Upload CodeBERT Task B baseline metrics
Browse files- config.json +54 -0
- confusion_matrix_val_seen.csv +12 -0
- merges.txt +0 -0
- metrics_summary_val.json +13 -0
- metrics_val_seen.json +248 -0
- model.safetensors +3 -0
- per_class_val_seen.csv +12 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4",
|
| 18 |
+
"5": "LABEL_5",
|
| 19 |
+
"6": "LABEL_6",
|
| 20 |
+
"7": "LABEL_7",
|
| 21 |
+
"8": "LABEL_8",
|
| 22 |
+
"9": "LABEL_9",
|
| 23 |
+
"10": "LABEL_10"
|
| 24 |
+
},
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"LABEL_0": 0,
|
| 29 |
+
"LABEL_1": 1,
|
| 30 |
+
"LABEL_10": 10,
|
| 31 |
+
"LABEL_2": 2,
|
| 32 |
+
"LABEL_3": 3,
|
| 33 |
+
"LABEL_4": 4,
|
| 34 |
+
"LABEL_5": 5,
|
| 35 |
+
"LABEL_6": 6,
|
| 36 |
+
"LABEL_7": 7,
|
| 37 |
+
"LABEL_8": 8,
|
| 38 |
+
"LABEL_9": 9
|
| 39 |
+
},
|
| 40 |
+
"layer_norm_eps": 1e-05,
|
| 41 |
+
"max_position_embeddings": 514,
|
| 42 |
+
"model_type": "roberta",
|
| 43 |
+
"num_attention_heads": 12,
|
| 44 |
+
"num_hidden_layers": 12,
|
| 45 |
+
"output_past": true,
|
| 46 |
+
"pad_token_id": 1,
|
| 47 |
+
"position_embedding_type": "absolute",
|
| 48 |
+
"problem_type": "single_label_classification",
|
| 49 |
+
"torch_dtype": "float32",
|
| 50 |
+
"transformers_version": "4.53.3",
|
| 51 |
+
"type_vocab_size": 1,
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"vocab_size": 50265
|
| 54 |
+
}
|
confusion_matrix_val_seen.csv
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
0,1,2,3,4,5,6,7,8,9,10
|
| 2 |
+
27307,47,51,0,6,7,1,54,46,3,108
|
| 3 |
+
44,61,17,0,2,13,1,9,36,1,49
|
| 4 |
+
48,4,143,8,2,12,44,41,34,0,115
|
| 5 |
+
15,7,55,13,2,4,13,23,7,0,33
|
| 6 |
+
13,0,3,0,45,0,0,19,0,0,1
|
| 7 |
+
11,9,4,0,0,38,0,3,27,0,18
|
| 8 |
+
9,2,72,2,0,0,109,12,11,0,34
|
| 9 |
+
78,6,86,4,6,4,11,124,28,0,48
|
| 10 |
+
20,12,5,0,0,7,1,1,335,1,44
|
| 11 |
+
9,9,3,0,0,10,0,2,58,1,22
|
| 12 |
+
29,3,48,0,0,7,5,3,43,0,537
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
metrics_summary_val.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"val_seen": {
|
| 3 |
+
"accuracy": 0.9402383915122143,
|
| 4 |
+
"f1_macro": 0.4429154171231265,
|
| 5 |
+
"f1_weighted": 0.9373528237692644,
|
| 6 |
+
"precision_macro": 0.4984888502219219,
|
| 7 |
+
"recall_macro": 0.44387968282940715,
|
| 8 |
+
"mcc": 0.6707747786438902,
|
| 9 |
+
"balanced_accuracy": 0.44387968282940715,
|
| 10 |
+
"roc_auc_ovr_macro": 0.9778007633245402,
|
| 11 |
+
"pr_auc_binary": NaN
|
| 12 |
+
}
|
| 13 |
+
}
|
metrics_val_seen.json
ADDED
|
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"overall": {
|
| 3 |
+
"accuracy": 0.9402383915122143,
|
| 4 |
+
"f1_macro": 0.4429154171231265,
|
| 5 |
+
"f1_weighted": 0.9373528237692644,
|
| 6 |
+
"precision_macro": 0.4984888502219219,
|
| 7 |
+
"recall_macro": 0.44387968282940715,
|
| 8 |
+
"mcc": 0.6707747786438902,
|
| 9 |
+
"balanced_accuracy": 0.44387968282940715,
|
| 10 |
+
"roc_auc_ovr_macro": 0.9778007633245402,
|
| 11 |
+
"pr_auc_binary": NaN
|
| 12 |
+
},
|
| 13 |
+
"per_class": [
|
| 14 |
+
{
|
| 15 |
+
"label_id": 0,
