Hugging Face's logo

ethansimrm
/
opus_wmt_finetuned_enfr_adapt_wce

Transformers
PyTorch
marian
text2text-generation
Model card Files
xet
Community
1
Ethan Sim commited on
Commit
29c838c
·
1 Parent(s): 45ba4e5

stage best adapt_wce model

Browse files
Files changed (23) hide show
  1. checkpoint-80000/config.json +62 -0
  2. checkpoint-80000/generation_config.json +15 -0
  3. checkpoint-80000/optimizer.pt +3 -0
  4. checkpoint-80000/pytorch_model.bin +3 -0
  5. checkpoint-80000/rng_state.pth +3 -0
  6. checkpoint-80000/scaler.pt +3 -0
  7. checkpoint-80000/scheduler.pt +3 -0
  8. checkpoint-80000/source.spm +0 -0
  9. checkpoint-80000/special_tokens_map.json +5 -0
  10. checkpoint-80000/target.spm +0 -0
  11. checkpoint-80000/tokenizer_config.json +12 -0
  12. checkpoint-80000/trainer_state.json +336 -0
  13. checkpoint-80000/training_args.bin +3 -0
  14. checkpoint-80000/vocab.json +0 -0
  15. config.json +62 -0
  16. generation_config.json +15 -0
  17. pytorch_model.bin +3 -0
  18. source.spm +0 -0
  19. special_tokens_map.json +5 -0
  20. target.spm +0 -0
  21. tokenizer_config.json +12 -0
  22. training_args.bin +3 -0
  23. vocab.json +0 -0
checkpoint-80000/config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "swish",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "MarianMTModel"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": [
13
+ [
14
+ 59513
15
+ ]
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 512,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 2048,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 59513,
26
+ "decoder_vocab_size": 59514,
27
+ "dropout": 0.1,
28
+ "encoder_attention_heads": 8,
29
+ "encoder_ffn_dim": 2048,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 0,
33
+ "forced_eos_token_id": 0,
34
+ "gradient_checkpointing": false,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1",
38
+ "2": "LABEL_2"
39
+ },
40
+ "init_std": 0.02,
41
+ "is_encoder_decoder": true,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1,
45
+ "LABEL_2": 2
46
+ },
47
+ "max_length": 512,
48
+ "max_position_embeddings": 512,
49
+ "model_type": "marian",
50
+ "normalize_before": false,
51
+ "normalize_embedding": false,
52
+ "num_beams": 4,
53
+ "num_hidden_layers": 6,
54
+ "pad_token_id": 59513,
55
+ "scale_embedding": true,
56
+ "share_encoder_decoder_embeddings": true,
57
+ "static_position_embeddings": true,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.28.0",
60
+ "use_cache": true,
61
+ "vocab_size": 59514
62
+ }
checkpoint-80000/generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 59513
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 59513,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 59513,
14
+ "transformers_version": "4.28.0"
15
+ }
checkpoint-80000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3d90d9aa1eefdc3f3fc3ea18169602a1ce23ab084af0653b6577f17a4ed364
3
+ size 597026309
checkpoint-80000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e026079d280c7be8556f4cd84790ffd00c84f056aeb211845aab4a55f95ec5e
3
+ size 298763205
checkpoint-80000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ef34011f7579acd0156ff0158558ef6d4dbad3d34289f67965235226a6cd4a
3
+ size 14575
checkpoint-80000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa28cbb5b773e7127942fc44f4c268fa251bcf60503e86ff75009ad140da1c3
3
+ size 557
checkpoint-80000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3349122e2399c65deb4183b16094c6d030d1768282a8e017f61e944aead1de
3
+ size 627
checkpoint-80000/source.spm ADDED
Binary file (778 kB). View file
 
checkpoint-80000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-80000/target.spm ADDED
