Hugging Face's logo

hodeld
/
Anti-Vax-Misinfo-Detector

PyTorch
TensorBoard
English
distilbert
Model card Files Metrics Community
hodeld commited on
Commit
df3bdd6
·
verified ·
1 Parent(s): 4f83f63

Upload 28 model files

Browse files
Files changed (28) hide show
  1. checkpoint-2000/config.json +33 -0
  2. checkpoint-2000/pytorch_model.bin +3 -0
  3. checkpoint-2000/rng_state.pth +3 -0
  4. checkpoint-2000/scheduler.pt +3 -0
  5. checkpoint-2000/special_tokens_map.json +7 -0
  6. checkpoint-2000/tokenizer.json +0 -0
  7. checkpoint-2000/tokenizer_config.json +13 -0
  8. checkpoint-2000/trainer_state.json +76 -0
  9. checkpoint-2000/training_args.bin +3 -0
  10. checkpoint-2000/vocab.txt +0 -0
  11. checkpoint-500/config.json +33 -0
  12. checkpoint-500/rng_state.pth +3 -0
  13. checkpoint-500/scheduler.pt +3 -0
  14. checkpoint-500/special_tokens_map.json +7 -0
  15. checkpoint-500/tokenizer.json +0 -0
  16. checkpoint-500/tokenizer_config.json +13 -0
  17. checkpoint-500/trainer_state.json +31 -0
  18. checkpoint-500/training_args.bin +3 -0
  19. checkpoint-500/vocab.txt +0 -0
  20. config.json +33 -0
  21. pytorch_model.bin +3 -0
  22. runs/May23_00-41-03_4bf3b595ef41/1684802464.150275/events.out.tfevents.1684802464.4bf3b595ef41.238.1 +3 -0
  23. runs/May23_00-41-03_4bf3b595ef41/events.out.tfevents.1684802464.4bf3b595ef41.238.0 +3 -0
  24. special_tokens_map.json +7 -0
  25. tokenizer.json +0 -0
  26. tokenizer_config.json +13 -0
  27. training_args.bin +3 -0
  28. vocab.txt +0 -0
checkpoint-2000/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": "no_misinfo",
13
+ "1": "is_misinfo"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "is_misinfo": 1,
18
+ "no_misinfo": 0
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": "4.28.0",
32
+ "vocab_size": 30522
33
+ }
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39ffa4a4f120aeb96540451385c7471ebb78e04a955a2a026c9976f36104dbb2
3
+ size 267854125
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4fe9dbbd2055a2522a5acf65f6a67572e1a7c6c76be223a3634cfc277e4128a
3
+ size 13553
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9282a8ef7bc9b1564c90002f4e40a8dd310a4981144e054507ebef7c341e579
3
+ size 627
checkpoint-2000/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
+ }
checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/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
+ }
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.15006756782531738,
3
+ "best_model_checkpoint": "/content/gdrive/MyDrive/22_MI_Index/misinfo_vaccine/data/vaxx_bert_model/checkpoint-500",
4
+ "epoch": 2.6666666666666665,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.67,
12
+ "learning_rate": 1.555555555555556e-05,
13
+ "loss": 0.1865,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.67,
18
+ "eval_accuracy": 0.9607750472589792,
19
+ "eval_loss": 0.15006756782531738,
20
+ "eval_runtime": 94.9029,
21
+ "eval_samples_per_second": 22.296,
22
+ "eval_steps_per_second": 1.401,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 1.33,
27
+ "learning_rate": 1.1111111111111113e-05,
28
+ "loss": 0.0809,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 1.33,
33
+ "eval_accuracy": 0.9593572778827977,
34
+ "eval_loss": 0.15499280393123627,
35
+ "eval_runtime": 94.4075,
36
+ "eval_samples_per_second": 22.413,
37
+ "eval_steps_per_second": 1.409,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 2.0,
42
+ "learning_rate": 6.666666666666667e-06,
43
+ "loss": 0.0691,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 2.0,
48
+ "eval_accuracy": 0.9636105860113422,
49
+ "eval_loss": 0.16342061758041382,
50
+ "eval_runtime": 94.3706,
51
+ "eval_samples_per_second": 22.422,
52
+ "eval_steps_per_second": 1.409,
53
+ "step": 1500
54
+ },
55
+ {
56
+ "epoch": 2.67,
57
+ "learning_rate": 2.222222222222222e-06,
58
+ "loss": 0.0349,
59
+ "step": 2000
60
+ },
61
+ {
62
+ "epoch": 2.67,
63
+ "eval_accuracy": 0.9621928166351607,
64
+ "eval_loss": 0.17404669523239136,
65
+ "eval_runtime": 93.7717,
66
+ "eval_samples_per_second": 22.565,
67
+ "eval_steps_per_second": 1.418,
68
+ "step": 2000
69
+ }
70
+ ],
71
+ "max_steps": 2250,
72
+ "num_train_epochs": 3,
73
+ "total_flos": 331071733344888.0,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2565c62c73f962aed7e88088471f4f25259d92910b39c6f1867908995392f61
3
+ size 3707
checkpoint-2000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/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": "no_misinfo",
13
+ "1": "is_misinfo"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "is_misinfo": 1,
18
+ "no_misinfo": 0
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": "4.28.0",
32
+ "vocab_size": 30522
33
+ }
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac847bf33de7dce135492220dbee31f98aa713327e7f68a6001ea65e30c0e1be
3
+ size 13553
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab452554c3c7e850cf198b2ed8e830a52bd24557a2fdb6cbe2df2bf8763eb88
3
+ size 627
checkpoint-500/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
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/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
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.15006756782531738,
3
+ "best_model_checkpoint": "/content/gdrive/MyDrive/22_MI_Index/misinfo_vaccine/data/vaxx_bert_model/checkpoint-500",
4
+ "epoch": 0.6666666666666666,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.67,
12
+ "learning_rate": 1.555555555555556e-05,
13
+ "loss": 0.1865,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.67,
18
+ "eval_accuracy": 0.9607750472589792,
19
+ "eval_loss": 0.15006756782531738,
20
+ "eval_runtime": 94.9029,
21
+ "eval_samples_per_second": 22.296,
22
+ "eval_steps_per_second": 1.401,
23
+ "step": 500
24
+ }
25
+ ],
26
+ "max_steps": 2250,
27
+ "num_train_epochs": 3,
28
+ "total_flos": 83450321547072.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2565c62c73f962aed7e88088471f4f25259d92910b39c6f1867908995392f61
3
+ size 3707
checkpoint-500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
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": "no_misinfo",
13
+ "1": "is_misinfo"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "is_misinfo": 1,
18
+ "no_misinfo": 0
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": "4.28.0",
32
+ "vocab_size": 30522
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f7f5ea99f68650be869427adbbd2d08244f2dabaad116a20c44c6f757cec97c
3
+ size 267854125
runs/May23_00-41-03_4bf3b595ef41/1684802464.150275/events.out.tfevents.1684802464.4bf3b595ef41.238.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5457856067bc1ff071f680d1d85922f8ff554e11120e2d7455e7142d64a38ef
3
+ size 6044
runs/May23_00-41-03_4bf3b595ef41/events.out.tfevents.1684802464.4bf3b595ef41.238.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10786b5bd7c31453a368c3604dd8fd1e38bf906ad7d380b8a0d4cddcb0a166ce
3
+ size 6440
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2565c62c73f962aed7e88088471f4f25259d92910b39c6f1867908995392f61
3
+ size 3707
vocab.txt ADDED
The diff for this file is too large to render. See raw diff