Training in progress, step 3000
Browse files- .gitignore +1 -0
- config.json +42 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +2171 -0
- tokenizer_config.json +10 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Lakoc/gpt2_512h_16l_add_head8",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMMultiHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"average_logits": false,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"head_locations": [
|
13 |
+
8
|
14 |
+
],
|
15 |
+
"head_weights": [
|
16 |
+
0.7,
|
17 |
+
0.3
|
18 |
+
],
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"layer_norm_epsilon": 1e-05,
|
21 |
+
"model_type": "gpt2-multi-head",
|
22 |
+
"n_embd": 512,
|
23 |
+
"n_head": 8,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 16,
|
26 |
+
"n_positions": 256,
|
27 |
+
"pad_token_id": 3,
|
28 |
+
"reorder_and_upcast_attn": false,
|
29 |
+
"resid_pdrop": 0.1,
|
30 |
+
"scale_attn_by_inverse_layer_idx": false,
|
31 |
+
"scale_attn_weights": true,
|
32 |
+
"summary_activation": null,
|
33 |
+
"summary_first_dropout": 0.1,
|
34 |
+
"summary_proj_to_labels": true,
|
35 |
+
"summary_type": "cls_index",
|
36 |
+
"summary_use_proj": true,
|
37 |
+
"tie_additional_weights": false,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.31.0.dev0",
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 500
|
42 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc28aafc76f249db0a9befc381c2cf6088c2c3d56d91db44df5df0f81d117caf
|
3 |
+
size 204393438
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,2171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "<s>",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "</s>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "<unk>",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "<pad>",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "<mask>",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"normalizer": {
|
53 |
+
"type": "Sequence",
|
54 |
+
"normalizers": [
|
55 |
+
{
|
56 |
+
"type": "Replace",
|
57 |
+
"pattern": {
|
58 |
+
"String": "``"
|
59 |
+
},
|
60 |
+
"content": "\""
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"type": "Replace",
|
64 |
+
"pattern": {
|
65 |
+
"String": "''"
|
66 |
+
},
|
67 |
+
"content": "\""
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"type": "Lowercase"
|
71 |
+
}
|
72 |
+
]
|
73 |
+
},
|
74 |
+
"pre_tokenizer": {
|
75 |
+
"type": "Metaspace",
|
76 |
+
"replacement": "▁",
|
77 |
+
"add_prefix_space": true
|
78 |
+
},
|
79 |
+
"post_processor": {
|
80 |
+
"type": "TemplateProcessing",
|
81 |
+
"single": [
|
82 |
+
{
|
83 |
+
"SpecialToken": {
|
84 |
+
"id": "<s>",
|
85 |
+
"type_id": 0
|
86 |
+
}
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"Sequence": {
|
90 |
+
"id": "A",
|
91 |
+
"type_id": 0
|
92 |
+
}
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"SpecialToken": {
|
96 |
+
"id": "</s>",
|
97 |
+
"type_id": 0
|
98 |
+
}
|
99 |
+
}
|
100 |
+
],
|
101 |
+
"pair": [
|
102 |
+
{
|
103 |
+
"SpecialToken": {
|
104 |
+
"id": "<s>",
|
105 |
+
"type_id": 0
|
106 |
+
}
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"Sequence": {
|
110 |
+
"id": "A",
|
111 |
+
"type_id": 0
|
112 |
+
}
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"SpecialToken": {
|
116 |
+
"id": "</s>",
|
117 |
+
"type_id": 0
|
118 |
+
}
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"SpecialToken": {
|
122 |
+
"id": "<s>",
|
123 |
+
"type_id": 1
|
124 |
+
}
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"Sequence": {
|
128 |
+
"id": "B",
|
129 |
+
"type_id": 1
|
130 |
+
}
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"SpecialToken": {
|
134 |
+
"id": "</s>",
|
135 |
+
"type_id": 1
|
136 |
+
}
|
137 |
+
}
|
138 |
+
],
|
139 |
+
"special_tokens": {
|
140 |
+
"</s>": {
|
141 |
+
"id": "</s>",
|
142 |
+
"ids": [
|
143 |
+
1
|
144 |
+
],
|
145 |
+
"tokens": [
|
146 |
+
"</s>"
|
147 |
+
]
|
148 |
+
},
|
149 |
+
"<s>": {
|
150 |
+
"id": "<s>",
|
151 |
+
"ids": [
|
152 |
+
0
|
153 |
+
],
|
154 |
+
"tokens": [
|
155 |
+
"<s>"
|
156 |
+
]
|
157 |
+
}
|
158 |
+
}
|
159 |
+
},
|
160 |
+
"decoder": {
|
161 |
+
"type": "Metaspace",
|
162 |
+
"replacement": "▁",
|
163 |
+
"add_prefix_space": true
|
164 |
+
},
|
165 |
+
"model": {
|
166 |
+
"type": "Unigram",
|
167 |
+
"unk_id": 2,
|
168 |
+
"vocab": [
|
169 |
+
[
|
170 |
+
"<s>",
|
171 |
+
0.0
|
172 |
+
],
|
173 |
+
[
|
174 |
+
"</s>",
|
175 |
+
0.0
|
176 |
+
],
|
177 |
+
[
|
178 |
+
"<unk>",
|
179 |
+
0.0
|
180 |
+
],
|
181 |
+
[
|
182 |
+
"<pad>",
|
183 |
+
0.0
|
184 |
+
],
|
185 |
+
[
|
186 |
+
"<mask>",
|
187 |
+
0.0
|
188 |
+
],
|
189 |
+
[
|
190 |
+
"▁",
|
191 |
+
-2.365659253373373
|
192 |
+
],
|
193 |
+
[
|
194 |
+
"e",
|
195 |
+
-2.7726274257071672
|
196 |
+
],
|
197 |
+
[
|
198 |
+
"s",
|
199 |
+
-2.8092594726709414
|
200 |
+
],
|
201 |
+
[
|
202 |
+
"t",
|
203 |
+
-2.937906677759426
|
204 |
+
],
|
205 |
+
[
|
206 |
+
"a",
|
207 |
+
-3.023488039566267
|
208 |
+
],
|
209 |
+
[
|
210 |
+
"i",
|
211 |
+
-3.130101696517439
|
212 |
+
],
|
213 |
+
[
|
214 |
+
"r",
|
215 |
+
-3.3167080850029116
|
216 |
+
],
|
217 |
+
[
|
218 |
+
"o",
|
219 |
+
-3.4890814730909696
|
220 |
+
],
|
221 |
+
[
|
222 |
+
"n",
|
223 |
+
-3.6166233466724087
|
224 |
+
],
|
225 |
+
[
|
226 |
+
"d",
|
227 |
+
