nickmuchi commited on
Commit
c5e334d
1 Parent(s): 1ccb476

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "action",
15
+ "1": "adventure",
16
+ "2": "crime",
17
+ "3": "family",
18
+ "4": "fantasy",
19
+ "5": "horror",
20
+ "6": "mystery",
21
+ "7": "romance",
22
+ "8": "scifi",
23
+ "9": "thriller"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 4096,
27
+ "label2id": {
28
+ "action": 0,
29
+ "adventure": 1,
30
+ "crime": 2,
31
+ "family": 3,
32
+ "fantasy": 4,
33
+ "horror": 5,
34
+ "mystery": 6,
35
+ "romance": 7,
36
+ "scifi": 8,
37
+ "thriller": 9
38
+ },
39
+ "layer_norm_eps": 1e-05,
40
+ "max_position_embeddings": 514,
41
+ "model_type": "roberta",
42
+ "num_attention_heads": 16,
43
+ "num_hidden_layers": 24,
44
+ "pad_token_id": 1,
45
+ "position_embedding_type": "absolute",
46
+ "problem_type": "single_label_classification",
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.30.2",
49
+ "type_vocab_size": 1,
50
+ "use_cache": true,
51
+ "vocab_size": 50265
52
+ }
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:f8ecf8a5e5167ecc453fe12fb60781a59481ed23487299915cf7d7e250d33627
3
+ size 1421619957
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": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
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 sha256:7247b24cc04f871640376edce8206d252a9d1a3484209474db7b4c71fc239436
3
+ size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff