Hugging Face's logo

lgrobol
/
m2m100_418M_br_fr

Translation
Transformers
PyTorch
Safetensors
Breton
French
m2m_100
text2text-generation
Model card Files
xet
Community
1
lgrobol commited on
Commit
1fa552f
·
1 Parent(s): 816741d

initial

Browse files
Files changed (11) hide show
  1. README.md +51 -0
  2. all_results.json +8 -0
  3. config.json +38 -0
  4. pytorch_model.bin +3 -0
  5. sentencepiece.bpe.model +3 -0
  6. special_tokens_map.json +109 -0
  7. tokenizer_config.json +119 -0
  8. train_results.json +8 -0
  9. trainer_state.json +241 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
README.md CHANGED
@@ -1,3 +1,54 @@
1
  ---
 
 
 
2
  license: mit
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - br
4
+ - fr
5
  license: mit
6
+ tags:
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: m2m100_br_fr
10
+ results: []
11
  ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # m2m100_br_fr
17
+
18
+ This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on an unknown dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3.0
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.23.1
52
+ - Pytorch 1.12.1+cu116
53
+ - Datasets 2.6.1
54
+ - Tokenizers 0.13.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.4955534830489579,
4
+ "train_runtime": 15709.331,
5
+ "train_samples": 48907,
6
+ "train_samples_per_second": 9.34,
7
+ "train_steps_per_second": 1.168
8
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/m2m100_418M",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "M2M100ForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "d_model": 1024,
11
+ "decoder_attention_heads": 16,
12
+ "decoder_ffn_dim": 4096,
13
+ "decoder_layerdrop": 0.05,
14
+ "decoder_layers": 12,
15
+ "decoder_start_token_id": 2,
16
+ "dropout": 0.1,
17
+ "early_stopping": true,
18
+ "encoder_attention_heads": 16,
19
+ "encoder_ffn_dim": 4096,
20
+ "encoder_layerdrop": 0.05,
21
+ "encoder_layers": 12,
22
+ "eos_token_id": 2,
23
+ "forced_bos_token_id": 128028,
24
+ "gradient_checkpointing": false,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "max_length": 200,
28
+ "max_position_embeddings": 1024,
29
+ "model_type": "m2m_100",
30
+ "num_beams": 5,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 1,
33
+ "scale_embedding": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.23.1",
36
+ "use_cache": true,
37
+ "vocab_size": 128112
38
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e6ca2e2048c0abf133d1ea4f986221f7744da591536e2c96c4aa7c8ad290d8e
3
+ size 1935792071
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
3
+ size 2423393
special_tokens_map.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__af__",
4
+ "__am__",
5
+ "__ar__",
6
+ "__ast__",
7
+ "__az__",
8
+ "__ba__",
9
+ "__be__",
10
+ "__bg__",
11
+ "__bn__",
12
+ "__br__",
13
+ "__bs__",
14
+ "__ca__",
15
+ "__ceb__",
16
+ "__cs__",
17
+ "__cy__",
18
+ "__da__",
19
+ "__de__",
20
+ "__el__",
21
+ "__en__",
22
+ "__es__",
23
+ "__et__",
24
+ "__fa__",
25
+ "__ff__",
26
+ "__fi__",
27
+ "__fr__",
28
+ "__fy__",
29
+ "__ga__",
30
+ "__gd__",
31
+ "__gl__",
32
+ "__gu__",
33
+ "__ha__",
34
+ "__he__",
35
+ "__hi__",
36
+ "__hr__",
37
+ "__ht__",
38
+ "__hu__",
39
+ "__hy__",
40
+ "__id__",
41
+ "__ig__",
42
+ "__ilo__",
43
+ "__is__",
44
+ "__it__",
45
+ "__ja__",
46
+ "__jv__",
47
+ "__ka__",
48
+ "__kk__",
49
+ "__km__",
50
+ "__kn__",
51
+ "__ko__",
52
+ "__lb__",
53
+ "__lg__",
54
+ "__ln__",
55
+ "__lo__",
56
+ "__lt__",
57
+ "__lv__",
58
+ "__mg__",
59
+ "__mk__",
60
+ "__ml__",
61
+ "__mn__",
62
+ "__mr__",
63
+ "__ms__",
64
+ "__my__",
65
+ "__ne__",
66
+ "__nl__",
67
+ "__no__",
68
+ "__ns__",
69
+ "__oc__",
70
+ "__or__",
71
+ "__pa__",
72
+ "__pl__",
73
+ "__ps__",
74
+ "__pt__",
75
+ "__ro__",
76
+ "__ru__",
77
+ "__sd__",
78
+ "__si__",
79
+ "__sk__",
80
+ "__sl__",
81
+ "__so__",
82
+ "__sq__",
83
+ "__sr__",
84
+ "__ss__",
85
+ "__su__",
86
+ "__sv__",
87
+ "__sw__",
88
+ "__ta__",
89
+ "__th__",
90
+ "__tl__",
91
+ "__tn__",
92
+ "__tr__",
93
+ "__uk__",
94
+ "__ur__",
95
+ "__uz__",
96
+ "__vi__",
97
+ "__wo__",
98
+ "__xh__",
99
+ "__yi__",
100
+ "__yo__",
101
+ "__zh__",
102
+ "__zu__"
103
+ ],
104
+ "bos_token": "<s>",
105
+ "eos_token": "</s>",
106
+ "pad_token": "<pad>",
107
+ "sep_token": "</s>",
108
+ "unk_token": "<unk>"
109
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "__af__",
4
+ "__am__",
5
+ "__ar__",
6
+ "__ast__",
7
+ "__az__",
8
+ "__ba__",
9
+ "__be__",
10
+ "__bg__",
11
+ "__bn__",
12
+ "__br__",
13
+ "__bs__",
14
+ "__ca__",
15
+ "__ceb__",
16
+ "__cs__",
17
+ "__cy__",
18
+ "__da__",
19
+ "__de__",
20
+ "__el__",
21
+ "__en__",
22
+ "__es__",
23
+ "__et__",
24
+ "__fa__",
25
+ "__ff__",
26
+ "__fi__",
27
+ "__fr__",
28
+ "__fy__",
29
+ "__ga__",
30
+ "__gd__",
31
+ "__gl__",
32
+ "__gu__",
33
+ "__ha__",
34
+ "__he__",
35
+ "__hi__",
36
+ "__hr__",
37
+ "__ht__",
38
+ "__hu__",
39
+ "__hy__",
40
+ "__id__",
41
+ "__ig__",
42
+ "__ilo__",
43
+ "__is__",
44
+ "__it__",
45
+ "__ja__",
46
+ "__jv__",
47
+ "__ka__",
48
+ "__kk__",
49
+ "__km__",
50
+ "__kn__",
51
+ "__ko__",
52
+ "__lb__",
53
+ "__lg__",
54
+ "__ln__",
55
+ "__lo__",
56
+ "__lt__",
57
+ "__lv__",
58
+ "__mg__",
59
+ "__mk__",
60
+ "__ml__",
61
+ "__mn__",
62
+ "__mr__",
63
+ "__ms__",
64
+ "__my__",
65
+ "__ne__",
66
+ "__nl__",
67
+ "__no__",
68
+ "__ns__",
69
+ "__oc__",
70
+ "__or__",
71
+ "__pa__",
72
+ "__pl__",
73
+ "__ps__",
74
+ "__pt__",
75
+ "__ro__",
76
+ "__ru__",
77
+ "__sd__",
78
+ "__si__",
79
+ "__sk__",
80
+ "__sl__",
81
+ "__so__",
82
+ "__sq__",
83
+ "__sr__",
84
+ "__ss__",
85
+ "__su__",
86
+ "__sv__",
87
+ "__sw__",
88
+ "__ta__",
89
+ "__th__",
90
+ "__tl__",
91
+ "__tn__",
92
+ "__tr__",
93
+ "__uk__",
94
+ "__ur__",
95
+ "__uz__",
96
+ "__vi__",
97
+ "__wo__",
98
+ "__xh__",
99
+ "__yi__",
100
+ "__yo__",
101
+ "__zh__",
102
+ "__zu__"
103
+ ],
104
+ "bos_token": "<s>",
105
+ "eos_token": "</s>",
106
+ "language_codes": "m2m100",
107
+ "model_max_length": 1024,
108
+ "name_or_path": "facebook/m2m100_418M",
109
+ "num_madeup_words": 8,
110
+ "pad_token": "<pad>",
111
+ "sep_token": "</s>",
112
+ "sp_model_kwargs": {},
113
+ "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json",
114
+ "src_lang": null,
115
+ "tgt_lang": null,
116
+ "tokenizer_class": "M2M100Tokenizer",
117
+ "tokenizer_file": null,
118
+ "unk_token": "<unk>"
119
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.4955534830489579,
4
+ "train_runtime": 15709.331,
5
+ "train_samples": 48907,
6
+ "train_samples_per_second": 9.34,
7
+ "train_steps_per_second": 1.168
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 18342,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.08,
12
+ "learning_rate": 4.863700795987351e-05,
13
+ "loss": 2.8121,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.16,
18
+ "learning_rate": 4.7274015919747035e-05,
19
+ "loss": 2.3962,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.25,
24
+ "learning_rate": 4.5911023879620545e-05,
25
+ "loss": 2.2275,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.33,
30
+ "learning_rate": 4.454803183949406e-05,
31
+ "loss": 2.1283,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.41,
36
+ "learning_rate": 4.318503979936757e-05,
37
+ "loss": 2.0421,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.49,
42
+ "learning_rate": 4.182204775924109e-05,
43
+ "loss": 1.9646,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.57,
48
+ "learning_rate": 4.0459055719114605e-05,
49
+ "loss": 1.9383,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.65,
54
+ "learning_rate": 3.9096063678988114e-05,
55
+ "loss": 1.8862,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.74,
60
+ "learning_rate": 3.773307163886163e-05,
61
+ "loss": 1.8524,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.82,
66
+ "learning_rate": 3.637007959873515e-05,
67
