Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-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-toigen-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: 0.3150
|
| 22 |
+
- Wer: 0.3762
|
| 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 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 100
|
| 50 |
+
- num_epochs: 30.0
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:-------:|:----:|:---------------:|:------:|
|
| 57 |
+
| 15.204 | 0.4474 | 100 | 3.5867 | 1.0672 |
|
| 58 |
+
| 4.2355 | 0.8949 | 200 | 0.5745 | 0.5648 |
|
| 59 |
+
| 1.4309 | 1.3400 | 300 | 0.4451 | 0.5084 |
|
| 60 |
+
| 1.1797 | 1.7875 | 400 | 0.4035 | 0.4828 |
|
| 61 |
+
| 1.1218 | 2.2327 | 500 | 0.3912 | 0.4663 |
|
| 62 |
+
| 1.0287 | 2.6801 | 600 | 0.3838 | 0.4552 |
|
| 63 |
+
| 0.9773 | 3.1253 | 700 | 0.3751 | 0.4481 |
|
| 64 |
+
| 1.038 | 3.5727 | 800 | 0.3665 | 0.4421 |
|
| 65 |
+
| 0.9878 | 4.0179 | 900 | 0.3571 | 0.4356 |
|
| 66 |
+
| 0.9888 | 4.4653 | 1000 | 0.3510 | 0.4359 |
|
| 67 |
+
| 0.8904 | 4.9128 | 1100 | 0.3498 | 0.4172 |
|
| 68 |
+
| 0.8178 | 5.3579 | 1200 | 0.3456 | 0.4152 |
|
| 69 |
+
| 0.9608 | 5.8054 | 1300 | 0.3384 | 0.4184 |
|
| 70 |
+
| 0.9166 | 6.2506 | 1400 | 0.3416 | 0.4099 |
|
| 71 |
+
| 0.8623 | 6.6980 | 1500 | 0.3351 | 0.4034 |
|
| 72 |
+
| 0.823 | 7.1432 | 1600 | 0.3306 | 0.3977 |
|
| 73 |
+
| 0.8495 | 7.5906 | 1700 | 0.3321 | 0.3937 |
|
| 74 |
+
| 0.8691 | 8.0358 | 1800 | 0.3244 | 0.3986 |
|
| 75 |
+
| 0.8225 | 8.4832 | 1900 | 0.3261 | 0.3956 |
|
| 76 |
+
| 0.8193 | 8.9306 | 2000 | 0.3224 | 0.3921 |
|
| 77 |
+
| 0.79 | 9.3758 | 2100 | 0.3181 | 0.3884 |
|
| 78 |
+
| 0.8035 | 9.8233 | 2200 | 0.3272 | 0.3887 |
|
| 79 |
+
| 0.8391 | 10.2685 | 2300 | 0.3177 | 0.3894 |
|
| 80 |
+
| 0.8055 | 10.7159 | 2400 | 0.3255 | 0.3790 |
|
| 81 |
+
| 0.7124 | 11.1611 | 2500 | 0.3137 | 0.3912 |
|
| 82 |
+
| 0.7747 | 11.6085 | 2600 | 0.3264 | 0.3850 |
|
| 83 |
+
| 0.795 | 12.0537 | 2700 | 0.3150 | 0.3852 |
|
| 84 |
+
| 0.7749 | 12.5011 | 2800 | 0.3177 | 0.3806 |
|
| 85 |
+
| 0.7364 | 12.9485 | 2900 | 0.3150 | 0.3762 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- Transformers 4.47.1
|
| 91 |
+
- Pytorch 2.5.1+cu124
|
| 92 |
+
- Datasets 3.2.0
|
| 93 |
+
- 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:c05b949901cc9c216d0ffb8113ce5711b72ee9fd81f61cdaf2c19ee213e916e7
|
| 3 |
size 3858885800
|
runs/Jan03_15-39-30_srvrocgpu011.uct.ac.za/events.out.tfevents.1735911637.srvrocgpu011.uct.ac.za
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3748dc3bb02e777d89c7ae3edc5c7a5542248d7bd7a2464403ab062dcf7b373
|
| 3 |
+
size 22242
|