-3.662076718281828
|
228 |
+
],
|
229 |
+
[
|
230 |
+
"▁the",
|
231 |
+
-3.8362751907891095
|
232 |
+
],
|
233 |
+
[
|
234 |
+
"\n",
|
235 |
+
-3.8534604095366554
|
236 |
+
],
|
237 |
+
[
|
238 |
+
"l",
|
239 |
+
-3.882923720655637
|
240 |
+
],
|
241 |
+
[
|
242 |
+
"c",
|
243 |
+
-4.143267028826475
|
244 |
+
],
|
245 |
+
[
|
246 |
+
"m",
|
247 |
+
-4.228727291757142
|
248 |
+
],
|
249 |
+
[
|
250 |
+
"u",
|
251 |
+
-4.335524745161631
|
252 |
+
],
|
253 |
+
[
|
254 |
+
"p",
|
255 |
+
-4.359575101224133
|
256 |
+
],
|
257 |
+
[
|
258 |
+
"▁to",
|
259 |
+
-4.38651368841003
|
260 |
+
],
|
261 |
+
[
|
262 |
+
"ing",
|
263 |
+
-4.483100337757891
|
264 |
+
],
|
265 |
+
[
|
266 |
+
"▁and",
|
267 |
+
-4.520970283112547
|
268 |
+
],
|
269 |
+
[
|
270 |
+
"f",
|
271 |
+
-4.525275602775807
|
272 |
+
],
|
273 |
+
[
|
274 |
+
"▁of",
|
275 |
+
-4.5760527119177485
|
276 |
+
],
|
277 |
+
[
|
278 |
+
"y",
|
279 |
+
-4.58382387353196
|
280 |
+
],
|
281 |
+
[
|
282 |
+
"▁in",
|
283 |
+
-4.740397653766369
|
284 |
+
],
|
285 |
+
[
|
286 |
+
"g",
|
287 |
+
-4.791754116540275
|
288 |
+
],
|
289 |
+
[
|
290 |
+
"h",
|
291 |
+
-4.836474590087411
|
292 |
+
],
|
293 |
+
[
|
294 |
+
"b",
|
295 |
+
-4.909411232248003
|
296 |
+
],
|
297 |
+
[
|
298 |
+
"▁that",
|
299 |
+
-5.199912115593683
|
300 |
+
],
|
301 |
+
[
|
302 |
+
"k",
|
303 |
+
-5.263461955826319
|
304 |
+
],
|
305 |
+
[
|
306 |
+
"w",
|
307 |
+
-5.28123698440287
|
308 |
+
],
|
309 |
+
[
|
310 |
+
"▁is",
|
311 |
+
-5.299636845493664
|
312 |
+
],
|
313 |
+
[
|
314 |
+
"▁be",
|
315 |
+
-5.419702910541615
|
316 |
+
],
|
317 |
+
[
|
318 |
+
"in",
|
319 |
+
-5.4359103464709335
|
320 |
+
],
|
321 |
+
[
|
322 |
+
"▁for",
|
323 |
+
-5.512356650709716
|
324 |
+
],
|
325 |
+
[
|
326 |
+
"v",
|
327 |
+
-5.604824905017555
|
328 |
+
],
|
329 |
+
[
|
330 |
+
"▁we",
|
331 |
+
-5.6102446335917335
|
332 |
+
],
|
333 |
+
[
|
334 |
+
"ly",
|
335 |
+
-5.626062101437649
|
336 |
+
],
|
337 |
+
[
|
338 |
+
"▁you",
|
339 |
+
-5.7438848880358755
|
340 |
+
],
|
341 |
+
[
|
342 |
+
"▁on",
|
343 |
+
-5.812146705563066
|
344 |
+
],
|
345 |
+
[
|
346 |
+
"▁he",
|
347 |
+
-5.884272913006647
|
348 |
+
],
|
349 |
+
[
|
350 |
+
"▁are",
|
351 |
+
-5.911223094826356
|
352 |
+
],
|
353 |
+
[
|
354 |
+
"▁as",
|
355 |
+
-5.929833784333763
|
356 |
+
],
|
357 |
+
[
|
358 |
+
"▁was",
|
359 |
+
-5.944656786916921
|
360 |
+
],
|
361 |
+
[
|
362 |
+
"▁with",
|
363 |
+
-5.9466281189802785
|
364 |
+
],
|
365 |
+
[
|
366 |
+
"ve",
|
367 |
+
-6.029713712838138
|
368 |
+
],
|
369 |
+
[
|
370 |
+
"▁have",
|
371 |
+
-6.056062667440742
|
372 |
+
],
|
373 |
+
[
|
374 |
+
"▁but",
|
375 |
+
-6.078495912607513
|
376 |
+
],
|
377 |
+
[
|
378 |
+
"▁do",
|
379 |
+
-6.120033501363503
|
380 |
+
],
|
381 |
+
[
|
382 |
+
"▁this",
|
383 |
+
-6.1351301241312495
|
384 |
+
],
|
385 |
+
[
|
386 |
+
"ur",
|
387 |
+
-6.159085253292082
|
388 |
+
],
|
389 |
+
[
|
390 |
+
"▁co",
|
391 |
+
-6.163495625813539
|
392 |
+
],
|
393 |
+
[
|
394 |
+
"▁not",
|
395 |
+
-6.168869881961024
|
396 |
+
],
|
397 |
+
[
|
398 |
+
"ation",
|
399 |
+
-6.174891736114809
|
400 |
+
],
|
401 |
+
[
|
402 |
+
"▁they",
|
403 |
+
-6.23089689749701
|
404 |
+
],
|
405 |
+
[
|
406 |
+
"us",
|
407 |
+
-6.263880501182481
|
408 |
+
],
|
409 |
+
[
|
410 |
+
"▁one",
|
411 |
+
-6.280948860315329
|
412 |
+
],
|
413 |
+
[
|
414 |
+
"'s",
|
415 |
+
-6.287063313479678
|
416 |
+
],
|
417 |
+
[
|
418 |
+
"▁or",
|
419 |
+
-6.295727284839586
|
420 |
+
],
|
421 |
+
[
|
422 |
+
"▁ma",
|
423 |
+
-6.3328402203360845
|
424 |
+
],
|
425 |
+
[
|
426 |
+
"▁me",
|
427 |
+
-6.342682111290028
|
428 |
+
],
|
429 |
+
[
|
430 |
+
"▁can",
|
431 |
+
-6.347928769198855
|
432 |
+
],
|
433 |
+
[
|
434 |
+
"▁an",
|
435 |
+
-6.386687084496497
|
436 |
+
],
|
437 |
+
[
|
438 |
+
"▁con",
|
439 |
+
-6.411591977758148
|
440 |
+
],
|
441 |
+
[
|
442 |
+
"ll",
|
443 |
+
-6.421978033658174
|
444 |
+
],
|
445 |
+
[
|
446 |
+
"▁pa",
|
447 |
+
-6.485767473048488
|
448 |
+
],
|
449 |
+
[
|
450 |
+
"ck",
|
451 |
+
-6.498920060222398
|
452 |
+
],
|
453 |
+
[
|
454 |
+
"▁from",
|
455 |
+
-6.510430181366688
|
456 |
+
],
|
457 |
+
[
|
458 |
+
"▁said",
|
459 |
+
-6.549799059746496
|
460 |
+
],
|
461 |
+
[
|
462 |
+
"▁all",
|
463 |
+
-6.55976072022162
|
464 |
+
],
|
465 |
+
[
|
466 |
+
"▁ch",
|
467 |
+
-6.569055886948073
|
468 |
+
],
|
469 |
+
[
|
470 |
+
"▁there",
|
471 |
+
-6.583017726253843
|
472 |
+
],
|
473 |
+
[
|
474 |
+
"▁what",
|
475 |
+
-6.586112233691296
|
476 |
+
],
|
477 |
+
[
|
478 |
+
"▁ca",
|
479 |
+
-6.617227466784206
|
480 |
+
],
|
481 |
+
[
|
482 |
+
"ide",
|
483 |
+
-6.630277697578055
|
484 |
+
],
|
485 |
+
[
|
486 |
+
"'",
|
487 |
+
-6.636383868446295
|
488 |
+
],
|
489 |
+
[
|
490 |
+
"▁lo",
|
491 |
+
-6.6583996554982825
|
492 |
+
],
|
493 |
+
[
|
494 |
+
"▁ex",
|
495 |
+
-6.680873400433887
|
496 |
+
],
|
497 |
+
[
|
498 |
+
"▁go",
|
499 |
+
-6.684875077627904
|
500 |
+
],
|
501 |
+
[
|
502 |
+
"▁ba",
|
503 |
+
-6.691013699795855
|
504 |
+
],
|
505 |
+
[
|
506 |
+
"age",
|
507 |
+
-6.692079993714321
|
508 |
+
],
|
509 |
+
[
|
510 |
+
"▁by",
|
511 |
+
-6.697920339970178
|
512 |
+
],
|
513 |
+
[
|
514 |
+
"▁about",
|
515 |
+
-6.705057222090151
|
516 |
+
],
|
517 |
+
[
|
518 |
+
"▁more",
|
519 |
+
-6.712459504370521
|
520 |
+
],
|
521 |
+
[
|
522 |
+
"▁no",
|
523 |
+
