All_balanced-mms1ball-Dec1
This model is a fine-tuned version of facebook/mms-1b-all on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9305
- Wer: 0.2261
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: 0.001
- train_batch_size: 2
- eval_batch_size: 3
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 100
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
30.1424 | 0.0401 | 100 | 3.7336 | 1.0008 |
2.6594 | 0.0803 | 200 | 2.0779 | 0.4646 |
2.0363 | 0.1204 | 300 | 1.8221 | 0.4703 |
2.0967 | 0.1606 | 400 | 1.7232 | 0.4188 |
1.9542 | 0.2007 | 500 | 1.7077 | 0.3860 |
1.7691 | 0.2409 | 600 | 1.6618 | 0.3761 |
1.7044 | 0.2810 | 700 | 1.5637 | 0.3880 |
2.0279 | 0.3212 | 800 | 1.5381 | 0.3639 |
1.4932 | 0.3613 | 900 | 1.4764 | 0.3508 |
1.716 | 0.4014 | 1000 | 1.6347 | 0.3790 |
1.5974 | 0.4416 | 1100 | 1.3676 | 0.4139 |
1.5057 | 0.4817 | 1200 | 1.4292 | 0.3810 |
1.4473 | 0.5219 | 1300 | 1.4154 | 0.3376 |
1.6372 | 0.5620 | 1400 | 1.3669 | 0.3970 |
1.9814 | 0.6022 | 1500 | 1.4457 | 0.4454 |
1.3699 | 0.6423 | 1600 | 1.3653 | 0.3690 |
1.6035 | 0.6825 | 1700 | 1.3627 | 0.3529 |
1.3893 | 0.7226 | 1800 | 1.7891 | 0.4372 |
1.8617 | 0.7627 | 1900 | 1.5076 | 0.3882 |
1.6314 | 0.8029 | 2000 | 1.3478 | 0.3353 |
1.431 | 0.8430 | 2100 | 1.4674 | 0.3700 |
1.5303 | 0.8832 | 2200 | 1.3097 | 0.3296 |
1.6582 | 0.9233 | 2300 | 1.4948 | 0.3853 |
1.4098 | 0.9635 | 2400 | 1.4371 | 0.3226 |
1.5419 | 1.0036 | 2500 | 1.3125 | 0.3026 |
1.38 | 1.0438 | 2600 | 1.1613 | 0.2898 |
1.3182 | 1.0839 | 2700 | 1.1790 | 0.3112 |
1.1875 | 1.1240 | 2800 | 1.2010 | 0.2926 |
1.5817 | 1.1642 | 2900 | 1.3179 | 0.2920 |
1.1699 | 1.2043 | 3000 | 1.1878 | 0.2796 |
1.2902 | 1.2445 | 3100 | 1.1227 | 0.3314 |
1.3457 | 1.2846 | 3200 | 1.4403 | 0.2932 |
1.3949 | 1.3248 | 3300 | 1.2656 | 0.2887 |
1.4007 | 1.3649 | 3400 | 1.1206 | 0.2724 |
1.2666 | 1.4051 | 3500 | 1.1643 | 0.2906 |
1.2119 | 1.4452 | 3600 | 1.1876 | 0.2943 |
1.1352 | 1.4853 | 3700 | 1.1176 | 0.2990 |
1.4364 | 1.5255 | 3800 | 1.1091 | 0.2898 |
1.3138 | 1.5656 | 3900 | 1.1573 | 0.2896 |
1.1814 | 1.6058 | 4000 | 1.1657 | 0.2753 |
1.3583 | 1.6459 | 4100 | 1.1842 | 0.3014 |
1.3155 | 1.6861 | 4200 | 1.2304 | 0.2879 |
1.187 | 1.7262 | 4300 | 1.8192 | 0.2926 |
1.1076 | 1.7664 | 4400 | 1.1733 | 0.2879 |
1.2891 | 1.8065 | 4500 | 1.2238 | 0.2820 |
1.2036 | 1.8466 | 4600 | 1.3209 | 0.2955 |
1.2638 | 1.8868 | 4700 | 1.1884 | 0.2851 |
