Hugging Face's logo

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

Translation
Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Kumshe commited on
Commit
a1912ba
•
1 Parent(s): 7f123b2

Training complete

Browse files
Files changed (2) hide show
  1. README.md +38 -11
  2. runs/Aug30_03-54-49_30190107fae3/events.out.tfevents.1724990090.30190107fae3.3467.1 +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: 1.1744
23
- - Bleu: 64.9563
24
- - Gen Len: 6.9771
25
 
26
  ## Model description
27
 
@@ -45,18 +45,45 @@ The following hyperparameters were used during training:
45
  - eval_batch_size: 32
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
- | 3.0004 | 1.0 | 749 | 1.7696 | 49.0794 | 7.1609 |
58
- | 1.6495 | 2.0 | 1498 | 1.2629 | 62.1864 | 6.9756 |
59
- | 1.2293 | 3.0 | 2247 | 1.1744 | 64.9563 | 6.9771 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 1.5734
23
+ - Bleu: 71.4633
24
+ - Gen Len: 6.984
25
 
26
  ## Model description
27
 
 
45
  - eval_batch_size: 32
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: 3000
50
+ - num_epochs: 30
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
56
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
57
+ | 3.4817 | 1.0 | 749 | 2.2949 | 34.5266 | 7.5496 |
58
+ | 2.0957 | 2.0 | 1498 | 1.6167 | 53.0797 | 6.8785 |
59
+ | 1.562 | 3.0 | 2247 | 1.3650 | 60.3083 | 7.0095 |
60
+ | 1.2877 | 4.0 | 2996 | 1.2149 | 63.8437 | 6.9444 |
61
+ | 1.1026 | 5.0 | 3745 | 1.1452 | 66.7883 | 7.13 |
62
+ | 0.9531 | 6.0 | 4494 | 1.1028 | 67.3774 | 6.911 |
63
+ | 0.8402 | 7.0 | 5243 | 1.0995 | 68.0354 | 6.8114 |
64
+ | 0.7513 | 8.0 | 5992 | 1.0878 | 69.4876 | 7.0216 |
65
+ | 0.6746 | 9.0 | 6741 | 1.1109 | 69.7327 | 7.1134 |
66
+ | 0.6073 | 10.0 | 7490 | 1.1167 | 70.1607 | 7.0526 |
67
+ | 0.5531 | 11.0 | 8239 | 1.1468 | 69.8006 | 6.8101 |
68
+ | 0.4981 | 12.0 | 8988 | 1.1856 | 70.5423 | 6.8789 |
69
+ | 0.4544 | 13.0 | 9737 | 1.2019 | 70.5876 | 6.9313 |
70
+ | 0.4095 | 14.0 | 10486 | 1.2347 | 70.7996 | 6.8371 |
71
+ | 0.373 | 15.0 | 11235 | 1.2734 | 71.0903 | 7.0274 |
72
+ | 0.3408 | 16.0 | 11984 | 1.2974 | 71.104 | 7.0025 |
73
+ | 0.3096 | 17.0 | 12733 | 1.3313 | 70.7308 | 6.925 |
74
+ | 0.2856 | 18.0 | 13482 | 1.3820 | 70.9862 | 6.9656 |
75
+ | 0.2601 | 19.0 | 14231 | 1.4016 | 71.1836 | 7.0082 |
76
+ | 0.2404 | 20.0 | 14980 | 1.4483 | 71.0219 | 6.9268 |
77
+ | 0.2241 | 21.0 | 15729 | 1.4714 | 71.2721 | 6.9552 |
78
+ | 0.2065 | 22.0 | 16478 | 1.4814 | 71.3874 | 6.9968 |
79
+ | 0.1942 | 23.0 | 17227 | 1.5090 | 71.4722 | 6.9404 |
80
+ | 0.1831 | 24.0 | 17976 | 1.5265 | 71.4556 | 6.9771 |
81
+ | 0.173 | 25.0 | 18725 | 1.5379 | 71.4026 | 6.9998 |
82
+ | 0.1662 | 26.0 | 19474 | 1.5530 | 71.4843 | 6.9932 |
83
+ | 0.159 | 27.0 | 20223 | 1.5668 | 71.3663 | 6.9784 |
84
+ | 0.1568 | 28.0 | 20972 | 1.5742 | 71.3261 | 6.9734 |
85
+ | 0.1566 | 29.0 | 21721 | 1.5739 | 71.4435 | 6.9843 |
86
+ | 0.156 | 30.0 | 22470 | 1.5734 | 71.4633 | 6.984 |
87
 
88
 
89
  ### Framework versions
runs/Aug30_03-54-49_30190107fae3/events.out.tfevents.1724990090.30190107fae3.3467.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cef96208f469e030045d23a0a00cd02e9d3df7ac234515356666b1d631c462f
3
- size 23111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08e3449c914bbca6181c72363ad7dddf990e7e87c0c3154e04922d9a5831f3e4
3
+ size 23848