Svetlana0303 commited on
Commit
7a2954f
1 Parent(s): e4eaddc

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "LABEL_0"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "label2id": {
22
+ "LABEL_0": 0
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "mem_len": null,
26
+ "model_type": "xlnet",
27
+ "n_head": 12,
28
+ "n_layer": 12,
29
+ "pad_token_id": 5,
30
+ "reuse_len": null,
31
+ "same_length": false,
32
+ "start_n_top": 5,
33
+ "summary_activation": "tanh",
34
+ "summary_last_dropout": 0.1,
35
+ "summary_type": "last",
36
+ "summary_use_proj": true,
37
+ "task_specific_params": {
38
+ "text-generation": {
39
+ "do_sample": true,
40
+ "max_length": 250
41
+ }
42
+ },
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.27.4",
45
+ "untie_r": true,
46
+ "use_mems_eval": true,
47
+ "use_mems_train": false,
48
+ "vocab_size": 32000
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa6e5b1fd7b97747f65c9dcc5b18c519f31150928154b2af24416de50aa005f
3
+ size 469308693
runs/Apr11_06-05-30_cb3b97645533/1681193151.1240287/events.out.tfevents.1681193151.cb3b97645533.161.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5029e00a68595f4c51e4ea3ba19fc1d1954b61b5ec59c49035c408531e98a11
3
+ size 5831
runs/Apr11_06-05-30_cb3b97645533/events.out.tfevents.1681193151.cb3b97645533.161.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88691400be39fa9d0ed707fac0b855ae20619c5b46b30e9420c3724835b8db4c
3
+ size 5069
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
+ "cls_token": "<cls>",
8
+ "do_lower_case": false,
9
+ "eos_token": "</s>",
10
+ "keep_accents": false,
11
+ "mask_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<mask>",
14
+ "lstrip": true,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "model_max_length": 1000000000000000019884624838656,
20
+ "pad_token": "<pad>",
21
+ "remove_space": true,
22
+ "sep_token": "<sep>",
23
+ "special_tokens_map_file": null,
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 sha256:658544bd9ad487f65b252c8017cd85d75e5cbdc6d646a5ad923236be5e4c8e44
3
+ size 3579