Hugging Face's logo

Padomin
/
t5-base-TEDxJP-6front-1body-6rear

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Padomin commited on
Commit
4b9e154
•
1 Parent(s): f0edc3d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -20
README.md CHANGED
@@ -17,15 +17,15 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.4394
20
- - Wer: 0.1715
21
- - Mer: 0.1655
22
- - Wil: 0.2514
23
- - Wip: 0.7486
24
- - Hits: 55840
25
- - Substitutions: 6324
26
- - Deletions: 2423
27
- - Insertions: 2327
28
- - Cer: 0.1370
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: 30
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
- | 0.5934 | 1.0 | 1457 | 0.4618 | 0.2350 | 0.2167 | 0.3040 | 0.6960 | 54861 | 6643 | 3083 | 5449 | 0.2143 |
61
- | 0.5143 | 2.0 | 2914 | 0.4200 | 0.1809 | 0.1738 | 0.2621 | 0.7379 | 55519 | 6548 | 2520 | 2613 | 0.1457 |
62
- | 0.4671 | 3.0 | 4371 | 0.4138 | 0.1726 | 0.1669 | 0.2535 | 0.7465 | 55651 | 6368 | 2568 | 2212 | 0.1349 |
63
- | 0.4044 | 4.0 | 5828 | 0.4077 | 0.1708 | 0.1653 | 0.2518 | 0.7482 | 55708 | 6359 | 2520 | 2155 | 0.1371 |
64
- | 0.398 | 5.0 | 7285 | 0.4140 | 0.1691 | 0.1638 | 0.2496 | 0.7504 | 55749 | 6294 | 2544 | 2083 | 0.1329 |
65
- | 0.3394 | 6.0 | 8742 | 0.4190 | 0.1701 | 0.1645 | 0.2511 | 0.7489 | 55822 | 6375 | 2390 | 2224 | 0.1348 |
66
- | 0.3009 | 7.0 | 10199 | 0.4264 | 0.1720 | 0.1659 | 0.2519 | 0.7481 | 55861 | 6341 | 2385 | 2381 | 0.1369 |
67
- | 0.273 | 8.0 | 11656 | 0.4307 | 0.1703 | 0.1647 | 0.2509 | 0.7491 | 55772 | 6337 | 2478 | 2184 | 0.1352 |
68
- | 0.2939 | 9.0 | 13113 | 0.4350 | 0.1697 | 0.1640 | 0.2499 | 0.7501 | 55843 | 6313 | 2431 | 2214 | 0.1353 |
69
- | 0.2747 | 10.0 | 14570 | 0.4394 | 0.1715 | 0.1655 | 0.2514 | 0.7486 | 55840 | 6324 | 2423 | 2327 | 0.1370 |
70
 
71
 
72
  ### Framework versions
 
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: 0.4394
20
+ - Wer: 0.1704
21
+ - Mer: 0.1647
22
+ - Wil: 0.2508
23
+ - Wip: 0.7492
24
+ - Hits: 55836
25
+ - Substitutions: 6340
26
+ - Deletions: 2411
27
+ - Insertions: 2256
28
+ - Cer: 0.1351
29
 
30
  ## Model description
31
 
 
47
  - learning_rate: 0.0001
48
  - train_batch_size: 32
49
  - eval_batch_size: 32
50
+ - seed: 40
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
+ | 0.6164 | 1.0 | 1457 | 0.4627 | 0.2224 | 0.2073 | 0.2961 | 0.7039 | 54939 | 6736 | 2912 | 4716 | 0.1954 |
61
+ | 0.5064 | 2.0 | 2914 | 0.4222 | 0.1785 | 0.1722 | 0.2591 | 0.7409 | 55427 | 6402 | 2758 | 2370 | 0.1416 |
62
+ | 0.4909 | 3.0 | 4371 | 0.4147 | 0.1717 | 0.1664 | 0.2514 | 0.7486 | 55563 | 6218 | 2806 | 2068 | 0.1350 |
63
+ | 0.4365 | 4.0 | 5828 | 0.4120 | 0.1722 | 0.1661 | 0.2525 | 0.7475 | 55848 | 6373 | 2366 | 2385 | 0.1380 |
64
+ | 0.3954 | 5.0 | 7285 | 0.4145 | 0.1715 | 0.1655 | 0.2517 | 0.7483 | 55861 | 6355 | 2371 | 2351 | 0.1384 |
65
+ | 0.3181 | 6.0 | 8742 | 0.4178 | 0.1710 | 0.1650 | 0.2509 | 0.7491 | 55891 | 6326 | 2370 | 2348 | 0.1368 |
66
+ | 0.2971 | 7.0 | 10199 | 0.4261 | 0.1698 | 0.1640 | 0.2497 | 0.7503 | 55900 | 6304 | 2383 | 2279 | 0.1348 |
67
+ | 0.2754 | 8.0 | 11656 | 0.4299 | 0.1703 | 0.1645 | 0.2504 | 0.7496 | 55875 | 6320 | 2392 | 2288 | 0.1354 |
68
+ | 0.2604 | 9.0 | 13113 | 0.4371 | 0.1702 | 0.1644 | 0.2506 | 0.7494 | 55864 | 6343 | 2380 | 2267 | 0.1347 |
69
+ | 0.2477 | 10.0 | 14570 | 0.4394 | 0.1704 | 0.1647 | 0.2508 | 0.7492 | 55836 | 6340 | 2411 | 2256 | 0.1351 |
70
 
71
 
72
  ### Framework versions