-6.724089235660815
|
524 |
+
],
|
525 |
+
[
|
526 |
+
"▁who",
|
527 |
+
-6.728620204290843
|
528 |
+
],
|
529 |
+
[
|
530 |
+
"▁my",
|
531 |
+
-6.738463579994516
|
532 |
+
],
|
533 |
+
[
|
534 |
+
"▁out",
|
535 |
+
-6.743812086790612
|
536 |
+
],
|
537 |
+
[
|
538 |
+
"men",
|
539 |
+
-6.749756175437181
|
540 |
+
],
|
541 |
+
[
|
542 |
+
"▁will",
|
543 |
+
-6.750296473528447
|
544 |
+
],
|
545 |
+
[
|
546 |
+
"▁people",
|
547 |
+
-6.752779647842171
|
548 |
+
],
|
549 |
+
[
|
550 |
+
"▁their",
|
551 |
+
-6.762497277425371
|
552 |
+
],
|
553 |
+
[
|
554 |
+
"▁pro",
|
555 |
+
-6.778461406812822
|
556 |
+
],
|
557 |
+
[
|
558 |
+
"rea",
|
559 |
+
-6.784288329157702
|
560 |
+
],
|
561 |
+
[
|
562 |
+
"j",
|
563 |
+
-6.7882011736527
|
564 |
+
],
|
565 |
+
[
|
566 |
+
"one",
|
567 |
+
-6.794778316215314
|
568 |
+
],
|
569 |
+
[
|
570 |
+
"ive",
|
571 |
+
-6.813780868209756
|
572 |
+
],
|
573 |
+
[
|
574 |
+
"▁up",
|
575 |
+
-6.820641238110763
|
576 |
+
],
|
577 |
+
[
|
578 |
+
"▁th",
|
579 |
+
-6.828317656094255
|
580 |
+
],
|
581 |
+
[
|
582 |
+
"per",
|
583 |
+
-6.830780397681883
|
584 |
+
],
|
585 |
+
[
|
586 |
+
"▁when",
|
587 |
+
-6.845789034417839
|
588 |
+
],
|
589 |
+
[
|
590 |
+
"▁like",
|
591 |
+
-6.846099446872435
|
592 |
+
],
|
593 |
+
[
|
594 |
+
"▁has",
|
595 |
+
-6.858481313045967
|
596 |
+
],
|
597 |
+
[
|
598 |
+
"▁two",
|
599 |
+
-6.875403572167361
|
600 |
+
],
|
601 |
+
[
|
602 |
+
"▁her",
|
603 |
+
-6.87786488262225
|
604 |
+
],
|
605 |
+
[
|
606 |
+
"ure",
|
607 |
+
-6.890885409969632
|
608 |
+
],
|
609 |
+
[
|
610 |
+
"x",
|
611 |
+
-6.898140163448579
|
612 |
+
],
|
613 |
+
[
|
614 |
+
"▁some",
|
615 |
+
-6.901803863061465
|
616 |
+
],
|
617 |
+
[
|
618 |
+
"▁his",
|
619 |
+
-6.903905558474838
|
620 |
+
],
|
621 |
+
[
|
622 |
+
"▁time",
|
623 |
+
-6.9079754944200875
|
624 |
+
],
|
625 |
+
[
|
626 |
+
"les",
|
627 |
+
-6.940601705628119
|
628 |
+
],
|
629 |
+
[
|
630 |
+
"▁she",
|
631 |
+
-6.950713176332071
|
632 |
+
],
|
633 |
+
[
|
634 |
+
"▁sh",
|
635 |
+
-6.952521338654098
|
636 |
+
],
|
637 |
+
[
|
638 |
+
"red",
|
639 |
+
-6.958620516243249
|
640 |
+
],
|
641 |
+
[
|
642 |
+
"▁see",
|
643 |
+
-6.982276000845513
|
644 |
+
],
|
645 |
+
[
|
646 |
+
"▁would",
|
647 |
+
-6.983175910632584
|
648 |
+
],
|
649 |
+
[
|
650 |
+
"▁get",
|
651 |
+
-6.9876750913724255
|
652 |
+
],
|
653 |
+
[
|
654 |
+
"▁ha",
|
655 |
+
-6.988701633352516
|
656 |
+
],
|
657 |
+
[
|
658 |
+
"▁our",
|
659 |
+
-6.994954275263089
|
660 |
+
],
|
661 |
+
[
|
662 |
+
"▁pre",
|
663 |
+
-7.001261302546547
|
664 |
+
],
|
665 |
+
[
|
666 |
+
"▁had",
|
667 |
+
-7.0086949025400305
|
668 |
+
],
|
669 |
+
[
|
670 |
+
"▁were",
|
671 |
+
-7.014572559915722
|
672 |
+
],
|
673 |
+
[
|
674 |
+
"▁just",
|
675 |
+
-7.015066325981126
|
676 |
+
],
|
677 |
+
[
|
678 |
+
"▁thousand",
|
679 |
+
-7.027882847809208
|
680 |
+
],
|
681 |
+
[
|
682 |
+
"end",
|
683 |
+
-7.032569076938101
|
684 |
+
],
|
685 |
+
[
|
686 |
+
"▁cl",
|
687 |
+
-7.033247703700155
|
688 |
+
],
|
689 |
+
[
|
690 |
+
"z",
|
691 |
+
-7.036404857337107
|
692 |
+
],
|
693 |
+
[
|
694 |
+
"able",
|
695 |
+
-7.045084509819366
|
696 |
+
],
|
697 |
+
[
|
698 |
+
"ight",
|
699 |
+
-7.049731749195802
|
700 |
+
],
|
701 |
+
[
|
702 |
+
"▁it's",
|
703 |
+
-7.051805370713197
|
704 |
+
],
|
705 |
+
[
|
706 |
+
"▁how",
|
707 |
+
-7.058726391933213
|
708 |
+
],
|
709 |
+
[
|
710 |
+
"▁hundred",
|
711 |
+
-7.059674179353372
|
712 |
+
],
|
713 |
+
[
|
714 |
+
"▁comp",
|
715 |
+
-7.083542356209991
|
716 |
+
],
|
717 |
+
[
|
718 |
+
"▁dis",
|
719 |
+
-7.093914212996811
|
720 |
+
],
|
721 |
+
[
|
722 |
+
"▁your",
|
723 |
+
-7.117440901089486
|
724 |
+
],
|
725 |
+
[
|
726 |
+
"▁than",
|
727 |
+
-7.1288683714327
|
728 |
+
],
|
729 |
+
[
|
730 |
+
"▁which",
|
731 |
+
-7.12935647113321
|
732 |
+
],
|
733 |
+
[
|
734 |
+
"▁work",
|
735 |
+
-7.129359951395429
|
736 |
+
],
|
737 |
+
[
|
738 |
+
"▁other",
|
739 |
+
-7.135976300026181
|
740 |
+
],
|
741 |
+
[
|
742 |
+
"▁say",
|
743 |
+
-7.177611083373813
|
744 |
+
],
|
745 |
+
[
|
746 |
+
"▁vi",
|
747 |
+
-7.181149894078873
|
748 |
+
],
|
749 |
+
[
|
750 |
+
"ver",
|
751 |
+
-7.19196386046308
|
752 |
+
],
|
753 |
+
[
|
754 |
+
"▁cr",
|
755 |
+
-7.19324258190079
|
756 |
+
],
|
757 |
+
[
|
758 |
+
"▁know",
|
759 |
+
-7.196656171543747
|
760 |
+
],
|
761 |
+
[
|
762 |
+
"▁new",
|
763 |
+
-7.200727503764982
|
764 |
+
],
|
765 |
+
[
|
766 |
+
"ther",
|
767 |
+
-7.2049247144042905
|
768 |
+
],
|
769 |
+
[
|
770 |
+
"▁been",
|
771 |
+
-7.205833241748344
|
772 |
+
],
|
773 |
+
[
|
774 |
+
"ach",
|
775 |
+
-7.20822932829242
|
776 |
+
],
|
777 |
+
[
|
778 |
+
"ance",
|
779 |
+
-7.208401352102109
|
780 |
+
],
|
781 |
+
[
|
782 |
+
"com",
|
783 |
+
-7.2587815267099085
|
784 |
+
],
|
785 |
+
[
|
786 |
+
"ical",
|
787 |
+
-7.278190190681173
|
788 |
+
],
|
789 |
+
[
|
790 |
+
"▁sta",
|
791 |
+
-7.296280193027171
|
792 |
+
],
|
793 |
+
[
|
794 |
+
"▁make",
|
795 |
+
-7.297080155631601
|
796 |
+
],
|
797 |
+
[
|
798 |
+
"man",
|
799 |
+
-7.297357070474021
|
800 |
+
],
|
801 |
+
[
|
802 |
+
"▁pu",
|
803 |
+
-7.301110944798579
|
804 |
+
],
|
805 |
+
[
|
806 |
+
"▁car",
|
807 |
+
-7.307416744513652
|
808 |
+
],
|
809 |
+
[
|
810 |
+
"▁think",
|
811 |
+
-7.315076410486416
|
812 |
+
],
|
813 |
+
[
|
814 |
+
"gra",
|
815 |
+
