haophancs commited on
Commit
45f88c2
1 Parent(s): 11ea500

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "uclanlp/visualbert-vqa",
3
+ "architectures": [
4
+ "VisualBertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "bypass_transformer": false,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1,
37
+ "LABEL_10": 10,
38
+ "LABEL_11": 11,
39
+ "LABEL_12": 12,
40
+ "LABEL_13": 13,
41
+ "LABEL_14": 14,
42
+ "LABEL_15": 15,
43
+ "LABEL_16": 16,
44
+ "LABEL_2": 2,
45
+ "LABEL_3": 3,
46
+ "LABEL_4": 4,
47
+ "LABEL_5": 5,
48
+ "LABEL_6": 6,
49
+ "LABEL_7": 7,
50
+ "LABEL_8": 8,
51
+ "LABEL_9": 9
52
+ },
53
+ "layer_norm_eps": 1e-12,
54
+ "max_position_embeddings": 512,
55
+ "model_type": "visual_bert",
56
+ "num_attention_heads": 12,
57
+ "num_hidden_layers": 12,
58
+ "pad_token_id": 1,
59
+ "special_visual_initialize": true,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.41.2",
62
+ "type_vocab_size": 2,
63
+ "visual_embedding_dim": 2048,
64
+ "vocab_size": 64000
65
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a56eae549d869361544ed8bc074d9d4e9733b7ace995886d9166543ebeeed1bf
3
+ size 548724596
test/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fb51f79c52aea1833b31f62fd1daf5739f3c32146d3c6251649cbdba94b0687
3
+ size 8218416
test/dataset_info.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "parquet",
3
+ "citation": "",
4
+ "config_name": "default",
5
+ "dataset_name": "viclevr-no-images",
6
+ "dataset_size": 4949863,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "hf://datasets/haophancs/viclevr-no-images@b0ff9ce3dbd9bfe6a51418bff9d0cf6e0d040407/data/train-00000-of-00001.parquet": {
10
+ "num_bytes": 1021585,
11
+ "checksum": null
12
+ },
13
+ "hf://datasets/haophancs/viclevr-no-images@b0ff9ce3dbd9bfe6a51418bff9d0cf6e0d040407/data/val-00000-of-00001.parquet": {
14
+ "num_bytes": 316193,
15
+ "checksum": null
16
+ },
17
+ "hf://datasets/haophancs/viclevr-no-images@b0ff9ce3dbd9bfe6a51418bff9d0cf6e0d040407/data/test-00000-of-00001.parquet": {
18
+ "num_bytes": 157886,
19
+ "checksum": null
20
+ }
21
+ },
22
+ "download_size": 1495664,
23
+ "features": {
24
+ "input_ids": {
25
+ "feature": {
26
+ "dtype": "int32",
27
+ "_type": "Value"
28
+ },
29
+ "_type": "Sequence"
30
+ },
31
+ "token_type_ids": {
32
+ "feature": {
33
+ "dtype": "int8",
34
+ "_type": "Value"
35
+ },
36
+ "_type": "Sequence"
37
+ },
38
+ "attention_mask": {
39
+ "feature": {
40
+ "dtype": "int8",
41
+ "_type": "Value"
42
+ },
43
+ "_type": "Sequence"
44
+ },
45
+ "visual_embeds": {
46
+ "feature": {
47
+ "feature": {
48
+ "dtype": "float32",
49
+ "_type": "Value"
50
+ },
51
+ "_type": "Sequence"
52
+ },
53
+ "_type": "Sequence"
54
+ },
55
+ "visual_token_type_ids": {
56
+ "feature": {
57
+ "dtype": "int64",
58
+ "_type": "Value"
59
+ },
60
+ "_type": "Sequence"
61
+ },
62
+ "visual_attention_mask": {
63
+ "feature": {
64
+ "dtype": "float32",
65
+ "_type": "Value"
66
+ },
67
+ "_type": "Sequence"
68
+ },
69
+ "labels": {
70
+ "feature": {
71
+ "dtype": "float32",
72
+ "_type": "Value"
73
+ },
74
+ "_type": "Sequence"
75
+ }
76
+ },
77
+ "homepage": "",
78
+ "license": "",
79
+ "size_in_bytes": 6445527,
80
+ "splits": {
81
+ "train": {
82
+ "name": "train",
