Hugging Face's logo

prancyFox
/
tiny-bert-enron-spam

Text Classification
Transformers
Safetensors
English
bert
spam
ham
email
tinybert
enron
Eval Results
Model card Files
xet
Community
prancyFox commited on
Commit
2acc614
·
verified ·
1 Parent(s): 97eef92

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. checkpoint-45/config.json +36 -0
  2. checkpoint-45/model.safetensors +3 -0
  3. checkpoint-45/optimizer.pt +3 -0
  4. checkpoint-45/rng_state.pth +3 -0
  5. checkpoint-45/scheduler.pt +3 -0
  6. checkpoint-45/special_tokens_map.json +37 -0
  7. checkpoint-45/tokenizer.json +0 -0
  8. checkpoint-45/tokenizer_config.json +62 -0
  9. checkpoint-45/trainer_state.json +42 -0
  10. checkpoint-45/training_args.bin +3 -0
  11. checkpoint-45/vocab.txt +0 -0
  12. config.json +36 -36
  13. eval_metrics.json +10 -10
  14. label_mapping.json +9 -9
  15. model.safetensors +1 -1
  16. special_tokens_map.json +37 -7
  17. tokenizer_config.json +62 -58
  18. training_args.bin +2 -2
checkpoint-45/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "cell": {},
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "emb_size": 312,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "ham",
15
+ "1": "spam"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 1200,
19
+ "label2id": {
20
+ "ham": 0,
21
+ "spam": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 4,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "pre_trained": "",
31
+ "structure": [],
32
+ "transformers_version": "4.56.1",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-45/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737c4773ef38e343c4f43193c5c302adf0183422d264c2a3e8afba5529f81040
3
+ size 57411808
checkpoint-45/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8daa7d2044ce7d0e092dff585ee1394b28d9aed40788880b0e3f27cca179c9af
3
+ size 114864267
checkpoint-45/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba4fde4ee04d2f472bb4dea96a48e8fdf7891d2b0694a8f012e8133a2e176ae
3
+ size 14455
checkpoint-45/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3ee91f13049c6c3776c60b415c793f9b048dfabe12cf335d035a2054b81544
3
+ size 1465
checkpoint-45/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-45/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-45/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 256,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
checkpoint-45/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 200,
7
+ "global_step": 45,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [],
12
+ "logging_steps": 50,
13
+ "max_steps": 45,
14
+ "num_input_tokens_seen": 0,
15
+ "num_train_epochs": 3,
16
+ "save_steps": 200,
17
+ "stateful_callbacks": {
18
+ "EarlyStoppingCallback": {
19
+ "args": {
20
+ "early_stopping_patience": 5,
21
+ "early_stopping_threshold": 0.0005
22
+ },
23
+ "attributes": {
24
+ "early_stopping_patience_counter": 0
25
+ }
26
+ },
27
+ "TrainerControl": {
28
+ "args": {
29
+ "should_epoch_stop": false,
30
+ "should_evaluate": false,
31
+ "should_log": false,
32
+ "should_save": true,
33
+ "should_training_stop": true
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 9672717175464.0,
39
+ "train_batch_size": 32,
40
+ "trial_name": null,
41
+ "trial_params": null
42
+ }
checkpoint-45/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d19a1b7f7a3043c7f0b1af0f0938ce04f84957bbe17b2fc15b138edb3c02807
3
+ size 5777
checkpoint-45/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -1,36 +1,36 @@
1
- {
2
- "architectures": [
3
- "BertForSequenceClassification"
4
- ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "cell": {},
7
- "classifier_dropout": null,
8
- "emb_size": 312,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 312,
12
- "id2label": {
13
- "0": "ham",
14
- "1": "spam"
15
- },
16
- "initializer_range": 0.02,
17
- "intermediate_size": 1200,
18
- "label2id": {
19
- "ham": 0,
20
- "spam": 1
21
- },
22
- "layer_norm_eps": 1e-12,
23
- "max_position_embeddings": 512,
24
- "model_type": "bert",
25
- "num_attention_heads": 12,
26
- "num_hidden_layers": 4,
27
- "pad_token_id": 0,
28
- "position_embedding_type": "absolute",
29
- "pre_trained": "",
30
- "structure": [],
31
- "torch_dtype": "float32",
32
- "transformers_version": "4.55.0",
33
- "type_vocab_size": 2,
34
- "use_cache": true,
35
- "vocab_size": 30522
36
- }
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "cell": {},
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "emb_size": 312,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "ham",
15
+ "1": "spam"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 1200,
19
+ "label2id": {
20
+ "ham": 0,
21
+ "spam": 1
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 4,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "pre_trained": "",
31
+ "structure": [],
32
+ "transformers_version": "4.56.1",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
eval_metrics.json CHANGED
@@ -1,11 +1,11 @@
1
- {
2
- "eval_loss": 0.016226448118686676,
3
- "eval_accuracy": 0.9967329967329968,
4
- "eval_precision": 0.9936342592592593,
5
- "eval_recall": 1.0,
6
- "eval_f1": 0.9968069666182874,
7
- "eval_runtime": 71.2724,
8
- "eval_samples_per_second": 47.241,
9
- "eval_steps_per_second": 2.96,
10
- "epoch": 2.1119324181626187
11
  }
 
1
+ {
2
+ "eval_loss": 0.689111590385437,
3
+ "eval_accuracy": 0.8392857142857143,
4
+ "eval_precision": 0.2777777777777778,
5
+ "eval_recall": 0.5,
6
+ "eval_f1": 0.35714285714285715,
7
+ "eval_runtime": 0.4314,
8
+ "eval_samples_per_second": 259.649,
9
+ "eval_steps_per_second": 16.228,
10
+ "epoch": 3.0
11
  }
label_mapping.json CHANGED
@@ -1,10 +1,10 @@
1
- {
2
- "id2label": {
3
- "0": "ham",
4
- "1": "spam"
5
- },
6
- "label2id": {
7
- "ham": 0,
8
- "spam": 1
9
- }
10
  }
 
1
+ {
2
+ "id2label": {
3
+ "0": "ham",
4
+ "1": "spam"
5
+ },
6
+ "label2id": {
7
+ "ham": 0,
8
+ "spam": 1
9
+ }
10
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a31c635559db3cefbb53de0825299d4849ec2c98ffa325475aa5c1b93b52a599
3
  size 57411808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737c4773ef38e343c4f43193c5c302adf0183422d264c2a3e8afba5529f81040
3
  size 57411808
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json CHANGED
@@ -1,58 +1,62 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "100": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "101": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "102": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "103": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
- "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
- "do_lower_case": true,
48
- "extra_special_tokens": {},
49
- "mask_token": "[MASK]",
50
- "model_max_length": 1000000000000000019884624838656,
51
- "never_split": null,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
54
- "strip_accents": null,
55
- "tokenize_chinese_chars": true,
56
- "tokenizer_class": "BertTokenizer",
57
- "unk_token": "[UNK]"
58
- }
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 256,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f6ee5be6db1ab816abaa77671d6a299c7d2015f383c82c395377bcfdce9d1cd
3
- size 5713
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d19a1b7f7a3043c7f0b1af0f0938ce04f84957bbe17b2fc15b138edb3c02807
3
+ size 5777