-7.327973901718581
|
816 |
+
],
|
817 |
+
[
|
818 |
+
"▁even",
|
819 |
+
-7.329667453772981
|
820 |
+
],
|
821 |
+
[
|
822 |
+
"▁now",
|
823 |
+
-7.334324859615645
|
824 |
+
],
|
825 |
+
[
|
826 |
+
"▁want",
|
827 |
+
-7.338644082597577
|
828 |
+
],
|
829 |
+
[
|
830 |
+
"▁bu",
|
831 |
+
-7.340994934917262
|
832 |
+
],
|
833 |
+
[
|
834 |
+
"▁over",
|
835 |
+
-7.357011041337032
|
836 |
+
],
|
837 |
+
[
|
838 |
+
"▁way",
|
839 |
+
-7.358907442350613
|
840 |
+
],
|
841 |
+
[
|
842 |
+
"▁into",
|
843 |
+
-7.361535232495493
|
844 |
+
],
|
845 |
+
[
|
846 |
+
"ction",
|
847 |
+
-7.370624313735973
|
848 |
+
],
|
849 |
+
[
|
850 |
+
"▁res",
|
851 |
+
-7.370897459814927
|
852 |
+
],
|
853 |
+
[
|
854 |
+
"tter",
|
855 |
+
-7.372367561211393
|
856 |
+
],
|
857 |
+
[
|
858 |
+
"▁la",
|
859 |
+
-7.373978735498742
|
860 |
+
],
|
861 |
+
[
|
862 |
+
"ful",
|
863 |
+
-7.374168968662772
|
864 |
+
],
|
865 |
+
[
|
866 |
+
"▁because",
|
867 |
+
-7.374226327340219
|
868 |
+
],
|
869 |
+
[
|
870 |
+
"▁nine",
|
871 |
+
-7.377940224587501
|
872 |
+
],
|
873 |
+
[
|
874 |
+
"ell",
|
875 |
+
-7.381683580843712
|
876 |
+
],
|
877 |
+
[
|
878 |
+
"he",
|
879 |
+
-7.385884132318933
|
880 |
+
],
|
881 |
+
[
|
882 |
+
"▁li",
|
883 |
+
-7.386083738518794
|
884 |
+
],
|
885 |
+
[
|
886 |
+
"▁could",
|
887 |
+
-7.387987936442446
|
888 |
+
],
|
889 |
+
[
|
890 |
+
"ence",
|
891 |
+
-7.401823391179237
|
892 |
+
],
|
893 |
+
[
|
894 |
+
"▁very",
|
895 |
+
-7.408068976933194
|
896 |
+
],
|
897 |
+
[
|
898 |
+
"▁ar",
|
899 |
+
-7.416235924919285
|
900 |
+
],
|
901 |
+
[
|
902 |
+
"▁us",
|
903 |
+
-7.421022762491443
|
904 |
+
],
|
905 |
+
[
|
906 |
+
"▁them",
|
907 |
+
-7.439007960826133
|
908 |
+
],
|
909 |
+
[
|
910 |
+
"ze",
|
911 |
+
-7.442237617833339
|
912 |
+
],
|
913 |
+
[
|
914 |
+
"ally",
|
915 |
+
-7.44567320812796
|
916 |
+
],
|
917 |
+
[
|
918 |
+
"und",
|
919 |
+
-7.449077104870009
|
920 |
+
],
|
921 |
+
[
|
922 |
+
"▁look",
|
923 |
+
-7.465920105389392
|
924 |
+
],
|
925 |
+
[
|
926 |
+
"ving",
|
927 |
+
-7.476701160870153
|
928 |
+
],
|
929 |
+
[
|
930 |
+
"▁use",
|
931 |
+
-7.489550017591283
|
932 |
+
],
|
933 |
+
[
|
934 |
+
"▁need",
|
935 |
+
-7.507395353897271
|
936 |
+
],
|
937 |
+
[
|
938 |
+
"▁most",
|
939 |
+
-7.508463507233218
|
940 |
+
],
|
941 |
+
[
|
942 |
+
"ang",
|
943 |
+
-7.512544632371608
|
944 |
+
],
|
945 |
+
[
|
946 |
+
"▁every",
|
947 |
+
-7.51759581004417
|
948 |
+
],
|
949 |
+
[
|
950 |
+
"qui",
|
951 |
+
-7.5224431600372945
|
952 |
+
],
|
953 |
+
[
|
954 |
+
"▁any",
|
955 |
+
-7.523800340825591
|
956 |
+
],
|
957 |
+
[
|
958 |
+
"▁bi",
|
959 |
+
-7.526209973364397
|
960 |
+
],
|
961 |
+
[
|
962 |
+
"▁cu",
|
963 |
+
-7.53298549315272
|
964 |
+
],
|
965 |
+
[
|
966 |
+
"ill",
|
967 |
+
-7.542831181363784
|
968 |
+
],
|
969 |
+
[
|
970 |
+
"▁only",
|
971 |
+
-7.542967005319634
|
972 |
+
],
|
973 |
+
[
|
974 |
+
"▁its",
|
975 |
+
-7.548158954564297
|
976 |
+
],
|
977 |
+
[
|
978 |
+
"▁take",
|
979 |
+
-7.549454035649397
|
980 |
+
],
|
981 |
+
[
|
982 |
+
"▁day",
|
983 |
+
-7.552893231103514
|
984 |
+
],
|
985 |
+
[
|
986 |
+
"▁part",
|
987 |
+
-7.555055024187217
|
988 |
+
],
|
989 |
+
[
|
990 |
+
"▁back",
|
991 |
+
-7.556383210659435
|
992 |
+
],
|
993 |
+
[
|
994 |
+
"▁three",
|
995 |
+
-7.557901106933517
|
996 |
+
],
|
997 |
+
[
|
998 |
+
"▁going",
|
999 |
+
-7.561348004910165
|
1000 |
+
],
|
1001 |
+
[
|
1002 |
+
"ever",
|
1003 |
+
-7.562036821423799
|
1004 |
+
],
|
1005 |
+
[
|
1006 |
+
"▁years",
|
1007 |
+
-7.562332353467326
|
1008 |
+
],
|
1009 |
+
[
|
1010 |
+
"▁also",
|
1011 |
+
-7.563420504567631
|
1012 |
+
],
|
1013 |
+
[
|
1014 |
+
"▁these",
|
1015 |
+
-7.563445901010146
|
1016 |
+
],
|
1017 |
+
[
|
1018 |
+
"▁world",
|
1019 |
+
-7.5658527282563615
|
1020 |
+
],
|
1021 |
+
[
|
1022 |
+
"▁jo",
|
1023 |
+
-7.566271341802086
|
1024 |
+
],
|
1025 |
+
[
|
1026 |
+
"for",
|
1027 |
+
-7.573909200353221
|
1028 |
+
],
|
1029 |
+
[
|
1030 |
+
"ated",
|
1031 |
+
-7.574595698553555
|
1032 |
+
],
|
1033 |
+
[
|
1034 |
+
"▁where",
|
1035 |
+
-7.582311490247017
|
1036 |
+
],
|
1037 |
+
[
|
1038 |
+
"▁app",
|
1039 |
+
-7.583407657098212
|
1040 |
+
],
|
1041 |
+
[
|
1042 |
+
"ble",
|
1043 |
+
-7.627885239687924
|
1044 |
+
],
|
1045 |
+
[
|
1046 |
+
"▁five",
|
1047 |
+
-7.631767928016325
|
1048 |
+
],
|
1049 |
+
[
|
1050 |
+
"▁many",
|
1051 |
+
-7.635697451452412
|
1052 |
+
],
|
1053 |
+
[
|
1054 |
+
"▁rec",
|
1055 |
+
-7.637686462277017
|
1056 |
+
],
|
1057 |
+
[
|
1058 |
+
"▁first",
|
1059 |
+
-7.644434380130837
|
1060 |
+
],
|
1061 |
+
[
|
1062 |
+
"▁much",
|
1063 |
+
-7.644436171280626
|
1064 |
+
],
|
1065 |
+
[
|
1066 |
+
"▁good",
|
1067 |
+
-7.657353544125229
|
1068 |
+
],
|
1069 |
+
[
|
1070 |
+
"▁don't",
|
1071 |
+
-7.676856549107038
|
1072 |
+
],
|
1073 |
+
[
|
1074 |
+
"▁ga",
|
1075 |
+
-7.692179576415008
|
1076 |
+
],
|
1077 |
+
[
|
1078 |
+
"▁six",
|
1079 |
+
-7.69269356597826
|
1080 |
+
],
|
1081 |
+
[
|
1082 |
+
"q",
|
1083 |
+
-7.696493807735175
|
1084 |
+
],
|
1085 |
+
[
|
1086 |
+
"rac",
|
1087 |
+
-7.70076984035417
|
1088 |
+
],
|
1089 |
+
[
|
1090 |
+
"▁him",
|
1091 |
+
-7.708060244213304
|
1092 |
+
],
|
1093 |
+
[
|
1094 |
+
"▁may",
|
1095 |
+
-7.710511654127949
|
1096 |
+
],
|
1097 |
+
[
|
1098 |
+
"▁pri",
|
1099 |
+
-7.722091815046568
|
1100 |
+
],
|
1101 |
+
