Upload 8 files
Browse files- config.json +34 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +127 -0
- tokenizer.json +1947 -0
- tokenizer_config.json +1328 -0
- trainer_state.json +149 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/acf15718oa/ReactionT5_neword/forward_reaction_prediction_drop_dup/t5/checkpoint-486000",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2048,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"eval_beams": 5,
|
| 15 |
+
"feed_forward_proj": "gated-gelu",
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"max_length": 150,
|
| 21 |
+
"model_type": "t5",
|
| 22 |
+
"num_decoder_layers": 12,
|
| 23 |
+
"num_heads": 12,
|
| 24 |
+
"num_layers": 12,
|
| 25 |
+
"output_past": true,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"relative_attention_max_distance": 128,
|
| 28 |
+
"relative_attention_num_buckets": 32,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.40.2",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 268
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"max_length": 150,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.40.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5fdde934cb203742547527154c3af33560a143e606118dcea81076f0e4ab458
|
| 3 |
+
size 794597224
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>",
|
| 103 |
+
"REACTANT:",
|
| 104 |
+
"REAGENT:"
|
| 105 |
+
],
|
| 106 |
+
"eos_token": {
|
| 107 |
+
"content": "</s>",
|
| 108 |
+
"lstrip": false,
|
| 109 |
+
"normalized": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"single_word": false
|
| 112 |
+
},
|
| 113 |
+
"pad_token": {
|
| 114 |
+
"content": "<pad>",
|
| 115 |
+
"lstrip": false,
|
| 116 |
+
"normalized": false,
|
| 117 |
+
"rstrip": false,
|
| 118 |
+
"single_word": false
|
| 119 |
+
},
|
| 120 |
+
"unk_token": {
|
| 121 |
+
"content": "<unk>",
|
| 122 |
+
"lstrip": false,
|
| 123 |
+
"normalized": false,
|
| 124 |
+
"rstrip": false,
|
| 125 |
+
"single_word": false
|
| 126 |
+
}
|
| 127 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,1947 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 150,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": null,
|
| 10 |
+
"added_tokens": [
|
| 11 |
+
{
|
| 12 |
+
"id": 0,
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"single_word": false,
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"id": 1,
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"id": 2,
|
| 31 |
+
"content": "<unk>",
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"id": 36,
|
| 40 |
+
"content": "Cl",
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"lstrip": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"normalized": true,
|
| 45 |
+
"special": false
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"id": 121,
|
| 49 |
+
"content": "<extra_id_0>",
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"rstrip": false,
|
| 53 |
+
"normalized": false,
|
| 54 |
+
"special": true
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"id": 122,
|
| 58 |
+
"content": "<extra_id_1>",
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"lstrip": false,
|
| 61 |
+
"rstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"special": true
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"id": 123,
|
| 67 |
+
"content": "<extra_id_2>",
|
| 68 |
+
"single_word": false,
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"special": true
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"id": 124,
|
| 76 |
+
"content": "<extra_id_3>",
|
| 77 |
+
"single_word": false,
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"id": 125,
|
| 85 |
+
"content": "<extra_id_4>",
|
| 86 |
+
"single_word": false,
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"id": 126,
|
| 94 |
+
"content": "<extra_id_5>",
|
| 95 |
+
"single_word": false,
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"normalized": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"id": 127,
|
| 103 |
+
"content": "<extra_id_6>",
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"lstrip": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"id": 128,
|
| 112 |
+
"content": "<extra_id_7>",
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"lstrip": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"normalized": false,
|
| 117 |
+
"special": true
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"id": 129,
|
| 121 |
+
"content": "<extra_id_8>",
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"lstrip": false,
|
| 124 |
+
"rstrip": false,
|
| 125 |
+
"normalized": false,
|
| 126 |
+
"special": true
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"id": 130,
|
| 130 |
+
"content": "<extra_id_9>",
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"lstrip": false,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"special": true
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"id": 131,
|
| 139 |
+
"content": "<extra_id_10>",
|
| 140 |
+
"single_word": false,
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"rstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"special": true
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"id": 132,
|
| 148 |
+
"content": "<extra_id_11>",
|
| 149 |
+
"single_word": false,
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"id": 133,
|
| 157 |
+
"content": "<extra_id_12>",
|
| 158 |
+
"single_word": false,
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"id": 134,
|
| 166 |
+
"content": "<extra_id_13>",
|
| 167 |
+
"single_word": false,
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"normalized": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"id": 135,
|
| 175 |
+
"content": "<extra_id_14>",
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"lstrip": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"normalized": false,
|
| 180 |
+
"special": true
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"id": 136,
|
| 184 |
+
"content": "<extra_id_15>",
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"lstrip": false,
|
| 187 |
+
"rstrip": false,
|
| 188 |
+
"normalized": false,
|
| 189 |
+
"special": true
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"id": 137,
|
| 193 |
+
"content": "<extra_id_16>",
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"lstrip": false,
|
| 196 |
+
"rstrip": false,
|
| 197 |
+
"normalized": false,
|
| 198 |
+
"special": true
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"id": 138,
|
| 202 |
+
"content": "<extra_id_17>",
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"lstrip": false,
|
| 205 |
+
"rstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"special": true
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"id": 139,
|
| 211 |
+
"content": "<extra_id_18>",
|
| 212 |
+
"single_word": false,
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"rstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"special": true
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"id": 140,
|
| 220 |
+
"content": "<extra_id_19>",
|
| 221 |
+
"single_word": false,
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"id": 141,
|
| 229 |
+
"content": "<extra_id_20>",
|
| 230 |
+
"single_word": false,
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"id": 142,
|
| 238 |
+
"content": "<extra_id_21>",
|
| 239 |
+
"single_word": false,
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"normalized": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"id": 143,
|
| 247 |
+
"content": "<extra_id_22>",
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"lstrip": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"normalized": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"id": 144,
|
| 256 |
+
"content": "<extra_id_23>",
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"lstrip": false,
|
| 259 |
+
"rstrip": false,
|
| 260 |
+
"normalized": false,
|
| 261 |
+
"special": true
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"id": 145,
|
| 265 |
+
"content": "<extra_id_24>",
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"lstrip": false,
|
| 268 |
+
"rstrip": false,
|
| 269 |
+
"normalized": false,
|
| 270 |
+
"special": true
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"id": 146,
|
| 274 |
+
"content": "<extra_id_25>",
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"lstrip": false,
|
| 277 |
+
"rstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"special": true
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"id": 147,
|
| 283 |
+
"content": "<extra_id_26>",
|
| 284 |
+
"single_word": false,
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"rstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"special": true
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"id": 148,
|
| 292 |
+
"content": "<extra_id_27>",
|
| 293 |
+
"single_word": false,
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"id": 149,
|
| 301 |
+
"content": "<extra_id_28>",
|
| 302 |
+
"single_word": false,
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"id": 150,
|
| 310 |
+
"content": "<extra_id_29>",
|
| 311 |
+
"single_word": false,
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"normalized": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"id": 151,
|
| 319 |
+
"content": "<extra_id_30>",
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"lstrip": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"normalized": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"id": 152,
|
| 328 |
+
"content": "<extra_id_31>",
