Upload 7 files
Browse files- .gitattributes +1 -0
- config.json +68 -0
- model.safetensors +3 -0
- special_tokens_map.json +55 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2018 -0
- trainer_state.json +604 -0
- training_args.bin +3 -0
.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 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForTokenClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 1,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"dtype": "float32",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 1,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"global_rope_theta": 160000,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"id2label": {
|
| 24 |
+
"0": "O",
|
| 25 |
+
"1": "B-LOC",
|
| 26 |
+
"2": "I-LOC",
|
| 27 |
+
"3": "B-MISC",
|
| 28 |
+
"4": "I-MISC",
|
| 29 |
+
"5": "B-ORG",
|
| 30 |
+
"6": "I-ORG",
|
| 31 |
+
"7": "B-PER",
|
| 32 |
+
"8": "I-PER"
|
| 33 |
+
},
|
| 34 |
+
"initializer_cutoff_factor": 2.0,
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"intermediate_size": 1152,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"B-LOC": 1,
|
| 39 |
+
"B-MISC": 3,
|
| 40 |
+
"B-ORG": 5,
|
| 41 |
+
"B-PER": 7,
|
| 42 |
+
"I-LOC": 2,
|
| 43 |
+
"I-MISC": 4,
|
| 44 |
+
"I-ORG": 6,
|
| 45 |
+
"I-PER": 8,
|
| 46 |
+
"O": 0
|
| 47 |
+
},
|
| 48 |
+
"layer_norm_eps": 1e-05,
|
| 49 |
+
"local_attention": 128,
|
| 50 |
+
"local_rope_theta": 160000,
|
| 51 |
+
"mask_token_id": 4,
|
| 52 |
+
"max_position_embeddings": 8192,
|
| 53 |
+
"mlp_bias": false,
|
| 54 |
+
"mlp_dropout": 0.0,
|
| 55 |
+
"model_type": "modernbert",
|
| 56 |
+
"norm_bias": false,
|
| 57 |
+
"norm_eps": 1e-05,
|
| 58 |
+
"num_attention_heads": 12,
|
| 59 |
+
"num_hidden_layers": 22,
|
| 60 |
+
"pad_token_id": 0,
|
| 61 |
+
"position_embedding_type": "sans_pos",
|
| 62 |
+
"repad_logits_with_grad": false,
|
| 63 |
+
"sep_token_id": 1,
|
| 64 |
+
"sparse_pred_ignore_index": -100,
|
| 65 |
+
"sparse_prediction": false,
|
| 66 |
+
"transformers_version": "4.57.3",
|
| 67 |
+
"vocab_size": 256000
|
| 68 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d38b44caf5ef51f3e45d8158895d0fb205528f6f1763f41cb10fd3a20031d749
|
| 3 |
+
size 1230162964
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<start_of_turn>",
|
| 4 |
+
"<end_of_turn>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<bos>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"cls_token": {
|
| 14 |
+
"content": "<bos>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "<eos>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"mask_token": {
|
| 28 |
+
"content": "<mask>",
|
| 29 |
+
"lstrip": true,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
},
|
| 34 |
+
"pad_token": {
|
| 35 |
+
"content": "<pad>",
|
| 36 |
+
"lstrip": false,
|
| 37 |
+
"normalized": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"single_word": false
|
| 40 |
+
},
|
| 41 |
+
"sep_token": {
|
| 42 |
+
"content": "<eos>",
|
| 43 |
+
"lstrip": false,
|
| 44 |
+
"normalized": false,
|
| 45 |
+
"rstrip": false,
|
| 46 |
+
"single_word": false
|
| 47 |
+
},
|
| 48 |
+
"unk_token": {
|
| 49 |
+
"content": "<unk>",
|
| 50 |
+
"lstrip": false,
|
| 51 |
+
"normalized": false,
|
| 52 |
+
"rstrip": false,
|
| 53 |
+
"single_word": false
|
| 54 |
+
}
|
| 55 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a086e6a7efb90bbab8e379a63f3463fb13e6256ebec3343c1f1612cab693935b
|
| 3 |
+
size 34363287
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2018 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<eos>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<bos>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 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 |
+
"5": {
|
| 45 |
+
"content": "<2mass>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "[@BOS@]",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<unused0>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<unused1>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<unused2>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<unused3>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<unused4>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<unused5>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<unused6>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<unused7>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<unused8>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<unused9>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<unused10>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<unused11>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"19": {
|
| 157 |
+
"content": "<unused12>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"20": {
|
| 165 |
+
"content": "<unused13>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"21": {
|
| 173 |
+
"content": "<unused14>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"22": {
|
| 181 |
+
"content": "<unused15>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"23": {
|
| 189 |
+
"content": "<unused16>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"24": {
|
| 197 |
+
"content": "<unused17>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"25": {
|
| 205 |
+
"content": "<unused18>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"26": {
|
| 213 |
+
"content": "<unused19>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"27": {
|
| 221 |
+
"content": "<unused20>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"28": {
|
| 229 |
+
"content": "<unused21>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"29": {
|
| 237 |
+
"content": "<unused22>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"30": {
|
| 245 |
+
"content": "<unused23>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"31": {
|
| 253 |
+
"content": "<unused24>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"32": {
|
| 261 |
+
"content": "<unused25>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"33": {
|
| 269 |
+
"content": "<unused26>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"34": {
|
| 277 |
+
"content": "<unused27>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"35": {
|
| 285 |
+
"content": "<unused28>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"36": {
|
| 293 |
+
"content": "<unused29>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"37": {
|
| 301 |
+
"content": "<unused30>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"38": {
|
| 309 |
+
"content": "<unused31>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
},
|
| 316 |
+
"39": {
|
| 317 |
+
"content": "<unused32>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": false
|
| 323 |
+
},
|
| 324 |
+
"40": {
|
| 325 |
+
"content": "<unused33>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": false
|
| 331 |
+
},
|
| 332 |
+
"41": {
|
| 333 |
+
"content": "<unused34>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": false
|
| 339 |
+
},
|
| 340 |
+
"42": {
|
| 341 |
+
"content": "<unused35>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": false
|
| 347 |
+
},
|
| 348 |
+
"43": {
|
| 349 |
+
"content": "<unused36>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": false
|
| 355 |
+
},
|
| 356 |
+
"44": {
|
| 357 |
+
"content": "<unused37>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": false
|
| 363 |
+
},
|
| 364 |
+
"45": {
|
| 365 |
+
"content": "<unused38>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": false
|
| 371 |
+
},
|
| 372 |
+
"46": {
|
| 373 |
+
"content": "<unused39>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": false
|
| 379 |
+
},
|
| 380 |
+
"47": {
|
| 381 |
+
"content": "<unused40>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": false
|
| 387 |
+
},
|
| 388 |
+
"48": {
|
| 389 |
+
"content": "<unused41>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": false
|
| 395 |
+
},
|
| 396 |
+
"49": {
|
| 397 |
+
"content": "<unused42>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": false
|
| 403 |
+
},
|
| 404 |
+
"50": {
|
| 405 |
+
"content": "<unused43>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": false
|
| 411 |
+
},
|
| 412 |
+
"51": {
|
| 413 |
+
"content": "<unused44>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": false
|
| 419 |
+
},
|
| 420 |
+
"52": {
|
| 421 |
+
"content": "<unused45>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": false
|
| 427 |
+
},
|
| 428 |
+
"53": {
|
| 429 |
+
"content": "<unused46>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": false
|
| 435 |
+
},
|
| 436 |
+
"54": {
|
| 437 |
+
"content": "<unused47>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": false
|
| 443 |
+
},
|
| 444 |
+
"55": {
|
| 445 |
+
"content": "<unused48>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": false
|
| 451 |
+
},
|
| 452 |
+
"56": {
|
| 453 |
+
"content": "<unused49>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": false
|
| 459 |
+
},
|
| 460 |
+
"57": {
|
| 461 |
+
"content": "<unused50>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": false
|
| 467 |
+
},
|
| 468 |
+
