Model save
Browse files- README.md +82 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
base_model: mms-meta/mms-zeroshot-300m
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: mms-zeroshot-300m-genbed-m-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-zeroshot-300m-genbed-m-model
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mms-meta/mms-zeroshot-300m](https://huggingface.co/mms-meta/mms-zeroshot-300m) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.3402
|
| 22 |
+
- Wer: 0.4576
|
| 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: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 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 |
+
| No log | 0.5510 | 200 | 2.3107 | 1.0 |
|
| 56 |
+
| No log | 1.1019 | 400 | 0.4860 | 0.6380 |
|
| 57 |
+
| 2.8087 | 1.6529 | 600 | 0.4381 | 0.5988 |
|
| 58 |
+
| 2.8087 | 2.2039 | 800 | 0.4281 | 0.5855 |
|
| 59 |
+
| 0.6248 | 2.7548 | 1000 | 0.4056 | 0.5656 |
|
| 60 |
+
| 0.6248 | 3.3058 | 1200 | 0.4017 | 0.5513 |
|
| 61 |
+
| 0.6248 | 3.8567 | 1400 | 0.3904 | 0.5617 |
|
| 62 |
+
| 0.578 | 4.4077 | 1600 | 0.3776 | 0.5306 |
|
| 63 |
+
| 0.578 | 4.9587 | 1800 | 0.3722 | 0.5178 |
|
| 64 |
+
| 0.5343 | 5.5096 | 2000 | 0.3659 | 0.5152 |
|
| 65 |
+
| 0.5343 | 6.0606 | 2200 | 0.3614 | 0.5150 |
|
| 66 |
+
| 0.5343 | 6.6116 | 2400 | 0.3573 | 0.5016 |
|
| 67 |
+
| 0.5153 | 7.1625 | 2600 | 0.3625 | 0.5026 |
|
| 68 |
+
| 0.5153 | 7.7135 | 2800 | 0.3545 | 0.4867 |
|
| 69 |
+
| 0.4935 | 8.2645 | 3000 | 0.3506 | 0.4814 |
|
| 70 |
+
| 0.4935 | 8.8154 | 3200 | 0.3482 | 0.4922 |
|
| 71 |
+
| 0.4935 | 9.3664 | 3400 | 0.3383 | 0.4761 |
|
| 72 |
+
| 0.4731 | 9.9174 | 3600 | 0.3419 | 0.4645 |
|
| 73 |
+
| 0.4731 | 10.4683 | 3800 | 0.3391 | 0.4686 |
|
| 74 |
+
| 0.4619 | 11.0193 | 4000 | 0.3402 | 0.4576 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.46.0.dev0
|
| 80 |
+
- Pytorch 2.4.1+cu121
|
| 81 |
+
- Datasets 3.0.1
|
| 82 |
+
- Tokenizers 0.20.0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1265394748
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93de82a2c7a2d6fb4fe78ada7d99fa915b8e1ee52f5389ad79723b6fe8668c81
|
| 3 |
size 1265394748
|