End of training
Browse files- README.md +152 -12
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Wer: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -45,20 +45,160 @@ The following hyperparameters were used during training:
|
|
| 45 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 100
|
| 48 |
-
- num_epochs:
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
-
| Training Loss | Epoch
|
| 54 |
-
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 1.
|
| 61 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2531
|
| 22 |
+
- Wer: 0.3172
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 45 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 100
|
| 48 |
+
- num_epochs: 20
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-------:|:-----:|:---------------:|:------:|
|
| 55 |
+
| 10.4014 | 0.1355 | 100 | 4.9727 | 0.9997 |
|
| 56 |
+
| 2.7516 | 0.2710 | 200 | 0.6059 | 0.5024 |
|
| 57 |
+
| 0.6736 | 0.4065 | 300 | 0.5783 | 0.4747 |
|
| 58 |
+
| 0.5917 | 0.5420 | 400 | 0.5185 | 0.4412 |
|
| 59 |
+
| 0.5776 | 0.6775 | 500 | 0.4926 | 0.4249 |
|
| 60 |
+
| 1.0538 | 0.8130 | 600 | 0.5035 | 0.4255 |
|
| 61 |
+
| 0.5216 | 0.9485 | 700 | 0.4767 | 0.4167 |
|
| 62 |
+
| 0.6692 | 1.0840 | 800 | 0.4524 | 0.4274 |
|
| 63 |
+
| 0.5159 | 1.2195 | 900 | 0.4474 | 0.4035 |
|
| 64 |
+
| 0.631 | 1.3550 | 1000 | 0.4456 | 0.4117 |
|
| 65 |
+
| 0.6377 | 1.4905 | 1100 | 0.4422 | 0.4104 |
|
| 66 |
+
| 0.7765 | 1.6260 | 1200 | 0.4571 | 0.4082 |
|
| 67 |
+
| 0.4849 | 1.7615 | 1300 | 0.4563 | 0.4026 |
|
| 68 |
+
| 0.4695 | 1.8970 | 1400 | 0.4385 | 0.4004 |
|
| 69 |
+
| 0.6693 | 2.0325 | 1500 | 0.4209 | 0.3928 |
|
| 70 |
+
| 0.6357 | 2.1680 | 1600 | 0.4203 | 0.3966 |
|
| 71 |
+
| 0.4671 | 2.3035 | 1700 | 0.4201 | 0.3994 |
|
| 72 |
+
| 0.4672 | 2.4390 | 1800 | 0.4208 | 0.4038 |
|
| 73 |
+
| 0.7265 | 2.5745 | 1900 | 0.4195 | 0.4098 |
|
| 74 |
+
| 0.4802 | 2.7100 | 2000 | 0.3781 | 0.3828 |
|
| 75 |
+
| 0.6319 | 2.8455 | 2100 | 0.3727 | 0.3844 |
|
| 76 |
+
| 0.5765 | 2.9810 | 2200 | 0.3976 | 0.3853 |
|
| 77 |
+
| 0.5579 | 3.1165 | 2300 | 0.3601 | 0.3850 |
|
| 78 |
+
| 0.4431 | 3.2520 | 2400 | 0.3513 | 0.3881 |
|
| 79 |
+
| 0.6378 | 3.3875 | 2500 | 0.3406 | 0.3693 |
|
| 80 |
+
| 0.6201 | 3.5230 | 2600 | 0.3366 | 0.3725 |
|
| 81 |
+
| 0.5285 | 3.6585 | 2700 | 0.3390 | 0.3731 |
|
| 82 |
+
| 0.573 | 3.7940 | 2800 | 0.3563 | 0.3750 |
|
