Gayathri142214002's picture
update model card README.md
d722ba1
---
tags:
- generated_from_trainer
model-index:
- name: Pegasus_paraphraser_1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Pegasus_paraphraser_1
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2991
## 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.0688 | 0.01 | 10 | 0.2457 |
| 0.2896 | 0.01 | 20 | 0.2403 |
| 0.2359 | 0.02 | 30 | 0.2326 |
| 0.3123 | 0.02 | 40 | 0.2367 |
| 0.2913 | 0.03 | 50 | 0.2309 |
| 0.2572 | 0.03 | 60 | 0.2256 |
| 0.2803 | 0.04 | 70 | 0.2263 |
| 0.2946 | 0.04 | 80 | 0.2243 |
| 0.2211 | 0.05 | 90 | 0.2283 |
| 0.2161 | 0.05 | 100 | 0.2405 |
| 0.2927 | 0.06 | 110 | 0.2355 |
| 0.3544 | 0.07 | 120 | 0.2330 |
| 0.2933 | 0.07 | 130 | 0.2322 |
| 0.2535 | 0.08 | 140 | 0.2301 |
| 0.2799 | 0.08 | 150 | 0.2302 |
| 0.2532 | 0.09 | 160 | 0.2296 |
| 0.2382 | 0.09 | 170 | 0.2356 |
| 0.2758 | 0.1 | 180 | 0.2376 |
| 0.2552 | 0.1 | 190 | 0.2451 |
| 0.289 | 0.11 | 200 | 0.2439 |
| 0.247 | 0.11 | 210 | 0.2424 |
| 0.259 | 0.12 | 220 | 0.2448 |
| 0.2562 | 0.13 | 230 | 0.2491 |
| 0.2951 | 0.13 | 240 | 0.2554 |
| 0.2624 | 0.14 | 250 | 0.2476 |
| 0.2542 | 0.14 | 260 | 0.2474 |
| 0.2178 | 0.15 | 270 | 0.2501 |
| 0.3126 | 0.15 | 280 | 0.2483 |
| 0.2585 | 0.16 | 290 | 0.2492 |
| 0.2559 | 0.16 | 300 | 0.2502 |
| 0.231 | 0.17 | 310 | 0.2539 |
| 0.3023 | 0.17 | 320 | 0.2486 |
| 0.328 | 0.18 | 330 | 0.2491 |
| 0.313 | 0.19 | 340 | 0.2490 |
| 0.3041 | 0.19 | 350 | 0.2471 |
| 0.2719 | 0.2 | 360 | 0.2433 |
| 0.2655 | 0.2 | 370 | 0.2443 |
| 0.3171 | 0.21 | 380 | 0.2453 |
| 0.2398 | 0.21 | 390 | 0.2440 |
| 0.2682 | 0.22 | 400 | 0.2477 |
| 0.3193 | 0.22 | 410 | 0.2476 |
| 0.2754 | 0.23 | 420 | 0.2455 |
| 0.2635 | 0.23 | 430 | 0.2451 |
| 0.2593 | 0.24 | 440 | 0.2479 |
| 0.2955 | 0.25 | 450 | 0.2454 |
| 0.2923 | 0.25 | 460 | 0.2472 |
| 0.2947 | 0.26 | 470 | 0.2488 |
| 0.2718 | 0.26 | 480 | 0.2503 |
| 0.2772 | 0.27 | 490 | 0.2507 |
| 0.2183 | 0.27 | 500 | 0.2545 |
| 0.3563 | 0.28 | 510 | 0.2574 |
| 0.2762 | 0.28 | 520 | 0.2585 |
| 0.2336 | 0.29 | 530 | 0.2537 |
| 0.2548 | 0.29 | 540 | 0.2550 |
| 0.315 | 0.3 | 550 | 0.2625 |
| 0.2827 | 0.31 | 560 | 0.2641 |
| 0.2911 | 0.31 | 570 | 0.2621 |
| 0.2515 | 0.32 | 580 | 0.2625 |
| 0.3003 | 0.32 | 590 | 0.2665 |
| 0.2987 | 0.33 | 600 | 0.2653 |
| 0.3119 | 0.33 | 610 | 0.2622 |
| 0.305 | 0.34 | 620 | 0.2638 |
| 0.2828 | 0.34 | 630 | 0.2637 |
| 0.2416 | 0.35 | 640 | 0.2641 |
| 0.2829 | 0.35 | 650 | 0.2642 |
| 0.2757 | 0.36 | 660 | 0.2645 |
| 0.2548 | 0.37 | 670 | 0.2640 |
| 0.2737 | 0.37 | 680 | 0.2607 |
| 0.2963 | 0.38 | 690 | 0.2673 |
| 0.2622 | 0.38 | 700 | 0.2641 |
| 0.2773 | 0.39 | 710 | 0.2673 |
| 0.2883 | 0.39 | 720 | 0.2666 |
| 0.2855 | 0.4 | 730 | 0.2685 |
| 0.271 | 0.4 | 740 | 0.2655 |
| 0.2627 | 0.41 | 750 | 0.2673 |
| 0.2739 | 0.41 | 760 | 0.2677 |
| 0.2539 | 0.42 | 770 | 0.2702 |
| 0.2824 | 0.43 | 780 | 0.2723 |
| 0.3174 | 0.43 | 790 | 0.2767 |
| 0.2902 | 0.44 | 800 | 0.2790 |
| 0.2755 | 0.44 | 810 | 0.2701 |
| 0.253 | 0.45 | 820 | 0.2711 |
| 0.2619 | 0.45 | 830 | 0.2708 |
| 0.2819 | 0.46 | 840 | 0.2706 |
| 0.2686 | 0.46 | 850 | 0.2683 |
| 0.2683 | 0.47 | 860 | 0.2734 |
