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
Model card Files
xet
Metrics Community
1
Demosthene-OR commited on
Commit
2756794
·
1 Parent(s): bfe9f4d

End of training

Browse files
Files changed (4) hide show
  1. README.md +112 -9
  2. pytorch_model.bin +1 -1
  3. tokenizer_config.json +4 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,8 @@
1
  ---
2
  tags:
3
  - generated_from_trainer
 
 
4
  model-index:
5
  - name: t5-small-finetuned-en-to-fr
6
  results: []
@@ -13,14 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - eval_loss: 0.0858
17
- - eval_bleu: 100.0
18
- - eval_gen_len: 13.5
19
- - eval_runtime: 0.209
20
- - eval_samples_per_second: 9.568
21
- - eval_steps_per_second: 4.784
22
- - epoch: 103.0
23
- - step: 103
24
 
25
  ## Model description
26
 
@@ -45,7 +42,113 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - num_epochs: 200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
 
50
  ### Framework versions
51
 
 
1
  ---
2
  tags:
3
  - generated_from_trainer
4
+ metrics:
5
+ - bleu
6
  model-index:
7
  - name: t5-small-finetuned-en-to-fr
8
  results: []
 
15
 
16
  This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1355
19
+ - Bleu: 0.0
20
+ - Gen Len: 3.0
 
 
 
 
 