+ "loss": 1.8164,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.9,
72
+ "learning_rate": 3.500708755860866e-05,
73
+ "loss": 1.7536,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.98,
78
+ "learning_rate": 3.3644095518482174e-05,
79
+ "loss": 1.7631,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.06,
84
+ "learning_rate": 3.228110347835569e-05,
85
+ "loss": 1.4821,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.14,
90
+ "learning_rate": 3.09181114382292e-05,
91
+ "loss": 1.4501,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.23,
96
+ "learning_rate": 2.9555119398102717e-05,
97
+ "loss": 1.4364,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.31,
102
+ "learning_rate": 2.8192127357976233e-05,
103
+ "loss": 1.4028,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.39,
108
+ "learning_rate": 2.6829135317849746e-05,
109
+ "loss": 1.3865,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.47,
114
+ "learning_rate": 2.546614327772326e-05,
115
+ "loss": 1.4069,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.55,
120
+ "learning_rate": 2.4103151237596773e-05,
121
+ "loss": 1.3883,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.64,
126
+ "learning_rate": 2.2740159197470286e-05,
127
+ "loss": 1.3654,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.72,
132
+ "learning_rate": 2.1377167157343802e-05,
133
+ "loss": 1.3411,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.8,
138
+ "learning_rate": 2.0014175117217316e-05,
139
+ "loss": 1.3359,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 1.88,
144
+ "learning_rate": 1.8651183077090832e-05,
145
+ "loss": 1.379,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 1.96,
150
+ "learning_rate": 1.7288191036964345e-05,
151
+ "loss": 1.3316,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.04,
156
+ "learning_rate": 1.592519899683786e-05,
157
+ "loss": 1.2242,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.13,
162
+ "learning_rate": 1.4562206956711375e-05,
163
+ "loss": 1.0537,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.21,
168
+ "learning_rate": 1.3199214916584887e-05,
169
+ "loss": 1.0697,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.29,
174
+ "learning_rate": 1.1836222876458403e-05,
175
+ "loss": 1.0704,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.37,
180
+ "learning_rate": 1.0473230836331916e-05,
181
+ "loss": 1.0918,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.45,
186
+ "learning_rate": 9.110238796205431e-06,
187
+ "loss": 1.0878,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.54,
192
+ "learning_rate": 7.747246756078944e-06,
193
+ "loss": 1.0506,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 2.62,
198
+ "learning_rate": 6.384254715952459e-06,
199
+ "loss": 1.0557,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 2.7,
204
+ "learning_rate": 5.021262675825973e-06,
205
+ "loss": 1.0325,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 2.78,
210
+ "learning_rate": 3.658270635699488e-06,
211
+ "loss": 1.0784,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 2.86,
216
+ "learning_rate": 2.295278595573002e-06,
217
+ "loss": 1.0239,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 2.94,
222
+ "learning_rate": 9.322865554465163e-07,
223
+ "loss": 1.0211,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 3.0,
228
+ "step": 18342,
229
+ "total_flos": 2.148457555862323e+16,
230
+ "train_loss": 1.4955534830489579,
231
+ "train_runtime": 15709.331,
232
+ "train_samples_per_second": 9.34,
233
+ "train_steps_per_second": 1.168
234
+ }
235
+ ],
236
+ "max_steps": 18342,
237
+ "num_train_epochs": 3,
238
+ "total_flos": 2.148457555862323e+16,
239
+ "trial_name": null,
240
+ "trial_params": null
241
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906c9235c8bf75589426402d4a87903317a704f12dd138c3607b781101161aea
3
+ size 3503
vocab.json ADDED
The diff for this file is too large to render. See raw diff