[
|
1102 |
+
"▁come",
|
1103 |
+
-7.723292409553084
|
1104 |
+
],
|
1105 |
+
[
|
1106 |
+
"▁those",
|
1107 |
+
-7.724939069549471
|
1108 |
+
],
|
1109 |
+
[
|
1110 |
+
"▁play",
|
1111 |
+
-7.728249278606006
|
1112 |
+
],
|
1113 |
+
[
|
1114 |
+
"ster",
|
1115 |
+
-7.729194989675044
|
1116 |
+
],
|
1117 |
+
[
|
1118 |
+
"▁life",
|
1119 |
+
-7.739615405532483
|
1120 |
+
],
|
1121 |
+
[
|
1122 |
+
"led",
|
1123 |
+
-7.741277900326592
|
1124 |
+
],
|
1125 |
+
[
|
1126 |
+
"▁mu",
|
1127 |
+
-7.743922966825698
|
1128 |
+
],
|
1129 |
+
[
|
1130 |
+
"ries",
|
1131 |
+
-7.744512973191547
|
1132 |
+
],
|
1133 |
+
[
|
1134 |
+
"▁four",
|
1135 |
+
-7.755243064488333
|
1136 |
+
],
|
1137 |
+
[
|
1138 |
+
"mer",
|
1139 |
+
-7.759376851450931
|
1140 |
+
],
|
1141 |
+
[
|
1142 |
+
"lic",
|
1143 |
+
-7.759810124548855
|
1144 |
+
],
|
1145 |
+
[
|
1146 |
+
"▁after",
|
1147 |
+
-7.77115435303911
|
1148 |
+
],
|
1149 |
+
[
|
1150 |
+
"ress",
|
1151 |
+
-7.772231241897558
|
1152 |
+
],
|
1153 |
+
[
|
1154 |
+
"▁eight",
|
1155 |
+
-7.775065267931247
|
1156 |
+
],
|
1157 |
+
[
|
1158 |
+
"▁really",
|
1159 |
+
-7.78233366423092
|
1160 |
+
],
|
1161 |
+
[
|
1162 |
+
"▁year",
|
1163 |
+
-7.788820100546483
|
1164 |
+
],
|
1165 |
+
[
|
1166 |
+
"rate",
|
1167 |
+
-7.790966895572762
|
1168 |
+
],
|
1169 |
+
[
|
1170 |
+
"▁well",
|
1171 |
+
-7.79503801679831
|
1172 |
+
],
|
1173 |
+
[
|
1174 |
+
"▁rel",
|
1175 |
+
-7.800763301209921
|
1176 |
+
],
|
1177 |
+
[
|
1178 |
+
"ugh",
|
1179 |
+
-7.80508067156425
|
1180 |
+
],
|
1181 |
+
[
|
1182 |
+
"▁long",
|
1183 |
+
-7.81463592369218
|
1184 |
+
],
|
1185 |
+
[
|
1186 |
+
"▁through",
|
1187 |
+
-7.829704400466477
|
1188 |
+
],
|
1189 |
+
[
|
1190 |
+
"▁seven",
|
1191 |
+
-7.836407871710429
|
1192 |
+
],
|
1193 |
+
[
|
1194 |
+
"▁down",
|
1195 |
+
-7.836418492278396
|
1196 |
+
],
|
1197 |
+
[
|
1198 |
+
"▁right",
|
1199 |
+
-7.858358391858477
|
1200 |
+
],
|
1201 |
+
[
|
1202 |
+
"▁gu",
|
1203 |
+
-7.86040337421632
|
1204 |
+
],
|
1205 |
+
[
|
1206 |
+
"▁should",
|
1207 |
+
-7.8786070173740015
|
1208 |
+
],
|
1209 |
+
[
|
1210 |
+
"▁show",
|
1211 |
+
-7.8912844366308175
|
1212 |
+
],
|
1213 |
+
[
|
1214 |
+
"cent",
|
1215 |
+
-7.898714301504919
|
1216 |
+
],
|
1217 |
+
[
|
1218 |
+
"▁imp",
|
1219 |
+
-7.9007884922169005
|
1220 |
+
],
|
1221 |
+
[
|
1222 |
+
"low",
|
1223 |
+
-7.905991712097462
|
1224 |
+
],
|
1225 |
+
[
|
1226 |
+
"port",
|
1227 |
+
-7.914066728567356
|
1228 |
+
],
|
1229 |
+
[
|
1230 |
+
"line",
|
1231 |
+
-7.9204166022994045
|
1232 |
+
],
|
1233 |
+
[
|
1234 |
+
"▁twenty",
|
1235 |
+
-7.9331023799425235
|
1236 |
+
],
|
1237 |
+
[
|
1238 |
+
"▁inter",
|
1239 |
+
-7.933146540231563
|
1240 |
+
],
|
1241 |
+
[
|
1242 |
+
"▁point",
|
1243 |
+
-7.947713293554528
|
1244 |
+
],
|
1245 |
+
[
|
1246 |
+
"▁though",
|
1247 |
+
-7.950963442024104
|
1248 |
+
],
|
1249 |
+
[
|
1250 |
+
"▁help",
|
1251 |
+
-7.953395760731329
|
1252 |
+
],
|
1253 |
+
[
|
1254 |
+
"unk",
|
1255 |
+
-7.964053831789903
|
1256 |
+
],
|
1257 |
+
[
|
1258 |
+
"land",
|
1259 |
+
-7.969005005504924
|
1260 |
+
],
|
1261 |
+
[
|
1262 |
+
"late",
|
1263 |
+
-7.974607980796545
|
1264 |
+
],
|
1265 |
+
[
|
1266 |
+
"▁high",
|
1267 |
+
-7.979294411944041
|
1268 |
+
],
|
1269 |
+
[
|
1270 |
+
"hol",
|
1271 |
+
-7.984142148598162
|
1272 |
+
],
|
1273 |
+
[
|
1274 |
+
"▁something",
|
1275 |
+
-7.987930016312793
|
1276 |
+
],
|
1277 |
+
[
|
1278 |
+
"▁start",
|
1279 |
+
-7.9915214497126765
|
1280 |
+
],
|
1281 |
+
[
|
1282 |
+
"▁great",
|
1283 |
+
-7.995695921767435
|
1284 |
+
],
|
1285 |
+
[
|
1286 |
+
"▁did",
|
1287 |
+
-7.995769657368475
|
1288 |
+
],
|
1289 |
+
[
|
1290 |
+
"▁own",
|
1291 |
+
-7.998997362615388
|
1292 |
+
],
|
1293 |
+
[
|
1294 |
+
"▁still",
|
1295 |
+
-8.004415671326594
|
1296 |
+
],
|
1297 |
+
[
|
1298 |
+
"▁give",
|
1299 |
+
-8.007682726112
|
1300 |
+
],
|
1301 |
+
[
|
1302 |
+
"▁change",
|
1303 |
+
-8.04354751743401
|
1304 |
+
],
|
1305 |
+
[
|
1306 |
+
"▁live",
|
1307 |
+
-8.045269835331224
|
1308 |
+
],
|
1309 |
+
[
|
1310 |
+
"▁mean",
|
1311 |
+
-8.05133774848325
|
1312 |
+
],
|
1313 |
+
[
|
1314 |
+
"▁ten",
|
1315 |
+
-8.056860573632987
|
1316 |
+
],
|
1317 |
+
[
|
1318 |
+
"ions",
|
1319 |
+
-8.056903676226453
|
1320 |
+
],
|
1321 |
+
[
|
1322 |
+
"▁feel",
|
1323 |
+
-8.0580666657745
|
1324 |
+
],
|
1325 |
+
[
|
1326 |
+
"dent",
|
1327 |
+
-8.066761170886625
|
1328 |
+
],
|
1329 |
+
[
|
1330 |
+
"▁plan",
|
1331 |
+
-8.071036532069423
|
1332 |
+
],
|
1333 |
+
[
|
1334 |
+
"▁around",
|
1335 |
+
-8.07490021206401
|
1336 |
+
],
|
1337 |
+
[
|
1338 |
+
"▁again",
|
1339 |
+
-8.088898555817392
|
1340 |
+
],
|
1341 |
+
[
|
1342 |
+
"ked",
|
1343 |
+
-8.090024710382105
|
1344 |
+
],
|
1345 |
+
[
|
1346 |
+
"▁i'm",
|
1347 |
+
-8.092715477262875
|
1348 |
+
],
|
1349 |
+
[
|
1350 |
+
"▁win",
|
1351 |
+
-8.100661165025913
|
1352 |
+
],
|
1353 |
+
[
|
1354 |
+
"▁before",
|
1355 |
+
-8.10448978812413
|
1356 |
+
],
|
1357 |
+
[
|
1358 |
+
"▁place",
|
1359 |
+
-8.104619689156987
|
1360 |
+
],
|
1361 |
+
[
|
1362 |
+
"▁find",
|
1363 |
+
-8.114301047518076
|
1364 |
+
],
|
1365 |
+
[
|
1366 |
+
"▁rep",
|
1367 |
+
-8.122315146334142
|
1368 |
+
],
|
1369 |
+
[
|
1370 |
+
"▁old",
|
1371 |
+
-8.123425447706955
|
1372 |
+
],
|
1373 |
+
[
|
1374 |
+
"que",
|
1375 |
+
-8.124806078291178
