--- base_model: facebook/mms-1b-all license: cc-by-nc-4.0 metrics: - wer tags: - generated_from_trainer model-index: - name: wav2vec2-large-mms-1b-nepali results: [] --- # wav2vec2-large-mms-1b-nepali This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2018 - Wer: 0.2738 ## 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: 4 - eval_batch_size: 8 - 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: 4 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:-----:|:---------------:|:------:| | 15.7875 | 0.0081 | 100 | 0.7128 | 0.5596 | | 0.7921 | 0.0162 | 200 | 0.4744 | 0.4651 | | 0.6639 | 0.0242 | 300 | 0.4011 | 0.4230 | | 0.6205 | 0.0323 | 400 | 0.3838 | 0.4260 | | 0.568 | 0.0404 | 500 | 0.3772 | 0.4248 | | 0.6622 | 0.0485 | 600 | 0.4107 | 0.4200 | | 0.5324 | 0.0566 | 700 | 0.4006 | 0.4085 | | 0.6095 | 0.0646 | 800 | 0.3860 | 0.4194 | | 0.621 | 0.0727 | 900 | 0.3578 | 0.4061 | | 0.5708 | 0.0808 | 1000 | 0.3734 | 0.4085 | | 0.5543 | 0.0889 | 1100 | 0.3835 | 0.4182 | | 0.5417 | 0.0970 | 1200 | 0.3685 | 0.4194 | | 0.5531 | 0.1051 | 1300 | 0.3499 | 0.3983 | | 0.5259 | 0.1131 | 1400 | 0.4114 | 0.4507 | | 0.5338 | 0.1212 | 1500 | 0.3347 | 0.3911 | | 0.538 | 0.1293 | 1600 | 0.3508 | 0.4067 | | 0.5817 | 0.1374 | 1700 | 0.3404 | 0.3917 | | 0.5473 | 0.1455 | 1800 | 0.5090 | 0.5439 | | 0.5294 | 0.1535 | 1900 | 0.3251 | 0.3821 | | 0.5427 | 0.1616 | 2000 | 0.3250 | 0.3797 | | 0.5325 | 0.1697 | 2100 | 0.3147 | 0.3755 | | 0.5552 | 0.1778 | 2200 | 0.3287 | 0.3911 | | 0.504 | 0.1859 | 2300 | 0.3200 | 0.3628 | | 0.5586 | 0.1939 | 2400 | 0.3537 | 0.3791 | | 0.4779 | 0.2020 | 2500 | 0.3147 | 0.3682 | | 0.5105 | 0.2101 | 2600 | 0.3333 | 0.3959 | | 0.5016 | 0.2182 | 2700 | 0.3420 | 0.3833 | | 0.5255 | 0.2263 | 2800 | 0.3145 | 0.3676 | | 0.4935 | 0.2343 | 2900 | 0.3415 | 0.3700 | | 0.5525 | 0.2424 | 3000 | 0.3250 | 0.3658 | | 0.5626 | 0.2505 | 3100 | 0.3303 | 0.3646 | | 0.4871 | 0.2586 | 3200 | 0.3303 | 0.3995 | | 0.5081 | 0.2667 | 3300 | 0.3206 | 0.3736 | | 0.5103 | 0.2747 | 3400 | 0.3091 | 0.3664 | | 0.4824 | 0.2828 | 3500 | 0.3247 | 0.3833 | | 0.4981 | 0.2909 | 3600 | 0.3175 | 0.3688 | | 0.4506 | 0.2990 | 3700 | 0.3255 | 0.3688 | | 0.5137 | 0.3071 | 3800 | 0.3321 | 0.3857 | | 0.495 | 0.3152 | 3900 | 0.3110 | 0.3580 | | 0.4884 | 0.3232 | 4000 | 0.3032 | 0.3616 | | 0.4847 | 0.3313 | 4100 | 0.3235 | 0.3845 | | 0.5265 | 0.3394 | 4200 | 0.3365 | 0.3887 | | 0.5055 | 0.3475 | 4300 | 0.3296 | 0.3664 | | 0.4912 | 0.3556 | 4400 | 0.3137 | 0.3742 | | 0.5137 | 0.3636 | 4500 | 0.3191 | 0.3761 | | 0.4948 | 0.3717 | 4600 | 0.3285 | 0.3742 | | 0.5144 | 0.3798 | 4700 | 0.3491 | 0.4091 | | 0.5589 | 0.3879 | 4800 | 0.3027 | 0.3682 | | 0.4573 | 0.3960 | 4900 | 0.3266 | 0.3700 | | 0.4707 | 0.4040 | 5000 | 0.3295 | 0.3604 | | 0.519 | 0.4121 | 5100 | 0.3657 | 0.4152 | | 0.4831 | 0.4202 | 5200 | 0.3081 | 0.3568 | | 0.4799 | 0.4283 | 5300 | 0.3032 | 0.3460 | | 0.5275 | 0.4364 | 5400 | 0.3017 | 0.3598 | | 0.5697 | 0.4444 | 5500 | 0.3040 | 0.3682 | | 0.4993 | 0.4525 | 5600 | 0.3063 | 0.3839 | | 0.4442 | 0.4606 | 5700 | 0.3219 | 0.3821 | | 0.4489 | 0.4687 | 5800 | 0.3151 | 0.3550 | | 0.4445 | 0.4768 | 5900 | 0.3308 | 0.3809 | | 0.5076 | 0.4848 | 6000 | 0.3075 | 0.3598 | | 0.4927 | 0.4929 | 6100 | 0.2955 | 0.3418 | | 0.462 | 0.5010 | 6200 | 0.3045 | 0.3442 | | 0.4713 | 0.5091 | 6300 | 0.3161 | 0.3718 | | 0.4738 | 0.5172 | 6400 | 0.2917 | 0.3460 | | 0.4744 | 0.5253 | 6500 | 0.3352 | 0.4019 | | 0.5123 | 0.5333 | 6600 | 0.2994 | 0.3670 | | 0.4307 | 0.5414 | 6700 | 0.3026 | 0.3550 | | 0.4752 | 0.5495 | 6800 | 0.3372 | 0.3833 | | 0.5713 | 0.5576 | 6900 | 0.3215 | 0.3773 | | 0.4748 | 0.5657 | 7000 | 0.2975 | 0.3652 | | 0.4392 | 0.5737 | 7100 | 0.3242 | 0.3983 | | 0.4674 | 0.5818 | 7200 | 0.2947 | 0.3544 | | 0.5192 | 0.5899 | 7300 | 0.2837 | 0.3544 | | 0.4789 | 0.5980 | 7400 | 0.2942 | 0.3502 | | 0.4905 | 0.6061 | 7500 | 0.2882 | 0.3460 | | 0.5102 | 0.6141 | 7600 | 0.2933 | 0.3562 | | 0.4122 | 0.6222 | 7700 | 0.2882 | 0.3604 | | 0.4543 | 0.6303 | 7800 | 0.2913 | 0.3622 | | 0.4413 | 0.6384 | 7900 | 0.2874 | 0.3502 | | 0.5043 | 0.6465 | 8000 | 0.2785 | 0.3568 | | 0.4628 | 0.6545 | 8100 | 0.2852 | 0.3598 | | 0.4577 | 0.6626 | 8200 | 0.2903 | 0.3436 | | 0.4575 | 0.6707 | 8300 | 0.2958 | 0.3562 | | 0.474 | 0.6788 | 8400 | 0.2876 | 0.3478 | | 0.4095 | 0.6869 | 8500 | 0.2719 | 0.3406 | | 0.4292 | 0.6949 | 8600 | 0.2808 | 0.3375 | | 0.483 | 0.7030 | 8700 | 0.2973 | 0.3718 | | 0.4899 | 0.7111 | 8800 | 0.2952 | 0.3574 | | 0.4779 | 0.7192 | 8900 | 0.2945 | 0.3586 | | 0.4629 | 0.7273 | 9000 | 0.2912 | 0.3520 | | 0.4934 | 0.7354 | 9100 | 0.2799 | 0.3574 | | 0.4781 | 0.7434 | 9200 | 0.2903 | 0.3568 | | 0.4611 | 0.7515 | 9300 | 0.2802 | 0.3381 | | 0.4391 | 0.7596 | 9400 | 0.2707 | 0.3297 | | 0.3961 | 0.7677 | 9500 | 0.2780 | 0.3321 | | 0.4649 | 0.7758 | 9600 | 0.2962 | 0.3761 | | 0.4548 | 0.7838 | 9700 | 0.2818 | 0.3394 | | 0.4207 | 0.7919 | 9800 | 0.2851 | 0.3460 | | 0.4527 | 0.8 | 9900 | 0.3131 | 0.3742 | | 0.4595 | 0.8081 | 10000 | 0.2884 | 0.3550 | | 0.4243 | 0.8162 | 10100 | 0.2812 | 0.3454 | | 0.4485 | 0.8242 | 10200 | 0.2998 | 0.3562 | | 0.4134 | 0.8323 | 10300 | 0.2891 | 0.3532 | | 0.5286 | 0.8404 | 10400 | 0.2656 | 0.3279 | | 0.4652 | 0.8485 | 10500 | 0.2827 | 0.3345 | | 0.5523 | 0.8566 | 10600 | 0.2749 | 0.3472 | | 0.4316 | 0.8646 | 10700 | 0.2800 | 0.3478 | | 0.4282 | 0.8727 | 10800 | 0.2781 | 0.3375 | | 0.4838 | 0.8808 | 10900 | 0.2862 | 0.3562 | | 0.4217 | 0.8889 | 11000 | 0.2820 | 0.3484 | | 0.4761 | 0.8970 | 11100 | 0.2787 | 0.3436 | | 0.4112 | 0.9051 | 11200 | 0.2694 | 0.3460 | | 0.4902 | 0.9131 | 11300 | 0.2745 | 0.3508 | | 0.4582 | 0.9212 | 11400 | 0.2857 | 0.3394 | | 0.4203 | 0.9293 | 11500 | 0.2767 | 0.3550 | | 0.4695 | 0.9374 | 11600 | 0.2809 | 0.3400 | | 0.4653 | 0.9455 | 11700 | 0.2824 | 0.3448 | | 0.4176 | 0.9535 | 11800 | 0.2779 | 0.3369 | | 0.4494 | 0.9616 | 11900 | 0.2799 | 0.3472 | | 0.4087 | 0.9697 | 12000 | 0.2640 | 0.3369 | | 0.6171 | 0.9778 | 12100 | 0.2635 | 0.3418 | | 0.4507 | 0.9859 | 12200 | 0.2662 | 0.3418 | | 0.463 | 0.9939 | 12300 | 0.2703 | 0.3598 | | 0.4189 | 1.0020 | 12400 | 0.2597 | 0.3225 | | 0.444 | 1.0101 | 12500 | 0.2593 | 0.3267 | | 0.4328 | 1.0182 | 12600 | 0.2645 | 0.3285 | | 0.4335 | 1.0263 | 12700 | 0.2613 | 0.3273 | | 0.4412 | 1.0343 | 12800 | 0.2633 | 0.3183 | | 0.4179 | 1.0424 | 12900 | 0.2731 | 0.3213 | | 0.4265 | 1.0505 | 13000 | 0.2735 | 0.3478 | | 0.378 | 1.0586 | 13100 | 0.2627 | 0.3249 | | 0.5185 | 1.0667 | 13200 | 0.2627 | 0.3165 | | 0.4193 | 1.0747 | 13300 | 0.2711 | 0.3394 | | 0.4204 | 1.0828 | 13400 | 0.2650 | 0.3303 | | 0.421 | 1.0909 | 13500 | 0.2686 | 0.3406 | | 0.5101 | 1.0990 | 13600 | 0.2761 | 0.3508 | | 0.4284 | 1.1071 | 13700 | 0.2678 | 0.3267 | | 0.435 | 1.1152 | 13800 | 0.2716 | 0.3436 | | 0.416 | 1.1232 | 13900 | 0.2676 | 0.3249 | | 0.4338 | 1.1313 | 14000 | 0.2641 | 0.3327 | | 0.3972 | 1.1394 | 14100 | 0.2631 | 0.3201 | | 0.4168 | 1.1475 | 14200 | 0.2671 | 0.3430 | | 0.4692 | 1.1556 | 14300 | 0.2722 | 0.3424 | | 0.4201 | 1.1636 | 14400 | 0.2633 | 0.3333 | | 0.4526 | 1.1717 | 14500 | 0.2575 | 0.3285 | | 0.3899 | 1.1798 | 14600 | 0.2639 | 0.3285 | | 0.4057 | 1.1879 | 14700 | 0.2730 | 0.3406 | | 0.3923 | 1.1960 | 14800 | 0.2626 | 0.3213 | | 0.3788 | 1.2040 | 14900 | 0.2651 | 0.3394 | | 0.4175 | 1.2121 | 15000 | 0.2668 | 0.3442 | | 0.409 | 1.2202 | 15100 | 0.2698 | 0.3201 | | 0.4194 | 1.2283 | 15200 | 0.2773 | 0.3484 | | 0.4265 | 1.2364 | 15300 | 0.2551 | 0.3165 | | 0.4349 | 1.2444 | 15400 | 0.2620 | 0.3189 | | 0.4156 | 1.2525 | 15500 | 0.2657 | 0.3532 | | 0.4293 | 1.2606 | 15600 | 0.2557 | 0.3032 | | 0.4109 | 1.2687 | 15700 | 0.2535 | 0.3105 | | 0.3708 | 1.2768 | 15800 | 0.2597 | 0.3207 | | 0.4767 | 1.2848 | 15900 | 0.2611 | 0.3159 | | 0.4414 | 1.2929 | 16000 | 0.2578 | 0.3255 | | 0.3919 | 1.3010 | 16100 | 0.2528 | 0.3183 | | 0.4225 | 1.3091 | 16200 | 0.2627 | 0.3514 | | 0.4427 | 1.3172 | 16300 | 0.2507 | 0.3093 | | 0.3986 | 1.3253 | 16400 | 0.2686 | 0.3484 | | 0.4117 | 1.3333 | 16500 | 0.2549 | 0.3261 | | 0.4071 | 1.3414 | 16600 | 0.2622 | 0.3261 | | 0.3876 | 1.3495 | 16700 | 0.2593 | 0.3369 | | 0.437 | 1.3576 | 16800 | 0.2512 | 0.3183 | | 0.4414 | 1.3657 | 16900 | 0.2460 | 0.3020 | | 0.4109 | 1.3737 | 17000 | 0.2557 | 0.3321 | | 0.4121 | 1.3818 | 17100 | 0.2574 | 0.3291 | | 0.3989 | 1.3899 | 17200 | 0.2514 | 0.3207 | | 0.3941 | 1.3980 | 17300 | 0.2591 | 0.3165 | | 0.4127 | 1.4061 | 17400 | 0.2590 | 0.3141 | | 0.397 | 1.4141 | 17500 | 0.2510 | 0.3093 | | 0.401 | 1.4222 | 17600 | 0.2620 | 0.3249 | | 0.439 | 1.4303 | 17700 | 0.2550 | 0.3177 | | 0.4145 | 1.4384 | 17800 | 0.2532 | 0.3153 | | 0.4733 | 1.4465 | 17900 | 0.2578 | 0.3249 | | 0.3935 | 1.4545 | 18000 | 0.2590 | 0.3189 | | 0.4028 | 1.4626 | 18100 | 0.2594 | 0.3159 | | 