"58": {
|
| 469 |
+
"content": "<unused51>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": false
|
| 475 |
+
},
|
| 476 |
+
"59": {
|
| 477 |
+
"content": "<unused52>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": false
|
| 483 |
+
},
|
| 484 |
+
"60": {
|
| 485 |
+
"content": "<unused53>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": false
|
| 491 |
+
},
|
| 492 |
+
"61": {
|
| 493 |
+
"content": "<unused54>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": false
|
| 499 |
+
},
|
| 500 |
+
"62": {
|
| 501 |
+
"content": "<unused55>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": false
|
| 507 |
+
},
|
| 508 |
+
"63": {
|
| 509 |
+
"content": "<unused56>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": false
|
| 515 |
+
},
|
| 516 |
+
"64": {
|
| 517 |
+
"content": "<unused57>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": false
|
| 523 |
+
},
|
| 524 |
+
"65": {
|
| 525 |
+
"content": "<unused58>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": false
|
| 531 |
+
},
|
| 532 |
+
"66": {
|
| 533 |
+
"content": "<unused59>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": false
|
| 539 |
+
},
|
| 540 |
+
"67": {
|
| 541 |
+
"content": "<unused60>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": false
|
| 547 |
+
},
|
| 548 |
+
"68": {
|
| 549 |
+
"content": "<unused61>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": false
|
| 555 |
+
},
|
| 556 |
+
"69": {
|
| 557 |
+
"content": "<unused62>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": false
|
| 563 |
+
},
|
| 564 |
+
"70": {
|
| 565 |
+
"content": "<unused63>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": false
|
| 571 |
+
},
|
| 572 |
+
"71": {
|
| 573 |
+
"content": "<unused64>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": false
|
| 579 |
+
},
|
| 580 |
+
"72": {
|
| 581 |
+
"content": "<unused65>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": false
|
| 587 |
+
},
|
| 588 |
+
"73": {
|
| 589 |
+
"content": "<unused66>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": false
|
| 595 |
+
},
|
| 596 |
+
"74": {
|
| 597 |
+
"content": "<unused67>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": false
|
| 603 |
+
},
|
| 604 |
+
"75": {
|
| 605 |
+
"content": "<unused68>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": false
|
| 611 |
+
},
|
| 612 |
+
"76": {
|
| 613 |
+
"content": "<unused69>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": false
|
| 619 |
+
},
|
| 620 |
+
"77": {
|
| 621 |
+
"content": "<unused70>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": false
|
| 627 |
+
},
|
| 628 |
+
"78": {
|
| 629 |
+
"content": "<unused71>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": false
|
| 635 |
+
},
|
| 636 |
+
"79": {
|
| 637 |
+
"content": "<unused72>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": false
|
| 643 |
+
},
|
| 644 |
+
"80": {
|
| 645 |
+
"content": "<unused73>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": false
|
| 651 |
+
},
|
| 652 |
+
"81": {
|
| 653 |
+
"content": "<unused74>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": false
|
| 659 |
+
},
|
| 660 |
+
"82": {
|
| 661 |
+
"content": "<unused75>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": false
|
| 667 |
+
},
|
| 668 |
+
"83": {
|
| 669 |
+
"content": "<unused76>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": false
|
| 675 |
+
},
|
| 676 |
+
"84": {
|
| 677 |
+
"content": "<unused77>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": false
|
| 683 |
+
},
|
| 684 |
+
"85": {
|
| 685 |
+
"content": "<unused78>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": false
|
| 691 |
+
},
|
| 692 |
+
"86": {
|
| 693 |
+
"content": "<unused79>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": false
|
| 699 |
+
},
|
| 700 |
+
"87": {
|
| 701 |
+
"content": "<unused80>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": false
|
| 707 |
+
},
|
| 708 |
+
"88": {
|
| 709 |
+
"content": "<unused81>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": false
|
| 715 |
+
},
|
| 716 |
+
"89": {
|
| 717 |
+
"content": "<unused82>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": false
|
| 723 |
+
},
|
| 724 |
+
"90": {
|
| 725 |
+
"content": "<unused83>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": false
|
| 731 |
+
},
|
| 732 |
+
"91": {
|
| 733 |
+
"content": "<unused84>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": false
|
| 739 |
+
},
|
| 740 |
+
"92": {
|
| 741 |
+
"content": "<unused85>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": false
|
| 747 |
+
},
|
| 748 |
+
"93": {
|
| 749 |
+
"content": "<unused86>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": false
|
| 755 |
+
},
|
| 756 |
+
"94": {
|
| 757 |
+
"content": "<unused87>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": false
|
| 763 |
+
},
|
| 764 |
+
"95": {
|
| 765 |
+
"content": "<unused88>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": false
|
| 771 |
+
},
|
| 772 |
+
"96": {
|
| 773 |
+
"content": "<unused89>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": false
|
| 779 |
+
},
|
| 780 |
+
"97": {
|
| 781 |
+
"content": "<unused90>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": false
|
| 787 |
+
},
|
| 788 |
+
"98": {
|
| 789 |
+
"content": "<unused91>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": false
|
| 795 |
+
},
|
| 796 |
+
"99": {
|
| 797 |
+
"content": "<unused92>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": false
|
| 803 |
+
},
|
| 804 |
+
"100": {
|
| 805 |
+
"content": "<unused93>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": false
|
| 811 |
+
},
|
| 812 |
+
"101": {
|
| 813 |
+
"content": "<unused94>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": false
|
| 819 |
+
},
|
| 820 |
+
"102": {
|
| 821 |
+
"content": "<unused95>",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": false
|
| 827 |
+
},
|
| 828 |
+
"103": {
|
| 829 |
+
"content": "<unused96>",
|
| 830 |
+
"lstrip": false,
|
| 831 |
+
"normalized": false,
|
| 832 |
+
"rstrip": false,
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"special": false
|
| 835 |
+
},
|
| 836 |
+
"104": {
|
| 837 |
+
"content": "<unused97>",
|
| 838 |
+
"lstrip": false,
|
| 839 |
+
"normalized": false,
|
| 840 |
+
"rstrip": false,
|
| 841 |
+
"single_word": false,
|
| 842 |
+
"special": false
|
| 843 |
+
},
|
| 844 |
+
"105": {
|
| 845 |
+
"content": "<unused98>",
|
| 846 |
+
"lstrip": false,
|
| 847 |
+
"normalized": false,
|
| 848 |
+
"rstrip": false,
|
| 849 |
+
"single_word": false,
|
| 850 |
+
"special": false
|
| 851 |
+
},
|
| 852 |
+
"106": {
|
| 853 |
+
"content": "<start_of_turn>",
|
| 854 |
+
"lstrip": false,
|
| 855 |
+
"normalized": false,
|
| 856 |
+
"rstrip": false,
|
| 857 |
+
"single_word": false,
|
| 858 |
+
"special": true
|
| 859 |
+
},
|
| 860 |
+
"107": {
|
| 861 |
+
"content": "<end_of_turn>",
|
| 862 |
+
"lstrip": false,
|
| 863 |
+
"normalized": false,
|
| 864 |
+
"rstrip": false,
|
| 865 |
+
"single_word": false,
|
| 866 |
+
"special": true
|
| 867 |
+
},
|
| 868 |
+
"108": {
|
| 869 |
+
"content": "\n",
|
| 870 |
+
"lstrip": false,
|
| 871 |
+
"normalized": false,
|
| 872 |
+
"rstrip": false,
|
| 873 |
+
"single_word": false,
|
| 874 |
+
"special": false
|
| 875 |
+
},
|
| 876 |
+
"109": {
|
| 877 |
+
"content": "\n\n",
|
| 878 |
+
"lstrip": false,
|
| 879 |
+
"normalized": false,
|
| 880 |
+
"rstrip": false,
|
| 881 |
+
"single_word": false,
|
| 882 |
+
"special": false
|
| 883 |
+
},
|
| 884 |
+
"110": {
|
| 885 |
+
"content": "\n\n\n",
|
| 886 |
+
"lstrip": false,
|
| 887 |
+
"normalized": false,
|
| 888 |
+
"rstrip": false,
|
| 889 |
+
"single_word": false,
|
| 890 |
+
"special": false
|
| 891 |
+
},
|
| 892 |
+
"111": {
|
| 893 |
+
"content": "\n\n\n\n",
|
| 894 |
+
"lstrip": false,
|
| 895 |
+
"normalized": false,
|
| 896 |
+
"rstrip": false,
|
| 897 |
+
"single_word": false,
|
| 898 |
+
"special": false
|
| 899 |
+
},
|
| 900 |
+
"112": {
|
| 901 |
+
"content": "\n\n\n\n\n",
|
| 902 |
+
"lstrip": false,
|
| 903 |
+
"normalized": false,
|
| 904 |
+
"rstrip": false,
|
| 905 |
+
"single_word": false,
|
| 906 |
+
"special": false
|
| 907 |
+
},
|
| 908 |
+
"113": {
|
| 909 |
+
"content": "\n\n\n\n\n\n",
|
| 910 |
+
"lstrip": false,
|
| 911 |
+
"normalized": false,
|
| 912 |
+
"rstrip": false,
|
| 913 |
+
"single_word": false,
|
| 914 |
+
"special": false
|
| 915 |
+
},
|
| 916 |
+
"114": {
|
| 917 |
+
"content": "\n\n\n\n\n\n\n",
|
| 918 |
+
"lstrip": false,
|
| 919 |
+
"normalized": false,
|
| 920 |
+
"rstrip": false,
|
| 921 |
+
"single_word": false,
|
| 922 |
+
"special": false
|
| 923 |
+
},
|
| 924 |
+
"115": {
|
| 925 |
+
"content": "\n\n\n\n\n\n\n\n",
|
| 926 |
+
"lstrip": false,
|
| 927 |
+
"normalized": false,
|
| 928 |
+
"rstrip": false,
|
| 929 |
+
"single_word": false,
|
| 930 |
+
"special": false
|
| 931 |
+
},
|
| 932 |
+
"116": {
|
| 933 |
+
"content": "\n\n\n\n\n\n\n\n\n",
|
| 934 |
+
"lstrip": false,
|
| 935 |
+
"normalized": false,
|
| 936 |
+
"rstrip": false,
|
| 937 |
