Hugging Face's logo

Demosthene-OR
/
t5-small-finetuned-en-to-fr

Translation
Transformers
PyTorch
TensorBoard
English
French
t5
text2text-generation
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Demosthene-OR commited on
Commit
77f7f15
•
1 Parent(s): b981351

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +104 -104
README.md CHANGED
@@ -14,11 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # t5-small-finetuned-en-to-fr
16
 
17
- This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.8160
20
- - Bleu: 52.5642
21
- - Gen Len: 6.6667
22
 
23
  ## Model description
24
 
@@ -49,106 +49,106 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
51
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
52
- | No log | 1.0 | 1 | 2.6488 | 21.9728 | 9.0 |
53
- | No log | 2.0 | 2 | 2.5800 | 21.9728 | 9.0 |
54
- | No log | 3.0 | 3 | 2.5120 | 31.7783 | 9.0 |
55
- | No log | 4.0 | 4 | 2.4455 | 31.7783 | 9.0 |
56
- | No log | 5.0 | 5 | 2.3783 | 31.7783 | 9.0 |
57
- | No log | 6.0 | 6 | 2.3129 | 32.857 | 9.0 |
58
- | No log | 7.0 | 7 | 2.2477 | 32.857 | 9.0 |
59
- | No log | 8.0 | 8 | 2.1856 | 32.857 | 9.0 |
60
- | No log | 9.0 | 9 | 2.1239 | 32.857 | 9.0 |
61
- | No log | 10.0 | 10 | 2.0648 | 32.857 | 9.0 |
62
- | No log | 11.0 | 11 | 2.0086 | 42.1181 | 8.6667 |
63
- | No log | 12.0 | 12 | 1.9568 | 42.1181 | 8.6667 |
64
- | No log | 13.0 | 13 | 1.9103 | 42.1181 | 8.6667 |
65
- | No log | 14.0 | 14 | 1.8669 | 42.1181 | 8.6667 |
66
- | No log | 15.0 | 15 | 1.8262 | 50.8368 | 7.0 |
67
- | No log | 16.0 | 16 | 1.7884 | 50.8368 | 7.0 |
68
- | No log | 17.0 | 17 | 1.7525 | 50.8368 | 7.0 |
69
- | No log | 18.0 | 18 | 1.7177 | 50.8368 | 7.0 |
70
- | No log | 19.0 | 19 | 1.6839 | 50.8368 | 7.0 |
71
- | No log | 20.0 | 20 | 1.6512 | 50.8368 | 7.0 |
72
- | No log | 21.0 | 21 | 1.6205 | 50.8368 | 7.0 |
73
- | No log | 22.0 | 22 | 1.5914 | 50.8368 | 7.0 |
74
- | No log | 23.0 | 23 | 1.5629 | 50.8368 | 7.0 |
75
- | No log | 24.0 | 24 | 1.5351 | 50.8368 | 7.0 |
76
- | No log | 25.0 | 25 | 1.5085 | 50.8368 | 7.0 |
77
- | No log | 26.0 | 26 | 1.4834 | 50.8368 | 7.0 |
78
- | No log | 27.0 | 27 | 1.4596 | 50.8368 | 7.0 |
79
- | No log | 28.0 | 28 | 1.4364 | 50.8368 | 7.0 |
80
- | No log | 29.0 | 29 | 1.4138 | 50.8368 | 7.0 |
81
- | No log | 30.0 | 30 | 1.3922 | 50.8368 | 7.0 |
82
- | No log | 31.0 | 31 | 1.3717 | 50.8368 | 7.0 |
83
- | No log | 32.0 | 32 | 1.3520 | 50.8368 | 7.0 |
84
- | No log | 33.0 | 33 | 1.3329 | 50.8368 | 7.0 |
85
- | No log | 34.0 | 34 | 1.3143 | 50.8368 | 7.0 |
86
- | No log | 35.0 | 35 | 1.2964 | 52.5642 | 6.6667 |
87
- | No log | 36.0 | 36 | 1.2786 | 52.5642 | 6.6667 |
88
- | No log | 37.0 | 37 | 1.2611 | 52.5642 | 6.6667 |
89
- | No log | 38.0 | 38 | 1.2446 | 52.5642 | 6.6667 |
90
- | No log | 39.0 | 39 | 1.2285 | 52.5642 | 6.6667 |
91
- | No log | 40.0 | 40 | 1.2128 | 52.5642 | 6.6667 |
92
- | No log | 41.0 | 41 | 1.1977 | 52.5642 | 6.6667 |
93
- | No log | 42.0 | 42 | 1.1828 | 52.5642 | 6.6667 |
94
- | No log | 43.0 | 43 | 1.1679 | 52.5642 | 6.6667 |
95
- | No log | 44.0 | 44 | 1.1532 | 52.5642 | 6.6667 |
96
- | No log | 45.0 | 45 | 1.1392 | 52.5642 | 6.6667 |
97
