Buseak commited on
Commit
5b15ef9
1 Parent(s): 6be14e2

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/canine-s",
3
+ "architectures": [
4
+ "CanineForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 57344,
8
+ "downsampling_rate": 4,
9
+ "eos_token_id": 57345,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "1",
15
+ "1": "9",
16
+ "2": "3",
17
+ "3": "6",
18
+ "4": " ",
19
+ "5": "y",
20
+ "6": "l",
21
+ "7": "\u0131",
22
+ "8": "n",
23
+ "9": "d",
24
+ "10": "a",
25
+ "11": "z",
26
+ "12": ".",
27
+ "13": "\u00df",
28
+ "14": "NaN",
29
+ "15": "A",
30
+ "16": "e",
31
+ "17": "t",
32
+ "18": "k",
33
+ "19": "i",
34
+ "20": "m",
35
+ "21": "g",
36
+ "22": "\u015f",
37
+ "23": "b",
38
+ "24": "r",
39
+ "25": "h",
40
+ "26": "\u00e7",
41
+ "27": "O",
42
+ "28": "s",
43
+ "29": "u",
44
+ "30": "\u011f",
45
+ "31": "o",
46
+ "32": "\u00f6",
47
+ "33": "\u00fc",
48
+ "34": "v",
49
+ "35": "R",
50
+ "36": ",",
51
+ "37": "B",
52
+ "38": "'",
53
+ "39": "p",
54
+ "40": "\u00e2",
55
+ "41": "\u00d6",
56
+ "42": "S",
57
+ "43": "-",
58
+ "44": "L",
59
+ "45": "c",
60
+ "46": "T",
61
+ "47": "w",
62
+ "48": "K",
63
+ "49": "0",
64
+ "50": "P",
65
+ "51": "?",
66
+ "52": "M",
67
+ "53": "f",
68
+ "54": "Y",
69
+ "55": "7",
70
+ "56": "8",
71
+ "57": "U",
72
+ "58": "\"",
73
+ "59": "5",
74
+ "60": "N",
75
+ "61": "j",
76
+ "62": "H",
77
+ "63": "2",
78
+ "64": "\u0130",
79
+ "65": "D",
80
+ "66": "G",
81
+ "67": "I",
82
+ "68": "C",
83
+ "69": "F",
84
+ "70": "\u00c7",
85
+ "71": ";",
86
+ "72": "x",
87
+ "73": "E",
88
+ "74": "(",
89
+ "75": ")",
90
+ "76": "4",
91
+ "77": "\u00dc",
92
+ "78": "!",
93
+ "79": "J",
94
+ "80": "V",
95
+ "81": "\u015e",
96
+ "82": ":",
97
+ "83": "Z",
98
+ "84": "W",
99
+ "85": "*",
100
+ "86": "/",
101
+ "87": "%",
102
+ "88": "|",
103
+ "89": "\u011e",
104
+ "90": "q",
105
+ "91": "\u00fb",
106
+ "92": "\u201c",
107
+ "93": "\u25a0",
108
+ "94": "\u00e8",
109
+ "95": "\u201d",
110
+ "96": "\u2019",
111
+ "97": "Q",
112
+ "98": "\u00c2",
113
+ "99": "X",
114
+ "100": "+",
115
+ "101": "=",
116
+ "102": "\u00e9",
117
+ "103": "\u00ce",
118
+ "104": "\u2014",
119
+ "105": ">"
120
+ },
121
+ "initializer_range": 0.02,
122
+ "intermediate_size": 3072,
123
+ "label2id": {
124
+ " ": 4,
125
+ "!": 78,
126
+ "\"": 58,
127
+ "%": 87,
128
+ "'": 38,
129
+ "(": 74,
130
+ ")": 75,
131
+ "*": 85,
132
+ "+": 100,
133
+ ",": 36,
134
+ "-": 43,
135
+ ".": 12,
136
+ "/": 86,
137
+ "0": 49,
138
+ "1": 0,
139
+ "2": 63,
140
+ "3": 2,
141
+ "4": 76,
142
+ "5": 59,
143
+ "6": 3,
144
+ "7": 55,
145
+ "8": 56,
146
+ "9": 1,
147
+ ":": 82,
148
+ ";": 71,
149
+ "=": 101,
150
+ ">": 105,
151
+ "?": 51,
152
+ "A": 15,
153
+ "B": 37,
154
+ "C": 68,
155
+ "D": 65,
156
+ "E": 73,
157
+ "F": 69,
158
+ "G": 66,