| 83 |
+
| 0.3998 | 3.9295 | 2900 | 0.4177 | 0.3731 |
|
| 84 |
+
| 0.6257 | 4.0650 | 3000 | 0.3899 | 0.3800 |
|
| 85 |
+
| 0.5346 | 4.2005 | 3100 | 0.3567 | 0.3803 |
|
| 86 |
+
| 0.5731 | 4.3360 | 3200 | 0.3671 | 0.3866 |
|
| 87 |
+
| 0.5217 | 4.4715 | 3300 | 0.3429 | 0.3768 |
|
| 88 |
+
| 0.4091 | 4.6070 | 3400 | 0.3363 | 0.3822 |
|
| 89 |
+
| 0.6284 | 4.7425 | 3500 | 0.3727 | 0.3794 |
|
| 90 |
+
| 0.3642 | 4.8780 | 3600 | 0.3273 | 0.3834 |
|
| 91 |
+
| 0.4199 | 5.0136 | 3700 | 0.3299 | 0.3765 |
|
| 92 |
+
| 0.361 | 5.1491 | 3800 | 0.3164 | 0.3539 |
|
| 93 |
+
| 0.5072 | 5.2846 | 3900 | 0.3255 | 0.3640 |
|
| 94 |
+
| 0.584 | 5.4201 | 4000 | 0.3168 | 0.3681 |
|
| 95 |
+
| 0.7192 | 5.5556 | 4100 | 0.3266 | 0.3586 |
|
| 96 |
+
| 0.4023 | 5.6911 | 4200 | 0.3279 | 0.3765 |
|
| 97 |
+
| 0.3849 | 5.8266 | 4300 | 0.3274 | 0.3533 |
|
| 98 |
+
| 0.5499 | 5.9621 | 4400 | 0.3182 | 0.3546 |
|
| 99 |
+
| 0.505 | 6.0976 | 4500 | 0.3199 | 0.3590 |
|
| 100 |
+
| 0.3689 | 6.2331 | 4600 | 0.3168 | 0.3411 |
|
| 101 |
+
| 0.4963 | 6.3686 | 4700 | 0.3228 | 0.3455 |
|
| 102 |
+
| 0.4904 | 6.5041 | 4800 | 0.3248 | 0.3634 |
|
| 103 |
+
| 0.3871 | 6.6396 | 4900 | 0.3128 | 0.3555 |
|
| 104 |
+
| 0.5636 | 6.7751 | 5000 | 0.3129 | 0.3552 |
|
| 105 |
+
| 0.525 | 6.9106 | 5100 | 0.3089 | 0.3608 |
|
| 106 |
+
| 0.5762 | 7.0461 | 5200 | 0.3170 | 0.3527 |
|
| 107 |
+
| 0.3613 | 7.1816 | 5300 | 0.3156 | 0.3602 |
|
| 108 |
+
| 0.4433 | 7.3171 | 5400 | 0.3015 | 0.3612 |
|
| 109 |
+
| 0.3692 | 7.4526 | 5500 | 0.3228 | 0.3608 |
|
| 110 |
+
| 0.6615 | 7.5881 | 5600 | 0.3052 | 0.3561 |
|
| 111 |
+
| 0.4931 | 7.7236 | 5700 | 0.3039 | 0.3458 |
|
| 112 |
+
| 0.3608 | 7.8591 | 5800 | 0.3075 | 0.3464 |
|
| 113 |
+
| 0.4666 | 7.9946 | 5900 | 0.3047 | 0.3583 |
|
| 114 |
+
| 0.3236 | 8.1301 | 6000 | 0.3117 | 0.3574 |
|
| 115 |
+
| 0.6959 | 8.2656 | 6100 | 0.3431 | 0.3499 |
|
| 116 |
+
| 0.3459 | 8.4011 | 6200 | 0.3075 | 0.3517 |
|
| 117 |
+
| 0.4103 | 8.5366 | 6300 | 0.2924 | 0.3408 |
|
| 118 |
+
| 0.424 | 8.6721 | 6400 | 0.3148 | 0.3511 |
|
| 119 |
+
| 0.3373 | 8.8076 | 6500 | 0.3104 | 0.3473 |
|
| 120 |
+
| 0.4517 | 8.9431 | 6600 | 0.3218 | 0.3546 |
|
| 121 |
+
| 0.4533 | 9.0786 | 6700 | 0.3196 | 0.3514 |
|
| 122 |
+
| 0.4015 | 9.2141 | 6800 | 0.3088 | 0.3583 |
|
| 123 |
+
| 0.336 | 9.3496 | 6900 | 0.2927 | 0.3370 |
|
| 124 |
+
| 0.5446 | 9.4851 | 7000 | 0.2840 | 0.3430 |
