Davlan commited on
Commit
b0a6d31
1 Parent(s): 40e98f8

add MT model

Browse files
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_bleu": 10.3059,
4
+ "eval_gen_len": 45.176,
5
+ "eval_loss": 2.421374797821045,
6
+ "eval_runtime": 641.7966,
7
+ "eval_samples": 1506,
8
+ "eval_samples_per_second": 2.347,
9
+ "eval_steps_per_second": 0.235,
10
+ "predict_bleu": 9.3128,
11
+ "predict_gen_len": 48.1407,
12
+ "predict_loss": 2.428270101547241,
13
+ "predict_runtime": 728.7378,
14
+ "predict_samples": 1500,
15
+ "predict_samples_per_second": 2.058,
16
+ "predict_steps_per_second": 0.206,
17
+ "train_loss": 1.5980410317117855,
18
+ "train_runtime": 2382.5719,
19
+ "train_samples": 25362,
20
+ "train_samples_per_second": 31.934,
21
+ "train_steps_per_second": 3.194
22
+ }
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": "4.10.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128112
38
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_bleu": 10.3059,
4
+ "eval_gen_len": 45.176,
5
+ "eval_loss": 2.421374797821045,
6
+ "eval_runtime": 641.7966,
7
+ "eval_samples": 1506,
8
+ "eval_samples_per_second": 2.347,
9
+ "eval_steps_per_second": 0.235
10
+ }
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": 9.3128,
3
+ "predict_gen_len": 48.1407,
4
+ "predict_loss": 2.428270101547241,
5
+ "predict_runtime": 728.7378,
6
+ "predict_samples": 1500,
7
+ "predict_samples_per_second": 2.058,
8
+ "predict_steps_per_second": 0.206
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9620dcb1ddf792c0483d98dff211127393bba7e2ae2114191dce758d6ac5dca4
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": "facebook/m2m100_418M", "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": 1.5980410317117855,
4
+ "train_runtime": 2382.5719,
5
+ "train_samples": 25362,
6
+ "train_samples_per_second": 31.934,
7
+ "train_steps_per_second": 3.194
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 7611,
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": 4.6715280515044016e-05,
13
+ "loss": 2.6428,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.39,
18
+ "learning_rate": 4.343056103008804e-05,
19
+ "loss": 2.1936,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.59,
24
+ "learning_rate": 4.0145841545132044e-05,
25
+ "loss": 2.0029,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.79,
30
+ "learning_rate": 3.6861122060176065e-05,
31
+ "loss": 1.9101,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.99,
36
+ "learning_rate": 3.357640257522008e-05,
37
+ "loss": 1.8112,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.18,
42
+ "learning_rate": 3.0291683090264093e-05,
43
+ "loss": 1.5651,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.38,
48
+ "learning_rate": 2.7006963605308104e-05,
49
+ "loss": 1.502,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 1.58,
54
+ "learning_rate": 2.372224412035212e-05,
55
+ "loss": 1.5072,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 1.77,
60
+ "learning_rate": 2.043752463539614e-05,
61
+ "loss": 1.4634,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.97,
66
+ "learning_rate": 1.7152805150440153e-05,
67
+ "loss": 1.4422,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 2.17,
72
+ "learning_rate": 1.3868085665484169e-05,
73
+ "loss": 1.2386,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 2.36,
78
+ "learning_rate": 1.0583366180528183e-05,
79
+ "loss": 1.2121,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 2.56,
84
+ "learning_rate": 7.298646695572199e-06,
85
+ "loss": 1.1924,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 2.76,
90
+ "learning_rate": 4.013927210616213e-06,
91
+ "loss": 1.198,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 2.96,
96
+ "learning_rate": 7.292077256602286e-07,
97
+ "loss": 1.1828,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 3.0,
102
+ "step": 7611,
103
+ "total_flos": 1.3124190737596416e+16,
104
+ "train_loss": 1.5980410317117855,
105
+ "train_runtime": 2382.5719,
106
+ "train_samples_per_second": 31.934,
107
+ "train_steps_per_second": 3.194
108
+ }
109
+ ],
110
+ "max_steps": 7611,
111
+ "num_train_epochs": 3,
112
+ "total_flos": 1.3124190737596416e+16,
113
+ "trial_name": null,
114
+ "trial_params": null
115
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea706f41dfe3e9d2b7f8bec3ab0aaa31f36fa8f26592b7f061e5984175003602
3
+ size 2799
vocab.json ADDED
The diff for this file is too large to render. See raw diff