update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: byt5-small-wikipron-eng-latn-nz-broad
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# byt5-small-wikipron-eng-latn-nz-broad
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.1880
|
| 18 |
+
- Per: 0.3259
|
| 19 |
+
- Gen Len: 16.3063
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 32
|
| 40 |
+
- eval_batch_size: 32
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 128
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- num_epochs: 10.0
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Per | Gen Len |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
| 53 |
+
| 2.2173 | 1.0 | 235 | 0.3860 | 0.5095 | 15.7391 |
|
| 54 |
+
| 0.3895 | 2.0 | 470 | 0.2617 | 0.4065 | 16.1533 |
|
| 55 |
+
| 0.2907 | 3.0 | 705 | 0.2238 | 0.3594 | 16.2184 |
|
| 56 |
+
| 0.2479 | 4.0 | 941 | 0.2088 | 0.3451 | 16.2767 |
|
| 57 |
+
| 0.2274 | 5.0 | 1176 | 0.2000 | 0.3362 | 16.2672 |
|
| 58 |
+
| 0.2114 | 6.0 | 1411 | 0.1949 | 0.3366 | 16.3016 |
|
| 59 |
+
| 0.1997 | 7.0 | 1646 | 0.1935 | 0.3333 | 16.3086 |
|
| 60 |
+
| 0.1909 | 8.0 | 1882 | 0.1899 | 0.327 | 16.307 |
|
| 61 |
+
| 0.1854 | 9.0 | 2117 | 0.1882 | 0.3261 | 16.3109 |
|
| 62 |
+
| 0.1811 | 9.99 | 2350 | 0.1880 | 0.3259 | 16.3063 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.29.2
|
| 68 |
+
- Pytorch 2.0.1+cu117
|
| 69 |
+
- Datasets 2.12.0
|
| 70 |
+
- Tokenizers 0.13.3
|