|
| 125 |
+
| 0.4258 | 9.6206 | 7100 | 0.3002 | 0.3430 |
|
| 126 |
+
| 0.3432 | 9.7561 | 7200 | 0.2911 | 0.3486 |
|
| 127 |
+
| 0.3131 | 9.8916 | 7300 | 0.2907 | 0.3323 |
|
| 128 |
+
| 0.5729 | 10.0271 | 7400 | 0.2942 | 0.3326 |
|
| 129 |
+
| 0.3266 | 10.1626 | 7500 | 0.2914 | 0.3401 |
|
| 130 |
+
| 0.3512 | 10.2981 | 7600 | 0.2956 | 0.3414 |
|
| 131 |
+
| 0.6843 | 10.4336 | 7700 | 0.2840 | 0.3392 |
|
| 132 |
+
| 0.3667 | 10.5691 | 7800 | 0.2857 | 0.3348 |
|
| 133 |
+
| 0.3088 | 10.7046 | 7900 | 0.2888 | 0.3351 |
|
| 134 |
+
| 0.3679 | 10.8401 | 8000 | 0.2896 | 0.3361 |
|
| 135 |
+
| 0.319 | 10.9756 | 8100 | 0.2768 | 0.3320 |
|
| 136 |
+
| 0.3045 | 11.1111 | 8200 | 0.2810 | 0.3348 |
|
| 137 |
+
| 0.3169 | 11.2466 | 8300 | 0.2813 | 0.3307 |
|
| 138 |
+
| 0.3837 | 11.3821 | 8400 | 0.2831 | 0.3251 |
|
| 139 |
+
| 0.3687 | 11.5176 | 8500 | 0.2864 | 0.3351 |
|
| 140 |
+
| 0.322 | 11.6531 | 8600 | 0.2831 | 0.3216 |
|
| 141 |
+
| 0.565 | 11.7886 | 8700 | 0.2776 | 0.3348 |
|
| 142 |
+
| 0.363 | 11.9241 | 8800 | 0.2738 | 0.3270 |
|
| 143 |
+
| 0.3281 | 12.0596 | 8900 | 0.2785 | 0.3244 |
|
| 144 |
+
| 0.3626 | 12.1951 | 9000 | 0.2773 | 0.3414 |
|
| 145 |
+
| 0.3201 | 12.3306 | 9100 | 0.2748 | 0.3222 |
|
| 146 |
+
| 0.2993 | 12.4661 | 9200 | 0.2833 | 0.3251 |
|
| 147 |
+
| 0.5219 | 12.6016 | 9300 | 0.2936 | 0.3323 |
|
| 148 |
+
| 0.3078 | 12.7371 | 9400 | 0.2801 | 0.3329 |
|
| 149 |
+
| 0.3282 | 12.8726 | 9500 | 0.2890 | 0.3298 |
|
| 150 |
+
| 0.3013 | 13.0081 | 9600 | 0.2807 | 0.3285 |
|
| 151 |
+
| 0.2689 | 13.1436 | 9700 | 0.3006 | 0.3389 |
|
| 152 |
+
| 0.3119 | 13.2791 | 9800 | 0.2885 | 0.3310 |
|
| 153 |
+
| 0.3178 | 13.4146 | 9900 | 0.2816 | 0.3279 |
|
| 154 |
+
| 0.5885 | 13.5501 | 10000 | 0.2699 | 0.3188 |
|
| 155 |
+
| 0.3134 | 13.6856 | 10100 | 0.2857 | 0.3213 |
|
| 156 |
+
| 0.3355 | 13.8211 | 10200 | 0.2729 | 0.3175 |
|
| 157 |
+
| 0.296 | 13.9566 | 10300 | 0.2732 | 0.3229 |
|
| 158 |
+
| 0.3573 | 14.0921 | 10400 | 0.2699 | 0.3345 |
|
| 159 |
+
| 0.478 | 14.2276 | 10500 | 0.2692 | 0.3188 |
|
| 160 |
+
| 0.3013 | 14.3631 | 10600 | 0.2636 | 0.3179 |
|
| 161 |
+
| 0.2978 | 14.4986 | 10700 | 0.2641 | 0.3175 |
|
| 162 |
+
| 0.2753 | 14.6341 | 10800 | 0.2697 | 0.3169 |
|
| 163 |
+
| 0.3017 | 14.7696 | 10900 | 0.2688 | 0.3179 |
|
| 164 |
+
| 0.2897 | 14.9051 | 11000 | 0.2662 | 0.3135 |
|
| 165 |
+
| 0.2861 | 15.0407 | 11100 | 0.2650 | 0.3201 |