+
"single_word": false,
|
| 938 |
+
"special": false
|
| 939 |
+
},
|
| 940 |
+
"117": {
|
| 941 |
+
"content": "\n\n\n\n\n\n\n\n\n\n",
|
| 942 |
+
"lstrip": false,
|
| 943 |
+
"normalized": false,
|
| 944 |
+
"rstrip": false,
|
| 945 |
+
"single_word": false,
|
| 946 |
+
"special": false
|
| 947 |
+
},
|
| 948 |
+
"118": {
|
| 949 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n",
|
| 950 |
+
"lstrip": false,
|
| 951 |
+
"normalized": false,
|
| 952 |
+
"rstrip": false,
|
| 953 |
+
"single_word": false,
|
| 954 |
+
"special": false
|
| 955 |
+
},
|
| 956 |
+
"119": {
|
| 957 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 958 |
+
"lstrip": false,
|
| 959 |
+
"normalized": false,
|
| 960 |
+
"rstrip": false,
|
| 961 |
+
"single_word": false,
|
| 962 |
+
"special": false
|
| 963 |
+
},
|
| 964 |
+
"120": {
|
| 965 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 966 |
+
"lstrip": false,
|
| 967 |
+
"normalized": false,
|
| 968 |
+
"rstrip": false,
|
| 969 |
+
"single_word": false,
|
| 970 |
+
"special": false
|
| 971 |
+
},
|
| 972 |
+
"121": {
|
| 973 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 974 |
+
"lstrip": false,
|
| 975 |
+
"normalized": false,
|
| 976 |
+
"rstrip": false,
|
| 977 |
+
"single_word": false,
|
| 978 |
+
"special": false
|
| 979 |
+
},
|
| 980 |
+
"122": {
|
| 981 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 982 |
+
"lstrip": false,
|
| 983 |
+
"normalized": false,
|
| 984 |
+
"rstrip": false,
|
| 985 |
+
"single_word": false,
|
| 986 |
+
"special": false
|
| 987 |
+
},
|
| 988 |
+
"123": {
|
| 989 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 990 |
+
"lstrip": false,
|
| 991 |
+
"normalized": false,
|
| 992 |
+
"rstrip": false,
|
| 993 |
+
"single_word": false,
|
| 994 |
+
"special": false
|
| 995 |
+
},
|
| 996 |
+
"124": {
|
| 997 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 998 |
+
"lstrip": false,
|
| 999 |
+
"normalized": false,
|
| 1000 |
+
"rstrip": false,
|
| 1001 |
+
"single_word": false,
|
| 1002 |
+
"special": false
|
| 1003 |
+
},
|
| 1004 |
+
"125": {
|
| 1005 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1006 |
+
"lstrip": false,
|
| 1007 |
+
"normalized": false,
|
| 1008 |
+
"rstrip": false,
|
| 1009 |
+
"single_word": false,
|
| 1010 |
+
"special": false
|
| 1011 |
+
},
|
| 1012 |
+
"126": {
|
| 1013 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1014 |
+
"lstrip": false,
|
| 1015 |
+
"normalized": false,
|
| 1016 |
+
"rstrip": false,
|
| 1017 |
+
"single_word": false,
|
| 1018 |
+
"special": false
|
| 1019 |
+
},
|
| 1020 |
+
"127": {
|
| 1021 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1022 |
+
"lstrip": false,
|
| 1023 |
+
"normalized": false,
|
| 1024 |
+
"rstrip": false,
|
| 1025 |
+
"single_word": false,
|
| 1026 |
+
"special": false
|
| 1027 |
+
},
|
| 1028 |
+
"128": {
|
| 1029 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1030 |
+
"lstrip": false,
|
| 1031 |
+
"normalized": false,
|
| 1032 |
+
"rstrip": false,
|
| 1033 |
+
"single_word": false,
|
| 1034 |
+
"special": false
|
| 1035 |
+
},
|
| 1036 |
+
"129": {
|
| 1037 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1038 |
+
"lstrip": false,
|
| 1039 |
+
"normalized": false,
|
| 1040 |
+
"rstrip": false,
|
| 1041 |
+
"single_word": false,
|
| 1042 |
+
"special": false
|
| 1043 |
+
},
|
| 1044 |
+
"130": {
|
| 1045 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1046 |
+
"lstrip": false,
|
| 1047 |
+
"normalized": false,
|
| 1048 |
+
"rstrip": false,
|
| 1049 |
+
"single_word": false,
|
| 1050 |
+
"special": false
|
| 1051 |
+
},
|
| 1052 |
+
"131": {
|
| 1053 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1054 |
+
"lstrip": false,
|
| 1055 |
+
"normalized": false,
|
| 1056 |
+
"rstrip": false,
|
| 1057 |
+
"single_word": false,
|
| 1058 |
+
"special": false
|
| 1059 |
+
},
|
| 1060 |
+
"132": {
|
| 1061 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1062 |
+
"lstrip": false,
|
| 1063 |
+
"normalized": false,
|
| 1064 |
+
"rstrip": false,
|
| 1065 |
+
"single_word": false,
|
| 1066 |
+
"special": false
|
| 1067 |
+
},
|
| 1068 |
+
"133": {
|
| 1069 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1070 |
+
"lstrip": false,
|
| 1071 |
+
"normalized": false,
|
| 1072 |
+
"rstrip": false,
|
| 1073 |
+
"single_word": false,
|
| 1074 |
+
"special": false
|
| 1075 |
+
},
|
| 1076 |
+
"134": {
|
| 1077 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1078 |
+
"lstrip": false,
|
| 1079 |
+
"normalized": false,
|
| 1080 |
+
"rstrip": false,
|
| 1081 |
+
"single_word": false,
|
| 1082 |
+
"special": false
|
| 1083 |
+
},
|
| 1084 |
+
"135": {
|
| 1085 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1086 |
+
"lstrip": false,
|
| 1087 |
+
"normalized": false,
|
| 1088 |
+
"rstrip": false,
|
| 1089 |
+
"single_word": false,
|
| 1090 |
+
"special": false
|
| 1091 |
+
},
|
| 1092 |
+
"136": {
|
| 1093 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1094 |
+
"lstrip": false,
|
| 1095 |
+
"normalized": false,
|
| 1096 |
+
"rstrip": false,
|
| 1097 |
+
"single_word": false,
|
| 1098 |
+
"special": false
|
| 1099 |
+
},
|
| 1100 |
+
"137": {
|
| 1101 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1102 |
+
"lstrip": false,
|
| 1103 |
+
"normalized": false,
|
| 1104 |
+
"rstrip": false,
|
| 1105 |
+
"single_word": false,
|
| 1106 |
+
"special": false
|
| 1107 |
+
},
|
| 1108 |
+
"138": {
|
| 1109 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1110 |
+
"lstrip": false,
|
| 1111 |
+
"normalized": false,
|
| 1112 |
+
"rstrip": false,
|
| 1113 |
+
"single_word": false,
|
| 1114 |
+
"special": false
|
| 1115 |
+
},
|
| 1116 |
+
"139": {
|
| 1117 |
+
"content": "▁▁",
|
| 1118 |
+
"lstrip": false,
|
| 1119 |
+
"normalized": false,
|
| 1120 |
+
"rstrip": false,
|
| 1121 |
+
"single_word": false,
|
| 1122 |
+
"special": false
|
| 1123 |
+
},
|
| 1124 |
+
"140": {
|
| 1125 |
+
"content": "▁▁▁",
|
| 1126 |
+
"lstrip": false,
|
| 1127 |
+
"normalized": false,
|
| 1128 |
+
"rstrip": false,
|
| 1129 |
+
"single_word": false,
|
| 1130 |
+
"special": false
|
| 1131 |
+
},
|
| 1132 |
+
"141": {
|
| 1133 |
+
"content": "▁▁▁▁",
|
| 1134 |
+
"lstrip": false,
|
| 1135 |
+
"normalized": false,
|
| 1136 |
+
"rstrip": false,
|
| 1137 |
+
"single_word": false,
|
| 1138 |
+
"special": false
|
| 1139 |
+
},
|
| 1140 |
+
"142": {
|
| 1141 |
+
"content": "▁▁▁▁▁",
|
| 1142 |
+
"lstrip": false,
|
| 1143 |
+
"normalized": false,
|
| 1144 |
+
"rstrip": false,
|
| 1145 |
+
"single_word": false,
|
| 1146 |
+
"special": false
|
| 1147 |
+
},
|
| 1148 |
+
"143": {
|
| 1149 |
+
"content": "▁▁▁▁▁▁",
|
| 1150 |
+
"lstrip": false,
|
| 1151 |
+
"normalized": false,
|
| 1152 |
+
"rstrip": false,
|
| 1153 |
+
"single_word": false,
|
| 1154 |
+
"special": false
|
| 1155 |
+
},
|
| 1156 |
+
"144": {
|
| 1157 |
+
"content": "▁▁▁▁▁▁▁",
|
| 1158 |
+
"lstrip": false,
|
| 1159 |
+
"normalized": false,
|
| 1160 |
+
"rstrip": false,
|
| 1161 |
+
"single_word": false,
|
| 1162 |
+
"special": false
|
| 1163 |
+
},
|
| 1164 |
+
"145": {
|
| 1165 |
+
"content": "▁▁▁▁▁▁▁▁",
|
| 1166 |
+
"lstrip": false,
|
| 1167 |
+
"normalized": false,
|
| 1168 |
+
"rstrip": false,
|
| 1169 |
+
"single_word": false,
|
| 1170 |
+
"special": false
|
| 1171 |
+
},
|
| 1172 |
+
"146": {
|
| 1173 |
+
"content": "▁▁▁▁▁▁▁▁▁",
|
| 1174 |
+
"lstrip": false,
|
| 1175 |
+
"normalized": false,
|
| 1176 |
+
"rstrip": false,
|
| 1177 |
+
"single_word": false,
|
| 1178 |
+
"special": false
|
| 1179 |
+
},
|
| 1180 |
+
"147": {
|
| 1181 |
+
"content": "▁▁▁▁▁▁▁▁▁▁",
|
| 1182 |
+
"lstrip": false,
|
| 1183 |
+
"normalized": false,
|
| 1184 |
+
"rstrip": false,
|
| 1185 |
+
"single_word": false,
|
| 1186 |
+
"special": false
|
| 1187 |
+
},
|
| 1188 |
+
"148": {
|
| 1189 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁",
|
| 1190 |
+
"lstrip": false,
|
| 1191 |
+
"normalized": false,
|
| 1192 |
+
"rstrip": false,
|
| 1193 |
+
"single_word": false,
|
| 1194 |
+
"special": false
|
| 1195 |
+
},
|
| 1196 |
+
"149": {
|
| 1197 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1198 |
+
"lstrip": false,
|
| 1199 |
+
"normalized": false,
|
| 1200 |
+
"rstrip": false,
|
| 1201 |
+
"single_word": false,
|
| 1202 |
+
"special": false
|
| 1203 |
+
},
|
| 1204 |
+
"150": {
|
| 1205 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1206 |
+
"lstrip": false,
|
| 1207 |
+
"normalized": false,
|
| 1208 |
+
"rstrip": false,
|
| 1209 |
+
"single_word": false,
|
| 1210 |
+
"special": false
|
| 1211 |
+
},
|
| 1212 |
+
"151": {
|
| 1213 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1214 |
+
"lstrip": false,
|
| 1215 |
+
"normalized": false,
|
| 1216 |
+
"rstrip": false,
|
| 1217 |
+
"single_word": false,
|
| 1218 |
+
"special": false
|
| 1219 |
+
},
|
| 1220 |
+
"152": {
|
| 1221 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1222 |
+
"lstrip": false,
|
| 1223 |
+
"normalized": false,
|
| 1224 |
+
"rstrip": false,
|
| 1225 |
+
"single_word": false,
|
| 1226 |
+
"special": false
|
| 1227 |
+
},
|
| 1228 |
+
"153": {
|
