Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-toigen-balanced-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-toigen-balanced-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: 0.3752
|
| 22 |
+
- Wer: 0.3999
|
| 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 |
+
| 7.7726 | 0.4464 | 100 | 3.8109 | 0.9938 |
|
| 56 |
+
| 2.5726 | 0.8929 | 200 | 0.8106 | 0.6167 |
|
| 57 |
+
| 0.7986 | 1.3393 | 300 | 0.5409 | 0.5258 |
|
| 58 |
+
| 0.6324 | 1.7857 | 400 | 0.5256 | 0.5054 |
|
| 59 |
+
| 0.603 | 2.2321 | 500 | 0.4854 | 0.4832 |
|
| 60 |
+
| 0.59 | 2.6786 | 600 | 0.4733 | 0.4846 |
|
| 61 |
+
| 0.5489 | 3.125 | 700 | 0.4440 | 0.4657 |
|
| 62 |
+
| 0.5173 | 3.5714 | 800 | 0.4322 | 0.4576 |
|
| 63 |
+
| 0.5315 | 4.0179 | 900 | 0.4286 | 0.4453 |
|
| 64 |
+
| 0.4912 | 4.4643 | 1000 | 0.4254 | 0.4458 |
|
| 65 |
+
| 0.4728 | 4.9107 | 1100 | 0.4346 | 0.4430 |
|
| 66 |
+
| 0.4989 | 5.3571 | 1200 | 0.4050 | 0.4292 |
|
| 67 |
+
| 0.4661 | 5.8036 | 1300 | 0.4019 | 0.4255 |
|
| 68 |
+
| 0.4755 | 6.25 | 1400 | 0.4129 | 0.4449 |
|
| 69 |
+
| 0.4603 | 6.6964 | 1500 | 0.4046 | 0.4255 |
|
| 70 |
+
| 0.4229 | 7.1429 | 1600 | 0.3939 | 0.4150 |
|
| 71 |
+
| 0.455 | 7.5893 | 1700 | 0.4133 | 0.4155 |
|
| 72 |
+
| 0.4501 | 8.0357 | 1800 | 0.3978 | 0.4065 |
|
| 73 |
+
| 0.45 | 8.4821 | 1900 | 0.3925 | 0.4231 |
|
| 74 |
+
| 0.4226 | 8.9286 | 2000 | 0.3901 | 0.4098 |
|
| 75 |
+
| 0.3973 | 9.375 | 2100 | 0.3810 | 0.4056 |
|
| 76 |
+
| 0.4038 | 9.8214 | 2200 | 0.4178 | 0.4117 |
|
| 77 |
+
| 0.4559 | 10.2679 | 2300 | 0.3875 | 0.4075 |
|
| 78 |
+
| 0.4399 | 10.7143 | 2400 | 0.3742 | 0.3990 |
|
| 79 |
+
| 0.3545 | 11.1607 | 2500 | 0.3818 | 0.4013 |
|
| 80 |
+
| 0.4452 | 11.6071 | 2600 | 0.3906 | 0.3980 |
|
| 81 |
+
| 0.4014 | 12.0536 | 2700 | 0.3752 | 0.3999 |
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
### Framework versions
|
| 85 |
+
|
| 86 |
+
- Transformers 4.47.1
|
| 87 |
+
- Pytorch 2.5.1+cu124
|
| 88 |
+
- Datasets 3.2.0
|
| 89 |
+
- Tokenizers 0.21.0
|