Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-1b-lozgen-combined-model
|
| 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-1b-lozgen-combined-model
|
| 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: 0.4288
|
| 22 |
+
- Wer: 0.3297
|
| 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: 0.0003
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 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: 30.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-------:|:----:|:---------------:|:------:|
|
| 55 |
+
| 6.5686 | 0.4065 | 100 | 3.0827 | 0.9701 |
|
| 56 |
+
| 2.6223 | 0.8130 | 200 | 2.2379 | 0.9112 |
|
| 57 |
+
| 1.4386 | 1.2195 | 300 | 0.6910 | 0.7809 |
|
| 58 |
+
| 0.8073 | 1.6260 | 400 | 0.5903 | 0.5699 |
|
| 59 |
+
| 0.651 | 2.0325 | 500 | 0.5555 | 0.5037 |
|
| 60 |
+
| 0.655 | 2.4390 | 600 | 0.5298 | 0.4818 |
|
| 61 |
+
| 0.6579 | 2.8455 | 700 | 0.5298 | 0.4603 |
|
| 62 |
+
| 0.5699 | 3.2520 | 800 | 0.5160 | 0.4284 |
|
| 63 |
+
| 0.6104 | 3.6585 | 900 | 0.5070 | 0.4320 |
|
| 64 |
+
| 0.604 | 4.0650 | 1000 | 0.4978 | 0.4098 |
|
| 65 |
+
| 0.5681 | 4.4715 | 1100 | 0.4975 | 0.4072 |
|
| 66 |
+
| 0.5493 | 4.8780 | 1200 | 0.4878 | 0.4038 |
|
| 67 |
+
| 0.581 | 5.2846 | 1300 | 0.4826 | 0.3965 |
|
| 68 |
+
| 0.5746 | 5.6911 | 1400 | 0.4793 | 0.4242 |
|
| 69 |
+
| 0.5238 | 6.0976 | 1500 | 0.4724 | 0.3833 |
|
| 70 |
+
| 0.5204 | 6.5041 | 1600 | 0.4866 | 0.3864 |
|
| 71 |
+
| 0.5563 | 6.9106 | 1700 | 0.4672 | 0.3839 |
|
| 72 |
+
| 0.5121 | 7.3171 | 1800 | 0.4664 | 0.3719 |
|
| 73 |
+
| 0.4774 | 7.7236 | 1900 | 0.4625 | 0.3652 |
|
| 74 |
+
| 0.5356 | 8.1301 | 2000 | 0.4721 | 0.3693 |
|
| 75 |
+
| 0.4385 | 8.5366 | 2100 | 0.4560 | 0.3695 |
|
| 76 |
+
| 0.5561 | 8.9431 | 2200 | 0.4453 | 0.3594 |
|
| 77 |
+
| 0.414 | 9.3496 | 2300 | 0.4489 | 0.3546 |
|
| 78 |
+
| 0.4763 | 9.7561 | 2400 | 0.4525 | 0.3521 |
|
| 79 |
+
| 0.5317 | 10.1626 | 2500 | 0.4424 | 0.3557 |
|
| 80 |
+
| 0.4939 | 10.5691 | 2600 | 0.4398 | 0.3502 |
|
| 81 |
+
| 0.4456 | 10.9756 | 2700 | 0.4415 | 0.3467 |
|
| 82 |
+
| 0.4583 | 11.3821 | 2800 | 0.4502 | 0.3446 |
|
| 83 |
+
| 0.4573 | 11.7886 | 2900 | 0.4267 | 0.3403 |
|
| 84 |
+
| 0.398 | 12.1951 | 3000 | 0.4305 | 0.3406 |
|
| 85 |
+
| 0.472 | 12.6016 | 3100 | 0.4268 | 0.3320 |
|
| 86 |
+
| 0.3993 | 13.0081 | 3200 | 0.4288 | 0.3297 |
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
### Framework versions
|
| 90 |
+
|
| 91 |
+
- Transformers 4.48.0.dev0
|
| 92 |
+
- Pytorch 2.5.1+cu124
|
| 93 |
+
- Datasets 3.2.0
|
| 94 |
+
- Tokenizers 0.21.0
|