| 1229 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1230 |
+
"lstrip": false,
|
| 1231 |
+
"normalized": false,
|
| 1232 |
+
"rstrip": false,
|
| 1233 |
+
"single_word": false,
|
| 1234 |
+
"special": false
|
| 1235 |
+
},
|
| 1236 |
+
"154": {
|
| 1237 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1238 |
+
"lstrip": false,
|
| 1239 |
+
"normalized": false,
|
| 1240 |
+
"rstrip": false,
|
| 1241 |
+
"single_word": false,
|
| 1242 |
+
"special": false
|
| 1243 |
+
},
|
| 1244 |
+
"155": {
|
| 1245 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1246 |
+
"lstrip": false,
|
| 1247 |
+
"normalized": false,
|
| 1248 |
+
"rstrip": false,
|
| 1249 |
+
"single_word": false,
|
| 1250 |
+
"special": false
|
| 1251 |
+
},
|
| 1252 |
+
"156": {
|
| 1253 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1254 |
+
"lstrip": false,
|
| 1255 |
+
"normalized": false,
|
| 1256 |
+
"rstrip": false,
|
| 1257 |
+
"single_word": false,
|
| 1258 |
+
"special": false
|
| 1259 |
+
},
|
| 1260 |
+
"157": {
|
| 1261 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1262 |
+
"lstrip": false,
|
| 1263 |
+
"normalized": false,
|
| 1264 |
+
"rstrip": false,
|
| 1265 |
+
"single_word": false,
|
| 1266 |
+
"special": false
|
| 1267 |
+
},
|
| 1268 |
+
"158": {
|
| 1269 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1270 |
+
"lstrip": false,
|
| 1271 |
+
"normalized": false,
|
| 1272 |
+
"rstrip": false,
|
| 1273 |
+
"single_word": false,
|
| 1274 |
+
"special": false
|
| 1275 |
+
},
|
| 1276 |
+
"159": {
|
| 1277 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1278 |
+
"lstrip": false,
|
| 1279 |
+
"normalized": false,
|
| 1280 |
+
"rstrip": false,
|
| 1281 |
+
"single_word": false,
|
| 1282 |
+
"special": false
|
| 1283 |
+
},
|
| 1284 |
+
"160": {
|
| 1285 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1286 |
+
"lstrip": false,
|
| 1287 |
+
"normalized": false,
|
| 1288 |
+
"rstrip": false,
|
| 1289 |
+
"single_word": false,
|
| 1290 |
+
"special": false
|
| 1291 |
+
},
|
| 1292 |
+
"161": {
|
| 1293 |
+
"content": "▁▁▁���▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1294 |
+
"lstrip": false,
|
| 1295 |
+
"normalized": false,
|
| 1296 |
+
"rstrip": false,
|
| 1297 |
+
"single_word": false,
|
| 1298 |
+
"special": false
|
| 1299 |
+
},
|
| 1300 |
+
"162": {
|
| 1301 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1302 |
+
"lstrip": false,
|
| 1303 |
+
"normalized": false,
|
| 1304 |
+
"rstrip": false,
|
| 1305 |
+
"single_word": false,
|
| 1306 |
+
"special": false
|
| 1307 |
+
},
|
| 1308 |
+
"163": {
|
| 1309 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1310 |
+
"lstrip": false,
|
| 1311 |
+
"normalized": false,
|
| 1312 |
+
"rstrip": false,
|
| 1313 |
+
"single_word": false,
|
| 1314 |
+
"special": false
|
| 1315 |
+
},
|
| 1316 |
+
"164": {
|
| 1317 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1318 |
+
"lstrip": false,
|
| 1319 |
+
"normalized": false,
|
| 1320 |
+
"rstrip": false,
|
| 1321 |
+
"single_word": false,
|
| 1322 |
+
"special": false
|
| 1323 |
+
},
|
| 1324 |
+
"165": {
|
| 1325 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1326 |
+
"lstrip": false,
|
| 1327 |
+
"normalized": false,
|
| 1328 |
+
"rstrip": false,
|
| 1329 |
+
"single_word": false,
|
| 1330 |
+
"special": false
|
| 1331 |
+
},
|
| 1332 |
+
"166": {
|
| 1333 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1334 |
+
"lstrip": false,
|
| 1335 |
+
"normalized": false,
|
| 1336 |
+
"rstrip": false,
|
| 1337 |
+
"single_word": false,
|
| 1338 |
+
"special": false
|
| 1339 |
+
},
|
| 1340 |
+
"167": {
|
| 1341 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1342 |
+
"lstrip": false,
|
| 1343 |
+
"normalized": false,
|
| 1344 |
+
"rstrip": false,
|
| 1345 |
+
"single_word": false,
|
| 1346 |
+
"special": false
|
| 1347 |
+
},
|
| 1348 |
+
"168": {
|
| 1349 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1350 |
+
"lstrip": false,
|
| 1351 |
+
"normalized": false,
|
| 1352 |
+
"rstrip": false,
|
| 1353 |
+
"single_word": false,
|
| 1354 |
+
"special": false
|
| 1355 |
+
},
|
| 1356 |
+
"169": {
|
| 1357 |
+
"content": "<table>",
|
| 1358 |
+
"lstrip": false,
|
| 1359 |
+
"normalized": false,
|
| 1360 |
+
"rstrip": false,
|
| 1361 |
+
"single_word": false,
|
| 1362 |
+
"special": false
|
| 1363 |
+
},
|
| 1364 |
+
"170": {
|
| 1365 |
+
"content": "<caption>",
|
| 1366 |
+
"lstrip": false,
|
| 1367 |
+
"normalized": false,
|
| 1368 |
+
"rstrip": false,
|
| 1369 |
+
"single_word": false,
|
| 1370 |
+
"special": false
|
| 1371 |
+
},
|
| 1372 |
+
"171": {
|
| 1373 |
+
"content": "<thead>",
|
| 1374 |
+
"lstrip": false,
|
| 1375 |
+
"normalized": false,
|
| 1376 |
+
"rstrip": false,
|
| 1377 |
+
"single_word": false,
|
| 1378 |
+
"special": false
|
| 1379 |
+
},
|
| 1380 |
+
"172": {
|
| 1381 |
+
"content": "<tbody>",
|
| 1382 |
+
"lstrip": false,
|
| 1383 |
+
"normalized": false,
|
| 1384 |
+
"rstrip": false,
|
| 1385 |
+
"single_word": false,
|
| 1386 |
+
"special": false
|
| 1387 |
+
},
|
| 1388 |
+
"173": {
|
| 1389 |
+
"content": "<tfoot>",
|
| 1390 |
+
"lstrip": false,
|
| 1391 |
+
"normalized": false,
|
| 1392 |
+
"rstrip": false,
|
| 1393 |
+
"single_word": false,
|
| 1394 |
+
"special": false
|
| 1395 |
+
},
|
| 1396 |
+
"174": {
|
| 1397 |
+
"content": "<tr>",
|
| 1398 |
+
"lstrip": false,
|
| 1399 |
+
"normalized": false,
|
| 1400 |
+
"rstrip": false,
|
| 1401 |
+
"single_word": false,
|
| 1402 |
+
"special": false
|
| 1403 |
+
},
|
| 1404 |
+
"175": {
|
| 1405 |
+
"content": "<th>",
|
| 1406 |
+
"lstrip": false,
|
| 1407 |
+
"normalized": false,
|
| 1408 |
+
"rstrip": false,
|
| 1409 |
+
"single_word": false,
|
| 1410 |
+
"special": false
|
| 1411 |
+
},
|
| 1412 |
+
"176": {
|
| 1413 |
+
"content": "<td>",
|
| 1414 |
+
"lstrip": false,
|
| 1415 |
+
"normalized": false,
|
| 1416 |
+
"rstrip": false,
|
| 1417 |
+
"single_word": false,
|
| 1418 |
+
"special": false
|
| 1419 |
+
},
|
| 1420 |
+
"177": {
|
| 1421 |
+
"content": "</table>",
|
| 1422 |
+
"lstrip": false,
|
| 1423 |
+
"normalized": false,
|
| 1424 |
+
"rstrip": false,
|
| 1425 |
+
"single_word": false,
|
| 1426 |
+
"special": false
|
| 1427 |
+
},
|
| 1428 |
+
"178": {
|
| 1429 |
+
"content": "</caption>",
|
| 1430 |
+
"lstrip": false,
|
| 1431 |
+
"normalized": false,
|
| 1432 |
+
"rstrip": false,
|
| 1433 |
+
"single_word": false,
|
| 1434 |
+
"special": false
|
| 1435 |
+
},
|
| 1436 |
+
"179": {
|
| 1437 |
+
"content": "</thead>",
|
| 1438 |
+
"lstrip": false,
|
| 1439 |
+
"normalized": false,
|
| 1440 |
+
"rstrip": false,
|
| 1441 |
+
"single_word": false,
|
| 1442 |
+
"special": false
|
| 1443 |
+
},
|
| 1444 |
+
"180": {
|
| 1445 |
+
"content": "</tbody>",
|
| 1446 |
+
"lstrip": false,
|
| 1447 |
+
"normalized": false,
|
| 1448 |
+
"rstrip": false,
|
| 1449 |
+
"single_word": false,
|
| 1450 |
+
"special": false
|
| 1451 |
+
},
|
| 1452 |
+
"181": {
|
| 1453 |
+
"content": "</tfoot>",
|
| 1454 |
+
"lstrip": false,
|
| 1455 |
+
"normalized": false,
|
| 1456 |
+
"rstrip": false,
|
| 1457 |
+
"single_word": false,
|
| 1458 |
+
"special": false
|
| 1459 |
+
},
|
| 1460 |
+
"182": {
|
| 1461 |
+
"content": "</tr>",
|
| 1462 |
+
"lstrip": false,
|
| 1463 |
+
"normalized": false,
|
| 1464 |
+
"rstrip": false,
|
| 1465 |
+
"single_word": false,
|
| 1466 |
+
"special": false
|
| 1467 |
+
},
|
| 1468 |
+
"183": {
|
| 1469 |
+
"content": "</th>",
|
| 1470 |
+
"lstrip": false,
|
| 1471 |
+
"normalized": false,
|
| 1472 |
+
"rstrip": false,
|
| 1473 |
+
"single_word": false,
|
| 1474 |
+
"special": false
|
| 1475 |
+
},
|
| 1476 |
+
"184": {
|
| 1477 |
+
"content": "</td>",
|
| 1478 |
+
"lstrip": false,
|
| 1479 |
+
"normalized": false,
|
| 1480 |
+
"rstrip": false,
|
| 1481 |
+
"single_word": false,
|
| 1482 |
+
"special": false
|
| 1483 |
+
},
|
| 1484 |
+
"185": {
|
| 1485 |
+
"content": "<h1>",
|
| 1486 |
+
"lstrip": false,
|
| 1487 |
+
"normalized": false,
|
| 1488 |
+
"rstrip": false,
|
| 1489 |
+
"single_word": false,
|
| 1490 |
+
"special": false
|
| 1491 |
+
},
|
| 1492 |
+
"186": {
|
| 1493 |
+
"content": "<h2>",
|
| 1494 |
+
"lstrip": false,
|
| 1495 |
+
"normalized": false,
|
| 1496 |
+
"rstrip": false,
|
| 1497 |
+
"single_word": false,
|
| 1498 |
+
"special": false
|
| 1499 |
+
},
|
| 1500 |
+
"187": {
|
| 1501 |
+
"content": "<h3>",
|
| 1502 |
+
"lstrip": false,
|
| 1503 |
+
"normalized": false,
|
| 1504 |
+
"rstrip": false,
|
| 1505 |
+
"single_word": false,
|
| 1506 |
+
"special": false
|
| 1507 |
+
},
|
| 1508 |
+
"188": {
|
| 1509 |
+
"content": "<h4>",
|
| 1510 |
+
"lstrip": false,
|
| 1511 |
+
"normalized": false,
|
| 1512 |
+
"rstrip": false,
|
| 1513 |
+
"single_word": false,
|
| 1514 |
+
"special": false
|
| 1515 |
+
},
|
| 1516 |
+
"189": {
|
| 1517 |
+
"content": "<h5>",
|
| 1518 |
+
"lstrip": false,
|
| 1519 |
+
"normalized": false,
|
| 1520 |
+
"rstrip": false,
|
| 1521 |
+
"single_word": false,
|
| 1522 |
+
"special": false
|
| 1523 |
+
},
|
| 1524 |
+
"190": {
|
| 1525 |
+
"content": "<h6>",
|
| 1526 |
+
"lstrip": false,
