nickprock commited on
Commit
74bf9d4
1 Parent(s): f6bce98

Training in progress, step 500

Browse files
.gitattributes CHANGED
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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": "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
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27",
42
+ "28": "LABEL_28",
43
+ "29": "LABEL_29",
44
+ "30": "LABEL_30",
45
+ "31": "LABEL_31",
46
+ "32": "LABEL_32",
47
+ "33": "LABEL_33",
48
+ "34": "LABEL_34",
49
+ "35": "LABEL_35",
50
+ "36": "LABEL_36",
51
+ "37": "LABEL_37",
52
+ "38": "LABEL_38",
53
+ "39": "LABEL_39",
54
+ "40": "LABEL_40",
55
+ "41": "LABEL_41",
56
+ "42": "LABEL_42",
57
+ "43": "LABEL_43",
58
+ "44": "LABEL_44",
59
+ "45": "LABEL_45",
60
+ "46": "LABEL_46",
61
+ "47": "LABEL_47",
62
+ "48": "LABEL_48",
63
+ "49": "LABEL_49",
64
+ "50": "LABEL_50",
65
+ "51": "LABEL_51",
66
+ "52": "LABEL_52",
67
+ "53": "LABEL_53",
68
+ "54": "LABEL_54",
69
+ "55": "LABEL_55",
70
+ "56": "LABEL_56",
71
+ "57": "LABEL_57",
72
+ "58": "LABEL_58",
73
+ "59": "LABEL_59",
74
+ "60": "LABEL_60",
75
+ "61": "LABEL_61",
76
+ "62": "LABEL_62",
77
+ "63": "LABEL_63",
78
+ "64": "LABEL_64",
79
+ "65": "LABEL_65",
80
+ "66": "LABEL_66",
81
+ "67": "LABEL_67",
82
+ "68": "LABEL_68",
83
+ "69": "LABEL_69",
84
+ "70": "LABEL_70",
85
+ "71": "LABEL_71",
86
+ "72": "LABEL_72",
87
+ "73": "LABEL_73",
88
+ "74": "LABEL_74",
89
+ "75": "LABEL_75",
90
+ "76": "LABEL_76"
91
+ },
92
+ "initializer_range": 0.02,
93
+ "intermediate_size": 3072,
94
+ "label2id": {
95
+ "LABEL_0": 0,
96
+ "LABEL_1": 1,
97
+ "LABEL_10": 10,
98
+ "LABEL_11": 11,
99
+ "LABEL_12": 12,
100
+ "LABEL_13": 13,
101
+ "LABEL_14": 14,
102
+ "LABEL_15": 15,
103
+ "LABEL_16": 16,
104
+ "LABEL_17": 17,
105
+ "LABEL_18": 18,
106
+ "LABEL_19": 19,
107
+ "LABEL_2": 2,
108
+ "LABEL_20": 20,
109
+ "LABEL_21": 21,
110
+ "LABEL_22": 22,
111
+ "LABEL_23": 23,
112
+ "LABEL_24": 24,
113
+ "LABEL_25": 25,
114
+ "LABEL_26": 26,
115
+ "LABEL_27": 27,
116
+ "LABEL_28": 28,
117
+ "LABEL_29": 29,
118
+ "LABEL_3": 3,
119
+ "LABEL_30": 30,
120
+ "LABEL_31": 31,
121
+ "LABEL_32": 32,
122
+ "LABEL_33": 33,
123
+ "LABEL_34": 34,
124
+ "LABEL_35": 35,
125
+ "LABEL_36": 36,
126
+ "LABEL_37": 37,
127
+ "LABEL_38": 38,
128
+ "LABEL_39": 39,
129
+ "LABEL_4": 4,
130
+ "LABEL_40": 40,
131
+ "LABEL_41": 41,
132
+ "LABEL_42": 42,
133
+ "LABEL_43": 43,
134
+ "LABEL_44": 44,
135
+ "LABEL_45": 45,
136
+ "LABEL_46": 46,
137
+ "LABEL_47": 47,
138
+ "LABEL_48": 48,
139
+ "LABEL_49": 49,
140
+ "LABEL_5": 5,
141
+ "LABEL_50": 50,
142
+ "LABEL_51": 51,
143
+ "LABEL_52": 52,
144
+ "LABEL_53": 53,
145
+ "LABEL_54": 54,
146
+ "LABEL_55": 55,
147
+ "LABEL_56": 56,
148
+ "LABEL_57": 57,
149
+ "LABEL_58": 58,
150
+ "LABEL_59": 59,
151
+ "LABEL_6": 6,
152
+ "LABEL_60": 60,
153
+ "LABEL_61": 61,
154
+ "LABEL_62": 62,
155
+ "LABEL_63": 63,
156
+ "LABEL_64": 64,
157
+ "LABEL_65": 65,
158
+ "LABEL_66": 66,
159
+ "LABEL_67": 67,
160
+ "LABEL_68": 68,
161
+ "LABEL_69": 69,
162
+ "LABEL_7": 7,
163
+ "LABEL_70": 70,
164
+ "LABEL_71": 71,
165
+ "LABEL_72": 72,
166
+ "LABEL_73": 73,
167
+ "LABEL_74": 74,
168
+ "LABEL_75": 75,
169
+ "LABEL_76": 76,
170
+ "LABEL_8": 8,
171
+ "LABEL_9": 9
172
+ },
173
+ "layer_norm_eps": 1e-05,
174
+ "max_position_embeddings": 514,
175
+ "model_type": "xlm-roberta",
176
+ "num_attention_heads": 12,
177
+ "num_hidden_layers": 12,
178
+ "output_past": true,
179
+ "pad_token_id": 1,
180
+ "position_embedding_type": "absolute",
181
+ "problem_type": "single_label_classification",
182
+ "torch_dtype": "float32",
183
+ "transformers_version": "4.21.1",
184
+ "type_vocab_size": 1,
185
+ "use_cache": true,
186
+ "vocab_size": 250002
187
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689eae74473d3dc5c5114db7169c9194d0123d71e51f0d2bb04bf9efdcaf20bd
3
+ size 1112483053
runs/Aug16_13-06-09_b30c7cdb59e9/1660655201.3348172/events.out.tfevents.1660655201.b30c7cdb59e9.70.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e4ae4e1c64ff44e7e8e9a0bb543dc1b77071b998733a7304fbdd7c1e36c4390
3
+ size 5478
runs/Aug16_13-06-09_b30c7cdb59e9/events.out.tfevents.1660655201.b30c7cdb59e9.70.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e0ee74d48f18fd96478dbf198f0bc1ff3fcd15192458e5f3e656fde2d4d2d2d
3
+ size 8591
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 sha256:46afe88da5fd71bdbab5cfab5e84c1adce59c246ea5f9341bbecef061891d0a7
3
+ size 17082913
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "xlm-roberta-base",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "XLMRobertaTokenizer",
19
+ "unk_token": "<unk>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640f9942db1674a9de46cfa15ab106c3701dc3454d6923543b86ff6b493d88f1
3
+ size 3375