Training in progress, epoch 1
Browse files- config.json +83 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Apr21_03-16-26_7f213064b236/events.out.tfevents.1713669389.7f213064b236.745.6 +3 -0
- runs/Apr21_03-17-53_7f213064b236/events.out.tfevents.1713669474.7f213064b236.745.7 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ai-forever/ruRoberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "\u041f\u0440\u0438\u043a\u043b\u0430\u0434\u043d\u0430\u044f \u043c\u0430\u0442\u0435\u043c\u0430\u0442\u0438\u043a\u0430 \u0438 \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0442\u0438\u043a\u0430",
|
| 16 |
+
"1": "\u0418\u043d\u0444\u043e\u0440\u043c\u0430\u0442\u0438\u043a\u0430 \u0438 \u0432\u044b\u0447\u0438\u0441\u043b\u0438\u0442\u0435\u043b\u044c\u043d\u0430\u044f \u0442\u0435\u0445\u043d\u0438\u043a\u0430. \u0418\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u044b\u0439 \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442",
|
| 17 |
+
"2": "\u0418\u043d\u0444\u043e\u0440\u043c\u0430\u0442\u0438\u043a\u0430 \u0438 \u0432\u044b\u0447\u0438\u0441\u043b\u0438\u0442\u0435\u043b\u044c\u043d\u0430\u044f \u0442\u0435\u0445\u043d\u0438\u043a\u0430. \u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u043e\u0435 \u043c\u043e\u0434\u0435\u043b\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0438 \u043f\u0440\u043e\u0435\u043a\u0442\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435",
|
| 18 |
+
"3": "\u0418\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u043e\u043d\u043d\u044b\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0438 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438",
|
| 19 |
+
"4": "\u041f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u043d\u0430\u044f \u0438\u043d\u0436\u0435\u043d\u0435\u0440\u0438\u044f",
|
| 20 |
+
"5": "\u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u0430\u044f \u0431\u0435\u0437\u043e\u043f\u0430\u0441\u043d\u043e\u0441\u0442\u044c",
|
| 21 |
+
"6": "\u0420\u0430\u0434\u0438\u043e\u0442\u0435\u0445\u043d\u0438\u043a\u0430. \u0421\u0438\u0441\u0442\u0435\u043c\u044b \u043a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u043e\u0433\u043e \u0437\u0440\u0435\u043d\u0438\u044f",
|
| 22 |
+
"7": "\u0420\u0430\u0434\u0438\u043e\u0442\u0435\u0445\u043d\u0438\u043a\u0430. \u0426\u0438\u0444\u0440\u043e\u0432\u044b\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043b\u043e\u043a\u0430\u0446\u0438\u0438, \u0441\u0432\u044f\u0437\u0438 \u0438 \u043d\u0430\u0432\u0438\u0433\u0430\u0446\u0438\u0438",
|
| 23 |
+
"8": "\u0418\u043d\u0444\u043e\u043a\u043e\u043c\u043c\u0443\u043d\u0438\u043a\u0430\u0446\u0438\u043e\u043d\u043d\u044b\u0435 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 \u0438 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0441\u0432\u044f\u0437\u0438",
|
| 24 |
+
"9": "\u041a\u043e\u043d\u0441\u0442\u0440\u0443\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0438 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044f \u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u044b\u0445 \u0441\u0440\u0435\u0434\u0441\u0442\u0432",
|
| 25 |
+
"10": "\u042d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u0438\u043a\u0430 \u0438 \u043d\u0430\u043d\u043e\u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u0438\u043a\u0430",
|
| 26 |
+
"11": "\u0420\u0430\u0434\u0438\u043e\u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u044b\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0438 \u043a\u043e\u043c\u043f\u043b\u0435\u043a\u0441\u044b",