|
| 1527 |
+
"normalized": false,
|
| 1528 |
+
"rstrip": false,
|
| 1529 |
+
"single_word": false,
|
| 1530 |
+
"special": false
|
| 1531 |
+
},
|
| 1532 |
+
"191": {
|
| 1533 |
+
"content": "<blockquote>",
|
| 1534 |
+
"lstrip": false,
|
| 1535 |
+
"normalized": false,
|
| 1536 |
+
"rstrip": false,
|
| 1537 |
+
"single_word": false,
|
| 1538 |
+
"special": false
|
| 1539 |
+
},
|
| 1540 |
+
"192": {
|
| 1541 |
+
"content": "</h1>",
|
| 1542 |
+
"lstrip": false,
|
| 1543 |
+
"normalized": false,
|
| 1544 |
+
"rstrip": false,
|
| 1545 |
+
"single_word": false,
|
| 1546 |
+
"special": false
|
| 1547 |
+
},
|
| 1548 |
+
"193": {
|
| 1549 |
+
"content": "</h2>",
|
| 1550 |
+
"lstrip": false,
|
| 1551 |
+
"normalized": false,
|
| 1552 |
+
"rstrip": false,
|
| 1553 |
+
"single_word": false,
|
| 1554 |
+
"special": false
|
| 1555 |
+
},
|
| 1556 |
+
"194": {
|
| 1557 |
+
"content": "</h3>",
|
| 1558 |
+
"lstrip": false,
|
| 1559 |
+
"normalized": false,
|
| 1560 |
+
"rstrip": false,
|
| 1561 |
+
"single_word": false,
|
| 1562 |
+
"special": false
|
| 1563 |
+
},
|
| 1564 |
+
"195": {
|
| 1565 |
+
"content": "</h4>",
|
| 1566 |
+
"lstrip": false,
|
| 1567 |
+
"normalized": false,
|
| 1568 |
+
"rstrip": false,
|
| 1569 |
+
"single_word": false,
|
| 1570 |
+
"special": false
|
| 1571 |
+
},
|
| 1572 |
+
"196": {
|
| 1573 |
+
"content": "</h5>",
|
| 1574 |
+
"lstrip": false,
|
| 1575 |
+
"normalized": false,
|
| 1576 |
+
"rstrip": false,
|
| 1577 |
+
"single_word": false,
|
| 1578 |
+
"special": false
|
| 1579 |
+
},
|
| 1580 |
+
"197": {
|
| 1581 |
+
"content": "</h6>",
|
| 1582 |
+
"lstrip": false,
|
| 1583 |
+
"normalized": false,
|
| 1584 |
+
"rstrip": false,
|
| 1585 |
+
"single_word": false,
|
| 1586 |
+
"special": false
|
| 1587 |
+
},
|
| 1588 |
+
"198": {
|
| 1589 |
+
"content": "</blockquote>",
|
| 1590 |
+
"lstrip": false,
|
| 1591 |
+
"normalized": false,
|
| 1592 |
+
"rstrip": false,
|
| 1593 |
+
"single_word": false,
|
| 1594 |
+
"special": false
|
| 1595 |
+
},
|
| 1596 |
+
"199": {
|
| 1597 |
+
"content": "<strong>",
|
| 1598 |
+
"lstrip": false,
|
| 1599 |
+
"normalized": false,
|
| 1600 |
+
"rstrip": false,
|
| 1601 |
+
"single_word": false,
|
| 1602 |
+
"special": false
|
| 1603 |
+
},
|
| 1604 |
+
"200": {
|
| 1605 |
+
"content": "<em>",
|
| 1606 |
+
"lstrip": false,
|
| 1607 |
+
"normalized": false,
|
| 1608 |
+
"rstrip": false,
|
| 1609 |
+
"single_word": false,
|
| 1610 |
+
"special": false
|
| 1611 |
+
},
|
| 1612 |
+
"201": {
|
| 1613 |
+
"content": "<b>",
|
| 1614 |
+
"lstrip": false,
|
| 1615 |
+
"normalized": false,
|
| 1616 |
+
"rstrip": false,
|
| 1617 |
+
"single_word": false,
|
| 1618 |
+
"special": false
|
| 1619 |
+
},
|
| 1620 |
+
"202": {
|
| 1621 |
+
"content": "<i>",
|
| 1622 |
+
"lstrip": false,
|
| 1623 |
+
"normalized": false,
|
| 1624 |
+
"rstrip": false,
|
| 1625 |
+
"single_word": false,
|
| 1626 |
+
"special": false
|
| 1627 |
+
},
|
| 1628 |
+
"203": {
|
| 1629 |
+
"content": "<u>",
|
| 1630 |
+
"lstrip": false,
|
| 1631 |
+
"normalized": false,
|
| 1632 |
+
"rstrip": false,
|
| 1633 |
+
"single_word": false,
|
| 1634 |
+
"special": false
|
| 1635 |
+
},
|
| 1636 |
+
"204": {
|
| 1637 |
+
"content": "<s>",
|
| 1638 |
+
"lstrip": false,
|
| 1639 |
+
"normalized": false,
|
| 1640 |
+
"rstrip": false,
|
| 1641 |
+
"single_word": false,
|
| 1642 |
+
"special": false
|
| 1643 |
+
},
|
| 1644 |
+
"205": {
|
| 1645 |
+
"content": "<sub>",
|
| 1646 |
+
"lstrip": false,
|
| 1647 |
+
"normalized": false,
|
| 1648 |
+
"rstrip": false,
|
| 1649 |
+
"single_word": false,
|
| 1650 |
+
"special": false
|
| 1651 |
+
},
|
| 1652 |
+
"206": {
|
| 1653 |
+
"content": "<sup>",
|
| 1654 |
+
"lstrip": false,
|
| 1655 |
+
"normalized": false,
|
| 1656 |
+
"rstrip": false,
|
| 1657 |
+
"single_word": false,
|
| 1658 |
+
"special": false
|
| 1659 |
+
},
|
| 1660 |
+
"207": {
|
| 1661 |
+
"content": "<code>",
|
| 1662 |
+
"lstrip": false,
|
| 1663 |
+
"normalized": false,
|
| 1664 |
+
"rstrip": false,
|
| 1665 |
+
"single_word": false,
|
| 1666 |
+
"special": false
|
| 1667 |
+
},
|
| 1668 |
+
"208": {
|
| 1669 |
+
"content": "</strong>",
|
| 1670 |
+
"lstrip": false,
|
| 1671 |
+
"normalized": false,
|
| 1672 |
+
"rstrip": false,
|
| 1673 |
+
"single_word": false,
|
| 1674 |
+
"special": false
|
| 1675 |
+
},
|
| 1676 |
+
"209": {
|
| 1677 |
+
"content": "</em>",
|
| 1678 |
+
"lstrip": false,
|
| 1679 |
+
"normalized": false,
|
| 1680 |
+
"rstrip": false,
|
| 1681 |
+
"single_word": false,
|
| 1682 |
+
"special": false
|
| 1683 |
+
},
|
| 1684 |
+
"210": {
|
| 1685 |
+
"content": "</b>",
|
| 1686 |
+
"lstrip": false,
|
| 1687 |
+
"normalized": false,
|
| 1688 |
+
"rstrip": false,
|
| 1689 |
+
"single_word": false,
|
| 1690 |
+
"special": false
|
| 1691 |
+
},
|
| 1692 |
+
"211": {
|
| 1693 |
+
"content": "</i>",
|
| 1694 |
+
"lstrip": false,
|
| 1695 |
+
"normalized": false,
|
| 1696 |
+
"rstrip": false,
|
| 1697 |
+
"single_word": false,
|
| 1698 |
+
"special": false
|
| 1699 |
+
},
|
| 1700 |
+
"212": {
|
| 1701 |
+
"content": "</u>",
|
| 1702 |
+
"lstrip": false,
|
| 1703 |
+
"normalized": false,
|
| 1704 |
+
"rstrip": false,
|
| 1705 |
+
"single_word": false,
|
| 1706 |
+
"special": false
|
| 1707 |
+
},
|
| 1708 |
+
"213": {
|
| 1709 |
+
"content": "</s>",
|
| 1710 |
+
"lstrip": false,
|
| 1711 |
+
"normalized": false,
|
| 1712 |
+
"rstrip": false,
|
| 1713 |
+
"single_word": false,
|
| 1714 |
+
"special": false
|
| 1715 |
+
},
|
| 1716 |
+
"214": {
|
| 1717 |
+
"content": "</sub>",
|
| 1718 |
+
"lstrip": false,
|
| 1719 |
+
"normalized": false,
|
| 1720 |
+
"rstrip": false,
|
| 1721 |
+
"single_word": false,
|
| 1722 |
+
"special": false
|
| 1723 |
+
},
|
| 1724 |
+
"215": {
|
| 1725 |
+
"content": "</sup>",
|
| 1726 |
+
"lstrip": false,
|
| 1727 |
+
"normalized": false,
|
| 1728 |
+
"rstrip": false,
|
| 1729 |
+
"single_word": false,
|
| 1730 |
+
"special": false
|
| 1731 |
+
},
|
| 1732 |
+
"216": {
|
| 1733 |
+
"content": "</code>",
|
| 1734 |
+
"lstrip": false,
|
| 1735 |
+
"normalized": false,
|
| 1736 |
+
"rstrip": false,
|
| 1737 |
+
"single_word": false,
|
| 1738 |
+
"special": false
|
| 1739 |
+
},
|
| 1740 |
+
"255968": {
|
| 1741 |
+
"content": "[toxicity=0]",
|
| 1742 |
+
"lstrip": false,
|
| 1743 |
+
"normalized": false,
|
| 1744 |
+
"rstrip": false,
|
| 1745 |
+
"single_word": false,
|
| 1746 |
+
"special": false
|
| 1747 |
+
},
|
| 1748 |
+
"255969": {
|
| 1749 |
+
"content": "\t\t",
|
| 1750 |
+
"lstrip": false,
|
| 1751 |
+
"normalized": false,
|
| 1752 |
+
"rstrip": false,
|
| 1753 |
+
"single_word": false,
|
| 1754 |
+
"special": false
|
| 1755 |
+
},
|
| 1756 |
+
"255970": {
|
| 1757 |
+
"content": "\t\t\t",
|
| 1758 |
+
"lstrip": false,
|
| 1759 |
+
"normalized": false,
|
| 1760 |
+
"rstrip": false,
|
| 1761 |
+
"single_word": false,
|
| 1762 |
+
"special": false
|
| 1763 |
+
},
|
| 1764 |
+
"255971": {
|
| 1765 |
+
"content": "\t\t\t\t",
|
| 1766 |
+
"lstrip": false,
|
| 1767 |
+
"normalized": false,
|
| 1768 |
+
"rstrip": false,
|
| 1769 |
+
"single_word": false,
|
| 1770 |
+
"special": false
|
| 1771 |
+
},
|
| 1772 |
+
"255972": {
|
| 1773 |
+
"content": "\t\t\t\t\t",
|
| 1774 |
+
"lstrip": false,
|
| 1775 |
+
"normalized": false,
|
| 1776 |
+
"rstrip": false,
|
| 1777 |
+
"single_word": false,
|
| 1778 |
+
"special": false
|
| 1779 |
+
},
|
| 1780 |
+
"255973": {
|
| 1781 |
+
"content": "\t\t\t\t\t\t",
|
| 1782 |
+
"lstrip": false,
|
| 1783 |
+
"normalized": false,
|
| 1784 |
+
"rstrip": false,
|
| 1785 |
+
"single_word": false,
|
| 1786 |
+
"special": false
|
| 1787 |
+
},
|
| 1788 |
+
"255974": {
|
| 1789 |
+
"content": "\t\t\t\t\t\t\t",
|
| 1790 |
+
"lstrip": false,
|
| 1791 |
+
"normalized": false,
|
| 1792 |
+
"rstrip": false,
|
| 1793 |
+
"single_word": false,
|
| 1794 |
+
"special": false
|
| 1795 |
+
},
|
| 1796 |
+
"255975": {
|
| 1797 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 1798 |
+
"lstrip": false,
|
| 1799 |
+
"normalized": false,
|
| 1800 |
+
"rstrip": false,
|
| 1801 |
+
"single_word": false,
|
| 1802 |
+
"special": false
|
| 1803 |
+
},
|
| 1804 |
+
"255976": {
|
| 1805 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 1806 |
+
"lstrip": false,
|
| 1807 |
+
"normalized": false,
|
| 1808 |
+
"rstrip": false,
|
| 1809 |
+
"single_word": false,
|
| 1810 |
+
"special": false
|
| 1811 |
+
},
|
| 1812 |
+
"255977": {
|
| 1813 |
+
"content": "\t\t\t\t\t\t\t\t\t\t",
|
| 1814 |
+
"lstrip": false,
|
| 1815 |
+
"normalized": false,
|
| 1816 |
+
"rstrip": false,
|
| 1817 |
+
"single_word": false,
|
| 1818 |
+
"special": false
|
| 1819 |
+
},
|
| 1820 |
+
"255978": {
|
| 1821 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t",
|
| 1822 |
+
"lstrip": false,
|
| 1823 |
+
"normalized": false,
|
| 1824 |
+
"rstrip": false,
|
| 1825 |
+
"single_word": false,
|
| 1826 |
+
"special": false
|
| 1827 |
+
},
|
| 1828 |
+
"255979": {
|
| 1829 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1830 |
+
"lstrip": false,
|
| 1831 |
+
"normalized": false,
|
| 1832 |
+
"rstrip": false,
|
| 1833 |
+
"single_word": false,
|
| 1834 |
+
"special": false
|
| 1835 |
+
},
|
| 1836 |
+
"255980": {
|
| 1837 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1838 |
+
"lstrip": false,
|
| 1839 |
+
"normalized": false,
|
| 1840 |
+
"rstrip": false,
|
| 1841 |
+
"single_word": false,
|
| 1842 |
+
"special": false
|
| 1843 |
+
},
|
| 1844 |
+
"255981": {
|
| 1845 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1846 |
+
"lstrip": false,
|
| 1847 |
+
"normalized": false,
|
| 1848 |
+
"rstrip": false,
|
| 1849 |
+
"single_word": false,
|
| 1850 |
+
"special": false
|
| 1851 |
+
},
|
| 1852 |
+
"255982": {
|
| 1853 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1854 |
+
"lstrip": false,
|
| 1855 |
+
"normalized": false,
|
| 1856 |
+
"rstrip": false,
|
| 1857 |
+
"single_word": false,
|
| 1858 |
+
"special": false
|
| 1859 |
+
},
|
| 1860 |
+
"255983": {
|
| 1861 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1862 |
+
"lstrip": false,
|
| 1863 |
+
"normalized": false,
|
| 1864 |
+
"rstrip": false,
|
| 1865 |
+
"single_word": false,
|
| 1866 |
+
"special": false
|
| 1867 |
+
},
|
| 1868 |
+
"255984": {
|
| 1869 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1870 |
+
"lstrip": false,
|
| 1871 |
+
"normalized": false,
|
| 1872 |
+
"rstrip": false,
|
| 1873 |
+
"single_word": false,
|
| 1874 |
+
"special": false
|
| 1875 |
+
},
|
| 1876 |
+
"255985": {
|
| 1877 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1878 |
+
"lstrip": false,
|
| 1879 |
+
"normalized": false,
|
| 1880 |
+
"rstrip": false,
|
| 1881 |
+
"single_word": false,
|
| 1882 |
+
"special": false
|
| 1883 |
+
},
|
| 1884 |
+
"255986": {
|
| 1885 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1886 |
+
"lstrip": false,
|
| 1887 |
+
"normalized": false,
|
| 1888 |
+
"rstrip": false,
|
| 1889 |
+
"single_word": false,
|
| 1890 |
+
"special": false
|
| 1891 |
+
},
|
| 1892 |
+
"255987": {
|
| 1893 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1894 |
+
"lstrip": false,
|
| 1895 |
+
"normalized": false,
|
| 1896 |
+
"rstrip": false,
|
| 1897 |
+
"single_word": false,
|
| 1898 |
+
"special": false
|
| 1899 |
+
},
|
| 1900 |
+
"255988": {
|
| 1901 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1902 |
+
"lstrip": false,
|
| 1903 |
+
"normalized": false,
|
| 1904 |
+
"rstrip": false,
|
| 1905 |
+
"single_word": false,
|
| 1906 |
+
"special": false
|
| 1907 |
+
},
|
| 1908 |
+
"255989": {
|
| 1909 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1910 |
+
"lstrip": false,
|
| 1911 |
+
"normalized": false,
|
| 1912 |
+
"rstrip": false,
|
| 1913 |
+
"single_word": false,
|
| 1914 |
+
"special": false
|
| 1915 |
+
},
|
| 1916 |
+
"255990": {
|
| 1917 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1918 |
+
"lstrip": false,
|
| 1919 |
+
"normalized": false,
|
| 1920 |
+
"rstrip": false,
|
| 1921 |
+
"single_word": false,
|
| 1922 |
+
"special": false
|
| 1923 |
+
},
|
| 1924 |
+
"255991": {
|
| 1925 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1926 |
+
"lstrip": false,
|
| 1927 |
+
"normalized": false,
|
| 1928 |
+
"rstrip": false,
|
| 1929 |
+
"single_word": false,
|
| 1930 |
+
"special": false
|
| 1931 |
+
},
|
| 1932 |
+
"255992": {
|
| 1933 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1934 |
+
"lstrip": false,
|
| 1935 |
+
"normalized": false,
|
| 1936 |
+
"rstrip": false,
|
| 1937 |
+
"single_word": false,
|
| 1938 |
+
"special": false
|
| 1939 |
+
},
|
| 1940 |
+
"255993": {
|
| 1941 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1942 |
+
"lstrip": false,
|
| 1943 |
+
"normalized": false,
|
| 1944 |
+
"rstrip": false,
|
| 1945 |
+
"single_word": false,
|
| 1946 |
+
"special": false
|
| 1947 |
+
},
|
| 1948 |
+
"255994": {
|
| 1949 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1950 |
+
"lstrip": false,
|
| 1951 |
+
"normalized": false,
|
| 1952 |
+
"rstrip": false,
|
| 1953 |
+
"single_word": false,
|
| 1954 |
+
"special": false
|
| 1955 |
+
},
|
| 1956 |
+
"255995": {
|
| 1957 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1958 |
+
"lstrip": false,
|
| 1959 |
+
"normalized": false,
|
| 1960 |
+
"rstrip": false,
|
| 1961 |
+
"single_word": false,
|
| 1962 |
+
"special": false
|
| 1963 |
+
},
|
| 1964 |
+
"255996": {
|
| 1965 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1966 |
+
"lstrip": false,
|
| 1967 |
+
"normalized": false,
|
| 1968 |
+
"rstrip": false,
|
| 1969 |
+
"single_word": false,
|
| 1970 |
+
"special": false
|
| 1971 |
+
},
|
| 1972 |
+
"255997": {
|
| 1973 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1974 |
+
"lstrip": false,
|
| 1975 |
+
"normalized": false,
|
| 1976 |
+
"rstrip": false,
|
| 1977 |
+
"single_word": false,
|
| 1978 |
+
"special": false
|
| 1979 |
+
},
|
| 1980 |
+
"255998": {
|
| 1981 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1982 |
+
"lstrip": false,
|
| 1983 |
+
"normalized": false,
|
| 1984 |
+
"rstrip": false,
|
| 1985 |
+
"single_word": false,
|
| 1986 |
+
"special": false
|
| 1987 |
+
},
|
| 1988 |
+
"255999": {
|
| 1989 |
+
"content": "<unused99>",
|
| 1990 |
+
"lstrip": false,
|
| 1991 |
+
"normalized": false,
|
| 1992 |
+
"rstrip": false,
|
| 1993 |
+
"single_word": false,
|
| 1994 |
+
"special": false
|
| 1995 |
+
}
|
| 1996 |
+
},
|
| 1997 |
+
"additional_special_tokens": [
|
| 1998 |
+
"<start_of_turn>",
|
| 1999 |
+
"<end_of_turn>"
|
| 2000 |
+
],
|
| 2001 |
+
"bos_token": "<bos>",
|
| 2002 |
+
"clean_up_tokenization_spaces": false,
|
| 2003 |
+
"cls_token": "<bos>",
|
| 2004 |
+
"eos_token": "<eos>",
|
| 2005 |
+
"extra_special_tokens": {},
|
| 2006 |
+
"mask_token": "<mask>",
|
| 2007 |
+
"model_input_names": [
|
| 2008 |
+
"input_ids",
|
| 2009 |
+
"attention_mask"
|
| 2010 |
+
],
|
| 2011 |
+
"model_max_length": 8192,
|
| 2012 |
+
"pad_token": "<pad>",
|
| 2013 |
+
"padding_side": "right",
|
| 2014 |
+
"sep_token": "<eos>",
|
| 2015 |
+
"spaces_between_special_tokens": false,
|
| 2016 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2017 |
+
"unk_token": "<unk>"
|
| 2018 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,604 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 169584,
|
| 3 |
+
"best_metric": 0.9357306547788711,
|
| 4 |
+
"best_model_checkpoint": "/workspace/cannopy/result/train/ner/ner.mm-bert.b32.lr2e-05/checkpoint-169584",
|
| 5 |
+
"epoch": 30.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 211980,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 1.0,
|
| 14 |
+
"grad_norm": 0.8071305155754089,
|
| 15 |
+
"learning_rate": 1.933342768185678e-05,
|
| 16 |
+
"loss": 0.0833,
|
| 17 |
+
"step": 7066
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.0,
|
| 21 |
+
"eval_accuracy": 0.9816472726923888,
|
| 22 |
+
"eval_f1": 0.9143601801750758,
|
| 23 |
+
"eval_loss": 0.06737913936376572,
|
| 24 |
+
"eval_precision": 0.9067209043611152,
|
| 25 |
+
"eval_recall": 0.9221292740903273,
|
| 26 |
+
"eval_runtime": 63.6285,
|
| 27 |
+
"eval_samples_per_second": 444.094,
|
| 28 |
+
"eval_steps_per_second": 13.893,
|
| 29 |
+
"step": 7066
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 1.6214423179626465,
|
| 34 |
+
"learning_rate": 1.8666761015190115e-05,
|
| 35 |
+
"loss": 0.041,
|
| 36 |
+
"step": 14132
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.9832133401124307,
|
| 41 |
+
"eval_f1": 0.9247473576465666,
|
| 42 |
+
"eval_loss": 0.06235222890973091,
|
| 43 |
+
"eval_precision": 0.9153111601195607,
|
| 44 |
+
"eval_recall": 0.9343801426220516,
|
| 45 |
+
"eval_runtime": 26.8725,
|
| 46 |
+
"eval_samples_per_second": 1051.52,
|
| 47 |
+
"eval_steps_per_second": 32.896,
|
| 48 |
+
"step": 14132
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"grad_norm": 0.07880270481109619,
|
| 53 |
+
"learning_rate": 1.8000094348523447e-05,
|
| 54 |
+
"loss": 0.0238,
|
| 55 |
+
"step": 21198
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 3.0,
|
| 59 |
+
"eval_accuracy": 0.9830166823353351,
|
| 60 |
+
"eval_f1": 0.9234717685487634,
|
| 61 |
+
"eval_loss": 0.07555678486824036,
|
| 62 |
+
"eval_precision": 0.91971390356147,
|
| 63 |
+
"eval_recall": 0.9272604680928872,
|
| 64 |
+
"eval_runtime": 25.0859,
|
| 65 |
+
"eval_samples_per_second": 1126.41,
|
| 66 |
+
"eval_steps_per_second": 35.239,
|
| 67 |
+
"step": 21198
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 4.0,
|
| 71 |
+
"grad_norm": 0.9151579141616821,
|
| 72 |
+
"learning_rate": 1.733342768185678e-05,
|
| 73 |
+
"loss": 0.0146,
|
| 74 |
+
"step": 28264
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.0,
|
| 78 |
+
"eval_accuracy": 0.9836390322518754,
|
| 79 |
+
"eval_f1": 0.9253655132503873,
|
| 80 |
+
"eval_loss": 0.08953021466732025,
|
| 81 |
+
"eval_precision": 0.9188440087882372,
|
| 82 |
+
"eval_recall": 0.931980252331322,
|
| 83 |
+
"eval_runtime": 33.5139,
|
| 84 |
+
"eval_samples_per_second": 843.142,
|
| 85 |
+
"eval_steps_per_second": 26.377,
|
| 86 |
+
"step": 28264
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.0,
|
| 90 |
+
"grad_norm": 0.006677389610558748,
|
| 91 |
+
"learning_rate": 1.6666761015190114e-05,
