Upload 12 files
Browse files- ai_text_detector_model.joblib +3 -0
- best_model_epoch_1.pt +3 -0
- config.json +25 -0
- model.safetensors +3 -0
- model_config.json +39 -0
- preprocessing_config.json +22 -0
- pytorch_model_state.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_history.json +77 -0
- vocab.txt +0 -0
ai_text_detector_model.joblib
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9a9e33fa1750ee39be933ccaf99d988160ae81362a970e7b7769552d61ef113
|
3 |
+
size 40859
|
best_model_epoch_1.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99e463fd5f773ebc25787109c8df27313cd6940637984daafcd93f2a6a477d90
|
3 |
+
size 442760731
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForSequenceClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.52.4",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2271ea44970ac97bab48659a94a8ffd66f78ab5855418ede84ff7a749ed79cb7
|
3 |
+
size 437958648
|
model_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_name": "bert-base-uncased",
|
3 |
+
"max_length": 466,
|
4 |
+
"num_labels": 2,
|
5 |
+
"epochs_trained": 1,
|
6 |
+
"batch_size": 64,
|
7 |
+
"learning_rate": 2e-05,
|
8 |
+
"best_accuracy": 0.9453856968403337,
|
9 |
+
"final_accuracy": 0.9453856968403337,
|
10 |
+
"auc_score": 0.9939228407682139,
|
11 |
+
"macro_f1": 0.9427710333848727,
|
12 |
+
"weighted_f1": 0.9458933399827738,
|
13 |
+
"training_duration": "3:39:06.163419",
|
14 |
+
"training_timestamp": "2025-08-09T07:40:30.567858",
|
15 |
+
"total_parameters": 109483778,
|
16 |
+
"trainable_parameters": 592130,
|
17 |
+
"class_weights": [
|
18 |
+
0.7966578602790833,
|
19 |
+
1.3427214622497559
|
20 |
+
],
|
21 |
+
"confusion_matrix": [
|
22 |
+
[
|
23 |
+
56477,
|
24 |
+
4683
|
25 |
+
],
|
26 |
+
[
|
27 |
+
639,
|
28 |
+
35648
|
29 |
+
]
|
30 |
+
],
|
31 |
+
"classification_report": {
|
32 |
+
"human_precision": 0.9888122417536243,
|
33 |
+
"human_recall": 0.9234303466317855,
|
34 |
+
"human_f1": 0.955003551016267,
|
35 |
+
"ai_precision": 0.8838858446356401,
|
36 |
+
"ai_recall": 0.9823903877421666,
|
37 |
+
"ai_f1": 0.9305385157534782
|
38 |
+
}
|
39 |
+
}
|
preprocessing_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"preprocessing_params": {
|
3 |
+
"max_length": 512,
|
4 |
+
"mean_human_length": 1783.427587582612,
|
5 |
+
"mean_ai_length": 1798.8007539931875,
|
6 |
+
"total_samples": 487231,
|
7 |
+
"preprocessing_timestamp": "2025-08-09T03:53:51.664833"
|
8 |
+
},
|
9 |
+
"text_length_stats": {
|
10 |
+
"mean_length": 1789.2861020462615,
|
11 |
+
"max_length_used": 466,
|
12 |
+
"percentile_95": 466.69999999999993,
|
13 |
+
"percentile_99": 503.09000000000003
|
14 |
+
},
|
15 |
+
"dataset_stats": {
|
16 |
+
"total_samples": 487231,
|
17 |
+
"train_samples": 389784,
|
18 |
+
"test_samples": 97447,
|
19 |
+
"human_samples": 305797,
|
20 |
+
"ai_samples": 181434
|
21 |
+
}
|
22 |
+
}
|
pytorch_model_state.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4417a5ae83b5a6fafad2cb34d2fc0bfc6a5aa38be4f2a9cd2cea046637e63e79
|
3 |
+
size 438617724
|
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 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"extra_special_tokens": {},
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "BertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
training_history.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"train_losses": [
|
3 |
+
0.15264250313705058
|
4 |
+
],
|
5 |
+
"train_accuracies": [
|
6 |
+
0.9417934035260555
|
7 |
+
],
|
8 |
+
"val_losses": [
|
9 |
+
0.12102170220196481
|
10 |
+
],
|
11 |
+
"val_accuracies": [
|
12 |
+
0.9453856968403337
|
13 |
+
],
|
14 |
+
"learning_rates": [
|
15 |
+
2.0000000000000002e-07,
|
16 |
+
1.99966616591554e-05,
|
17 |
+
1.9662827574695376e-05,
|
18 |
+
1.9328993490235356e-05,
|
19 |
+
1.8995159405775333e-05,
|
20 |
+
1.8661325321315307e-05,
|
21 |
+
1.8327491236855283e-05,
|
22 |
+
1.799365715239526e-05,
|
23 |
+
1.7659823067935237e-05,
|
24 |
+
1.7325988983475214e-05,
|
25 |
+
1.699215489901519e-05,
|
26 |
+
1.6658320814555167e-05,
|
27 |
+
1.6324486730095144e-05,
|
28 |
+
1.599065264563512e-05,
|
29 |
+
1.5656818561175097e-05,
|
30 |
+
1.5322984476715074e-05,
|
31 |
+
1.498915039225505e-05,
|
32 |
+
1.4655316307795026e-05,
|
33 |
+
1.4321482223335005e-05,
|
34 |
+
1.3987648138874981e-05,
|
35 |
+
1.3653814054414958e-05,
|
36 |
+
1.3319979969954933e-05,
|
37 |
+
1.298614588549491e-05,
|
38 |
+
1.2652311801034887e-05,
|
39 |
+
1.2318477716574863e-05,
|
40 |
+
1.198464363211484e-05,
|
41 |
+
1.1650809547654815e-05,
|
42 |
+
1.1316975463194792e-05,
|
43 |
+
1.0983141378734769e-05,
|
44 |
+
1.0649307294274747e-05,
|
45 |
+
1.0315473209814724e-05,
|
46 |
+
9.981639125354699e-06,
|
47 |
+
9.647805040894676e-06,
|
48 |
+
9.313970956434653e-06,
|
49 |
+
8.98013687197463e-06,
|
50 |
+
8.646302787514606e-06,
|
51 |
+
8.312468703054583e-06,
|
52 |
+
7.97863461859456e-06,
|
53 |
+
7.644800534134535e-06,
|
54 |
+
7.310966449674512e-06,
|
55 |
+
6.977132365214488e-06,
|
56 |
+
6.643298280754466e-06,
|
57 |
+
6.309464196294443e-06,
|
58 |
+
5.975630111834419e-06,
|
59 |
+
5.641796027374395e-06,
|
60 |
+
5.307961942914372e-06,
|
61 |
+
4.974127858454348e-06,
|
62 |
+
4.640293773994326e-06,
|
63 |
+
4.3064596895343016e-06,
|
64 |
+
3.972625605074278e-06,
|
65 |
+
3.6387915206142547e-06,
|
66 |
+
3.3049574361542315e-06,
|
67 |
+
2.9711233516942082e-06,
|
68 |
+
2.637289267234185e-06,
|
69 |
+
2.3034551827741613e-06,
|
70 |
+
1.969621098314138e-06,
|
71 |
+
1.6357870138541146e-06,
|
72 |
+
1.3019529293940914e-06,
|
73 |
+
9.681188449340678e-07,
|
74 |
+
6.342847604740444e-07,
|
75 |
+
3.004506760140211e-07
|
76 |
+
]
|
77 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|