Hugging Face's logo

SmartestBoy
/
electra-malay-ai-detector

Safetensors
electra
Model card Files
xet
 Community
SmartestBoy commited on
Commit
420eda3
·
verified ·
1 Parent(s): 64cb2bb

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. config.json +37 -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 +58 -0
  9. trainer_state.json +178 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Human",
14
+ "1": "AI"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "AI": 1,
20
+ "Human": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "electra",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "position_embedding_type": "absolute",
29
+ "summary_activation": "gelu",
30
+ "summary_last_dropout": 0.1,
31
+ "summary_type": "first",
32
+ "summary_use_proj": true,
33
+ "transformers_version": "4.56.2",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 32000
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b23d43b4ac265397b1a6ba0b269fd737355d35a96465a195290406539501b516
3
+ size 442499672
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a131dfa53d426e18f6c2beb2d67b7ec074d09918a14af79373aef348f52bd7b
3
+ size 202031435
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d420a716ff13fe6c6cfa712e85147cdd935479d770764b798412ddcf6f7a2068
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8597a0eddb2edf7fb48a2a97659c7edd4875a357f2c4644de9a8f0f1e770a30a
3
+ size 1465
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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": false,
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": "ElectraTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 485,
3
+ "best_metric": 0.9733218588640276,
4
+ "best_model_checkpoint": "models/electra-base-discriminator-bahasa-cased-512-seq/checkpoint-485",
5
+ "epoch": 3.0,
6
+ "eval_steps": 97,
7
+ "global_step": 873,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.3333333333333333,
14
+ "grad_norm": 2.162574291229248,
15
+ "learning_rate": 0.00019994875242584925,
16
+ "loss": 0.6418,
17
+ "step": 97
18
+ },
19
+ {
20
+ "epoch": 0.3333333333333333,
21
+ "eval_accuracy": 0.6751290877796902,
22
+ "eval_loss": 0.6097611784934998,
23
+ "eval_runtime": 14.3421,
24
+ "eval_samples_per_second": 162.041,
25
+ "eval_steps_per_second": 5.09,
26
+ "step": 97
27
+ },
28
+ {
29
+ "epoch": 0.6666666666666666,
30
+ "grad_norm": 2.945030450820923,
31
+ "learning_rate": 0.00019130020543448704,
32
+ "loss": 0.4696,
33
+ "step": 194
34
+ },
35
+ {
36
+ "epoch": 0.6666666666666666,
37
+ "eval_accuracy": 0.9453528399311532,
38
+ "eval_loss": 0.2995855510234833,
39
+ "eval_runtime": 14.3943,
40
+ "eval_samples_per_second": 161.453,
41
+ "eval_steps_per_second": 5.071,
42
+ "step": 194
43
+ },
44
+ {
45
+ "epoch": 1.0,
46
+ "grad_norm": 20.851119995117188,
47
+ "learning_rate": 0.00016906493009392686,
48
+ "loss": 0.3585,
49
+ "step": 291
50
+ },
51
+ {
52
+ "epoch": 1.0,
53
+ "eval_accuracy": 0.9668674698795181,
54
+ "eval_loss": 0.2586265504360199,
55
+ "eval_runtime": 14.3873,
56
+ "eval_samples_per_second": 161.532,
57
+ "eval_steps_per_second": 5.074,
58
+ "step": 291
59
+ },
60
+ {
61
+ "epoch": 1.3333333333333333,
62
+ "grad_norm": 9.39693832397461,
63