159
+ "H": 62,
160
+ "I": 67,
161
+ "J": 79,
162
+ "K": 48,
163
+ "L": 44,
164
+ "M": 52,
165
+ "N": 60,
166
+ "NaN": 14,
167
+ "O": 27,
168
+ "P": 50,
169
+ "Q": 97,
170
+ "R": 35,
171
+ "S": 42,
172
+ "T": 46,
173
+ "U": 57,
174
+ "V": 80,
175
+ "W": 84,
176
+ "X": 99,
177
+ "Y": 54,
178
+ "Z": 83,
179
+ "a": 10,
180
+ "b": 23,
181
+ "c": 45,
182
+ "d": 9,
183
+ "e": 16,
184
+ "f": 53,
185
+ "g": 21,
186
+ "h": 25,
187
+ "i": 19,
188
+ "j": 61,
189
+ "k": 18,
190
+ "l": 6,
191
+ "m": 20,
192
+ "n": 8,
193
+ "o": 31,
194
+ "p": 39,
195
+ "q": 90,
196
+ "r": 24,
197
+ "s": 28,
198
+ "t": 17,
199
+ "u": 29,
200
+ "v": 34,
201
+ "w": 47,
202
+ "x": 72,
203
+ "y": 5,
204
+ "z": 11,
205
+ "|": 88,
206
+ "\u00c2": 98,
207
+ "\u00c7": 70,
208
+ "\u00ce": 103,
209
+ "\u00d6": 41,
210
+ "\u00dc": 77,
211
+ "\u00df": 13,
212
+ "\u00e2": 40,
213
+ "\u00e7": 26,
214
+ "\u00e8": 94,
215
+ "\u00e9": 102,
216
+ "\u00f6": 32,
217
+ "\u00fb": 91,
218
+ "\u00fc": 33,
219
+ "\u011e": 89,
220
+ "\u011f": 30,
221
+ "\u0130": 64,
222
+ "\u0131": 7,
223
+ "\u015e": 81,
224
+ "\u015f": 22,
225
+ "\u2014": 104,
226
+ "\u2019": 96,
227
+ "\u201c": 92,
228
+ "\u201d": 95,
229
+ "\u25a0": 93
230
+ },
231
+ "layer_norm_eps": 1e-12,
232
+ "local_transformer_stride": 128,
233
+ "max_position_embeddings": 16384,
234
+ "model_type": "canine",
235
+ "num_attention_heads": 12,
236
+ "num_hash_buckets": 16384,
237
+ "num_hash_functions": 8,
238
+ "num_hidden_layers": 12,
239
+ "pad_token_id": 0,
240
+ "torch_dtype": "float32",
241
+ "transformers_version": "4.28.0",
242
+ "type_vocab_size": 16,
243
+ "upsampling_kernel_size": 4,
244
+ "use_cache": true
245
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4b89e36291ac579a37c6bd2dfac2d01ac409e3640fb5b43ee676125466b9e8
3
+ size 528875054
runs/Oct31_19-39-46_ac7fc66b7409/1698781191.5681503/events.out.tfevents.1698781191.ac7fc66b7409.18781.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2dfcbcbdb24644281b340680a6d6b10abb36891c6a900fd5389830904e0a619
3
+ size 5891
runs/Oct31_19-39-46_ac7fc66b7409/events.out.tfevents.1698781191.ac7fc66b7409.18781.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40415cf10d997b4e89dc18ac21d518220c26d84fa979b2059b230690bf6e249
3
+ size 8262
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "\u0000",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 2048,
37
+ "pad_token": {
38
+ "__type": "AddedToken",
39
+ "content": "\u0000",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "sep_token": {
46
+ "__type": "AddedToken",
47
+ "content": "",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "tokenizer_class": "CanineTokenizer"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e836bd6c3bbbe3be267785040846ea748ad4781091b09864995ce9809f364a9
3
+ size 4024