|
1376 |
+
],
|
1377 |
+
[
|
1378 |
+
"▁home",
|
1379 |
+
-8.138270977097743
|
1380 |
+
],
|
1381 |
+
[
|
1382 |
+
"▁same",
|
1383 |
+
-8.146767026460111
|
1384 |
+
],
|
1385 |
+
[
|
1386 |
+
"▁made",
|
1387 |
+
-8.146986846010165
|
1388 |
+
],
|
1389 |
+
[
|
1390 |
+
"ities",
|
1391 |
+
-8.15076062197818
|
1392 |
+
],
|
1393 |
+
[
|
1394 |
+
"▁gene",
|
1395 |
+
-8.153271792321526
|
1396 |
+
],
|
1397 |
+
[
|
1398 |
+
"▁little",
|
1399 |
+
-8.157188696200281
|
1400 |
+
],
|
1401 |
+
[
|
1402 |
+
"▁never",
|
1403 |
+
-8.15876601141345
|
1404 |
+
],
|
1405 |
+
[
|
1406 |
+
"▁add",
|
1407 |
+
-8.16085152557753
|
1408 |
+
],
|
1409 |
+
[
|
1410 |
+
"▁dec",
|
1411 |
+
-8.162053869836686
|
1412 |
+
],
|
1413 |
+
[
|
1414 |
+
"▁such",
|
1415 |
+
-8.166487774779087
|
1416 |
+
],
|
1417 |
+
[
|
1418 |
+
"▁real",
|
1419 |
+
-8.170648079845972
|
1420 |
+
],
|
1421 |
+
[
|
1422 |
+
">",
|
1423 |
+
-8.174546931075477
|
1424 |
+
],
|
1425 |
+
[
|
1426 |
+
"<",
|
1427 |
+
-8.174546931075477
|
1428 |
+
],
|
1429 |
+
[
|
1430 |
+
"▁different",
|
1431 |
+
-8.177401003173864
|
1432 |
+
],
|
1433 |
+
[
|
1434 |
+
"▁america",
|
1435 |
+
-8.195006004980675
|
1436 |
+
],
|
1437 |
+
[
|
1438 |
+
"▁percent",
|
1439 |
+
-8.203669636244902
|
1440 |
+
],
|
1441 |
+
[
|
1442 |
+
"▁happen",
|
1443 |
+
-8.217603938472319
|
1444 |
+
],
|
1445 |
+
[
|
1446 |
+
"▁person",
|
1447 |
+
-8.22009536018725
|
1448 |
+
],
|
1449 |
+
[
|
1450 |
+
"▁try",
|
1451 |
+
-8.221193651201794
|
1452 |
+
],
|
1453 |
+
[
|
1454 |
+
"▁problem",
|
1455 |
+
-8.227408597224207
|
1456 |
+
],
|
1457 |
+
[
|
1458 |
+
"▁war",
|
1459 |
+
-8.230954901256146
|
1460 |
+
],
|
1461 |
+
[
|
1462 |
+
"▁hand",
|
1463 |
+
-8.254610862372143
|
1464 |
+
],
|
1465 |
+
[
|
1466 |
+
"▁few",
|
1467 |
+
-8.25542861805221
|
1468 |
+
],
|
1469 |
+
[
|
1470 |
+
"▁under",
|
1471 |
+
-8.259510957523512
|
1472 |
+
],
|
1473 |
+
[
|
1474 |
+
"▁might",
|
1475 |
+
-8.259548828010718
|
1476 |
+
],
|
1477 |
+
[
|
1478 |
+
"▁why",
|
1479 |
+
-8.266548799381441
|
1480 |
+
],
|
1481 |
+
[
|
1482 |
+
"▁far",
|
1483 |
+
-8.273004033857472
|
1484 |
+
],
|
1485 |
+
[
|
1486 |
+
"▁another",
|
1487 |
+
-8.275188116440123
|
1488 |
+
],
|
1489 |
+
[
|
1490 |
+
"▁while",
|
1491 |
+
-8.277332697575044
|
1492 |
+
],
|
1493 |
+
[
|
1494 |
+
"▁children",
|
1495 |
+
-8.278018743726047
|
1496 |
+
],
|
1497 |
+
[
|
1498 |
+
"▁turn",
|
1499 |
+
-8.295468236043428
|
1500 |
+
],
|
1501 |
+
[
|
1502 |
+
"▁hard",
|
1503 |
+
-8.319579651267661
|
1504 |
+
],
|
1505 |
+
[
|
1506 |
+
"▁school",
|
1507 |
+
-8.324874007903873
|
1508 |
+
],
|
1509 |
+
[
|
1510 |
+
"▁system",
|
1511 |
+
-8.334528863425346
|
1512 |
+
],
|
1513 |
+
[
|
1514 |
+
"▁fact",
|
1515 |
+
-8.340618576727202
|
1516 |
+
],
|
1517 |
+
[
|
1518 |
+
"ship",
|
1519 |
+
-8.356785263078958
|
1520 |
+
],
|
1521 |
+
[
|
1522 |
+
"▁fun",
|
1523 |
+
-8.35745033900121
|
1524 |
+
],
|
1525 |
+
[
|
1526 |
+
"▁found",
|
1527 |
+
-8.357664922206958
|
1528 |
+
],
|
1529 |
+
[
|
1530 |
+
"▁talk",
|
1531 |
+
-8.360321901371398
|
1532 |
+
],
|
1533 |
+
[
|
1534 |
+
"▁always",
|
1535 |
+
-8.36245965305476
|
1536 |
+
],
|
1537 |
+
[
|
1538 |
+
"▁water",
|
1539 |
+
-8.366181844042655
|
1540 |
+
],
|
1541 |
+
[
|
1542 |
+
"▁kind",
|
1543 |
+
-8.370441708712251
|
1544 |
+
],
|
1545 |
+
[
|
1546 |
+
"▁power",
|
1547 |
+
-8.407352983466396
|
1548 |
+
],
|
1549 |
+
[
|
1550 |
+
"serv",
|
1551 |
+
-8.417257194651873
|
1552 |
+
],
|
1553 |
+
[
|
1554 |
+
"▁human",
|
1555 |
+
-8.422197729087948
|
1556 |
+
],
|
1557 |
+
[
|
1558 |
+
"▁thirty",
|
1559 |
+
-8.424889240542294
|
1560 |
+
],
|
1561 |
+
[
|
1562 |
+
"▁move",
|
1563 |
+
-8.425313917158071
|
1564 |
+
],
|
1565 |
+
[
|
1566 |
+
"▁develop",
|
1567 |
+
-8.432217995201649
|
1568 |
+
],
|
1569 |
+
[
|
1570 |
+
"▁country",
|
1571 |
+
-8.437154694153355
|
1572 |
+
],
|
1573 |
+
[
|
1574 |
+
"bility",
|
1575 |
+
-8.442062543843859
|
1576 |
+
],
|
1577 |
+
[
|
1578 |
+
"▁trans",
|
1579 |
+
-8.445491134571297
|
1580 |
+
],
|
1581 |
+
[
|
1582 |
+
"▁keep",
|
1583 |
+
-8.447121538590636
|
1584 |
+
],
|
1585 |
+
[
|
1586 |
+
"▁between",
|
1587 |
+
-8.450074712109986
|
1588 |
+
],
|
1589 |
+
[
|
1590 |
+
"▁question",
|
1591 |
+
-8.45132704745506
|
1592 |
+
],
|
1593 |
+
[
|
1594 |
+
"▁blo",
|
1595 |
+
-8.457137199160444
|
1596 |
+
],
|
1597 |
+
[
|
1598 |
+
"▁small",
|
1599 |
+
-8.464488253220336
|
1600 |
+
],
|
1601 |
+
[
|
1602 |
+
"▁both",
|
1603 |
+
-8.465391170838778
|
1604 |
+
],
|
1605 |
+
[
|
1606 |
+
"▁money",
|
1607 |
+
-8.471480248618416
|
1608 |
+
],
|
1609 |
+
[
|
1610 |
+
"▁important",
|
1611 |
+
-8.474535449814978
|
1612 |
+
],
|
1613 |
+
[
|
1614 |
+
"▁women",
|
1615 |
+
-8.488463151090519
|
1616 |
+
],
|
1617 |
+
[
|
1618 |
+
"▁next",
|
1619 |
+
-8.499226729264004
|
1620 |
+
],
|
1621 |
+
[
|
1622 |
+
"▁fifty",
|
1623 |
+
-8.508940876979525
|
1624 |
+
],
|
1625 |
+
[
|
1626 |
+
"ality",
|
1627 |
+
-8.518162563343077
|
1628 |
+
],
|
1629 |
+
[
|
1630 |
+
"▁we're",
|
1631 |
+
-8.523634714033474
|
1632 |
+
],
|
1633 |
+
[
|
1634 |
+
"▁friend",
|
1635 |
+
-8.529359417835346
|
1636 |
+
],
|
1637 |
+
[
|
1638 |
+
"▁family",
|
1639 |
+
-8.535293339824516
|
1640 |
+
],
|
1641 |
+
[
|
1642 |
+
"▁without",
|
1643 |
+
-8.537235506300181
|
1644 |
+
],
|
1645 |
+
[
|
1646 |
+
"▁away",
