update model card README.md
Browse files
README.md
CHANGED
@@ -16,16 +16,16 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [sonoisa/t5-base-japanese](https://huggingface.co/sonoisa/t5-base-japanese) on the te_dx_jp dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Wer: 0.
|
21 |
-
- Mer: 0.
|
22 |
-
- Wil: 0.
|
23 |
-
- Wip: 0.
|
24 |
-
- Hits:
|
25 |
-
- Substitutions:
|
26 |
-
- Deletions:
|
27 |
-
- Insertions:
|
28 |
-
- Cer: 0.
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
|
|
47 |
- learning_rate: 0.0001
|
48 |
- train_batch_size: 32
|
49 |
- eval_batch_size: 32
|
50 |
-
- seed:
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
- lr_scheduler_warmup_ratio: 0.1
|
@@ -57,16 +57,16 @@ The following hyperparameters were used during training:
|
|
57 |
|
58 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Mer | Wil | Wip | Hits | Substitutions | Deletions | Insertions | Cer |
|
59 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:------:|:-----:|:-------------:|:---------:|:----------:|:------:|
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
|
71 |
|
72 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [sonoisa/t5-base-japanese](https://huggingface.co/sonoisa/t5-base-japanese) on the te_dx_jp dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.4378
|
20 |
+
- Wer: 0.1696
|
21 |
+
- Mer: 0.1640
|
22 |
+
- Wil: 0.2499
|
23 |
+
- Wip: 0.7501
|
24 |
+
- Hits: 55848
|
25 |
+
- Substitutions: 6316
|
26 |
+
- Deletions: 2423
|
27 |
+
- Insertions: 2216
|
28 |
+
- Cer: 0.1327
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
47 |
- learning_rate: 0.0001
|
48 |
- train_batch_size: 32
|
49 |
- eval_batch_size: 32
|
50 |
+
- seed: 20
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
57 |
|
58 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Mer | Wil | Wip | Hits | Substitutions | Deletions | Insertions | Cer |
|
59 |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:------:|:-----:|:-------------:|:---------:|:----------:|:------:|
|
60 |
+
| 0.5935 | 1.0 | 1457 | 0.4683 | 0.2101 | 0.1975 | 0.2870 | 0.7130 | 55138 | 6765 | 2684 | 4118 | 0.1740 |
|
61 |
+
| 0.5128 | 2.0 | 2914 | 0.4191 | 0.1781 | 0.1719 | 0.2585 | 0.7415 | 55397 | 6370 | 2820 | 2310 | 0.1415 |
|
62 |
+
| 0.4948 | 3.0 | 4371 | 0.4085 | 0.1738 | 0.1679 | 0.2540 | 0.7460 | 55644 | 6330 | 2613 | 2284 | 0.1367 |
|
63 |
+
| 0.4164 | 4.0 | 5828 | 0.4065 | 0.1698 | 0.1643 | 0.2497 | 0.7503 | 55778 | 6263 | 2546 | 2159 | 0.1326 |
|
64 |
+
| 0.3844 | 5.0 | 7285 | 0.4134 | 0.1705 | 0.1646 | 0.2502 | 0.7498 | 55882 | 6295 | 2410 | 2306 | 0.1344 |
|
65 |
+
| 0.3327 | 6.0 | 8742 | 0.4175 | 0.1706 | 0.1649 | 0.2506 | 0.7494 | 55774 | 6290 | 2523 | 2203 | 0.1338 |
|
66 |
+
| 0.2931 | 7.0 | 10199 | 0.4262 | 0.1717 | 0.1655 | 0.2511 | 0.7489 | 55899 | 6307 | 2381 | 2399 | 0.1353 |
|
67 |
+
| 0.2752 | 8.0 | 11656 | 0.4269 | 0.1694 | 0.1639 | 0.2495 | 0.7505 | 55833 | 6291 | 2463 | 2190 | 0.1324 |
|
68 |
+
| 0.274 | 9.0 | 13113 | 0.4359 | 0.1701 | 0.1643 | 0.2502 | 0.7498 | 55866 | 6311 | 2410 | 2266 | 0.1333 |
|
69 |
+
| 0.2426 | 10.0 | 14570 | 0.4378 | 0.1696 | 0.1640 | 0.2499 | 0.7501 | 55848 | 6316 | 2423 | 2216 | 0.1327 |
|
70 |
|
71 |
|
72 |
### Framework versions
|