1.3196 | 1.9269 | 4800 | 1.1179 | 0.2810 |
1.3898 | 1.9671 | 4900 | 1.1799 | 0.3186 |
1.2252 | 2.0072 | 5000 | 1.1878 | 0.3032 |
1.19 | 2.0474 | 5100 | 1.0254 | 0.2685 |
1.1543 | 2.0875 | 5200 | 1.0331 | 0.2749 |
1.1626 | 2.1277 | 5300 | 1.1425 | 0.2757 |
1.1574 | 2.1678 | 5400 | 1.2054 | 0.2834 |
1.1878 | 2.2079 | 5500 | 1.1708 | 0.2787 |
1.2212 | 2.2481 | 5600 | 1.3851 | 0.3096 |
1.3004 | 2.2882 | 5700 | 1.0818 | 0.2834 |
1.2182 | 2.3284 | 5800 | 1.0978 | 0.2832 |
1.1923 | 2.3685 | 5900 | 1.1581 | 0.2857 |
1.2636 | 2.4087 | 6000 | 1.0933 | 0.2779 |
1.1937 | 2.4488 | 6100 | 1.1801 | 0.2822 |
1.3104 | 2.4890 | 6200 | 1.1605 | 0.2722 |
1.1269 | 2.5291 | 6300 | 1.1499 | 0.2939 |
1.0863 | 2.5692 | 6400 | 1.0980 | 0.2857 |
1.1061 | 2.6094 | 6500 | 1.2168 | 0.2824 |
1.1683 | 2.6495 | 6600 | 1.1856 | 0.2912 |
0.9837 | 2.6897 | 6700 | 1.2781 | 0.2873 |
1.2996 | 2.7298 | 6800 | 1.1287 | 0.3063 |
1.0857 | 2.7700 | 6900 | 1.1789 | 0.2738 |
1.3039 | 2.8101 | 7000 | 1.1143 | 0.2959 |
1.2557 | 2.8503 | 7100 | 1.1730 | 0.2759 |
1.3501 | 2.8904 | 7200 | 1.2738 | 0.2965 |
1.1344 | 2.9305 | 7300 | 1.1162 | 0.2759 |
1.2145 | 2.9707 | 7400 | 1.2316 | 0.3041 |
1.263 | 3.0108 | 7500 | 1.1705 | 0.2716 |
1.2562 | 3.0510 | 7600 | 1.0760 | 0.3177 |
0.9114 | 3.0911 | 7700 | 1.1623 | 0.3055 |
1.0245 | 3.1313 | 7800 | 1.0781 | 0.2710 |
0.9855 | 3.1714 | 7900 | 1.1375 | 0.2757 |
1.2696 | 3.2116 | 8000 | 1.0723 | 0.2700 |
0.986 | 3.2517 | 8100 | 1.1825 | 0.2906 |
1.043 | 3.2919 | 8200 | 1.0997 | 0.2647 |
1.1965 | 3.3320 | 8300 | 1.0987 | 0.2986 |
1.2936 | 3.3721 | 8400 | 1.1487 | 0.2861 |
1.0926 | 3.4123 | 8500 | 1.1092 | 0.3130 |
1.0379 | 3.4524 | 8600 | 1.0739 | 0.2700 |
1.1263 | 3.4926 | 8700 | 1.1573 | 0.2832 |
1.049 | 3.5327 | 8800 | 1.1529 | 0.2898 |
1.4461 | 3.5729 | 8900 | 1.1033 | 0.2732 |
1.111 | 3.6130 | 9000 | 1.1459 | 0.3141 |
0.979 | 3.6532 | 9100 | 1.2492 | 0.2798 |
1.1531 | 3.6933 | 9200 | 1.1269 | 0.2736 |
1.0911 | 3.7334 | 9300 | 1.0199 | 0.2828 |
1.1625 | 3.7736 | 9400 | 1.1184 | 0.2873 |
1.1377 | 3.8137 | 9500 | 1.2753 | 0.2716 |
1.0377 | 3.8539 | 9600 | 1.2049 | 0.2679 |
1.1067 | 3.8940 | 9700 | 1.0571 | 0.2728 |
0.8826 | 3.9342 | 9800 | 1.2443 | 0.2663 |
1.3561 | 3.9743 | 9900 | 1.1295 | 0.2555 |
1.1467 | 4.0145 | 10000 | 1.1627 | 0.2914 |
1.1627 | 4.0546 | 10100 | 1.1231 | 0.2642 |
1.0101 | 4.0947 | 10200 | 1.1756 | 0.2522 |