|
| 27 |
+
"12": "\u041f\u0440\u0438\u0431\u043e\u0440\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u0435. \u0418\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0443\u0430\u043b\u044c\u043d\u044b\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b",
|
| 28 |
+
"13": "\u0411\u0438\u043e\u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0438 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438",
|
| 29 |
+
"14": "\u042d\u043b\u0435\u043a\u0442\u0440\u043e\u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u0430 \u0438 \u044d\u043b\u0435\u043a\u0442\u0440\u043e\u0442\u0435\u0445\u043d\u0438\u043a\u0430",
|
| 30 |
+
"15": "\u041c\u0435\u0445\u0430\u0442\u0440\u043e\u043d\u0438\u043a\u0430 \u0438 \u0440\u043e\u0431\u043e\u0442\u043e\u0442\u0435\u0445\u043d\u0438\u043a\u0430",
|
| 31 |
+
"16": "\u0422\u0435\u0445\u043d\u043e\u0441\u0444\u0435\u0440\u043d\u0430\u044f \u0431\u0435\u0437\u043e\u043f\u0430\u0441\u043d\u043e\u0441\u0442\u044c",
|
| 32 |
+
"17": "\u0421\u0438\u0441\u0442\u0435\u043c\u043d\u044b\u0439 \u0430\u043d\u0430\u043b\u0438\u0437 \u0438 \u0443\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u0435",
|
| 33 |
+
"18": "\u0423\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u0435 \u0432 \u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0441\u0438\u0441\u0442\u0435\u043c\u0430\u0445. \u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u044b\u0435 \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0443\u0430\u043b\u044c\u043d\u044b\u0435 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 \u0443\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0432 \u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0441\u0438\u0441\u0442\u0435\u043c\u0430\u0445",
|
| 34 |
+
"19": "\u0423\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u0435 \u0432 \u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0441\u0438\u0441\u0442\u0435\u043c\u0430\u0445. \u0410\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u043a\u0430 \u0438 \u0440\u043e\u0431\u043e\u0442\u043e\u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b",
|
| 35 |
+
"20": "\u0418\u043d\u043d\u043e\u0432\u0430\u0442\u0438\u043a\u0430",
|
| 36 |
+
"21": "\u041d\u0430\u043d\u043e\u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 \u0438 \u043c\u0438\u043a\u0440\u043e\u0441\u0438\u0441\u0442\u0435\u043c\u043d\u0430\u044f \u0442\u0435\u0445\u043d\u0438\u043a\u0430",
|
| 37 |
+
"22": "\u041c\u0435\u043d\u0435\u0434\u0436\u043c\u0435\u043d\u0442",
|
| 38 |
+
"23": "\u0420\u0435\u043a\u043b\u0430\u043c\u0430 \u0438 \u0441\u0432\u044f\u0437\u0438 \u0441 \u043e\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0441\u0442\u044c\u044e",
|
| 39 |
+
"24": "\u041b\u0438\u043d\u0433\u0432\u0438\u0441\u0442\u0438\u043a\u0430"
|
| 40 |
+
},
|
| 41 |
+
"initializer_range": 0.02,
|
| 42 |
+
"intermediate_size": 4096,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"\u0411\u0438\u043e\u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0438 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438": 13,
|
| 45 |
+
"\u0418\u043d\u043d\u043e\u0432\u0430\u0442\u0438\u043a\u0430": 20,
|
| 46 |
+
"\u0418\u043d\u0444\u043e\u043a\u043e\u043c\u043c\u0443\u043d\u0438\u043a\u0430\u0446\u0438\u043e\u043d\u043d\u044b\u0435 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 \u0438 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0441\u0432\u044f\u0437\u0438": 8,