0.4086 | 1.4707 | 18200 | 0.2506 | 0.3075 | | 0.3725 | 1.4788 | 18300 | 0.2895 | 0.3333 | | 0.4262 | 1.4869 | 18400 | 0.2586 | 0.3255 | | 0.425 | 1.4949 | 18500 | 0.2472 | 0.3177 | | 0.3984 | 1.5030 | 18600 | 0.2563 | 0.3171 | | 0.3879 | 1.5111 | 18700 | 0.2701 | 0.3574 | | 0.4227 | 1.5192 | 18800 | 0.2575 | 0.3243 | | 0.4294 | 1.5273 | 18900 | 0.2648 | 0.3357 | | 0.4068 | 1.5354 | 19000 | 0.2516 | 0.3231 | | 0.3703 | 1.5434 | 19100 | 0.2562 | 0.3249 | | 0.4191 | 1.5515 | 19200 | 0.2557 | 0.3339 | | 0.4242 | 1.5596 | 19300 | 0.2590 | 0.3297 | | 0.417 | 1.5677 | 19400 | 0.2483 | 0.3093 | | 0.3739 | 1.5758 | 19500 | 0.2531 | 0.3261 | | 0.4015 | 1.5838 | 19600 | 0.2502 | 0.3237 | | 0.4524 | 1.5919 | 19700 | 0.2489 | 0.3147 | | 0.4003 | 1.6 | 19800 | 0.2505 | 0.3153 | | 0.4222 | 1.6081 | 19900 | 0.2481 | 0.3093 | | 0.3949 | 1.6162 | 20000 | 0.2422 | 0.3165 | | 0.3868 | 1.6242 | 20100 | 0.2491 | 0.3171 | | 0.3918 | 1.6323 | 20200 | 0.2581 | 0.3171 | | 0.3857 | 1.6404 | 20300 | 0.2602 | 0.3387 | | 0.4372 | 1.6485 | 20400 | 0.2551 | 0.3165 | | 0.3828 | 1.6566 | 20500 | 0.2587 | 0.3111 | | 0.374 | 1.6646 | 20600 | 0.2600 | 0.3075 | | 0.386 | 1.6727 | 20700 | 0.2548 | 0.3135 | | 0.3849 | 1.6808 | 20800 | 0.2583 | 0.3123 | | 0.387 | 1.6889 | 20900 | 0.2418 | 0.3087 | | 0.3949 | 1.6970 | 21000 | 0.2496 | 0.3213 | | 0.4082 | 1.7051 | 21100 | 0.2538 | 0.3321 | | 0.383 | 1.7131 | 21200 | 0.2476 | 0.3153 | | 0.3763 | 1.7212 | 21300 | 0.2498 | 0.3105 | | 0.403 | 1.7293 | 21400 | 0.2414 | 0.3099 | | 0.3998 | 1.7374 | 21500 | 0.2487 | 0.3141 | | 0.3987 | 1.7455 | 21600 | 0.2529 | 0.3135 | | 0.3935 | 1.7535 | 21700 | 0.2470 | 0.3183 | | 0.3685 | 1.7616 | 21800 | 0.2543 | 0.3177 | | 0.3545 | 1.7697 | 21900 | 0.2570 | 0.3556 | | 0.4191 | 1.7778 | 22000 | 0.2485 | 0.3117 | | 0.3801 | 1.7859 | 22100 | 0.2523 | 0.3430 | | 0.3657 | 1.7939 | 22200 | 0.2512 | 0.3207 | | 0.3989 | 1.8020 | 22300 | 0.2512 | 0.3141 | | 0.4272 | 1.8101 | 22400 | 0.2479 | 0.3057 | | 0.3538 | 1.8182 | 22500 | 0.2522 | 0.3093 | | 0.3669 | 1.8263 | 22600 | 0.2449 | 0.3081 | | 0.4001 | 1.8343 | 22700 | 0.2464 | 0.3141 | | 0.4654 | 1.8424 | 22800 | 0.2414 | 0.3189 | | 0.4409 | 1.8505 | 22900 | 0.2571 | 0.3249 | | 0.4003 | 1.8586 | 23000 | 0.2491 | 0.3303 | | 0.373 | 1.8667 | 23100 | 0.2544 | 0.3273 | | 0.4319 | 1.8747 | 23200 | 0.2551 | 0.3051 | | 0.3598 | 1.8828 | 23300 | 0.2442 | 0.3141 | | 0.3741 | 1.8909 | 23400 | 0.2451 | 0.3153 | | 0.414 | 1.8990 | 23500 | 0.2415 | 0.3135 | | 0.3897 | 1.9071 | 23600 | 0.2473 | 0.3237 | | 0.3844 | 1.9152 | 23700 | 0.2453 | 0.3087 | | 0.401 | 1.9232 | 23800 | 0.2479 | 0.3129 | | 0.372 | 1.9313 | 23900 | 0.2415 | 0.2966 | | 0.3568 | 1.9394 | 24000 | 0.2417 | 0.3039 | | 0.3972 | 1.9475 | 24100 | 0.2442 | 0.3117 | | 0.3564 | 1.9556 | 24200 | 0.2487 | 0.3141 | | 0.3876 | 1.9636 | 24300 | 0.2533 | 0.3105 | | 0.413 | 1.9717 | 24400 | 0.2516 | 0.3279 | | 0.4999 | 1.9798 | 