Davlan commited on
Commit
6517438
1 Parent(s): 1339e54

add MT model

Browse files
all_results.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
  "epoch": 3.0,
3
- "predict_bleu": 6.8678,
4
- "predict_gen_len": 45.8158,
5
- "predict_loss": 2.570692300796509,
6
- "predict_runtime": 858.3289,
7
  "predict_samples": 1574,
8
- "predict_samples_per_second": 1.834,
9
- "predict_steps_per_second": 0.184,
10
- "train_loss": 2.3168928876540895,
11
- "train_runtime": 285.5448,
12
  "train_samples": 2287,
13
- "train_samples_per_second": 24.028,
14
- "train_steps_per_second": 2.406
15
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "predict_bleu": 7.0023,
4
+ "predict_gen_len": 42.6347,
5
+ "predict_loss": 2.5708374977111816,
6
+ "predict_runtime": 932.8364,
7
  "predict_samples": 1574,
8
+ "predict_samples_per_second": 1.687,
9
+ "predict_steps_per_second": 0.338,
10
+ "train_loss": 2.3068067170299993,
11
+ "train_runtime": 303.1653,
12
  "train_samples": 2287,
13
+ "train_samples_per_second": 22.631,
14
+ "train_steps_per_second": 2.266
15
  }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "m2m100_mos_fr",
3
  "activation_dropout": 0.0,
4
  "activation_function": "relu",
5
  "architectures": [
@@ -32,7 +32,7 @@
32
  "pad_token_id": 1,
33
  "scale_embedding": true,
34
  "torch_dtype": "float32",
35
- "transformers_version": "4.10.3",
36
  "use_cache": true,
37
  "vocab_size": 128112
38
  }
 
1
  {
2
+ "_name_or_path": "mos/m2m100_mos_fr",
3
  "activation_dropout": 0.0,
4
  "activation_function": "relu",
5
  "architectures": [
 
32
  "pad_token_id": 1,
33
  "scale_embedding": true,
34
  "torch_dtype": "float32",
35
+ "transformers_version": "4.12.0",
36
  "use_cache": true,
37
  "vocab_size": 128112
38
  }
generated_predictions.txt CHANGED
The diff for this file is too large to render. See raw diff
 
predict_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "predict_bleu": 6.8678,
3
- "predict_gen_len": 45.8158,
4
- "predict_loss": 2.570692300796509,
5
- "predict_runtime": 858.3289,
6
  "predict_samples": 1574,
7
- "predict_samples_per_second": 1.834,
8
- "predict_steps_per_second": 0.184
9
  }
 
1
  {
2
+ "predict_bleu": 7.0023,
3
+ "predict_gen_len": 42.6347,
4
+ "predict_loss": 2.5708374977111816,
5
+ "predict_runtime": 932.8364,
6
  "predict_samples": 1574,
7
+ "predict_samples_per_second": 1.687,
8
+ "predict_steps_per_second": 0.338
9
  }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe2ea90ce6978bd975a5685c6923e6249c01d1ebe9b1ccdbc279049af71282a
3
+ size 1935804116
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"src_lang": null, "tgt_lang": null, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "m2m100_mos_fr", "model_max_length": 1024, "additional_special_tokens": ["__af__", "__am__", "__ar__", "__ast__", "__az__", "__ba__", "__be__", "__bg__", "__bn__", "__br__", "__bs__", "__ca__", "__ceb__", "__cs__", "__cy__", "__da__", "__de__", "__el__", "__en__", "__es__", "__et__", "__fa__", "__ff__", "__fi__", "__fr__", "__fy__", "__ga__", "__gd__", "__gl__", "__gu__", "__ha__", "__he__", "__hi__", "__hr__", "__ht__", "__hu__", "__hy__", "__id__", "__ig__", "__ilo__", "__is__", "__it__", "__ja__", "__jv__", "__ka__", "__kk__", "__km__", "__kn__", "__ko__", "__lb__", "__lg__", "__ln__", "__lo__", "__lt__", "__lv__", "__mg__", "__mk__", "__ml__", "__mn__", "__mr__", "__ms__", "__my__", "__ne__", "__nl__", "__no__", "__ns__", "__oc__", "__or__", "__pa__", "__pl__", "__ps__", "__pt__", "__ro__", "__ru__", "__sd__", "__si__", "__sk__", "__sl__", "__so__", "__sq__", "__sr__", "__ss__", "__su__", "__sv__", "__sw__", "__ta__", "__th__", "__tl__", "__tn__", "__tr__", "__uk__", "__ur__", "__uz__", "__vi__", "__wo__", "__xh__", "__yi__", "__yo__", "__zh__", "__zu__"], "tokenizer_class": "M2M100Tokenizer"}
 