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"lstrip": false,
|
| 331 |
+
"rstrip": false,
|
| 332 |
+
"normalized": false,
|
| 333 |
+
"special": true
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"id": 153,
|
| 337 |
+
"content": "<extra_id_32>",
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"lstrip": false,
|
| 340 |
+
"rstrip": false,
|
| 341 |
+
"normalized": false,
|
| 342 |
+
"special": true
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"id": 154,
|
| 346 |
+
"content": "<extra_id_33>",
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"lstrip": false,
|
| 349 |
+
"rstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"special": true
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"id": 155,
|
| 355 |
+
"content": "<extra_id_34>",
|
| 356 |
+
"single_word": false,
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"rstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"special": true
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"id": 156,
|
| 364 |
+
"content": "<extra_id_35>",
|
| 365 |
+
"single_word": false,
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"id": 157,
|
| 373 |
+
"content": "<extra_id_36>",
|
| 374 |
+
"single_word": false,
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"id": 158,
|
| 382 |
+
"content": "<extra_id_37>",
|
| 383 |
+
"single_word": false,
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"normalized": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"id": 159,
|
| 391 |
+
"content": "<extra_id_38>",
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"lstrip": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"normalized": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"id": 160,
|
| 400 |
+
"content": "<extra_id_39>",
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"lstrip": false,
|
| 403 |
+
"rstrip": false,
|
| 404 |
+
"normalized": false,
|
| 405 |
+
"special": true
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"id": 161,
|
| 409 |
+
"content": "<extra_id_40>",
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"lstrip": false,
|
| 412 |
+
"rstrip": false,
|
| 413 |
+
"normalized": false,
|
| 414 |
+
"special": true
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"id": 162,
|
| 418 |
+
"content": "<extra_id_41>",
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"lstrip": false,
|
| 421 |
+
"rstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"special": true
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"id": 163,
|
| 427 |
+
"content": "<extra_id_42>",
|
| 428 |
+
"single_word": false,
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"rstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"special": true
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"id": 164,
|
| 436 |
+
"content": "<extra_id_43>",
|
| 437 |
+
"single_word": false,
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"id": 165,
|
| 445 |
+
"content": "<extra_id_44>",
|
| 446 |
+
"single_word": false,
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"normalized": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"id": 166,
|
| 454 |
+
"content": "<extra_id_45>",
|
| 455 |
+
"single_word": false,
|
| 456 |
+
"lstrip": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"normalized": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"id": 167,
|
| 463 |
+
"content": "<extra_id_46>",
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"lstrip": false,
|
| 466 |
+
"rstrip": false,
|
| 467 |
+
"normalized": false,
|
| 468 |
+
"special": true
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"id": 168,
|
| 472 |
+
"content": "<extra_id_47>",
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"lstrip": false,
|
| 475 |
+
"rstrip": false,
|
| 476 |
+
"normalized": false,
|
| 477 |
+
"special": true
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"id": 169,
|
| 481 |
+
"content": "<extra_id_48>",
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"lstrip": false,
|
| 484 |
+
"rstrip": false,
|
| 485 |
+
"normalized": false,
|
| 486 |
+
"special": true
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"id": 170,
|
| 490 |
+
"content": "<extra_id_49>",
|
| 491 |
+
"single_word": false,
|
| 492 |
+
"lstrip": false,
|
| 493 |
+
"rstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"special": true
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"id": 171,
|
| 499 |
+
"content": "<extra_id_50>",
|
| 500 |
+
"single_word": false,
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"rstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"special": true
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"id": 172,
|
| 508 |
+
"content": "<extra_id_51>",
|
| 509 |
+
"single_word": false,
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"id": 173,
|
| 517 |
+
"content": "<extra_id_52>",
|
| 518 |
+
"single_word": false,
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"normalized": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"id": 174,
|
| 526 |
+
"content": "<extra_id_53>",
|
| 527 |
+
"single_word": false,
|
| 528 |
+
"lstrip": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"normalized": false,
|
| 531 |
+
"special": true
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"id": 175,
|
| 535 |
+
"content": "<extra_id_54>",
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"lstrip": false,
|
| 538 |
+
"rstrip": false,
|
| 539 |
+
"normalized": false,
|
| 540 |
+
"special": true
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"id": 176,
|
| 544 |
+
"content": "<extra_id_55>",
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"lstrip": false,
|
| 547 |
+
"rstrip": false,
|
| 548 |
+
"normalized": false,
|
| 549 |
+
"special": true
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"id": 177,
|
| 553 |
+
"content": "<extra_id_56>",
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"lstrip": false,
|
| 556 |
+
"rstrip": false,
|
| 557 |
+
"normalized": false,
|
| 558 |
+
"special": true
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"id": 178,
|
| 562 |
+
"content": "<extra_id_57>",
|
| 563 |
+
"single_word": false,
|
| 564 |
+
"lstrip": false,
|
| 565 |
+
"rstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"special": true
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"id": 179,
|
| 571 |
+
"content": "<extra_id_58>",
|
| 572 |
+
"single_word": false,
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"rstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"special": true
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"id": 180,
|
| 580 |
+
"content": "<extra_id_59>",
|
| 581 |
+
"single_word": false,
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"id": 181,
|
| 589 |
+
"content": "<extra_id_60>",
|
| 590 |
+
"single_word": false,
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"normalized": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"id": 182,
|
| 598 |
+
"content": "<extra_id_61>",
|
| 599 |
+
"single_word": false,
|
| 600 |
+
"lstrip": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"normalized": false,
|
| 603 |
+
"special": true
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"id": 183,
|
| 607 |
+
"content": "<extra_id_62>",
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"lstrip": false,
|
| 610 |
+
"rstrip": false,
|
| 611 |
+
"normalized": false,
|
| 612 |
+
"special": true
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"id": 184,
|
| 616 |
+
"content": "<extra_id_63>",
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"lstrip": false,
|
| 619 |
+
"rstrip": false,
|
| 620 |
+
"normalized": false,
|
| 621 |
+
"special": true
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"id": 185,
|
| 625 |
+
"content": "<extra_id_64>",
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"lstrip": false,
|
| 628 |
+
"rstrip": false,
|
| 629 |
+
"normalized": false,
|
| 630 |
+
"special": true
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"id": 186,
|
| 634 |
+
"content": "<extra_id_65>",
|
| 635 |
+
"single_word": false,
|
| 636 |
+
"lstrip": false,
|
| 637 |
+
"rstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"special": true
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"id": 187,
|
| 643 |
+
"content": "<extra_id_66>",
|
| 644 |
+
"single_word": false,
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"rstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"special": true
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"id": 188,
|
| 652 |
+
"content": "<extra_id_67>",
|
| 653 |
+
"single_word": false,
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"id": 189,
|
| 661 |
+
"content": "<extra_id_68>",
|
| 662 |
+
"single_word": false,
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"normalized": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"id": 190,
|
| 670 |
+
"content": "<extra_id_69>",
|
| 671 |
+
"single_word": false,
|
| 672 |
+
"lstrip": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"normalized": false,
|
| 675 |
+
"special": true
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"id": 191,
|
| 679 |
+
"content": "<extra_id_70>",
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"lstrip": false,
|
| 682 |
+
"rstrip": false,
|
| 683 |
+
"normalized": false,
|
| 684 |
+
"special": true
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"id": 192,
|
| 688 |
+
"content": "<extra_id_71>",
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"lstrip": false,
|
| 691 |
+
"rstrip": false,
|
| 692 |
+