Binary file (802 kB). View file
 
checkpoint-80000/tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "</s>",
4
+ "model_max_length": 512,
5
+ "pad_token": "<pad>",
6
+ "separate_vocabs": false,
7
+ "source_lang": "en",
8
+ "sp_model_kwargs": {},
9
+ "target_lang": "fr",
10
+ "tokenizer_class": "MarianTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
checkpoint-80000/trainer_state.json ADDED
@@ -0,0 +1,336 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 42.688,
3
+ "best_model_checkpoint": "opus_wmt_finetuned_enfr_adapt_wce/checkpoint-80000",
4
+ "epoch": 3.943217665615142,
5
+ "global_step": 80000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.2,
12
+ "learning_rate": 1.9753918572555207e-05,
13
+ "loss": 0.2044,
14
+ "step": 4000
15
+ },
16
+ {
17
+ "epoch": 0.2,
18
+ "eval_bleu": 35.3087,
19
+ "eval_gen_len": 40.3365,
20
+ "eval_loss": 0.10896722972393036,
21
+ "eval_runtime": 182.4842,
22
+ "eval_samples_per_second": 5.716,
23
+ "eval_steps_per_second": 0.181,
24
+ "step": 4000
25
+ },
26
+ {
27
+ "epoch": 0.39,
28
+ "learning_rate": 1.950746746845426e-05,
29
+ "loss": 0.1714,
30
+ "step": 8000
31
+ },
32
+ {
33
+ "epoch": 0.39,
34
+ "eval_bleu": 37.5792,
35
+ "eval_gen_len": 37.976,
36
+ "eval_loss": 0.10649653524160385,
37
+ "eval_runtime": 199.3657,
38
+ "eval_samples_per_second": 5.232,
39
+ "eval_steps_per_second": 0.166,
40
+ "step": 8000
41
+ },
42
+ {
43
+ "epoch": 0.59,
44
+ "learning_rate": 1.9261016364353314e-05,
45
+ "loss": 0.1645,
46
+ "step": 12000
47
+ },
48
+ {
49
+ "epoch": 0.59,
50
+ "eval_bleu": 41.4587,
51
+ "eval_gen_len": 34.7162,
52
+ "eval_loss": 0.1052778959274292,
53
+ "eval_runtime": 172.9876,
54
+ "eval_samples_per_second": 6.029,
55
+ "eval_steps_per_second": 0.191,
56
+ "step": 12000
57
+ },
58
+ {
59
+ "epoch": 0.79,
60
+ "learning_rate": 1.9014565260252367e-05,
61
+ "loss": 0.1592,
62
+ "step": 16000
63
+ },
64
+ {
65
+ "epoch": 0.79,
66
+ "eval_bleu": 41.4431,
67
+ "eval_gen_len": 34.884,
68
+ "eval_loss": 0.10416532307863235,
69
+ "eval_runtime": 133.2352,
70
+ "eval_samples_per_second": 7.828,
71
+ "eval_steps_per_second": 0.248,
72
+ "step": 16000
73
+ },
74
+ {
75
+ "epoch": 0.99,
76
+ "learning_rate": 1.876811415615142e-05,
77
+ "loss": 0.1568,
78
+ "step": 20000
79
+ },
80
+ {
81
+ "epoch": 0.99,
82
+ "eval_bleu": 41.5116,
83
+ "eval_gen_len": 35.4871,
84
+ "eval_loss": 0.10362005233764648,
85
+ "eval_runtime": 165.327,
86
+ "eval_samples_per_second": 6.309,
87
+ "eval_steps_per_second": 0.2,
88
+ "step": 20000
89
+ },
90
+ {
91
+ "epoch": 1.18,
92
+ "learning_rate": 1.8521786277602524e-05,
93
+ "loss": 0.1453,
94
+ "step": 24000
95
+ },
96
+ {
97
+ "epoch": 1.18,
98
+ "eval_bleu": 41.5688,
99
+ "eval_gen_len": 35.5676,
100
+ "eval_loss": 0.10355014353990555,
101
+ "eval_runtime": 135.4173,
102
+ "eval_samples_per_second": 7.702,
103
+ "eval_steps_per_second": 0.244,
104
+ "step": 24000
105
+ },
106
+ {
107
+ "epoch": 1.38,
108
+ "learning_rate": 1.827545839905363e-05,
109
+ "loss": 0.1451,
110
+ "step": 28000
111
+ },
112
+ {
113
+ "epoch": 1.38,
114
+ "eval_bleu": 42.0159,
115
+ "eval_gen_len": 35.1572,
116
+ "eval_loss": 0.10274477303028107,
117
+ "eval_runtime": 127.4532,
118
+ "eval_samples_per_second": 8.183,
119
+ "eval_steps_per_second": 0.259,
120
+ "step": 28000
121
+ },
122
+ {
123
+ "epoch": 1.58,
124
+ "learning_rate": 1.8029130520504733e-05,
125
+ "loss": 0.1447,
126
+ "step": 32000
127
+ },
128
+ {
129
+ "epoch": 1.58,
130
+ "eval_bleu": 42.1031,
131
+ "eval_gen_len": 34.8984,
132
+ "eval_loss": 0.10220629721879959,
133
+ "eval_runtime": 149.575,
134
+ "eval_samples_per_second": 6.973,
135
+ "eval_steps_per_second": 0.221,
136
