Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-swagen-combined-30hrs-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-swagen-combined-30hrs-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: 0.2277
|
| 22 |
+
- Wer: 0.1922
|
| 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 |
+
| 16.9208 | 0.0399 | 100 | 4.2681 | 0.9999 |
|
| 58 |
+
| 7.2021 | 0.0798 | 200 | 3.4068 | 1.0027 |
|
| 59 |
+
| 6.725 | 0.1196 | 300 | 3.1580 | 1.0146 |
|
| 60 |
+
| 6.2214 | 0.1595 | 400 | 3.0439 | 1.0027 |
|
| 61 |
+
| 5.9996 | 0.1994 | 500 | 3.0050 | 1.0016 |
|
| 62 |
+
| 5.8133 | 0.2393 | 600 | 2.9415 | 1.0 |
|
| 63 |
+
| 5.805 | 0.2792 | 700 | 2.8951 | 0.9997 |
|
| 64 |
+
| 5.7621 | 0.3190 | 800 | 2.9054 | 0.9996 |
|
| 65 |
+
| 5.6973 | 0.3589 | 900 | 2.8109 | 0.9909 |
|
| 66 |
+
| 5.6541 | 0.3988 | 1000 | 2.8355 | 0.9911 |
|
| 67 |
+
| 5.4159 | 0.4387 | 1100 | 2.7632 | 0.9783 |
|
| 68 |
+
| 5.4112 | 0.4786 | 1200 | 2.6499 | 0.9793 |
|
| 69 |
+
| 4.2059 | 0.5184 | 1300 | 0.3675 | 0.2617 |
|
| 70 |
+
| 0.6493 | 0.5583 | 1400 | 0.2747 | 0.2077 |
|
| 71 |
+
| 0.5624 | 0.5982 | 1500 | 0.2649 | 0.2023 |
|
| 72 |
+
| 0.5197 | 0.6381 | 1600 | 0.2619 | 0.1988 |
|
| 73 |
+
| 0.4715 | 0.6780 | 1700 | 0.2589 | 0.1982 |
|
| 74 |
+
| 0.5126 | 0.7178 | 1800 | 0.2518 | 0.1979 |
|
| 75 |
+
| 0.4916 | 0.7577 | 1900 | 0.2549 | 0.1958 |
|
| 76 |
+
| 0.4667 | 0.7976 | 2000 | 0.2501 | 0.1947 |
|
| 77 |
+
| 0.4713 | 0.8375 | 2100 | 0.2479 | 0.1943 |
|
| 78 |
+
| 0.4875 | 0.8774 | 2200 | 0.2449 | 0.1931 |
|
| 79 |
+
| 0.4611 | 0.9172 | 2300 | 0.2436 | 0.1935 |
|
| 80 |
+
| 0.4587 | 0.9571 | 2400 | 0.2434 | 0.1928 |
|
| 81 |
+
| 0.4679 | 0.9970 | 2500 | 0.2409 | 0.1895 |
|
| 82 |
+
| 0.4141 | 1.0367 | 2600 | 0.2331 | 0.1896 |
|
| 83 |
+
| 0.4263 | 1.0766 | 2700 | 0.2329 | 0.1920 |
|
| 84 |
+
| 0.4142 | 1.1165 | 2800 | 0.2324 | 0.1918 |
|
| 85 |
+
| 0.4606 | 1.1563 | 2900 | 0.2257 | 0.1943 |
|
| 86 |
+
| 0.4048 | 1.1962 | 3000 | 0.2289 | 0.1928 |
|
| 87 |
+
| 0.4172 | 1.2361 | 3100 | 0.2326 | 0.1938 |
|
| 88 |
+
| 0.4294 | 1.2760 | 3200 | 0.2327 | 0.1941 |
|
| 89 |
+
| 0.468 | 1.3159 | 3300 | 0.2277 | 0.1922 |
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
### Framework versions
|
| 93 |
+
|
| 94 |
+
- Transformers 4.47.1
|
| 95 |
+
- Pytorch 2.5.1+cu124
|
| 96 |
+
- Datasets 3.2.0
|
| 97 |
+
- 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 3858998528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:079ba51b893f30a2e9e6681cf0cfd1e5a8f67bac728cb97507dbb3c6c862166b
|
| 3 |
size 3858998528
|
runs/Jan03_13-43-49_srvrocgpu011.uct.ac.za/events.out.tfevents.1735904709.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 sha256:566424f9514a0525d5d2b29e320a0967b4ac60753f0bd4b3bd185aa22fe0b55e
|
| 3 |
+
size 24376
|