Hugging Face's logo

PontifexMaximus
/
mt5-small-parsinlu-opus-translation_fa_en-finetuned-fa-to-en

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
generated_from_trainer
Eval Results
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
PontifexMaximus commited on
Commit
117e790
•
1 Parent(s): 06f933d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +38 -38
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Bleu
21
  type: bleu
22
- value: 9.5106
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,9 +29,9 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  This model is a fine-tuned version of [persiannlp/mt5-small-parsinlu-opus-translation_fa_en](https://huggingface.co/persiannlp/mt5-small-parsinlu-opus-translation_fa_en) on the opus_infopankki dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 2.5449
33
- - Bleu: 9.5106
34
- - Gen Len: 13.6434
35
 
36
  ## Model description
37
 
@@ -51,8 +51,8 @@ More information needed
51
 
52
  The following hyperparameters were used during training:
53
  - learning_rate: 2e-06
54
- - train_batch_size: 32
55
- - eval_batch_size: 32
56
  - seed: 42
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
@@ -61,38 +61,38 @@ The following hyperparameters were used during training:
61
 
62
  ### Training results
63
 
64
- | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
65
- |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
66
- | No log | 1.0 | 151 | 3.1656 | 7.194 | 14.1885 |
67
- | No log | 2.0 | 302 | 3.0419 | 7.7031 | 14.1005 |
68
- | No log | 3.0 | 453 | 2.9549 | 8.1502 | 13.9834 |
69
- | 3.5336 | 4.0 | 604 | 2.8857 | 8.4488 | 13.9251 |
70
- | 3.5336 | 5.0 | 755 | 2.8297 | 8.6606 | 13.786 |
71
- | 3.5336 | 6.0 | 906 | 2.7808 | 8.8217 | 13.7983 |
72
- | 3.2511 | 7.0 | 1057 | 2.7386 | 8.9221 | 13.7518 |
73
- | 3.2511 | 8.0 | 1208 | 2.7006 | 9.1988 | 13.7159 |
74
- | 3.2511 | 9.0 | 1359 | 2.6678 | 9.2751 | 13.676 |
75
- | 3.1055 | 10.0 | 1510 | 2.6387 | 9.4142 | 13.6648 |
76
- | 3.1055 | 11.0 | 1661 | 2.6154 | 9.5726 | 13.6841 |
77
- | 3.1055 | 12.0 | 1812 | 2.5945 | 9.6571 | 13.6546 |
78
- | 3.1055 | 13.0 | 1963 | 2.5813 | 9.8303 | 13.6571 |
79
- | 3.0199 | 14.0 | 2114 | 2.5709 | 9.6726 | 13.5855 |
80
- | 3.0199 | 15.0 | 2265 | 2.5619 | 9.632 | 13.6125 |
81
- | 3.0199 | 16.0 | 2416 | 2.5563 | 9.5773 | 13.6256 |
82
- | 2.9862 | 17.0 | 2567 | 2.5538 | 9.5425 | 13.6366 |
83
- | 2.9862 | 18.0 | 2718 | 2.5515 | 9.5359 | 13.6326 |
84
- | 2.9862 | 19.0 | 2869 | 2.5495 | 9.5544 | 13.642 |
85
- | 2.9859 | 20.0 | 3020 | 2.5478 | 9.5183 | 13.6374 |
86
- | 2.9859 | 21.0 | 3171 | 2.5466 | 9.5387 | 13.632 |
87
- | 2.9859 | 22.0 | 3322 | 2.5458 | 9.5183 | 13.6355 |
88
- | 2.9859 | 23.0 | 3473 | 2.5451 | 9.5019 | 13.6376 |
89
- | 2.9731 | 24.0 | 3624 | 2.5449 | 9.5004 | 13.6405 |
90
- | 2.9731 | 25.0 | 3775 | 2.5449 | 9.5106 | 13.6434 |
91
- | 2.9731 | 26.0 | 3926 | 2.5449 | 9.5106 | 13.6434 |
92
- | 2.9671 | 27.0 | 4077 | 2.5449 | 9.5106 | 13.6434 |
93
- | 2.9671 | 28.0 | 4228 | 2.5449 | 9.5106 | 13.6434 |
94
- | 2.9671 | 29.0 | 4379 | 2.5449 | 9.5106 | 13.6434 |
95
- | 2.97 | 30.0 | 4530 | 2.5449 | 9.5106 | 13.6434 |
96
 