"normalized": false,
|
| 693 |
+
"special": true
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"id": 193,
|
| 697 |
+
"content": "<extra_id_72>",
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"lstrip": false,
|
| 700 |
+
"rstrip": false,
|
| 701 |
+
"normalized": false,
|
| 702 |
+
"special": true
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"id": 194,
|
| 706 |
+
"content": "<extra_id_73>",
|
| 707 |
+
"single_word": false,
|
| 708 |
+
"lstrip": false,
|
| 709 |
+
"rstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"special": true
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"id": 195,
|
| 715 |
+
"content": "<extra_id_74>",
|
| 716 |
+
"single_word": false,
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"rstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"special": true
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"id": 196,
|
| 724 |
+
"content": "<extra_id_75>",
|
| 725 |
+
"single_word": false,
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"id": 197,
|
| 733 |
+
"content": "<extra_id_76>",
|
| 734 |
+
"single_word": false,
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"normalized": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"id": 198,
|
| 742 |
+
"content": "<extra_id_77>",
|
| 743 |
+
"single_word": false,
|
| 744 |
+
"lstrip": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"normalized": false,
|
| 747 |
+
"special": true
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"id": 199,
|
| 751 |
+
"content": "<extra_id_78>",
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"lstrip": false,
|
| 754 |
+
"rstrip": false,
|
| 755 |
+
"normalized": false,
|
| 756 |
+
"special": true
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"id": 200,
|
| 760 |
+
"content": "<extra_id_79>",
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"lstrip": false,
|
| 763 |
+
"rstrip": false,
|
| 764 |
+
"normalized": false,
|
| 765 |
+
"special": true
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"id": 201,
|
| 769 |
+
"content": "<extra_id_80>",
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"lstrip": false,
|
| 772 |
+
"rstrip": false,
|
| 773 |
+
"normalized": false,
|
| 774 |
+
"special": true
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"id": 202,
|
| 778 |
+
"content": "<extra_id_81>",
|
| 779 |
+
"single_word": false,
|
| 780 |
+
"lstrip": false,
|
| 781 |
+
"rstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"special": true
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"id": 203,
|
| 787 |
+
"content": "<extra_id_82>",
|
| 788 |
+
"single_word": false,
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"rstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"special": true
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"id": 204,
|
| 796 |
+
"content": "<extra_id_83>",
|
| 797 |
+
"single_word": false,
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"normalized": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"id": 205,
|
| 805 |
+
"content": "<extra_id_84>",
|
| 806 |
+
"single_word": false,
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"normalized": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"id": 206,
|
| 814 |
+
"content": "<extra_id_85>",
|
| 815 |
+
"single_word": false,
|
| 816 |
+
"lstrip": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"normalized": false,
|
| 819 |
+
"special": true
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"id": 207,
|
| 823 |
+
"content": "<extra_id_86>",
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"lstrip": false,
|
| 826 |
+
"rstrip": false,
|
| 827 |
+
"normalized": false,
|
| 828 |
+
"special": true
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"id": 208,
|
| 832 |
+
"content": "<extra_id_87>",
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"lstrip": false,
|
| 835 |
+
"rstrip": false,
|
| 836 |
+
"normalized": false,
|
| 837 |
+
"special": true
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"id": 209,
|
| 841 |
+
"content": "<extra_id_88>",
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"lstrip": false,
|
| 844 |
+
"rstrip": false,
|
| 845 |
+
"normalized": false,
|
| 846 |
+
"special": true
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"id": 210,
|
| 850 |
+
"content": "<extra_id_89>",
|
| 851 |
+
"single_word": false,
|
| 852 |
+
"lstrip": false,
|
| 853 |
+
"rstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"special": true
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"id": 211,
|
| 859 |
+
"content": "<extra_id_90>",
|
| 860 |
+
"single_word": false,
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"rstrip": false,
|
| 863 |
+
"normalized": false,
|
| 864 |
+
"special": true
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"id": 212,
|
| 868 |
+
"content": "<extra_id_91>",
|
| 869 |
+
"single_word": false,
|
| 870 |
+
"lstrip": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"normalized": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"id": 213,
|
| 877 |
+
"content": "<extra_id_92>",
|
| 878 |
+
"single_word": false,
|
| 879 |
+
"lstrip": false,
|
| 880 |
+
"rstrip": false,
|
| 881 |
+
"normalized": false,
|
| 882 |
+
"special": true
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"id": 214,
|
| 886 |
+
"content": "<extra_id_93>",
|
| 887 |
+
"single_word": false,
|
| 888 |
+
"lstrip": false,
|
| 889 |
+
"rstrip": false,
|
| 890 |
+
"normalized": false,
|
| 891 |
+
"special": true
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"id": 215,
|
| 895 |
+
"content": "<extra_id_94>",
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"lstrip": false,
|
| 898 |
+
"rstrip": false,
|
| 899 |
+
"normalized": false,
|
| 900 |
+
"special": true
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"id": 216,
|
| 904 |
+
"content": "<extra_id_95>",
|
| 905 |
+
"single_word": false,
|
| 906 |
+
"lstrip": false,
|
| 907 |
+
"rstrip": false,
|
| 908 |
+
"normalized": false,
|
| 909 |
+
"special": true
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"id": 217,
|
| 913 |
+
"content": "<extra_id_96>",
|
| 914 |
+
"single_word": false,
|
| 915 |
+
"lstrip": false,
|
| 916 |
+
"rstrip": false,
|
| 917 |
+
"normalized": false,
|
| 918 |
+
"special": true
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"id": 218,
|
| 922 |
+
"content": "<extra_id_97>",
|
| 923 |
+
"single_word": false,
|
| 924 |
+
"lstrip": false,
|
| 925 |
+
"rstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"special": true
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"id": 219,
|
| 931 |
+
"content": "<extra_id_98>",
|
| 932 |
+
"single_word": false,
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"rstrip": false,
|
| 935 |
+
"normalized": false,
|
| 936 |
+
"special": true
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"id": 220,
|
| 940 |
+
"content": "<extra_id_99>",
|
| 941 |
+
"single_word": false,
|
| 942 |
+
"lstrip": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"normalized": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"id": 221,
|
| 949 |
+
"content": ".",
|
| 950 |
+
"single_word": false,
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"rstrip": false,
|
| 953 |
+
"normalized": true,
|
| 954 |
+
"special": false
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"id": 222,
|
| 958 |
+
"content": "6",
|
| 959 |
+
"single_word": false,
|
| 960 |
+
"lstrip": false,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"normalized": true,
|
| 963 |
+
"special": false
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"id": 223,
|
| 967 |
+
"content": "7",
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"lstrip": false,
|
| 970 |
+
"rstrip": false,
|
| 971 |
+
"normalized": true,
|
| 972 |
+
"special": false
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"id": 224,
|
| 976 |
+
"content": "8",
|
| 977 |
+
"single_word": false,
|
| 978 |
+
"lstrip": false,
|
| 979 |
+
"rstrip": false,
|
| 980 |
+
"normalized": true,
|
| 981 |
+
"special": false
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"id": 225,
|
| 985 |
+
"content": "<",
|
| 986 |
+
"single_word": false,
|
| 987 |
+
"lstrip": false,
|
| 988 |
+
"rstrip": false,
|
| 989 |
+
"normalized": true,
|
| 990 |
+
"special": false
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"id": 226,
|
| 994 |
+
"content": ">",
|
| 995 |
+
"single_word": false,
|
| 996 |
+
"lstrip": false,
|
| 997 |
+
"rstrip": false,
|
| 998 |
+
"normalized": true,
|
| 999 |
+
"special": false
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"id": 227,
|
| 1003 |
+
"content": "Ag",
|
| 1004 |
+
"single_word": false,
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"rstrip": false,
|
| 1007 |
+
"normalized": true,
|
| 1008 |
+
"special": false
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"id": 228,
|
| 1012 |
+
"content": "Al",
|
| 1013 |
+
"single_word": false,
|
| 1014 |
+
"lstrip": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"normalized": true,
|
| 1017 |
+
"special": false
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"id": 229,
|
| 1021 |
+
"content": "Ar",
|
| 1022 |
+
"single_word": false,
|
| 1023 |
+
"lstrip": false,
|
| 1024 |
+
"rstrip": false,
|
| 1025 |
+
"normalized": true,
|
| 1026 |
+
"special": false
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"id": 230,
|
| 1030 |
+
"content": "As",
|
| 1031 |
+
"single_word": false,
|
| 1032 |
+
"lstrip": false,
|
| 1033 |
+
"rstrip": false,
|
| 1034 |
+
"normalized": true,
