wu981526092 commited on
Commit
0b8ae2a
1 Parent(s): b7d8888

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "n",
13
+ "1": "y"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "n": 0,
18
+ "y": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "pad_token_id": 0,
25
+ "problem_type": "single_label_classification",
26
+ "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.2,
28
+ "sinusoidal_pos_embds": false,
29
+ "tie_weights_": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.32.0",
32
+ "vocab_size": 30522
33
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2479079112bc710c2f582a54bff01dd4a97e6ec858011a04b7896de3ed6bd6de
3
+ size 535726853
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c297757ed61befded94f59b48488f14c2f861a6b1fd9c5ee8f6fb88ed84c8ea
3
+ size 267855533
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e201f84663455f750a9f923c1b5d0bf3e4f828eb14063fe9574d9845f6b848
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8e55b6480389487d996720fdc10d8c6ab15fa592abb6d05feecce9b0e194b3
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.647979736328125,
3
+ "best_model_checkpoint": "distilbert-base-uncased_cEXT_mypersonality/checkpoint-496",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 744,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.6038306451612904,
14
+ "eval_loss": 0.6622927188873291,
15
+ "eval_runtime": 3.8202,
16
+ "eval_samples_per_second": 519.349,
17
+ "eval_steps_per_second": 16.23,
18
+ "step": 248
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.6144153225806451,
23
+ "eval_loss": 0.647979736328125,
24
+ "eval_runtime": 3.8437,
25
+ "eval_samples_per_second": 516.174,
26
+ "eval_steps_per_second": 16.13,
27
+ "step": 496
28
+ },
29
+ {
30
+ "epoch": 2.02,
31
+ "learning_rate": 1.1935483870967743e-05,
32
+ "loss": 0.6625,
33
+ "step": 500
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_accuracy": 0.6038306451612904,
38
+ "eval_loss": 0.6553571820259094,
39
+ "eval_runtime": 3.8662,
40
+ "eval_samples_per_second": 513.169,
41
+ "eval_steps_per_second": 16.037,
42
+ "step": 744
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 1240,
47
+ "num_train_epochs": 5,
48
+ "save_steps": 500,
49
+ "total_flos": 485142443173500.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a92a2b69064c7bf06bd51fbf1269a69ef0e726d114516aa0568192536b2207e5
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff