Hugging Face's logo

0chanly
/
cai-deontological

Text Generation
PEFT
Safetensors
Transformers
lora
Model card Files
xet
 Community
cai-deontological
File size: 2,799 Bytes
9489173
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
118
119
120
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 113,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 1.5063320398330688,
      "learning_rate": 3.6e-05,
      "loss": 1.4051,
      "step": 10
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 1.7991224527359009,
      "learning_rate": 7.6e-05,
      "loss": 1.2966,
      "step": 20
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 1.6531014442443848,
      "learning_rate": 0.000116,
      "loss": 1.1773,
      "step": 30
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.5080221891403198,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.0591,
      "step": 40
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.470992088317871,
      "learning_rate": 0.000196,
      "loss": 1.0119,
      "step": 50
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.616141438484192,
      "learning_rate": 0.00019377162629757784,
      "loss": 0.9798,
      "step": 60
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 1.362313985824585,
      "learning_rate": 0.00018685121107266437,
      "loss": 0.9647,
      "step": 70
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 1.2892446517944336,
      "learning_rate": 0.00017993079584775087,
      "loss": 0.9841,
      "step": 80
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.0493370294570923,
      "learning_rate": 0.0001730103806228374,
      "loss": 0.9551,
      "step": 90
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.134190559387207,
      "learning_rate": 0.00016608996539792386,
      "loss": 1.0072,
      "step": 100
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 1.3157190084457397,
      "learning_rate": 0.0001591695501730104,
      "loss": 1.0067,
      "step": 110
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9378752112388611,
      "eval_runtime": 6.51,
      "eval_samples_per_second": 15.361,
      "eval_steps_per_second": 1.997,
      "step": 113
    }
  ],
  "logging_steps": 10,
  "max_steps": 339,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.96023945641984e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}