wu981526092 commited on
Commit
8742efc
1 Parent(s): 9a394d4

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:e5ad742bb72ddda315005ad2c01e051cb10b93247ef58d1ffbd2cc465fc9f6db
3
+ size 535726853
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67fbd18af5c71502fd2d2b7253e413f5ec037860afffcbf180491865d289a18c
3
+ size 267855533
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c84f8971fda27c9f2ec50b1f6ff0f2fe1b59f95f92d0b31d1c6ec6fdf03c2485
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4dd4d46a389fa6939b1f25e7d7b9c8c5cf13735a2290d81be0c8798ff1d93e
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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5306877493858337,
3
+ "best_model_checkpoint": "distilbert-base-uncased_cOPN_mypersonality/checkpoint-496",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 992,
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": 0.7368951612903226,
14
+ "eval_loss": 0.5459449887275696,
15
+ "eval_runtime": 3.9875,
16
+ "eval_samples_per_second": 497.556,
17
+ "eval_steps_per_second": 15.549,
18
+ "step": 248
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.7444556451612904,
23
+ "eval_loss": 0.5306877493858337,
24
+ "eval_runtime": 4.0234,
25
+ "eval_samples_per_second": 493.117,
26
+ "eval_steps_per_second": 15.41,
27
+ "step": 496
28
+ },
29
+ {
30
+ "epoch": 2.02,
31
+ "learning_rate": 1.1935483870967743e-05,
32
+ "loss": 0.5329,
33
+ "step": 500
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_accuracy": 0.751008064516129,
38
+ "eval_loss": 0.5426453351974487,
39
+ "eval_runtime": 4.0301,
40
+ "eval_samples_per_second": 492.3,
41
+ "eval_steps_per_second": 15.384,
42
+ "step": 744
43
+ },
44
+ {
45
+ "epoch": 4.0,
46
+ "eval_accuracy": 0.7479838709677419,
47
+ "eval_loss": 0.5962972044944763,
48
+ "eval_runtime": 4.0093,
49
+ "eval_samples_per_second": 494.845,
50
+ "eval_steps_per_second": 15.464,
51
+ "step": 992
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 1240,
56
+ "num_train_epochs": 5,
57
+ "save_steps": 500,
58
+ "total_flos": 640810523547624.0,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b643cb57876748cebb95b281f8e8780d0ff6ff8790d502e7fcb6dd1967af28
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff