Hugging Face's logo

nvsl
/
bert-for-harsh

Text Classification
Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
nvsl commited on
Commit
f9cc54b
•
1 Parent(s): 95868ea

Added Files

Browse files
Files changed (11) hide show
  1. config.json +35 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +55 -0
  9. trainer_state.json +139 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "NOT_harsh",
14
+ "1": "harsh"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "NOT_harsh": 0,
20
+ "harsh": 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": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "problem_type": "single_label_classification",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.35.0",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 30522
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e1a84e7235b5d9587da8b4ed3ebd0c7bbbb9f70b3ed57e37f4af3bdff6ebf3
3
+ size 437958648
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b6ab2d4744a9e17eb94c5a5eff8993f4306983ae462290f48e85a119b47b469
3
+ size 876037893
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eef4b036aa7c7d4ffcfa0d411651db7a4d24c6965c438a5ac14ea07c3819271
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b2b7208eef06c64f10c7b3aac7657e931e659fe04de8011d7b68945951cd3b
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
trainer_state.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1114240512251854,
3
+ "best_model_checkpoint": "/kaggle/working/BERT-BASE-harsh/checkpoint-4468",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 8936,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11,
13
+ "learning_rate": 1.8880931065353626e-05,
14
+ "loss": 0.151,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.22,
19
+ "learning_rate": 1.7761862130707253e-05,
20
+ "loss": 0.1135,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.34,
25
+ "learning_rate": 1.6642793196060877e-05,
26
+ "loss": 0.1061,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.45,
31
+ "learning_rate": 1.5523724261414504e-05,
32
+ "loss": 0.1125,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.56,
37
+ "learning_rate": 1.4404655326768131e-05,
38
+ "loss": 0.1068,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.67,
43
+ "learning_rate": 1.3285586392121757e-05,
44
+ "loss": 0.0979,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.78,
49
+ "learning_rate": 1.2166517457475382e-05,
50
+ "loss": 0.0952,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.9,
55
+ "learning_rate": 1.1047448522829008e-05,
56
+ "loss": 0.1026,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 1.0,
61
+ "eval_accuracy": 0.9645255147717099,
62
+ "eval_loss": 0.1114240512251854,
63
+ "eval_runtime": 219.6711,
64
+ "eval_samples_per_second": 81.358,
65
+ "eval_steps_per_second": 5.085,
66
+ "step": 4468
67
+ },
68
+ {
69
+ "epoch": 1.01,
70
+ "learning_rate": 9.928379588182634e-06,
71
+ "loss": 0.0949,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 1.12,
76
+ "learning_rate": 8.809310653536257e-06,
77
+ "loss": 0.0605,
78
+ "step": 5000
79
+ },
80
+ {
81
+ "epoch": 1.23,
82
+ "learning_rate": 7.690241718889885e-06,
83
+ "loss": 0.0595,
84
+ "step": 5500
85
+ },
86
+ {
87
+ "epoch": 1.34,
88
+ "learning_rate": 6.57117278424351e-06,
89
+ "loss": 0.0658,
90
+ "step": 6000
91
+ },
92
+ {
93
+ "epoch": 1.45,
94
+ "learning_rate": 5.452103849597136e-06,
95
+ "loss": 0.0622,
96
+ "step": 6500
97
+ },
98
+ {
99
+ "epoch": 1.57,
100
+ "learning_rate": 4.3330349149507615e-06,
101
+ "loss": 0.0639,
102
+ "step": 7000
103
+ },
104
+ {
105
+ "epoch": 1.68,
106
+ "learning_rate": 3.213965980304387e-06,
107
+ "loss": 0.0611,
108
+ "step": 7500
109
+ },
110
+ {
111
+ "epoch": 1.79,
112
+ "learning_rate": 2.0948970456580127e-06,
113
+ "loss": 0.0554,
114
+ "step": 8000
115
+ },
116
+ {
117
+ "epoch": 1.9,
118
+ "learning_rate": 9.758281110116385e-07,
119
+ "loss": 0.0625,
120
+ "step": 8500
121
+ },
122
+ {
123
+ "epoch": 2.0,
124
+ "eval_accuracy": 0.9682743957027753,
125
+ "eval_loss": 0.11515786498785019,
126
+ "eval_runtime": 219.7688,
127
+ "eval_samples_per_second": 81.322,
128
+ "eval_steps_per_second": 5.083,
129
+ "step": 8936
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 8936,
134
+ "num_train_epochs": 2,
135
+ "save_steps": 500,
136
+ "total_flos": 2.592649627027338e+16,
137
+ "trial_name": null,
138
+ "trial_params": null
139
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986bd3a1ecf2e3273885f66b49f9588044aff44158cb9a8f9bffd5eb6d2ee00e
3
+ size 4155
vocab.txt ADDED
The diff for this file is too large to render. See raw diff