|
| 47 |
+
"\u0418\u043d\u0444\u043e\u0440\u043c\u0430\u0442\u0438\u043a\u0430 \u0438 \u0432\u044b\u0447\u0438\u0441\u043b\u0438\u0442\u0435\u043b\u044c\u043d\u0430\u044f \u0442\u0435\u0445\u043d\u0438\u043a\u0430. \u0418\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u044b\u0439 \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442": 1,
|
| 48 |
+
"\u0418\u043d\u0444\u043e\u0440\u043c\u0430\u0442\u0438\u043a\u0430 \u0438 \u0432\u044b\u0447\u0438\u0441\u043b\u0438\u0442\u0435\u043b\u044c\u043d\u0430\u044f \u0442\u0435\u0445\u043d\u0438\u043a\u0430. \u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u043e\u0435 \u043c\u043e\u0434\u0435\u043b\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0438 \u043f\u0440\u043e\u0435\u043a\u0442\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435": 2,
|
| 49 |
+
"\u0418\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u043e\u043d\u043d\u044b\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0438 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438": 3,
|
| 50 |
+
"\u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u0430\u044f \u0431\u0435\u0437\u043e\u043f\u0430\u0441\u043d\u043e\u0441\u0442\u044c": 5,
|
| 51 |
+
"\u041a\u043e\u043d\u0441\u0442\u0440\u0443\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u0435 \u0438 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u044f \u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u044b\u0445 \u0441\u0440\u0435\u0434\u0441\u0442\u0432": 9,
|
| 52 |
+
"\u041b\u0438\u043d\u0433\u0432\u0438\u0441\u0442\u0438\u043a\u0430": 24,
|
| 53 |
+
"\u041c\u0435\u043d\u0435\u0434\u0436\u043c\u0435\u043d\u0442": 22,
|
| 54 |
+
"\u041c\u0435\u0445\u0430\u0442\u0440\u043e\u043d\u0438\u043a\u0430 \u0438 \u0440\u043e\u0431\u043e\u0442\u043e\u0442\u0435\u0445\u043d\u0438\u043a\u0430": 15,
|
| 55 |
+
"\u041d\u0430\u043d\u043e\u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 \u0438 \u043c\u0438\u043a\u0440\u043e\u0441\u0438\u0441\u0442\u0435\u043c\u043d\u0430\u044f \u0442\u0435\u0445\u043d\u0438\u043a\u0430": 21,
|
| 56 |
+
"\u041f\u0440\u0438\u0431\u043e\u0440\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u0435. \u0418\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0443\u0430\u043b\u044c\u043d\u044b\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b": 12,
|
| 57 |
+
"\u041f\u0440\u0438\u043a\u043b\u0430\u0434\u043d\u0430\u044f \u043c\u0430\u0442\u0435\u043c\u0430\u0442\u0438\u043a\u0430 \u0438 \u0438\u043d\u0444\u043e\u0440\u043c\u0430\u0442\u0438\u043a\u0430": 0,
|
| 58 |
+
"\u041f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u043d\u0430\u044f \u0438\u043d\u0436\u0435\u043d\u0435\u0440\u0438\u044f": 4,
|
| 59 |
+
"\u0420\u0430\u0434\u0438\u043e\u0442\u0435\u0445\u043d\u0438\u043a\u0430. \u0421\u0438\u0441\u0442\u0435\u043c\u044b \u043a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u043e\u0433\u043e \u0437\u0440\u0435\u043d\u0438\u044f": 6,
|
| 60 |
+
"\u0420\u0430\u0434\u0438\u043e\u0442\u0435\u0445\u043d\u0438\u043a\u0430. \u0426\u0438\u0444\u0440\u043e\u0432\u044b\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u043b\u043e\u043a\u0430\u0446\u0438\u0438, \u0441\u0432\u044f\u0437\u0438 \u0438 \u043d\u0430\u0432\u0438\u0433\u0430\u0446\u0438\u0438": 7,
|
| 61 |
+
"\u0420\u0430\u0434\u0438\u043e\u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u044b\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0438 \u043a\u043e\u043c\u043f\u043b\u0435\u043a\u0441\u044b": 11,