24500 | 0.2425 | 0.3165 | | 0.3829 | 1.9879 | 24600 | 0.2452 | 0.3093 | | 0.4165 | 1.9960 | 24700 | 0.2484 | 0.3039 | | 0.3879 | 2.0040 | 24800 | 0.2390 | 0.2984 | | 0.3857 | 2.0121 | 24900 | 0.2342 | 0.3081 | | 0.4062 | 2.0202 | 25000 | 0.2359 | 0.2948 | | 0.3909 | 2.0283 | 25100 | 0.2368 | 0.3069 | | 0.3664 | 2.0364 | 25200 | 0.2463 | 0.2990 | | 0.3949 | 2.0444 | 25300 | 0.2402 | 0.2996 | | 0.3731 | 2.0525 | 25400 | 0.2427 | 0.3117 | | 0.3693 | 2.0606 | 25500 | 0.2332 | 0.2984 | | 0.3648 | 2.0687 | 25600 | 0.2422 | 0.3045 | | 0.3734 | 2.0768 | 25700 | 0.2383 | 0.3008 | | 0.3858 | 2.0848 | 25800 | 0.2432 | 0.3153 | | 0.3668 | 2.0929 | 25900 | 0.2398 | 0.3183 | | 0.3795 | 2.1010 | 26000 | 0.2421 | 0.3093 | | 0.3515 | 2.1091 | 26100 | 0.2446 | 0.3135 | | 0.3636 | 2.1172 | 26200 | 0.2392 | 0.3002 | | 0.4091 | 2.1253 | 26300 | 0.2346 | 0.3105 | | 0.3878 | 2.1333 | 26400 | 0.2363 | 0.3026 | | 0.3577 | 2.1414 | 26500 | 0.2297 | 0.3111 | | 0.3776 | 2.1495 | 26600 | 0.2387 | 0.3045 | | 0.3691 | 2.1576 | 26700 | 0.2435 | 0.3255 | | 0.3642 | 2.1657 | 26800 | 0.2326 | 0.3008 | | 0.4176 | 2.1737 | 26900 | 0.2344 | 0.2924 | | 0.3463 | 2.1818 | 27000 | 0.2330 | 0.3117 | | 0.3967 | 2.1899 | 27100 | 0.2340 | 0.3026 | | 0.3597 | 2.1980 | 27200 | 0.2360 | 0.2990 | | 0.3596 | 2.2061 | 27300 | 0.2308 | 0.2942 | | 0.3889 | 2.2141 | 27400 | 0.2285 | 0.3002 | | 0.383 | 2.2222 | 27500 | 0.2343 | 0.2936 | | 0.3693 | 2.2303 | 27600 | 0.2240 | 0.2924 | | 0.3487 | 2.2384 | 27700 | 0.2344 | 0.3129 | | 0.3823 | 2.2465 | 27800 | 0.2294 | 0.2972 | | 0.3846 | 2.2545 | 27900 | 0.2279 | 0.3020 | | 0.3539 | 2.2626 | 28000 | 0.2309 | 0.2966 | | 0.3888 | 2.2707 | 28100 | 0.2251 | 0.3039 | | 0.3822 | 2.2788 | 28200 | 0.2302 | 0.3045 | | 0.3864 | 2.2869 | 28300 | 0.2290 | 0.3002 | | 0.3784 | 2.2949 | 28400 | 0.2319 | 0.3045 | | 0.3504 | 2.3030 | 28500 | 0.2312 | 0.3129 | | 0.3571 | 2.3111 | 28600 | 0.2299 | 0.3002 | | 0.3553 | 2.3192 | 28700 | 0.2271 | 0.2996 | | 0.3403 | 2.3273 | 28800 | 0.2318 | 0.3057 | | 0.3855 | 2.3354 | 28900 | 0.2249 | 0.2960 | | 0.3641 | 2.3434 | 29000 | 0.2301 | 0.2912 | | 0.3293 | 2.3515 | 29100 | 0.2384 | 0.3051 | | 0.3934 | 2.3596 | 29200 | 0.2264 | 0.2996 | | 0.385 | 2.3677 | 29300 | 0.2234 | 0.3002 | | 0.384 | 2.3758 | 29400 | 0.2270 | 0.3045 | | 0.3508 | 2.3838 | 29500 | 0.2361 | 0.3141 | | 0.3465 | 2.3919 | 29600 | 0.2352 | 0.3002 | | 0.353 | 2.4 | 29700 | 0.2299 | 0.2954 | | 0.3811 | 2.4081 | 29800 | 0.2276 | 0.2954 | | 0.3385 | 2.4162 | 29900 | 0.2232 | 0.3039 | | 0.3623 | 2.4242 | 30000 | 0.2218 | 0.2900 | | 0.3854 | 2.4323 | 30100 | 0.2274 | 0.2954 | | 0.4101 | 2.4404 | 30200 | 0.2243 | 0.2894 | | 0.3882 | 2.4485 | 30300 | 0.2243 | 0.2912 | | 0.3436 | 2.4566 | 30400 | 0.2234 | 0.2882 | | 0.3515 | 2.4646 | 30500 | 0.2309 | 0.2900 | | 0.3421 | 2.4727 | 30600 | 0.2266 | 0.2876 | | 0.3492 | 2.4808 | 30700 | 0.2335 | 0.2912 | | 0.349 | 2.4889 | 30800 | 0.2232 | 0.2918 | | 0.3532 | 2.4970 | 30900 | 0.2246 | 0.2954 | | 0.3389 | 2.5051 | 31000 | 0.2308 | 0.2996 | | 0.3824 | 2.5131 | 31100 | 0.2234 | 0.2978 | | 0.3734 | 2.5212 | 31200 | 0.2282 | 0.2990 | | 0.3607 | 2.5293 | 31300 | 0.2270 | 0.2990 | | 0.3282 | 2.5374 | 31400 | 0.2270 | 0.3117 | | 0.3163 | 2.5455 | 31500 | 0.2285 | 0.3032 | | 0.3884 | 2.5535 | 31600 | 0.2267 | 0.2906 | | 0.3776 | 2.5616 | 31700 | 0.2270 | 0.3032 | | 0.3693 | 2.5697 | 31800 | 0.2245 | 0.2966 | | 0.325 | 2.5778 | 31900 | 0.2308 | 0.3189 | | 0.3451 | 2.5859 | 32000 | 0.2280 | 0.2876 | | 0.3506 | 2.5939 | 32100 | 0.2253 | 0.2996 | | 0.3286 | 2.6020 | 32200 | 0.2247 | 0.2900 | | 0.3611 | 2.6101 | 32300 | 0.2246 | 0.2900 | | 0.3849 | 2.6182 | 32400 | 0.2217 | 0.2948 | | 0.3433 | 2.6263 | 32500 | 0.2161 | 0.2864 | | 0.3647 | 2.6343 | 32600 | 0.2233 | 0.2984 | | 0.3426 | 2.6424 | 32700 | 0.2232 | 0.2966 | | 0.3475 | 2.6505 | 32800 | 0.2226 | 0.2894 | | 0.3423 | 2.6586 | 32900 | 0.2295 | 0.2972 | | 0.3656 | 2.6667 | 33000 | 0.2210 | 0.3014 | | 0.3356 | 2.6747 | 33100 | 0.2210 | 0.2936 | | 0.3925 | 2.6828 | 33200 | 0.2164 | 0.2990 | | 0.3368 | 2.6909 | 33300 | 0.2252 | 0.3069 | | 0.3295 | 2.6990 | 33400 | 0.2211 | 0.2948 | | 0.342 | 2.7071 | 33500 | 0.2211 | 0.2966 | | 0.3738 | 2.7152 | 33600 | 0.2182 | 0.2828 | | 0.3291 | 2.7232 | 33700 | 0.2231 | 0.2930 | | 0.3686 | 2.7313 | 33800 | 0.2236 | 0.3075 | | 0.3412 | 2.7394 | 33900 | 0.2158 | 0.2942 | | 0.3689 | 2.7475 | 34000 | 0.2138 | 0.2900 | | 0.3223 | 2.7556 | 34100 | 0.2170 | 0.2930 | | 0.2917 | 2.7636 | 34200 | 0.2138 | 0.2972 | | 0.3351 | 2.7717 | 34300 | 0.2184 | 0.3111 | | 0.3306 | 2.7798 | 34400 | 0.2181 | 0.2966 | | 0.3135 | 2.7879 | 34500 | 0.2235 | 0.2942 | | 0.3416 | 2.7960 | 34600 | 0.2275 | 0.2882 | | 0.3932 | 2.8040 | 34700 | 0.2235 | 0.2858 | | 0.3595 | 2.8121 | 34800 | 0.2211 | 0.2918 | | 0.3198 | 2.8202 | 34900 | 0.2172 | 0.2888 | | 0.3397 | 2.8283 | 35000 | 0.2190 | 0.2882 | | 0.3443 | 2.8364 | 35100 | 0.2187 | 0.2828 | | 0.3616 | 2.8444 | 35200 | 0.2199 | 0.2852 | | 0.3615 | 2.8525 | 35300 | 0.2233 | 0.2954 | | 0.3611 | 2.8606 | 35400 | 0.2196 | 0.3002 | | 0.3097 | 2.8687 | 35500 | 0.2188 | 0.2888 | | 0.3947 | 2.8768 | 35600 | 0.2259 | 0.2888 | | 0.3261 | 2.8848 | 35700 | 0.2184 | 0.2888 | | 0.3392 | 2.8929 | 35800 | 0.2194 | 0.2948 | | 0.3251 | 2.9010 | 35900 | 0.2216 | 0.2978 | | 0.352 | 2.9091 | 36000 | 0.2179 | 0.2894 | | 0.3255 | 2.9172 | 36100 | 0.2208 | 0.2870 | | 0.3347 | 2.9253 | 36200 | 0.2245 | 0.2960 | | 0.3423 | 2.9333 | 36300 | 0.2209 | 0.2924 | | 0.3172 | 2.9414 | 36400 | 0.2176 | 0.2774 | | 0.3444 | 2.9495 | 36500 | 0.2174 | 0.2822 | | 0.3503 | 2.9576 | 36600 | 0.2175 | 0.2840 | | 0.3087 | 2.9657 | 36700 | 0.2240 | 0.2960 | | 0.3096 | 2.9737 | 36800 | 0.2249 | 0.2966 | | 0.4616 | 2.9818 | 36900 | 0.2200 | 0.2846 | | 0.3225 | 2.9899 | 37000 | 0.2290 | 0.3093 | | 0.3596 | 2.9980 | 37100 | 0.2224 | 0.2888 | | 0.3088 | 3.0061 | 37200 | 0.2182 | 0.2912 | | 0.3039 | 3.0141 | 37300 | 0.2217 | 0.2978 | | 0.3053 | 3.0222 | 37400 | 0.2148 | 0.2858 | | 0.3203 | 3.0303 | 37500 | 0.2188 | 0.2918 | | 0.3543 | 3.0384 | 37600 | 0.2181 | 0.2804 | | 0.3509 | 3.0465 | 37700 | 0.2157 | 0.2804 | | 0.3513 | 3.0545 | 37800 | 0.2130 | 0.2834 | | 0.3469 | 3.0626 | 37900 | 0.2147 | 0.2762 | | 0.3305 | 3.0707 | 38000 | 0.2128 | 0.2828 | | 0.3053 | 3.0788 | 38100 | 0.2166 | 0.2828 | | 0.3236 | 3.0869 | 38200 | 0.2150 | 0.2810 | | 0.3022 | 3.0949 | 38300 | 0.2164 | 0.2840 | | 0.3405 | 3.1030 | 38400 | 0.2125 | 0.2828 | | 0.3607 | 3.1111 | 38500 | 0.2155 | 0.2828 | | 0.3218 | 3.1192 | 38600 | 0.2172 | 0.2972 | | 0.3318 | 3.1273 | 38700 | 0.2194 | 0.2834 | | 0.3619 | 3.1354 | 38800 | 0.2119 | 0.2852 | | 0.3183 | 3.1434 | 38900 | 0.2108 | 0.2726 | | 0.3662 | 3.1515 | 39000 | 0.2133 | 0.2756 | | 0.3408 | 3.1596 | 39100 | 0.2109 | 0.2744 | | 0.3332 | 3.1677 | 39200 | 0.2129 | 0.2780 | | 0.4074 | 3.1758 | 39300 | 0.2151 | 0.2852 | | 0.3362 | 3.1838 | 39400 | 0.2112 | 0.2756 | | 0.2732 | 3.1919 | 39500 | 0.2115 | 0.2744 | | 0.3305 | 3.2 | 39600 | 0.2143 | 0.2756 | | 0.3362 | 3.2081 | 39700 | 0.2121 | 0.2696 | | 0.3237 | 3.2162 | 39800 | 0.2149 | 0.2744 | | 0.3223 | 3.2242 | 39900 | 0.2184 | 0.2900 | | 0.3578 | 3.2323 | 40000 | 0.2144 | 0.2852 | | 0.335 | 3.2404 | 40100 | 0.2144 | 0.2798 | | 0.3299 | 3.2485 | 40200 | 0.2156 | 0.2870 | | 0.3349 | 3.2566 | 40300 | 0.2154 | 0.2828 | | 0.3156 | 3.2646 | 40400 | 0.2142 | 0.2840 | | 0.3289 | 3.2727 | 40500 | 0.2127 | 0.2852 | | 0.3306 | 3.2808 | 40600 | 0.2147 | 0.2804 | | 0.3187 | 3.2889 | 40700 | 0.2145 | 0.2828 | | 0.3172 | 3.2970 | 40800 | 0.2168 | 0.2852 | | 0.3461 | 3.3051 | 40900 | 0.2145 | 0.2870 | | 0.3255 | 3.3131 | 41000 | 0.2121 | 0.2810 | | 0.3101 | 3.3212 | 41100 | 0.2121 | 0.2744 | | 0.2992 | 3.3293 | 41200 | 0.2118 | 0.2738 | | 0.3217 | 3.3374 | 41300 | 0.2122 | 0.2768 | | 0.3239 | 3.3455 | 41400 | 0.2099 | 0.2732 | | 0.3283 | 3.3535 | 41500 | 0.2140 | 0.2774 | | 0.3586 | 3.3616 | 41600 | 0.2112 | 0.2732 | | 0.3196 | 3.3697 | 41700 | 0.2110 | 0.2798 | | 0.3394 | 3.3778 | 41800 | 0.2115 | 0.2786 | | 0.3368 | 3.3859 | 41900 | 0.2106 | 0.2780 | | 0.2976 | 3.3939 | 42000 | 0.2105 | 0.2870 | | 0.3175 | 3.4020 | 42100 | 0.2089 | 0.2780 | | 0.3234 | 3.4101 | 42200 | 0.2104 | 0.2774 | | 0.3306 | 3.4182 | 42300 | 0.2096 | 0.2744 | | 0.362 | 3.4263 | 42400 | 0.2066 | 0.2780 | | 0.3188 | 3.4343 | 42500 | 0.2088 | 0.2804 | | 0.38 | 3.4424 | 42600 | 0.2084 | 0.2816 | | 0.3316 | 3.4505 | 42700 | 0.2093 | 0.2804 | | 0.2964 | 3.4586 | 42800 | 0.2079 | 0.2738 | | 0.3204 | 3.4667 | 42900 | 0.2061 | 0.2792 | | 0.2899 | 3.4747 | 43000 | 0.2060 | 0.2774 | | 0.3126 | 3.4828 | 43100 | 0.2093 | 0.2738 | | 0.3161 | 3.4909 | 43200 | 0.2093 | 0.2750 | | 0.312 | 3.4990 | 43300 | 0.2091 | 0.2816 | | 0.2768 | 3.5071 | 43400 | 0.2106 | 0.2744 | | 0.3602 | 3.5152 | 43500 | 0.2068 | 0.2696 | | 0.3375 | 3.5232 | 43600 | 0.2095 | 0.2780 | | 0.3238 | 3.5313 | 43700 | 0.2081 | 0.2756 | | 0.2775 | 3.5394 | 43800 | 0.2111 | 0.2774 | | 0.3183 | 3.5475 | 43900 | 0.2089 | 0.2804 | | 0.3839 | 3.5556 | 44000 | 0.2074 | 0.2798 | | 0.3158 | 3.5636 | 44100 | 0.2085 | 0.2774 | | 0.3061 | 3.5717 | 44200 | 0.2067 | 0.2750 | | 0.317 | 3.5798 | 44300 | 0.2087 | 0.2792 | | 0.341 | 3.5879 | 44400 | 0.2070 | 0.2798 | | 0.3186 | 3.5960 | 44500 | 0.2070 | 0.2786 | | 0.3621 | 3.6040 | 44600 | 0.2072 | 0.2780 | | 0.3305 | 3.6121 | 44700 | 0.2071 | 0.2792 | | 0.3022 | 3.6202 | 44800 | 0.2072 | 0.2768 | | 0.2915 | 3.6283 | 44900 | 0.2075 | 0.2792 | | 0.3064 | 3.6364 | 45000 | 0.2065 | 0.2756 | | 0.3063 | 3.6444 | 45100 | 0.2064 | 0.2732 | | 0.3129 | 3.6525 | 45200 | 0.2079 | 0.2780 | | 0.3258 | 3.6606 | 45300 | 0.2066 | 0.2768 | | 0.2909 | 3.6687 | 45400 | 0.2058 | 0.2756 | | 0.2995 | 3.6768 | 45500 | 0.2078 | 0.2774 | | 0.3169 | 3.6848 | 45600 | 0.2061 | 0.2756 | | 0.3219 | 3.6929 | 45700 | 0.2057 | 0.2738 | | 0.3248 | 3.7010 | 45800 | 0.2049 | 0.2810 | | 0.3287 | 3.7091 | 45900 | 0.2041 | 0.2780 | | 0.3036 | 3.7172 | 46000 | 0.2034 | 0.2756 | | 0.3154 | 3.7253 | 46100 | 0.2024 | 0.2744 | | 0.3255 | 3.7333 | 46200 | 0.2034 | 0.2732 | | 0.3313 | 3.7414 | 46300 | 0.2030 | 0.2690 | | 0.3366 | 3.7495 | 46400 | 0.2032 | 0.2726 | | 0.3281 | 3.7576 | 46500 | 0.2034 | 0.2774 | | 0.2544 | 3.7657 | 46600 | 0.2044 | 0.2750 | | 0.3329 | 3.7737 | 46700 | 0.2030 | 0.2744 | | 0.3236 | 3.7818 | 46800 | 0.2044 | 0.2774 | | 0.2832 | 3.7899 | 46900 | 0.2042 | 0.2744 | | 0.2946 | 3.7980 | 47000 | 0.2039 | 0.2750 | | 0.2979 | 3.8061 | 47100 | 0.2020 | 0.2690 | | 0.3227 | 3.8141 | 47200 | 0.2024 | 0.2690 | | 0.2861 | 3.8222 | 47300 | 0.2030 | 0.2714 | | 0.3177 | 3.8303 | 47400 | 0.2022 | 0.2659 | | 0.3644 | 3.8384 | 47500 | 0.2024 | 0.2671 | | 0.3227 | 3.8465 | 47600 | 0.2021 | 0.2762 | | 0.4016 | 3.8545 | 47700 | 0.2027 | 0.2762 | | 0.2869 | 3.8626 | 47800 | 0.2022 | 0.2744 | | 0.3261 | 3.8707 | 47900 | 0.2023 | 0.2702 | | 0.3377 | 3.8788 | 48000 | 0.2024 | 0.2726 | | 0.3018 | 3.8869 | 48100 | 0.2023 | 0.2714 | | 0.2937 | 3.8949 | 48200 | 0.2018 | 0.2702 | | 0.2998 | 3.9030 | 48300 | 0.2016 | 0.2726 | | 0.3123 | 3.9111 | 48400 | 0.2023 | 0.2738 | | 0.3144 | 3.9192 | 48500 | 0.2025 | 0.2750 | | 0.3238 | 3.9273 | 48600 | 0.2022 | 0.2720 | | 0.3168 | 3.9354 | 48700 | 0.2014 | 0.2744 | | 0.3445 | 3.9434 | 48800 | 0.2013 | 0.2720 | | 0.3328 | 3.9515 | 48900 | 0.2016 | 0.2750 | | 0.302 | 3.9596 | 49000 | 0.2014 | 0.2714 | | 0.2805 | 3.9677 | 49100 | 0.2017 | 0.2762 | | 0.4336 | 3.9758 | 49200 | 0.2017 | 0.2750 | | 0.3404 | 3.9838 | 49300 | 0.2018 | 0.2738 | | 0.3419 | 3.9919 | 49400 | 0.2019 | 0.2738 | | 0.3195 | 4.0 | 49500 | 0.2018 | 0.2738 | ### Framework versions - Transformers 4.45.0.dev0 - Pytorch 2.3.1+cu118 - Datasets 2.20.0 - Tokenizers 0.19.1