| 0.2702 | 0.47 | 870 | 0.2695 |
| 0.2793 | 0.48 | 880 | 0.2771 |
| 0.2807 | 0.49 | 890 | 0.2753 |
| 0.3387 | 0.49 | 900 | 0.2695 |
| 0.2924 | 0.5 | 910 | 0.2670 |
| 0.3004 | 0.5 | 920 | 0.2669 |
| 0.2653 | 0.51 | 930 | 0.2760 |
| 0.241 | 0.51 | 940 | 0.2700 |
| 0.2828 | 0.52 | 950 | 0.2704 |
| 0.2804 | 0.52 | 960 | 0.2707 |
| 0.2888 | 0.53 | 970 | 0.2672 |
| 0.3065 | 0.54 | 980 | 0.2678 |
| 0.2853 | 0.54 | 990 | 0.2706 |
| 0.2579 | 0.55 | 1000 | 0.2685 |
| 0.3108 | 0.55 | 1010 | 0.2679 |
| 0.3061 | 0.56 | 1020 | 0.2687 |
| 0.2836 | 0.56 | 1030 | 0.2688 |
| 0.2081 | 0.57 | 1040 | 0.2769 |
| 0.312 | 0.57 | 1050 | 0.2770 |
| 0.29 | 0.58 | 1060 | 0.2701 |
| 0.3126 | 0.58 | 1070 | 0.2699 |
| 0.3559 | 0.59 | 1080 | 0.2690 |
| 0.3611 | 0.6 | 1090 | 0.2864 |
| 0.3906 | 0.6 | 1100 | 0.4051 |
| 0.3261 | 0.61 | 1110 | 0.2743 |
| 0.2893 | 0.61 | 1120 | 0.2725 |
| 0.2796 | 0.62 | 1130 | 0.2713 |
| 0.289 | 0.62 | 1140 | 0.2717 |
| 0.29 | 0.63 | 1150 | 0.2718 |
| 0.2983 | 0.63 | 1160 | 0.2729 |
| 0.3058 | 0.64 | 1170 | 0.2696 |
| 0.23 | 0.64 | 1180 | 0.2731 |
| 0.2558 | 0.65 | 1190 | 0.2748 |
| 0.3722 | 0.66 | 1200 | 0.2740 |
| 0.3308 | 0.66 | 1210 | 0.2718 |
| 0.27 | 0.67 | 1220 | 0.2724 |
| 0.2897 | 0.67 | 1230 | 0.2750 |
| 0.2954 | 0.68 | 1240 | 0.2776 |
| 0.264 | 0.68 | 1250 | 0.2737 |
| 0.2802 | 0.69 | 1260 | 0.2738 |
| 0.3027 | 0.69 | 1270 | 0.2702 |
| 0.2881 | 0.7 | 1280 | 0.2701 |
| 0.2664 | 0.7 | 1290 | 0.2699 |
| 0.3288 | 0.71 | 1300 | 0.2707 |
| 0.3315 | 0.72 | 1310 | 0.2686 |
| 0.3577 | 0.72 | 1320 | 0.2686 |
| 0.3046 | 0.73 | 1330 | 0.2702 |
| 0.2872 | 0.73 | 1340 | 0.2697 |
| 0.3242 | 0.74 | 1350 | 0.2693 |
| 0.3268 | 0.74 | 1360 | 0.2704 |
| 0.2845 | 0.75 | 1370 | 0.2756 |
| 0.2816 | 0.75 | 1380 | 0.2705 |
| 0.3121 | 0.76 | 1390 | 0.2678 |
| 0.2989 | 0.76 | 1400 | 0.2687 |
| 0.2611 | 0.77 | 1410 | 0.2701 |
| 0.2954 | 0.78 | 1420 | 0.2711 |
| 0.3025 | 0.78 | 1430 | 0.2711 |
| 0.2692 | 0.79 | 1440 | 0.2732 |
| 0.249 | 0.79 | 1450 | 0.2753 |
| 0.2673 | 0.8 | 1460 | 0.2779 |
| 0.2471 | 0.8 | 1470 | 0.2829 |
| 0.2925 | 0.81 | 1480 | 0.2806 |
| 0.3005 | 0.81 | 1490 | 0.2785 |
| 0.3009 | 0.82 | 1500 | 0.2765 |
| 0.2556 | 0.82 | 1510 | 0.2740 |
| 0.3265 | 0.83 | 1520 | 0.2775 |
| 0.2731 | 0.84 | 1530 | 0.2816 |
| 0.3406 | 0.84 | 1540 | 0.2767 |
| 0.2936 | 0.85 | 1550 | 0.2760 |
| 0.3001 | 0.85 | 1560 | 0.2737 |
| 0.3017 | 0.86 | 1570 | 0.2755 |
| 0.3212 | 0.86 | 1580 | 0.2784 |
| 0.3122 | 0.87 | 1590 | 0.2742 |
| 0.2591 | 0.87 | 1600 | 0.2720 |
| 0.28 | 0.88 | 1610 | 0.2736 |
| 0.2641 | 0.88 | 1620 | 0.2736 |
| 0.3488 | 0.89 | 1630 | 0.2715 |
| 0.3505 | 0.9 | 1640 | 0.2701 |
| 0.2676 | 0.9 | 1650 | 0.2699 |
| 0.2444 | 0.91 | 1660 | 0.2711 |
| 0.2493 | 0.91 | 1670 | 0.2732 |
| 0.326 | 0.92 | 1680 | 0.2735 |
| 0.3099 | 0.92 | 1690 | 0.2737 |
| 0.2893 | 0.93 | 1700 | 0.2717 |
| 0.3139 | 0.93 | 1710 | 0.2737 |
| 0.2913 | 0.94 | 1720 | 0.2777 |
| 0.2999 | 0.94 | 1730 | 0.2721 |
| 0.2708 | 0.95 | 1740 | 0.2704 |
| 0.3208 | 0.96 | 1750 | 0.2690 |
| 0.2691 | 0.96 | 1760 | 0.2692 |
| 0.2921 | 0.97 | 1770 | 0.2696 |
| 0.2782 | 0.97 | 1780 | 0.2706 |
| 0.2937 | 0.98 | 1790 | 0.2703 |
