ArisuNguyen commited on
Commit
dbd8d12
1 Parent(s): 4459315

Training in progress, epoch 0

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "BartForQuestionAnswering"
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_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1
39
+ },
40
+ "max_position_embeddings": 1024,
41
+ "model_type": "bart",
42
+ "no_repeat_ngram_size": 3,
43
+ "normalize_before": false,
44
+ "num_beams": 4,
45
+ "num_hidden_layers": 12,
46
+ "pad_token_id": 1,
47
+ "scale_embedding": false,
48
+ "task_specific_params": {
49
+ "summarization": {
50
+ "length_penalty": 1.0,
51
+ "max_length": 128,
52
+ "min_length": 12,
53
+ "num_beams": 4
54
+ },
55
+ "summarization_cnn": {
56
+ "length_penalty": 2.0,
57
+ "max_length": 142,
58
+ "min_length": 56,
59
+ "num_beams": 4
60
+ },
61
+ "summarization_xsum": {
62
+ "length_penalty": 1.0,
63
+ "max_length": 62,
64
+ "min_length": 11,
65
+ "num_beams": 6
66
+ }
67
+ },
68
+ "torch_dtype": "float32",
69
+ "transformers_version": "4.28.1",
70
+ "use_cache": true,
71
+ "vocab_size": 50265
72
+ }
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:ef8b812721cbf958f5649caab9e31a6141468fe3df702e8c6f074fba8dfb2a7f
3
+ size 1625348817
runs/Apr20_06-08-22_81eed4ae6c1f/1681970909.8822742/events.out.tfevents.1681970909.81eed4ae6c1f.952.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ee808d95fa9b52fa96dea6058a9ddb79dd6835b8e1a23fe7185e777e4c4b0f
3
+ size 5871
runs/Apr20_06-08-22_81eed4ae6c1f/events.out.tfevents.1681970909.81eed4ae6c1f.952.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd54e0878f225a51b55c14baa925efb1a220813c99f38763309e61ba8de79d1
3
+ size 5356
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 1024,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "BartTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7b51714679ad602618e548515141f7cd448dd6a5e2ce099cd8e234a67170a5
3
+ size 3579
vocab.json ADDED
The diff for this file is too large to render. See raw diff