1.0248 | 4.1349 | 10300 | 1.0872 | 0.2867 |
1.0708 | 4.1750 | 10400 | 1.1104 | 0.2632 |
1.2335 | 4.2152 | 10500 | 1.2746 | 0.2679 |
0.9858 | 4.2553 | 10600 | 1.0965 | 0.2832 |
1.0919 | 4.2955 | 10700 | 1.0848 | 0.2567 |
1.361 | 4.3356 | 10800 | 0.9840 | 0.2610 |
0.9155 | 4.3758 | 10900 | 1.0058 | 0.2636 |
0.9557 | 4.4159 | 11000 | 1.0815 | 0.2712 |
1.1775 | 4.4560 | 11100 | 1.1054 | 0.2965 |
1.0284 | 4.4962 | 11200 | 1.0369 | 0.2559 |
0.907 | 4.5363 | 11300 | 1.0772 | 0.2604 |
1.2466 | 4.5765 | 11400 | 1.0534 | 0.2663 |
1.1716 | 4.6166 | 11500 | 1.0382 | 0.2685 |
1.1191 | 4.6568 | 11600 | 1.1413 | 0.2883 |
1.0867 | 4.6969 | 11700 | 1.0414 | 0.2667 |
1.0976 | 4.7371 | 11800 | 1.0494 | 0.2593 |
1.1804 | 4.7772 | 11900 | 1.0128 | 0.2902 |
0.9749 | 4.8173 | 12000 | 1.1092 | 0.3337 |
1.089 | 4.8575 | 12100 | 1.0601 | 0.2747 |
0.863 | 4.8976 | 12200 | 1.0894 | 0.2614 |
1.1661 | 4.9378 | 12300 | 1.0314 | 0.2546 |
0.9915 | 4.9779 | 12400 | 1.0132 | 0.2518 |
0.9994 | 5.0181 | 12500 | 1.0685 | 0.2663 |
1.077 | 5.0582 | 12600 | 1.0644 | 0.2789 |
0.9299 | 5.0984 | 12700 | 1.0351 | 0.2853 |
1.0591 | 5.1385 | 12800 | 1.0896 | 0.2577 |
1.0107 | 5.1786 | 12900 | 0.9707 | 0.2546 |
0.9835 | 5.2188 | 13000 | 1.0298 | 0.2559 |
1.015 | 5.2589 | 13100 | 1.0183 | 0.2581 |
0.8909 | 5.2991 | 13200 | 1.0265 | 0.2665 |
1.1977 | 5.3392 | 13300 | 1.0454 | 0.2606 |
1.0867 | 5.3794 | 13400 | 1.0444 | 0.2777 |
0.8658 | 5.4195 | 13500 | 1.0143 | 0.2759 |
0.8539 | 5.4597 | 13600 | 1.0826 | 0.2806 |
0.9105 | 5.4998 | 13700 | 1.2226 | 0.2591 |
0.9931 | 5.5399 | 13800 | 1.1005 | 0.2732 |
0.9585 | 5.5801 | 13900 | 1.0006 | 0.2687 |
0.9642 | 5.6202 | 14000 | 0.9744 | 0.2689 |
1.0453 | 5.6604 | 14100 | 1.0286 | 0.2879 |
0.9373 | 5.7005 | 14200 | 0.9668 | 0.2579 |
0.8088 | 5.7407 | 14300 | 1.1987 | 0.2559 |
1.1615 | 5.7808 | 14400 | 1.0843 | 0.2879 |
1.1297 | 5.8210 | 14500 | 1.0850 | 0.2979 |
1.032 | 5.8611 | 14600 | 1.1154 | 0.2732 |
1.106 | 5.9012 | 14700 | 0.9745 | 0.2661 |
1.1489 | 5.9414 | 14800 | 1.0991 | 0.2755 |
1.064 | 5.9815 | 14900 | 0.9742 | 0.2534 |
1.0298 | 6.0217 | 15000 | 1.0386 | 0.2939 |
0.8313 | 6.0618 | 15100 | 1.0906 | 0.2616 |
0.9847 | 6.1020 | 15200 | 1.0494 | 0.2410 |
0.9711 | 6.1421 | 15300 | 0.9615 | 0.2430 |
0.8575 | 6.1823 | 15400 | 1.0672 | 0.2504 |
0.964 | 6.2224 | 15500 | 1.1011 | 0.2469 |
0.9774 | 6.2625 | 15600 | 1.1612 | 0.2410 |