97
 
98
  ### Framework versions
19
  metrics:
20
  - name: Bleu
21
  type: bleu
22
+ value: 15.1329
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
 
30
  This model is a fine-tuned version of [persiannlp/mt5-small-parsinlu-opus-translation_fa_en](https://huggingface.co/persiannlp/mt5-small-parsinlu-opus-translation_fa_en) on the opus_infopankki dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 1.9193
33
+ - Bleu: 15.1329
34
+ - Gen Len: 13.4603
35
 
36
  ## Model description
37
 
51
 
52
  The following hyperparameters were used during training:
53
  - learning_rate: 2e-06
54
+ - train_batch_size: 8
55
+ - eval_batch_size: 8
56
  - seed: 42
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
61
 
62
  ### Training results
63
 
64
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
65
+ |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
66
+ | 3.1182 | 1.0 | 1807 | 2.5985 | 10.6445 | 13.7938 |
67
+ | 2.8377 | 2.0 | 3614 | 2.3799 | 11.852 | 13.6168 |
68
+ | 2.6644 | 3.0 | 5421 | 2.2426 | 12.877 | 13.5768 |
69
+ | 2.5286 | 4.0 | 7228 | 2.1521 | 13.5342 | 13.5567 |
70
+ | 2.4523 | 5.0 | 9035 | 2.0801 | 14.0355 | 13.5387 |
71
+ | 2.4026 | 6.0 | 10842 | 2.0197 | 14.4284 | 13.4956 |
72
+ | 2.317 | 7.0 | 12649 | 1.9691 | 14.7776 | 13.4325 |
73
+ | 2.3174 | 8.0 | 14456 | 1.9373 | 15.189 | 13.4261 |
74
+ | 2.3374 | 9.0 | 16263 | 1.9393 | 15.1149 | 13.4087 |
75
+ | 2.3131 | 10.0 | 18070 | 1.9304 | 15.0654 | 13.4234 |
76
+ | 2.295 | 11.0 | 19877 | 1.9239 | 15.102 | 13.4443 |
77
+ | 2.3017 | 12.0 | 21684 | 1.9203 | 15.1676 | 13.4575 |
78
+ | 2.3153 | 13.0 | 23491 | 1.9193 | 15.1329 | 13.4603 |
79
+ | 2.2939 | 14.0 | 25298 | 1.9193 | 15.1329 | 13.4603 |
80
+ | 2.3241 | 15.0 | 27105 | 1.9193 | 15.1329 | 13.4603 |
81
+ | 2.3376 | 16.0 | 28912 | 1.9193 | 15.1329 | 13.4603 |
82
+ | 2.2859 | 17.0 | 30719 | 1.9193 | 15.1329 | 13.4603 |
83
+ | 2.3016 | 18.0 | 32526 | 1.9193 | 15.1329 | 13.4603 |
84
+ | 2.3101 | 19.0 | 34333 | 1.9193 | 15.1329 | 13.4603 |
85
+ | 2.3088 | 20.0 | 36140 | 1.9193 | 15.1329 | 13.4603 |
86
+ | 2.2833 | 21.0 | 37947 | 1.9193 | 15.1329 | 13.4603 |
87
+ | 2.2986 | 22.0 | 39754 | 1.9193 | 15.1329 | 13.4603 |
88
+ | 2.3254 | 23.0 | 41561 | 1.9193 | 15.1329 | 13.4603 |
89
+ | 2.3165 | 24.0 | 43368 | 1.9193 | 15.1329 | 13.4603 |
90
+ | 2.289 | 25.0 | 45175 | 1.9193 | 15.1329 | 13.4603 |
91
+ | 2.3212 | 26.0 | 46982 | 1.9193 | 15.1329 | 13.4603 |
92
+ | 2.2902 | 27.0 | 48789 | 1.9193 | 15.1329 | 13.4603 |
93
+ | 2.3026 | 28.0 | 50596 | 1.9193 | 15.1329 | 13.4603 |
94
+ | 2.2949 | 29.0 | 52403 | 1.9193 | 15.1329 | 13.4603 |
95
+ | 2.3152 | 30.0 | 54210 | 1.9193 | 15.1329 | 13.4603 |
96
 
97
 
98
  ### Framework versions