Model save
Browse files- README.md +100 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-bigcgen-baseline-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-bigcgen-baseline-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: 0.5130
|
| 22 |
+
- Wer: 0.4597
|
| 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 |
+
| 12.3367 | 0.3058 | 100 | 1.3241 | 0.8893 |
|
| 58 |
+
| 1.8764 | 0.6116 | 200 | 0.6894 | 0.5815 |
|
| 59 |
+
| 1.6712 | 0.9174 | 300 | 0.6390 | 0.5514 |
|
| 60 |
+
| 1.5044 | 1.2232 | 400 | 0.6301 | 0.5351 |
|
| 61 |
+
| 1.6648 | 1.5291 | 500 | 0.6076 | 0.5283 |
|
| 62 |
+
| 1.6411 | 1.8349 | 600 | 0.6073 | 0.5283 |
|
| 63 |
+
| 1.4016 | 2.1407 | 700 | 0.5994 | 0.5124 |
|
| 64 |
+
| 1.5703 | 2.4465 | 800 | 0.5997 | 0.5162 |
|
| 65 |
+
| 1.4165 | 2.7523 | 900 | 0.5850 | 0.5084 |
|
| 66 |
+
| 1.4703 | 3.0581 | 1000 | 0.5912 | 0.5127 |
|
| 67 |
+
| 1.48 | 3.3639 | 1100 | 0.5707 | 0.4999 |
|
| 68 |
+
| 1.4769 | 3.6697 | 1200 | 0.5675 | 0.4949 |
|
| 69 |
+
| 1.312 | 3.9755 | 1300 | 0.5856 | 0.4980 |
|
| 70 |
+
| 1.3821 | 4.2813 | 1400 | 0.5642 | 0.4992 |
|
| 71 |
+
| 1.457 | 4.5872 | 1500 | 0.5588 | 0.5053 |
|
| 72 |
+
| 1.3606 | 4.8930 | 1600 | 0.5637 | 0.4866 |
|
| 73 |
+
| 1.3986 | 5.1988 | 1700 | 0.5511 | 0.4866 |
|
| 74 |
+
| 1.421 | 5.5046 | 1800 | 0.5846 | 0.5346 |
|
| 75 |
+
| 1.3004 | 5.8104 | 1900 | 0.5440 | 0.4736 |
|
| 76 |
+
| 1.3319 | 6.1162 | 2000 | 0.5318 | 0.4786 |
|
| 77 |
+
| 1.2665 | 6.4220 | 2100 | 0.5488 | 0.5065 |
|
| 78 |
+
| 1.3703 | 6.7278 | 2200 | 0.5304 | 0.4878 |
|
| 79 |
+
| 1.1954 | 7.0336 | 2300 | 0.5298 | 0.4807 |
|
| 80 |
+
| 1.2973 | 7.3394 | 2400 | 0.5258 | 0.4706 |
|
| 81 |
+
| 1.2086 | 7.6453 | 2500 | 0.5231 | 0.4807 |
|
| 82 |
+
| 1.2796 | 7.9511 | 2600 | 0.5404 | 0.4739 |
|
| 83 |
+
| 1.1428 | 8.2569 | 2700 | 0.5328 | 0.4831 |
|
| 84 |
+
| 1.3118 | 8.5627 | 2800 | 0.5198 | 0.4769 |
|
| 85 |
+
| 1.2569 | 8.8685 | 2900 | 0.5306 | 0.4847 |
|
| 86 |
+
| 1.1718 | 9.1743 | 3000 | 0.5160 | 0.4649 |
|
| 87 |
+
| 1.1354 | 9.4801 | 3100 | 0.5265 | 0.4777 |
|
| 88 |
+
| 1.2795 | 9.7859 | 3200 | 0.5090 | 0.4590 |
|
| 89 |
+
| 1.1793 | 10.0917 | 3300 | 0.5265 | 0.4684 |
|
| 90 |
+
| 1.1647 | 10.3976 | 3400 | 0.5385 | 0.4762 |
|
| 91 |
+
| 1.1978 | 10.7034 | 3500 | 0.5132 | 0.4715 |
|
| 92 |
+
| 1.1802 | 11.0092 | 3600 | 0.5130 | 0.4597 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- Transformers 4.47.1
|
| 98 |
+
- Pytorch 2.5.1+cu124
|
| 99 |
+
- Datasets 3.2.0
|
| 100 |
+
- 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 3858880676
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8da1c5510f97c4df84f9100e54a06d56dbc9a4a5c93f8143a61cea66a1cc57f7
|
| 3 |
size 3858880676
|