1.2381 | 6.3027 | 15700 | 1.2024 | 0.2481 |
0.9052 | 6.3428 | 15800 | 1.1362 | 0.2404 |
0.8335 | 6.3830 | 15900 | 1.0693 | 0.2481 |
1.0121 | 6.4231 | 16000 | 1.0522 | 0.2512 |
1.0453 | 6.4633 | 16100 | 1.0250 | 0.2438 |
0.9786 | 6.5034 | 16200 | 1.1154 | 0.2440 |
0.7854 | 6.5436 | 16300 | 1.1031 | 0.2522 |
0.9754 | 6.5837 | 16400 | 1.0633 | 0.2399 |
0.995 | 6.6238 | 16500 | 1.0055 | 0.2395 |
1.0816 | 6.6640 | 16600 | 0.9534 | 0.2408 |
1.0117 | 6.7041 | 16700 | 1.0803 | 0.2446 |
0.9712 | 6.7443 | 16800 | 1.0697 | 0.2485 |
1.2077 | 6.7844 | 16900 | 1.0392 | 0.2573 |
0.8853 | 6.8246 | 17000 | 1.0697 | 0.2477 |
0.9228 | 6.8647 | 17100 | 1.0667 | 0.2393 |
1.0343 | 6.9049 | 17200 | 0.9368 | 0.2414 |
0.955 | 6.9450 | 17300 | 0.9278 | 0.2375 |
1.0493 | 6.9851 | 17400 | 0.9663 | 0.2585 |
0.8626 | 7.0253 | 17500 | 1.0158 | 0.2336 |
0.9799 | 7.0654 | 17600 | 0.9995 | 0.2371 |
0.9035 | 7.1056 | 17700 | 0.9954 | 0.2401 |
0.855 | 7.1457 | 17800 | 1.0323 | 0.2369 |
0.8824 | 7.1859 | 17900 | 0.9786 | 0.2348 |
0.9551 | 7.2260 | 18000 | 0.9632 | 0.2440 |
0.9961 | 7.2662 | 18100 | 1.0595 | 0.2412 |
0.9624 | 7.3063 | 18200 | 0.9641 | 0.2355 |
0.8684 | 7.3464 | 18300 | 1.0987 | 0.2671 |
0.9115 | 7.3866 | 18400 | 1.0952 | 0.2338 |
1.0249 | 7.4267 | 18500 | 0.9679 | 0.2444 |
0.7095 | 7.4669 | 18600 | 0.9519 | 0.2393 |
1.0171 | 7.5070 | 18700 | 1.0720 | 0.2377 |
0.928 | 7.5472 | 18800 | 0.9080 | 0.2324 |
0.8984 | 7.5873 | 18900 | 0.9585 | 0.2342 |
0.9356 | 7.6275 | 19000 | 0.9375 | 0.2293 |
1.0438 | 7.6676 | 19100 | 0.9279 | 0.2320 |
1.0123 | 7.7077 | 19200 | 0.9517 | 0.2299 |
0.9772 | 7.7479 | 19300 | 0.9547 | 0.2312 |
0.8071 | 7.7880 | 19400 | 0.9990 | 0.2318 |
0.8644 | 7.8282 | 19500 | 0.9537 | 0.2222 |
0.9621 | 7.8683 | 19600 | 0.9610 | 0.2265 |
0.8496 | 7.9085 | 19700 | 1.1447 | 0.2326 |
1.0147 | 7.9486 | 19800 | 0.9625 | 0.2291 |
0.7951 | 7.9888 | 19900 | 0.8671 | 0.2336 |
0.8848 | 8.0289 | 20000 | 0.9265 | 0.2305 |
0.9517 | 8.0690 | 20100 | 0.9798 | 0.2365 |
0.9257 | 8.1092 | 20200 | 0.9162 | 0.2330 |
0.7344 | 8.1493 | 20300 | 0.9581 | 0.2379 |
0.7775 | 8.1895 | 20400 | 0.9086 | 0.2375 |
0.8103 | 8.2296 | 20500 | 0.9380 | 0.2681 |
0.9654 | 8.2698 | 20600 | 1.1129 | 0.2553 |
0.8725 | 8.3099 | 20700 | 0.9314 | 0.2534 |
0.9403 | 8.3501 | 20800 | 0.8826 | 0.2267 |
0.935 | 8.3902 | 20900 | 0.9237 | 0.2355 |
0.873 | 8.4303 | 21000 | 0.9173 | 0.2285 |
0.9888 | 8.4705 | 21100 | 0.8939 | 0.2491 |
0.8409 | 8.5106 | 21200 | 0.9323 | 0.2328 |
0.9142 | 8.5508 | 21300 | 0.8936 | 0.2357 |
0.9198 | 8.5909 | 21400 | 0.9490 | 0.2328 |
0.9415 | 8.6311 | 21500 | 0.8751 | 0.2236 |
0.8642 | 8.6712 | 21600 | 0.8856 | 0.2205 |
0.845 | 8.7114 | 21700 | 0.9220 | 0.2299 |
0.8273 | 8.7515 | 21800 | 0.9573 | 0.2275 |
0.9879 | 8.7916 | 21900 | 0.9256 | 0.2299 |
0.8437 | 8.8318 | 22000 | 0.9452 | 0.2287 |
0.8616 | 8.8719 | 22100 | 0.8573 | 0.2301 |
0.8818 | 8.9121 | 22200 | 0.9555 | 0.2326 |
0.9995 | 8.9522 | 22300 | 0.8606 | 0.2263 |
0.9717 | 8.9924 | 22400 | 0.9211 | 0.2242 |
0.8591 | 9.0325 | 22500 | 0.8784 | 0.2161 |
0.8465 | 9.0727 | 22600 | 0.8788 | 0.2181 |
0.5513 | 9.1128 | 22700 | 0.9324 | 0.2285 |
0.844 | 9.1530 | 22800 | 0.9018 | 0.2322 |
0.7938 | 9.1931 | 22900 | 0.9100 | 0.2240 |
0.8523 | 9.2332 | 23000 | 0.9281 | 0.2261 |
0.8709 | 9.2734 | 23100 | 1.0011 | 0.2414 |
0.7523 | 9.3135 | 23200 | 0.9418 | 0.2222 |
0.7934 | 9.3537 | 23300 | 0.8625 | 0.2244 |
0.9017 | 9.3938 | 23400 | 0.9092 | 0.2256 |
1.0757 | 9.4340 | 23500 | 0.9565 | 0.2399 |
1.0276 | 9.4741 | 23600 | 0.8874 | 0.2201 |
0.781 | 9.5143 | 23700 | 0.9413 | 0.2287 |
0.7004 | 9.5544 | 23800 | 0.8680 | 0.2214 |
1.0102 | 9.5945 | 23900 | 0.9048 | 0.2158 |
0.854 | 9.6347 | 24000 | 0.9205 | 0.2277 |
0.8407 | 9.6748 | 24100 | 0.9147 | 0.2212 |
0.9099 | 9.7150 | 24200 | 0.9409 | 0.2275 |
0.806 | 9.7551 | 24300 | 0.9361 | 0.2252 |
0.624 | 9.7953 | 24400 | 0.9124 | 0.2230 |
0.8258 | 9.8354 | 24500 | 0.9260 | 0.2318 |
0.8017 | 9.8756 | 24600 | 0.8602 | 0.2246 |
0.9073 | 9.9157 | 24700 | 0.8861 | 0.2226 |
0.7494 | 9.9558 | 24800 | 0.9136 | 0.2154 |
0.9192 | 9.9960 | 24900 | 0.8922 | 0.2818 |
0.8638 | 10.0361 | 25000 | 0.8879 | 0.2340 |
0.8078 | 10.0763 | 25100 | 1.0206 | 0.2361 |
0.7382 | 10.1164 | 25200 | 0.9848 | 0.2399 |
1.0449 | 10.1566 | 25300 | 0.9225 | 0.2655 |
0.7623 | 10.1967 | 25400 | 0.9574 | 0.2520 |
0.7644 | 10.2369 | 25500 | 0.9297 | 0.2457 |
0.8764 | 10.2770 | 25600 | 0.9570 | 0.2573 |
0.9522 | 10.3171 | 25700 | 0.8868 | 0.2551 |
0.9332 | 10.3573 | 25800 | 0.8586 | 0.2324 |
0.7203 | 10.3974 | 25900 | 1.0060 | 0.2898 |
0.8039 | 10.4376 | 26000 | 0.9118 | 0.2428 |
0.6854 | 10.4777 | 26100 | 0.8809 | 0.2254 |
0.8283 | 10.5179 | 26200 | 0.8793 | 0.2434 |
0.8677 | 10.5580 | 26300 | 0.8340 | 0.2226 |
0.8874 | 10.5982 | 26400 | 0.8902 | 0.2191 |
