| 83 |
+
| 0.2282 | 1.96 | 9500 | 0.2700 |
|
| 84 |
+
| 0.2511 | 1.97 | 9550 | 0.2701 |
|
| 85 |
+
| 0.2652 | 1.98 | 9600 | 0.2697 |
|
| 86 |
+
| 0.2615 | 1.99 | 9650 | 0.2699 |
|
| 87 |
+
| 0.2263 | 2.0 | 9700 | 0.2691 |
|
| 88 |
+
| 0.2136 | 2.01 | 9750 | 0.2807 |
|
| 89 |
+
| 0.1751 | 2.02 | 9800 | 0.2778 |
|
| 90 |
+
| 0.1891 | 2.03 | 9850 | 0.2796 |
|
| 91 |
+
| 0.1758 | 2.04 | 9900 | 0.2822 |
|
| 92 |
+
| 0.1901 | 2.05 | 9950 | 0.2780 |
|
| 93 |
+
| 0.2105 | 2.06 | 10000 | 0.2800 |
|
| 94 |
+
| 0.1901 | 2.07 | 10050 | 0.2794 |
|
| 95 |
+
| 0.1891 | 2.08 | 10100 | 0.2787 |
|
| 96 |
+
| 0.1772 | 2.09 | 10150 | 0.2834 |
|
| 97 |
+
| 0.1761 | 2.1 | 10200 | 0.2805 |
|
| 98 |
+
| 0.1792 | 2.11 | 10250 | 0.2805 |
|
| 99 |
+
| 0.1785 | 2.12 | 10300 | 0.2810 |
|
| 100 |
+
| 0.1899 | 2.13 | 10350 | 0.2821 |
|
| 101 |
+
| 0.174 | 2.14 | 10400 | 0.2813 |
|
| 102 |
+
| 0.1796 | 2.15 | 10450 | 0.2818 |
|
| 103 |
+
| 0.1658 | 2.16 | 10500 | 0.2816 |
|
| 104 |
+
| 0.1832 | 2.17 | 10550 | 0.2787 |
|
| 105 |
+
| 0.2024 | 2.18 | 10600 | 0.2795 |
|
| 106 |
+
| 0.1943 | 2.19 | 10650 | 0.2801 |
|
| 107 |
+
| 0.1772 | 2.2 | 10700 | 0.2798 |
|
| 108 |
+
| 0.1744 | 2.21 | 10750 | 0.2811 |
|
| 109 |
+
| 0.1929 | 2.22 | 10800 | 0.2792 |
|
| 110 |
+
| 0.1684 | 2.23 | 10850 | 0.2793 |
|
| 111 |
+
| 0.1672 | 2.24 | 10900 | 0.2783 |
|
| 112 |
+
| 0.1922 | 2.25 | 10950 | 0.2766 |
|
| 113 |
+
| 0.1735 | 2.26 | 11000 | 0.2782 |
|
| 114 |
+
| 0.1773 | 2.27 | 11050 | 0.2788 |
|
| 115 |
+
| 0.1736 | 2.28 | 11100 | 0.2788 |
|
| 116 |
+
| 0.1746 | 2.29 | 11150 | 0.2786 |
|
| 117 |
+
| 0.1769 | 2.31 | 11200 | 0.2785 |
|
| 118 |
+
| 0.1797 | 2.32 | 11250 | 0.2769 |
|
| 119 |
+
| 0.197 | 2.33 | 11300 | 0.2757 |
|
| 120 |
+
| 0.1734 | 2.34 | 11350 | 0.2767 |
|
| 121 |
+
| 0.1941 | 2.35 | 11400 | 0.2774 |
|
| 122 |
+
| 0.1742 | 2.36 | 11450 | 0.2783 |
|
| 123 |
+
| 0.186 | 2.37 | 11500 | 0.2779 |
|
| 124 |
+
| 0.1743 | 2.38 | 11550 | 0.2759 |
|
| 125 |
+
| 0.1836 | 2.39 | 11600 | 0.2772 |
|
| 126 |
+
| 0.1876 | 2.4 | 11650 | 0.2768 |