|
| 1035 |
+
"special": false
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"id": 231,
|
| 1039 |
+
"content": "Au",
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"lstrip": false,
|
| 1042 |
+
"rstrip": false,
|
| 1043 |
+
"normalized": true,
|
| 1044 |
+
"special": false
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"id": 232,
|
| 1048 |
+
"content": "Ba",
|
| 1049 |
+
"single_word": false,
|
| 1050 |
+
"lstrip": false,
|
| 1051 |
+
"rstrip": false,
|
| 1052 |
+
"normalized": true,
|
| 1053 |
+
"special": false
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"id": 233,
|
| 1057 |
+
"content": "Bi",
|
| 1058 |
+
"single_word": false,
|
| 1059 |
+
"lstrip": false,
|
| 1060 |
+
"rstrip": false,
|
| 1061 |
+
"normalized": true,
|
| 1062 |
+
"special": false
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"id": 234,
|
| 1066 |
+
"content": "Ca",
|
| 1067 |
+
"single_word": false,
|
| 1068 |
+
"lstrip": false,
|
| 1069 |
+
"rstrip": false,
|
| 1070 |
+
"normalized": true,
|
| 1071 |
+
"special": false
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"id": 235,
|
| 1075 |
+
"content": "Cu",
|
| 1076 |
+
"single_word": false,
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"rstrip": false,
|
| 1079 |
+
"normalized": true,
|
| 1080 |
+
"special": false
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"id": 236,
|
| 1084 |
+
"content": "Fe",
|
| 1085 |
+
"single_word": false,
|
| 1086 |
+
"lstrip": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"normalized": true,
|
| 1089 |
+
"special": false
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"id": 237,
|
| 1093 |
+
"content": "Ge",
|
| 1094 |
+
"single_word": false,
|
| 1095 |
+
"lstrip": false,
|
| 1096 |
+
"rstrip": false,
|
| 1097 |
+
"normalized": true,
|
| 1098 |
+
"special": false
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"id": 238,
|
| 1102 |
+
"content": "Hg",
|
| 1103 |
+
"single_word": false,
|
| 1104 |
+
"lstrip": false,
|
| 1105 |
+
"rstrip": false,
|
| 1106 |
+
"normalized": true,
|
| 1107 |
+
"special": false
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"id": 239,
|
| 1111 |
+
"content": "K",
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"lstrip": false,
|
| 1114 |
+
"rstrip": false,
|
| 1115 |
+
"normalized": true,
|
| 1116 |
+
"special": false
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"id": 240,
|
| 1120 |
+
"content": "Li",
|
| 1121 |
+
"single_word": false,
|
| 1122 |
+
"lstrip": false,
|
| 1123 |
+
"rstrip": false,
|
| 1124 |
+
"normalized": true,
|
| 1125 |
+
"special": false
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"id": 241,
|
| 1129 |
+
"content": "Mg",
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"lstrip": false,
|
| 1132 |
+
"rstrip": false,
|
| 1133 |
+
"normalized": true,
|
| 1134 |
+
"special": false
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"id": 242,
|
| 1138 |
+
"content": "Mn",
|
| 1139 |
+
"single_word": false,
|
| 1140 |
+
"lstrip": false,
|
| 1141 |
+
"rstrip": false,
|
| 1142 |
+
"normalized": true,
|
| 1143 |
+
"special": false
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"id": 243,
|
| 1147 |
+
"content": "Mo",
|
| 1148 |
+
"single_word": false,
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"rstrip": false,
|
| 1151 |
+
"normalized": true,
|
| 1152 |
+
"special": false
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"id": 244,
|
| 1156 |
+
"content": "Na",
|
| 1157 |
+
"single_word": false,
|
| 1158 |
+
"lstrip": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"normalized": true,
|
| 1161 |
+
"special": false
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"id": 245,
|
| 1165 |
+
"content": "Nd",
|
| 1166 |
+
"single_word": false,
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"rstrip": false,
|
| 1169 |
+
"normalized": true,
|
| 1170 |
+
"special": false
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"id": 246,
|
| 1174 |
+
"content": "Ni",
|
| 1175 |
+
"single_word": false,
|
| 1176 |
+
"lstrip": false,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"normalized": true,
|
| 1179 |
+
"special": false
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"id": 247,
|
| 1183 |
+
"content": "P",
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"lstrip": false,
|
| 1186 |
+
"rstrip": false,
|
| 1187 |
+
"normalized": true,
|
| 1188 |
+
"special": false
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"id": 248,
|
| 1192 |
+
"content": "Pb",
|
| 1193 |
+
"single_word": false,
|
| 1194 |
+
"lstrip": false,
|
| 1195 |
+
"rstrip": false,
|
| 1196 |
+
"normalized": true,
|
| 1197 |
+
"special": false
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"id": 249,
|
| 1201 |
+
"content": "Pd",
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"lstrip": false,
|
| 1204 |
+
"rstrip": false,
|
| 1205 |
+
"normalized": true,
|
| 1206 |
+
"special": false
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"id": 250,
|
| 1210 |
+
"content": "Pt",
|
| 1211 |
+
"single_word": false,
|
| 1212 |
+
"lstrip": false,
|
| 1213 |
+
"rstrip": false,
|
| 1214 |
+
"normalized": true,
|
| 1215 |
+
"special": false
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"id": 251,
|
| 1219 |
+
"content": "Re",
|
| 1220 |
+
"single_word": false,
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"rstrip": false,
|
| 1223 |
+
"normalized": true,
|
| 1224 |
+
"special": false
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"id": 252,
|
| 1228 |
+
"content": "Rh",
|
| 1229 |
+
"single_word": false,
|
| 1230 |
+
"lstrip": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"normalized": true,
|
| 1233 |
+
"special": false
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"id": 253,
|
| 1237 |
+
"content": "Ru",
|
| 1238 |
+
"single_word": false,
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"rstrip": false,
|
| 1241 |
+
"normalized": true,
|
| 1242 |
+
"special": false
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"id": 254,
|
| 1246 |
+
"content": "Sb",
|
| 1247 |
+
"single_word": false,
|
| 1248 |
+
"lstrip": false,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"normalized": true,
|
| 1251 |
+
"special": false
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"id": 255,
|
| 1255 |
+
"content": "Si",
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"lstrip": false,
|
| 1258 |
+
"rstrip": false,
|
| 1259 |
+
"normalized": true,
|
| 1260 |
+
"special": false
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"id": 256,
|
| 1264 |
+
"content": "Sm",
|
| 1265 |
+
"single_word": false,
|
| 1266 |
+
"lstrip": false,
|
| 1267 |
+
"rstrip": false,
|
| 1268 |
+
"normalized": true,
|
| 1269 |
+
"special": false
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"id": 257,
|
| 1273 |
+
"content": "Ta",
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"lstrip": false,
|
| 1276 |
+
"rstrip": false,
|
| 1277 |
+
"normalized": true,
|
| 1278 |
+
"special": false
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"id": 258,
|
| 1282 |
+
"content": "Ti",
|
| 1283 |
+
"single_word": false,
|
| 1284 |
+
"lstrip": false,
|
| 1285 |
+
"rstrip": false,
|
| 1286 |
+
"normalized": true,
|
| 1287 |
+
"special": false
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"id": 259,
|
| 1291 |
+
"content": "Tl",
|
| 1292 |
+
"single_word": false,
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"rstrip": false,
|
| 1295 |
+
"normalized": true,
|
| 1296 |
+
"special": false
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"id": 260,
|
| 1300 |
+
"content": "W",
|
| 1301 |
+
"single_word": false,
|
| 1302 |
+
"lstrip": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"normalized": true,
|
| 1305 |
+
"special": false
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"id": 261,
|
| 1309 |
+
"content": "Yb",
|
| 1310 |
+
"single_word": false,
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"rstrip": false,
|
| 1313 |
+
"normalized": true,
|
| 1314 |
+
"special": false
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"id": 262,
|
| 1318 |
+
"content": "Zn",
|
| 1319 |
+
"single_word": false,
|
| 1320 |
+
"lstrip": false,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"normalized": true,
|
| 1323 |
+
"special": false
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"id": 263,
|
| 1327 |
+
"content": "Zr",
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"lstrip": false,
|
| 1330 |
+
"rstrip": false,
|
| 1331 |
+
"normalized": true,
|
| 1332 |
+
"special": false
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"id": 264,
|
| 1336 |
+
"content": "e",
|
| 1337 |
+
"single_word": false,
|
| 1338 |
+
"lstrip": false,
|
| 1339 |
+
"rstrip": false,
|
| 1340 |
+
"normalized": true,
|
| 1341 |
+
"special": false
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"id": 265,
|
| 1345 |
+
"content": "p",
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"lstrip": false,
|
| 1348 |
+
"rstrip": false,
|
| 1349 |
+
"normalized": true,
|
| 1350 |
+
"special": false
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"id": 266,
|
| 1354 |
+
"content": "REACTANT:",
|
| 1355 |
+
"single_word": false,
|
| 1356 |
+
"lstrip": false,
|
| 1357 |
+
"rstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"special": true
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"id": 267,
|
| 1363 |
+
"content": "REAGENT:",
|
| 1364 |
+
"single_word": false,
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"rstrip": false,
|
| 1367 |
+
