--- license: llama2 library_name: peft tags: - trl - sft - generated_from_trainer base_model: codellama/CodeLlama-7b-Instruct-hf model-index: - name: Codellama-7b-lora-rps-adapter results: [] --- # Codellama-7b-lora-rps-adapter 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. It achieves the following results on the evaluation set: - Loss: 0.3206 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 6 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 0.3007 | 1.18 | 5000 | 0.3014 | | 0.2978 | 1.19 | 5050 | 0.3082 | | 0.2726 | 1.2 | 5100 | 0.3060 | | 0.2735 | 1.22 | 5150 | 0.3104 | | 0.3216 | 1.23 | 5200 | 0.3058 | | 0.258 | 1.24 | 5250 | 0.3076 | | 0.278 | 1.25 | 5300 | 0.3095 | | 0.2924 | 1.26 | 5350 | 0.3031 | | 0.279 | 1.28 | 5400 | 0.3058 | | 0.3125 | 1.29 | 5450 | 0.3009 | | 0.329 | 1.3 | 5500 | 0.3064 | | 0.2547 | 1.31 | 5550 | 0.3086 | | 0.3001 | 1.32 | 5600 | 0.3027 | | 0.2804 | 1.33 | 5650 | 0.3034 | | 0.3309 | 1.35 | 5700 | 0.3014 | | 0.3186 | 1.36 | 5750 | 0.3030 | | 0.2765 | 1.37 | 5800 | 0.3011 | | 0.2961 | 1.38 | 5850 | 0.3014 | | 0.2825 | 1.39 | 5900 | 0.3006 | | 0.2932 | 1.41 | 5950 | 0.2986 | | 0.2905 | 1.42 | 6000 | 0.3113 | | 0.2656 | 1.43 | 6050 | 0.2986 | | 0.27 | 1.44 | 6100 | 0.3008 | | 0.2808 | 1.45 | 6150 | 0.2972 | | 0.3102 | 1.46 | 6200 | 0.2933 | | 0.2885 | 1.48 | 6250 | 0.2958 | | 0.315 | 1.49 | 6300 | 0.2965 | | 0.3396 | 1.5 | 6350 | 0.2956 | | 0.2955 | 1.51 | 6400 | 0.2917 | | 0.2986 | 1.52 | 6450 | 0.2919 | | 0.2952 | 1.54 | 6500 | 0.2924 | | 0.2483 | 1.55 | 6550 | 0.2926 | | 0.3115 | 1.56 | 6600 | 0.2938 | | 0.3432 | 1.57 | 6650 | 0.2873 | | 0.2858 | 1.58 | 6700 | 0.2863 | | 0.256 | 1.59 | 6750 | 0.2909 | | 0.2594 | 1.61 | 6800 | 0.2918 | | 0.2719 | 1.62 | 6850 | 0.2915 | | 0.2781 | 1.63 | 6900 | 0.2891 | | 0.2827 | 1.64 | 6950 | 0.2887 | | 0.2692 | 1.65 | 7000 | 0.2906 | | 0.2931 | 1.67 | 7050 | 0.2925 | | 0.3297 | 1.68 | 7100 | 0.2902 | | 0.2818 | 1.69 | 7150 | 0.2894 | | 0.321 | 1.7 | 7200 | 0.2874 | | 0.2855 | 1.71 | 7250 | 0.2866 | | 0.2638 | 1.72 | 7300 | 0.2897 | | 0.2806 | 1.74 | 7350 | 0.2902 | | 0.3048 | 1.75 | 7400 | 0.2902 | | 0.2755 | 1.76 | 7450 | 0.2862 | | 0.3178 | 1.77 | 7500 | 0.2880 | | 0.2741 | 1.78 | 7550 | 0.2880 | | 0.3232 | 1.8 | 7600 | 0.2877 | | 0.2843 | 1.81 | 7650 | 0.2859 | | 0.2774 | 1.82 | 7700 | 0.2863 | | 0.3258 | 1.83 | 7750 | 0.2857 | | 0.2939 | 1.84 | 7800 | 0.2865 | | 0.2987 | 1.85 | 7850 | 0.2876 | | 0.2934 | 1.87 | 7900 | 