lingxf1131 commited on
Commit
28e0abb
1 Parent(s): 37c0381

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": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 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 sha256:04eca5ef0706e474820c9d9e1dc0b620005df4cdb1b80728b803aca0337881a3
3
+ size 535726853
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9265c2760013fe193f7358f11c7a63920bc75a2259842869e404a490bb217eda
3
+ size 267855533
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da20a5aa3a29e74e049b9d2fbf5d37d371bd1fe3b11b6b6f5d9fbd70c24b692
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6891b8b4168c9b8d3f4e182e380d5c97884bba5afb92e70c7dd044dd0616bcd
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 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.23137560486793518,
3
+ "best_model_checkpoint": "my_awesome_model\\checkpoint-3126",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3126,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.32,
13
+ "learning_rate": 1.6801023672424827e-05,
14
+ "loss": 0.3295,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.64,
19
+ "learning_rate": 1.3602047344849649e-05,
20
+ "loss": 0.2497,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.96,
25
+ "learning_rate": 1.0403071017274472e-05,
26
+ "loss": 0.2238,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 1.0,
31
+ "eval_accuracy": 0.91268,
32
+ "eval_loss": 0.24340802431106567,
33
+ "eval_runtime": 106.2572,
34
+ "eval_samples_per_second": 235.278,
35
+ "eval_steps_per_second": 14.71,
36
+ "step": 1563
37
+ },
38
+ {
39
+ "epoch": 1.28,
40
+ "learning_rate": 7.204094689699297e-06,
41
+ "loss": 0.1606,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 1.6,
46
+ "learning_rate": 4.005118362124121e-06,
47
+ "loss": 0.1459,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.92,
52
+ "learning_rate": 8.061420345489445e-07,
53
+ "loss": 0.1564,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 2.0,
58
+ "eval_accuracy": 0.93228,
59
+ "eval_loss": 0.23137560486793518,
60
+ "eval_runtime": 101.0576,
61
+ "eval_samples_per_second": 247.384,
62
+ "eval_steps_per_second": 15.466,
63
+ "step": 3126
64
+ }
65
+ ],
66
+ "logging_steps": 500,
67
+ "max_steps": 3126,
68
+ "num_train_epochs": 2,
69
+ "save_steps": 500,
70
+ "total_flos": 6564686875195392.0,
71
+ "trial_name": null,
72
+ "trial_params": null
73
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:914918262f739fc21acd394420a42c753563c03a427ccaad8a20b55bf76941b6
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff