stepanom commited on
Commit
8ea9467
1 Parent(s): ea82139

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "date",
16
+ "10": "coffee_type",
17
+ "11": "time",
18
+ "12": "music_album",
19
+ "13": "radio_name",
20
+ "14": "game_type",
21
+ "15": "business_name",
22
+ "16": "relation",
23
+ "17": "time_zone",
24
+ "18": "sport_type",
25
+ "19": "audiobook_name",
26
+ "2": "meal_type",
27
+ "20": "movie_name",
28
+ "21": "podcast_descriptor",
29
+ "22": "media_type",
30
+ "23": "playlist_name",
31
+ "24": "device_type",
32
+ "25": "podcast_name",
33
+ "26": "music_genre",
34
+ "27": "person",
35
+ "28": "place_name",
36
+ "29": "house_place",
37
+ "3": "alarm_type",
38
+ "30": "definition_word",
39
+ "31": "timeofday",
40
+ "32": "food_type",
41
+ "33": "player_setting",
42
+ "34": "email_folder",
43
+ "35": "transport_type",
44
+ "36": "event_name",
45
+ "37": "transport_agency",
46
+ "38": "transport_name",
47
+ "39": "cooking_type",
48
+ "4": "song_name",
49
+ "40": "personal_info",
50
+ "41": "business_type",
51
+ "42": "general_frequency",
52
+ "43": "app_name",
53
+ "44": "color_type",
54
+ "45": "music_descriptor",
55
+ "46": "order_type",
56
+ "47": "weather_descriptor",
57
+ "48": "drink_type",
58
+ "49": "ingredient",
59
+ "5": "audiobook_author",
60
+ "50": "email_address",
61
+ "51": "movie_type",
62
+ "52": "game_name",
63
+ "53": "joke_type",
64
+ "54": "change_amount",
65
+ "55": "transport_descriptor",
66
+ "6": "news_topic",
67
+ "7": "list_name",
68
+ "8": "currency_name",
69
+ "9": "artist_name"
70
+ },
71
+ "initializer_range": 0.02,
72
+ "intermediate_size": 3072,
73
+ "label2id": {
74
+ "O": "0",
75
+ "alarm_type": "3",
76
+ "app_name": "43",
77
+ "artist_name": "9",
78
+ "audiobook_author": "5",
79
+ "audiobook_name": "19",
80
+ "business_name": "15",
81
+ "business_type": "41",
82
+ "change_amount": "54",
83
+ "coffee_type": "10",
84
+ "color_type": "44",
85
+ "cooking_type": "39",
86
+ "currency_name": "8",
87
+ "date": "1",
88
+ "definition_word": "30",
89
+ "device_type": "24",
90
+ "drink_type": "48",
91
+ "email_address": "50",
92
+ "email_folder": "34",
93
+ "event_name": "36",
94
+ "food_type": "32",
95
+ "game_name": "52",
96
+ "game_type": "14",
97
+ "general_frequency": "42",
98
+ "house_place": "29",
99
+ "ingredient": "49",
100
+ "joke_type": "53",
101
+ "list_name": "7",
102
+ "meal_type": "2",
103
+ "media_type": "22",
104
+ "movie_name": "20",
105
+ "movie_type": "51",
106
+ "music_album": "12",
107
+ "music_descriptor": "45",
108
+ "music_genre": "26",
109
+ "news_topic": "6",
110
+ "order_type": "46",
111
+ "person": "27",
112
+ "personal_info": "40",
113
+ "place_name": "28",
114
+ "player_setting": "33",
115
+ "playlist_name": "23",
116
+ "podcast_descriptor": "21",
117
+ "podcast_name": "25",
118
+ "radio_name": "13",
119
+ "relation": "16",
120
+ "song_name": "4",
121
+ "sport_type": "18",
122
+ "time": "11",
123
+ "time_zone": "17",
124
+ "timeofday": "31",
125
+ "transport_agency": "37",
126
+ "transport_descriptor": "55",
127
+ "transport_name": "38",
128
+ "transport_type": "35",
129
+ "weather_descriptor": "47"
130
+ },
131
+ "layer_norm_eps": 1e-05,
132
+ "max_position_embeddings": 514,
133
+ "model_type": "xlm-roberta",
134
+ "num_attention_heads": 12,
135
+ "num_hidden_layers": 12,
136
+ "output_past": true,
137
+ "pad_token_id": 1,
138
+ "position_embedding_type": "absolute",
139
+ "torch_dtype": "float32",
140
+ "transformers_version": "4.41.0",
141
+ "type_vocab_size": 1,
142
+ "use_cache": true,
143
+ "vocab_size": 250002
144
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b352b7be4244d54926926166d7bad400ad2a34389bf6922566c8bb4fe1ec8a4a
3
+ size 1110008536
runs/May24_10-30-18_b37c2f13a272/events.out.tfevents.1716546642.b37c2f13a272.567.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46677f85809cd3a125f1682cbde23aa73913530f216bd4b43271053dc8a05d6
3
+ size 8434
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
3
+ size 17082832
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bfdee26ed7a4f61acd970cff9bf5062639fa3d3155584e58b842247ec7271b
3
+ size 5176