0.9027 | 10.6383 | 26500 | 0.9032 | 0.2267 |
0.8415 | 10.6784 | 26600 | 0.8526 | 0.2163 |
0.8014 | 10.7186 | 26700 | 0.8931 | 0.2295 |
0.8515 | 10.7587 | 26800 | 0.8927 | 0.2318 |
0.8301 | 10.7989 | 26900 | 0.8608 | 0.2297 |
0.7786 | 10.8390 | 27000 | 0.8592 | 0.2230 |
0.8312 | 10.8792 | 27100 | 0.9120 | 0.2453 |
0.7982 | 10.9193 | 27200 | 0.8837 | 0.2179 |
0.8149 | 10.9595 | 27300 | 0.8610 | 0.2283 |
0.728 | 10.9996 | 27400 | 0.9033 | 0.2246 |
0.9352 | 11.0397 | 27500 | 0.8505 | 0.2201 |
0.7205 | 11.0799 | 27600 | 0.8699 | 0.2212 |
0.7428 | 11.1200 | 27700 | 0.9217 | 0.2595 |
0.8372 | 11.1602 | 27800 | 0.9184 | 0.2369 |
0.8076 | 11.2003 | 27900 | 1.0621 | 0.2367 |
0.765 | 11.2405 | 28000 | 0.8950 | 0.2234 |
0.6942 | 11.2806 | 28100 | 0.8770 | 0.2308 |
0.7333 | 11.3208 | 28200 | 0.8796 | 0.2163 |
0.8084 | 11.3609 | 28300 | 0.9290 | 0.2414 |
0.7314 | 11.4010 | 28400 | 0.9867 | 0.2244 |
0.7662 | 11.4412 | 28500 | 0.9568 | 0.2222 |
0.6608 | 11.4813 | 28600 | 0.8829 | 0.2179 |
0.6865 | 11.5215 | 28700 | 0.9207 | 0.2220 |
0.8024 | 11.5616 | 28800 | 0.8663 | 0.2083 |
0.9772 | 11.6018 | 28900 | 0.8212 | 0.2118 |
0.7438 | 11.6419 | 29000 | 0.8901 | 0.2146 |
0.777 | 11.6821 | 29100 | 0.8588 | 0.2111 |
0.7074 | 11.7222 | 29200 | 1.0209 | 0.2271 |
0.7386 | 11.7623 | 29300 | 0.8616 | 0.2056 |
0.8962 | 11.8025 | 29400 | 0.8774 | 0.2132 |
0.8545 | 11.8426 | 29500 | 0.9754 | 0.2185 |
0.8524 | 11.8828 | 29600 | 0.8556 | 0.2122 |
0.8451 | 11.9229 | 29700 | 1.0848 | 0.2267 |
0.7956 | 11.9631 | 29800 | 0.8507 | 0.2126 |
0.6324 | 12.0032 | 29900 | 0.9171 | 0.2073 |
0.645 | 12.0434 | 30000 | 0.8779 | 0.1993 |
0.7425 | 12.0835 | 30100 | 0.8785 | 0.2046 |
0.531 | 12.1236 | 30200 | 0.9416 | 0.2030 |
0.8121 | 12.1638 | 30300 | 0.8835 | 0.2093 |
0.7112 | 12.2039 | 30400 | 0.8631 | 0.2062 |
0.7436 | 12.2441 | 30500 | 0.8850 | 0.2132 |
0.7704 | 12.2842 | 30600 | 0.8954 | 0.2187 |
0.9455 | 12.3244 | 30700 | 0.8952 | 0.2069 |
0.8331 | 12.3645 | 30800 | 0.8798 | 0.2132 |
0.7309 | 12.4047 | 30900 | 0.9515 | 0.2093 |
0.7844 | 12.4448 | 31000 | 0.9657 | 0.2101 |
0.8537 | 12.4849 | 31100 | 0.8691 | 0.2101 |
0.6888 | 12.5251 | 31200 | 0.8883 | 0.2128 |
0.6188 | 12.5652 | 31300 | 0.8470 | 0.2169 |
0.7129 | 12.6054 | 31400 | 0.8225 | 0.2018 |
0.7773 | 12.6455 | 31500 | 0.7836 | 0.2134 |
0.6845 | 12.6857 | 31600 | 0.8167 | 0.2077 |
0.8228 | 12.7258 | 31700 | 0.9364 | 0.2183 |