+ "step": 32000
137
+ },
138
+ {
139
+ "epoch": 1.77,
140
+ "learning_rate": 1.7782802641955836e-05,
141
+ "loss": 0.1433,
142
+ "step": 36000
143
+ },
144
+ {
145
+ "epoch": 1.77,
146
+ "eval_bleu": 41.1447,
147
+ "eval_gen_len": 36.395,
148
+ "eval_loss": 0.1017821803689003,
149
+ "eval_runtime": 125.7409,
150
+ "eval_samples_per_second": 8.295,
151
+ "eval_steps_per_second": 0.262,
152
+ "step": 36000
153
+ },
154
+ {
155
+ "epoch": 1.97,
156
+ "learning_rate": 1.7536474763406942e-05,
157
+ "loss": 0.1425,
158
+ "step": 40000
159
+ },
160
+ {
161
+ "epoch": 1.97,
162
+ "eval_bleu": 42.2608,
163
+ "eval_gen_len": 34.7306,
164
+ "eval_loss": 0.10189028084278107,
165
+ "eval_runtime": 125.2478,
166
+ "eval_samples_per_second": 8.327,
167
+ "eval_steps_per_second": 0.263,
168
+ "step": 40000
169
+ },
170
+ {
171
+ "epoch": 2.17,
172
+ "learning_rate": 1.7290146884858045e-05,
173
+ "loss": 0.1351,
174
+ "step": 44000
175
+ },
176
+ {
177
+ "epoch": 2.17,
178
+ "eval_bleu": 42.088,
179
+ "eval_gen_len": 34.9895,
180
+ "eval_loss": 0.10226716101169586,
181
+ "eval_runtime": 160.4011,
182
+ "eval_samples_per_second": 6.502,
183
+ "eval_steps_per_second": 0.206,
184
+ "step": 44000
185
+ },
186
+ {
187
+ "epoch": 2.37,
188
+ "learning_rate": 1.704381900630915e-05,
189
+ "loss": 0.1342,
190
+ "step": 48000
191
+ },
192
+ {
193
+ "epoch": 2.37,
194
+ "eval_bleu": 42.2928,
195
+ "eval_gen_len": 35.8667,
196
+ "eval_loss": 0.10214818269014359,
197
+ "eval_runtime": 129.6369,
198
+ "eval_samples_per_second": 8.046,
199
+ "eval_steps_per_second": 0.255,
200
+ "step": 48000
201
+ },
202
+ {
203
+ "epoch": 2.56,
204
+ "learning_rate": 1.6797491127760255e-05,
205
+ "loss": 0.1331,
206
+ "step": 52000
207
+ },
208
+ {
209
+ "epoch": 2.56,
210
+ "eval_bleu": 42.2938,
211
+ "eval_gen_len": 35.0709,
212
+ "eval_loss": 0.10183799266815186,
213
+ "eval_runtime": 122.6411,
214
+ "eval_samples_per_second": 8.504,
215
+ "eval_steps_per_second": 0.269,
216
+ "step": 52000
217
+ },
218
+ {
219
+ "epoch": 2.76,
220
+ "learning_rate": 1.6551163249211358e-05,
221
+ "loss": 0.1334,
222
+ "step": 56000
223
+ },
224
+ {
225
+ "epoch": 2.76,
226
+ "eval_bleu": 42.2699,
227
+ "eval_gen_len": 35.7756,
228
+ "eval_loss": 0.10165245831012726,
229
+ "eval_runtime": 169.9521,
230
+ "eval_samples_per_second": 6.137,
231
+ "eval_steps_per_second": 0.194,
232
+ "step": 56000
233
+ },
234
+ {
235
+ "epoch": 2.96,
236
+ "learning_rate": 1.630483537066246e-05,
237
+ "loss": 0.1337,
238
+ "step": 60000
239
+ },
240
+ {
241
+ "epoch": 2.96,
242
+ "eval_bleu": 42.4051,
243
+ "eval_gen_len": 34.5417,
244
+ "eval_loss": 0.10104605555534363,
245
+ "eval_runtime": 133.5256,
246
+ "eval_samples_per_second": 7.811,
247
+ "eval_steps_per_second": 0.247,
248
+ "step": 60000
249
+ },
250
+ {
251
+ "epoch": 3.15,
252
+ "learning_rate": 1.6058507492113567e-05,
253
+ "loss": 0.1274,
254
+ "step": 64000
255
+ },
256
+ {
257
+ "epoch": 3.15,
258
+ "eval_bleu": 42.2349,
259
+ "eval_gen_len": 34.4947,
260
+ "eval_loss": 0.10177486389875412,
261
+ "eval_runtime": 127.4115,
262
+ "eval_samples_per_second": 8.186,
263
+ "eval_steps_per_second": 0.259,
264
+ "step": 64000
265
+ },
266
+ {
267
+ "epoch": 3.35,
268
+ "learning_rate": 1.581217961356467e-05,
269
+ "loss": 0.1269,
270
+ "step": 68000
271
+ },
272
+ {
273
+ "epoch": 3.35,
274
+ "eval_bleu": 42.525,
275
+ "eval_gen_len": 34.7172,
276
+ "eval_loss": 0.10204348713159561,
277
+ "eval_runtime": 126.0576,
278
+ "eval_samples_per_second": 8.274,
279
+ "eval_steps_per_second": 0.262,
280
+ "step": 68000
281
+ },
282
+ {
283
+ "epoch": 3.55,
284
+ "learning_rate": 1.5565790122239748e-05,
285
+ "loss": 0.1257,
286
+ "step": 72000
