dirkgr commited on
Commit
81ea232
1 Parent(s): a41cda0

Update repository

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.th filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - allennlp
4
+ ---
5
+
6
+ # TODO: Fill this model card
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dataset_reader": {
3
+ "type": "squad",
4
+ "token_indexers": {
5
+ "token_characters": {
6
+ "type": "characters",
7
+ "character_tokenizer": {
8
+ "byte_encoding": "utf-8",
9
+ "end_tokens": [
10
+ 260
11
+ ],
12
+ "start_tokens": [
13
+ 259
14
+ ]
15
+ },
16
+ "min_padding_length": 5
17
+ },
18
+ "tokens": {
19
+ "type": "single_id",
20
+ "lowercase_tokens": true
21
+ }
22
+ }
23
+ },
24
+ "model": {
25
+ "type": "bidaf",
26
+ "dropout": 0.2,
27
+ "matrix_attention": {
28
+ "type": "linear",
29
+ "combination": "x,y,x*y",
30
+ "tensor_1_dim": 200,
31
+ "tensor_2_dim": 200
32
+ },
33
+ "modeling_layer": {
34
+ "type": "lstm",
35
+ "bidirectional": true,
36
+ "dropout": 0.2,
37
+ "hidden_size": 100,
38
+ "input_size": 800,
39
+ "num_layers": 2
40
+ },
41
+ "num_highway_layers": 2,
42
+ "phrase_layer": {
43
+ "type": "lstm",
44
+ "bidirectional": true,
45
+ "hidden_size": 100,
46
+ "input_size": 200,
47
+ "num_layers": 1
48
+ },
49
+ "span_end_encoder": {
50
+ "type": "lstm",
51
+ "bidirectional": true,
52
+ "hidden_size": 100,
53
+ "input_size": 1400,
54
+ "num_layers": 1
55
+ },
56
+ "text_field_embedder": {
57
+ "token_embedders": {
58
+ "token_characters": {
59
+ "type": "character_encoding",
60
+ "dropout": 0.2,
61
+ "embedding": {
62
+ "embedding_dim": 16,
63
+ "num_embeddings": 262
64
+ },
65
+ "encoder": {
66
+ "type": "cnn",
67
+ "embedding_dim": 16,
68
+ "ngram_filter_sizes": [
69
+ 5
70
+ ],
71
+ "num_filters": 100
72
+ }
73
+ },
74
+ "tokens": {
75
+ "type": "embedding",
76
+ "embedding_dim": 100,
77
+ "pretrained_file": "https://allennlp.s3.amazonaws.com/datasets/glove/glove.6B.100d.txt.gz",
78
+ "trainable": false
79
+ }
80
+ }
81
+ }
82
+ },
83
+ "train_data_path": "https://allennlp.s3.amazonaws.com/datasets/squad/squad-train-v1.1.json",
84
+ "validation_data_path": "https://allennlp.s3.amazonaws.com/datasets/squad/squad-dev-v1.1.json",
85
+ "trainer": {
86
+ "grad_norm": 5,
87
+ "learning_rate_scheduler": {
88
+ "type": "reduce_on_plateau",
89
+ "factor": 0.5,
90
+ "mode": "max",
91
+ "patience": 2
92
+ },
93
+ "num_epochs": 20,
94
+ "optimizer": {
95
+ "type": "adam",
96
+ "betas": [
97
+ 0.9,
98
+ 0.9
99
+ ]
100
+ },
101
+ "patience": 10,
102
+ "validation_metric": "+em"
103
+ },
104
+ "data_loader": {
105
+ "batch_sampler": {
106
+ "type": "bucket",
107
+ "batch_size": 40
108
+ }
109
+ }
110
+ }
metrics.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_epoch": 6,
3
+ "peak_worker_0_memory_MB": 10198.55859375,
4
+ "peak_gpu_0_memory_MB": 2483.1318359375,
5
+ "training_duration": "1:05:21.359214",
6
+ "epoch": 16,
7
+ "training_start_acc": 0.8171212000136988,
8
+ "training_end_acc": 0.8648158083996392,
9
+ "training_span_acc": 0.7419034463863743,
10
+ "training_em": 0.7959451591913149,
11
+ "training_f1": 0.9018048409974154,
12
+ "training_loss": 0.9448039527761337,
13
+ "training_worker_0_memory_MB": 10198.55859375,
14
+ "training_gpu_0_memory_MB": 2474.52490234375,
15
+ "validation_start_acc": 0.6181646168401135,
16
+ "validation_end_acc": 0.6535477767265847,
17
+ "validation_span_acc": 0.5310312204351939,
18
+ "validation_em": 0.661116367076632,
19
+ "validation_f1": 0.7646617261058106,
20
+ "validation_loss": 3.421157140551873,
21
+ "best_validation_start_acc": 0.6307473982970672,
22
+ "best_validation_end_acc": 0.6674550614947966,
23
+ "best_validation_span_acc": 0.5439924314096499,
24
+ "best_validation_em": 0.6747398297067171,
25
+ "best_validation_f1": 0.7706741501743936,
26
+ "best_validation_loss": 2.50613601477641
27
+ }
model.th ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b1ef8c68f1840c7a458358782ce8e4359552e8cb358c6856a3dffd8c5b9ff2
3
+ size 49008050
vocabulary/.lock ADDED
File without changes
vocabulary/non_padded_namespaces.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ *labels
2
+ *tags
vocabulary/tokens.txt ADDED
The diff for this file is too large to render. See raw diff