model update
Browse files- config.json +1 -72
config.json
CHANGED
@@ -1,72 +1 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "lmqg_output/optimized/bart_large_squad/model_byrqch/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": 1024,
|
15 |
-
"decoder_attention_heads": 16,
|
16 |
-
"decoder_ffn_dim": 4096,
|
17 |
-
"decoder_layerdrop": 0.0,
|
18 |
-
"decoder_layers": 12,
|
19 |
-
"decoder_start_token_id": 2,
|
20 |
-
"dropout": 0.1,
|
21 |
-
"early_stopping": true,
|
22 |
-
"encoder_attention_heads": 16,
|
23 |
-
"encoder_ffn_dim": 4096,
|
24 |
-
"encoder_layerdrop": 0.0,
|
25 |
-
"encoder_layers": 12,
|
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 |
-
"num_beams": 4,
|
46 |
-
"num_hidden_layers": 12,
|
47 |
-
"pad_token_id": 1,
|
48 |
-
"scale_embedding": false,
|
49 |
-
"task_specific_params": {
|
50 |
-
"summarization": {
|
51 |
-
"length_penalty": 1.0,
|
52 |
-
"max_length": 128,
|
53 |
-
"min_length": 12,
|
54 |
-
"num_beams": 4
|
55 |
-
},
|
56 |
-
"summarization_cnn": {
|
57 |
-
"length_penalty": 2.0,
|
58 |
-
"max_length": 142,
|
59 |
-
"min_length": 56,
|
60 |
-
"num_beams": 4
|
61 |
-
},
|
62 |
-
"summarization_xsum": {
|
63 |
-
"length_penalty": 1.0,
|
64 |
-
"max_length": 62,
|
65 |
-
"min_length": 11,
|
66 |
-
"num_beams": 6
|
67 |
-
}
|
68 |
-
},
|
69 |
-
"transformers_version": "4.8.2",
|
70 |
-
"use_cache": true,
|
71 |
-
"vocab_size": 50266
|
72 |
-
}
|
|
|
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}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|