Hugging Face's logo

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

Translation
Transformers
PyTorch
English
French
t5
text2text-generation
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
Demosthene-OR commited on
Commit
675547c
•
1 Parent(s): 1da8c93

End of training

Browse files
Files changed (6) hide show
  1. README.md +104 -104
  2. config.json +1 -1
  3. pytorch_model.bin +1 -1
  4. tokenizer.json +1 -8
  5. tokenizer_config.json +4 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: t5-base
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # t5-base-finetuned-en-to-fr
17
 
18
- This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0007
21
  - Bleu: 100.0
22
- - Gen Len: 7.0
23
 
24
  ## Model description
25
 
@@ -50,106 +50,106 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
53
- | No log | 1.0 | 1 | 0.1580 | 88.3831 | 7.4545 |
54
- | No log | 2.0 | 2 | 0.1440 | 88.3831 | 7.2727 |
55
- | No log | 3.0 | 3 | 0.1307 | 89.8848 | 7.4545 |
56
- | No log | 4.0 | 4 | 0.1188 | 89.8848 | 7.4545 |
57
- | No log | 5.0 | 5 | 0.1077 | 89.8848 | 7.4545 |
58
- | No log | 6.0 | 6 | 0.0978 | 94.6403 | 7.2727 |
59
- | No log | 7.0 | 7 | 0.0886 | 99.3527 | 7.1818 |
60
- | No log | 8.0 | 8 | 0.0799 | 99.3527 | 7.1818 |
61
- | No log | 9.0 | 9 | 0.0718 | 100.0 | 7.0 |
62
- | No log | 10.0 | 10 | 0.0641 | 100.0 | 7.0 |
63
- | No log | 11.0 | 11 | 0.0571 | 100.0 | 7.0 |
64
- | No log | 12.0 | 12 | 0.0506 | 100.0 | 7.0 |
65
- | No log | 13.0 | 13 | 0.0447 | 100.0 | 7.0 |
66
- | No log | 14.0 | 14 | 0.0394 | 100.0 | 7.0 |
67
- | No log | 15.0 | 15 | 0.0347 | 100.0 | 7.0 |
68
- | No log | 16.0 | 16 | 0.0304 | 100.0 | 7.0 |
69
- | No log | 17.0 | 17 | 0.0266 | 100.0 | 7.0 |
70
- | No log | 18.0 | 18 | 0.0231 | 100.0 | 7.0 |
71
- | No log | 19.0 | 19 | 0.0202 | 100.0 | 7.0 |
72
- | No log | 20.0 | 20 | 0.0175 | 100.0 | 7.0 |
73
- | No log | 21.0 | 21 | 0.0152 | 100.0 | 7.0 |
74
- | No log | 22.0 | 22 | 0.0133 | 100.0 | 7.0 |
75
- | No log | 23.0 | 23 | 0.0116 | 100.0 | 7.0 |
76
- | No log | 24.0 | 24 | 0.0103 | 100.0 | 7.0 |
77
- | No log | 25.0 | 25 | 0.0091 | 100.0 | 7.0 |
78
- | No log | 26.0 | 26 | 0.0080 | 100.0 | 7.0 |
79
- | No log | 27.0 | 27 | 0.0071 | 100.0 | 7.0 |
80
- | No log | 28.0 | 28 | 0.0064 | 100.0 | 7.0 |
81
- | No log | 29.0 | 29 | 0.0057 | 100.0 | 7.0 |
82
- | No log | 30.0 | 30 | 0.0052 | 100.0 | 7.0 |
83
- | No log | 31.0 | 31 | 0.0047 | 100.0 | 7.0 |
84
- | No log | 32.0 | 32 | 0.0043 | 100.0 | 7.0 |
85
- | No log | 33.0 | 33 | 0.0039 | 100.0 | 7.0 |
86
- | No log | 34.0 | 34 | 0.0035 | 100.0 | 7.0 |
87
- | No log | 35.0 | 35 | 0.0032 | 100.0 | 7.0 |
88
- | No log | 36.0 | 36 | 0.0030 | 100.0 | 7.0 |
89
- | No log | 37.0 | 37 | 0.0028 | 100.0 | 7.0 |
90
- | No log | 38.0 | 38 | 0.0025 | 100.0 | 7.0 |
91
- | No log | 39.0 | 39 | 0.0024 | 100.0 | 7.0 |
92
- | No log | 40.0 | 40 | 0.0022 | 100.0 | 7.0 |
93
- | No log | 41.0 | 41 | 0.0021 | 100.0 | 7.0 |
94
- | No log | 42.0 | 42 | 0.0020 | 100.0 | 7.0 |
95
