sackel commited on
Commit
d99af64
1 Parent(s): e5ff40b

Qna First commit

Browse files
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForQuestionAnswering"
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
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.22.2",
23
+ "vocab_size": 30522
24
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba5a58fce8b98f508392fa297fc13ea7fe61ca13aaaffc197227ffe8ac3cd290
3
+ size 530974121
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f248cee4868379a386a23a1fc9364cb0173a2537af26646543eca2b6e112968c
3
+ size 265491317
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a41e665458f179be422920f1f8b88383451e48a92c15aaf2b60b7d2f147face
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a0e0f6ba69eae521e6753c4adb0bb2c9333d8e467287f60f6f4b393d188a6e
3
+ size 623
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "distilbert-base-uncased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "DistilBertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9940357852882704,
5
+ "global_step": 5500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 1.819266220856678e-05,
13
+ "loss": 3.0844,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 1.6385324417133565e-05,
19
+ "loss": 1.8306,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.27,
24
+ "learning_rate": 1.4577986625700345e-05,
25
+ "loss": 1.6551,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.36,
30
+ "learning_rate": 1.2770648834267125e-05,
31
+ "loss": 1.5101,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.45,
36
+ "learning_rate": 1.0963311042833906e-05,
37
+ "loss": 1.4381,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.54,
42
+ "learning_rate": 9.155973251400688e-06,
43
+ "loss": 1.3683,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.63,
48
+ "learning_rate": 7.348635459967468e-06,
49
+ "loss": 1.2983,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.72,
54
+ "learning_rate": 5.541297668534249e-06,
55
+ "loss": 1.3465,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.81,
60
+ "learning_rate": 3.7339598771010305e-06,
61
+ "loss": 1.3036,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.9,
66
+ "learning_rate": 1.9266220856678112e-06,
67
+ "loss": 1.2562,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.99,
72
+ "learning_rate": 1.1928429423459245e-07,
73
+ "loss": 1.2602,
74
+ "step": 5500
75
+ }
76
+ ],
77
+ "max_steps": 5533,
78
+ "num_train_epochs": 1,
79
+ "total_flos": 8623104602112000.0,
80
+ "trial_name": null,
81
+ "trial_params": null
82
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a23b901c523ac1ed9cf37e35d74292a94f945c1b8a9e094f5f4561b0625e0d
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff