Davlan commited on
Commit
eae203e
1 Parent(s): a89e194

add MT model

Browse files
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "predict_bleu": 30.7178,
4
+ "predict_gen_len": 33.0948,
5
+ "predict_loss": 1.6477829217910767,
6
+ "predict_runtime": 537.564,
7
+ "predict_samples": 1835,
8
+ "predict_samples_per_second": 3.414,
9
+ "predict_steps_per_second": 0.342,
10
+ "train_loss": 1.4262250119942639,
11
+ "train_runtime": 2645.2092,
12
+ "train_samples": 30782,
13
+ "train_samples_per_second": 34.911,
14
+ "train_steps_per_second": 3.492
15
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "m2m100_sw_en",
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": 128022,
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": "4.10.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128112
38
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu": 30.7178,
3
+ "predict_gen_len": 33.0948,
4
+ "predict_loss": 1.6477829217910767,
5
+ "predict_runtime": 537.564,
6
+ "predict_samples": 1835,
7
+ "predict_samples_per_second": 3.414,
8
+ "predict_steps_per_second": 0.342
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b2385f42616ffb72afdbe88e7aa9d2e1f235f849d9debf84297be93a3360318
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 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "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_config.json ADDED
@@ -0,0 +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_sw_en", "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 ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.4262250119942639,
4
+ "train_runtime": 2645.2092,
5
+ "train_samples": 30782,
6
+ "train_samples_per_second": 34.911,
7
+ "train_steps_per_second": 3.492
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 9237,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.16,
12
+ "learning_rate": 4.729349355851467e-05,
13
+ "loss": 2.1999,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.32,
18
+ "learning_rate": 4.458698711702934e-05,
19
+ "loss": 1.9935,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.49,
24
+ "learning_rate": 4.188048067554401e-05,
25
+ "loss": 1.877,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.65,
30
+ "learning_rate": 3.917397423405868e-05,
31
+ "loss": 1.8246,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.81,
36
+ "learning_rate": 3.646746779257334e-05,
37
+ "loss": 1.7882,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.97,
42
+ "learning_rate": 3.376096135108802e-05,
43
+ "loss": 1.7572,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.14,
48
+ "learning_rate": 3.105445490960269e-05,
49
+ "loss": 1.4072,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.3,
54
+ "learning_rate": 2.8347948468117357e-05,
55
+ "loss": 1.3441,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.46,
60
+ "learning_rate": 2.5641442026632023e-05,
61
+ "loss": 1.3168,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.62,
66
+ "learning_rate": 2.2934935585146693e-05,
67
+ "loss": 1.3491,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.79,
72
+ "learning_rate": 2.0228429143661362e-05,
73
+ "loss": 1.324,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.95,
78
+ "learning_rate": 1.752192270217603e-05,
79
+ "loss": 1.3135,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 2.11,
84
+ "learning_rate": 1.4815416260690701e-05,
85
+ "loss": 1.1231,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.27,
90
+ "learning_rate": 1.210890981920537e-05,
91
+ "loss": 1.0582,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.44,
96
+ "learning_rate": 9.40240337772004e-06,
97
+ "loss": 1.0529,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 2.6,
102
+ "learning_rate": 6.695896936234708e-06,
103
+ "loss": 1.041,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 2.76,
108
+ "learning_rate": 3.9893904947493776e-06,
109
+ "loss": 1.0416,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 2.92,
114
+ "learning_rate": 1.2828840532640467e-06,
115
+ "loss": 1.047,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 3.0,
120
+ "step": 9237,
121
+ "total_flos": 1.5124907716509696e+16,
122
+ "train_loss": 1.4262250119942639,
123
+ "train_runtime": 2645.2092,
124
+ "train_samples_per_second": 34.911,
125
+ "train_steps_per_second": 3.492
126
+ }
127
+ ],
128
+ "max_steps": 9237,
129
+ "num_train_epochs": 3,
130
+ "total_flos": 1.5124907716509696e+16,
131
+ "trial_name": null,
132
+ "trial_params": null
133
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6b137ecefc6cba98055f1dfc85c65010b179207f301596776823e4b0fd6aa4
3
+ size 2735
vocab.json ADDED
The diff for this file is too large to render. See raw diff