- | No log | 43.0 | 43 | 0.0019 | 100.0 | 7.0 |
96
- | No log | 44.0 | 44 | 0.0018 | 100.0 | 7.0 |
97
- | No log | 45.0 | 45 | 0.0017 | 100.0 | 7.0 |
98
- | No log | 46.0 | 46 | 0.0016 | 100.0 | 7.0 |
99
- | No log | 47.0 | 47 | 0.0015 | 100.0 | 7.0 |
100
- | No log | 48.0 | 48 | 0.0015 | 100.0 | 7.0 |
101
- | No log | 49.0 | 49 | 0.0014 | 100.0 | 7.0 |
102
- | No log | 50.0 | 50 | 0.0013 | 100.0 | 7.0 |
103
- | No log | 51.0 | 51 | 0.0013 | 100.0 | 7.0 |
104
- | No log | 52.0 | 52 | 0.0013 | 100.0 | 7.0 |
105
- | No log | 53.0 | 53 | 0.0012 | 100.0 | 7.0 |
106
- | No log | 54.0 | 54 | 0.0012 | 100.0 | 7.0 |
107
- | No log | 55.0 | 55 | 0.0011 | 100.0 | 7.0 |
108
- | No log | 56.0 | 56 | 0.0011 | 100.0 | 7.0 |
109
- | No log | 57.0 | 57 | 0.0011 | 100.0 | 7.0 |
110
- | No log | 58.0 | 58 | 0.0011 | 100.0 | 7.0 |
111
- | No log | 59.0 | 59 | 0.0011 | 100.0 | 7.0 |
112
- | No log | 60.0 | 60 | 0.0010 | 100.0 | 7.0 |
113
- | No log | 61.0 | 61 | 0.0010 | 100.0 | 7.0 |
114
- | No log | 62.0 | 62 | 0.0010 | 100.0 | 7.0 |
115
- | No log | 63.0 | 63 | 0.0010 | 100.0 | 7.0 |
116
- | No log | 64.0 | 64 | 0.0010 | 100.0 | 7.0 |
117
- | No log | 65.0 | 65 | 0.0009 | 100.0 | 7.0 |
118
- | No log | 66.0 | 66 | 0.0009 | 100.0 | 7.0 |
119
- | No log | 67.0 | 67 | 0.0009 | 100.0 | 7.0 |
120
- | No log | 68.0 | 68 | 0.0009 | 100.0 | 7.0 |
121
- | No log | 69.0 | 69 | 0.0009 | 100.0 | 7.0 |
122
- | No log | 70.0 | 70 | 0.0009 | 100.0 | 7.0 |
123
- | No log | 71.0 | 71 | 0.0009 | 100.0 | 7.0 |
124
- | No log | 72.0 | 72 | 0.0009 | 100.0 | 7.0 |
125
- | No log | 73.0 | 73 | 0.0009 | 100.0 | 7.0 |
126
- | No log | 74.0 | 74 | 0.0008 | 100.0 | 7.0 |
127
- | No log | 75.0 | 75 | 0.0008 | 100.0 | 7.0 |
128
- | No log | 76.0 | 76 | 0.0008 | 100.0 | 7.0 |
129
- | No log | 77.0 | 77 | 0.0008 | 100.0 | 7.0 |
130
- | No log | 78.0 | 78 | 0.0008 | 100.0 | 7.0 |
131
- | No log | 79.0 | 79 | 0.0008 | 100.0 | 7.0 |
132
- | No log | 80.0 | 80 | 0.0008 | 100.0 | 7.0 |
133
- | No log | 81.0 | 81 | 0.0008 | 100.0 | 7.0 |
134
- | No log | 82.0 | 82 | 0.0008 | 100.0 | 7.0 |
135
- | No log | 83.0 | 83 | 0.0008 | 100.0 | 7.0 |
136
- | No log | 84.0 | 84 | 0.0008 | 100.0 | 7.0 |
137
- | No log | 85.0 | 85 | 0.0008 | 100.0 | 7.0 |
138
- | No log | 86.0 | 86 | 0.0008 | 100.0 | 7.0 |
139
- | No log | 87.0 | 87 | 0.0008 | 100.0 | 7.0 |
140
- | No log | 88.0 | 88 | 0.0008 | 100.0 | 7.0 |
141
- | No log | 89.0 | 89 | 0.0008 | 100.0 | 7.0 |
142
- | No log | 90.0 | 90 | 0.0008 | 100.0 | 7.0 |
143
- | No log | 91.0 | 91 | 0.0008 | 100.0 | 7.0 |
144
- | No log | 92.0 | 92 | 0.0007 | 100.0 | 7.0 |
145
- | No log | 93.0 | 93 | 0.0007 | 100.0 | 7.0 |
146
- | No log | 94.0 | 94 | 0.0007 | 100.0 | 7.0 |
147
- | No log | 95.0 | 95 | 0.0007 | 100.0 | 7.0 |
148
- | No log | 96.0 | 96 | 0.0007 | 100.0 | 7.0 |
149
- | No log | 97.0 | 97 | 0.0007 | 100.0 | 7.0 |
150
- | No log | 98.0 | 98 | 0.0007 | 100.0 | 7.0 |
151
- | No log | 99.0 | 99 | 0.0007 | 100.0 | 7.0 |
152
- | No log | 100.0 | 100 | 0.0007 | 100.0 | 7.0 |
153
 
