Hugging Face's logo

diallomama
/
ff-en

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
diallomama commited on
Commit
f5f07f1
·
verified ·
1 Parent(s): 859400d

Model save

Browse files
Files changed (1) hide show
  1. README.md +52 -52
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.0208
20
 
21
  ## Model description
22
 
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0003
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
@@ -47,56 +47,56 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 3.2934 | 1.0 | 20 | 1.0480 |
51
- | 1.1576 | 2.0 | 40 | 0.9532 |
52
- | 1.0316 | 3.0 | 60 | 0.8803 |
53
- | 0.9428 | 4.0 | 80 | 0.8531 |
54
- | 0.8739 | 5.0 | 100 | 0.8284 |
55
- | 0.8312 | 6.0 | 120 | 0.8240 |
56
- | 0.7682 | 7.0 | 140 | 0.8247 |
57
- | 0.7325 | 8.0 | 160 | 0.8245 |
58
- | 0.7102 | 9.0 | 180 | 0.8220 |
59
- | 0.6386 | 10.0 | 200 | 0.8228 |
60
- | 0.6317 | 11.0 | 220 | 0.8307 |
61
- | 0.5935 | 12.0 | 240 | 0.8297 |
62
- | 0.5636 | 13.0 | 260 | 0.8402 |
63
- | 0.5445 | 14.0 | 280 | 0.8468 |
64
- | 0.5208 | 15.0 | 300 | 0.8589 |
65
- | 0.4867 | 16.0 | 320 | 0.8629 |
66
- | 0.4706 | 17.0 | 340 | 0.8675 |
67
- | 0.4429 | 18.0 | 360 | 0.8722 |
68
- | 0.4201 | 19.0 | 380 | 0.8882 |
69
- | 0.4081 | 20.0 | 400 | 0.8949 |
70
- | 0.3923 | 21.0 | 420 | 0.9109 |
71
- | 0.3771 | 22.0 | 440 | 0.9141 |
72
- | 0.3734 | 23.0 | 460 | 0.9245 |
73
- | 0.3436 | 24.0 | 480 | 0.9314 |
74
- | 0.341 | 25.0 | 500 | 0.9347 |
75
- | 0.3193 | 26.0 | 520 | 0.9462 |
76
- | 0.2991 | 27.0 | 540 | 0.9538 |
77
- | 0.2994 | 28.0 | 560 | 0.9539 |
78
- | 0.2991 | 29.0 | 580 | 0.9703 |
79
- | 0.2922 | 30.0 | 600 | 0.9625 |
80
- | 0.2726 | 31.0 | 620 | 0.9682 |
81
- | 0.2641 | 32.0 | 640 | 0.9722 |
82
- | 0.2514 | 33.0 | 660 | 0.9779 |
83
- | 0.245 | 34.0 | 680 | 0.9853 |
84
- | 0.2578 | 35.0 | 700 | 0.9875 |
85
- | 0.2443 | 36.0 | 720 | 0.9915 |
86
- | 0.2389 | 37.0 | 740 | 0.9948 |
87
- | 0.2317 | 38.0 | 760 | 0.9973 |
88
- | 0.2236 | 39.0 | 780 | 0.9984 |
89
- | 0.2128 | 40.0 | 800 | 1.0058 |
90
- | 0.219 | 41.0 | 820 | 1.0122 |
91
- | 0.215 | 42.0 | 840 | 1.0137 |
92
- | 0.2076 | 43.0 | 860 | 1.0173 |
93
- | 0.2098 | 44.0 | 880 | 1.0147 |
94
- | 0.1976 | 45.0 | 900 | 1.0149 |
95
- | 0.1988 | 46.0 | 920 | 1.0170 |
96
- | 0.1941 | 47.0 | 940 | 1.0204 |
97
- | 0.2083 | 48.0 | 960 | 1.0206 |
98
- | 0.2007 | 49.0 | 980 | 1.0208 |
99
- | 0.1931 | 50.0 | 1000 | 1.0208 |
100
 
