dassum commited on
Commit
516d424
1 Parent(s): b3ceea2

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlnet-base-cased",
3
+ "architectures": [
4
+ "XLNetForSequenceClassification"
5
+ ],
6
+ "attn_type": "bi",
7
+ "bi_data": false,
8
+ "bos_token_id": 1,
9
+ "clamp_len": -1,
10
+ "d_head": 64,
11
+ "d_inner": 3072,
12
+ "d_model": 768,
13
+ "dropout": 0.1,
14
+ "end_n_top": 5,
15
+ "eos_token_id": 2,
16
+ "ff_activation": "gelu",
17
+ "id2label": {
18
+ "0": "fantasy",
19
+ "1": "horror",
20
+ "2": "family",
21
+ "3": "scifi",
22
+ "4": "action",
23
+ "5": "crime",
24
+ "6": "adventure",
25
+ "7": "mystery",
26
+ "8": "romance",
27
+ "9": "thriller"
28
+ },
29
+ "initializer_range": 0.02,
30
+ "label2id": {
31
+ "action": 4,
32
+ "adventure": 6,
33
+ "crime": 5,
34
+ "family": 2,
35
+ "fantasy": 0,
36
+ "horror": 1,
37
+ "mystery": 7,
38
+ "romance": 8,
39
+ "scifi": 3,
40
+ "thriller": 9
41
+ },
42
+ "layer_norm_eps": 1e-12,
43
+ "mem_len": null,
44
+ "model_type": "xlnet",
45
+ "n_head": 12,
46
+ "n_layer": 12,
47
+ "pad_token_id": 5,
48
+ "problem_type": "single_label_classification",
49
+ "reuse_len": null,
50
+ "same_length": false,
51
+ "start_n_top": 5,
52
+ "summary_activation": "tanh",
53
+ "summary_last_dropout": 0.1,
54
+ "summary_type": "last",
55
+ "summary_use_proj": true,
56
+ "task_specific_params": {
57
+ "text-generation": {
58
+ "do_sample": true,
59
+ "max_length": 250
60
+ }
61
+ },
62
+ "torch_dtype": "float32",
63
+ "transformers_version": "4.31.0",
64
+ "untie_r": true,
65
+ "use_mems_eval": true,
66
+ "use_mems_train": false,
67
+ "vocab_size": 32000
68
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6145bab1299cd7abb9b2101d16eee2b48d56fcc2a5139773f846313a24deeb26
3
+ size 469336341
runs/Jul29_06-28-18_2d2a427bc447/events.out.tfevents.1690612113.2d2a427bc447.5283.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58cf4a76e6a7a48b8b83834af502e0afd65ced3fa77aead19f803ecb4c2bc078
3
+ size 5398
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<cls>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "<sep>",
18
+ "unk_token": "<unk>"
19
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
3
+ size 798011
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "clean_up_tokenization_spaces": true,
8
+ "cls_token": "<cls>",
9
+ "do_lower_case": false,
10
+ "eos_token": "</s>",
11
+ "keep_accents": false,
12
+ "mask_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<mask>",
15
+ "lstrip": true,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": "<pad>",
22
+ "remove_space": true,
23
+ "sep_token": "<sep>",
24
+ "tokenizer_class": "XLNetTokenizer",
25
+ "unk_token": "<unk>"
26
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f89e3f975d4032d6196361ead1def20b52cab47df6653eb946274da4e13da65f
3
+ size 4027