cportoca/MMS_Quechua_finetuned_qve
Browse files
README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
base_model: facebook/mms-1b-all
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: MMS_Quechua_finetuned_qve
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# MMS_Quechua_finetuned_qve
|
| 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: 0.2527
|
| 22 |
+
- Wer: 0.3191
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.001
|
| 42 |
+
- train_batch_size: 16
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 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 |
+
| 1.5146 | 0.1355 | 100 | 0.6473 | 0.5519 |
|
| 56 |
+
| 0.74 | 0.2710 | 200 | 0.5775 | 0.4716 |
|
| 57 |
+
| 0.6064 | 0.4065 | 300 | 0.5398 | 0.4490 |
|
| 58 |
+
| 0.59 | 0.5420 | 400 | 0.5168 | 0.4365 |
|
| 59 |
+
| 0.5733 | 0.6775 | 500 | 0.5090 | 0.4707 |
|
| 60 |
+
| 1.0555 | 0.8130 | 600 | 0.5121 | 0.4321 |
|
| 61 |
+
| 0.5509 | 0.9485 | 700 | 0.4951 | 0.4506 |
|
| 62 |
+
| 0.6772 | 1.0840 | 800 | 0.4541 | 0.4161 |
|
| 63 |
+
| 0.5271 | 1.2195 | 900 | 0.4531 | 0.4437 |
|
| 64 |
+
| 0.6283 | 1.3550 | 1000 | 0.4684 | 0.4198 |
|
| 65 |
+
| 0.6823 | 1.4905 | 1100 | 0.4647 | 0.4518 |
|
| 66 |
+
| 0.7715 | 1.6260 | 1200 | 0.4325 | 0.4057 |
|
| 67 |
+
| 0.4755 | 1.7615 | 1300 | 0.4222 | 0.4048 |
|
| 68 |
+
| 0.4751 | 1.8970 | 1400 | 0.4169 | 0.4321 |
|
| 69 |
+
| 0.6891 | 2.0325 | 1500 | 0.4054 | 0.4063 |
|
| 70 |
+
| 0.6245 | 2.1680 | 1600 | 0.3862 | 0.4060 |
|
| 71 |
+
| 0.4548 | 2.3035 | 1700 | 0.3839 | 0.4302 |
|
| 72 |
+
| 0.4506 | 2.4390 | 1800 | 0.3661 | 0.4079 |
|
| 73 |
+
| 0.7592 | 2.5745 | 1900 | 0.3587 | 0.3916 |
|
| 74 |
+
| 0.4698 | 2.7100 | 2000 | 0.3737 | 0.4114 |
|
| 75 |
+
| 0.6196 | 2.8455 | 2100 | 0.3558 | 0.3888 |
|
| 76 |
+
| 0.6997 | 2.9810 | 2200 | 0.3518 | 0.3822 |
|
| 77 |
+
| 0.5634 | 3.1165 | 2300 | 0.3674 | 0.3897 |
|
| 78 |
+
| 0.4163 | 3.2520 | 2400 | 0.3636 | 0.3894 |
|
| 79 |
+
| 0.6243 | 3.3875 | 2500 | 0.3652 | 0.3721 |
|
| 80 |
+
| 0.623 | 3.5230 | 2600 | 0.3393 | 0.3778 |
|
| 81 |
+
| 0.557 | 3.6585 | 2700 | 0.3453 | 0.3900 |
|
| 82 |
+
| 0.573 | 3.7940 | 2800 | 0.3574 | 0.3885 |
|
| 83 |
+
| 0.4114 | 3.9295 | 2900 | 0.3537 | 0.3812 |
|
| 84 |
+
| 0.6551 | 4.0650 | 3000 | 0.3646 | 0.3897 |
|
| 85 |
+
| 0.5701 | 4.2005 | 3100 | 0.3513 | 0.3954 |