| 0.2948 | 0.98 | 1800 | 0.2695 |
| 0.3195 | 0.99 | 1810 | 0.2682 |
| 0.2525 | 0.99 | 1820 | 0.2678 |
| 0.2434 | 1.0 | 1830 | 0.2685 |
| 0.2043 | 1.0 | 1840 | 0.2721 |
| 0.216 | 1.01 | 1850 | 0.2733 |
| 0.1924 | 1.02 | 1860 | 0.2696 |
| 0.2219 | 1.02 | 1870 | 0.2707 |
| 0.2198 | 1.03 | 1880 | 0.2722 |
| 0.1829 | 1.03 | 1890 | 0.2735 |
| 0.247 | 1.04 | 1900 | 0.2768 |
| 0.2243 | 1.04 | 1910 | 0.2759 |
| 0.2747 | 1.05 | 1920 | 0.2769 |
| 0.187 | 1.05 | 1930 | 0.2796 |
| 0.2698 | 1.06 | 1940 | 0.2797 |
| 0.218 | 1.06 | 1950 | 0.2822 |
| 0.2155 | 1.07 | 1960 | 0.2817 |
| 0.2352 | 1.08 | 1970 | 0.2832 |
| 0.1915 | 1.08 | 1980 | 0.2799 |
| 0.2425 | 1.09 | 1990 | 0.2779 |
| 0.2212 | 1.09 | 2000 | 0.2824 |
| 0.2271 | 1.1 | 2010 | 0.2848 |
| 0.2349 | 1.1 | 2020 | 0.2851 |
| 0.2579 | 1.11 | 2030 | 0.2817 |
| 0.2097 | 1.11 | 2040 | 0.2832 |
| 0.2205 | 1.12 | 2050 | 0.2852 |
| 0.2462 | 1.12 | 2060 | 0.2868 |
| 0.2121 | 1.13 | 2070 | 0.2895 |
| 0.2251 | 1.14 | 2080 | 0.2864 |
| 0.2052 | 1.14 | 2090 | 0.2833 |
| 0.2202 | 1.15 | 2100 | 0.2851 |
| 0.2295 | 1.15 | 2110 | 0.2850 |
| 0.2419 | 1.16 | 2120 | 0.2904 |
| 0.2639 | 1.16 | 2130 | 0.2866 |
| 0.2106 | 1.17 | 2140 | 0.2913 |
| 0.2454 | 1.17 | 2150 | 0.2924 |
| 0.2348 | 1.18 | 2160 | 0.2890 |
| 0.209 | 1.18 | 2170 | 0.2885 |
| 0.2523 | 1.19 | 2180 | 0.2873 |
| 0.2293 | 1.2 | 2190 | 0.2836 |
| 0.2258 | 1.2 | 2200 | 0.2842 |
| 0.249 | 1.21 | 2210 | 0.2849 |
| 0.2917 | 1.21 | 2220 | 0.2834 |
| 0.2268 | 1.22 | 2230 | 0.2824 |
| 0.2453 | 1.22 | 2240 | 0.2820 |
| 0.236 | 1.23 | 2250 | 0.2829 |
| 0.2191 | 1.23 | 2260 | 0.2841 |
| 0.2509 | 1.24 | 2270 | 0.2822 |
| 0.2481 | 1.24 | 2280 | 0.2830 |
| 0.2268 | 1.25 | 2290 | 0.2840 |
| 0.2594 | 1.26 | 2300 | 0.2803 |
| 0.242 | 1.26 | 2310 | 0.2827 |
| 0.2563 | 1.27 | 2320 | 0.2827 |
| 0.2269 | 1.27 | 2330 | 0.2803 |
| 0.2409 | 1.28 | 2340 | 0.2780 |
| 0.2946 | 1.28 | 2350 | 0.2778 |
| 0.2718 | 1.29 | 2360 | 0.2757 |
| 0.2407 | 1.29 | 2370 | 0.2776 |
| 0.2259 | 1.3 | 2380 | 0.2810 |
| 0.2235 | 1.3 | 2390 | 0.2829 |
| 0.266 | 1.31 | 2400 | 0.2806 |
| 0.229 | 1.32 | 2410 | 0.2796 |
| 0.2154 | 1.32 | 2420 | 0.2794 |
| 0.2551 | 1.33 | 2430 | 0.2766 |
| 0.2169 | 1.33 | 2440 | 0.2779 |
| 0.2396 | 1.34 | 2450 | 0.2776 |
| 0.2239 | 1.34 | 2460 | 0.2835 |
| 0.2325 | 1.35 | 2470 | 0.2823 |
| 0.2421 | 1.35 | 2480 | 0.2841 |
| 0.2456 | 1.36 | 2490 | 0.2861 |
| 0.2295 | 1.36 | 2500 | 0.2828 |
| 0.2549 | 1.37 | 2510 | 0.2835 |
| 0.2442 | 1.38 | 2520 | 0.2832 |
| 0.2572 | 1.38 | 2530 | 0.2821 |
| 0.235 | 1.39 | 2540 | 0.2796 |
| 0.2687 | 1.39 | 2550 | 0.2791 |
| 0.2539 | 1.4 | 2560 | 0.2787 |
| 0.2496 | 1.4 | 2570 | 0.2789 |
| 0.269 | 1.41 | 2580 | 0.2806 |
| 0.2851 | 1.41 | 2590 | 0.2808 |
| 0.274 | 1.42 | 2600 | 0.2806 |
| 0.2365 | 1.42 | 2610 | 0.2814 |
| 0.2031 | 1.43 | 2620 | 0.2864 |
| 0.2371 | 1.44 | 2630 | 0.2901 |
| 0.2513 | 1.44 | 2640 | 0.2891 |
| 0.2393 | 1.45 | 2650 | 0.2843 |
| 0.2498 | 1.45 | 2660 | 0.2832 |
| 0.2634 | 1.46 | 2670 | 0.2842 |
| 0.2845 | 1.46 | 2680 | 0.2812 |
| 0.263 | 1.47 | 2690 | 0.2791 |
| 0.261 | 1.47 | 2700 | 0.2794 |
| 0.2543 | 1.48 | 2710 | 0.2802 |