0.2809 | | 0.2916 | 1.88 | 7950 | 0.2816 | | 0.2805 | 1.89 | 8000 | 0.2828 | | 0.3092 | 1.9 | 8050 | 0.2842 | | 0.32 | 1.91 | 8100 | 0.2816 | | 0.2644 | 1.93 | 8150 | 0.2847 | | 0.2646 | 1.94 | 8200 | 0.2845 | | 0.3287 | 1.95 | 8250 | 0.2841 | | 0.2667 | 1.96 | 8300 | 0.2834 | | 0.2657 | 1.97 | 8350 | 0.2837 | | 0.2937 | 1.98 | 8400 | 0.2823 | | 0.3119 | 2.0 | 8450 | 0.2782 | | 0.241 | 2.01 | 8500 | 0.2938 | | 0.2399 | 2.02 | 8550 | 0.2873 | | 0.209 | 2.03 | 8600 | 0.2897 | | 0.2162 | 2.04 | 8650 | 0.2923 | | 0.2233 | 2.06 | 8700 | 0.2936 | | 0.2133 | 2.07 | 8750 | 0.2872 | | 0.2085 | 2.08 | 8800 | 0.2909 | | 0.2502 | 2.09 | 8850 | 0.2892 | | 0.2509 | 2.1 | 8900 | 0.2937 | | 0.2101 | 2.11 | 8950 | 0.2908 | | 0.2182 | 2.13 | 9000 | 0.2897 | | 0.2154 | 2.14 | 9050 | 0.2934 | | 0.2121 | 2.15 | 9100 | 0.2925 | | 0.1998 | 2.16 | 9150 | 0.2927 | | 0.2292 | 2.17 | 9200 | 0.2915 | | 0.2196 | 2.19 | 9250 | 0.2927 | | 0.2435 | 2.2 | 9300 | 0.2851 | | 0.2135 | 2.21 | 9350 | 0.2898 | | 0.2079 | 2.22 | 9400 | 0.2907 | | 0.1996 | 2.23 | 9450 | 0.2880 | | 0.2122 | 2.24 | 9500 | 0.2877 | | 0.2678 | 2.26 | 9550 | 0.2885 | | 0.2546 | 2.27 | 9600 | 0.2890 | | 0.2662 | 2.28 | 9650 | 0.2865 | | 0.2255 | 2.29 | 9700 | 0.2851 | | 0.2413 | 2.3 | 9750 | 0.2857 | | 0.2527 | 2.32 | 9800 | 0.2857 | | 0.2195 | 2.33 | 9850 | 0.2856 | | 0.2425 | 2.34 | 9900 | 0.2869 | | 0.234 | 2.35 | 9950 | 0.2850 | | 0.2203 | 2.36 | 10000 | 0.2861 | | 0.234 | 2.37 | 10050 | 0.2853 | | 0.2561 | 2.39 | 10100 | 0.2822 | | 0.2553 | 2.4 | 10150 | 0.2846 | | 0.2446 | 2.41 | 10200 | 0.2847 | | 0.2265 | 2.42 | 10250 | 0.2831 | | 0.206 | 2.43 | 10300 | 0.2869 | | 0.2478 | 2.45 | 10350 | 0.2833 | | 0.2107 | 2.46 | 10400 | 0.2856 | | 0.2076 | 2.47 | 10450 | 0.2854 | | 0.224 | 2.48 | 10500 | 0.2859 | | 0.2118 | 2.49 | 10550 | 0.2841 | | 0.2346 | 2.5 | 10600 | 0.2820 | | 0.2395 | 2.52 | 10650 | 0.2786 | | 0.264 | 2.53 | 10700 | 0.2826 | | 0.2298 | 2.54 | 10750 | 0.2805 | | 0.2041 | 2.55 | 10800 | 0.2792 | | 0.2108 | 2.56 | 10850 | 0.2774 | | 0.2487 | 2.58 | 10900 | 0.2802 | | 0.2365 | 2.59 | 10950 | 0.2814 | | 0.2233 | 2.6 | 11000 | 0.2812 | | 0.2192 | 2.61 | 11050 | 0.2801 | | 0.2113 | 2.62 | 11100 | 0.2828 | | 0.2286 | 2.63 | 11150 | 0.2779 | | 0.2251 | 2.65 | 11200 | 0.2792 | | 0.2161 | 2.66 | 11250 | 0.2789 | | 0.2213 | 2.67 | 11300 | 0.2782 | | 0.2063 | 2.68 | 11350 | 0.2791 | | 0.2042 | 2.69 | 11400 | 0.2789 | | 0.188 | 2.7 | 11450 | 0.2793 | | 0.2181 | 2.72 | 11500 | 0.2767 | | 0.2187 | 2.73 | 11550 | 0.2784 | | 0.2255 | 2.74 | 11600 | 0.2782 | | 0.2529 | 2.75 | 11650 | 0.2753 | | 0.2164 | 2.76 | 11700 | 0.2763 | | 0.2039 | 2.78 | 11750 | 0.2766 | | 0.2238 | 2.79 | 11800 | 0.2742 | | 0.2393 | 2.8 | 11850 | 0.2757 | | 0.2235 | 2.81 | 11900 | 0.2776 | | 0.1983 | 2.82 | 11950 | 0.2778 | | 0.2078 | 2.83 | 12000 | 0.2757 | | 0.2487 | 2.85 | 12050 | 0.2748 | | 0.2134 | 2.86 | 12100 | 0.2783 | | 0.2503 | 2.87 | 12150 | 0.2772 | | 0.2481 | 2.88 | 12200 | 0.2726 | | 0.2274 | 2.89 | 12250 | 0.2755 | | 0.243 | 2.91 | 12300 | 0.2738 | | 0.2354 | 2.92 | 12350 | 0.2740 | | 0.2323 | 2.93 | 12400 | 0.2729 | | 0.2709 | 2.94 | 12450 | 0.2708 | | 0.247 | 2.95 | 12500 | 0.2732 | | 0.2242 | 2.96 | 12550 | 0.2727 | | 0.2283 | 2.98 | 12600 | 0.2739 | | 0.2057 | 2.99 | 12650 | 0.2730 | | 0.2255 | 3.0 | 12700 | 0.2708 | | 0.187 | 3.01 | 12750 | 0.2869 | | 0.183 | 3.02 | 12800 | 0.2857 | | 0.1653 | 3.04 | 12850 | 0.2910 | | 0.1588 | 3.05 | 12900 | 0.2869 | | 0.1742 | 3.06 | 12950 | 0.2873 | | 0.1671 | 3.07 | 13000 | 0.2935 | | 0.1506 | 3.08 | 13050 | 0.2896 | | 0.1705 | 3.09 | 13100 | 0.2854 | | 0.2033 | 3.11 | 13150 | 0.2872 | | 0.1758 | 3.12 | 13200 | 0.2857 | | 0.1483 | 3.13 | 13250 | 0.2875 | | 0.1506 | 3.14 | 13300 | 0.2872 | | 0.1602 | 3.15 | 13350 | 0.2874 | | 0.1678 | 3.17 | 13400 | 0.2918 | | 0.189 | 3.18 | 13450 | 0.2877 | | 0.1654 | 3.19 | 13500 | 0.2878 | | 0.1549 | 3.2 | 13550 | 0.2908 | | 0.1669 | 3.21 | 13600 | 0.2886 | | 0.1586 | 3.22 | 13650 | 0.2905 | | 0.1714 | 3.24 | 13700 | 0.2858 | | 0.1503 | 3.25 | 13750 | 0.2857 | | 0.1706 | 3.26 | 13800 | 0.2889 | | 0.1692 | 3.27 | 13850 | 0.2851 | | 0.1828 | 3.28 | 13900 | 0.2877 | | 0.1567 | 3.3 | 13950 | 0.2861 | | 0.1559 | 3.31 | 14000 | 0.2897 | | 0.1752 | 3.32 | 14050 | 0.2899 | | 0.1702 | 3.33 | 14100 | 0.2870 | | 0.1536 | 3.34 | 14150 | 0.2900 | | 0.1771 | 3.35 | 14200 | 0.2881 | | 0.1705 | 3.37 | 14250 | 0.2871 | | 0.1679 | 3.38 | 14300 | 0.2840 | | 0.1662 | 3.39 | 14350 | 0.2862 | | 0.1502 | 3.4 | 14400 | 0.2881 | | 0.1694 | 3.41 | 14450 | 0.2871 | | 0.1699 | 3.43 | 14500 | 0.2840 | | 0.1705 | 3.44 | 14550 | 0.2877 | | 0.1741 | 3.45 | 14600 | 0.2874 | | 0.1654 | 3.46 | 14650 | 0.2854 | | 0.1956 | 3.47 | 14700 | 0.2845 | | 0.1659 | 3.48 | 14750 | 0.2860 | | 0.18 | 3.5 | 14800 | 0.2826 | | 0.1645 | 3.51 | 14850 | 0.2829 | | 0.1835 | 3.52 | 14900 | 0.2828 | | 0.1645 | 3.53 | 14950 | 0.2839 | | 0.1843 | 3.54 | 15000 | 0.2833 | | 0.1796 | 3.56 | 15050 | 0.2799 | | 0.1639 | 3.57 | 15100 | 0.2839 | | 0.169 | 3.58 | 15150 | 0.2809 | | 0.1568 | 3.59 | 15200 | 0.2817 | | 0.1971 | 3.6 | 15250 | 0.2819 | | 0.1702 | 3.61 | 15300 | 0.2787 | | 0.1778 | 3.63 | 15350 | 0.2792 | | 0.1862 | 3.64 | 15400 | 0.2786 | | 0.1691 | 3.65 | 15450 | 0.2840 | | 0.1679 | 3.66 | 15500 | 0.2844 | | 0.1693 | 3.67 | 15550 | 0.2801 | | 0.1622 | 3.69 | 15600 | 0.2773 | | 0.1533 | 3.7 | 15650 | 0.2800 | | 0.1674 | 3.71 | 15700 | 0.2786 | | 0.1711 | 3.72 | 15750 | 0.2784 | | 0.1683 | 3.73 | 15800 | 0.2797 | | 0.1807 | 3.74 | 15850 | 0.2781 | | 0.1698 | 3.76 | 15900 | 0.2779 | | 0.1557 | 3.77 | 15950 | 0.2799 | | 0.1801 | 3.78 | 16000 | 0.2783 | | 0.184 | 3.79 | 16050 | 0.2765 | | 0.1907 | 3.8 | 16100 | 0.2759 | | 0.1626 | 3.82 | 16150 | 0.2766 | | 0.1524 | 3.83 | 16200 | 0.2803 | | 0.1574 | 3.84 | 16250 | 0.2784 | | 0.1669 | 3.85 | 16300 | 0.2808 | | 0.1888 | 3.86 | 16350 | 0.2782 | | 0.1847 | 3.87 | 16400 | 0.2779 | | 0.1846 | 3.89 | 16450 | 0.2783 | | 0.183 | 3.9 | 16500 | 0.2783 | | 0.1573 | 3.91 | 16550 | 0.2781 | | 0.1729 | 3.92 | 16600 | 0.2788 | | 0.1626 | 3.93 | 16650 | 0.2771 | | 0.177 | 3.95 | 16700 | 0.2770 | | 0.1529 | 3.96 | 16750 | 0.2773 | | 0.1712 | 3.97 | 16800 | 0.2734 | | 0.1748 | 3.98 | 16850 | 0.2740 | | 0.1555 | 3.99 | 16900 | 0.2729 | | 0.1464 | 4.0 | 16950 | 0.2843 | | 0.1393 | 4.02 | 17000 | 0.2933 | | 0.1237 | 4.03 | 17050 | 0.2943 | | 0.1168 | 4.04 | 17100 | 0.2953 | | 0.1121 | 4.05 | 17150 | 0.2948 | | 0.1169 | 4.06 | 17200 | 0.2933 | | 0.1209 | 4.08 | 17250 | 0.2936 | | 0.1145 | 4.09 | 17300 | 0.2953 | | 0.1143 | 4.1 | 17350 | 0.2946 | | 0.1341 | 4.11 | 17400 | 0.2966 | | 0.1299 | 4.12 | 17450 | 0.2921 | | 0.1162 | 4.13 | 17500 | 0.2917 | | 0.1175 | 4.15 | 17550 | 0.2937 | | 0.1185 | 4.16 | 17600 | 0.2940 | | 0.1185 | 4.17 | 17650 | 0.2922 | | 0.1332 | 4.18 | 17700 | 0.2916 | | 0.13 | 4.19 | 17750 | 0.2916 | | 0.1301 | 4.21 | 17800 | 0.2921 | | 0.1196 | 4.22 | 17850 | 0.2921 | | 0.1169 | 4.23 | 17900 | 0.2924 | | 0.1079 | 4.24 | 17950 | 0.2977 | | 0.1103 | 4.25 | 18000 | 0.2945 | | 0.1205 | 4.26 | 18050 | 0.2919 | | 0.1191 | 4.28 | 18100 | 0.2918 | | 0.1271 | 4.29 | 18150 | 0.2924 | | 0.1181 | 4.3 | 18200 | 0.2934 | | 0.1151 | 4.31 | 18250 | 0.2935 | | 0.1323 | 4.32 | 18300 | 0.2922 | | 0.1073 | 4.33 | 18350 | 0.2940 | | 0.1173 | 4.35 | 18400 | 0.2898 | | 0.118 | 4.36 | 18450 | 0.2937 | | 0.122 | 4.37 | 18500 | 0.2921 | | 