|
| 86 |
+
| 0.5688 | 4.3360 | 3200 | 0.3395 | 0.3772 |
|
| 87 |
+
| 0.5151 | 4.4715 | 3300 | 0.3633 | 0.3919 |
|
| 88 |
+
| 0.4063 | 4.6070 | 3400 | 0.3365 | 0.3781 |
|
| 89 |
+
| 0.671 | 4.7425 | 3500 | 0.3765 | 0.4016 |
|
| 90 |
+
| 0.3761 | 4.8780 | 3600 | 0.3294 | 0.3734 |
|
| 91 |
+
| 0.4151 | 5.0136 | 3700 | 0.3322 | 0.3634 |
|
| 92 |
+
| 0.3634 | 5.1491 | 3800 | 0.3291 | 0.3740 |
|
| 93 |
+
| 0.5112 | 5.2846 | 3900 | 0.3723 | 0.3762 |
|
| 94 |
+
| 0.5892 | 5.4201 | 4000 | 0.3300 | 0.3863 |
|
| 95 |
+
| 0.723 | 5.5556 | 4100 | 0.3261 | 0.3659 |
|
| 96 |
+
| 0.4026 | 5.6911 | 4200 | 0.3332 | 0.3888 |
|
| 97 |
+
| 0.3836 | 5.8266 | 4300 | 0.3407 | 0.3574 |
|
| 98 |
+
| 0.5441 | 5.9621 | 4400 | 0.3370 | 0.3803 |
|
| 99 |
+
| 0.5204 | 6.0976 | 4500 | 0.3405 | 0.3778 |
|
| 100 |
+
| 0.3738 | 6.2331 | 4600 | 0.3310 | 0.3784 |
|
| 101 |
+
| 0.4918 | 6.3686 | 4700 | 0.3300 | 0.3768 |
|
| 102 |
+
| 0.5163 | 6.5041 | 4800 | 0.3314 | 0.3652 |
|
| 103 |
+
| 0.3839 | 6.6396 | 4900 | 0.3071 | 0.3574 |
|
| 104 |
+
| 0.5652 | 6.7751 | 5000 | 0.3008 | 0.3624 |
|
| 105 |
+
| 0.4961 | 6.9106 | 5100 | 0.3086 | 0.3894 |
|
| 106 |
+
| 0.58 | 7.0461 | 5200 | 0.3137 | 0.4010 |
|
| 107 |
+
| 0.3617 | 7.1816 | 5300 | 0.3328 | 0.3787 |
|
| 108 |
+
| 0.4433 | 7.3171 | 5400 | 0.3015 | 0.3806 |
|
| 109 |
+
| 0.3693 | 7.4526 | 5500 | 0.2966 | 0.3693 |
|
| 110 |
+
| 0.6693 | 7.5881 | 5600 | 0.3112 | 0.3693 |
|
| 111 |
+
| 0.4791 | 7.7236 | 5700 | 0.3076 | 0.3596 |
|
| 112 |
+
| 0.3541 | 7.8591 | 5800 | 0.3129 | 0.3590 |
|
| 113 |
+
| 0.4792 | 7.9946 | 5900 | 0.3028 | 0.3590 |
|
| 114 |
+
| 0.3385 | 8.1301 | 6000 | 0.3127 | 0.3960 |
|
| 115 |
+
| 0.6656 | 8.2656 | 6100 | 0.3139 | 0.3806 |
|
| 116 |
+
| 0.3467 | 8.4011 | 6200 | 0.3235 | 0.3706 |
|
| 117 |
+
| 0.4183 | 8.5366 | 6300 | 0.2967 | 0.3624 |
|
| 118 |
+
| 0.4535 | 8.6721 | 6400 | 0.3101 | 0.3524 |
|
| 119 |
+
| 0.3376 | 8.8076 | 6500 | 0.3109 | 0.3966 |
|
| 120 |
+
| 0.4307 | 8.9431 | 6600 | 0.3290 | 0.3822 |
|
| 121 |
+
| 0.4738 | 9.0786 | 6700 | 0.3083 | 0.3511 |
|
| 122 |
+
| 0.4388 | 9.2141 | 6800 | 0.2974 | 0.3778 |
|
| 123 |
+
| 0.3341 | 9.3496 | 6900 | 0.2917 | 0.3417 |
|
| 124 |
+
| 0.5376 | 9.4851 | 7000 | 0.2960 | 0.3436 |
|
| 125 |
+
| 0.4649 | 9.6206 | 7100 | 0.3293 | 0.3593 |
|
| 126 |
+
| 0.347 | 9.7561 | 7200 | 0.2865 | 0.3470 |