"normalized": false,
|
| 1368 |
+
"special": true
|
| 1369 |
+
}
|
| 1370 |
+
],
|
| 1371 |
+
"normalizer": {
|
| 1372 |
+
"type": "Sequence",
|
| 1373 |
+
"normalizers": [
|
| 1374 |
+
{
|
| 1375 |
+
"type": "Nmt"
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"type": "NFKC"
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"type": "Replace",
|
| 1382 |
+
"pattern": {
|
| 1383 |
+
"Regex": " {2,}"
|
| 1384 |
+
},
|
| 1385 |
+
"content": " "
|
| 1386 |
+
}
|
| 1387 |
+
]
|
| 1388 |
+
},
|
| 1389 |
+
"pre_tokenizer": {
|
| 1390 |
+
"type": "Sequence",
|
| 1391 |
+
"pretokenizers": [
|
| 1392 |
+
{
|
| 1393 |
+
"type": "Metaspace",
|
| 1394 |
+
"replacement": "▁",
|
| 1395 |
+
"prepend_scheme": "always",
|
| 1396 |
+
"split": true
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"type": "Digits",
|
| 1400 |
+
"individual_digits": true
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"type": "Punctuation",
|
| 1404 |
+
"behavior": "Isolated"
|
| 1405 |
+
}
|
| 1406 |
+
]
|
| 1407 |
+
},
|
| 1408 |
+
"post_processor": {
|
| 1409 |
+
"type": "TemplateProcessing",
|
| 1410 |
+
"single": [
|
| 1411 |
+
{
|
| 1412 |
+
"Sequence": {
|
| 1413 |
+
"id": "A",
|
| 1414 |
+
"type_id": 0
|
| 1415 |
+
}
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"SpecialToken": {
|
| 1419 |
+
"id": "</s>",
|
| 1420 |
+
"type_id": 0
|
| 1421 |
+
}
|
| 1422 |
+
}
|
| 1423 |
+
],
|
| 1424 |
+
"pair": [
|
| 1425 |
+
{
|
| 1426 |
+
"Sequence": {
|
| 1427 |
+
"id": "A",
|
| 1428 |
+
"type_id": 0
|
| 1429 |
+
}
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"Sequence": {
|
| 1433 |
+
"id": "B",
|
| 1434 |
+
"type_id": 1
|
| 1435 |
+
}
|
| 1436 |
+
}
|
| 1437 |
+
],
|
| 1438 |
+
"special_tokens": {
|
| 1439 |
+
"</s>": {
|
| 1440 |
+
"id": "</s>",
|
| 1441 |
+
"ids": [
|
| 1442 |
+
1
|
| 1443 |
+
],
|
| 1444 |
+
"tokens": [
|
| 1445 |
+
"</s>"
|
| 1446 |
+
]
|
| 1447 |
+
}
|
| 1448 |
+
}
|
| 1449 |
+
},
|
| 1450 |
+
"decoder": {
|
| 1451 |
+
"type": "Metaspace",
|
| 1452 |
+
"replacement": "▁",
|
| 1453 |
+
"prepend_scheme": "always",
|
| 1454 |
+
"split": true
|
| 1455 |
+
},
|
| 1456 |
+
"model": {
|
| 1457 |
+
"type": "Unigram",
|
| 1458 |
+
"unk_id": 2,
|
| 1459 |
+
"vocab": [
|
| 1460 |
+
[
|
| 1461 |
+
"<pad>",
|
| 1462 |
+
0.0
|
| 1463 |
+
],
|
| 1464 |
+
[
|
| 1465 |
+
"</s>",
|
| 1466 |
+
0.0
|
| 1467 |
+
],
|
| 1468 |
+
[
|
| 1469 |
+
"<unk>",
|
| 1470 |
+
0.0
|
| 1471 |
+
],
|
| 1472 |
+
[
|
| 1473 |
+
"C",
|
| 1474 |
+
-1.934062026530869
|
| 1475 |
+
],
|
| 1476 |
+
[
|
| 1477 |
+
"c",
|
| 1478 |
+
-2.005135123981896
|
| 1479 |
+
],
|
| 1480 |
+
[
|
| 1481 |
+
")",
|
| 1482 |
+
-2.3305416341016603
|
| 1483 |
+
],
|
| 1484 |
+
[
|
| 1485 |
+
"(",
|
| 1486 |
+
-2.3305416341016603
|
| 1487 |
+
],
|
| 1488 |
+
[
|
| 1489 |
+
"1",
|
| 1490 |
+
-2.659489340254079
|
| 1491 |
+
],
|
| 1492 |
+
[
|
| 1493 |
+
"2",
|
| 1494 |
+
-3.0147314517826524
|
| 1495 |
+
],
|
| 1496 |
+
[
|
| 1497 |
+
"O",
|
| 1498 |
+
-3.1705660462226426
|
| 1499 |
+
],
|
| 1500 |
+
[
|
| 1501 |
+
"]",
|
| 1502 |
+
-3.306692943444802
|
| 1503 |
+
],
|
| 1504 |
+
[
|
| 1505 |
+
"[",
|
| 1506 |
+
-3.306692943444802
|
| 1507 |
+
],
|
| 1508 |
+
[
|
| 1509 |
+
"N",
|
| 1510 |
+
-3.3379525475363145
|
| 1511 |
+
],
|
| 1512 |
+
[
|
| 1513 |
+
"@",
|
| 1514 |
+
-3.375613737475505
|
| 1515 |
+
],
|
| 1516 |
+
[
|
| 1517 |
+
"H",
|
| 1518 |
+
-3.3960003181228675
|
| 1519 |
+
],
|
| 1520 |
+
[
|
| 1521 |
+
"=",
|
| 1522 |
+
-3.4342358584336026
|
| 1523 |
+
],
|
| 1524 |
+
[
|
| 1525 |
+
"n",
|
| 1526 |
+
-3.9996436484078535
|
| 1527 |
+
],
|
| 1528 |
+
[
|
| 1529 |
+
"3",
|
| 1530 |
+
-4.06624150723795
|
| 1531 |
+
],
|
| 1532 |
+
[
|
| 1533 |
+
"+",
|
| 1534 |
+
-4.576587821405814
|
| 1535 |
+
],
|
| 1536 |
+
[
|
| 1537 |
+
"ccc",
|
| 1538 |
+
-4.581329068949029
|
| 1539 |
+
],
|
| 1540 |
+
[
|
| 1541 |
+
"cccc",
|
| 1542 |
+
-4.794168477161054
|
| 1543 |
+
],
|
| 1544 |
+
[
|
| 1545 |
+
"F",
|
| 1546 |
+
-4.844444469349959
|
| 1547 |
+
],
|
| 1548 |
+
[
|
| 1549 |
+
"▁C",
|
| 1550 |
+
-4.930731418706828
|
| 1551 |
+
],
|
| 1552 |
+
[
|
| 1553 |
+
"-",
|
| 1554 |
+
-5.128151794820781
|
| 1555 |
+
],
|
| 1556 |
+
[
|
| 1557 |
+
"CC",
|
| 1558 |
+
-5.188054847421637
|
| 1559 |
+
],
|
| 1560 |
+
[
|
| 1561 |
+
"▁",
|
| 1562 |
+
-5.243375183264384
|
| 1563 |
+
],
|
| 1564 |
+
[
|
| 1565 |
+
"▁CC",
|
| 1566 |
+
-5.43665410318811
|
| 1567 |
+
],
|
| 1568 |
+
[
|
| 1569 |
+
"cc",
|
| 1570 |
+
-5.5072446210190025
|
| 1571 |
+
],
|
| 1572 |
+
[
|
| 1573 |
+
"S",
|
| 1574 |
+
-5.607990514129369
|
| 1575 |
+
],
|
| 1576 |
+
[
|
| 1577 |
+
"CCC",
|
| 1578 |
+
-5.610845771534942
|
| 1579 |
+
],
|
| 1580 |
+
[
|
| 1581 |
+
"4",
|
| 1582 |
+
-5.6728058623804705
|
| 1583 |
+
],
|
| 1584 |
+
[
|
| 1585 |
+
"CCN",
|
| 1586 |
+
-5.984229431727735
|
| 1587 |
+
],
|
| 1588 |
+
[
|
| 1589 |
+
"▁CO",
|
| 1590 |
+
-6.136725098692515
|
| 1591 |
+
],
|
| 1592 |
+
[
|
| 1593 |
+
"s",
|
| 1594 |
+
-6.163972117410355
|
| 1595 |
+
],
|
| 1596 |
+
[
|
| 1597 |
+
"l",
|
| 1598 |
+
-6.244242813422005
|
| 1599 |
+
],
|
| 1600 |
+
[
|
| 1601 |
+
"nc",
|
| 1602 |
+
-6.260369976115332
|
| 1603 |
+
],
|
| 1604 |
+
[
|
| 1605 |
+
"Cl",
|
| 1606 |
+
-6.29041030199948
|
| 1607 |
+
],
|
| 1608 |
+
[
|
| 1609 |
+
"NC",
|
| 1610 |
+
-6.301741325285667
|
| 1611 |
+
],
|
| 1612 |
+
[
|
| 1613 |
+
"#",
|
| 1614 |
+
-6.475695381808137
|
| 1615 |
+
],
|
| 1616 |
+
[
|
| 1617 |
+
"CCCC",
|
| 1618 |
+
-6.630889749196982
|
| 1619 |
+
],
|
| 1620 |
+
[
|
| 1621 |
+
"Br",
|
| 1622 |
+
-6.708882955827546
|
| 1623 |
+
],
|
| 1624 |
+
[
|
| 1625 |
+
"o",
|
| 1626 |
+
-6.8821690990922
|
| 1627 |
+
],
|
| 1628 |
+
[
|
| 1629 |
+
"no",
|
| 1630 |
+
-7.085301372799254
|
| 1631 |
+
],
|
| 1632 |
+
[
|
| 1633 |
+
"nn",
|
| 1634 |
+
-7.118314757276033
|
| 1635 |
+
],
|
| 1636 |
+
[
|
| 1637 |
+
"CN",
|
| 1638 |
+
-7.148023077707199
|
| 1639 |
+
],
|
| 1640 |
+
[
|
| 1641 |
+
"▁O",
|
| 1642 |
+
-7.184905330255651
|
| 1643 |
+
],
|
| 1644 |
+
[
|
| 1645 |
+
"CCO",
|
| 1646 |
+
-7.223262672570243
|
| 1647 |
+
],
|
| 1648 |
+
[
|
| 1649 |
+
"▁CN",
|
| 1650 |
+
-7.340957119808042
|
| 1651 |
+
],
|
| 1652 |
+
[
|
| 1653 |
+
"ccs",
|
| 1654 |
+
-7.358439269448935
|
| 1655 |
+
],
|
| 1656 |
+
[
|
| 1657 |
+
"▁CCC",
|
| 1658 |
+
-7.384181818093239
|
| 1659 |
+
],
|
| 1660 |
+
[
|
| 1661 |
+
"OC",
|
| 1662 |
+
-7.401588967543117
|
| 1663 |
+
],
|
| 1664 |
+
[
|
| 1665 |
+
"/",
|
| 1666 |
+
-7.412130091887384
|
| 1667 |
+
],
|
| 1668 |
+
[
|
| 1669 |
+
"▁COC",
|
| 1670 |
+
-7.453342081307827
|
| 1671 |
+
],
|
| 1672 |
+
[
|
| 1673 |
+
"nnc",
|
| 1674 |
+
-7.47808245293119
|
| 1675 |
+
],
|
| 1676 |
+
[
|
| 1677 |
+
"cccn",
|
| 1678 |
+
-7.526117466256242
|
| 1679 |
+
],
|
| 1680 |
+
[
|
| 1681 |
+
"▁CCOC",
|
| 1682 |
+
-7.581460400684973
|
| 1683 |
+
],
|
| 1684 |
+
[
|
| 1685 |
+
"sc",
|
| 1686 |
+
-7.587476370908391
|
| 1687 |
+
],
|
| 1688 |
+
[
|
| 1689 |
+
"cco",
|
| 1690 |
+
-7.601812309424911
|
| 1691 |
+
],
|
| 1692 |
+
[
|
| 1693 |
+
"CCOCC",
|
| 1694 |
+
-7.70962259415791
|
| 1695 |
+
],
|
| 1696 |
+
[
|
| 1697 |
+
"CCCN",
|
| 1698 |
+
-7.716050546596486
|
| 1699 |
+
],
|
| 1700 |
+
[
|
| 1701 |
+
"oc",
|
| 1702 |
+
-7.76950331715161
|
| 1703 |
+
],
|
| 1704 |
+
[
|
| 1705 |
+
"ccnc",
|
| 1706 |
+
-7.885377075776418
|
| 1707 |
+
],
|
| 1708 |
+
[
|
| 1709 |
+
"▁CCO",
|
| 1710 |
+
-7.958354042052764
|
| 1711 |
+
],
|
| 1712 |
+
[
|
| 1713 |
+
"cs",
|
| 1714 |
+
-7.963618836898841
|
| 1715 |
+
],
|
| 1716 |
+
[
|
| 1717 |
+
"▁CCN",
|
| 1718 |
+
-7.969745690077621
|
| 1719 |
+
],
|
| 1720 |
+
[
|
| 1721 |
+
"NCC",
|
| 1722 |
+
-7.982831223650715
|
| 1723 |
+
],
|
| 1724 |
+
[
|
| 1725 |
+
"CNC",
|
| 1726 |
+
-8.015812540478317
|
| 1727 |
+
],
|
| 1728 |
+
[
|
| 1729 |
+
"CCCO",
|
| 1730 |
+
-8.02283744281797
|
| 1731 |
+
],
|
| 1732 |
+
[
|
| 1733 |
+
"nccn",
|
| 1734 |
+
-8.023781204384559
|
| 1735 |
+
],
|
| 1736 |
+
[
|
| 1737 |
+
"CCCCC",
|
| 1738 |
+
-8.113410349713947
|
| 1739 |
+
],
|
| 1740 |
+
[
|
| 1741 |
+
"csc",
|
| 1742 |
+
-8.123340128859317
|
| 1743 |
+
],
|
| 1744 |
+
[
|
| 1745 |
+
"nnn",
|
| 1746 |
+
-8.16923209155111
|
| 1747 |
+
],
|
| 1748 |
+
[
|
| 1749 |
+
"CO",
|
| 1750 |
+
-8.197076591417558
|
| 1751 |
+
],
|
| 1752 |
+
[
|
| 1753 |
+
"cnc",
|
| 1754 |
+
-8.24948897316689
|
| 1755 |
+
],
|
| 1756 |
+
[
|
| 1757 |
+
"OCC",
|
| 1758 |
+
-8.337244843539168
|
| 1759 |
+
],
|
| 1760 |
+
[
|
| 1761 |
+
"ncc",
|
| 1762 |
+
-8.35350988501787
|
| 1763 |
+
],
|
| 1764 |
+
[
|
| 1765 |
+
"CCNC",
|
| 1766 |
+
-8.374584543880331
|
| 1767 |
+
],
|
| 1768 |
+
[
|
| 1769 |
+
"cnn",
|
| 1770 |
+
-8.379764985534148
|
| 1771 |
+
],
|
| 1772 |
+
[
|
| 1773 |
+
"▁CCCC",
|
| 1774 |
+
-8.408946579060395
|
| 1775 |
+
],
|
| 1776 |
+
[
|
| 1777 |
+
"ccn",
|
| 1778 |
+
-8.441316367356151
|
| 1779 |
+
],
|
| 1780 |
+
[
|
| 1781 |
+
"▁CCCN",
|
| 1782 |
+
-8.455940453267049
|
| 1783 |
+
],
|
| 1784 |
+
[
|
| 1785 |
+
"ncn",
|
| 1786 |
+
-8.509281787409483
|
| 1787 |
+
],
|
| 1788 |
+
[
|
| 1789 |
+
"CCOC",
|
| 1790 |
+
-8.545791064619086
|
| 1791 |
+
],
|
| 1792 |
+
[
|
| 1793 |
+
"5",
|
| 1794 |
+
-8.595231126796552
|
| 1795 |
+
],
|
| 1796 |
+
[
|
| 1797 |
+
"OCCO",
|
| 1798 |
+
-8.620568633537287
|
| 1799 |
+
],
|
| 1800 |
+
[
|
| 1801 |
+
"SCC",
|
| 1802 |
+
-8.675945846432537
|
| 1803 |
+
],
|
| 1804 |
+
[
|
| 1805 |
+
"\\",
|
| 1806 |
+
-8.738088269693655
|
| 1807 |
+
],
|
| 1808 |
+
[
|
| 1809 |
+
"▁CS",
|
| 1810 |
+
-8.745760398405787
|
| 1811 |
+
],
|
| 1812 |
+
[
|
| 1813 |
+
"cn",
|
| 1814 |
+
