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
1c2b0aa
•
1 Parent(s): 9c8dee1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -21
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: 0.4403
20
- - Wer: 0.1702
21
- - Mer: 0.1645
22
- - Wil: 0.2505
23
- - Wip: 0.7495
24
- - Hits: 55830
25
- - Substitutions: 6323
26
- - Deletions: 2434
27
- - Insertions: 2236
28
- - Cer: 0.1350
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: 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
@@ -57,16 +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
- | 0.5914 | 1.0 | 1457 | 0.4710 | 0.2143 | 0.2009 | 0.2909 | 0.7091 | 55053 | 6819 | 2715 | 4307 | 0.1805 |
61
- | 0.5181 | 2.0 | 2914 | 0.4222 | 0.1774 | 0.1715 | 0.2589 | 0.7411 | 55350 | 6433 | 2804 | 2218 | 0.1393 |
62
- | 0.4888 | 3.0 | 4371 | 0.4133 | 0.1732 | 0.1671 | 0.2539 | 0.7461 | 55729 | 6396 | 2462 | 2326 | 0.1357 |
63
- | 0.4148 | 4.0 | 5828 | 0.4120 | 0.1712 | 0.1654 | 0.2515 | 0.7485 | 55770 | 6328 | 2489 | 2238 | 0.1358 |
64
- | 0.3905 | 5.0 | 7285 | 0.4167 | 0.1731 | 0.1670 | 0.2537 | 0.7463 | 55742 | 6387 | 2458 | 2332 | 0.1400 |
65
- | 0.3473 | 6.0 | 8742 | 0.4203 | 0.1715 | 0.1658 | 0.2528 | 0.7472 | 55736 | 6406 | 2445 | 2227 | 0.1353 |
66
- | 0.2979 | 7.0 | 10199 | 0.4262 | 0.1709 | 0.1651 | 0.2515 | 0.7485 | 55806 | 6360 | 2421 | 2254 | 0.1347 |
67
- | 0.2747 | 8.0 | 11656 | 0.4309 | 0.1704 | 0.1648 | 0.2507 | 0.7493 | 55804 | 6320 | 2463 | 2225 | 0.1356 |
68
- | 0.2728 | 9.0 | 13113 | 0.4374 | 0.1705 | 0.1647 | 0.2509 | 0.7491 | 55841 | 6343 | 2403 | 2264 | 0.1359 |
69
- | 0.2436 | 10.0 | 14570 | 0.4403 | 0.1702 | 0.1645 | 0.2505 | 0.7495 | 55830 | 6323 | 2434 | 2236 | 0.1350 |
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: 0.4394
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
  - 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
 
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