Model save
Browse files- README.md +66 -11
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,16 +1,71 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
- text: 'translate: Japanese to Ainu (沙流, first): 私はアイヌ語を一年間勉強しています。'
|
| 10 |
-
- text: 'translate: Japanese to Ainu (沙流, first): 夏は暑いので、私は嫌いです。'
|
| 11 |
-
- text: 'translate: Japanese to Ainu (沙流, first): 自分には、人間の生活というものが、見当つかないのです。'
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
|
|
|
| 14 |
# mt5-small-ainu
|
| 15 |
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- bleu
|
| 6 |
+
model-index:
|
| 7 |
+
- name: mt5-small-ainu
|
| 8 |
+
results: []
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
# mt5-small-ainu
|
| 15 |
|
| 16 |
+
This model was trained from scratch on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 1.8639
|
| 19 |
+
- Bleu: 19.8267
|
| 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: 0.0006
|
| 39 |
+
- train_batch_size: 32
|
| 40 |
+
- eval_batch_size: 32
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 20
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
|
| 50 |
+
| 2.4842 | 1.0 | 4670 | 2.1813 | 8.3904 |
|
| 51 |
+
| 2.0771 | 2.0 | 9340 | 1.9269 | 5.7433 |
|
| 52 |
+
| 1.8222 | 3.0 | 14010 | 1.8170 | 12.8222 |
|
| 53 |
+
| 1.6758 | 4.0 | 18680 | 1.7569 | 14.3024 |
|
| 54 |
+
| 1.5447 | 5.0 | 23350 | 1.7277 | 12.3842 |
|
| 55 |
+
| 1.4545 | 6.0 | 28020 | 1.7188 | 14.1082 |
|
| 56 |
+
| 1.3417 | 7.0 | 32690 | 1.7104 | 16.6177 |
|
| 57 |
+
| 1.2347 | 8.0 | 37360 | 1.7262 | 17.4827 |
|
| 58 |
+
| 1.1565 | 9.0 | 42030 | 1.7268 | 17.7124 |
|
| 59 |
+
| 1.081 | 10.0 | 46700 | 1.7581 | 18.6729 |
|
| 60 |
+
| 1.02 | 11.0 | 51370 | 1.7768 | 20.2419 |
|
| 61 |
+
| 0.9513 | 12.0 | 56040 | 1.8162 | 20.0469 |
|
| 62 |
+
| 0.8934 | 13.0 | 60710 | 1.8370 | 19.7150 |
|
| 63 |
+
| 0.8343 | 14.0 | 65380 | 1.8639 | 19.8267 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.40.1
|
| 69 |
+
- Pytorch 2.1.2
|
| 70 |
+
- Datasets 2.19.0
|
| 71 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1200729512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32e3588485a7f62e463b5178ed4cd0391ffcb6d01fbb23a2c0125f48626ab56c
|
| 3 |
size 1200729512
|