Hugging Face's logo

Padomin
/
t5-base-TEDxJP-8front-1body-8rear

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Padomin commited on
Commit
6162b81
•
1 Parent(s): 81f23fa

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: 0.4357
20
- - Wer: 0.1706
21
- - Mer: 0.1649
22
- - Wil: 0.2512
23
- - Wip: 0.7488
24
- - Hits: 55798
25
- - Substitutions: 6352
26
- - Deletions: 2437
27
- - Insertions: 2230
28
- - Cer: 0.1344
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
- | 0.585 | 1.0 | 1457 | 0.4589 | 0.2109 | 0.1988 | 0.2866 | 0.7134 | 54910 | 6576 | 3101 | 3947 | 0.1850 |
61
- | 0.5098 | 2.0 | 2914 | 0.4190 | 0.1814 | 0.1744 | 0.2618 | 0.7382 | 55486 | 6473 | 2628 | 2617 | 0.1435 |
62
- | 0.4648 | 3.0 | 4371 | 0.4108 | 0.1728 | 0.1669 | 0.2526 | 0.7474 | 55696 | 6298 | 2593 | 2267 | 0.1366 |
63
- | 0.4075 | 4.0 | 5828 | 0.4071 | 0.1728 | 0.1670 | 0.2534 | 0.7466 | 55649 | 6356 | 2582 | 2220 | 0.1364 |
64
- | 0.3904 | 5.0 | 7285 | 0.4118 | 0.1709 | 0.1652 | 0.2514 | 0.7486 | 55753 | 6334 | 2500 | 2203 | 0.1343 |
65
- | 0.343 | 6.0 | 8742 | 0.4131 | 0.1701 | 0.1647 | 0.2509 | 0.7491 | 55741 | 6334 | 2512 | 2142 | 0.1338 |
66
- | 0.2981 | 7.0 | 10199 | 0.4211 | 0.1701 | 0.1645 | 0.2503 | 0.7497 | 55788 | 6302 | 2497 | 2187 | 0.1345 |
67
- | 0.2663 | 8.0 | 11656 | 0.4291 | 0.1698 | 0.1642 | 0.2503 | 0.7497 | 55851 | 6338 | 2398 | 2234 | 0.1339 |
68
- | 0.2938 | 9.0 | 13113 | 0.4317 | 0.1699 | 0.1642 | 0.2503 | 0.7497 | 55833 | 6329 | 2425 | 2218 | 0.1340 |
69
- | 0.2692 | 10.0 | 14570 | 0.4357 | 0.1706 | 0.1649 | 0.2512 | 0.7488 | 55798 | 6352 | 2437 | 2230 | 0.1344 |
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: 0.4376
20
+ - Wer: 0.1693
21
+ - Mer: 0.1635
22
+ - Wil: 0.2492
23
+ - Wip: 0.7508
24
+ - Hits: 55925
25
+ - Substitutions: 6304
26
+ - Deletions: 2358
27
+ - Insertions: 2270
28
+ - Cer: 0.1339
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
+ | 0.6093 | 1.0 | 1457 | 0.4649 | 0.2573 | 0.2324 | 0.3203 | 0.6797 | 54884 | 6813 | 2890 | 6916 | 0.2380 |
61
+ | 0.5049 | 2.0 | 2914 | 0.4186 | 0.1791 | 0.1722 | 0.2595 | 0.7405 | 55594 | 6456 | 2537 | 2575 | 0.1432 |
62
+ | 0.4746 | 3.0 | 4371 | 0.4147 | 0.1741 | 0.1681 | 0.2539 | 0.7461 | 55665 | 6315 | 2607 | 2324 | 0.1392 |
63
+ | 0.4295 | 4.0 | 5828 | 0.4118 | 0.1723 | 0.1661 | 0.2523 | 0.7477 | 55884 | 6360 | 2343 | 2425 | 0.1342 |
64
+ | 0.3881 | 5.0 | 7285 | 0.4123 | 0.1696 | 0.1639 | 0.2496 | 0.7504 | 55896 | 6301 | 2390 | 2265 | 0.1397 |
65
+ | 0.3151 | 6.0 | 8742 | 0.4174 | 0.1687 | 0.1631 | 0.2482 | 0.7518 | 55924 | 6249 | 2414 | 2236 | 0.1329 |
66
+ | 0.2977 | 7.0 | 10199 | 0.4248 | 0.1674 | 0.1618 | 0.2466 | 0.7534 | 56006 | 6227 | 2354 | 2229 | 0.1321 |
67
+ | 0.2737 | 8.0 | 11656 | 0.4293 | 0.1685 | 0.1629 | 0.2485 | 0.7515 | 55898 | 6288 | 2401 | 2192 | 0.1340 |
68
+ | 0.2574 | 9.0 | 13113 | 0.4374 | 0.1683 | 0.1627 | 0.2480 | 0.7520 | 55930 | 6268 | 2389 | 2212 | 0.1329 |
69
+ | 0.2472 | 10.0 | 14570 | 0.4376 | 0.1693 | 0.1635 | 0.2492 | 0.7508 | 55925 | 6304 | 2358 | 2270 | 0.1339 |
70
 
71
 
72
  ### Framework versions