model update
Browse files- added_tokens.json +1 -0
- config.json +73 -0
- eval/metric.first.answer.json +1 -0
- eval/metric.first.sentence.json +1 -0
- eval/samples.dev.hyp.txt +0 -0
- eval/samples.test.hyp.txt +0 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<hl>": 50265}
|
config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "lmqg_output/optimized_no_answer/bart_base_squad/model_chjgyo/epoch_2",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"forced_eos_token_id": 2,
|
28 |
+
"gradient_checkpointing": false,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_position_embeddings": 1024,
|
42 |
+
"model_type": "bart",
|
43 |
+
"no_repeat_ngram_size": 3,
|
44 |
+
"normalize_before": false,
|
45 |
+
"normalize_embedding": true,
|
46 |
+
"num_beams": 4,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 1,
|
49 |
+
"scale_embedding": false,
|
50 |
+
"task_specific_params": {
|
51 |
+
"summarization": {
|
52 |
+
"length_penalty": 1.0,
|
53 |
+
"max_length": 128,
|
54 |
+
"min_length": 12,
|
55 |
+
"num_beams": 4
|
56 |
+
},
|
57 |
+
"summarization_cnn": {
|
58 |
+
"length_penalty": 2.0,
|
59 |
+
"max_length": 142,
|
60 |
+
"min_length": 56,
|
61 |
+
"num_beams": 4
|
62 |
+
},
|
63 |
+
"summarization_xsum": {
|
64 |
+
"length_penalty": 1.0,
|
65 |
+
"max_length": 62,
|
66 |
+
"min_length": 11,
|
67 |
+
"num_beams": 6
|
68 |
+
}
|
69 |
+
},
|
70 |
+
"transformers_version": "4.8.2",
|
71 |
+
"use_cache": true,
|
72 |
+
"vocab_size": 50266
|
73 |
+
}
|
eval/metric.first.answer.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"dev": {"Bleu_1": 0.46955432990552126, "Bleu_2": 0.32483496437351833, "Bleu_3": 0.2467106027090486, "Bleu_4": 0.19442422962027203, "METEOR": 0.22394166689789516, "ROUGE_L": 0.4731500565165573}, "test": {"Bleu_1": 0.4465112464118293, "Bleu_2": 0.301283476122586, "Bleu_3": 0.22393199100774094, "Bleu_4": 0.17207751354682618, "METEOR": 0.21526782645073061, "ROUGE_L": 0.4570271246101089}}
|
eval/metric.first.sentence.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"dev": {"Bleu_1": 0.5247222015368843, "Bleu_2": 0.37314134136078203, "Bleu_3": 0.2883222891032023, "Bleu_4": 0.22989282717530174, "METEOR": 0.24116195563199724, "ROUGE_L": 0.5015342399331303}, "test": {"Bleu_1": 0.5241678282777086, "Bleu_2": 0.3680650325404349, "Bleu_3": 0.279111469043949, "Bleu_4": 0.21730306951662412, "METEOR": 0.23715466422245665, "ROUGE_L": 0.4956716531845775}}
|
eval/samples.dev.hyp.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
eval/samples.test.hyp.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24f35f82c8389ead1dd6831d3f0825b6b0bd2b18371103e5cfa5ca475f1e4853
|
3 |
+
size 557982265
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<hl>"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "name_or_path": "lmqg_output/optimized_no_answer/bart_base_squad/model_chjgyo/epoch_2", "special_tokens_map_file": "lmqg_output/optimized_no_answer/bart_base_squad/model_chjgyo/epoch_2/special_tokens_map.json", "tokenizer_class": "BartTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|