83
+ "num_bytes": 3386001,
84
+ "num_examples": 21000,
85
+ "dataset_name": "viclevr-no-images"
86
+ },
87
+ "val": {
88
+ "name": "val",
89
+ "num_bytes": 1041768,
90
+ "num_examples": 6000,
91
+ "dataset_name": "viclevr-no-images"
92
+ },
93
+ "test": {
94
+ "name": "test",
95
+ "num_bytes": 522094,
96
+ "num_examples": 3000,
97
+ "dataset_name": "viclevr-no-images"
98
+ }
99
+ },
100
+ "version": {
101
+ "version_str": "0.0.0",
102
+ "major": 0,
103
+ "minor": 0,
104
+ "patch": 0
105
+ }
106
+ }
test/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "7e66b10c2f38c4ec",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": "torch",
11
+ "_output_all_columns": false,
12
+ "_split": "test[:20]"
13
+ }
train/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e59012533716e39e1a1444645d8b0be2fe3f66c6d0068821ead99e63f829398
3
+ size 8218416
train/dataset_info.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "parquet",
3
+ "citation": "",
4
+ "config_name": "default",
5
+ "dataset_name": "viclevr-no-images",
6
+ "dataset_size": 4949863,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "hf://datasets/haophancs/viclevr-no-images@b0ff9ce3dbd9bfe6a51418bff9d0cf6e0d040407/data/train-00000-of-00001.parquet": {
10
+ "num_bytes": 1021585,
11
+ "checksum": null
12
+ },
13
+ "hf://datasets/haophancs/viclevr-no-images@b0ff9ce3dbd9bfe6a51418bff9d0cf6e0d040407/data/val-00000-of-00001.parquet": {
14
+ "num_bytes": 316193,
15
+ "checksum": null
16
+ },
17
+ "hf://datasets/haophancs/viclevr-no-images@b0ff9ce3dbd9bfe6a51418bff9d0cf6e0d040407/data/test-00000-of-00001.parquet": {
18
+ "num_bytes": 157886,
19
+ "checksum": null
20
+ }
21
+ },
22
+ "download_size": 1495664,
23
+ "features": {
24
+ "input_ids": {
25
+ "feature": {
26
+ "dtype": "int32",
27
+ "_type": "Value"
28
+ },
29
+ "_type": "Sequence"
30
+ },
31
+ "token_type_ids": {
32
+ "feature": {
33
+ "dtype": "int8",
34
+ "_type": "Value"
35
+ },
36
+ "_type": "Sequence"
37
+ },
38
+ "attention_mask": {
39
+ "feature": {
40
+ "dtype": "int8",
41
+ "_type": "Value"
42
+ },
43
+ "_type": "Sequence"
44
+ },
45
+ "visual_embeds": {
46
+ "feature": {
47
+ "feature": {
48
+ "dtype": "float32",
49
+ "_type": "Value"
50
+ },
51
+ "_type": "Sequence"
52
+ },
53
+ "_type": "Sequence"
54
+ },
55
+ "visual_token_type_ids": {
56
+ "feature": {
57
+ "dtype": "int64",
58
+ "_type": "Value"
59
+ },
60
+ "_type": "Sequence"
61
+ },
62
+ "visual_attention_mask": {
63
+ "feature": {
64
+ "dtype": "float32",
65
+ "_type": "Value"
66
+ },
67
+ "_type": "Sequence"
68
+ },
69
+ "labels": {
70
+ "feature": {
71
+ "dtype": "float32",
72
+ "_type": "Value"
73
+ },
74
+ "_type": "Sequence"
75
+ }
76
+ },
77
+ "homepage": "",
78
+ "license": "",
79
+ "size_in_bytes": 6445527,
80
+ "splits": {
81
+ "train": {
82
+ "name": "train",
83
+ "num_bytes": 3386001,
84
+ "num_examples": 21000,
85
+ "dataset_name": "viclevr-no-images"
86
+ },
87
+ "val": {
88
+ "name": "val",
89
+ "num_bytes": 1041768,
90
+ "num_examples": 6000,
91
+ "dataset_name": "viclevr-no-images"
92
+ },
93
+ "test": {
94
+ "name": "test",
95
+ "num_bytes": 522094,
96
+ "num_examples": 3000,
97
+ "dataset_name": "viclevr-no-images"
98
+ }
99
+ },
100
+ "version": {
101
+ "version_str": "0.0.0",
102
+ "major": 0,
103
+ "minor": 0,
104
+ "patch": 0
105
+ }
106
+ }
train/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "962afac895328b8e",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": "torch",
11
+ "_output_all_columns": false,
12
+ "_split": "train[:20]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:848534c2b49cfdcdd72fa793cb49f11ff457ad46c49e8ab7e2cc5c8569eab875
3
+ size 5176
val/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c62269db13c046592afdd7a9db7991dfd170fdc8a81cd1749edc97ea953f778b
3
+ size 8218416
val/dataset_info.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "parquet",
3
+ "citation": "",
4
+ "config_name": "default",
5
+ "dataset_name": "viclevr-no-images",
6
+ "dataset_size": 4949863,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "hf://datasets/haophancs/viclevr-no-images@b0ff9ce3dbd9bfe6a51418bff9d0cf6e0d040407/data/train-00000-of-00001.parquet": {
10
+ "num_bytes": 1021585,
11
+ "checksum": null
12
+ },
13
+ "hf://datasets/haophancs/viclevr-no-images@b0ff9ce3dbd9bfe6a51418bff9d0cf6e0d040407/data/val-00000-of-00001.parquet": {
14
+ "num_bytes": 316193,
15
+ "checksum": null
16
+ },
17
+ "hf://datasets/haophancs/viclevr-no-images@b0ff9ce3dbd9bfe6a51418bff9d0cf6e0d040407/data/test-00000-of-00001.parquet": {
18
+ "num_bytes": 157886,
19
+ "checksum": null
20
+ }
21
+ },
22
+ "download_size": 1495664,
23
+ "features": {
24
+ "input_ids": {
25
+ "feature": {
26
+ "dtype": "int32",
27
+ "_type": "Value"
28
+ },
29
+ "_type": "Sequence"
30
+ },
31
+ "token_type_ids": {
32
+ "feature": {
33
+ "dtype": "int8",
34
+ "_type": "Value"
35
+ },
36
+ "_type": "Sequence"
37
+ },
38
+ "attention_mask": {
39
+ "feature": {
40
+ "dtype": "int8",
41
+ "_type": "Value"
42
+ },
43
+ "_type": "Sequence"
44
+ },
45
+ "visual_embeds": {
46
+ "feature": {
47
+ "feature": {
48
+ "dtype": "float32",
49
+ "_type": "Value"
50
+ },
51
+ "_type": "Sequence"
52
+ },
53
+ "_type": "Sequence"
54
+ },
55
+ "visual_token_type_ids": {
56
+ "feature": {
57
+ "dtype": "int64",
58
+ "_type": "Value"
59
+ },
60
+ "_type": "Sequence"
61
+ },
62
+ "visual_attention_mask": {
63
+ "feature": {
64
+ "dtype": "float32",
65
+ "_type": "Value"
66
+ },
67
+ "_type": "Sequence"
68
+ },
69
+ "labels": {
70
+ "feature": {
71
+ "dtype": "float32",
72
+ "_type": "Value"
73
+ },
74
+ "_type": "Sequence"
75
+ }
76
+ },
77
+ "homepage": "",
78
+ "license": "",
79
+ "size_in_bytes": 6445527,
80
+ "splits": {
81
+ "train": {
82
+ "name": "train",
83
+ "num_bytes": 3386001,
84
+ "num_examples": 21000,
85
+ "dataset_name": "viclevr-no-images"
86
+ },
87
+ "val": {
88
+ "name": "val",
89
+ "num_bytes": 1041768,
90
+ "num_examples": 6000,
91
+ "dataset_name": "viclevr-no-images"
92
+ },
93
+ "test": {
94
+ "name": "test",
95
+ "num_bytes": 522094,
96
+ "num_examples": 3000,
97
+ "dataset_name": "viclevr-no-images"
98
+ }
99
+ },
100
+ "version": {
101
+ "version_str": "0.0.0",
102
+ "major": 0,
103
+ "minor": 0,
104
+ "patch": 0
105
+ }
106
+ }
val/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "066aaea996993023",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": "torch",
11
+ "_output_all_columns": false,
12
+ "_split": "val[:20]"
13
+ }