|
| 92 |
+
"loss": 0.0096,
|
| 93 |
+
"step": 35330
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 5.0,
|
| 97 |
+
"eval_accuracy": 0.983770936858464,
|
| 98 |
+
"eval_f1": 0.9272781274631878,
|
| 99 |
+
"eval_loss": 0.08903905749320984,
|
| 100 |
+
"eval_precision": 0.9269075296320826,
|
| 101 |
+
"eval_recall": 0.9276490217590053,
|
| 102 |
+
"eval_runtime": 24.8287,
|
| 103 |
+
"eval_samples_per_second": 1138.077,
|
| 104 |
+
"eval_steps_per_second": 35.604,
|
| 105 |
+
"step": 35330
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.0,
|
| 109 |
+
"grad_norm": 0.060630589723587036,
|
| 110 |
+
"learning_rate": 1.6000094348523446e-05,
|
| 111 |
+
"loss": 0.0069,
|
| 112 |
+
"step": 42396
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.0,
|
| 116 |
+
"eval_accuracy": 0.9842493908405441,
|
| 117 |
+
"eval_f1": 0.9304571065067249,
|
| 118 |
+
"eval_loss": 0.10069137066602707,
|
| 119 |
+
"eval_precision": 0.9249096657633243,
|
| 120 |
+
"eval_recall": 0.9360714938745658,
|
| 121 |
+
"eval_runtime": 24.4078,
|
| 122 |
+
"eval_samples_per_second": 1157.705,
|
| 123 |
+
"eval_steps_per_second": 36.218,
|
| 124 |
+
"step": 42396
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 7.0,
|
| 128 |
+
"grad_norm": 0.6270243525505066,
|
| 129 |
+
"learning_rate": 1.533342768185678e-05,
|
| 130 |
+
"loss": 0.0055,
|
| 131 |
+
"step": 49462
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 7.0,
|
| 135 |
+
"eval_accuracy": 0.9841822394044627,
|
| 136 |
+
"eval_f1": 0.9297173805559187,
|
| 137 |
+
"eval_loss": 0.1080186516046524,
|
| 138 |
+
"eval_precision": 0.924709180731881,
|
| 139 |
+
"eval_recall": 0.9347801243371732,
|
| 140 |
+
"eval_runtime": 25.0447,
|
| 141 |
+
"eval_samples_per_second": 1128.262,
|
| 142 |
+
"eval_steps_per_second": 35.297,
|
| 143 |
+
"step": 49462
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 8.0,
|
| 147 |
+
"grad_norm": 0.0023466802667826414,
|
| 148 |
+
"learning_rate": 1.4666761015190114e-05,
|
| 149 |
+
"loss": 0.0044,
|
| 150 |
+
"step": 56528
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 8.0,
|
| 154 |
+
"eval_accuracy": 0.9840215556109821,
|
| 155 |
+
"eval_f1": 0.9293982272654773,
|
| 156 |
+
"eval_loss": 0.13059474527835846,
|
| 157 |
+
"eval_precision": 0.9265480895915679,
|
| 158 |
+
"eval_recall": 0.9322659535564088,
|
| 159 |
+
"eval_runtime": 24.3355,
|
| 160 |
+
"eval_samples_per_second": 1161.141,
|
| 161 |
+
"eval_steps_per_second": 36.325,
|
| 162 |
+
"step": 56528
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 9.0,
|
| 166 |
+
"grad_norm": 0.28039243817329407,
|
| 167 |
+
"learning_rate": 1.4000094348523448e-05,
|
| 168 |
+
"loss": 0.0038,
|
| 169 |
+
"step": 63594
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 9.0,
|
| 173 |
+
"eval_accuracy": 0.983985581627367,
|
| 174 |
+
"eval_f1": 0.9288880061288766,
|
| 175 |
+
"eval_loss": 0.11633551865816116,
|
| 176 |
+
"eval_precision": 0.9225687907925736,
|
| 177 |
+
"eval_recall": 0.9352943865423295,
|
| 178 |
+
"eval_runtime": 25.2015,
|
| 179 |
+
"eval_samples_per_second": 1121.242,
|
| 180 |
+
"eval_steps_per_second": 35.077,
|
| 181 |
+
"step": 63594
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 10.0,
|
| 185 |
+
"grad_norm": 0.08014234900474548,
|
| 186 |
+
"learning_rate": 1.3333427681856781e-05,
|
| 187 |
+
"loss": 0.0035,
|
| 188 |
+
"step": 70660
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 10.0,
|
| 192 |
+
"eval_accuracy": 0.9841786420061012,
|
| 193 |
+
"eval_f1": 0.9307753433987968,
|
| 194 |
+
"eval_loss": 0.12983541190624237,
|
| 195 |
+
"eval_precision": 0.9246244756191078,
|
| 196 |
+
"eval_recall": 0.9370085938928506,
|
| 197 |
+
"eval_runtime": 24.5312,
|
| 198 |
+
"eval_samples_per_second": 1151.881,
|
| 199 |
+
"eval_steps_per_second": 36.036,
|
| 200 |
+
"step": 70660
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 11.0,
|
| 204 |
+
"grad_norm": 0.00041744596092030406,
|
| 205 |
+
"learning_rate": 1.2666761015190115e-05,
|
| 206 |
+
"loss": 0.0028,
|
| 207 |
+
"step": 77726
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 11.0,
|
| 211 |
+
"eval_accuracy": 0.9843285336044972,
|
| 212 |
+
"eval_f1": 0.9306707629288274,
|
| 213 |
+
"eval_loss": 0.14403043687343597,
|
| 214 |
+
"eval_precision": 0.9266535245734484,
|
| 215 |
+
"eval_recall": 0.9347229840921558,
|
| 216 |
+
"eval_runtime": 25.1796,
|
| 217 |
+
"eval_samples_per_second": 1122.216,
|
| 218 |
+
"eval_steps_per_second": 35.108,
|
| 219 |
+
"step": 77726
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 12.0,
|
| 223 |
+
"grad_norm": 0.00028503904468379915,
|
| 224 |
+
"learning_rate": 1.2000094348523445e-05,
|
| 225 |
+
"loss": 0.0025,
|
| 226 |
+
"step": 84792
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 12.0,
|
| 230 |
+
"eval_accuracy": 0.9844340572897681,
|
| 231 |
+
"eval_f1": 0.9317236158307861,
|
| 232 |
+
"eval_loss": 0.14104171097278595,
|
| 233 |
+
"eval_precision": 0.9281574978169406,
|
| 234 |
+
"eval_recall": 0.9353172426403364,
|
| 235 |
+
"eval_runtime": 24.4922,
|
| 236 |
+
"eval_samples_per_second": 1153.715,
|
| 237 |
+
"eval_steps_per_second": 36.093,
|
| 238 |
+
"step": 84792
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 13.0,
|
| 242 |
+
"grad_norm": 0.0035878911148756742,
|
| 243 |
+
"learning_rate": 1.1333427681856779e-05,
|
| 244 |
+
"loss": 0.0022,
|
| 245 |
+
"step": 91858
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 13.0,
|
| 249 |
+
"eval_accuracy": 0.9844544425471499,
|
| 250 |
+
"eval_f1": 0.9315798786508901,
|
| 251 |
+
"eval_loss": 0.13236555457115173,
|
| 252 |
+
"eval_precision": 0.9305759866808069,
|
| 253 |
+
"eval_recall": 0.9325859389285062,
|
| 254 |
+
"eval_runtime": 25.03,
|
| 255 |
+
"eval_samples_per_second": 1128.927,
|
| 256 |
+
"eval_steps_per_second": 35.318,
|
| 257 |
+
"step": 91858
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 14.0,
|
| 261 |
+
"grad_norm": 0.00016986434638965875,
|
| 262 |
+
"learning_rate": 1.0666761015190112e-05,
|
| 263 |
+
"loss": 0.0021,
|
| 264 |
+
"step": 98924
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 14.0,
|
| 268 |
+
"eval_accuracy": 0.9844880182651906,
|
| 269 |
+
"eval_f1": 0.9330711130112583,
|
| 270 |
+
"eval_loss": 0.13451294600963593,
|
| 271 |
+
"eval_precision": 0.9308583842312985,
|
| 272 |
+
"eval_recall": 0.9352943865423295,
|
| 273 |
+
"eval_runtime": 24.4183,
|
| 274 |
+
"eval_samples_per_second": 1157.205,
|
| 275 |
+
"eval_steps_per_second": 36.202,
|
| 276 |
+
"step": 98924
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 15.0,
|
| 280 |
+
"grad_norm": 0.0010187036823481321,
|
| 281 |
+
"learning_rate": 1.0000094348523446e-05,
|
| 282 |
+
"loss": 0.002,
|
| 283 |
+
"step": 105990
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 15.0,
|
| 287 |
+
"eval_accuracy": 0.9843788971815582,
|
| 288 |
+
"eval_f1": 0.9319383071528353,
|
| 289 |
+
"eval_loss": 0.13619445264339447,
|
| 290 |
+
"eval_precision": 0.929939349802574,
|
| 291 |
+
"eval_recall": 0.9339458767599196,
|
| 292 |
+
"eval_runtime": 25.0941,
|
| 293 |
+
"eval_samples_per_second": 1126.042,
|
| 294 |
+
"eval_steps_per_second": 35.227,
|
| 295 |
+
"step": 105990
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 16.0,
|
| 299 |
+
"grad_norm": 0.00028575636679306626,
|
| 300 |
+
"learning_rate": 9.333427681856779e-06,
|
| 301 |
+
"loss": 0.0017,
|
| 302 |
+
"step": 113056
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 16.0,
|
| 306 |
+
"eval_accuracy": 0.9843669058536866,
|
| 307 |
+
"eval_f1": 0.9323486068748073,
|
| 308 |
+
"eval_loss": 0.15387865900993347,
|
| 309 |
+
"eval_precision": 0.9319972593353888,
|
| 310 |
+
"eval_recall": 0.9327002194185409,
|
| 311 |
+
"eval_runtime": 24.3506,
|
| 312 |
+
"eval_samples_per_second": 1160.422,
|
| 313 |
+
"eval_steps_per_second": 36.303,
|
| 314 |
+
"step": 113056
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 17.0,
|
| 318 |
+
"grad_norm": 0.00035141929402016103,
|
| 319 |
+
"learning_rate": 8.666761015190113e-06,
|
| 320 |
+
"loss": 0.0016,
|
| 321 |
+
"step": 120122
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 17.0,
|
| 325 |
+
"eval_accuracy": 0.9846175246062048,
|
| 326 |
+
"eval_f1": 0.9333576463482042,
|
| 327 |
+
"eval_loss": 0.14764520525932312,
|
| 328 |
+
"eval_precision": 0.9308063874524066,
|
| 329 |
+
"eval_recall": 0.9359229292375205,
|
| 330 |
+
"eval_runtime": 25.0122,
|
| 331 |
+
"eval_samples_per_second": 1129.728,
|
| 332 |
+
"eval_steps_per_second": 35.343,
|
| 333 |
+
"step": 120122
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 18.0,
|
| 337 |
+
"grad_norm": 0.00019602595421019942,
|
| 338 |
+
"learning_rate": 8.000094348523446e-06,
|
| 339 |
+
"loss": 0.0014,
|
| 340 |
+
"step": 127188
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 18.0,
|
| 344 |
+
"eval_accuracy": 0.9846570959881813,
|
| 345 |
+
"eval_f1": 0.9343024019274798,
|
| 346 |
+
"eval_loss": 0.16399884223937988,
|
| 347 |
+
"eval_precision": 0.9335402238524992,
|
| 348 |
+
"eval_recall": 0.93506582556226,
|
