Hugging Face's logo

memerchik
/
past_reference_detector

Safetensors
Model card Files
xet
Community
past_reference_detector
File size: 2,453 Bytes
dc24b09
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_global_step": 42,
  "best_metric": 0.9879518072289156,
  "best_model_checkpoint": "./past_ref_classifier/updated_model_3\\checkpoint-42",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.023024849593639374,
      "learning_rate": 1.3492063492063494e-05,
      "loss": 0.0746,
      "step": 42
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9879518072289156,
      "eval_f1": 0.9846153846153847,
      "eval_loss": 0.04217565059661865,
      "eval_precision": 1.0,
      "eval_recall": 0.9696969696969697,
      "eval_runtime": 0.3062,
      "eval_samples_per_second": 271.102,
      "eval_steps_per_second": 9.799,
      "step": 42
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.017906757071614265,
      "learning_rate": 6.825396825396826e-06,
      "loss": 0.0302,
      "step": 84
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9879518072289156,
      "eval_f1": 0.9846153846153847,
      "eval_loss": 0.05502840504050255,
      "eval_precision": 1.0,
      "eval_recall": 0.9696969696969697,
      "eval_runtime": 0.3281,
      "eval_samples_per_second": 252.973,
      "eval_steps_per_second": 9.144,
      "step": 84
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.044038157910108566,
      "learning_rate": 1.5873015873015874e-07,
      "loss": 0.0272,
      "step": 126
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9879518072289156,
      "eval_f1": 0.9846153846153847,
      "eval_loss": 0.05505102127790451,
      "eval_precision": 1.0,
      "eval_recall": 0.9696969696969697,
      "eval_runtime": 0.3131,
      "eval_samples_per_second": 265.072,
      "eval_steps_per_second": 9.581,
      "step": 126
    }
  ],
  "logging_steps": 100,
  "max_steps": 126,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 65968764530688.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}