usakha commited on
Commit
08f5adb
1 Parent(s): ef1810f

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/prophetnet-large-uncased",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_cross_attention": true,
6
+ "architectures": [
7
+ "ProphetNetForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 102,
11
+ "decoder_ffn_dim": 4096,
12
+ "decoder_layerdrop": 0.0,
13
+ "decoder_max_position_embeddings": 514,
14
+ "decoder_start_token_id": 102,
15
+ "disable_ngram_loss": false,
16
+ "dropout": 0.1,
17
+ "early_stopping": true,
18
+ "encoder_ffn_dim": 4096,
19
+ "encoder_layerdrop": 0.0,
20
+ "encoder_max_position_embeddings": 513,
21
+ "eos_token_id": 102,
22
+ "eps": 0.0,
23
+ "hidden_size": 1024,
24
+ "id2label": {
25
+ "0": "LABEL_0",
26
+ "1": "LABEL_1",
27
+ "2": "LABEL_2"
28
+ },
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1,
34
+ "LABEL_2": 2
35
+ },
36
+ "length_penalty": 2.0,
37
+ "max_length": 142,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "prophetnet",
40
+ "ngram": 2,
41
+ "no_repeat_ngram_size": 3,
42
+ "num_beams": 4,
43
+ "num_buckets": 32,
44
+ "num_decoder_attention_heads": 16,
45
+ "num_decoder_layers": 12,
46
+ "num_encoder_attention_heads": 16,
47
+ "num_encoder_layers": 12,
48
+ "output_past": false,
49
+ "pad_token_id": 0,
50
+ "prefix": " ",
51
+ "relative_max_distance": 128,
52
+ "task_specific_params": {
53
+ "summarization": {
54
+ "early_stopping": true,
55
+ "length_penalty": 2.0,
56
+ "no_repeat_ngram_size": 3,
57
+ "num_beams": 4
58
+ }
59
+ },
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.31.0.dev0",
62
+ "use_cache": true,
63
+ "vocab_size": 30522
64
+ }
prophetnet.tokenizer 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 sha256:02c4e7cb170abd311e2c29a552306de135e758fc7f68c69ab6dcb8d97cea81f0
3
+ size 1565474989
runs/Jun26_17-21-06_6ec4302fc76d/events.out.tfevents.1687800074.6ec4302fc76d.19521.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09e820d4727214e3f56ce4efedab4340a987e5bf0f93e02d1afdaa776ac4229
3
+ size 5269
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "[PAD]",
4
+ "sep_token": "[SEP]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "ProphetNetTokenizer",
13
+ "unk_token": "[UNK]",
14
+ "x_sep_token": "[X_SEP]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311ed643c23c09cd295b2d780c56b421f48f7879ffc5670ff2f370b209c4b8a7
3
+ size 4155