|
| 127 |
+
| 0.1912 | 2.41 | 11700 | 0.2748 |
|
| 128 |
+
| 0.2035 | 2.42 | 11750 | 0.2781 |
|
| 129 |
+
| 0.1742 | 2.43 | 11800 | 0.2780 |
|
| 130 |
+
| 0.1612 | 2.44 | 11850 | 0.2759 |
|
| 131 |
+
| 0.1674 | 2.45 | 11900 | 0.2775 |
|
| 132 |
+
| 0.1725 | 2.46 | 11950 | 0.2745 |
|
| 133 |
+
| 0.1877 | 2.47 | 12000 | 0.2756 |
|
| 134 |
+
| 0.1869 | 2.48 | 12050 | 0.2753 |
|
| 135 |
+
| 0.1803 | 2.49 | 12100 | 0.2749 |
|
| 136 |
+
| 0.1747 | 2.5 | 12150 | 0.2761 |
|
| 137 |
+
| 0.18 | 2.51 | 12200 | 0.2754 |
|
| 138 |
+
| 0.181 | 2.52 | 12250 | 0.2746 |
|
| 139 |
+
| 0.1707 | 2.53 | 12300 | 0.2746 |
|
| 140 |
+
| 0.1875 | 2.54 | 12350 | 0.2749 |
|
| 141 |
+
| 0.1781 | 2.55 | 12400 | 0.2758 |
|
| 142 |
+
| 0.1644 | 2.56 | 12450 | 0.2753 |
|
| 143 |
+
| 0.1995 | 2.57 | 12500 | 0.2727 |
|
| 144 |
+
| 0.1662 | 2.58 | 12550 | 0.2744 |
|
| 145 |
+
| 0.1847 | 2.59 | 12600 | 0.2738 |
|
| 146 |
+
| 0.1771 | 2.6 | 12650 | 0.2731 |
|
| 147 |
+
| 0.1708 | 2.61 | 12700 | 0.2743 |
|
| 148 |
+
| 0.1759 | 2.62 | 12750 | 0.2748 |
|
| 149 |
+
| 0.1899 | 2.63 | 12800 | 0.2743 |
|
| 150 |
+
| 0.2015 | 2.64 | 12850 | 0.2744 |
|
| 151 |
+
| 0.1803 | 2.65 | 12900 | 0.2726 |
|
| 152 |
+
| 0.1588 | 2.67 | 12950 | 0.2750 |
|
| 153 |
+
| 0.1564 | 2.68 | 13000 | 0.2728 |
|
| 154 |
+
| 0.1773 | 2.69 | 13050 | 0.2715 |
|
| 155 |
+
| 0.1707 | 2.7 | 13100 | 0.2736 |
|
| 156 |
+
| 0.1746 | 2.71 | 13150 | 0.2738 |
|
| 157 |
+
| 0.1946 | 2.72 | 13200 | 0.2704 |
|
| 158 |
+
| 0.1669 | 2.73 | 13250 | 0.2740 |
|
| 159 |
+
| 0.1925 | 2.74 | 13300 | 0.2721 |
|
| 160 |
+
| 0.1622 | 2.75 | 13350 | 0.2728 |
|
| 161 |
+
| 0.1741 | 2.76 | 13400 | 0.2705 |
|
| 162 |
+
| 0.1838 | 2.77 | 13450 | 0.2730 |
|
| 163 |
+
| 0.1755 | 2.78 | 13500 | 0.2712 |
|
| 164 |
+
| 0.1718 | 2.79 | 13550 | 0.2719 |
|
| 165 |
+
| 0.1723 | 2.8 | 13600 | 0.2717 |
|
| 166 |
+
| 0.164 | 2.81 | 13650 | 0.2720 |
|
| 167 |
+
| 0.1881 | 2.82 | 13700 | 0.2727 |
|
| 168 |
+
| 0.1639 | 2.83 | 13750 | 0.2690 |
|
| 169 |
+
| 0.1703 | 2.84 | 13800 | 0.2716 |
|
| 170 |
+
| 0.1678 | 2.85 | 13850 | 0.2719 |
|
| 171 |
+
| 0.1737 | 2.86 | 13900 | 0.2719 |
|
| 172 |
+
| 0.1836 | 2.87 | 13950 | 0.2707 |
|
| 173 |
+
| 0.1988 | 2.88 | 14000 | 0.2707 |
|
| 174 |
+
| 0.1779 | 2.89 | 14050 | 0.2697 |
|
| 175 |
+
| 0.1679 | 2.9 | 14100 | 0.2706 |
|
| 176 |
+
| 0.1837 | 2.91 | 14150 | 0.2679 |
|
| 177 |
+
| 0.1561 | 2.92 | 14200 | 0.2683 |
|
| 178 |
+
| 0.1693 | 2.93 | 14250 | 0.2683 |
|
| 179 |
+
| 0.2069 | 2.94 | 14300 | 0.2690 |
|
| 180 |
+
| 0.1703 | 2.95 | 14350 | 0.2692 |
|
| 181 |
+
| 0.1909 | 2.96 | 14400 | 0.2675 |
|
| 182 |
+
| 0.2116 | 2.97 | 14450 | 0.2687 |
|
| 183 |
+
| 0.1787 | 2.98 | 14500 | 0.2683 |
|
| 184 |
+
| 0.1569 | 2.99 | 14550 | 0.2683 |
|
| 185 |
+
| 0.1433 | 3.0 | 14600 | 0.2770 |
|
| 186 |
+
| 0.126 | 3.02 | 14650 | 0.2872 |
|
| 187 |
+
| 0.1211 | 3.03 | 14700 | 0.2918 |
|
| 188 |
+
| 0.1178 | 3.04 | 14750 | 0.2927 |
|
| 189 |
+
| 0.117 | 3.05 | 14800 | 0.2891 |
|
| 190 |
+
| 0.1362 | 3.06 | 14850 | 0.2891 |
|
| 191 |
+
| 0.1128 | 3.07 | 14900 | 0.2904 |
|
| 192 |
+
| 0.1162 | 3.08 | 14950 | 0.2897 |
|
| 193 |
+
| 0.1189 | 3.09 | 15000 | 0.2930 |
|
| 194 |
+
| 0.1267 | 3.1 | 15050 | 0.2895 |
|
| 195 |
+
| 0.1234 | 3.11 | 15100 | 0.2902 |
|
| 196 |
+
| 0.1241 | 3.12 | 15150 | 0.2895 |
|
| 197 |
+
| 0.1302 | 3.13 | 15200 | 0.2918 |
|
| 198 |
+
| 0.1066 | 3.14 | 15250 | 0.2930 |
|
| 199 |
+
| 0.1194 | 3.15 | 15300 | 0.2938 |
|
| 200 |
+
| 0.1209 | 3.16 | 15350 | 0.2931 |
|
| 201 |
+
| 0.1148 | 3.17 | 15400 | 0.2926 |
|
| 202 |
+
| 0.1344 | 3.18 | 15450 | 0.2918 |
|
| 203 |
+
| 0.1145 | 3.19 | 15500 | 0.2894 |
|
| 204 |
+
| 0.1171 | 3.2 | 15550 | 0.2902 |
|
| 205 |
+
| 0.1319 | 3.21 | 15600 | 0.2894 |
|
| 206 |
+
| 0.1196 | 3.22 | 15650 | 0.2889 |
|
| 207 |
+
| 0.1161 | 3.23 | 15700 | 0.2887 |
|
| 208 |
+
| 0.124 | 3.24 | 15750 | 0.2900 |
|
| 209 |
+
| 0.1188 | 3.25 | 15800 | 0.2910 |
|
| 210 |
+
| 0.1222 | 3.26 | 15850 | 0.2901 |
|
| 211 |
+
| 0.1044 | 3.27 | 15900 | 0.2905 |
|
| 212 |
+
| 0.1262 | 3.28 | 15950 | 0.2888 |
|
| 213 |
+