287
+ },
288
+ {
289
+ "epoch": 3.55,
290
+ "eval_bleu": 42.1522,
291
+ "eval_gen_len": 34.9981,
292
+ "eval_loss": 0.10202893614768982,
293
+ "eval_runtime": 102.2658,
294
+ "eval_samples_per_second": 10.199,
295
+ "eval_steps_per_second": 0.323,
296
+ "step": 72000
297
+ },
298
+ {
299
+ "epoch": 3.75,
300
+ "learning_rate": 1.531946224369085e-05,
301
+ "loss": 0.1262,
302
+ "step": 76000
303
+ },
304
+ {
305
+ "epoch": 3.75,
306
+ "eval_bleu": 42.342,
307
+ "eval_gen_len": 36.0019,
308
+ "eval_loss": 0.10173359513282776,
309
+ "eval_runtime": 111.861,
310
+ "eval_samples_per_second": 9.324,
311
+ "eval_steps_per_second": 0.295,
312
+ "step": 76000
313
+ },
314
+ {
315
+ "epoch": 3.94,
316
+ "learning_rate": 1.5073072752365931e-05,
317
+ "loss": 0.127,
318
+ "step": 80000
319
+ },
320
+ {
321
+ "epoch": 3.94,
322
+ "eval_bleu": 42.688,
323
+ "eval_gen_len": 34.0681,
324
+ "eval_loss": 0.1015457883477211,
325
+ "eval_runtime": 138.9899,
326
+ "eval_samples_per_second": 7.504,
327
+ "eval_steps_per_second": 0.237,
328
+ "step": 80000
329
+ }
330
+ ],
331
+ "max_steps": 324608,
332
+ "num_train_epochs": 16,
333
+ "total_flos": 1.3796012702564352e+17,
334
+ "trial_name": null,
335
+ "trial_params": null
336
+ }
checkpoint-80000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70da2186a4fde0020923974f0e3f65f21769ea0d49c10b9d3ad38b40d597b4f9
3
+ size 3771
checkpoint-80000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "swish",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "MarianMTModel"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": [
13
+ [
14
+ 59513
15
+ ]
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 512,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 2048,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 59513,
26
+ "decoder_vocab_size": 59514,
27
+ "dropout": 0.1,
28
+ "encoder_attention_heads": 8,
29
+ "encoder_ffn_dim": 2048,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 0,
33
+ "forced_eos_token_id": 0,
34
+ "gradient_checkpointing": false,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1",
38
+ "2": "LABEL_2"
39
+ },
40
+ "init_std": 0.02,
41
+ "is_encoder_decoder": true,
42
+ "label2id": {
43
+ "LABEL_0": 0,
44
+ "LABEL_1": 1,
45
+ "LABEL_2": 2
46
+ },
47
+ "max_length": 512,
48
+ "max_position_embeddings": 512,
49
+ "model_type": "marian",
50
+ "normalize_before": false,
51
+ "normalize_embedding": false,
52
+ "num_beams": 4,
53
+ "num_hidden_layers": 6,
54
+ "pad_token_id": 59513,
55
+ "scale_embedding": true,
56
+ "share_encoder_decoder_embeddings": true,
57
+ "static_position_embeddings": true,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.28.0",
60
+ "use_cache": true,
61
+ "vocab_size": 59514
62
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 59513
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 59513,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 59513,
14
+ "transformers_version": "4.28.0"
15
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e026079d280c7be8556f4cd84790ffd00c84f056aeb211845aab4a55f95ec5e
3
+ size 298763205
source.spm ADDED
Binary file (778 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm ADDED
Binary file (802 kB). View file
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "</s>",
4
+ "model_max_length": 512,
5
+ "pad_token": "<pad>",
6
+ "separate_vocabs": false,
7
+ "source_lang": "en",
8
+ "sp_model_kwargs": {},
9
+ "target_lang": "fr",
10
+ "tokenizer_class": "MarianTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70da2186a4fde0020923974f0e3f65f21769ea0d49c10b9d3ad38b40d597b4f9
3
+ size 3771
vocab.json ADDED
The diff for this file is too large to render. See raw diff