| 0.278 | 1.48 | 2720 | 0.2812 |
| 0.2583 | 1.49 | 2730 | 0.2843 |
| 0.238 | 1.5 | 2740 | 0.2839 |
| 0.2525 | 1.5 | 2750 | 0.2821 |
| 0.2605 | 1.51 | 2760 | 0.2814 |
| 0.2673 | 1.51 | 2770 | 0.2826 |
| 0.2298 | 1.52 | 2780 | 0.2856 |
| 0.2409 | 1.52 | 2790 | 0.2872 |
| 0.2502 | 1.53 | 2800 | 0.2879 |
| 0.2569 | 1.53 | 2810 | 0.2864 |
| 0.2299 | 1.54 | 2820 | 0.2858 |
| 0.2508 | 1.54 | 2830 | 0.2843 |
| 0.213 | 1.55 | 2840 | 0.2839 |
| 0.2404 | 1.56 | 2850 | 0.2842 |
| 0.2626 | 1.56 | 2860 | 0.2823 |
| 0.2296 | 1.57 | 2870 | 0.2821 |
| 0.2284 | 1.57 | 2880 | 0.2834 |
| 0.2481 | 1.58 | 2890 | 0.2834 |
| 0.271 | 1.58 | 2900 | 0.2801 |
| 0.2779 | 1.59 | 2910 | 0.2796 |
| 0.2247 | 1.59 | 2920 | 0.2782 |
| 0.2334 | 1.6 | 2930 | 0.2785 |
| 0.2469 | 1.61 | 2940 | 0.2811 |
| 0.2526 | 1.61 | 2950 | 0.2801 |
| 0.2788 | 1.62 | 2960 | 0.2801 |
| 0.2463 | 1.62 | 2970 | 0.2804 |
| 0.2367 | 1.63 | 2980 | 0.2815 |
| 0.2096 | 1.63 | 2990 | 0.2822 |
| 0.2252 | 1.64 | 3000 | 0.2826 |
| 0.2724 | 1.64 | 3010 | 0.2829 |
| 0.2514 | 1.65 | 3020 | 0.2814 |
| 0.2396 | 1.65 | 3030 | 0.2802 |
| 0.2736 | 1.66 | 3040 | 0.2800 |
| 0.2549 | 1.67 | 3050 | 0.2798 |
| 0.2278 | 1.67 | 3060 | 0.2792 |
| 0.2857 | 1.68 | 3070 | 0.2798 |
| 0.249 | 1.68 | 3080 | 0.2804 |
| 0.2314 | 1.69 | 3090 | 0.2820 |
| 0.254 | 1.69 | 3100 | 0.2810 |
| 0.2812 | 1.7 | 3110 | 0.2812 |
| 0.2398 | 1.7 | 3120 | 0.2824 |
| 0.2418 | 1.71 | 3130 | 0.2839 |
| 0.2487 | 1.71 | 3140 | 0.2826 |
| 0.2839 | 1.72 | 3150 | 0.2840 |
| 0.2479 | 1.73 | 3160 | 0.2857 |
| 0.2579 | 1.73 | 3170 | 0.2834 |
| 0.2549 | 1.74 | 3180 | 0.2838 |
| 0.2406 | 1.74 | 3190 | 0.2872 |
| 0.262 | 1.75 | 3200 | 0.2879 |
| 0.2632 | 1.75 | 3210 | 0.2877 |
| 0.2256 | 1.76 | 3220 | 0.2850 |
| 0.263 | 1.76 | 3230 | 0.2837 |
| 0.27 | 1.77 | 3240 | 0.2826 |
| 0.2642 | 1.77 | 3250 | 0.2803 |
| 0.2423 | 1.78 | 3260 | 0.2801 |
| 0.2709 | 1.79 | 3270 | 0.2808 |
| 0.2409 | 1.79 | 3280 | 0.2832 |
| 0.2262 | 1.8 | 3290 | 0.2855 |
| 0.242 | 1.8 | 3300 | 0.2864 |
| 0.268 | 1.81 | 3310 | 0.2869 |
| 0.2767 | 1.81 | 3320 | 0.2857 |
| 0.264 | 1.82 | 3330 | 0.2848 |
| 0.2741 | 1.82 | 3340 | 0.2821 |
| 0.282 | 1.83 | 3350 | 0.2806 |
| 0.2616 | 1.83 | 3360 | 0.2796 |
| 0.2924 | 1.84 | 3370 | 0.2816 |
| 0.2563 | 1.85 | 3380 | 0.2826 |
| 0.2556 | 1.85 | 3390 | 0.2856 |
| 0.3117 | 1.86 | 3400 | 0.2832 |
| 0.2397 | 1.86 | 3410 | 0.2825 |
| 0.2329 | 1.87 | 3420 | 0.2842 |
| 0.2044 | 1.87 | 3430 | 0.2853 |
| 0.2469 | 1.88 | 3440 | 0.2870 |
| 0.2566 | 1.88 | 3450 | 0.2875 |
| 0.222 | 1.89 | 3460 | 0.2868 |
| 0.24 | 1.89 | 3470 | 0.2828 |
| 0.2582 | 1.9 | 3480 | 0.2827 |
| 0.2723 | 1.91 | 3490 | 0.2832 |
| 0.2731 | 1.91 | 3500 | 0.2825 |
| 0.2713 | 1.92 | 3510 | 0.2822 |
| 0.2558 | 1.92 | 3520 | 0.2815 |
| 0.2655 | 1.93 | 3530 | 0.2801 |
| 0.2461 | 1.93 | 3540 | 0.2801 |
| 0.2604 | 1.94 | 3550 | 0.2810 |
| 0.2393 | 1.94 | 3560 | 0.2809 |
| 0.2434 | 1.95 | 3570 | 0.2800 |
| 0.2252 | 1.95 | 3580 | 0.2830 |
| 0.2571 | 1.96 | 3590 | 0.2853 |
| 0.2809 | 1.97 | 3600 | 0.2834 |
| 0.245 | 1.97 | 3610 | 0.2799 |
| 0.2309 | 1.98 | 3620 | 0.2786 |
| 0.228 | 1.98 | 3630 | 0.2793 |
| 0.2546 | 1.99 | 3640 | 0.2797 |