|
| 16 |
+
"label": "0",
|
| 17 |
+
"precision": 0.989993836783526,
|
| 18 |
+
"recall": 0.988309808179515,
|
| 19 |
+
"f1": 0.9891511057178561,
|
| 20 |
+
"support": 27630
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"label_id": 1,
|
| 24 |
+
"label": "1",
|
| 25 |
+
"precision": 0.38125,
|
| 26 |
+
"recall": 0.26180257510729615,
|
| 27 |
+
"f1": 0.3104325699745547,
|
| 28 |
+
"support": 233
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"label_id": 2,
|
| 32 |
+
"label": "2",
|
| 33 |
+
"precision": 0.2936344969199179,
|
| 34 |
+
"recall": 0.3170731707317073,
|
| 35 |
+
"f1": 0.3049040511727079,
|
| 36 |
+
"support": 451
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"label_id": 3,
|
| 40 |
+
"label": "3",
|
| 41 |
+
"precision": 0.48148148148148145,
|
| 42 |
+
"recall": 0.0755813953488372,
|
| 43 |
+
"f1": 0.1306532663316583,
|
| 44 |
+
"support": 172
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"label_id": 4,
|
| 48 |
+
"label": "4",
|
| 49 |
+
"precision": 0.7142857142857143,
|
| 50 |
+
"recall": 0.5555555555555556,
|
| 51 |
+
"f1": 0.6250000000000001,
|
| 52 |
+
"support": 81
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"label_id": 5,
|
| 56 |
+
"label": "5",
|
| 57 |
+
"precision": 0.37254901960784315,
|
| 58 |
+
"recall": 0.34545454545454546,
|
| 59 |
+
"f1": 0.3584905660377358,
|
| 60 |
+
"support": 110
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"label_id": 6,
|
| 64 |
+
"label": "6",
|
| 65 |
+
"precision": 0.5891891891891892,
|
| 66 |
+
"recall": 0.4342629482071713,
|
| 67 |
+
"f1": 0.5,
|
| 68 |
+
"support": 251
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"label_id": 7,
|
| 72 |
+
"label": "7",
|
| 73 |
+
"precision": 0.4261168384879725,
|
| 74 |
+
"recall": 0.3139240506329114,
|
| 75 |
+
"f1": 0.3615160349854228,
|
| 76 |
+
"support": 395
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"label_id": 8,
|
| 80 |
+
"label": "8",
|
| 81 |
+
"precision": 0.536,
|
| 82 |
+
"recall": 0.7863849765258216,
|
| 83 |
+
"f1": 0.6374881065651762,
|
| 84 |
+
"support": 426
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"label_id": 9,
|
| 88 |
+
"label": "9",
|
| 89 |
+
"precision": 0.16666666666666666,
|
| 90 |
+
"recall": 0.008771929824561403,
|
| 91 |
+
"f1": 0.016666666666666666,
|
| 92 |
+
"support": 114
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"label_id": 10,
|
| 96 |
+
"label": "10",
|
| 97 |
+
"precision": 0.5322101090188305,
|
| 98 |
+
"recall": 0.7955555555555556,
|
| 99 |
+
"f1": 0.6377672209026128,
|
| 100 |
+
"support": 675
|
| 101 |
+
}
|
| 102 |
+
],
|
| 103 |
+
"confusion_matrix": [
|
| 104 |
+
[
|
| 105 |
+
27307,
|
| 106 |
+
47,
|
| 107 |
+
51,
|
| 108 |
+
0,
|
| 109 |
+
6,
|
| 110 |
+
7,
|
| 111 |
+
1,
|
| 112 |
+
54,
|
| 113 |
+
46,
|
| 114 |
+
3,
|
| 115 |
+
108
|
| 116 |
+
],
|
| 117 |
+
[
|
| 118 |
+
44,
|
| 119 |
+
61,
|
| 120 |
+
17,
|
| 121 |
+
0,
|
| 122 |
+
2,
|
| 123 |
+
13,
|
| 124 |
+
1,
|
| 125 |
+
9,
|
| 126 |
+
36,
|
| 127 |
+
1,
|
| 128 |
+
49
|
| 129 |
+
],
|
| 130 |
+
[
|