154
 
155
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: Demosthene-OR/t5-base-finetuned-en-to-fr
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # t5-base-finetuned-en-to-fr
17
 
18
+ This model is a fine-tuned version of [Demosthene-OR/t5-base-finetuned-en-to-fr](https://huggingface.co/Demosthene-OR/t5-base-finetuned-en-to-fr) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0003
21
  - Bleu: 100.0
22
+ - Gen Len: 7.3333
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
52
  |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
53
+ | No log | 1.0 | 1 | 0.0962 | 77.3107 | 7.5 |
54
+ | No log | 2.0 | 2 | 0.0649 | 77.3107 | 7.5 |
55
+ | No log | 3.0 | 3 | 0.0405 | 77.3107 | 7.5 |
56
+ | No log | 4.0 | 4 | 0.0250 | 82.4954 | 7.5 |
57
+ | No log | 5.0 | 5 | 0.0159 | 100.0 | 7.3333 |
58
+ | No log | 6.0 | 6 | 0.0118 | 100.0 | 7.3333 |
59
+ | No log | 7.0 | 7 | 0.0094 | 100.0 | 7.3333 |
60
+ | No log | 8.0 | 8 | 0.0078 | 100.0 | 7.3333 |
61
+ | No log | 9.0 | 9 | 0.0066 | 100.0 | 7.3333 |
62
+ | No log | 10.0 | 10 | 0.0057 | 100.0 | 7.3333 |
63
+ | No log | 11.0 | 11 | 0.0050 | 100.0 | 7.3333 |
64
+ | No log | 12.0 | 12 | 0.0044 | 100.0 | 7.3333 |
65
+ | No log | 13.0 | 13 | 0.0040 | 100.0 | 7.3333 |
66
+ | No log | 14.0 | 14 | 0.0036 | 100.0 | 7.3333 |
67
+ | No log | 15.0 | 15 | 0.0033 | 100.0 | 7.3333 |
68
+ | No log | 16.0 | 16 | 0.0030 | 100.0 | 7.3333 |
69
+ | No log | 17.0 | 17 | 0.0027 | 100.0 | 7.3333 |
70
+ | No log | 18.0 | 18 | 0.0025 | 100.0 | 7.3333 |
71
+ | No log | 19.0 | 19 | 0.0022 | 100.0 | 7.3333 |
72
+ | No log | 20.0 | 20 | 0.0021 | 100.0 | 7.3333 |
73
+ | No log | 21.0 | 21 | 0.0019 | 100.0 | 7.3333 |
74
+ | No log | 22.0 | 22 | 0.0017 | 100.0 | 7.3333 |
75
+ | No log | 23.0 | 23 | 0.0016 | 100.0 | 7.3333 |
76
+ | No log | 24.0 | 24 | 0.0015 | 100.0 | 7.3333 |
77
+ | No log | 25.0 | 25 | 0.0014 | 100.0 | 7.3333 |
78
+ | No log | 26.0 | 26 | 0.0013 | 100.0 | 7.3333 |
79
+ | No log | 27.0 | 27 | 0.0012 | 100.0 | 7.3333 |
80
+ | No log | 28.0 | 28 | 0.0011 | 100.0 | 7.3333 |
81
+ | No log | 29.0 | 29 | 0.0010 | 100.0 | 7.3333 |
82
+ | No log | 30.0 | 30 | 0.0010 | 100.0 | 7.3333 |
83
+ | No log | 31.0 | 31 | 0.0009 | 100.0 | 7.3333 |
84
+ | No log | 32.0 | 32 | 0.0009 | 100.0 | 7.3333 |
85
+ | No log | 33.0 | 33 | 0.0008 | 100.0 | 7.3333 |
86
+ | No log | 34.0 | 34 | 0.0008 | 100.0 | 7.3333 |
87
+ | No log | 35.0 | 35 | 0.0008 | 100.0 | 7.3333 |
88
+ | No log | 36.0 | 36 | 0.0007 | 100.0 | 7.3333 |
89
+ | No log | 37.0 | 37 | 0.0007 | 100.0 | 7.3333 |
90
+ | No log | 38.0 | 38 | 0.0007 | 100.0 | 7.3333 |
91
+ | No log | 39.0 | 39 | 0.0007 | 100.0 | 7.3333 |
92
+ | No log | 40.0 | 40 | 0.0006 | 100.0 | 7.3333 |
93
+ | No log | 41.0 | 41 | 0.0006 | 100.0 | 7.3333 |
94
+ | No log | 42.0 | 42 | 0.0006 | 100.0 | 7.3333 |
95
+ | No log | 43.0 | 43 | 0.0006 | 100.0 | 7.3333 |
96
+ | No log | 44.0 | 44 | 0.0006 | 100.0 | 7.3333 |
97
+ | No log | 45.0 | 45 | 0.0006 | 100.0 | 7.3333 |
98
+ | No log | 46.0 | 46 | 0.0005 | 100.0 | 7.3333 |