- | No log | 46.0 | 46 | 1.1253 | 52.5642 | 6.6667 |
98
- | No log | 47.0 | 47 | 1.1119 | 52.5642 | 6.6667 |
99
- | No log | 48.0 | 48 | 1.0989 | 52.5642 | 6.6667 |
100
- | No log | 49.0 | 49 | 1.0867 | 52.5642 | 6.6667 |
101
- | No log | 50.0 | 50 | 1.0748 | 52.5642 | 6.6667 |
102
- | No log | 51.0 | 51 | 1.0636 | 52.5642 | 6.6667 |
103
- | No log | 52.0 | 52 | 1.0527 | 52.5642 | 6.6667 |
104
- | No log | 53.0 | 53 | 1.0421 | 52.5642 | 6.6667 |
105
- | No log | 54.0 | 54 | 1.0315 | 52.5642 | 6.6667 |
106
- | No log | 55.0 | 55 | 1.0213 | 52.5642 | 6.6667 |
107
- | No log | 56.0 | 56 | 1.0116 | 52.5642 | 6.6667 |
108
- | No log | 57.0 | 57 | 1.0018 | 52.5642 | 6.6667 |
109
- | No log | 58.0 | 58 | 0.9923 | 52.5642 | 6.6667 |
110
- | No log | 59.0 | 59 | 0.9832 | 52.5642 | 6.6667 |
111
- | No log | 60.0 | 60 | 0.9743 | 52.5642 | 6.6667 |
112
- | No log | 61.0 | 61 | 0.9659 | 52.5642 | 6.6667 |
113
- | No log | 62.0 | 62 | 0.9578 | 52.5642 | 6.6667 |
114
- | No log | 63.0 | 63 | 0.9496 | 52.5642 | 6.6667 |
115
- | No log | 64.0 | 64 | 0.9416 | 52.5642 | 6.6667 |
116
- | No log | 65.0 | 65 | 0.9341 | 52.5642 | 6.6667 |
117
- | No log | 66.0 | 66 | 0.9266 | 52.5642 | 6.6667 |
118
- | No log | 67.0 | 67 | 0.9195 | 52.5642 | 6.6667 |
119
- | No log | 68.0 | 68 | 0.9125 | 52.5642 | 6.6667 |
120
- | No log | 69.0 | 69 | 0.9062 | 52.5642 | 6.6667 |
121
- | No log | 70.0 | 70 | 0.9002 | 52.5642 | 6.6667 |
122
- | No log | 71.0 | 71 | 0.8947 | 52.5642 | 6.6667 |
123
- | No log | 72.0 | 72 | 0.8894 | 52.5642 | 6.6667 |
124
- | No log | 73.0 | 73 | 0.8843 | 52.5642 | 6.6667 |
125
- | No log | 74.0 | 74 | 0.8794 | 52.5642 | 6.6667 |
126
- | No log | 75.0 | 75 | 0.8745 | 52.5642 | 6.6667 |
127
- | No log | 76.0 | 76 | 0.8698 | 52.5642 | 6.6667 |
128
- | No log | 77.0 | 77 | 0.8651 | 52.5642 | 6.6667 |
129
- | No log | 78.0 | 78 | 0.8607 | 52.5642 | 6.6667 |
130
- | No log | 79.0 | 79 | 0.8564 | 52.5642 | 6.6667 |
131
- | No log | 80.0 | 80 | 0.8525 | 52.5642 | 6.6667 |
132
- | No log | 81.0 | 81 | 0.8486 | 52.5642 | 6.6667 |
133
- | No log | 82.0 | 82 | 0.8449 | 52.5642 | 6.6667 |
134
- | No log | 83.0 | 83 | 0.8416 | 52.5642 | 6.6667 |
135
- | No log | 84.0 | 84 | 0.8386 | 52.5642 | 6.6667 |
136
- | No log | 85.0 | 85 | 0.8359 | 52.5642 | 6.6667 |
137
- | No log | 86.0 | 86 | 0.8333 | 52.5642 | 6.6667 |
138
- | No log | 87.0 | 87 | 0.8310 | 52.5642 | 6.6667 |
139
- | No log | 88.0 | 88 | 0.8290 | 52.5642 | 6.6667 |
140
- | No log | 89.0 | 89 | 0.8270 | 52.5642 | 6.6667 |
141
- | No log | 90.0 | 90 | 0.8251 | 52.5642 | 6.6667 |
142
- | No log | 91.0 | 91 | 0.8234 | 52.5642 | 6.6667 |
143
- | No log | 92.0 | 92 | 0.8218 | 52.5642 | 6.6667 |
144
- | No log | 93.0 | 93 | 0.8205 | 52.5642 | 6.6667 |
145
- | No log | 94.0 | 94 | 0.8193 | 52.5642 | 6.6667 |
146
- | No log | 95.0 | 95 | 0.8183 | 52.5642 | 6.6667 |
147
- | No log | 96.0 | 96 | 0.8175 | 52.5642 | 6.6667 |
148
- | No log | 97.0 | 97 | 0.8169 | 52.5642 | 6.6667 |
149
- | No log | 98.0 | 98 | 0.8164 | 52.5642 | 6.6667 |
150
- | No log | 99.0 | 99 | 0.8161 | 52.5642 | 6.6667 |
151
- | No log | 100.0 | 100 | 0.8160 | 52.5642 | 6.6667 |
152
 