-8.81287462848524
|
| 1815 |
+
],
|
| 1816 |
+
[
|
| 1817 |
+
"CS",
|
| 1818 |
+
-8.852680543942768
|
| 1819 |
+
],
|
| 1820 |
+
[
|
| 1821 |
+
"COC",
|
| 1822 |
+
-8.901532120821837
|
| 1823 |
+
],
|
| 1824 |
+
[
|
| 1825 |
+
"▁CCCO",
|
| 1826 |
+
-8.971729419021525
|
| 1827 |
+
],
|
| 1828 |
+
[
|
| 1829 |
+
"▁COCC",
|
| 1830 |
+
-8.986602855501445
|
| 1831 |
+
],
|
| 1832 |
+
[
|
| 1833 |
+
"▁F",
|
| 1834 |
+
-9.08172188898926
|
| 1835 |
+
],
|
| 1836 |
+
[
|
| 1837 |
+
"▁CCNC",
|
| 1838 |
+
-9.213239929783953
|
| 1839 |
+
],
|
| 1840 |
+
[
|
| 1841 |
+
"nccc",
|
| 1842 |
+
-9.267617565078302
|
| 1843 |
+
],
|
| 1844 |
+
[
|
| 1845 |
+
"▁CCS",
|
| 1846 |
+
-9.284123840101111
|
| 1847 |
+
],
|
| 1848 |
+
[
|
| 1849 |
+
"▁N",
|
| 1850 |
+
-9.46465900903722
|
| 1851 |
+
],
|
| 1852 |
+
[
|
| 1853 |
+
"▁CCCCO",
|
| 1854 |
+
-9.549659454320029
|
| 1855 |
+
],
|
| 1856 |
+
[
|
| 1857 |
+
"NCCC",
|
| 1858 |
+
-9.592808545839064
|
| 1859 |
+
],
|
| 1860 |
+
[
|
| 1861 |
+
"NCCN",
|
| 1862 |
+
-9.616093114468232
|
| 1863 |
+
],
|
| 1864 |
+
[
|
| 1865 |
+
"CCS",
|
| 1866 |
+
-9.68568843530331
|
| 1867 |
+
],
|
| 1868 |
+
[
|
| 1869 |
+
"cncc",
|
| 1870 |
+
-9.884757958758378
|
| 1871 |
+
],
|
| 1872 |
+
[
|
| 1873 |
+
"CCCS",
|
| 1874 |
+
-10.07490132384844
|
| 1875 |
+
],
|
| 1876 |
+
[
|
| 1877 |
+
"▁NC",
|
| 1878 |
+
-10.174180411834037
|
| 1879 |
+
],
|
| 1880 |
+
[
|
| 1881 |
+
"▁COCCN",
|
| 1882 |
+
-10.182867019690027
|
| 1883 |
+
],
|
| 1884 |
+
[
|
| 1885 |
+
"▁COCCO",
|
| 1886 |
+
-10.210382702506402
|
| 1887 |
+
],
|
| 1888 |
+
[
|
| 1889 |
+
"▁COCCC",
|
| 1890 |
+
-10.390960567106395
|
| 1891 |
+
],
|
| 1892 |
+
[
|
| 1893 |
+
"OCO",
|
| 1894 |
+
-10.445584736697652
|
| 1895 |
+
],
|
| 1896 |
+
[
|
| 1897 |
+
"COCC",
|
| 1898 |
+
-10.469925833149428
|
| 1899 |
+
],
|
| 1900 |
+
[
|
| 1901 |
+
"▁CCOCCN",
|
| 1902 |
+
-10.487938027145828
|
| 1903 |
+
],
|
| 1904 |
+
[
|
| 1905 |
+
"SC",
|
| 1906 |
+
-10.868655865451124
|
| 1907 |
+
],
|
| 1908 |
+
[
|
| 1909 |
+
"co",
|
| 1910 |
+
-11.175046369147724
|
| 1911 |
+
],
|
| 1912 |
+
[
|
| 1913 |
+
"I",
|
| 1914 |
+
-11.188088269693656
|
| 1915 |
+
],
|
| 1916 |
+
[
|
| 1917 |
+
"on",
|
| 1918 |
+
-11.199838029113598
|
| 1919 |
+
],
|
| 1920 |
+
[
|
| 1921 |
+
"CCCCN",
|
| 1922 |
+
-11.273835881601958
|
| 1923 |
+
],
|
| 1924 |
+
[
|
| 1925 |
+
"▁CCCCN",
|
| 1926 |
+
-11.694782342260607
|
| 1927 |
+
],
|
| 1928 |
+
[
|
| 1929 |
+
"CCOCCN",
|
| 1930 |
+
-11.98760417613926
|
| 1931 |
+
],
|
| 1932 |
+
[
|
| 1933 |
+
"r",
|
| 1934 |
+
-12.313357692926305
|
| 1935 |
+
],
|
| 1936 |
+
[
|
| 1937 |
+
"B",
|
| 1938 |
+
-12.313457692926304
|
| 1939 |
+
],
|
| 1940 |
+
[
|
| 1941 |
+
"CCCCO",
|
| 1942 |
+
-12.313457692926304
|
| 1943 |
+
]
|
| 1944 |
+
],
|
| 1945 |
+
"byte_fallback": false
|
| 1946 |
+
}
|
| 1947 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1328 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"36": {
|
| 28 |
+
"content": "Cl",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"121": {
|
| 36 |
+
"content": "<extra_id_0>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"122": {
|
| 44 |
+
"content": "<extra_id_1>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"123": {
|
| 52 |
+
"content": "<extra_id_2>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"124": {
|
| 60 |
+
"content": "<extra_id_3>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"125": {
|
| 68 |
+
"content": "<extra_id_4>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"126": {
|
| 76 |
+
"content": "<extra_id_5>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"127": {
|
| 84 |
+
"content": "<extra_id_6>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128": {
|
| 92 |
+
"content": "<extra_id_7>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"129": {
|
| 100 |
+
"content": "<extra_id_8>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"130": {
|
| 108 |
+
"content": "<extra_id_9>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"131": {
|
| 116 |
+
"content": "<extra_id_10>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"132": {
|
| 124 |
+
"content": "<extra_id_11>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"133": {
|
| 132 |
+
"content": "<extra_id_12>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"134": {
|
| 140 |
+
"content": "<extra_id_13>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"135": {
|
| 148 |
+
"content": "<extra_id_14>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"136": {
|
| 156 |
+
"content": "<extra_id_15>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"137": {
|
| 164 |
+
"content": "<extra_id_16>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"138": {
|
| 172 |
+
"content": "<extra_id_17>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"139": {
|
| 180 |
+
"content": "<extra_id_18>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"140": {
|
| 188 |
+
"content": "<extra_id_19>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"141": {
|
| 196 |
+
"content": "<extra_id_20>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"142": {
|
| 204 |
+
"content": "<extra_id_21>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"143": {
|
| 212 |
+
"content": "<extra_id_22>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"144": {
|
| 220 |
+
"content": "<extra_id_23>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"145": {
|
| 228 |
+
"content": "<extra_id_24>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"146": {
|
| 236 |
+
"content": "<extra_id_25>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"147": {
|
| 244 |
+
"content": "<extra_id_26>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"148": {
|
| 252 |
+
"content": "<extra_id_27>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"149": {
|
| 260 |
+
"content": "<extra_id_28>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"150": {
|
| 268 |
+
"content": "<extra_id_29>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"151": {
|
| 276 |
+
"content": "<extra_id_30>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"152": {
|
| 284 |
+
"content": "<extra_id_31>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"153": {
|
| 292 |
+
"content": "<extra_id_32>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"154": {
|
| 300 |
+
"content": "<extra_id_33>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"155": {
|
| 308 |
+
"content": "<extra_id_34>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"156": {
|
| 316 |
+
"content": "<extra_id_35>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"157": {
|
| 324 |
+
"content": "<extra_id_36>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"158": {
|
| 332 |
+
"content": "<extra_id_37>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"159": {
|
| 340 |
+
"content": "<extra_id_38>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"160": {
|
| 348 |
+
"content": "<extra_id_39>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"161": {
|
| 356 |
+
"content": "<extra_id_40>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"162": {
|
| 364 |
+
"content": "<extra_id_41>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"163": {
|
| 372 |
+
"content": "<extra_id_42>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"164": {
|
| 380 |
+
"content": "<extra_id_43>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"165": {
|
| 388 |
+
"content": "<extra_id_44>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"166": {
|
| 396 |
+
"content": "<extra_id_45>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"167": {
|
| 404 |
+
"content": "<extra_id_46>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"168": {
|
| 412 |
+
"content": "<extra_id_47>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"169": {
|
| 420 |
+
"content": "<extra_id_48>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"170": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"171": {
|
| 436 |
+
"content": "<extra_id_50>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"172": {
|
| 444 |
+
"content": "<extra_id_51>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"173": {
|
| 452 |
+
"content": "<extra_id_52>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"174": {
|
| 460 |
+
"content": "<extra_id_53>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"175": {
|
| 468 |
+
"content": "<extra_id_54>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"176": {
|
| 476 |
+
"content": "<extra_id_55>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"177": {
|
| 484 |
+
"content": "<extra_id_56>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"178": {
|
| 492 |
+
"content": "<extra_id_57>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"179": {
|
| 500 |
+
"content": "<extra_id_58>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"180": {
|
| 508 |
+
"content": "<extra_id_59>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"181": {
|
| 516 |
+
"content": "<extra_id_60>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"182": {
|
| 524 |
+
"content": "<extra_id_61>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"183": {
|
| 532 |
+
"content": "<extra_id_62>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"184": {
|
| 540 |
+
"content": "<extra_id_63>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"185": {
|
| 548 |
+
"content": "<extra_id_64>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"186": {
|
| 556 |
+
"content": "<extra_id_65>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"187": {