0.1276 | 4.38 | 18550 | 0.2899 | | 0.145 | 4.39 | 18600 | 0.2918 | | 0.1219 | 4.41 | 18650 | 0.2943 | | 0.1198 | 4.42 | 18700 | 0.2917 | | 0.1242 | 4.43 | 18750 | 0.2926 | | 0.1188 | 4.44 | 18800 | 0.2939 | | 0.1098 | 4.45 | 18850 | 0.2946 | | 0.1163 | 4.46 | 18900 | 0.2912 | | 0.1181 | 4.48 | 18950 | 0.2912 | | 0.1341 | 4.49 | 19000 | 0.2903 | | 0.1198 | 4.5 | 19050 | 0.2890 | | 0.1234 | 4.51 | 19100 | 0.2892 | | 0.1192 | 4.52 | 19150 | 0.2933 | | 0.1185 | 4.54 | 19200 | 0.2932 | | 0.1122 | 4.55 | 19250 | 0.2925 | | 0.1259 | 4.56 | 19300 | 0.2877 | | 0.1218 | 4.57 | 19350 | 0.2903 | | 0.1245 | 4.58 | 19400 | 0.2894 | | 0.1086 | 4.59 | 19450 | 0.2914 | | 0.1234 | 4.61 | 19500 | 0.2924 | | 0.1238 | 4.62 | 19550 | 0.2929 | | 0.1162 | 4.63 | 19600 | 0.2931 | | 0.1271 | 4.64 | 19650 | 0.2910 | | 0.1165 | 4.65 | 19700 | 0.2875 | | 0.125 | 4.67 | 19750 | 0.2902 | | 0.122 | 4.68 | 19800 | 0.2882 | | 0.115 | 4.69 | 19850 | 0.2896 | | 0.1112 | 4.7 | 19900 | 0.2904 | | 0.1215 | 4.71 | 19950 | 0.2901 | | 0.1241 | 4.72 | 20000 | 0.2912 | | 0.1181 | 4.74 | 20050 | 0.2911 | | 0.1215 | 4.75 | 20100 | 0.2901 | | 0.1196 | 4.76 | 20150 | 0.2907 | | 0.1205 | 4.77 | 20200 | 0.2919 | | 0.1237 | 4.78 | 20250 | 0.2915 | | 0.127 | 4.8 | 20300 | 0.2888 | | 0.1108 | 4.81 | 20350 | 0.2923 | | 0.1064 | 4.82 | 20400 | 0.2925 | | 0.1238 | 4.83 | 20450 | 0.2899 | | 0.1213 | 4.84 | 20500 | 0.2894 | | 0.1325 | 4.85 | 20550 | 0.2891 | | 0.1219 | 4.87 | 20600 | 0.2894 | | 0.12 | 4.88 | 20650 | 0.2912 | | 0.1241 | 4.89 | 20700 | 0.2878 | | 0.1258 | 4.9 | 20750 | 0.2873 | | 0.1201 | 4.91 | 20800 | 0.2900 | | 0.1136 | 4.93 | 20850 | 0.2892 | | 0.1308 | 4.94 | 20900 | 0.2879 | | 0.1143 | 4.95 | 20950 | 0.2879 | | 0.1161 | 4.96 | 21000 | 0.2911 | | 0.108 | 4.97 | 21050 | 0.2884 | | 0.1326 | 4.98 | 21100 | 0.2853 | | 0.1127 | 5.0 | 21150 | 0.2887 | | 0.0953 | 5.01 | 21200 | 0.3096 | | 0.078 | 5.02 | 21250 | 0.3143 | | 0.0815 | 5.03 | 21300 | 0.3126 | | 0.0732 | 5.04 | 21350 | 0.3179 | | 0.083 | 5.06 | 21400 | 0.3153 | | 0.0726 | 5.07 | 21450 | 0.3163 | | 0.073 | 5.08 | 21500 | 0.3144 | | 0.0787 | 5.09 | 21550 | 0.3164 | | 0.0763 | 5.1 | 21600 | 0.3146 | | 0.0735 | 5.11 | 21650 | 0.3133 | | 0.0809 | 5.13 | 21700 | 0.3179 | | 0.0745 | 5.14 | 21750 | 0.3136 | | 0.0803 | 5.15 | 21800 | 0.3153 | | 0.0808 | 5.16 | 21850 | 0.3173 | | 0.0735 | 5.17 | 21900 | 0.3194 | | 0.0773 | 5.19 | 21950 | 0.3181 | | 0.0758 | 5.2 | 22000 | 0.3199 | | 0.0758 | 5.21 | 22050 | 0.3183 | | 0.0735 | 5.22 | 22100 | 0.3158 | | 0.0791 | 5.23 | 22150 | 0.3178 | | 0.0828 | 5.24 | 22200 | 0.3190 | | 0.0694 | 5.26 | 22250 | 0.3199 | | 0.0745 | 5.27 | 22300 | 0.3190 | | 0.0728 | 5.28 | 22350 | 0.3194 | | 0.0716 | 5.29 | 22400 | 0.3211 | | 0.0756 | 5.3 | 22450 | 0.3188 | | 0.0713 | 5.32 | 22500 | 0.3188 | | 0.0772 | 5.33 | 22550 | 0.3199 | | 0.0809 | 5.34 | 22600 | 0.3184 | | 0.0739 | 5.35 | 22650 | 0.3189 | | 0.0739 | 5.36 | 22700 | 0.3186 | | 0.0815 | 5.37 | 22750 | 0.3177 | | 0.0734 | 5.39 | 22800 | 0.3183 | | 0.084 | 5.4 | 22850 | 0.3168 | | 0.0736 | 5.41 | 22900 | 0.3188 | | 0.0761 | 5.42 | 22950 | 0.3188 | | 0.0735 | 5.43 | 23000 | 0.3183 | | 0.075 | 5.45 | 23050 | 0.3187 | | 0.0767 | 5.46 | 23100 | 0.3192 | | 0.0856 | 5.47 | 23150 | 0.3182 | | 0.0695 | 5.48 | 23200 | 0.3210 | | 0.0754 | 5.49 | 23250 | 0.3207 | | 0.0795 | 5.5 | 23300 | 0.3197 | | 0.0733 | 5.52 | 23350 | 0.3196 | | 0.076 | 5.53 | 23400 | 0.3217 | | 0.0764 | 5.54 | 23450 | 0.3197 | | 0.0742 | 5.55 | 23500 | 0.3212 | | 0.075 | 5.56 | 23550 | 0.3211 | | 0.078 | 5.58 | 23600 | 0.3196 | | 0.0798 | 5.59 | 23650 | 0.3200 | | 0.0736 | 5.6 | 23700 | 0.3181 | | 0.0848 | 5.61 | 23750 | 0.3184 | | 0.0752 | 5.62 | 23800 | 0.3193 | | 0.0732 | 5.63 | 23850 | 0.3186 | | 0.0788 | 5.65 | 23900 | 0.3175 | | 0.0822 | 5.66 | 23950 | 0.3186 | | 0.0772 | 5.67 | 24000 | 0.3195 | | 0.0779 | 5.68 | 24050 | 0.3197 | | 0.0778 | 5.69 | 24100 | 0.3202 | | 0.0765 | 5.71 | 24150 | 0.3207 | | 0.0819 | 5.72 | 24200 | 0.3193 | | 0.0767 | 5.73 | 24250 | 0.3204 | | 0.0726 | 5.74 | 24300 | 0.3214 | | 0.0911 | 5.75 | 24350 | 0.3212 | | 0.0665 | 5.76 | 24400 | 0.3208 | | 0.0733 | 5.78 | 24450 | 0.3208 | | 0.0745 | 5.79 | 24500 | 0.3202 | | 0.0735 | 5.8 | 24550 | 0.3203 | | 0.0717 | 5.81 | 24600 | 0.3202 | | 0.0693 | 5.82 | 24650 | 0.3203 | | 0.0748 | 5.84 | 24700 | 0.3198 | | 0.0722 | 5.85 | 24750 | 0.3203 | | 0.0805 | 5.86 | 24800 | 0.3205 | | 0.0761 | 5.87 | 24850 | 0.3210 | | 0.0706 | 5.88 | 24900 | 0.3208 | | 0.0701 | 5.89 | 24950 | 0.3213 | | 0.0776 | 5.91 | 25000 | 0.3210 | | 0.081 | 5.92 | 25050 | 0.3208 | | 0.0698 | 5.93 | 25100 | 0.3207 | | 0.0708 | 5.94 | 25150 | 0.3208 | | 0.0785 | 5.95 | 25200 | 0.3206 | | 0.0708 | 5.97 | 25250 | 0.3206 | | 0.0721 | 5.98 | 25300 | 0.3206 | | 0.0718 | 5.99 | 25350 | 0.3206 | ### Framework versions - PEFT 0.10.0 - Transformers 4.39.1 - Pytorch 2.2.1+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2