Davlan commited on
Commit
6825281
1 Parent(s): a7f5449

add MT model

Browse files
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_bleu": 17.2678,
4
+ "eval_gen_len": 30.1993,
5
+ "eval_loss": 2.5319368839263916,
6
+ "eval_runtime": 385.9668,
7
+ "eval_samples": 1500,
8
+ "eval_samples_per_second": 3.886,
9
+ "eval_steps_per_second": 0.389,
10
+ "predict_bleu": 20.3381,
11
+ "predict_gen_len": 29.4427,
12
+ "predict_loss": 2.334970474243164,
13
+ "predict_runtime": 382.7007,
14
+ "predict_samples": 1500,
15
+ "predict_samples_per_second": 3.92,
16
+ "predict_steps_per_second": 0.392,
17
+ "train_loss": 0.920722548348563,
18
+ "train_runtime": 2143.3946,
19
+ "train_samples": 6998,
20
+ "train_samples_per_second": 32.649,
21
+ "train_steps_per_second": 3.266
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": 128042,
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": 10.0,
3
+ "eval_bleu": 17.2678,
4
+ "eval_gen_len": 30.1993,
5
+ "eval_loss": 2.5319368839263916,
6
+ "eval_runtime": 385.9668,
7
+ "eval_samples": 1500,
8
+ "eval_samples_per_second": 3.886,
9
+ "eval_steps_per_second": 0.389
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": 20.3381,
3
+ "predict_gen_len": 29.4427,
4
+ "predict_loss": 2.334970474243164,
5
+ "predict_runtime": 382.7007,
6
+ "predict_samples": 1500,
7
+ "predict_samples_per_second": 3.92,
8
+ "predict_steps_per_second": 0.392
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15cebf23392094629741ac82c2b1eef4f0a5fc11861eb454ba07a6795ee200f9
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": 10.0,
3
+ "train_loss": 0.920722548348563,
4
+ "train_runtime": 2143.3946,
5
+ "train_samples": 6998,
6
+ "train_samples_per_second": 32.649,
7
+ "train_steps_per_second": 3.266
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 7000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.71,
12
+ "learning_rate": 4.642857142857143e-05,
13
+ "loss": 2.7393,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.43,
18
+ "learning_rate": 4.2857142857142856e-05,
19
+ "loss": 1.9187,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.14,
24
+ "learning_rate": 3.928571428571429e-05,
25
+ "loss": 1.5915,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.86,
30
+ "learning_rate": 3.571428571428572e-05,
31
+ "loss": 1.2868,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 3.57,
36
+ "learning_rate": 3.2142857142857144e-05,
37
+ "loss": 1.0518,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 4.29,
42
+ "learning_rate": 2.857142857142857e-05,
43
+ "loss": 0.8824,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 5.0,
48
+ "learning_rate": 2.5e-05,
49
+ "loss": 0.7554,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 5.71,
54
+ "learning_rate": 2.1428571428571428e-05,
55
+ "loss": 0.5744,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 6.43,
60
+ "learning_rate": 1.785714285714286e-05,
61
+ "loss": 0.5093,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 7.14,
66
+ "learning_rate": 1.4285714285714285e-05,
67
+ "loss": 0.4241,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 7.86,
72
+ "learning_rate": 1.0714285714285714e-05,
73
+ "loss": 0.3528,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 8.57,
78
+ "learning_rate": 7.142857142857143e-06,
79
+ "loss": 0.2971,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 9.29,
84
+ "learning_rate": 3.5714285714285714e-06,
85
+ "loss": 0.2636,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 10.0,
90
+ "learning_rate": 0.0,
91
+ "loss": 0.2431,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 10.0,
96
+ "step": 7000,
97
+ "total_flos": 9381607974764544.0,
98
+ "train_loss": 0.920722548348563,
99
+ "train_runtime": 2143.3946,
100
+ "train_samples_per_second": 32.649,
101
+ "train_steps_per_second": 3.266
102
+ }
103
+ ],
104
+ "max_steps": 7000,
105
+ "num_train_epochs": 10,
106
+ "total_flos": 9381607974764544.0,
107
+ "trial_name": null,
108
+ "trial_params": null
109
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb1555f7d16c30bc752075b3aebef0dbb8053fa9c22abba12c008de4e86b9c0
3
+ size 2799
vocab.json ADDED
The diff for this file is too large to render. See raw diff