asahi417 commited on
Commit
e46f785
1 Parent(s): 570f968
Files changed (2) hide show
  1. config.json +74 -1
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1 +1,74 @@
1
- {"_name_or_path": "lmqg_output/optimized/bart_large_squad/model_byrqch/epoch_2", "activation_dropout": 0.1, "activation_function": "gelu", "add_bias_logits": false, "add_final_layer_norm": false, "architectures": ["BartForConditionalGeneration"], "attention_dropout": 0.1, "bos_token_id": 0, "classif_dropout": 0.1, "classifier_dropout": 0.0, "d_model": 1024, "decoder_attention_heads": 16, "decoder_ffn_dim": 4096, "decoder_layerdrop": 0.0, "decoder_layers": 12, "decoder_start_token_id": 2, "dropout": 0.1, "early_stopping": true, "encoder_attention_heads": 16, "encoder_ffn_dim": 4096, "encoder_layerdrop": 0.0, "encoder_layers": 12, "eos_token_id": 2, "forced_eos_token_id": 2, "gradient_checkpointing": false, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "init_std": 0.02, "is_encoder_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "max_position_embeddings": 1024, "model_type": "bart", "no_repeat_ngram_size": 3, "normalize_before": false, "num_beams": 4, "num_hidden_layers": 12, "pad_token_id": 1, "scale_embedding": false, "task_specific_params": {"summarization": {"length_penalty": 1.0, "max_length": 128, "min_length": 12, "num_beams": 4}, "summarization_cnn": {"length_penalty": 2.0, "max_length": 142, "min_length": 56, "num_beams": 4}, "summarization_xsum": {"length_penalty": 1.0, "max_length": 62, "min_length": 11, "num_beams": 6}}, "transformers_version": "4.8.2", "use_cache": true, "vocab_size": 50266, "add_prefix": false}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bart-large-squad",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "add_prefix": false,
8
+ "architectures": [
9
+ "BartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.1,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 12,
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
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.21.2",
72
+ "use_cache": true,
73
+ "vocab_size": 50266
74
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8029322e267b1d4436eeb7d3ca55b703cd37520a55d8551e2bf4c5387c74188d
3
- size 1625561409
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7459c35f63c5c6f2f8fa1dc68fe5e67388451f9dd786cb1656f950ffc81373e8
3
+ size 1625538317