+ "learning_rate": 0.00013655184169503949,
64
+ "loss": 0.2635,
65
+ "step": 388
66
+ },
67
+ {
68
+ "epoch": 1.3333333333333333,
69
+ "eval_accuracy": 0.9707401032702238,
70
+ "eval_loss": 0.26390692591667175,
71
+ "eval_runtime": 14.3548,
72
+ "eval_samples_per_second": 161.897,
73
+ "eval_steps_per_second": 5.085,
74
+ "step": 388
75
+ },
76
+ {
77
+ "epoch": 1.6666666666666665,
78
+ "grad_norm": 1.9695847034454346,
79
+ "learning_rate": 9.85993357021825e-05,
80
+ "loss": 0.2569,
81
+ "step": 485
82
+ },
83
+ {
84
+ "epoch": 1.6666666666666665,
85
+ "eval_accuracy": 0.9733218588640276,
86
+ "eval_loss": 0.25199127197265625,
87
+ "eval_runtime": 14.3798,
88
+ "eval_samples_per_second": 161.615,
89
+ "eval_steps_per_second": 5.077,
90
+ "step": 485
91
+ },
92
+ {
93
+ "epoch": 2.0,
94
+ "grad_norm": 0.28883352875709534,
95
+ "learning_rate": 6.085526785283575e-05,
96
+ "loss": 0.2484,
97
+ "step": 582
98
+ },
99
+ {
100
+ "epoch": 2.0,
101
+ "eval_accuracy": 0.9462134251290878,
102
+ "eval_loss": 0.31412678956985474,
103
+ "eval_runtime": 14.3715,
104
+ "eval_samples_per_second": 161.709,
105
+ "eval_steps_per_second": 5.079,
106
+ "step": 582
107
+ },
108
+ {
109
+ "epoch": 2.3333333333333335,
110
+ "grad_norm": 3.2036261558532715,
111
+ "learning_rate": 2.8936475417214794e-05,
112
+ "loss": 0.2213,
113
+ "step": 679
114
+ },
115
+ {
116
+ "epoch": 2.3333333333333335,
117
+ "eval_accuracy": 0.9677280550774526,
118
+ "eval_loss": 0.27302563190460205,
119
+ "eval_runtime": 14.3894,
120
+ "eval_samples_per_second": 161.507,
121
+ "eval_steps_per_second": 5.073,
122
+ "step": 679
123
+ },
124
+ {
125
+ "epoch": 2.6666666666666665,
126
+ "grad_norm": 10.041082382202148,
127
+ "learning_rate": 7.59291443313389e-06,
128
+ "loss": 0.2173,
129
+ "step": 776
130
+ },
131
+ {
132
+ "epoch": 2.6666666666666665,
133
+ "eval_accuracy": 0.9612736660929432,
134
+ "eval_loss": 0.287920206785202,
135
+ "eval_runtime": 14.3754,
136
+ "eval_samples_per_second": 161.665,
137
+ "eval_steps_per_second": 5.078,
138
+ "step": 776
139
+ },
140
+ {
141
+ "epoch": 3.0,
142
+ "grad_norm": 0.965843141078949,
143
+ "learning_rate": 8.008106802126492e-10,
144
+ "loss": 0.2196,
145
+ "step": 873
146
+ },
147
+ {
148
+ "epoch": 3.0,
149
+ "eval_accuracy": 0.9664371772805508,
150
+ "eval_loss": 0.2767605185508728,
151
+ "eval_runtime": 14.3762,
152
+ "eval_samples_per_second": 161.656,
153
+ "eval_steps_per_second": 5.078,
154
+ "step": 873
155
+ }
156
+ ],
157
+ "logging_steps": 97,
158
+ "max_steps": 873,
159
+ "num_input_tokens_seen": 0,
160
+ "num_train_epochs": 3,
161
+ "save_steps": 97,
162
+ "stateful_callbacks": {
163
+ "TrainerControl": {
164
+ "args": {
165
+ "should_epoch_stop": false,
166
+ "should_evaluate": false,
167
+ "should_log": false,
168
+ "should_save": true,
169
+ "should_training_stop": true
170
+ },
171
+ "attributes": {}
172
+ }
173
+ },
174
+ "total_flos": 4489644826458240.0,
175
+ "train_batch_size": 32,
176
+ "trial_name": null,
177
+ "trial_params": null
178
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61e24b1392f667241644d855919889280be6467f22d0772287e2dae06e59987f
3
+ size 6033
vocab.txt ADDED
The diff for this file is too large to render. See raw diff