| 0.268 | 1.99 | 3650 | 0.2813 |
| 0.2606 | 2.0 | 3660 | 0.2819 |
| 0.2064 | 2.0 | 3670 | 0.2823 |
| 0.2117 | 2.01 | 3680 | 0.2848 |
| 0.1986 | 2.01 | 3690 | 0.2876 |
| 0.2054 | 2.02 | 3700 | 0.2895 |
| 0.1849 | 2.03 | 3710 | 0.2923 |
| 0.1822 | 2.03 | 3720 | 0.2953 |
| 0.2254 | 2.04 | 3730 | 0.2973 |
| 0.1946 | 2.04 | 3740 | 0.2975 |
| 0.2095 | 2.05 | 3750 | 0.2982 |
| 0.215 | 2.05 | 3760 | 0.2961 |
| 0.2382 | 2.06 | 3770 | 0.2933 |
| 0.1946 | 2.06 | 3780 | 0.2919 |
| 0.1892 | 2.07 | 3790 | 0.2912 |
| 0.1666 | 2.07 | 3800 | 0.2924 |
| 0.1955 | 2.08 | 3810 | 0.2953 |
| 0.1646 | 2.09 | 3820 | 0.2959 |
| 0.2396 | 2.09 | 3830 | 0.2980 |
| 0.1862 | 2.1 | 3840 | 0.2996 |
| 0.1811 | 2.1 | 3850 | 0.2978 |
| 0.2129 | 2.11 | 3860 | 0.2966 |
| 0.1959 | 2.11 | 3870 | 0.2962 |
| 0.1969 | 2.12 | 3880 | 0.2958 |
| 0.219 | 2.12 | 3890 | 0.2965 |
| 0.1885 | 2.13 | 3900 | 0.2966 |
| 0.2433 | 2.13 | 3910 | 0.2944 |
| 0.2665 | 2.14 | 3920 | 0.2937 |
| 0.2126 | 2.15 | 3930 | 0.2927 |
| 0.218 | 2.15 | 3940 | 0.2914 |
| 0.2105 | 2.16 | 3950 | 0.2928 |
| 0.1908 | 2.16 | 3960 | 0.2938 |
| 0.1822 | 2.17 | 3970 | 0.2981 |
| 0.2149 | 2.17 | 3980 | 0.3015 |
| 0.2011 | 2.18 | 3990 | 0.3020 |
| 0.2381 | 2.18 | 4000 | 0.3004 |
| 0.2155 | 2.19 | 4010 | 0.2978 |
| 0.1989 | 2.19 | 4020 | 0.2994 |
| 0.206 | 2.2 | 4030 | 0.2988 |
| 0.1669 | 2.21 | 4040 | 0.3002 |
| 0.2143 | 2.21 | 4050 | 0.2977 |
| 0.1955 | 2.22 | 4060 | 0.2950 |
| 0.203 | 2.22 | 4070 | 0.2947 |
| 0.2407 | 2.23 | 4080 | 0.2943 |
| 0.202 | 2.23 | 4090 | 0.2936 |
| 0.1995 | 2.24 | 4100 | 0.2925 |
| 0.2061 | 2.24 | 4110 | 0.2946 |
| 0.2583 | 2.25 | 4120 | 0.2966 |
| 0.1948 | 2.25 | 4130 | 0.2981 |
| 0.2126 | 2.26 | 4140 | 0.2992 |
| 0.2032 | 2.27 | 4150 | 0.2980 |
| 0.2131 | 2.27 | 4160 | 0.2980 |
| 0.1854 | 2.28 | 4170 | 0.2996 |
| 0.2263 | 2.28 | 4180 | 0.2960 |
| 0.2191 | 2.29 | 4190 | 0.2965 |
| 0.234 | 2.29 | 4200 | 0.2972 |
| 0.2642 | 2.3 | 4210 | 0.2954 |
| 0.2234 | 2.3 | 4220 | 0.2966 |
| 0.1953 | 2.31 | 4230 | 0.2965 |
| 0.1917 | 2.31 | 4240 | 0.2983 |
| 0.202 | 2.32 | 4250 | 0.2978 |
| 0.2409 | 2.33 | 4260 | 0.2973 |
| 0.1934 | 2.33 | 4270 | 0.2957 |
| 0.2146 | 2.34 | 4280 | 0.2955 |
| 0.2162 | 2.34 | 4290 | 0.2997 |
| 0.1929 | 2.35 | 4300 | 0.3005 |
| 0.2275 | 2.35 | 4310 | 0.2986 |
| 0.2033 | 2.36 | 4320 | 0.2962 |
| 0.1949 | 2.36 | 4330 | 0.2943 |
| 0.2024 | 2.37 | 4340 | 0.2940 |
| 0.2438 | 2.37 | 4350 | 0.2954 |
| 0.208 | 2.38 | 4360 | 0.2969 |
| 0.2075 | 2.39 | 4370 | 0.2989 |
| 0.2436 | 2.39 | 4380 | 0.3001 |
| 0.2498 | 2.4 | 4390 | 0.3000 |
| 0.2046 | 2.4 | 4400 | 0.3002 |
| 0.2059 | 2.41 | 4410 | 0.3008 |
| 0.2226 | 2.41 | 4420 | 0.3008 |
| 0.2182 | 2.42 | 4430 | 0.3004 |
| 0.1929 | 2.42 | 4440 | 0.2998 |
| 0.2115 | 2.43 | 4450 | 0.2994 |
| 0.1898 | 2.43 | 4460 | 0.3000 |
| 0.1954 | 2.44 | 4470 | 0.3015 |
| 0.2181 | 2.45 | 4480 | 0.3010 |
| 0.1941 | 2.45 | 4490 | 0.2994 |
| 0.2325 | 2.46 | 4500 | 0.2977 |
| 0.1721 | 2.46 | 4510 | 0.2995 |
| 0.2326 | 2.47 | 4520 | 0.3000 |
| 0.1852 | 2.47 | 4530 | 0.2980 |
| 0.2475 | 2.48 | 4540 | 0.2979 |
| 0.1841 | 2.48 | 4550 | 0.2984 |
| 0.2014 | 2.49 | 4560 | 0.2996 |