0.8195 | 12.7660 | 31800 | 0.8969 | 0.2105 |
0.7402 | 12.8061 | 31900 | 1.0006 | 0.2114 |
0.7813 | 12.8462 | 32000 | 0.8498 | 0.2026 |
0.6478 | 12.8864 | 32100 | 0.9004 | 0.2124 |
0.8361 | 12.9265 | 32200 | 0.9111 | 0.2052 |
0.7994 | 12.9667 | 32300 | 0.9034 | 0.2144 |
0.7909 | 13.0068 | 32400 | 0.8938 | 0.2079 |
0.6811 | 13.0470 | 32500 | 0.8858 | 0.2091 |
0.563 | 13.0871 | 32600 | 0.8999 | 0.2034 |
0.6682 | 13.1273 | 32700 | 0.8981 | 0.2034 |
0.706 | 13.1674 | 32800 | 0.8612 | 0.2056 |
0.7976 | 13.2075 | 32900 | 0.8138 | 0.2103 |
0.8008 | 13.2477 | 33000 | 0.7958 | 0.2085 |
0.8463 | 13.2878 | 33100 | 0.8712 | 0.2038 |
0.6681 | 13.3280 | 33200 | 0.8361 | 0.2158 |
0.7134 | 13.3681 | 33300 | 0.8597 | 0.2034 |
0.7329 | 13.4083 | 33400 | 0.9157 | 0.2056 |
0.7727 | 13.4484 | 33500 | 0.8357 | 0.2230 |
0.6033 | 13.4886 | 33600 | 0.8803 | 0.2173 |
0.8581 | 13.5287 | 33700 | 0.8431 | 0.2038 |
0.6832 | 13.5688 | 33800 | 0.8858 | 0.2126 |
0.8517 | 13.6090 | 33900 | 0.8502 | 0.2073 |
0.8283 | 13.6491 | 34000 | 0.8683 | 0.1989 |
0.7186 | 13.6893 | 34100 | 0.8529 | 0.2101 |
0.6209 | 13.7294 | 34200 | 0.8507 | 0.2005 |
0.7638 | 13.7696 | 34300 | 0.8467 | 0.2020 |
0.7863 | 13.8097 | 34400 | 0.8806 | 0.2048 |
0.8402 | 13.8499 | 34500 | 0.8145 | 0.2256 |
0.7758 | 13.8900 | 34600 | 0.7671 | 0.1987 |
0.7806 | 13.9301 | 34700 | 0.8569 | 0.2024 |
0.8085 | 13.9703 | 34800 | 0.8708 | 0.2142 |
0.727 | 14.0104 | 34900 | 0.8301 | 0.2434 |
0.7736 | 14.0506 | 35000 | 0.8420 | 0.2173 |
0.6747 | 14.0907 | 35100 | 0.8429 | 0.2120 |
0.5693 | 14.1309 | 35200 | 0.8368 | 0.2001 |
0.6668 | 14.1710 | 35300 | 0.8503 | 0.2224 |
0.7383 | 14.2112 | 35400 | 0.8251 | 0.2116 |
0.745 | 14.2513 | 35500 | 0.9056 | 0.2101 |
0.7397 | 14.2914 | 35600 | 0.8141 | 0.2203 |
0.4953 | 14.3316 | 35700 | 0.8187 | 0.2050 |
0.7503 | 14.3717 | 35800 | 0.8143 | 0.2042 |
0.8601 | 14.4119 | 35900 | 0.8500 | 0.2116 |
0.684 | 14.4520 | 36000 | 0.8394 | 0.2085 |
0.7865 | 14.4922 | 36100 | 0.8065 | 0.2013 |
0.7138 | 14.5323 | 36200 | 0.7788 | 0.1977 |
0.6454 | 14.5725 | 36300 | 0.7670 | 0.2103 |
0.706 | 14.6126 | 36400 | 0.8304 | 0.2038 |
0.5968 | 14.6527 | 36500 | 0.9246 | 0.2226 |
0.6861 | 14.6929 | 36600 | 0.9305 | 0.2261 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.4.1
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 17
Model tree for sqrk/All_balanced-mms1ball-Dec1
Base model
facebook/mms-1b-all