1
+ {"src_lang": null, "tgt_lang": null, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "mos/m2m100_mos_fr", "model_max_length": 1024, "additional_special_tokens": ["__af__", "__am__", "__ar__", "__ast__", "__az__", "__ba__", "__be__", "__bg__", "__bn__", "__br__", "__bs__", "__ca__", "__ceb__", "__cs__", "__cy__", "__da__", "__de__", "__el__", "__en__", "__es__", "__et__", "__fa__", "__ff__", "__fi__", "__fr__", "__fy__", "__ga__", "__gd__", "__gl__", "__gu__", "__ha__", "__he__", "__hi__", "__hr__", "__ht__", "__hu__", "__hy__", "__id__", "__ig__", "__ilo__", "__is__", "__it__", "__ja__", "__jv__", "__ka__", "__kk__", "__km__", "__kn__", "__ko__", "__lb__", "__lg__", "__ln__", "__lo__", "__lt__", "__lv__", "__mg__", "__mk__", "__ml__", "__mn__", "__mr__", "__ms__", "__my__", "__ne__", "__nl__", "__no__", "__ns__", "__oc__", "__or__", "__pa__", "__pl__", "__ps__", "__pt__", "__ro__", "__ru__", "__sd__", "__si__", "__sk__", "__sl__", "__so__", "__sq__", "__sr__", "__ss__", "__su__", "__sv__", "__sw__", "__ta__", "__th__", "__tl__", "__tn__", "__tr__", "__uk__", "__ur__", "__uz__", "__vi__", "__wo__", "__xh__", "__yi__", "__yo__", "__zh__", "__zu__"], "tokenizer_class": "M2M100Tokenizer"}
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
- "train_loss": 2.3168928876540895,
4
- "train_runtime": 285.5448,
5
  "train_samples": 2287,
6
- "train_samples_per_second": 24.028,
7
- "train_steps_per_second": 2.406
8
  }
 
1
  {
2
  "epoch": 3.0,
3
+ "train_loss": 2.3068067170299993,
4
+ "train_runtime": 303.1653,
5
  "train_samples": 2287,
6
+ "train_samples_per_second": 22.631,
7
+ "train_steps_per_second": 2.266
8
  }
trainer_state.json CHANGED
@@ -10,22 +10,22 @@
10
  {
11
  "epoch": 2.18,
12
  "learning_rate": 1.3609898107714703e-05,
13
- "loss": 2.5124,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 3.0,
18
  "step": 687,
19
- "total_flos": 1835798017572864.0,
20
- "train_loss": 2.3168928876540895,
21
- "train_runtime": 285.5448,
22
- "train_samples_per_second": 24.028,
23
- "train_steps_per_second": 2.406
24
  }
25
  ],
26
  "max_steps": 687,
27
  "num_train_epochs": 3,
28
- "total_flos": 1835798017572864.0,
29
  "trial_name": null,
30
  "trial_params": null
31
  }
 
10
  {
11
  "epoch": 2.18,
12
  "learning_rate": 1.3609898107714703e-05,
13
+ "loss": 2.5059,
14
  "step": 500
15
  },
16
  {
17
  "epoch": 3.0,
18
  "step": 687,
19
+ "total_flos": 1622235349991424.0,
20
+ "train_loss": 2.3068067170299993,
21
+ "train_runtime": 303.1653,
22
+ "train_samples_per_second": 22.631,
23
+ "train_steps_per_second": 2.266
24
  }
25
  ],
26
  "max_steps": 687,
27
  "num_train_epochs": 3,
28
+ "total_flos": 1622235349991424.0,
29
  "trial_name": null,
30
  "trial_params": null
31
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de61e04c3597e86275ac1c995c80972410aca37665e0f225fe1a295204b40207
3
- size 2735
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eb0b478f98e8d9b04eeff2dc65b1652523554c0545d9d09a6377c021b9d29f1
3
+ size 2927