| 349 |
+
"eval_runtime": 24.5918,
|
| 350 |
+
"eval_samples_per_second": 1149.04,
|
| 351 |
+
"eval_steps_per_second": 35.947,
|
| 352 |
+
"step": 127188
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 19.0,
|
| 356 |
+
"grad_norm": 0.00016485151718370616,
|
| 357 |
+
"learning_rate": 7.33342768185678e-06,
|
| 358 |
+
"loss": 0.0013,
|
| 359 |
+
"step": 134254
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 19.0,
|
| 363 |
+
"eval_accuracy": 0.984291360488095,
|
| 364 |
+
"eval_f1": 0.9317829016575214,
|
| 365 |
+
"eval_loss": 0.16133514046669006,
|
| 366 |
+
"eval_precision": 0.9272642908070302,
|
| 367 |
+
"eval_recall": 0.9363457670506491,
|
| 368 |
+
"eval_runtime": 36.0736,
|
| 369 |
+
"eval_samples_per_second": 783.315,
|
| 370 |
+
"eval_steps_per_second": 24.505,
|
| 371 |
+
"step": 134254
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 20.0,
|
| 375 |
+
"grad_norm": 3.631131039583124e-05,
|
| 376 |
+
"learning_rate": 6.666761015190113e-06,
|
| 377 |
+
"loss": 0.0011,
|
| 378 |
+
"step": 141320
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 20.0,
|
| 382 |
+
"eval_accuracy": 0.9844688321405959,
|
| 383 |
+
"eval_f1": 0.933409899819197,
|
| 384 |
+
"eval_loss": 0.15595203638076782,
|
| 385 |
+
"eval_precision": 0.9287944963678744,
|
| 386 |
+
"eval_recall": 0.9380714024501737,
|
| 387 |
+
"eval_runtime": 24.4307,
|
| 388 |
+
"eval_samples_per_second": 1156.619,
|
| 389 |
+
"eval_steps_per_second": 36.184,
|
| 390 |
+
"step": 141320
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 21.0,
|
| 394 |
+
"grad_norm": 0.00046227360144257545,
|
| 395 |
+
"learning_rate": 6.000094348523447e-06,
|
| 396 |
+
"loss": 0.001,
|
| 397 |
+
"step": 148386
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 21.0,
|
| 401 |
+
"eval_accuracy": 0.9848237754455977,
|
| 402 |
+
"eval_f1": 0.9352061312288099,
|
| 403 |
+
"eval_loss": 0.15601831674575806,
|
| 404 |
+
"eval_precision": 0.9326181086702049,
|
| 405 |
+
"eval_recall": 0.9378085573230938,
|
| 406 |
+
"eval_runtime": 25.2528,
|
| 407 |
+
"eval_samples_per_second": 1118.963,
|
| 408 |
+
"eval_steps_per_second": 35.006,
|
| 409 |
+
"step": 148386
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 22.0,
|
| 413 |
+
"grad_norm": 1.7225727333425311e-06,
|
| 414 |
+
"learning_rate": 5.33342768185678e-06,
|
| 415 |
+
"loss": 0.0009,
|
| 416 |
+
"step": 155452
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 22.0,
|
| 420 |
+
"eval_accuracy": 0.9847434335488575,
|
| 421 |
+
"eval_f1": 0.9346046246074793,
|
| 422 |
+
"eval_loss": 0.17021338641643524,
|
| 423 |
+
"eval_precision": 0.9338475229902106,
|
| 424 |
+
"eval_recall": 0.9353629548363503,
|
| 425 |
+
"eval_runtime": 27.4692,
|
| 426 |
+
"eval_samples_per_second": 1028.681,
|
| 427 |
+
"eval_steps_per_second": 32.182,
|
| 428 |
+
"step": 155452
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 23.0,
|
| 432 |
+
"grad_norm": 0.00017540222324896604,
|
| 433 |
+
"learning_rate": 4.666761015190113e-06,
|
| 434 |
+
"loss": 0.0009,
|
| 435 |
+
"step": 162518
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 23.0,
|
| 439 |
+
"eval_accuracy": 0.9847638188062393,
|
| 440 |
+
"eval_f1": 0.9339199036024054,
|
| 441 |
+
"eval_loss": 0.16753220558166504,
|
| 442 |
+
"eval_precision": 0.9290092046045638,
|
| 443 |
+
"eval_recall": 0.9388827939294204,
|
| 444 |
+
"eval_runtime": 25.2471,
|
| 445 |
+
"eval_samples_per_second": 1119.219,
|
| 446 |
+
"eval_steps_per_second": 35.014,
|
| 447 |
+
"step": 162518
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 24.0,
|
| 451 |
+
"grad_norm": 1.526959204056766e-05,
|
| 452 |
+
"learning_rate": 4.000094348523446e-06,
|
| 453 |
+
"loss": 0.0008,
|
| 454 |
+
"step": 169584
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 24.0,
|
| 458 |
+
"eval_accuracy": 0.9849400913259531,
|
| 459 |
+
"eval_f1": 0.9357306547788711,
|
| 460 |
+
"eval_loss": 0.17812186479568481,
|
| 461 |
+
"eval_precision": 0.9335486953158769,
|
| 462 |
+
"eval_recall": 0.9379228378131286,
|
| 463 |
+
"eval_runtime": 24.4734,
|
| 464 |
+
"eval_samples_per_second": 1154.601,
|
| 465 |
+
"eval_steps_per_second": 36.121,
|
| 466 |
+
"step": 169584
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 25.0,
|
| 470 |
+
"grad_norm": 8.847219760355074e-06,
|
| 471 |
+
"learning_rate": 3.333427681856779e-06,
|
| 472 |
+
"loss": 0.0007,
|
| 473 |
+
"step": 176650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 25.0,
|
| 477 |
+
"eval_accuracy": 0.9848741390226589,
|
| 478 |
+
"eval_f1": 0.935050123741204,
|
| 479 |
+
"eval_loss": 0.17935001850128174,
|
| 480 |
+
"eval_precision": 0.9331451594545993,
|
| 481 |
+
"eval_recall": 0.9369628816968367,
|
| 482 |
+
"eval_runtime": 25.1905,
|
| 483 |
+
"eval_samples_per_second": 1121.735,
|
| 484 |
+
"eval_steps_per_second": 35.093,
|
| 485 |
+
"step": 176650
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 26.0,
|
| 489 |
+
"grad_norm": 0.00021123145415913314,
|
| 490 |
+
"learning_rate": 2.6667610151901125e-06,
|
| 491 |
+
"loss": 0.0007,
|
| 492 |
+
"step": 183716
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 26.0,
|
| 496 |
+
"eval_accuracy": 0.9848621476947871,
|
| 497 |
+
"eval_f1": 0.9346344803971922,
|
| 498 |
+
"eval_loss": 0.17747123539447784,
|
| 499 |
+
"eval_precision": 0.9334518842760413,
|
| 500 |
+
"eval_recall": 0.9358200767964893,
|
| 501 |
+
"eval_runtime": 24.5312,
|
| 502 |
+
"eval_samples_per_second": 1151.881,
|
| 503 |
+
"eval_steps_per_second": 36.036,
|
| 504 |
+
"step": 183716
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 27.0,
|
| 508 |
+
"grad_norm": 2.859743472072296e-05,
|
| 509 |
+
"learning_rate": 2.000094348523446e-06,
|
| 510 |
+
"loss": 0.0007,
|
| 511 |
+
"step": 190782
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 27.0,
|
| 515 |
+
"eval_accuracy": 0.9849700696456323,
|
| 516 |
+
"eval_f1": 0.9355334631546582,
|
| 517 |
+
"eval_loss": 0.1866326779127121,
|
| 518 |
+
"eval_precision": 0.9322530128685231,
|
| 519 |
+
"eval_recall": 0.9388370817334065,
|
| 520 |
+
"eval_runtime": 25.0727,
|
| 521 |
+
"eval_samples_per_second": 1127.002,
|
| 522 |
+
"eval_steps_per_second": 35.257,
|
| 523 |
+
"step": 190782
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 28.0,
|
| 527 |
+
"grad_norm": 0.0020877772476524115,
|
| 528 |
+
"learning_rate": 1.333427681856779e-06,
|
| 529 |
+
"loss": 0.0007,
|
| 530 |
+
"step": 197848
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 28.0,
|
| 534 |
+
"eval_accuracy": 0.984804589321003,
|
| 535 |
+
"eval_f1": 0.9346563738215604,
|
| 536 |
+
"eval_loss": 0.1925719529390335,
|
| 537 |
+
"eval_precision": 0.9312210726926219,
|
| 538 |
+
"eval_recall": 0.9381171146461876,
|
| 539 |
+
"eval_runtime": 24.3867,
|
| 540 |
+
"eval_samples_per_second": 1158.706,
|
| 541 |
+
"eval_steps_per_second": 36.249,
|
| 542 |
+
"step": 197848
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 29.0,
|
| 546 |
+
"grad_norm": 1.088813405658584e-06,
|
| 547 |
+
"learning_rate": 6.667610151901123e-07,
|
| 548 |
+
"loss": 0.0006,
|
| 549 |
+
"step": 204914
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 29.0,
|
| 553 |
+
"eval_accuracy": 0.9849496843882504,
|
| 554 |
+
"eval_f1": 0.9355303716618523,
|
| 555 |
+
"eval_loss": 0.198269322514534,
|
| 556 |
+
"eval_precision": 0.9328674507130277,
|
| 557 |
+
"eval_recall": 0.9382085390382154,
|
| 558 |
+
"eval_runtime": 25.149,
|
| 559 |
+
"eval_samples_per_second": 1123.581,
|
| 560 |
+
"eval_steps_per_second": 35.15,
|
| 561 |
+
"step": 204914
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 30.0,
|
| 565 |
+
"grad_norm": 5.2584637160180137e-05,
|
| 566 |
+
"learning_rate": 9.434852344560809e-11,
|
| 567 |
+
"loss": 0.0006,
|
| 568 |
+
"step": 211980
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 30.0,
|
| 572 |
+
"eval_accuracy": 0.9849424895915274,
|
| 573 |
+
"eval_f1": 0.9356125356125355,
|
| 574 |
+
"eval_loss": 0.20442676544189453,
|
| 575 |
+
"eval_precision": 0.9329969544070185,
|
| 576 |
+
"eval_recall": 0.9382428231852258,
|
| 577 |
+
"eval_runtime": 24.5229,
|
| 578 |
+
"eval_samples_per_second": 1152.27,
|
| 579 |
+
"eval_steps_per_second": 36.048,
|
| 580 |
+
"step": 211980
|
| 581 |
+
}
|
| 582 |
+
],
|
| 583 |
+
"logging_steps": 500,
|
| 584 |
+
"max_steps": 211980,
|
| 585 |
+
"num_input_tokens_seen": 0,
|
| 586 |
+
"num_train_epochs": 30,
|
| 587 |
+
"save_steps": 500,
|
| 588 |
+
"stateful_callbacks": {
|
| 589 |
+
"TrainerControl": {
|
| 590 |
+
"args": {
|
| 591 |
+
"should_epoch_stop": false,
|
| 592 |
+
"should_evaluate": false,
|
| 593 |
+
"should_log": false,
|
| 594 |
+
"should_save": true,
|
| 595 |
+
"should_training_stop": true
|
| 596 |
+
},
|
| 597 |
+
"attributes": {}
|
| 598 |
+
}
|
| 599 |
+
},
|
| 600 |
+
"total_flos": 4.3987517048244486e+17,
|
| 601 |
+
"train_batch_size": 32,
|
| 602 |
+
"trial_name": null,
|
| 603 |
+
"trial_params": null
|
| 604 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb73d92f0650424273e99cc7811e21f197ac29cf0ac5e1db9a33b5063216acaa
|
| 3 |
+
size 5841
|