|
1647 |
+
-8.538471008287003
|
1648 |
+
],
|
1649 |
+
[
|
1650 |
+
"▁build",
|
1651 |
+
-8.53887194141614
|
1652 |
+
],
|
1653 |
+
[
|
1654 |
+
"▁lead",
|
1655 |
+
-8.541724089953993
|
1656 |
+
],
|
1657 |
+
[
|
1658 |
+
"▁today",
|
1659 |
+
-8.556512784276263
|
1660 |
+
],
|
1661 |
+
[
|
1662 |
+
"▁number",
|
1663 |
+
-8.558202484196892
|
1664 |
+
],
|
1665 |
+
[
|
1666 |
+
"▁large",
|
1667 |
+
-8.564258756492881
|
1668 |
+
],
|
1669 |
+
[
|
1670 |
+
"▁health",
|
1671 |
+
-8.565300531106967
|
1672 |
+
],
|
1673 |
+
[
|
1674 |
+
"▁learn",
|
1675 |
+
-8.567104799745971
|
1676 |
+
],
|
1677 |
+
[
|
1678 |
+
"▁believe",
|
1679 |
+
-8.577380612888348
|
1680 |
+
],
|
1681 |
+
[
|
1682 |
+
"▁face",
|
1683 |
+
-8.5781215463003
|
1684 |
+
],
|
1685 |
+
[
|
1686 |
+
"ption",
|
1687 |
+
-8.585144346347143
|
1688 |
+
],
|
1689 |
+
[
|
1690 |
+
"▁free",
|
1691 |
+
-8.592213001257278
|
1692 |
+
],
|
1693 |
+
[
|
1694 |
+
"▁book",
|
1695 |
+
-8.599140662214898
|
1696 |
+
],
|
1697 |
+
[
|
1698 |
+
"▁house",
|
1699 |
+
-8.602072174491202
|
1700 |
+
],
|
1701 |
+
[
|
1702 |
+
"▁business",
|
1703 |
+
-8.603458120072414
|
1704 |
+
],
|
1705 |
+
[
|
1706 |
+
"▁open",
|
1707 |
+
-8.624533589738132
|
1708 |
+
],
|
1709 |
+
[
|
1710 |
+
"▁you're",
|
1711 |
+
-8.648211923200755
|
1712 |
+
],
|
1713 |
+
[
|
1714 |
+
"▁didn't",
|
1715 |
+
-8.650732869456236
|
1716 |
+
],
|
1717 |
+
[
|
1718 |
+
"▁research",
|
1719 |
+
-8.654318581492854
|
1720 |
+
],
|
1721 |
+
[
|
1722 |
+
"▁government",
|
1723 |
+
-8.659900246962522
|
1724 |
+
],
|
1725 |
+
[
|
1726 |
+
"▁enough",
|
1727 |
+
-8.661264202203283
|
1728 |
+
],
|
1729 |
+
[
|
1730 |
+
"▁market",
|
1731 |
+
-8.667470844760473
|
1732 |
+
],
|
1733 |
+
[
|
1734 |
+
"▁experience",
|
1735 |
+
-8.668982145927787
|
1736 |
+
],
|
1737 |
+
[
|
1738 |
+
"▁course",
|
1739 |
+
-8.66977737797813
|
1740 |
+
],
|
1741 |
+
[
|
1742 |
+
"▁second",
|
1743 |
+
-8.700729924214153
|
1744 |
+
],
|
1745 |
+
[
|
1746 |
+
"▁create",
|
1747 |
+
-8.70142942845552
|
1748 |
+
],
|
1749 |
+
[
|
1750 |
+
"▁together",
|
1751 |
+
-8.705533541005918
|
1752 |
+
],
|
1753 |
+
[
|
1754 |
+
"▁product",
|
1755 |
+
-8.707952333543426
|
1756 |
+
],
|
1757 |
+
[
|
1758 |
+
"▁month",
|
1759 |
+
-8.712667102719207
|
1760 |
+
],
|
1761 |
+
[
|
1762 |
+
"▁understand",
|
1763 |
+
-8.714626952165377
|
1764 |
+
],
|
1765 |
+
[
|
1766 |
+
"▁group",
|
1767 |
+
-8.719622335030813
|
1768 |
+
],
|
1769 |
+
[
|
1770 |
+
"▁hope",
|
1771 |
+
-8.72761204981612
|
1772 |
+
],
|
1773 |
+
[
|
1774 |
+
"▁word",
|
1775 |
+
-8.738163070498095
|
1776 |
+
],
|
1777 |
+
[
|
1778 |
+
"▁actually",
|
1779 |
+
-8.739409587339784
|
1780 |
+
],
|
1781 |
+
[
|
1782 |
+
"▁million",
|
1783 |
+
-8.74144010215678
|
1784 |
+
],
|
1785 |
+
[
|
1786 |
+
"▁public",
|
1787 |
+
-8.742966764345939
|
1788 |
+
],
|
1789 |
+
[
|
1790 |
+
"▁food",
|
1791 |
+
-8.752893623113762
|
1792 |
+
],
|
1793 |
+
[
|
1794 |
+
"▁effect",
|
1795 |
+
-8.757232196017489
|
1796 |
+
],
|
1797 |
+
[
|
1798 |
+
"▁design",
|
1799 |
+
-8.76188226991536
|
1800 |
+
],
|
1801 |
+
[
|
1802 |
+
"▁level",
|
1803 |
+
-8.804900237478842
|
1804 |
+
],
|
1805 |
+
[
|
1806 |
+
"▁reason",
|
1807 |
+
-8.815829965488463
|
1808 |
+
],
|
1809 |
+
[
|
1810 |
+
"▁result",
|
1811 |
+
-8.816553476957232
|
1812 |
+
],
|
1813 |
+
[
|
1814 |
+
"▁everything",
|
1815 |
+
-8.818899965733237
|
1816 |
+
],
|
1817 |
+
[
|
1818 |
+
"▁direct",
|
1819 |
+
-8.836863579748076
|
1820 |
+
],
|
1821 |
+
[
|
1822 |
+
"▁they're",
|
1823 |
+
-8.839261528715383
|
1824 |
+
],
|
1825 |
+
[
|
1826 |
+
"▁story",
|
1827 |
+
-8.848157809410475
|
1828 |
+
],
|
1829 |
+
[
|
1830 |
+
"▁watch",
|
1831 |
+
-8.856317693526307
|
1832 |
+
],
|
1833 |
+
[
|
1834 |
+
"▁process",
|
1835 |
+
-8.864285937562878
|
1836 |
+
],
|
1837 |
+
[
|
1838 |
+
"▁certain",
|
1839 |
+
-8.86481025845487
|
1840 |
+
],
|
1841 |
+
[
|
1842 |
+
"▁moment",
|
1843 |
+
-8.874608010450409
|
1844 |
+
],
|
1845 |
+
[
|
1846 |
+
"▁student",
|
1847 |
+
-8.891495076518078
|
1848 |
+
],
|
1849 |
+
[
|
1850 |
+
"▁future",
|
1851 |
+
-8.903920388479646
|
1852 |
+
],
|
1853 |
+
[
|
1854 |
+
"▁space",
|
1855 |
+
-8.907814016098657
|
1856 |
+
],
|
1857 |
+
[
|
1858 |
+
"▁whether",
|
1859 |
+
-8.913050460769428
|
1860 |
+
],
|
1861 |
+
[
|
1862 |
+
"▁anything",
|
1863 |
+
-8.915366793380104
|
1864 |
+
],
|
1865 |
+
[
|
1866 |
+
"▁control",
|
1867 |
+
-8.919573217710804
|
1868 |
+
],
|
1869 |
+
[
|
1870 |
+
"▁almost",
|
1871 |
+
-8.94655005817442
|
1872 |
+
],
|
1873 |
+
[
|
1874 |
+
"▁support",
|
1875 |
+
-8.951967867236126
|
1876 |
+
],
|
1877 |
+
[
|
1878 |
+
"▁walk",
|
1879 |
+
-8.955584246502458
|
1880 |
+
],
|
1881 |
+
[
|
1882 |
+
"▁doesn't",
|
1883 |
+
-8.963873365007096
|
1884 |
+
],
|
1885 |
+
[
|
1886 |
+
"▁information",
|
1887 |
+
-8.968889128612766
|
1888 |
+
],
|
1889 |
+
[
|
1890 |
+
"▁social",
|
1891 |
+
-8.971342303562139
|
1892 |
+
],
|
1893 |
+
[
|
1894 |
+
"▁follow",
|
1895 |
+
-8.974468157141684
|
1896 |
+
],
|
1897 |
+
[
|
1898 |
+
"▁until",
|
1899 |
+
-8.990321616601861
|
1900 |
+
],
|
1901 |
+
[
|
1902 |
+
"▁example",
|
1903 |
+
-9.001875521562726
|
1904 |
+
],
|
1905 |
+
[
|
1906 |
+
"▁difficult",
|
1907 |
+
-9.016530669785697
|
1908 |
+
],
|
1909 |
+
[
|
1910 |
+
"▁already",
|
1911 |
+
-9.017723103965798
|
1912 |
+
],