153
 
154
  ### Framework versions
 
14
 
15
  # t5-small-finetuned-en-to-fr
16
 
17
+ This model is a fine-tuned version of [Demosthene-OR/t5-small-finetuned-en-to-fr](https://huggingface.co/Demosthene-OR/t5-small-finetuned-en-to-fr) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.2463
20
+ - Bleu: 61.4528
21
+ - Gen Len: 8.0
22
 
23
  ## Model description
24
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
51
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
52
+ | No log | 1.0 | 1 | 0.7997 | 52.5642 | 6.6667 |
53
+ | No log | 2.0 | 2 | 0.7828 | 52.5642 | 6.6667 |
54
+ | No log | 3.0 | 3 | 0.7665 | 52.5642 | 6.6667 |
55
+ | No log | 4.0 | 4 | 0.7499 | 52.5642 | 6.6667 |
56
+ | No log | 5.0 | 5 | 0.7360 | 52.5642 | 6.6667 |
57
+ | No log | 6.0 | 6 | 0.7227 | 52.5642 | 6.6667 |
58
+ | No log | 7.0 | 7 | 0.7083 | 52.5642 | 6.6667 |
59
+ | No log | 8.0 | 8 | 0.6948 | 52.5642 | 6.6667 |
60
+ | No log | 9.0 | 9 | 0.6811 | 52.5642 | 6.6667 |
61
+ | No log | 10.0 | 10 | 0.6676 | 52.5642 | 6.6667 |
62
+ | No log | 11.0 | 11 | 0.6547 | 52.5642 | 6.6667 |
63
+ | No log | 12.0 | 12 | 0.6421 | 52.5642 | 6.6667 |
64
+ | No log | 13.0 | 13 | 0.6299 | 52.5642 | 6.6667 |
65
+ | No log | 14.0 | 14 | 0.6185 | 52.5642 | 6.6667 |
66
+ | No log | 15.0 | 15 | 0.6082 | 52.5642 | 6.6667 |
67
+ | No log | 16.0 | 16 | 0.5977 | 52.5642 | 6.6667 |
68
+ | No log | 17.0 | 17 | 0.5877 | 52.5642 | 6.6667 |
69
+ | No log | 18.0 | 18 | 0.5784 | 52.5642 | 6.6667 |
70
+ | No log | 19.0 | 19 | 0.5687 | 52.5642 | 6.6667 |
71
+ | No log | 20.0 | 20 | 0.5588 | 52.5642 | 6.6667 |
72
+ | No log | 21.0 | 21 | 0.5496 | 52.5642 | 6.6667 |
73
+ | No log | 22.0 | 22 | 0.5406 | 52.5642 | 6.6667 |
74
+ | No log | 23.0 | 23 | 0.5311 | 52.5642 | 6.6667 |
75
+ | No log | 24.0 | 24 | 0.5216 | 52.5642 | 6.6667 |
76
+ | No log | 25.0 | 25 | 0.5124 | 52.5642 | 6.6667 |
77
+ | No log | 26.0 | 26 | 0.5036 | 52.5642 | 6.6667 |
78
+ | No log | 27.0 | 27 | 0.4951 | 52.5642 | 6.6667 |
79
