-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathlog
154 lines (150 loc) · 3.73 KB
/
log
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
{
"do_train": false,
"do_test": false,
"do_infer": true,
"num_infer_batches": null,
"hparams_file": null,
"BPETextField": {
"vocab_path": "model/Bert/vocab.txt",
"filtered": false,
"max_len": 256,
"min_utt_len": 1,
"max_utt_len": 50,
"min_ctx_turn": 1,
"max_ctx_turn": 16,
"max_knowledge_num": 16,
"max_knowledge_len": 16,
"tokenizer_type": "Bert"
},
"Dataset": {
"data_dir": "data/DDE_Dialog",
"data_type": "multi_knowledge"
},
"Trainer": {
"use_data_distributed": false,
"valid_metric_name": "-loss",
"num_epochs": 10,
"save_dir": "outputs/DDE.infer",
"batch_size": 8,
"log_steps": 100,
"valid_steps": 2000,
"save_checkpoint": true,
"save_summary": false,
"shuffle": true,
"sort_pool_size": 0
},
"Model": {
"init_checkpoint": null,
"model": "UnifiedTransformer",
"num_token_embeddings": 30522,
"num_pos_embeddings": 512,
"num_type_embeddings": 2,
"num_turn_embeddings": 16,
"num_latent": 20,
"tau": 0.67,
"with_bow": true,
"hidden_dim": 768,
"num_heads": 12,
"num_layers": 12,
"padding_idx": 0,
"dropout": 0.1,
"embed_dropout": 0.0,
"attn_dropout": 0.1,
"ff_dropout": 0.1,
"use_discriminator": false,
"dis_ratio": 1.0,
"weight_sharing": true,
"pos_trainable": true,
"two_layer_predictor": false,
"bidirectional_context": true,
"label_smooth": 0.0,
"initializer_range": 0.02,
"lr": 5e-05,
"weight_decay": 0.0,
"max_grad_norm": null
},
"Generator": {
"generator": "BeamSearch",
"min_gen_len": 1,
"max_gen_len": 30,
"beam_size": 5,
"length_average": false,
"length_penalty": -1.0,
"ignore_unk": true
}
}
{
"do_train": false,
"do_test": false,
"do_infer": true,
"num_infer_batches": null,
"hparams_file": null,
"BPETextField": {
"vocab_path": "model/Bert/vocab.txt",
"filtered": false,
"max_len": 256,
"min_utt_len": 1,
"max_utt_len": 50,
"min_ctx_turn": 1,
"max_ctx_turn": 16,
"max_knowledge_num": 16,
"max_knowledge_len": 16,
"tokenizer_type": "Bert"
},
"Dataset": {
"data_dir": "data/DDE_Dialog",
"data_type": "multi_knowledge"
},
"Trainer": {
"use_data_distributed": false,
"valid_metric_name": "-loss",
"num_epochs": 10,
"save_dir": "outputs/DDE.infer",
"batch_size": 1,
"log_steps": 100,
"valid_steps": 2000,
"save_checkpoint": true,
"save_summary": false,
"shuffle": true,
"sort_pool_size": 0
},
"Model": {
"init_checkpoint": "outputs/DDE_Dialog/best.model",
"model": "UnifiedTransformer",
"num_token_embeddings": -1,
"num_pos_embeddings": 512,
"num_type_embeddings": 3,
"num_turn_embeddings": 16,
"num_latent": 20,
"tau": 0.67,
"with_bow": true,
"hidden_dim": 768,
"num_heads": 12,
"num_layers": 12,
"padding_idx": 0,
"dropout": 0.1,
"embed_dropout": 0.0,
"attn_dropout": 0.1,
"ff_dropout": 0.1,
"use_discriminator": true,
"dis_ratio": 1.0,
"weight_sharing": true,
"pos_trainable": true,
"two_layer_predictor": false,
"bidirectional_context": true,
"label_smooth": 0.0,
"initializer_range": 0.02,
"lr": 5e-05,
"weight_decay": 0.0,
"max_grad_norm": null
},
"Generator": {
"generator": "BeamSearch",
"min_gen_len": 1,
"max_gen_len": 30,
"beam_size": 5,
"length_average": false,
"length_penalty": -1.0,
"ignore_unk": true
}
}