| 0.1107 | 3.29 | 16000 | 0.2903 |
|
| 214 |
+
| 0.1169 | 3.3 | 16050 | 0.2905 |
|
| 215 |
+
| 0.1067 | 3.31 | 16100 | 0.2892 |
|
| 216 |
+
| 0.1299 | 3.32 | 16150 | 0.2892 |
|
| 217 |
+
| 0.1353 | 3.33 | 16200 | 0.2865 |
|
| 218 |
+
| 0.1305 | 3.34 | 16250 | 0.2903 |
|
| 219 |
+
| 0.1262 | 3.35 | 16300 | 0.2894 |
|
| 220 |
+
| 0.1363 | 3.36 | 16350 | 0.2878 |
|
| 221 |
+
| 0.1202 | 3.38 | 16400 | 0.2877 |
|
| 222 |
+
| 0.1208 | 3.39 | 16450 | 0.2876 |
|
| 223 |
+
| 0.1234 | 3.4 | 16500 | 0.2880 |
|
| 224 |
+
| 0.1186 | 3.41 | 16550 | 0.2870 |
|
| 225 |
+
| 0.1171 | 3.42 | 16600 | 0.2875 |
|
| 226 |
+
| 0.1225 | 3.43 | 16650 | 0.2883 |
|
| 227 |
+
| 0.1095 | 3.44 | 16700 | 0.2877 |
|
| 228 |
+
| 0.1269 | 3.45 | 16750 | 0.2888 |
|
| 229 |
+
| 0.1212 | 3.46 | 16800 | 0.2894 |
|
| 230 |
+
| 0.1434 | 3.47 | 16850 | 0.2886 |
|
| 231 |
+
| 0.1349 | 3.48 | 16900 | 0.2888 |
|
| 232 |
+
| 0.1166 | 3.49 | 16950 | 0.2887 |
|
| 233 |
+
| 0.1094 | 3.5 | 17000 | 0.2875 |
|
| 234 |
+
| 0.1188 | 3.51 | 17050 | 0.2901 |
|
| 235 |
+
| 0.1227 | 3.52 | 17100 | 0.2865 |
|
| 236 |
+
| 0.1204 | 3.53 | 17150 | 0.2871 |
|
| 237 |
+
| 0.13 | 3.54 | 17200 | 0.2872 |
|
| 238 |
+
| 0.1197 | 3.55 | 17250 | 0.2885 |
|
| 239 |
+
| 0.1269 | 3.56 | 17300 | 0.2885 |
|
| 240 |
+
| 0.1144 | 3.57 | 17350 | 0.2887 |
|
| 241 |
+
| 0.1133 | 3.58 | 17400 | 0.2897 |
|
| 242 |
+
| 0.1209 | 3.59 | 17450 | 0.2886 |
|
| 243 |
+
| 0.1216 | 3.6 | 17500 | 0.2887 |
|
| 244 |
+
| 0.118 | 3.61 | 17550 | 0.2884 |
|
| 245 |
+
| 0.1245 | 3.62 | 17600 | 0.2879 |
|
| 246 |
+
| 0.1222 | 3.63 | 17650 | 0.2887 |
|
| 247 |
+
| 0.1231 | 3.64 | 17700 | 0.2892 |
|
| 248 |
+
| 0.1229 | 3.65 | 17750 | 0.2881 |
|
| 249 |
+
| 0.1301 | 3.66 | 17800 | 0.2879 |
|
| 250 |
+
| 0.1201 | 3.67 | 17850 | 0.2878 |
|
| 251 |
+
| 0.1146 | 3.68 | 17900 | 0.2898 |
|
| 252 |
+
| 0.1176 | 3.69 | 17950 | 0.2897 |
|
| 253 |
+
| 0.1157 | 3.7 | 18000 | 0.2896 |
|
| 254 |
+
| 0.1283 | 3.71 | 18050 | 0.2894 |
|
| 255 |
+
| 0.1144 | 3.73 | 18100 | 0.2888 |
|
| 256 |
+
| 0.1106 | 3.74 | 18150 | 0.2901 |