|
| 564 |
+
"content": "<extra_id_66>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"188": {
|
| 572 |
+
"content": "<extra_id_67>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"189": {
|
| 580 |
+
"content": "<extra_id_68>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"190": {
|
| 588 |
+
"content": "<extra_id_69>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"191": {
|
| 596 |
+
"content": "<extra_id_70>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"192": {
|
| 604 |
+
"content": "<extra_id_71>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"193": {
|
| 612 |
+
"content": "<extra_id_72>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"194": {
|
| 620 |
+
"content": "<extra_id_73>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"195": {
|
| 628 |
+
"content": "<extra_id_74>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"196": {
|
| 636 |
+
"content": "<extra_id_75>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"197": {
|
| 644 |
+
"content": "<extra_id_76>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"198": {
|
| 652 |
+
"content": "<extra_id_77>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"199": {
|
| 660 |
+
"content": "<extra_id_78>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"200": {
|
| 668 |
+
"content": "<extra_id_79>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"201": {
|
| 676 |
+
"content": "<extra_id_80>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"202": {
|
| 684 |
+
"content": "<extra_id_81>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"203": {
|
| 692 |
+
"content": "<extra_id_82>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"204": {
|
| 700 |
+
"content": "<extra_id_83>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"205": {
|
| 708 |
+
"content": "<extra_id_84>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"206": {
|
| 716 |
+
"content": "<extra_id_85>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"207": {
|
| 724 |
+
"content": "<extra_id_86>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"208": {
|
| 732 |
+
"content": "<extra_id_87>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"209": {
|
| 740 |
+
"content": "<extra_id_88>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"210": {
|
| 748 |
+
"content": "<extra_id_89>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"211": {
|
| 756 |
+
"content": "<extra_id_90>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"212": {
|
| 764 |
+
"content": "<extra_id_91>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"213": {
|
| 772 |
+
"content": "<extra_id_92>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"214": {
|
| 780 |
+
"content": "<extra_id_93>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"215": {
|
| 788 |
+
"content": "<extra_id_94>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"216": {
|
| 796 |
+
"content": "<extra_id_95>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"217": {
|
| 804 |
+
"content": "<extra_id_96>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"218": {
|
| 812 |
+
"content": "<extra_id_97>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"219": {
|
| 820 |
+
"content": "<extra_id_98>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"220": {
|
| 828 |
+
"content": "<extra_id_99>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"221": {
|
| 836 |
+
"content": ".",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
+
},
|
| 843 |
+
"222": {
|
| 844 |
+
"content": "6",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"223": {
|
| 852 |
+
"content": "7",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"224": {
|
| 860 |
+
"content": "8",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"225": {
|
| 868 |
+
"content": "<",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"226": {
|
| 876 |
+
"content": ">",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"227": {
|
| 884 |
+
"content": "Ag",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"228": {
|
| 892 |
+
"content": "Al",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"229": {
|
| 900 |
+
"content": "Ar",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"230": {
|
| 908 |
+
"content": "As",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"231": {
|
| 916 |
+
"content": "Au",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"232": {
|
| 924 |
+
"content": "Ba",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
},
|
| 931 |
+
"233": {
|
| 932 |
+
"content": "Bi",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": true,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": false
|
| 938 |
+
},
|
| 939 |
+
"234": {
|
| 940 |
+
"content": "Ca",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": true,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": false
|
| 946 |
+
},
|
| 947 |
+
"235": {
|
| 948 |
+
"content": "Cu",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": true,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": false
|
| 954 |
+
},
|
| 955 |
+
"236": {
|
| 956 |
+
"content": "Fe",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": true,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": false
|
| 962 |
+
},
|
| 963 |
+
"237": {
|
| 964 |
+
"content": "Ge",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": true,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": false
|
| 970 |
+
},
|
| 971 |
+
"238": {
|
| 972 |
+
"content": "Hg",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": true,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": false
|
| 978 |
+
},
|
| 979 |
+
"239": {
|
| 980 |
+
"content": "K",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": true,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": false
|
| 986 |
+
},
|
| 987 |
+
"240": {
|
| 988 |
+
"content": "Li",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": true,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": false
|
| 994 |
+
},
|
| 995 |
+
"241": {
|
| 996 |
+
"content": "Mg",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": true,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": false
|
| 1002 |
+
},
|
| 1003 |
+
"242": {
|
| 1004 |
+
"content": "Mn",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": true,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": false
|
| 1010 |
+
},
|
| 1011 |
+
"243": {
|
| 1012 |
+
"content": "Mo",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": true,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": false
|
| 1018 |
+
},
|
| 1019 |
+
"244": {
|
| 1020 |
+
"content": "Na",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": true,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": false
|
| 1026 |
+
},
|
| 1027 |
+
"245": {
|
| 1028 |
+
"content": "Nd",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": true,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": false
|
| 1034 |
+
},
|
| 1035 |
+
"246": {
|
| 1036 |
+
"content": "Ni",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": true,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": false
|
| 1042 |
+
},
|
| 1043 |
+
"247": {
|
| 1044 |
+
"content": "P",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": true,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": false
|
| 1050 |
+
},
|
| 1051 |
+
"248": {
|
| 1052 |
+
"content": "Pb",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": true,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": false
|
| 1058 |
+
},
|
| 1059 |
+
"249": {
|
| 1060 |
+
"content": "Pd",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": true,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": false
|
| 1066 |
+
},
|
| 1067 |
+
"250": {
|
| 1068 |
+
"content": "Pt",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": true,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": false
|
| 1074 |
+
},
|
| 1075 |
+
"251": {
|
| 1076 |
+
"content": "Re",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": true,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": false
|
| 1082 |
+
},
|
| 1083 |
+
"252": {
|
| 1084 |
+
"content": "Rh",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": true,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": false
|
| 1090 |
+
},
|
| 1091 |
+
"253": {
|
| 1092 |
+
"content": "Ru",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": true,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": false
|
| 1098 |
+
},
|
| 1099 |
+
"254": {
|
| 1100 |
+
"content": "Sb",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": true,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": false
|
| 1106 |
+
},
|
| 1107 |
+
"255": {
|
| 1108 |
+
"content": "Si",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": true,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": false
|
| 1114 |
+
},
|
| 1115 |
+
"256": {
|
| 1116 |
+
"content": "Sm",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": true,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": false
|
| 1122 |
+
},
|
| 1123 |
+
"257": {
|
| 1124 |
+
"content": "Ta",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": true,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": false
|
| 1130 |
+
},
|
| 1131 |
+
"258": {
|
| 1132 |
+
"content": "Ti",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": true,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": false
|
| 1138 |
+
},
|
| 1139 |
+
"259": {
|
| 1140 |
+
