Hugging Face's logo

kokovova
/
69a29746-40cd-4612-8c63-12829ed16088

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
69a29746-40cd-4612-8c63-12829ed16088
File size: 3,306 Bytes 
1ba42f6
 
 
a98a99d
1ba42f6
a98a99d
1ba42f6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fcba99d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a98a99d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1ba42f6
 
 
 
 
 
 
 
 
 
 
 
 
 
a98a99d
1ba42f6
 
 
 
a98a99d
1ba42f6
 
 
 
 
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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000717240060248165,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.390800200827217e-05,
      "eval_loss": 3.313004493713379,
      "eval_runtime": 1025.2737,
      "eval_samples_per_second": 17.178,
      "eval_steps_per_second": 8.589,
      "step": 1
    },
    {
      "epoch": 7.17240060248165e-05,
      "grad_norm": 0.719241738319397,
      "learning_rate": 6e-05,
      "loss": 2.9884,
      "step": 3
    },
    {
      "epoch": 0.000143448012049633,
      "grad_norm": 1.0542523860931396,
      "learning_rate": 0.00012,
      "loss": 3.239,
      "step": 6
    },
    {
      "epoch": 0.00019126401606617735,
      "eval_loss": 3.1983094215393066,
      "eval_runtime": 1029.1587,
      "eval_samples_per_second": 17.113,
      "eval_steps_per_second": 8.557,
      "step": 8
    },
    {
      "epoch": 0.0002151720180744495,
      "grad_norm": 0.9659188389778137,
      "learning_rate": 0.00018,
      "loss": 3.1847,
      "step": 9
    },
    {
      "epoch": 0.000286896024099266,
      "grad_norm": 0.5769478678703308,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.5024,
      "step": 12
    },
    {
      "epoch": 0.0003586200301240825,
      "grad_norm": 1.169776439666748,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.9598,
      "step": 15
    },
    {
      "epoch": 0.0003825280321323547,
      "eval_loss": 2.9964921474456787,
      "eval_runtime": 1029.7079,
      "eval_samples_per_second": 17.104,
      "eval_steps_per_second": 8.552,
      "step": 16
    },
    {
      "epoch": 0.000430344036148899,
      "grad_norm": 1.353364109992981,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.0052,
      "step": 18
    },
    {
      "epoch": 0.0005020680421737155,
      "grad_norm": 1.4587379693984985,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.0622,
      "step": 21
    },
    {
      "epoch": 0.000573792048198532,
      "grad_norm": 0.7186371684074402,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.4507,
      "step": 24
    },
    {
      "epoch": 0.000573792048198532,
      "eval_loss": 2.9365055561065674,
      "eval_runtime": 1029.7686,
      "eval_samples_per_second": 17.103,
      "eval_steps_per_second": 8.551,
      "step": 24
    },
    {
      "epoch": 0.0006455160542233485,
      "grad_norm": 1.1878702640533447,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.7715,
      "step": 27
    },
    {
      "epoch": 0.000717240060248165,
      "grad_norm": 1.223516821861267,
      "learning_rate": 0.0,
      "loss": 2.7356,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1406516984741888e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}