| 0.2029 | 2.49 | 4570 | 0.3004 |
| 0.2122 | 2.5 | 4580 | 0.3012 |
| 0.2003 | 2.51 | 4590 | 0.3021 |
| 0.1822 | 2.51 | 4600 | 0.3042 |
| 0.246 | 2.52 | 4610 | 0.3061 |
| 0.2134 | 2.52 | 4620 | 0.3069 |
| 0.1931 | 2.53 | 4630 | 0.3063 |
| 0.2058 | 2.53 | 4640 | 0.3044 |
| 0.237 | 2.54 | 4650 | 0.3037 |
| 0.2188 | 2.54 | 4660 | 0.3036 |
| 0.2228 | 2.55 | 4670 | 0.3025 |
| 0.1872 | 2.55 | 4680 | 0.3001 |
| 0.2243 | 2.56 | 4690 | 0.3003 |
| 0.2329 | 2.57 | 4700 | 0.3006 |
| 0.1908 | 2.57 | 4710 | 0.3019 |
| 0.2003 | 2.58 | 4720 | 0.2991 |
| 0.2004 | 2.58 | 4730 | 0.2998 |
| 0.2116 | 2.59 | 4740 | 0.3000 |
| 0.1833 | 2.59 | 4750 | 0.2999 |
| 0.1811 | 2.6 | 4760 | 0.3007 |
| 0.2552 | 2.6 | 4770 | 0.2988 |
| 0.1911 | 2.61 | 4780 | 0.2962 |
| 0.2097 | 2.61 | 4790 | 0.2950 |
| 0.2278 | 2.62 | 4800 | 0.2945 |
| 0.224 | 2.63 | 4810 | 0.2938 |
| 0.2078 | 2.63 | 4820 | 0.2934 |
| 0.1998 | 2.64 | 4830 | 0.2927 |
| 0.185 | 2.64 | 4840 | 0.2927 |
| 0.2384 | 2.65 | 4850 | 0.2936 |
| 0.2291 | 2.65 | 4860 | 0.2935 |
| 0.2003 | 2.66 | 4870 | 0.2935 |
| 0.2198 | 2.66 | 4880 | 0.2936 |
| 0.2061 | 2.67 | 4890 | 0.2921 |
| 0.2059 | 2.68 | 4900 | 0.2925 |
| 0.2044 | 2.68 | 4910 | 0.2932 |
| 0.2061 | 2.69 | 4920 | 0.2933 |
| 0.1954 | 2.69 | 4930 | 0.2940 |
| 0.205 | 2.7 | 4940 | 0.2937 |
| 0.1863 | 2.7 | 4950 | 0.2938 |
| 0.2036 | 2.71 | 4960 | 0.2952 |
| 0.2242 | 2.71 | 4970 | 0.2955 |
| 0.1985 | 2.72 | 4980 | 0.2925 |
| 0.2372 | 2.72 | 4990 | 0.2910 |
| 0.2018 | 2.73 | 5000 | 0.2898 |
| 0.2337 | 2.74 | 5010 | 0.2903 |
| 0.2096 | 2.74 | 5020 | 0.2899 |
| 0.2303 | 2.75 | 5030 | 0.2909 |
| 0.2422 | 2.75 | 5040 | 0.2916 |
| 0.2121 | 2.76 | 5050 | 0.2904 |
| 0.2431 | 2.76 | 5060 | 0.2892 |
| 0.2362 | 2.77 | 5070 | 0.2888 |
| 0.2512 | 2.77 | 5080 | 0.2885 |
| 0.2106 | 2.78 | 5090 | 0.2888 |
| 0.2471 | 2.78 | 5100 | 0.2887 |
| 0.2347 | 2.79 | 5110 | 0.2895 |
| 0.2233 | 2.8 | 5120 | 0.2905 |
| 0.2056 | 2.8 | 5130 | 0.2897 |
| 0.2193 | 2.81 | 5140 | 0.2888 |
| 0.2017 | 2.81 | 5150 | 0.2889 |
| 0.2278 | 2.82 | 5160 | 0.2899 |
| 0.2126 | 2.82 | 5170 | 0.2908 |
| 0.2196 | 2.83 | 5180 | 0.2910 |
| 0.2003 | 2.83 | 5190 | 0.2921 |
| 0.2054 | 2.84 | 5200 | 0.2921 |
| 0.214 | 2.84 | 5210 | 0.2922 |
| 0.2199 | 2.85 | 5220 | 0.2924 |
| 0.1937 | 2.86 | 5230 | 0.2932 |
| 0.2092 | 2.86 | 5240 | 0.2930 |
| 0.2247 | 2.87 | 5250 | 0.2931 |
| 0.2079 | 2.87 | 5260 | 0.2927 |
| 0.1823 | 2.88 | 5270 | 0.2937 |
| 0.2123 | 2.88 | 5280 | 0.2946 |
| 0.2186 | 2.89 | 5290 | 0.2946 |
| 0.2402 | 2.89 | 5300 | 0.2931 |
| 0.2237 | 2.9 | 5310 | 0.2920 |
| 0.2385 | 2.9 | 5320 | 0.2909 |
| 0.2099 | 2.91 | 5330 | 0.2905 |
| 0.2114 | 2.92 | 5340 | 0.2911 |
| 0.2172 | 2.92 | 5350 | 0.2917 |
| 0.1933 | 2.93 | 5360 | 0.2928 |
| 0.2114 | 2.93 | 5370 | 0.2932 |
| 0.2336 | 2.94 | 5380 | 0.2932 |
| 0.2572 | 2.94 | 5390 | 0.2930 |
| 0.2003 | 2.95 | 5400 | 0.2918 |
| 0.2198 | 2.95 | 5410 | 0.2916 |
| 0.2539 | 2.96 | 5420 | 0.2914 |
| 0.2198 | 2.96 | 5430 | 0.2910 |
| 0.198 | 2.97 | 5440 | 0.2911 |
| 0.2302 | 2.98 | 5450 | 0.2914 |
| 0.2102 | 2.98 | 5460 | 0.2918 |
| 0.2476 | 2.99 | 5470 | 0.2915 |
| 0.2052 | 2.99 | 5480 | 0.2914 |
| 0.2329 | 3.0 | 5490 | 0.2909 |
