Hugging Face's logo

av-codes
/
pi-detector-distilbert

Text Classification
Transformers
Safetensors
English
distilbert
prompt-injection
security
cybersecurity
llm-security
ml-intern
text-embeddings-inference
Model card Files
xet
 Community
pi-detector-distilbert
File size: 2,871 Bytes
551ef81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
{
  "best_global_step": 99,
  "best_metric": 1.0,
  "best_model_checkpoint": "./pi-detector/checkpoint-99",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 1.3391671180725098,
      "learning_rate": 0.0,
      "loss": 0.6838793754577637,
      "step": 1
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.2506626844406128,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.6808025042215983,
      "step": 10
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 1.1518597602844238,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.6861461639404297,
      "step": 20
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.91855788230896,
      "learning_rate": 5.8e-06,
      "loss": 0.6577313423156739,
      "step": 30
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 1.835654854774475,
      "learning_rate": 7.800000000000002e-06,
      "loss": 0.5954501628875732,
      "step": 40
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 1.999822735786438,
      "learning_rate": 9.800000000000001e-06,
      "loss": 0.5008408069610596,
      "step": 50
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 2.83133864402771,
      "learning_rate": 1.18e-05,
      "loss": 0.37516820430755615,
      "step": 60
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 1.6260528564453125,
      "learning_rate": 1.38e-05,
      "loss": 0.29813175201416015,
      "step": 70
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 1.7019435167312622,
      "learning_rate": 1.58e-05,
      "loss": 0.2266446352005005,
      "step": 80
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.1480830907821655,
      "learning_rate": 1.7800000000000002e-05,
      "loss": 0.17041007280349732,
      "step": 90
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 1.0,
      "eval_f1": 1.0,
      "eval_loss": 0.032340291887521744,
      "eval_precision": 1.0,
      "eval_recall": 1.0,
      "eval_runtime": 0.2543,
      "eval_samples_per_second": 503.339,
      "eval_steps_per_second": 15.729,
      "step": 99
    }
  ],
  "logging_steps": 10,
  "max_steps": 495,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 32576631053856.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}