Hugging Face's logo

Kumshe
/
t5-small-finetuned-hausa-to-chinese

Translation
Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Kumshe commited on
Commit
eed174c
•
1 Parent(s): e012c3a

Training complete

Browse files
Files changed (2) hide show
  1. README.md +28 -11
  2. runs/Aug30_09-16-10_bd5f5edc4032/events.out.tfevents.1725009372.bd5f5edc4032.290.0 +2 -2
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.2589
23
- - Bleu: 18.0414
24
- - Gen Len: 3.4084
25
 
26
  ## Model description
27
 
@@ -45,18 +45,35 @@ The following hyperparameters were used during training:
45
  - eval_batch_size: 64
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
- - lr_scheduler_type: linear
49
- - lr_scheduler_warmup_steps: 1000
50
- - num_epochs: 3
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
56
- |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
57
- | 0.5399 | 1.0 | 846 | 0.3096 | 7.7834 | 3.2823 |
58
- | 0.2863 | 2.0 | 1692 | 0.2769 | 6.2706 | 3.247 |
59
- | 0.2346 | 3.0 | 2538 | 0.2589 | 18.0414 | 3.4084 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.3817
23
+ - Bleu: 30.2633
24
+ - Gen Len: 3.5559
25
 
26
  ## Model description
27
 
 
45
  - eval_batch_size: 64
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_steps: 4000
50
+ - num_epochs: 20
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
56
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
57
+ | 0.6981 | 1.0 | 846 | 0.2900 | 14.2476 | 3.4917 |
58
+ | 0.3149 | 2.0 | 1692 | 0.2639 | 18.6104 | 3.4725 |
59
+ | 0.2782 | 3.0 | 2538 | 0.2467 | 9.1092 | 3.2542 |
60
+ | 0.2622 | 4.0 | 3384 | 0.2481 | 24.1345 | 3.4047 |
61
+ | 0.2428 | 5.0 | 4230 | 0.2529 | 16.9217 | 3.3965 |
62
+ | 0.2271 | 6.0 | 5076 | 0.2491 | 27.8491 | 3.5349 |
63
+ | 0.2047 | 7.0 | 5922 | 0.2507 | 16.6565 | 3.339 |
64
+ | 0.1902 | 8.0 | 6768 | 0.2506 | 25.6462 | 3.5667 |
65
+ | 0.1739 | 9.0 | 7614 | 0.2610 | 27.1673 | 3.5916 |
66
+ | 0.1587 | 10.0 | 8460 | 0.2438 | 29.306 | 3.5839 |
67
+ | 0.1425 | 11.0 | 9306 | 0.2660 | 29.08 | 3.6478 |
68
+ | 0.1251 | 12.0 | 10152 | 0.2721 | 29.9148 | 3.4994 |
69
+ | 0.1105 | 13.0 | 10998 | 0.2929 | 28.1895 | 3.5526 |
70
+ | 0.0956 | 14.0 | 11844 | 0.3010 | 30.552 | 3.5717 |
71
+ | 0.083 | 15.0 | 12690 | 0.3307 | 27.9728 | 3.5303 |
72
+ | 0.0724 | 16.0 | 13536 | 0.3404 | 27.1874 | 3.5146 |
73
+ | 0.0652 | 17.0 | 14382 | 0.3592 | 29.9567 | 3.5529 |
74
+ | 0.0568 | 18.0 | 15228 | 0.3774 | 30.5145 | 3.5668 |
75
+ | 0.0549 | 19.0 | 16074 | 0.3795 | 30.6604 | 3.5637 |
76
+ | 0.0526 | 20.0 | 16920 | 0.3817 | 30.2633 | 3.5559 |
77
 
78
 
79
  ### Framework versions
runs/Aug30_09-16-10_bd5f5edc4032/events.out.tfevents.1725009372.bd5f5edc4032.290.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64322d6b0b9598d1829f1dc2af514423f4af442734c5165f15d1d2610b080a38
3
- size 17212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5508daab8ea73587693dfeabea04bebab50a4badb7ead46716a527f4307b7fcd
3
+ size 17949