mskov commited on
Commit
2007ac7
·
1 Parent(s): 17a025b

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.30.2",
24
+ "vocab_size": 30522
25
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d0b399daf293df8cf5bd15d9a0e45441f11e16010c82c0f747d1ffb4c5f237f
3
+ size 535701061
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acbd06422b4bd3267e9ad82540cea4a01bd315bf11df1f976a87cbd6b4f6a1f8
3
+ size 267855533
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c8eeeb6e2bf404f5ed571226697d476883b67047a9ed02f4a1aae12a2346a02
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f0a8742e92408542706f24b1a568e15bed8f8d626e4fe3668408b0bd598dc73
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": false,
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 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.459016393442623,
5
+ "global_step": 4500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.27,
12
+ "learning_rate": 1.8907103825136616e-05,
13
+ "loss": 0.4115,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.55,
18
+ "learning_rate": 1.7814207650273227e-05,
19
+ "loss": 0.3067,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.82,
24
+ "learning_rate": 1.6721311475409837e-05,
25
+ "loss": 0.2982,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.09,
30
+ "learning_rate": 1.5628415300546448e-05,
31
+ "loss": 0.2788,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.37,
36
+ "learning_rate": 1.4535519125683062e-05,
37
+ "loss": 0.2543,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 1.64,
42
+ "learning_rate": 1.3442622950819673e-05,
43
+ "loss": 0.254,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 1.91,
48
+ "learning_rate": 1.2349726775956286e-05,
49
+ "loss": 0.253,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 2.19,
54
+ "learning_rate": 1.1256830601092897e-05,
55
+ "loss": 0.214,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 2.46,
60
+ "learning_rate": 1.0163934426229509e-05,
61
+ "loss": 0.2061,
62
+ "step": 4500
63
+ }
64
+ ],
65
+ "max_steps": 9150,
66
+ "num_train_epochs": 5,
67
+ "total_flos": 9536063094448128.0,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a7b495045ce76fca9ba5f65945a89b1b50a33cb5b9bef17ea8952618fe0abaf
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff