End of training
Browse files- README.md +72 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ylacombe/w2v-bert-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice_16_0
|
| 7 |
+
model-index:
|
| 8 |
+
- name: w2v-bert-2.0-japanese-colab-CV16.0
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# w2v-bert-2.0-japanese-colab-CV16.0
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [ylacombe/w2v-bert-2.0](https://huggingface.co/ylacombe/w2v-bert-2.0) on the common_voice_16_0 dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: inf
|
| 20 |
+
- Cer: 0.3171
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 8
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- num_epochs: 10
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 4.2694 | 0.96 | 300 | inf | 0.6823 |
|
| 56 |
+
| 2.0595 | 1.93 | 600 | inf | 0.4528 |
|
| 57 |
+
| 1.3044 | 2.89 | 900 | inf | 0.3920 |
|
| 58 |
+
| 1.0889 | 3.85 | 1200 | inf | 0.3579 |
|
| 59 |
+
| 0.7867 | 4.82 | 1500 | inf | 0.3518 |
|
| 60 |
+
| 0.4371 | 5.78 | 1800 | inf | 0.3371 |
|
| 61 |
+
| 0.3414 | 6.74 | 2100 | inf | 0.3246 |
|
| 62 |
+
| 0.2373 | 7.7 | 2400 | inf | 0.3253 |
|
| 63 |
+
| 0.1171 | 8.67 | 2700 | inf | 0.3183 |
|
| 64 |
+
| 0.0524 | 9.63 | 3000 | inf | 0.3171 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.37.0.dev0
|
| 70 |
+
- Pytorch 2.1.2+cu121
|
| 71 |
+
- Datasets 2.16.1
|
| 72 |
+
- Tokenizers 0.15.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2433773876
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8d681bc74d8c4c1cd66189857d2dd31aeeea7d7d11579a3db1fd4a38ae88bf5
|
| 3 |
size 2433773876
|