| 0.202 | 3.0 | 5500 | 0.2914 |
| 0.1624 | 3.01 | 5510 | 0.2916 |
| 0.166 | 3.01 | 5520 | 0.2911 |
| 0.1646 | 3.02 | 5530 | 0.2912 |
| 0.193 | 3.02 | 5540 | 0.2916 |
| 0.1849 | 3.03 | 5550 | 0.2930 |
| 0.1734 | 3.04 | 5560 | 0.2940 |
| 0.1748 | 3.04 | 5570 | 0.2943 |
| 0.1608 | 3.05 | 5580 | 0.2957 |
| 0.169 | 3.05 | 5590 | 0.2957 |
| 0.1853 | 3.06 | 5600 | 0.2965 |
| 0.1752 | 3.06 | 5610 | 0.2970 |
| 0.161 | 3.07 | 5620 | 0.2980 |
| 0.1901 | 3.07 | 5630 | 0.2980 |
| 0.1727 | 3.08 | 5640 | 0.2990 |
| 0.1528 | 3.08 | 5650 | 0.2998 |
| 0.1808 | 3.09 | 5660 | 0.3006 |
| 0.1739 | 3.1 | 5670 | 0.3007 |
| 0.2049 | 3.1 | 5680 | 0.2994 |
| 0.1911 | 3.11 | 5690 | 0.2986 |
| 0.1907 | 3.11 | 5700 | 0.2986 |
| 0.1854 | 3.12 | 5710 | 0.2993 |
| 0.1677 | 3.12 | 5720 | 0.2996 |
| 0.1882 | 3.13 | 5730 | 0.2998 |
| 0.1874 | 3.13 | 5740 | 0.2997 |
| 0.1492 | 3.14 | 5750 | 0.3005 |
| 0.1886 | 3.14 | 5760 | 0.3011 |
| 0.1836 | 3.15 | 5770 | 0.3012 |
| 0.1772 | 3.16 | 5780 | 0.3008 |
| 0.1699 | 3.16 | 5790 | 0.3009 |
| 0.1633 | 3.17 | 5800 | 0.3023 |
| 0.2072 | 3.17 | 5810 | 0.3022 |
| 0.1921 | 3.18 | 5820 | 0.3023 |
| 0.199 | 3.18 | 5830 | 0.3027 |
| 0.1901 | 3.19 | 5840 | 0.3019 |
| 0.1769 | 3.19 | 5850 | 0.3016 |
| 0.1857 | 3.2 | 5860 | 0.3002 |
| 0.1613 | 3.2 | 5870 | 0.2994 |
| 0.1843 | 3.21 | 5880 | 0.3000 |
| 0.1895 | 3.22 | 5890 | 0.3014 |
| 0.1695 | 3.22 | 5900 | 0.3017 |
| 0.1525 | 3.23 | 5910 | 0.3026 |
| 0.2128 | 3.23 | 5920 | 0.3027 |
| 0.182 | 3.24 | 5930 | 0.3025 |
| 0.2059 | 3.24 | 5940 | 0.3016 |
| 0.1631 | 3.25 | 5950 | 0.3001 |
| 0.2012 | 3.25 | 5960 | 0.2999 |
| 0.1745 | 3.26 | 5970 | 0.2996 |
| 0.1934 | 3.26 | 5980 | 0.2998 |
| 0.1665 | 3.27 | 5990 | 0.3005 |
| 0.1733 | 3.28 | 6000 | 0.3018 |
| 0.17 | 3.28 | 6010 | 0.3029 |
| 0.192 | 3.29 | 6020 | 0.3047 |
| 0.1909 | 3.29 | 6030 | 0.3055 |
| 0.1854 | 3.3 | 6040 | 0.3047 |
| 0.1876 | 3.3 | 6050 | 0.3046 |
| 0.1538 | 3.31 | 6060 | 0.3051 |
| 0.1679 | 3.31 | 6070 | 0.3056 |
| 0.1927 | 3.32 | 6080 | 0.3063 |
| 0.1922 | 3.32 | 6090 | 0.3066 |
| 0.1976 | 3.33 | 6100 | 0.3064 |
| 0.1683 | 3.34 | 6110 | 0.3053 |
| 0.1891 | 3.34 | 6120 | 0.3045 |
| 0.1878 | 3.35 | 6130 | 0.3031 |
| 0.174 | 3.35 | 6140 | 0.3028 |
| 0.1773 | 3.36 | 6150 | 0.3027 |
| 0.2057 | 3.36 | 6160 | 0.3022 |
| 0.1838 | 3.37 | 6170 | 0.3022 |
| 0.1976 | 3.37 | 6180 | 0.3020 |
| 0.1802 | 3.38 | 6190 | 0.3006 |
| 0.1734 | 3.38 | 6200 | 0.3005 |
| 0.1806 | 3.39 | 6210 | 0.3008 |
| 0.1675 | 3.4 | 6220 | 0.3009 |
| 0.1998 | 3.4 | 6230 | 0.3008 |
| 0.1838 | 3.41 | 6240 | 0.3013 |
| 0.1693 | 3.41 | 6250 | 0.3025 |
| 0.1795 | 3.42 | 6260 | 0.3033 |
| 0.2184 | 3.42 | 6270 | 0.3034 |
| 0.1881 | 3.43 | 6280 | 0.3031 |
| 0.1943 | 3.43 | 6290 | 0.3027 |
| 0.1717 | 3.44 | 6300 | 0.3028 |
| 0.2016 | 3.44 | 6310 | 0.3028 |
| 0.2001 | 3.45 | 6320 | 0.3026 |
| 0.158 | 3.46 | 6330 | 0.3025 |
| 0.1562 | 3.46 | 6340 | 0.3033 |
| 0.1698 | 3.47 | 6350 | 0.3039 |
| 0.2106 | 3.47 | 6360 | 0.3045 |
| 0.2117 | 3.48 | 6370 | 0.3048 |
| 0.1635 | 3.48 | 6380 | 0.3051 |
| 0.1853 | 3.49 | 6390 | 0.3055 |
| 0.2109 | 3.49 | 6400 | 0.3058 |
| 0.1838 | 3.5 | 6410 | 0.3057 |
| 0.1789 | 3.5 | 6420 | 0.3051 |
| 0.2018 | 3.51 | 6430 | 0.3035 |
| 0.1885 | 3.52 | 6440 | 0.3019 |
| 0.189 | 3.52 | 6450 | 0.3011 |
| 0.1718 | 3.53 | 6460 | 0.3006 |
| 0.1711 | 3.53 | 6470 | 0.3006 |
| 0.1804 | 3.54 | 6480 | 0.3013 |
| 0.1677 | 3.54 | 6490 | 0.3021 |
| 0.1861 | 3.55 | 6500 | 0.3023 |
| 0.1634 | 3.55 | 6510 | 0.3027 |
| 0.2138 | 3.56 | 6520 | 0.3030 |
| 0.185 | 3.56 | 6530 | 0.3036 |
| 0.1744 | 3.57 | 6540 | 0.3037 |
| 0.1893 | 3.58 | 6550 | 0.3033 |
| 0.1856 | 3.58 | 6560 | 0.3027 |
| 0.1951 | 3.59 | 6570 | 0.3022 |
| 0.1787 | 3.59 | 6580 | 0.3019 |
| 0.1817 | 3.6 | 6590 | 0.3017 |
| 0.1911 | 3.6 | 6600 | 0.3012 |
| 0.204 | 3.61 | 6610 | 0.3012 |
| 0.1643 | 3.61 | 6620 | 0.3008 |
| 0.1766 | 3.62 | 6630 | 0.3006 |
| 0.1846 | 3.62 | 6640 | 0.3004 |
| 0.1792 | 3.63 | 6650 | 0.3007 |
| 0.1924 | 3.64 | 6660 | 0.3008 |
| 0.1723 | 3.64 | 6670 | 0.3007 |
| 0.1769 | 3.65 | 6680 | 0.3009 |
| 0.1702 | 3.65 | 6690 | 0.3013 |
| 0.1681 | 3.66 | 6700 | 0.3016 |
| 0.1885 | 3.66 | 6710 | 0.3016 |
| 0.2321 | 3.67 | 6720 | 0.3012 |
| 0.1648 | 3.67 | 6730 | 0.3011 |
| 0.1941 | 3.68 | 6740 | 0.3011 |
| 0.1729 | 3.69 | 6750 | 0.3008 |
| 0.1854 | 3.69 | 6760 | 0.3004 |
| 0.1844 | 3.7 | 6770 | 0.3002 |
| 0.1811 | 3.7 | 6780 | 0.3001 |
| 0.1957 | 3.71 | 6790 | 0.3001 |
| 0.1988 | 3.71 | 6800 | 0.2999 |
| 0.2051 | 3.72 | 6810 | 0.2994 |
| 0.2074 | 3.72 | 6820 | 0.2987 |
| 0.1825 | 3.73 | 6830 | 0.2985 |
| 0.1802 | 3.73 | 6840 | 0.2986 |
| 0.1904 | 3.74 | 6850 | 0.2985 |
| 0.1676 | 3.75 | 6860 | 0.2986 |
| 0.1999 | 3.75 | 6870 | 0.2987 |
| 0.1791 | 3.76 | 6880 | 0.2990 |
| 0.1763 | 3.76 | 6890 | 0.2997 |
| 0.1964 | 3.77 | 6900 | 0.2999 |
| 0.2253 | 3.77 | 6910 | 0.2998 |
| 0.2008 | 3.78 | 6920 | 0.2995 |
| 0.1881 | 3.78 | 6930 | 0.2995 |
| 0.1945 | 3.79 | 6940 | 0.2992 |
| 0.1904 | 3.79 | 6950 | 0.2991 |
| 0.1718 | 3.8 | 6960 | 0.2991 |
| 0.2027 | 3.81 | 6970 | 0.2990 |
| 0.1889 | 3.81 | 6980 | 0.2989 |
| 0.1663 | 3.82 | 6990 | 0.2989 |
| 0.2035 | 3.82 | 7000 | 0.2988 |
| 0.1859 | 3.83 | 7010 | 0.2989 |
| 0.1852 | 3.83 | 7020 | 0.2992 |
| 0.1834 | 3.84 | 7030 | 0.2994 |
| 0.1643 | 3.84 | 7040 | 0.2996 |
| 0.1779 | 3.85 | 7050 | 0.3000 |
| 0.1875 | 3.85 | 7060 | 0.3002 |
| 0.187 | 3.86 | 7070 | 0.3003 |
| 0.1933 | 3.87 | 7080 | 0.3004 |
| 0.1777 | 3.87 | 7090 | 0.3002 |
| 0.1796 | 3.88 | 7100 | 0.3000 |
| 0.2047 | 3.88 | 7110 | 0.2998 |
| 0.1829 | 3.89 | 7120 | 0.2997 |
| 0.1846 | 3.89 | 7130 | 0.2996 |
| 0.2037 | 3.9 | 7140 | 0.2995 |
| 0.1805 | 3.9 | 7150 | 0.2994 |
| 0.1937 | 3.91 | 7160 | 0.2994 |
| 0.2001 | 3.91 | 7170 | 0.2994 |
| 0.2366 | 3.92 | 7180 | 0.2993 |
| 0.1813 | 3.93 | 7190 | 0.2992 |
| 0.1777 | 3.93 | 7200 | 0.2992 |
| 0.2077 | 3.94 | 7210 | 0.2992 |
| 0.1887 | 3.94 | 7220 | 0.2992 |
| 0.1966 | 3.95 | 7230 | 0.2991 |
| 0.1888 | 3.95 | 7240 | 0.2991 |
| 0.1931 | 3.96 | 7250 | 0.2991 |
| 0.1773 | 3.96 | 7260 | 0.2991 |
| 0.1701 | 3.97 | 7270 | 0.2992 |
| 0.1698 | 3.97 | 7280 | 0.2992 |
| 0.1855 | 3.98 | 7290 | 0.2992 |
| 0.2032 | 3.99 | 7300 | 0.2991 |
| 0.1966 | 3.99 | 7310 | 0.2991 |
| 0.1757 | 4.0 | 7320 | 0.2991 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3