+ | No log | 28.0 | 28 | 0.4867 | 61.4528 | 8.0 |
80
+ | No log | 29.0 | 29 | 0.4786 | 61.4528 | 8.0 |
81
+ | No log | 30.0 | 30 | 0.4705 | 61.4528 | 8.0 |
82
+ | No log | 31.0 | 31 | 0.4626 | 61.4528 | 8.0 |
83
+ | No log | 32.0 | 32 | 0.4547 | 61.4528 | 8.0 |
84
+ | No log | 33.0 | 33 | 0.4470 | 61.4528 | 8.0 |
85
+ | No log | 34.0 | 34 | 0.4392 | 61.4528 | 8.0 |
86
+ | No log | 35.0 | 35 | 0.4317 | 61.4528 | 8.0 |
87
+ | No log | 36.0 | 36 | 0.4241 | 61.4528 | 8.0 |
88
+ | No log | 37.0 | 37 | 0.4169 | 61.4528 | 8.0 |
89
+ | No log | 38.0 | 38 | 0.4103 | 61.4528 | 8.0 |
90
+ | No log | 39.0 | 39 | 0.4038 | 61.4528 | 8.0 |
91
+ | No log | 40.0 | 40 | 0.3975 | 61.4528 | 8.0 |
92
+ | No log | 41.0 | 41 | 0.3915 | 61.4528 | 8.0 |
93
+ | No log | 42.0 | 42 | 0.3858 | 61.4528 | 8.0 |
94
+ | No log | 43.0 | 43 | 0.3803 | 61.4528 | 8.0 |
95
+ | No log | 44.0 | 44 | 0.3748 | 61.4528 | 8.0 |
96
+ | No log | 45.0 | 45 | 0.3696 | 61.4528 | 8.0 |
97
+ | No log | 46.0 | 46 | 0.3645 | 61.4528 | 8.0 |
98
+ | No log | 47.0 | 47 | 0.3596 | 61.4528 | 8.0 |
99
+ | No log | 48.0 | 48 | 0.3548 | 61.4528 | 8.0 |
100
+ | No log | 49.0 | 49 | 0.3504 | 61.4528 | 8.0 |
101
+ | No log | 50.0 | 50 | 0.3460 | 61.4528 | 8.0 |
102
+ | No log | 51.0 | 51 | 0.3419 | 61.4528 | 8.0 |
103
+ | No log | 52.0 | 52 | 0.3379 | 61.4528 | 8.0 |
104
+ | No log | 53.0 | 53 | 0.3341 | 61.4528 | 8.0 |
105
+ | No log | 54.0 | 54 | 0.3304 | 61.4528 | 8.0 |
106
+ | No log | 55.0 | 55 | 0.3267 | 61.4528 | 8.0 |
107
+ | No log | 56.0 | 56 | 0.3232 | 61.4528 | 8.0 |
108
+ | No log | 57.0 | 57 | 0.3197 | 61.4528 | 8.0 |
109
+ | No log | 58.0 | 58 | 0.3163 | 61.4528 | 8.0 |
110
+ | No log | 59.0 | 59 | 0.3130 | 61.4528 | 8.0 |
111
+ | No log | 60.0 | 60 | 0.3096 | 61.4528 | 8.0 |
112
+ | No log | 61.0 | 61 | 0.3064 | 61.4528 | 8.0 |
113
+ | No log | 62.0 | 62 | 0.3032 | 61.4528 | 8.0 |
114
+ | No log | 63.0 | 63 | 0.3001 | 61.4528 | 8.0 |
115
+ | No log | 64.0 | 64 | 0.2970 | 61.4528 | 8.0 |
116
