Model save
Browse files- README.md +83 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-male-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-male-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: 0.3107
|
| 22 |
+
- Wer: 0.3264
|
| 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 |
+
| 6.7665 | 0.7634 | 100 | 3.1610 | 0.9990 |
|
| 56 |
+
| 2.6476 | 1.5267 | 200 | 2.2410 | 0.8953 |
|
| 57 |
+
| 1.5694 | 2.2901 | 300 | 0.5585 | 0.7599 |
|
| 58 |
+
| 0.6761 | 3.0534 | 400 | 0.4566 | 0.6319 |
|
| 59 |
+
| 0.5793 | 3.8168 | 500 | 0.4013 | 0.4822 |
|
| 60 |
+
| 0.5392 | 4.5802 | 600 | 0.3795 | 0.4554 |
|
| 61 |
+
| 0.4809 | 5.3435 | 700 | 0.3730 | 0.4333 |
|
| 62 |
+
| 0.4813 | 6.1069 | 800 | 0.3597 | 0.4230 |
|
| 63 |
+
| 0.4484 | 6.8702 | 900 | 0.3432 | 0.3925 |
|
| 64 |
+
| 0.4418 | 7.6336 | 1000 | 0.3391 | 0.3947 |
|
| 65 |
+
| 0.4322 | 8.3969 | 1100 | 0.3339 | 0.3841 |
|
| 66 |
+
| 0.3963 | 9.1603 | 1200 | 0.3294 | 0.3669 |
|
| 67 |
+
| 0.4104 | 9.9237 | 1300 | 0.3217 | 0.3635 |
|
| 68 |
+
| 0.3777 | 10.6870 | 1400 | 0.3177 | 0.3610 |
|
| 69 |
+
| 0.3785 | 11.4504 | 1500 | 0.3236 | 0.3539 |
|
| 70 |
+
| 0.3682 | 12.2137 | 1600 | 0.3144 | 0.3468 |
|
| 71 |
+
| 0.3654 | 12.9771 | 1700 | 0.3122 | 0.3529 |
|
| 72 |
+
| 0.3509 | 13.7405 | 1800 | 0.3088 | 0.3463 |
|
| 73 |
+
| 0.3412 | 14.5038 | 1900 | 0.3146 | 0.3347 |
|
| 74 |
+
| 0.3344 | 15.2672 | 2000 | 0.3108 | 0.3416 |
|
| 75 |
+
| 0.3351 | 16.0305 | 2100 | 0.3107 | 0.3264 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.48.0.dev0
|
| 81 |
+
- Pytorch 2.5.1+cu124
|
| 82 |
+
- Datasets 3.2.0
|
| 83 |
+
- Tokenizers 0.21.0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3858885800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0868bb3f5dbba99f030ddc729f2895a9fcb8d56dd0df65ca36e6587784ab2d8e
|
| 3 |
size 3858885800
|