|
| 62 |
+
"\u0420\u0435\u043a\u043b\u0430\u043c\u0430 \u0438 \u0441\u0432\u044f\u0437\u0438 \u0441 \u043e\u0431\u0449\u0435\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0441\u0442\u044c\u044e": 23,
|
| 63 |
+
"\u0421\u0438\u0441\u0442\u0435\u043c\u043d\u044b\u0439 \u0430\u043d\u0430\u043b\u0438\u0437 \u0438 \u0443\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u0435": 17,
|
| 64 |
+
"\u0422\u0435\u0445\u043d\u043e\u0441\u0444\u0435\u0440\u043d\u0430\u044f \u0431\u0435\u0437\u043e\u043f\u0430\u0441\u043d\u043e\u0441\u0442\u044c": 16,
|
| 65 |
+
"\u0423\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u0435 \u0432 \u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0441\u0438\u0441\u0442\u0435\u043c\u0430\u0445. \u0410\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u043a\u0430 \u0438 \u0440\u043e\u0431\u043e\u0442\u043e\u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u0441\u0438\u0441\u0442\u0435\u043c\u044b": 19,
|
| 66 |
+
"\u0423\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u0435 \u0432 \u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0441\u0438\u0441\u0442\u0435\u043c\u0430\u0445. \u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u044b\u0435 \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0443\u0430\u043b\u044c\u043d\u044b\u0435 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0438 \u0443\u043f\u0440\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0432 \u0442\u0435\u0445\u043d\u0438\u0447\u0435\u0441\u043a\u0438\u0445 \u0441\u0438\u0441\u0442\u0435\u043c\u0430\u0445": 18,
|
| 67 |
+
"\u042d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u0438\u043a\u0430 \u0438 \u043d\u0430\u043d\u043e\u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u0438\u043a\u0430": 10,
|
| 68 |
+
"\u042d\u043b\u0435\u043a\u0442\u0440\u043e\u044d\u043d\u0435\u0440\u0433\u0435\u0442\u0438\u043a\u0430 \u0438 \u044d\u043b\u0435\u043a\u0442\u0440\u043e\u0442\u0435\u0445\u043d\u0438\u043a\u0430": 14
|
| 69 |
+
},
|
| 70 |
+
"layer_norm_eps": 1e-05,
|
| 71 |
+
"max_position_embeddings": 514,
|
| 72 |
+
"model_type": "roberta",
|
| 73 |
+
"num_attention_heads": 16,
|
| 74 |
+
"num_hidden_layers": 24,
|
| 75 |
+
"pad_token_id": 1,
|
| 76 |
+
"position_embedding_type": "absolute",
|
| 77 |
+
"problem_type": "single_label_classification",
|
| 78 |
+
"torch_dtype": "float32",
|
| 79 |
+
"transformers_version": "4.38.2",
|
| 80 |
+
"type_vocab_size": 1,
|
| 81 |
+
"use_cache": true,
|
| 82 |
+
"vocab_size": 50265
|
| 83 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1f0dbd002cfda82fefd067afeb22e1640c1d3ee6e2401c4462f3c4444966967
|
| 3 |
+
size 1421589716
|
runs/Apr21_03-16-26_7f213064b236/events.out.tfevents.1713669389.7f213064b236.745.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48b78f91b8ad7d7e807f5e8615d23593a25f032de11a6fdad37e9f5cbb57f7f3
|
| 3 |
+
size 16612
|
runs/Apr21_03-17-53_7f213064b236/events.out.tfevents.1713669474.7f213064b236.745.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d79012d222f53bb6241f88963ac77005b93d23d8eb6a893f1dd0b58f3406648
|
| 3 |
+
size 17020
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<s>",
|
| 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 |
+
"4": {
|
| 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": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e1fbed591f490aeafba6355435a9b5a2f54522facace8ae6c59c326bac75335
|
| 3 |
+
size 4856
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|