|
| 127 |
+
| 0.3213 | 9.8916 | 7300 | 0.2892 | 0.3458 |
|
| 128 |
+
| 0.5857 | 10.0271 | 7400 | 0.2850 | 0.3386 |
|
| 129 |
+
| 0.3177 | 10.1626 | 7500 | 0.2967 | 0.3502 |
|
| 130 |
+
| 0.3382 | 10.2981 | 7600 | 0.2828 | 0.3411 |
|
| 131 |
+
| 0.6518 | 10.4336 | 7700 | 0.2918 | 0.3467 |
|
| 132 |
+
| 0.3755 | 10.5691 | 7800 | 0.2953 | 0.3404 |
|
| 133 |
+
| 0.2995 | 10.7046 | 7900 | 0.2988 | 0.3646 |
|
| 134 |
+
| 0.3929 | 10.8401 | 8000 | 0.2903 | 0.3477 |
|
| 135 |
+
| 0.3097 | 10.9756 | 8100 | 0.2762 | 0.3659 |
|
| 136 |
+
| 0.3004 | 11.1111 | 8200 | 0.2929 | 0.3599 |
|
| 137 |
+
| 0.312 | 11.2466 | 8300 | 0.2822 | 0.3527 |
|
| 138 |
+
| 0.3812 | 11.3821 | 8400 | 0.2833 | 0.3386 |
|
| 139 |
+
| 0.3812 | 11.5176 | 8500 | 0.2926 | 0.3395 |
|
| 140 |
+
| 0.3133 | 11.6531 | 8600 | 0.2838 | 0.3414 |
|
| 141 |
+
| 0.5852 | 11.7886 | 8700 | 0.2836 | 0.3517 |
|
| 142 |
+
| 0.3755 | 11.9241 | 8800 | 0.2772 | 0.3536 |
|
| 143 |
+
| 0.3526 | 12.0596 | 8900 | 0.2828 | 0.3621 |
|
| 144 |
+
| 0.3837 | 12.1951 | 9000 | 0.2826 | 0.3652 |
|
| 145 |
+
| 0.318 | 12.3306 | 9100 | 0.2790 | 0.3696 |
|
| 146 |
+
| 0.2932 | 12.4661 | 9200 | 0.2846 | 0.3649 |
|
| 147 |
+
| 0.5292 | 12.6016 | 9300 | 0.2754 | 0.3417 |
|
| 148 |
+
| 0.2977 | 12.7371 | 9400 | 0.2808 | 0.3652 |
|
| 149 |
+
| 0.3229 | 12.8726 | 9500 | 0.2811 | 0.3521 |
|
| 150 |
+
| 0.3711 | 13.0081 | 9600 | 0.2855 | 0.3436 |
|
| 151 |
+
| 0.255 | 13.1436 | 9700 | 0.3100 | 0.3546 |
|
| 152 |
+
| 0.369 | 13.2791 | 9800 | 0.2865 | 0.3326 |
|
| 153 |
+
| 0.3094 | 13.4146 | 9900 | 0.2817 | 0.3423 |
|
| 154 |
+
| 0.5302 | 13.5501 | 10000 | 0.2715 | 0.3295 |
|
| 155 |
+
| 0.3156 | 13.6856 | 10100 | 0.2777 | 0.3439 |
|
| 156 |
+
| 0.356 | 13.8211 | 10200 | 0.2766 | 0.3354 |
|
| 157 |
+
| 0.2856 | 13.9566 | 10300 | 0.2806 | 0.3436 |
|
| 158 |
+
| 0.326 | 14.0921 | 10400 | 0.2738 | 0.3502 |
|
| 159 |
+
| 0.4744 | 14.2276 | 10500 | 0.2732 | 0.3339 |
|
| 160 |
+
| 0.2968 | 14.3631 | 10600 | 0.2683 | 0.3332 |
|
| 161 |
+
| 0.2897 | 14.4986 | 10700 | 0.2704 | 0.3373 |
|
| 162 |
+
| 0.2684 | 14.6341 | 10800 | 0.2694 | 0.3470 |
|
| 163 |
+
| 0.2939 | 14.7696 | 10900 | 0.2762 | 0.3345 |
|
| 164 |
+
| 0.2777 | 14.9051 | 11000 | 0.2646 | 0.3514 |
|
| 165 |
+
| 0.2785 | 15.0407 | 11100 | 0.2633 | 0.3404 |
|
| 166 |
+