|
1913 |
+
[
|
1914 |
+
"▁expect",
|
1915 |
+
-9.02178472609668
|
1916 |
+
],
|
1917 |
+
[
|
1918 |
+
"▁energy",
|
1919 |
+
-9.024561047592886
|
1920 |
+
],
|
1921 |
+
[
|
1922 |
+
"▁success",
|
1923 |
+
-9.028600208851303
|
1924 |
+
],
|
1925 |
+
[
|
1926 |
+
"▁minute",
|
1927 |
+
-9.030795425316873
|
1928 |
+
],
|
1929 |
+
[
|
1930 |
+
"▁europe",
|
1931 |
+
-9.047719522871835
|
1932 |
+
],
|
1933 |
+
[
|
1934 |
+
"▁probably",
|
1935 |
+
-9.048211213265372
|
1936 |
+
],
|
1937 |
+
[
|
1938 |
+
"▁project",
|
1939 |
+
-9.05081191490136
|
1940 |
+
],
|
1941 |
+
[
|
1942 |
+
"▁sometimes",
|
1943 |
+
-9.053271521338392
|
1944 |
+
],
|
1945 |
+
[
|
1946 |
+
"▁photo",
|
1947 |
+
-9.059860032471327
|
1948 |
+
],
|
1949 |
+
[
|
1950 |
+
"▁patient",
|
1951 |
+
-9.075396006321792
|
1952 |
+
],
|
1953 |
+
[
|
1954 |
+
"▁across",
|
1955 |
+
-9.08167587656886
|
1956 |
+
],
|
1957 |
+
[
|
1958 |
+
"▁particular",
|
1959 |
+
-9.08822856829106
|
1960 |
+
],
|
1961 |
+
[
|
1962 |
+
"▁possible",
|
1963 |
+
-9.095938491890514
|
1964 |
+
],
|
1965 |
+
[
|
1966 |
+
"vision",
|
1967 |
+
-9.105540231265378
|
1968 |
+
],
|
1969 |
+
[
|
1970 |
+
"▁technology",
|
1971 |
+
-9.151043704411448
|
1972 |
+
],
|
1973 |
+
[
|
1974 |
+
"▁environment",
|
1975 |
+
-9.15969788447536
|
1976 |
+
],
|
1977 |
+
[
|
1978 |
+
"▁political",
|
1979 |
+
-9.167264556603437
|
1980 |
+
],
|
1981 |
+
[
|
1982 |
+
"▁themselves",
|
1983 |
+
-9.17697704069669
|
1984 |
+
],
|
1985 |
+
[
|
1986 |
+
"position",
|
1987 |
+
-9.20491759319196
|
1988 |
+
],
|
1989 |
+
[
|
1990 |
+
"▁strong",
|
1991 |
+
-9.205733742263186
|
1992 |
+
],
|
1993 |
+
[
|
1994 |
+
"▁remember",
|
1995 |
+
-9.206030914810098
|
1996 |
+
],
|
1997 |
+
[
|
1998 |
+
"▁character",
|
1999 |
+
-9.20991178052067
|
2000 |
+
],
|
2001 |
+
[
|
2002 |
+
"▁picture",
|
2003 |
+
-9.223497104806157
|
2004 |
+
],
|
2005 |
+
[
|
2006 |
+
"▁wonder",
|
2007 |
+
-9.231224767871147
|
2008 |
+
],
|
2009 |
+
[
|
2010 |
+
"▁community",
|
2011 |
+
-9.241375579372438
|
2012 |
+
],
|
2013 |
+
[
|
2014 |
+
"▁perhaps",
|
2015 |
+
-9.253591058587716
|
2016 |
+
],
|
2017 |
+
[
|
2018 |
+
"▁economic",
|
2019 |
+
-9.254737082281682
|
2020 |
+
],
|
2021 |
+
[
|
2022 |
+
"▁global",
|
2023 |
+
-9.257818271485323
|
2024 |
+
],
|
2025 |
+
[
|
2026 |
+
"▁challenge",
|
2027 |
+
-9.258951607073556
|
2028 |
+
],
|
2029 |
+
[
|
2030 |
+
"▁individual",
|
2031 |
+
-9.297649240927925
|
2032 |
+
],
|
2033 |
+
[
|
2034 |
+
"▁suggest",
|
2035 |
+
-9.299664904893849
|
2036 |
+
],
|
2037 |
+
[
|
2038 |
+
"▁natural",
|
2039 |
+
-9.30603455476944
|
2040 |
+
],
|
2041 |
+
[
|
2042 |
+
"▁special",
|
2043 |
+
-9.344672135415555
|
2044 |
+
],
|
2045 |
+
[
|
2046 |
+
"▁difference",
|
2047 |
+
-9.372803643965124
|
2048 |
+
],
|
2049 |
+
[
|
2050 |
+
"▁especially",
|
2051 |
+
-9.410608286507564
|
2052 |
+
],
|
2053 |
+
[
|
2054 |
+
"▁tradition",
|
2055 |
+
-9.46199084516556
|
2056 |
+
],
|
2057 |
+
[
|
2058 |
+
"▁although",
|
2059 |
+
-9.471896386211808
|
2060 |
+
],
|
2061 |
+
[
|
2062 |
+
"▁economy",
|
2063 |
+
-9.487149405320343
|
2064 |
+
],
|
2065 |
+
[
|
2066 |
+
"▁potential",
|
2067 |
+
-9.5558471063055
|
2068 |
+
],
|
2069 |
+
[
|
2070 |
+
"▁opportunity",
|
2071 |
+
-9.567421441451728
|
2072 |
+
],
|
2073 |
+
[
|
2074 |
+
"▁university",
|
2075 |
+
-9.678153863522152
|
2076 |
+
],
|
2077 |
+
[
|
2078 |
+
"▁significant",
|
2079 |
+
-9.94182875191974
|
2080 |
+
],
|
2081 |
+
[
|
2082 |
+
"0",
|
2083 |
+
-13.077322941590932
|
2084 |
+
],
|
2085 |
+
[
|
2086 |
+
"1",
|
2087 |
+
-13.45284742159885
|
2088 |
+
],
|
2089 |
+
[
|
2090 |
+
"2",
|
2091 |
+
-13.656091927467775
|
2092 |
+
],
|
2093 |
+
[
|
2094 |
+
"9",
|
2095 |
+
-14.17117877050488
|
2096 |
+
],
|
2097 |
+
[
|
2098 |
+
"[",
|
2099 |
+
-14.347114963703774
|
2100 |
+
],
|
2101 |
+
[
|
2102 |
+
"]",
|
2103 |
+
-14.378726769576591
|
2104 |
+
],
|
2105 |
+
[
|
2106 |
+
"3",
|
2107 |
+
-14.45452055080778
|
2108 |
+
],
|
2109 |
+
[
|
2110 |
+
"5",
|
2111 |
+
-14.67569730318567
|
2112 |
+
],
|
2113 |
+
[
|
2114 |
+
"8",
|
2115 |
+
-14.707636103260414
|
2116 |
+
],
|
2117 |
+
[
|
2118 |
+
"4",
|
2119 |
+
-15.036026851076915
|
2120 |
+
],
|
2121 |
+
[
|
2122 |
+
"$",
|
2123 |
+
-15.036026851076915
|
2124 |
+
],
|
2125 |
+
[
|
2126 |
+
"6",
|
2127 |
+
-15.187832394806907
|
2128 |
+
],
|
2129 |
+
[
|
2130 |
+
"7",
|
2131 |
+
-15.187832394806907
|
2132 |
+
],
|
2133 |
+
[
|
2134 |
+
"&",
|
2135 |
+
-15.63514202146954
|
2136 |
+
],
|
2137 |
+
[
|
2138 |
+
"+",
|
2139 |
+
-17.41148545414651
|
2140 |
+
],
|
2141 |
+
[
|
2142 |
+
"=",
|
2143 |
+
-17.61208069224178
|
2144 |
+
],
|
2145 |
+
[
|
2146 |
+
"#",
|
2147 |
+
-17.863246193407697
|
2148 |
+
],
|
2149 |
+
[
|
2150 |
+
"%",
|
2151 |
+
-18.342214447428265
|
2152 |
+
],
|
2153 |
+
[
|
2154 |
+
"@",
|
2155 |
+
-18.95888111409493
|
2156 |
+
],
|
2157 |
+
[
|
2158 |
+
"^",
|
2159 |
+
-19.792214447428265
|
2160 |
+
],
|
2161 |
+
[
|
2162 |
+
"\\",
|
2163 |
+
-20.792214447428265
|
2164 |
+
],
|
2165 |
+
[
|
2166 |
+
"*",
|
2167 |
+
-20.792214447428265
|
2168 |
+
]
|
2169 |
+
]
|
2170 |
+
}
|
2171 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
9 |
+
"unk_token": "<unk>"
|
10 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cb8968574f90016df9beab62205eca5ff58a4ec6847ab13bca6f287aa860f7e
|
3 |
+
size 5112
|