mabornea commited on
Commit
bd3b739
1 Parent(s): 17af0e1

Upload 9 files

Browse files

The model files.

config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartFiDModelForDownstreamTasks"
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
+ "decoding_times_with_dropout": 5,
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_bos_token_id": 0,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_position_embeddings": 1024,
44
+ "model_type": "bart",
45
+ "no_repeat_ngram_size": 3,
46
+ "normalize_before": false,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 12,
49
+ "output_dropout_rate": 0.25,
50
+ "pad_token_id": 1,
51
+ "scale_embedding": false,
52
+ "sep_token_id": 2,
53
+ "task_specific_params": {
54
+ "summarization": {
55
+ "length_penalty": 1.0,
56
+ "max_length": 128,
57
+ "min_length": 12,
58
+ "num_beams": 4
59
+ },
60
+ "summarization_cnn": {
61
+ "length_penalty": 2.0,
62
+ "max_length": 142,
63
+ "min_length": 56,
64
+ "num_beams": 4
65
+ },
66
+ "summarization_xsum": {
67
+ "length_penalty": 1.0,
68
+ "max_length": 62,
69
+ "min_length": 11,
70
+ "num_beams": 6
71
+ }
72
+ },
73
+ "torch_dtype": "float32",
74
+ "transformers_version": "4.17.0",
75
+ "use_cache": true,
76
+ "vocab_size": 50265
77
+ }
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 sha256:8b71886f1da12e87e403cba426710b69ca12040474350ab5740d6ea8a23579d7
3
+ size 1625558785
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}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large", "tokenizer_class": "BartTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 3.0558416822739383,
4
+ "train_runtime": 31869.4497,
5
+ "train_samples": 526459,
6
+ "train_samples_per_second": 49.558,
7
+ "train_steps_per_second": 1.549
8
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b76aa1a6e7d69521e70fab8534a1a758c597af740f193d3d1d471b53520127
3
+ size 3247
vocab.json ADDED
The diff for this file is too large to render. See raw diff