| 131 |
+
48,
|
| 132 |
+
4,
|
| 133 |
+
143,
|
| 134 |
+
8,
|
| 135 |
+
2,
|
| 136 |
+
12,
|
| 137 |
+
44,
|
| 138 |
+
41,
|
| 139 |
+
34,
|
| 140 |
+
0,
|
| 141 |
+
115
|
| 142 |
+
],
|
| 143 |
+
[
|
| 144 |
+
15,
|
| 145 |
+
7,
|
| 146 |
+
55,
|
| 147 |
+
13,
|
| 148 |
+
2,
|
| 149 |
+
4,
|
| 150 |
+
13,
|
| 151 |
+
23,
|
| 152 |
+
7,
|
| 153 |
+
0,
|
| 154 |
+
33
|
| 155 |
+
],
|
| 156 |
+
[
|
| 157 |
+
13,
|
| 158 |
+
0,
|
| 159 |
+
3,
|
| 160 |
+
0,
|
| 161 |
+
45,
|
| 162 |
+
0,
|
| 163 |
+
0,
|
| 164 |
+
19,
|
| 165 |
+
0,
|
| 166 |
+
0,
|
| 167 |
+
1
|
| 168 |
+
],
|
| 169 |
+
[
|
| 170 |
+
11,
|
| 171 |
+
9,
|
| 172 |
+
4,
|
| 173 |
+
0,
|
| 174 |
+
0,
|
| 175 |
+
38,
|
| 176 |
+
0,
|
| 177 |
+
3,
|
| 178 |
+
27,
|
| 179 |
+
0,
|
| 180 |
+
18
|
| 181 |
+
],
|
| 182 |
+
[
|
| 183 |
+
9,
|
| 184 |
+
2,
|
| 185 |
+
72,
|
| 186 |
+
2,
|
| 187 |
+
0,
|
| 188 |
+
0,
|
| 189 |
+
109,
|
| 190 |
+
12,
|
| 191 |
+
11,
|
| 192 |
+
0,
|
| 193 |
+
34
|
| 194 |
+
],
|
| 195 |
+
[
|
| 196 |
+
78,
|
| 197 |
+
6,
|
| 198 |
+
86,
|
| 199 |
+
4,
|
| 200 |
+
6,
|
| 201 |
+
4,
|
| 202 |
+
11,
|
| 203 |
+
124,
|
| 204 |
+
28,
|
| 205 |
+
0,
|
| 206 |
+
48
|
| 207 |
+
],
|
| 208 |
+
[
|
| 209 |
+
20,
|
| 210 |
+
12,
|
| 211 |
+
5,
|
| 212 |
+
0,
|
| 213 |
+
0,
|
| 214 |
+
7,
|
| 215 |
+
1,
|
| 216 |
+
1,
|
| 217 |
+
335,
|
| 218 |
+
1,
|
| 219 |
+
44
|
| 220 |
+
],
|
| 221 |
+
[
|
| 222 |
+
9,
|
| 223 |
+
9,
|
| 224 |
+
3,
|
| 225 |
+
0,
|
| 226 |
+
0,
|
| 227 |
+
10,
|
| 228 |
+
0,
|
| 229 |
+
2,
|
| 230 |
+
58,
|
| 231 |
+
1,
|
| 232 |
+
22
|
| 233 |
+
],
|
| 234 |
+
[
|
| 235 |
+
29,
|
| 236 |
+
3,
|
| 237 |
+
48,
|
| 238 |
+
0,
|
| 239 |
+
0,
|
| 240 |
+
7,
|
| 241 |
+
5,
|
| 242 |
+
3,
|
| 243 |
+
43,
|
| 244 |
+
0,
|
| 245 |
+
537
|
| 246 |
+
]
|
| 247 |
+
]
|
| 248 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7eb98331a3e38a8a707ad26ded88cf3474ec2022b27d6a4ba7fd6eb39014f899
|
| 3 |
+
size 498640508
|
per_class_val_seen.csv
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
label_id,label,precision,recall,f1,support
|
| 2 |
+
0,0,0.989993836783526,0.988309808179515,0.9891511057178561,27630
|
| 3 |
+
1,1,0.38125,0.26180257510729615,0.3104325699745547,233
|
| 4 |
+
2,2,0.2936344969199179,0.3170731707317073,0.3049040511727079,451
|
| 5 |
+
3,3,0.48148148148148145,0.0755813953488372,0.1306532663316583,172
|
| 6 |
+
4,4,0.7142857142857143,0.5555555555555556,0.6250000000000001,81
|
| 7 |
+
5,5,0.37254901960784315,0.34545454545454546,0.3584905660377358,110
|
| 8 |
+
6,6,0.5891891891891892,0.4342629482071713,0.5,251
|
| 9 |
+
7,7,0.4261168384879725,0.3139240506329114,0.3615160349854228,395
|
| 10 |
+
8,8,0.536,0.7863849765258216,0.6374881065651762,426
|
| 11 |
+
9,9,0.16666666666666666,0.008771929824561403,0.016666666666666666,114
|
| 12 |
+
10,10,0.5322101090188305,0.7955555555555556,0.6377672209026128,675
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e391192737a406901798e6a2ca7e1256a3952f13c24cbbc0e586d89cef753ea
|
| 3 |
+
size 5304
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|