Trong-Nghia commited on
Commit
789f655
1 Parent(s): 68fafed

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlnet-large-cased",
3
+ "architectures": [
4
+ "XLNetForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attn_type": "bi",
8
+ "bi_data": false,
9
+ "bos_token_id": 1,
10
+ "clamp_len": -1,
11
+ "classifier_dropout": 0.1,
12
+ "d_head": 64,
13
+ "d_inner": 4096,
14
+ "d_model": 1024,
15
+ "dropout": 0.1,
16
+ "end_n_top": 5,
17
+ "eos_token_id": 2,
18
+ "ff_activation": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "initializer_range": 0.02,
21
+ "layer_norm_eps": 1e-12,
22
+ "mem_len": null,
23
+ "model_type": "xlnet",
24
+ "n_head": 16,
25
+ "n_layer": 24,
26
+ "pad_token_id": 5,
27
+ "problem_type": "single_label_classification",
28
+ "reuse_len": null,
29
+ "same_length": false,
30
+ "start_n_top": 5,
31
+ "summary_activation": "tanh",
32
+ "summary_last_dropout": 0.1,
33
+ "summary_type": "last",
34
+ "summary_use_proj": true,
35
+ "task_specific_params": {
36
+ "text-generation": {
37
+ "do_sample": true,
38
+ "max_length": 250
39
+ }
40
+ },
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.31.0",
43
+ "untie_r": true,
44
+ "use_mems_eval": true,
45
+ "use_mems_train": false,
46
+ "vocab_size": 32000
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a7dc6174b491f54d713143478cbc51210dffae957c43561bd730378851f0f4
3
+ size 1445420229
runs/Jul20_07-34-27_6276b0746e6e/events.out.tfevents.1689838501.6276b0746e6e.3918.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:832e32699e8dcf18c5d8a7418548ff18094d1d055784760c307574d518053bce
3
+ size 4666
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
+ }
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:de5faf30d71ef8b81cf18c4e54eb759d29609716747530c93ace96fc2c023a0a
3
+ size 4027