99
+ | No log | 47.0 | 47 | 0.0005 | 100.0 | 7.3333 |
100
+ | No log | 48.0 | 48 | 0.0005 | 100.0 | 7.3333 |
101
+ | No log | 49.0 | 49 | 0.0005 | 100.0 | 7.3333 |
102
+ | No log | 50.0 | 50 | 0.0005 | 100.0 | 7.3333 |
103
+ | No log | 51.0 | 51 | 0.0005 | 100.0 | 7.3333 |
104
+ | No log | 52.0 | 52 | 0.0005 | 100.0 | 7.3333 |
105
+ | No log | 53.0 | 53 | 0.0005 | 100.0 | 7.3333 |
106
+ | No log | 54.0 | 54 | 0.0005 | 100.0 | 7.3333 |
107
+ | No log | 55.0 | 55 | 0.0004 | 100.0 | 7.3333 |
108
+ | No log | 56.0 | 56 | 0.0004 | 100.0 | 7.3333 |
109
+ | No log | 57.0 | 57 | 0.0004 | 100.0 | 7.3333 |
110
+ | No log | 58.0 | 58 | 0.0004 | 100.0 | 7.3333 |
111
+ | No log | 59.0 | 59 | 0.0004 | 100.0 | 7.3333 |
112
+ | No log | 60.0 | 60 | 0.0004 | 100.0 | 7.3333 |
113
+ | No log | 61.0 | 61 | 0.0004 | 100.0 | 7.3333 |
114
+ | No log | 62.0 | 62 | 0.0004 | 100.0 | 7.3333 |
115
+ | No log | 63.0 | 63 | 0.0004 | 100.0 | 7.3333 |
116
+ | No log | 64.0 | 64 | 0.0004 | 100.0 | 7.3333 |
117
+ | No log | 65.0 | 65 | 0.0004 | 100.0 | 7.3333 |
118
+ | No log | 66.0 | 66 | 0.0004 | 100.0 | 7.3333 |
119
+ | No log | 67.0 | 67 | 0.0004 | 100.0 | 7.3333 |
120
+ | No log | 68.0 | 68 | 0.0004 | 100.0 | 7.3333 |
121
+ | No log | 69.0 | 69 | 0.0004 | 100.0 | 7.3333 |
122
+ | No log | 70.0 | 70 | 0.0004 | 100.0 | 7.3333 |
123
+ | No log | 71.0 | 71 | 0.0004 | 100.0 | 7.3333 |
124
+ | No log | 72.0 | 72 | 0.0004 | 100.0 | 7.3333 |
125
+ | No log | 73.0 | 73 | 0.0003 | 100.0 | 7.3333 |
126
+ | No log | 74.0 | 74 | 0.0003 | 100.0 | 7.3333 |
127
+ | No log | 75.0 | 75 | 0.0003 | 100.0 | 7.3333 |
128
+ | No log | 76.0 | 76 | 0.0003 | 100.0 | 7.3333 |
129
+ | No log | 77.0 | 77 | 0.0003 | 100.0 | 7.3333 |
130
+ | No log | 78.0 | 78 | 0.0003 | 100.0 | 7.3333 |
131
+ | No log | 79.0 | 79 | 0.0003 | 100.0 | 7.3333 |
132
+ | No log | 80.0 | 80 | 0.0003 | 100.0 | 7.3333 |
133
+ | No log | 81.0 | 81 | 0.0003 | 100.0 | 7.3333 |
134
+ | No log | 82.0 | 82 | 0.0003 | 100.0 | 7.3333 |
135
+ | No log | 83.0 | 83 | 0.0003 | 100.0 | 7.3333 |
136
+ | No log | 84.0 | 84 | 0.0003 | 100.0 | 7.3333 |
137
+ | No log | 85.0 | 85 | 0.0003 | 100.0 | 7.3333 |
138
+ | No log | 86.0 | 86 | 0.0003 | 100.0 | 7.3333 |
139
+ | No log | 87.0 | 87 | 0.0003 | 100.0 | 7.3333 |
140
+ | No log | 88.0 | 88 | 0.0003 | 100.0 | 7.3333 |
141
+ | No log | 89.0 | 89 | 0.0003 | 100.0 | 7.3333 |
142
+ | No log | 90.0 | 90 | 0.0003 | 100.0 | 7.3333 |
143
+ | No log | 91.0 | 91 | 0.0003 | 100.0 | 7.3333 |
144
+ | No log | 92.0 | 92 | 0.0003 | 100.0 | 7.3333 |
145
+ | No log | 93.0 | 93 | 0.0003 | 100.0 | 7.3333 |
146
+ | No log | 94.0 | 94 | 0.0003 | 100.0 | 7.3333 |
147
+ | No log | 95.0 | 95 | 0.0003 | 100.0 | 7.3333 |
148
+ | No log | 96.0 | 96 | 0.0003 | 100.0 | 7.3333 |
149
+ | No log | 97.0 | 97 | 0.0003 | 100.0 | 7.3333 |
150
+ | No log | 98.0 | 98 | 0.0003 | 100.0 | 7.3333 |
151
+ | No log | 99.0 | 99 | 0.0003 | 100.0 | 7.3333 |
152
+ | No log | 100.0 | 100 | 0.0003 | 100.0 | 7.3333 |
153
 