| 0.2633 | 15.1762 | 11200 | 0.2640 | 0.3426 |
|
| 167 |
+
| 0.2957 | 15.3117 | 11300 | 0.2654 | 0.3546 |
|
| 168 |
+
| 0.2758 | 15.4472 | 11400 | 0.2694 | 0.3467 |
|
| 169 |
+
| 0.2881 | 15.5827 | 11500 | 0.2628 | 0.3329 |
|
| 170 |
+
| 0.522 | 15.7182 | 11600 | 0.2636 | 0.3348 |
|
| 171 |
+
| 0.2944 | 15.8537 | 11700 | 0.2656 | 0.3458 |
|
| 172 |
+
| 0.2911 | 15.9892 | 11800 | 0.2598 | 0.3401 |
|
| 173 |
+
| 0.2578 | 16.1247 | 11900 | 0.2629 | 0.3452 |
|
| 174 |
+
| 0.2737 | 16.2602 | 12000 | 0.2612 | 0.3464 |
|
| 175 |
+
| 0.3107 | 16.3957 | 12100 | 0.2566 | 0.3401 |
|
| 176 |
+
| 0.4585 | 16.5312 | 12200 | 0.2489 | 0.3549 |
|
| 177 |
+
| 0.2808 | 16.6667 | 12300 | 0.2566 | 0.3558 |
|
| 178 |
+
| 0.2682 | 16.8022 | 12400 | 0.2566 | 0.3455 |
|
| 179 |
+
| 0.2603 | 16.9377 | 12500 | 0.2552 | 0.3348 |
|
| 180 |
+
| 0.2951 | 17.0732 | 12600 | 0.2521 | 0.3310 |
|
| 181 |
+
| 0.2658 | 17.2087 | 12700 | 0.2599 | 0.3332 |
|
| 182 |
+
| 0.2642 | 17.3442 | 12800 | 0.2578 | 0.3282 |
|
| 183 |
+
| 0.2603 | 17.4797 | 12900 | 0.2586 | 0.3204 |
|
| 184 |
+
| 0.2675 | 17.6152 | 13000 | 0.2625 | 0.3332 |
|
| 185 |
+
| 0.2587 | 17.7507 | 13100 | 0.2566 | 0.3282 |
|
| 186 |
+
| 0.4357 | 17.8862 | 13200 | 0.2550 | 0.3191 |
|
| 187 |
+
| 0.2487 | 18.0217 | 13300 | 0.2534 | 0.3248 |
|
| 188 |
+
| 0.4185 | 18.1572 | 13400 | 0.2579 | 0.3241 |
|
| 189 |
+
| 0.2771 | 18.2927 | 13500 | 0.2549 | 0.3201 |
|
| 190 |
+
| 0.2514 | 18.4282 | 13600 | 0.2588 | 0.3175 |
|
| 191 |
+
| 0.2615 | 18.5637 | 13700 | 0.2527 | 0.3222 |
|
| 192 |
+
| 0.2658 | 18.6992 | 13800 | 0.2534 | 0.3160 |
|
| 193 |
+
| 0.2415 | 18.8347 | 13900 | 0.2525 | 0.3229 |
|
| 194 |
+
| 0.2427 | 18.9702 | 14000 | 0.2533 | 0.3248 |
|
| 195 |
+
| 0.2477 | 19.1057 | 14100 | 0.2517 | 0.3185 |
|
| 196 |
+
| 0.2475 | 19.2412 | 14200 | 0.2521 | 0.3201 |
|
| 197 |
+
| 0.259 | 19.3767 | 14300 | 0.2535 | 0.3232 |
|
| 198 |
+
| 0.2765 | 19.5122 | 14400 | 0.2522 | 0.3197 |
|
| 199 |
+
| 0.2503 | 19.6477 | 14500 | 0.2513 | 0.3210 |
|
| 200 |
+
| 0.3933 | 19.7832 | 14600 | 0.2525 | 0.3188 |
|
| 201 |
+
| 0.2434 | 19.9187 | 14700 | 0.2527 | 0.3191 |
|
| 202 |
+
|
| 203 |
+
|
| 204 |
+
### Framework versions
|
| 205 |
+
|
| 206 |
+
- Transformers 4.46.3
|
| 207 |
+
- Pytorch 2.4.1+cu121
|
| 208 |
+
- Datasets 3.1.0
|
| 209 |
+
- Tokenizers 0.20.3
|