101
 
102
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.8258
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 8.2472 | 1.0 | 20 | 3.2102 |
51
+ | 2.8238 | 2.0 | 40 | 1.2139 |
52
+ | 1.7661 | 3.0 | 60 | 1.1075 |
53
+ | 1.4094 | 4.0 | 80 | 1.0537 |
54
+ | 1.2869 | 5.0 | 100 | 1.0106 |
55
+ | 1.2366 | 6.0 | 120 | 0.9804 |
56
+ | 1.1731 | 7.0 | 140 | 0.9549 |
57
+ | 1.1356 | 8.0 | 160 | 0.9422 |
58
+ | 1.1196 | 9.0 | 180 | 0.9286 |
59
+ | 1.031 | 10.0 | 200 | 0.9169 |
60
+ | 1.0438 | 11.0 | 220 | 0.9014 |
61
+ | 1.0231 | 12.0 | 240 | 0.9007 |
62
+ | 1.0015 | 13.0 | 260 | 0.8829 |
63
+ | 0.9908 | 14.0 | 280 | 0.8803 |
64
+ | 0.995 | 15.0 | 300 | 0.8689 |
65
+ | 0.951 | 16.0 | 320 | 0.8638 |
66
+ | 0.948 | 17.0 | 340 | 0.8601 |
67
+ | 0.9157 | 18.0 | 360 | 0.8551 |
68
+ | 0.9074 | 19.0 | 380 | 0.8519 |
69
+ | 0.9021 | 20.0 | 400 | 0.8506 |
70
+ | 0.8898 | 21.0 | 420 | 0.8472 |
71
+ | 0.8842 | 22.0 | 440 | 0.8448 |
72
+ | 0.9024 | 23.0 | 460 | 0.8437 |
73
+ | 0.858 | 24.0 | 480 | 0.8403 |
74
+ | 0.8801 | 25.0 | 500 | 0.8381 |
75
+ | 0.8441 | 26.0 | 520 | 0.8375 |
76
+ | 0.8379 | 27.0 | 540 | 0.8358 |
77
+ | 0.8403 | 28.0 | 560 | 0.8344 |
78
+ | 0.8615 | 29.0 | 580 | 0.8333 |
79
+ | 0.8697 | 30.0 | 600 | 0.8327 |
80
+ | 0.8403 | 31.0 | 620 | 0.8314 |
81
+ | 0.8373 | 32.0 | 640 | 0.8299 |
82
+ | 0.8094 | 33.0 | 660 | 0.8292 |
83
+ | 0.8023 | 34.0 | 680 | 0.8291 |
84
+ | 0.8426 | 35.0 | 700 | 0.8289 |
85
+ | 0.8275 | 36.0 | 720 | 0.8281 |
86
+ | 0.8177 | 37.0 | 740 | 0.8278 |
87
+ | 0.8183 | 38.0 | 760 | 0.8266 |
88
+ | 0.8058 | 39.0 | 780 | 0.8262 |
89
+ | 0.7929 | 40.0 | 800 | 0.8263 |
90
+ | 0.8218 | 41.0 | 820 | 0.8261 |
91
+ | 0.8198 | 42.0 | 840 | 0.8261 |
92
+ | 0.7957 | 43.0 | 860 | 0.8259 |
93
+ | 0.7966 | 44.0 | 880 | 0.8260 |
94
+ | 0.7941 | 45.0 | 900 | 0.8260 |
95
+ | 0.7771 | 46.0 | 920 | 0.8261 |
96
+ | 0.7883 | 47.0 | 940 | 0.8260 |
97
+ | 0.8113 | 48.0 | 960 | 0.8259 |
98
+ | 0.8155 | 49.0 | 980 | 0.8258 |
99
+ | 0.7782 | 50.0 | 1000 | 0.8258 |
100
 
101
 
102
  ### Framework versions