|
| 257 |
+
| 0.1224 | 3.75 | 18200 | 0.2891 |
|
| 258 |
+
| 0.1252 | 3.76 | 18250 | 0.2895 |
|
| 259 |
+
| 0.1163 | 3.77 | 18300 | 0.2886 |
|
| 260 |
+
| 0.1213 | 3.78 | 18350 | 0.2883 |
|
| 261 |
+
| 0.1177 | 3.79 | 18400 | 0.2883 |
|
| 262 |
+
| 0.1254 | 3.8 | 18450 | 0.2893 |
|
| 263 |
+
| 0.136 | 3.81 | 18500 | 0.2892 |
|
| 264 |
+
| 0.1239 | 3.82 | 18550 | 0.2879 |
|
| 265 |
+
| 0.1229 | 3.83 | 18600 | 0.2882 |
|
| 266 |
+
| 0.1164 | 3.84 | 18650 | 0.2882 |
|
| 267 |
+
| 0.1354 | 3.85 | 18700 | 0.2873 |
|
| 268 |
+
| 0.1167 | 3.86 | 18750 | 0.2873 |
|
| 269 |
+
| 0.1161 | 3.87 | 18800 | 0.2876 |
|
| 270 |
+
| 0.112 | 3.88 | 18850 | 0.2883 |
|
| 271 |
+
| 0.1053 | 3.89 | 18900 | 0.2882 |
|
| 272 |
+
| 0.1114 | 3.9 | 18950 | 0.2879 |
|
| 273 |
+
| 0.1104 | 3.91 | 19000 | 0.2877 |
|
| 274 |
+
| 0.1095 | 3.92 | 19050 | 0.2874 |
|
| 275 |
+
| 0.123 | 3.93 | 19100 | 0.2881 |
|
| 276 |
+
| 0.1163 | 3.94 | 19150 | 0.2879 |
|
| 277 |
+
| 0.1261 | 3.95 | 19200 | 0.2881 |
|
| 278 |
+
| 0.1151 | 3.96 | 19250 | 0.2880 |
|
| 279 |
+
| 0.133 | 3.97 | 19300 | 0.2879 |
|
| 280 |
+
| 0.1182 | 3.98 | 19350 | 0.2878 |
|
| 281 |
+
| 0.1144 | 3.99 | 19400 | 0.2878 |
|
| 282 |
|
| 283 |
|
| 284 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"k_proj",
|
| 24 |
-
"gate_proj",
|
| 25 |
-
"v_proj",
|
| 26 |
-
"down_proj",
|
| 27 |
"q_proj",
|
| 28 |
"o_proj",
|
| 29 |
-
"up_proj"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"q_proj",
|
| 24 |
"o_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2332095256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b381f2ecf8765edf09debb574855dbff7ac998d4698ca057175cebeaa71346c
|
| 3 |
size 2332095256
|
runs/Apr16_06-42-36_f519ac071db6/events.out.tfevents.1713249766.f519ac071db6.2993.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:779287d26d81fe499db37ff19ae8f0652ae96d99c2b971d229bc27e6a6f3b1f1
|
| 3 |
+
size 150024
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b702b23936b5d4b2d52125a8dad797baf704f788801255df98e71917b490daca
|
| 3 |
size 4984
|