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 100
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
50
+ |:-------------:|:-----:|:----:|:---------------:|:----:|:-------:|
51
+ | No log | 1.0 | 1 | 0.7383 | 0.0 | 3.0 |
52
+ | No log | 2.0 | 2 | 0.6949 | 0.0 | 3.0 |
53
+ | No log | 3.0 | 3 | 0.6472 | 0.0 | 3.0 |
54
+ | No log | 4.0 | 4 | 0.6009 | 0.0 | 3.0 |
55
+ | No log | 5.0 | 5 | 0.5615 | 0.0 | 3.0 |
56
+ | No log | 6.0 | 6 | 0.5312 | 0.0 | 3.0 |
57
+ | No log | 7.0 | 7 | 0.4994 | 0.0 | 3.0 |
58
+ | No log | 8.0 | 8 | 0.4685 | 0.0 | 3.0 |
59
+ | No log | 9.0 | 9 | 0.4413 | 0.0 | 3.0 |
60
+ | No log | 10.0 | 10 | 0.4179 | 0.0 | 3.0 |
61
+ | No log | 11.0 | 11 | 0.3927 | 0.0 | 3.0 |
62
+ | No log | 12.0 | 12 | 0.3675 | 0.0 | 3.0 |
63
+ | No log | 13.0 | 13 | 0.3460 | 0.0 | 3.0 |
64
+ | No log | 14.0 | 14 | 0.3225 | 0.0 | 3.0 |
65
+ | No log | 15.0 | 15 | 0.3018 | 0.0 | 3.0 |
66
+ | No log | 16.0 | 16 | 0.2821 | 0.0 | 3.0 |
67
+ | No log | 17.0 | 17 | 0.2593 | 0.0 | 3.0 |
68
+ | No log | 18.0 | 18 | 0.2388 | 0.0 | 3.0 |
69
+ | No log | 19.0 | 19 | 0.2215 | 0.0 | 3.0 |
70
+ | No log | 20.0 | 20 | 0.2098 | 0.0 | 3.0 |
71
+ | No log | 21.0 | 21 | 0.2031 | 0.0 | 3.0 |
72
+ | No log | 22.0 | 22 | 0.1964 | 0.0 | 3.0 |
73
+ | No log | 23.0 | 23 | 0.1908 | 0.0 | 3.0 |
74
+ | No log | 24.0 | 24 | 0.1842 | 0.0 | 3.0 |
75
+ | No log | 25.0 | 25 | 0.1765 | 0.0 | 3.0 |
76
+ | No log | 26.0 | 26 | 0.1695 | 0.0 | 3.0 |
77
+ | No log | 27.0 | 27 | 0.1643 | 0.0 | 3.0 |
78
+ | No log | 28.0 | 28 | 0.1588 | 0.0 | 3.0 |
79
+ | No log | 29.0 | 29 | 0.1543 | 0.0 | 3.0 |
80
+ | No log | 30.0 | 30 | 0.1503 | 0.0 | 3.0 |
81
+ | No log | 31.0 | 31 | 0.1490 | 0.0 | 3.0 |
82
+ | No log | 32.0 | 32 | 0.1468 | 0.0 | 3.0 |
83
+ | No log | 33.0 | 33 | 0.1430 | 0.0 | 3.0 |
84
+ | No log | 34.0 | 34 | 0.1408 | 0.0 | 3.0 |
85
+ | No log | 35.0 | 35 | 0.1400 | 0.0 | 3.0 |
86
+ | No log | 36.0 | 36 | 0.1386 | 0.0 | 3.0 |
87
+ | No log | 37.0 | 37 | 0.1363 | 0.0 | 3.0 |
88
+ | No log | 38.0 | 38 | 0.1329 | 0.0 | 3.0 |
89
+ | No log | 39.0 | 39 | 0.1298 | 0.0 | 3.0 |
90
+ | No log | 40.0 | 40 | 0.1268 | 0.0 | 3.0 |
91
+ | No log | 41.0 | 41 | 0.1245 | 0.0 | 3.0 |
92
+ | No log | 42.0 | 42 | 0.1231 | 0.0 | 3.0 |
93
+ | No log | 43.0 | 43 | 0.1219 | 0.0 | 3.0 |
94
+ | No log | 44.0 | 44 | 0.1210 | 0.0 | 3.0 |
95
+ | No log | 45.0 | 45 | 0.1204 | 0.0 | 3.0 |
96
+ | No log | 46.0 | 46 | 0.1204 | 0.0 | 3.0 |
97
+ | No log | 47.0 | 47 | 0.1202 | 0.0 | 3.0 |
98
+ | No log | 48.0 | 48 | 0.1200 | 0.0 | 3.0 |
99
+ | No log | 49.0 | 49 | 0.1202 | 0.0 | 3.0 |
100
+ | No log | 50.0 | 50 | 0.1205 | 0.0 | 3.0 |
101
+ | No log | 51.0 | 51 | 0.1206 | 0.0 | 3.0 |
102
+ | No log | 52.0 | 52 | 0.1205 | 0.0 | 3.0 |
103
+ | No log | 53.0 | 53 | 0.1207 | 0.0 | 3.0 |
104
+ | No log | 54.0 | 54 | 0.1208 | 0.0 | 3.0 |
105
+ | No log | 55.0 | 55 | 0.1211 | 0.0 | 3.0 |
106
+ | No log | 56.0 | 56 | 0.1214 | 0.0 | 3.0 |
107
+ | No log | 57.0 | 57 | 0.1215 | 0.0 | 3.0 |
108
+ | No log | 58.0 | 58 | 0.1216 | 0.0 | 3.0 |
109
+ | No log | 59.0 | 59 | 0.1215 | 0.0 | 3.0 |
110
+ | No log | 60.0 | 60 | 0.1213 | 0.0 | 3.0 |
111
+ | No log | 61.0 | 61 | 0.1210 | 0.0 | 3.0 |
112
+ | No log | 62.0 | 62 | 0.1210 | 0.0 | 3.0 |
113
+ | No log | 63.0 | 63 | 0.1212 | 0.0 | 3.0 |
114
+ | No log | 64.0 | 64 | 0.1216 | 0.0 | 3.0 |
115
+ | No log | 65.0 | 65 | 0.1225 | 0.0 | 3.0 |
116
+ | No log | 66.0 | 66 | 0.1233 | 0.0 | 3.0 |
117
+ | No log | 67.0 | 67 | 0.1243 | 0.0 | 3.0 |
118
+ | No log | 68.0 | 68 | 0.1252 | 0.0 | 3.0 |
119
+ | No log | 69.0 | 69 | 0.1260 | 0.0 | 3.0 |
120
+ | No log | 70.0 | 70 | 0.1272 | 0.0 | 3.0 |
121
+ | No log | 71.0 | 71 | 0.1282 | 0.0 | 3.0 |
122
+ | No log | 72.0 | 72 | 0.1287 | 0.0 | 3.0 |
123
+ | No log | 73.0 | 73 | 0.1291 | 0.0 | 3.0 |
124
+ | No log | 74.0 | 74 | 0.1297 | 0.0 | 3.0 |
125
+ | No log | 75.0 | 75 | 0.1304 | 0.0 | 3.0 |
126
+ | No log | 76.0 | 76 | 0.1309 | 0.0 | 3.0 |
127
+ | No log | 77.0 | 77 | 0.1313 | 0.0 | 3.0 |
128
+ | No log | 78.0 | 78 | 0.1318 | 0.0 | 3.0 |
129
+ | No log | 79.0 | 79 | 0.1321 | 0.0 | 3.0 |
130
+ | No log | 80.0 | 80 | 0.1325 | 0.0 | 3.0 |
131
+ | No log | 81.0 | 81 | 0.1327 | 0.0 | 3.0 |
132
+ | No log | 82.0 | 82 | 0.1330 | 0.0 | 3.0 |
133
+ | No log | 83.0 | 83 | 0.1333 | 0.0 | 3.0 |
134
+ | No log | 84.0 | 84 | 0.1336 | 0.0 | 3.0 |
135
+ | No log | 85.0 | 85 | 0.1339 | 0.0 | 3.0 |
136
+ | No log | 86.0 | 86 | 0.1342 | 0.0 | 3.0 |
137
+ | No log | 87.0 | 87 | 0.1343 | 0.0 | 3.0 |
138
+ | No log | 88.0 | 88 | 0.1344 | 0.0 | 3.0 |
139
+ | No log | 89.0 | 89 | 0.1345 | 0.0 | 3.0 |
140
+ | No log | 90.0 | 90 | 0.1347 | 0.0 | 3.0 |
141
+ | No log | 91.0 | 91 | 0.1349 | 0.0 | 3.0 |
142
+ | No log | 92.0 | 92 | 0.1352 | 0.0 | 3.0 |
143
+ | No log | 93.0 | 93 | 0.1353 | 0.0 | 3.0 |
144
+ | No log | 94.0 | 94 | 0.1354 | 0.0 | 3.0 |
145
+ | No log | 95.0 | 95 | 0.1355 | 0.0 | 3.0 |
146
+ | No log | 96.0 | 96 | 0.1355 | 0.0 | 3.0 |
147
+ | No log | 97.0 | 97 | 0.1355 | 0.0 | 3.0 |
148
+ | No log | 98.0 | 98 | 0.1355 | 0.0 | 3.0 |
149
+ | No log | 99.0 | 99 | 0.1355 | 0.0 | 3.0 |
150
+ | No log | 100.0 | 100 | 0.1355 | 0.0 | 3.0 |
151
+
152
 
153
  ### Framework versions
154
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7359697aba65c176da4e6d8000e73a3291c39a05b27b3ef1652ac44931c3340
3
  size 242069785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82bb02c7e56ce0d60f87199c5b5d7b0e34538e18bae1264d4f709ec1e8d77be3
3
  size 242069785
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 sha256:9281b86b7ceb9f3178f1eb84662ff3aff8c2aa80445a6cff86d4d02117998841
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9aa47a42d271876f281b7c2643e31044a5161b056a1ea226bf8cc3104d03f2
3
  size 4219