|
| 166 |
+
| 0.2752 | 15.1762 | 11200 | 0.2582 | 0.3153 |
|
| 167 |
+
| 0.2908 | 15.3117 | 11300 | 0.2645 | 0.3219 |
|
| 168 |
+
| 0.286 | 15.4472 | 11400 | 0.2647 | 0.3147 |
|
| 169 |
+
| 0.2828 | 15.5827 | 11500 | 0.2633 | 0.3169 |
|
| 170 |
+
| 0.4632 | 15.7182 | 11600 | 0.2628 | 0.3207 |
|
| 171 |
+
| 0.2994 | 15.8537 | 11700 | 0.2595 | 0.3160 |
|
| 172 |
+
| 0.3075 | 15.9892 | 11800 | 0.2616 | 0.3201 |
|
| 173 |
+
| 0.267 | 16.1247 | 11900 | 0.2628 | 0.3207 |
|
| 174 |
+
| 0.2825 | 16.2602 | 12000 | 0.2593 | 0.3191 |
|
| 175 |
+
| 0.2684 | 16.3957 | 12100 | 0.2554 | 0.3175 |
|
| 176 |
+
| 0.4811 | 16.5312 | 12200 | 0.2554 | 0.3298 |
|
| 177 |
+
| 0.2904 | 16.6667 | 12300 | 0.2574 | 0.3160 |
|
| 178 |
+
| 0.2781 | 16.8022 | 12400 | 0.2612 | 0.3166 |
|
| 179 |
+
| 0.2667 | 16.9377 | 12500 | 0.2597 | 0.3191 |
|
| 180 |
+
| 0.2945 | 17.0732 | 12600 | 0.2584 | 0.3150 |
|
| 181 |
+
| 0.2697 | 17.2087 | 12700 | 0.2546 | 0.3125 |
|
| 182 |
+
| 0.2726 | 17.3442 | 12800 | 0.2548 | 0.3141 |
|
| 183 |
+
| 0.2679 | 17.4797 | 12900 | 0.2586 | 0.3119 |
|
| 184 |
+
| 0.2762 | 17.6152 | 13000 | 0.2588 | 0.3131 |
|
| 185 |
+
| 0.2713 | 17.7507 | 13100 | 0.2563 | 0.3125 |
|
| 186 |
+
| 0.4666 | 17.8862 | 13200 | 0.2540 | 0.3125 |
|
| 187 |
+
| 0.2568 | 18.0217 | 13300 | 0.2613 | 0.3131 |
|
| 188 |
+
| 0.4632 | 18.1572 | 13400 | 0.2566 | 0.3182 |
|
| 189 |
+
| 0.2926 | 18.2927 | 13500 | 0.2553 | 0.3166 |
|
| 190 |
+
| 0.2743 | 18.4282 | 13600 | 0.2535 | 0.3166 |
|
| 191 |
+
| 0.2677 | 18.5637 | 13700 | 0.2566 | 0.3128 |
|
| 192 |
+
| 0.2763 | 18.6992 | 13800 | 0.2537 | 0.3125 |
|
| 193 |
+
| 0.2581 | 18.8347 | 13900 | 0.2550 | 0.3144 |
|
| 194 |
+
| 0.2476 | 18.9702 | 14000 | 0.2543 | 0.3131 |
|
| 195 |
+
| 0.254 | 19.1057 | 14100 | 0.2548 | 0.3131 |
|
| 196 |
+
| 0.2591 | 19.2412 | 14200 | 0.2558 | 0.3144 |
|
| 197 |
+
| 0.2728 | 19.3767 | 14300 | 0.2534 | 0.3147 |
|
| 198 |
+
| 0.2856 | 19.5122 | 14400 | 0.2523 | 0.3144 |
|
| 199 |
+
| 0.2596 | 19.6477 | 14500 | 0.2510 | 0.3119 |
|
| 200 |
+
| 0.4273 | 19.7832 | 14600 | 0.2521 | 0.3153 |
|
| 201 |
+
| 0.2559 | 19.9187 | 14700 | 0.2531 | 0.3172 |
|
| 202 |
|
| 203 |
|
| 204 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3858890924
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b9795b5fb415587cad5a4e9ed6d1e1513c54ecb3c34e68cb65e59bc80de3c24
|
| 3 |
size 3858890924
|