154
 
155
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
 
1
  {
2
+ "_name_or_path": "Demosthene-OR/t5-base-finetuned-en-to-fr",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a060268b5922d433c165aaa02d36c09906cbd370919b06bf8900f779a6bf321
3
  size 891699345
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9c27924c07942d943e7ee21ec1c716ddde65e9280a68da1069fe75ea01523d
3
  size 891699345
tokenizer.json CHANGED
@@ -1,14 +1,7 @@
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
- "padding": {
5
- "strategy": "BatchLongest",
6
- "direction": "Right",
7
- "pad_to_multiple_of": null,
8
- "pad_id": 0,
9
- "pad_type_id": 0,
10
- "pad_token": "<pad>"
11
- },
12
  "added_tokens": [
13
  {
14
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
tokenizer_config.json CHANGED
@@ -104,8 +104,12 @@
104
  "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
  "extra_ids": 100,
 
107
  "model_max_length": 512,
 
108
  "pad_token": "<pad>",
 
 
109
  "tokenizer_class": "T5Tokenizer",
110
  "unk_token": "<unk>"
111
  }
 
104
  "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
  "extra_ids": 100,
107
+ "max_length": null,
108
  "model_max_length": 512,
109
+ "pad_to_multiple_of": null,
110
  "pad_token": "<pad>",
111
+ "pad_token_type_id": 0,
112
+ "padding_side": "right",
113
  "tokenizer_class": "T5Tokenizer",
114
  "unk_token": "<unk>"
115
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5db58779f4d6db536f4cfba593a9c9a99b353ef44b214265547b78082d50ab0b
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2d7f7af8adce5a292eec9a5bc9fc2ca8e754685b28511b636307f92ad003e71
3
  size 4155