+ | No log | 65.0 | 65 | 0.2940 | 61.4528 | 8.0 |
117
+ | No log | 66.0 | 66 | 0.2912 | 61.4528 | 8.0 |
118
+ | No log | 67.0 | 67 | 0.2885 | 61.4528 | 8.0 |
119
+ | No log | 68.0 | 68 | 0.2859 | 61.4528 | 8.0 |
120
+ | No log | 69.0 | 69 | 0.2834 | 61.4528 | 8.0 |
121
+ | No log | 70.0 | 70 | 0.2810 | 61.4528 | 8.0 |
122
+ | No log | 71.0 | 71 | 0.2788 | 61.4528 | 8.0 |
123
+ | No log | 72.0 | 72 | 0.2766 | 61.4528 | 8.0 |
124
+ | No log | 73.0 | 73 | 0.2745 | 61.4528 | 8.0 |
125
+ | No log | 74.0 | 74 | 0.2725 | 61.4528 | 8.0 |
126
+ | No log | 75.0 | 75 | 0.2707 | 61.4528 | 8.0 |
127
+ | No log | 76.0 | 76 | 0.2689 | 61.4528 | 8.0 |
128
+ | No log | 77.0 | 77 | 0.2671 | 61.4528 | 8.0 |
129
+ | No log | 78.0 | 78 | 0.2655 | 61.4528 | 8.0 |
130
+ | No log | 79.0 | 79 | 0.2639 | 61.4528 | 8.0 |
131
+ | No log | 80.0 | 80 | 0.2624 | 61.4528 | 8.0 |
132
+ | No log | 81.0 | 81 | 0.2609 | 61.4528 | 8.0 |
133
+ | No log | 82.0 | 82 | 0.2594 | 61.4528 | 8.0 |
134
+ | No log | 83.0 | 83 | 0.2580 | 61.4528 | 8.0 |
135
+ | No log | 84.0 | 84 | 0.2567 | 61.4528 | 8.0 |
136
+ | No log | 85.0 | 85 | 0.2554 | 61.4528 | 8.0 |
137
+ | No log | 86.0 | 86 | 0.2543 | 61.4528 | 8.0 |
138
+ | No log | 87.0 | 87 | 0.2532 | 61.4528 | 8.0 |
139
+ | No log | 88.0 | 88 | 0.2522 | 61.4528 | 8.0 |
140
+ | No log | 89.0 | 89 | 0.2512 | 61.4528 | 8.0 |
141
+ | No log | 90.0 | 90 | 0.2504 | 61.4528 | 8.0 |
142
+ | No log | 91.0 | 91 | 0.2496 | 61.4528 | 8.0 |
143
+ | No log | 92.0 | 92 | 0.2489 | 61.4528 | 8.0 |
144
+ | No log | 93.0 | 93 | 0.2483 | 61.4528 | 8.0 |
145
+ | No log | 94.0 | 94 | 0.2478 | 61.4528 | 8.0 |
146
+ | No log | 95.0 | 95 | 0.2474 | 61.4528 | 8.0 |
147
+ | No log | 96.0 | 96 | 0.2470 | 61.4528 | 8.0 |
148
+ | No log | 97.0 | 97 | 0.2468 | 61.4528 | 8.0 |
149
+ | No log | 98.0 | 98 | 0.2465 | 61.4528 | 8.0 |
150
+ | No log | 99.0 | 99 | 0.2464 | 61.4528 | 8.0 |
151
+ | No log | 100.0 | 100 | 0.2463 | 61.4528 | 8.0 |
152
 
153
 
154
  ### Framework versions