sheoran95 commited on
Commit
448a6bb
1 Parent(s): d0287f0

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ ":ARG0": 50265,
3
+ ":ARG1": 50266,
4
+ ":ARG2": 50267,
5
+ ":ARG3": 50268,
6
+ ":ARG4": 50269,
7
+ ":ARG5": 50270,
8
+ ":ARGM-CAU": 50275,
9
+ ":ARGM-DIR": 50276,
10
+ ":ARGM-EXT": 50277,
11
+ ":ARGM-LOC": 50271,
12
+ ":ARGM-MNR": 50273,
13
+ ":ARGM-NEG": 50278,
14
+ ":ARGM-PRP": 50274,
15
+ ":ARGM-TMP": 50272,
16
+ ":graph0": 50279,
17
+ ":graph1": 50280,
18
+ ":graph10": 50289,
19
+ ":graph11": 50290,
20
+ ":graph12": 50291,
21
+ ":graph13": 50292,
22
+ ":graph14": 50293,
23
+ ":graph15": 50294,
24
+ ":graph2": 50281,
25
+ ":graph3": 50282,
26
+ ":graph4": 50283,
27
+ ":graph5": 50284,
28
+ ":graph6": 50285,
29
+ ":graph7": 50286,
30
+ ":graph8": 50287,
31
+ ":graph9": 50288
32
+ }
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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_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
+ "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": "4.28.1",
72
+ "use_cache": true,
73
+ "vocab_size": 50295
74
+ }
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:dd1867405d6e2cb9fdb277e4a0458a0f777294aeb82754bfc002124329901007
3
+ size 1625664397
runs/Apr28_06-59-45_91ae283df3bd/1682665191.9133222/events.out.tfevents.1682665191.91ae283df3bd.1643.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae939b9dd31bdb7e71aaf56a4d44c9c08b4524406b4764c62fc7ef729833d98
3
+ size 6323
runs/Apr28_06-59-45_91ae283df3bd/events.out.tfevents.1682665191.91ae283df3bd.1643.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9b13de43ed0d02b83292ab2e1a7d7bf2fab7a9f339e38c867d64b68ecd3c66
3
+ size 5952
special_tokens_map.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ":ARG0",
4
+ ":ARG1",
5
+ ":ARG2",
6
+ ":ARG3",
7
+ ":ARG4",
8
+ ":ARG5",
9
+ ":ARGM-LOC",
10
+ ":ARGM-TMP",
11
+ ":ARGM-MNR",
12
+ ":ARGM-PRP",
13
+ ":ARGM-CAU",
14
+ ":ARGM-DIR",
15
+ ":ARGM-EXT",
16
+ ":ARGM-NEG",
17
+ ":graph0",
18
+ ":graph1",
19
+ ":graph2",
20
+ ":graph3",
21
+ ":graph4",
22
+ ":graph5",
23
+ ":graph6",
24
+ ":graph7",
25
+ ":graph8",
26
+ ":graph9",
27
+ ":graph10",
28
+ ":graph11",
29
+ ":graph12",
30
+ ":graph13",
31
+ ":graph14",
32
+ ":graph15"
33
+ ],
34
+ "bos_token": "<s>",
35
+ "cls_token": "<s>",
36
+ "eos_token": "</s>",
37
+ "mask_token": {
38
+ "content": "<mask>",
39
+ "lstrip": true,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "pad_token": "<pad>",
45
+ "sep_token": "</s>",
46
+ "unk_token": "<unk>"
47
+ }
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 sha256:54fe547bea9d6c03c5c051e05f260a092669c4bd1d7e1fc5149b1b00a13a55a6
3
+ size 3835
vocab.json ADDED
The diff for this file is too large to render. See raw diff