"content": "Tl",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": true,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": false
|
| 1146 |
+
},
|
| 1147 |
+
"260": {
|
| 1148 |
+
"content": "W",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": true,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": false
|
| 1154 |
+
},
|
| 1155 |
+
"261": {
|
| 1156 |
+
"content": "Yb",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": true,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": false
|
| 1162 |
+
},
|
| 1163 |
+
"262": {
|
| 1164 |
+
"content": "Zn",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": true,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": false
|
| 1170 |
+
},
|
| 1171 |
+
"263": {
|
| 1172 |
+
"content": "Zr",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": true,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": false
|
| 1178 |
+
},
|
| 1179 |
+
"264": {
|
| 1180 |
+
"content": "e",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": true,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": false
|
| 1186 |
+
},
|
| 1187 |
+
"265": {
|
| 1188 |
+
"content": "p",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": true,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": false
|
| 1194 |
+
},
|
| 1195 |
+
"266": {
|
| 1196 |
+
"content": "REACTANT:",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"267": {
|
| 1204 |
+
"content": "REAGENT:",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
}
|
| 1211 |
+
},
|
| 1212 |
+
"additional_special_tokens": [
|
| 1213 |
+
"<extra_id_0>",
|
| 1214 |
+
"<extra_id_1>",
|
| 1215 |
+
"<extra_id_2>",
|
| 1216 |
+
"<extra_id_3>",
|
| 1217 |
+
"<extra_id_4>",
|
| 1218 |
+
"<extra_id_5>",
|
| 1219 |
+
"<extra_id_6>",
|
| 1220 |
+
"<extra_id_7>",
|
| 1221 |
+
"<extra_id_8>",
|
| 1222 |
+
"<extra_id_9>",
|
| 1223 |
+
"<extra_id_10>",
|
| 1224 |
+
"<extra_id_11>",
|
| 1225 |
+
"<extra_id_12>",
|
| 1226 |
+
"<extra_id_13>",
|
| 1227 |
+
"<extra_id_14>",
|
| 1228 |
+
"<extra_id_15>",
|
| 1229 |
+
"<extra_id_16>",
|
| 1230 |
+
"<extra_id_17>",
|
| 1231 |
+
"<extra_id_18>",
|
| 1232 |
+
"<extra_id_19>",
|
| 1233 |
+
"<extra_id_20>",
|
| 1234 |
+
"<extra_id_21>",
|
| 1235 |
+
"<extra_id_22>",
|
| 1236 |
+
"<extra_id_23>",
|
| 1237 |
+
"<extra_id_24>",
|
| 1238 |
+
"<extra_id_25>",
|
| 1239 |
+
"<extra_id_26>",
|
| 1240 |
+
"<extra_id_27>",
|
| 1241 |
+
"<extra_id_28>",
|
| 1242 |
+
"<extra_id_29>",
|
| 1243 |
+
"<extra_id_30>",
|
| 1244 |
+
"<extra_id_31>",
|
| 1245 |
+
"<extra_id_32>",
|
| 1246 |
+
"<extra_id_33>",
|
| 1247 |
+
"<extra_id_34>",
|
| 1248 |
+
"<extra_id_35>",
|
| 1249 |
+
"<extra_id_36>",
|
| 1250 |
+
"<extra_id_37>",
|
| 1251 |
+
"<extra_id_38>",
|
| 1252 |
+
"<extra_id_39>",
|
| 1253 |
+
"<extra_id_40>",
|
| 1254 |
+
"<extra_id_41>",
|
| 1255 |
+
"<extra_id_42>",
|
| 1256 |
+
"<extra_id_43>",
|
| 1257 |
+
"<extra_id_44>",
|
| 1258 |
+
"<extra_id_45>",
|
| 1259 |
+
"<extra_id_46>",
|
| 1260 |
+
"<extra_id_47>",
|
| 1261 |
+
"<extra_id_48>",
|
| 1262 |
+
"<extra_id_49>",
|
| 1263 |
+
"<extra_id_50>",
|
| 1264 |
+
"<extra_id_51>",
|
| 1265 |
+
"<extra_id_52>",
|
| 1266 |
+
"<extra_id_53>",
|
| 1267 |
+
"<extra_id_54>",
|
| 1268 |
+
"<extra_id_55>",
|
| 1269 |
+
"<extra_id_56>",
|
| 1270 |
+
"<extra_id_57>",
|
| 1271 |
+
"<extra_id_58>",
|
| 1272 |
+
"<extra_id_59>",
|
| 1273 |
+
"<extra_id_60>",
|
| 1274 |
+
"<extra_id_61>",
|
| 1275 |
+
"<extra_id_62>",
|
| 1276 |
+
"<extra_id_63>",
|
| 1277 |
+
"<extra_id_64>",
|
| 1278 |
+
"<extra_id_65>",
|
| 1279 |
+
"<extra_id_66>",
|
| 1280 |
+
"<extra_id_67>",
|
| 1281 |
+
"<extra_id_68>",
|
| 1282 |
+
"<extra_id_69>",
|
| 1283 |
+
"<extra_id_70>",
|
| 1284 |
+
"<extra_id_71>",
|
| 1285 |
+
"<extra_id_72>",
|
| 1286 |
+
"<extra_id_73>",
|
| 1287 |
+
"<extra_id_74>",
|
| 1288 |
+
"<extra_id_75>",
|
| 1289 |
+
"<extra_id_76>",
|
| 1290 |
+
"<extra_id_77>",
|
| 1291 |
+
"<extra_id_78>",
|
| 1292 |
+
"<extra_id_79>",
|
| 1293 |
+
"<extra_id_80>",
|
| 1294 |
+
"<extra_id_81>",
|
| 1295 |
+
"<extra_id_82>",
|
| 1296 |
+
"<extra_id_83>",
|
| 1297 |
+
"<extra_id_84>",
|
| 1298 |
+
"<extra_id_85>",
|
| 1299 |
+
"<extra_id_86>",
|
| 1300 |
+
"<extra_id_87>",
|
| 1301 |
+
"<extra_id_88>",
|
| 1302 |
+
"<extra_id_89>",
|
| 1303 |
+
"<extra_id_90>",
|
| 1304 |
+
"<extra_id_91>",
|
| 1305 |
+
"<extra_id_92>",
|
| 1306 |
+
"<extra_id_93>",
|
| 1307 |
+
"<extra_id_94>",
|
| 1308 |
+
"<extra_id_95>",
|
| 1309 |
+
"<extra_id_96>",
|
| 1310 |
+
"<extra_id_97>",
|
| 1311 |
+
"<extra_id_98>",
|
| 1312 |
+
"<extra_id_99>",
|
| 1313 |
+
"REACTANT:",
|
| 1314 |
+
"REAGENT:"
|
| 1315 |
+
],
|
| 1316 |
+
"clean_up_tokenization_spaces": true,
|
| 1317 |
+
"eos_token": "</s>",
|
| 1318 |
+
"extra_ids": 100,
|
| 1319 |
+
"max_length": 100,
|
| 1320 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 1321 |
+
"pad_token": "<pad>",
|
| 1322 |
+
"return_tensors": "pt",
|
| 1323 |
+
"stride": 0,
|
| 1324 |
+
"tokenizer_class": "T5Tokenizer",
|
| 1325 |
+
"truncation_side": "right",
|
| 1326 |
+
"truncation_strategy": "longest_first",
|
| 1327 |
+
"unk_token": "<unk>"
|
| 1328 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.002982336562126875,
|
| 3 |
+
"best_model_checkpoint": "t5/checkpoint-25566",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 102264,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 0.09756029397249222,
|
| 14 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 15 |
+
"loss": 0.0059,
|
| 16 |
+
"step": 12783
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.9804666666666667,
|
| 21 |
+
"eval_loss": 0.0031315775122493505,
|
| 22 |
+
"eval_runtime": 472.802,
|
| 23 |
+
"eval_samples_per_second": 63.452,
|
| 24 |
+
"eval_steps_per_second": 0.497,
|
| 25 |
+
"step": 12783
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 0.0030228213872760534,
|
| 30 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 31 |
+
"loss": 0.0022,
|
| 32 |
+
"step": 25566
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.9818666666666667,
|
| 37 |
+
"eval_loss": 0.002982336562126875,
|
| 38 |
+
"eval_runtime": 474.0664,
|
| 39 |
+
"eval_samples_per_second": 63.282,
|
| 40 |
+
"eval_steps_per_second": 0.496,
|
| 41 |
+
"step": 25566
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"grad_norm": 0.00019585879635997117,
|
| 46 |
+
"learning_rate": 1.88e-05,
|
| 47 |
+
"loss": 0.0012,
|
| 48 |
+
"step": 38349
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_accuracy": 0.9825,
|
| 53 |
+
"eval_loss": 0.0032824024092406034,
|
| 54 |
+
"eval_runtime": 478.2854,
|
| 55 |
+
"eval_samples_per_second": 62.724,
|
| 56 |
+
"eval_steps_per_second": 0.491,
|
| 57 |
+
"step": 38349
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"grad_norm": 0.004981159698218107,
|
| 62 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 63 |
+
"loss": 0.0007,
|
| 64 |
+
"step": 51132
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.9826,
|
| 69 |
+
"eval_loss": 0.003532745875418186,
|
| 70 |
+
"eval_runtime": 469.3109,
|
| 71 |
+
"eval_samples_per_second": 63.924,
|
| 72 |
+
"eval_steps_per_second": 0.501,
|
| 73 |
+
"step": 51132
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 5.0,
|
| 77 |
+
"grad_norm": 0.002326933667063713,
|
| 78 |
+
"learning_rate": 1.8e-05,
|
| 79 |
+
"loss": 0.0005,
|
| 80 |
+
"step": 63915
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"eval_accuracy": 0.9821666666666666,
|
| 85 |
+
"eval_loss": 0.003947438672184944,
|
| 86 |
+
"eval_runtime": 471.3239,
|
| 87 |
+
"eval_samples_per_second": 63.65,
|
| 88 |
+
"eval_steps_per_second": 0.499,
|
| 89 |
+
"step": 63915
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 6.0,
|
| 93 |
+
"grad_norm": 0.034791357815265656,
|
| 94 |
+
"learning_rate": 1.76e-05,
|
| 95 |
+
"loss": 0.0004,
|
| 96 |
+
"step": 76698
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.9815666666666667,
|
| 101 |
+
"eval_loss": 0.0041623483411967754,
|
| 102 |
+
"eval_runtime": 470.7737,
|
| 103 |
+
"eval_samples_per_second": 63.725,
|
| 104 |
+
"eval_steps_per_second": 0.499,
|
| 105 |
+
"step": 76698
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.0,
|
| 109 |
+
"grad_norm": 9.868334018392488e-05,
|
| 110 |
+
"learning_rate": 1.72e-05,
|
| 111 |
+
"loss": 0.0003,
|
| 112 |
+
"step": 89481
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 7.0,
|
| 116 |
+
"eval_accuracy": 0.9822666666666666,
|
| 117 |
+
"eval_loss": 0.004203655291348696,
|
| 118 |
+
"eval_runtime": 471.0374,
|
| 119 |
+
"eval_samples_per_second": 63.689,
|
| 120 |
+
"eval_steps_per_second": 0.499,
|
| 121 |
+
"step": 89481
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"grad_norm": 0.002833570586517453,
|
| 126 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 127 |
+
"loss": 0.0003,
|
| 128 |
+
"step": 102264
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.9826,
|
| 133 |
+
"eval_loss": 0.0045397114008665085,
|
| 134 |
+
"eval_runtime": 469.6081,
|
| 135 |
+
"eval_samples_per_second": 63.883,
|
| 136 |
+
"eval_steps_per_second": 0.5,
|
| 137 |
+
"step": 102264
|
| 138 |
+
}
|
| 139 |
+
],
|
| 140 |
+
"logging_steps": 500,
|
| 141 |
+
"max_steps": 639150,
|
| 142 |
+
"num_input_tokens_seen": 0,
|
| 143 |
+
"num_train_epochs": 50,
|
| 144 |
+
"save_steps": 500,
|
| 145 |
+
"total_flos": 5.937159320662856e+17,
|
| 146 |
+
"train_batch_size": 32,
|
| 147 |
+
"trial_name": null,
|
| 148 |
+
"trial_params": null
|
| 149 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:480806311c2fb18be472ad7ff49ac238235b6f54c2285fee10edef8206fd5bab
|
| 3 |
+
size 5112
|