Hugging Face's logo

dimasik1987
/
eafea6e5-1d87-4eb2-a92d-8f29e493ec54

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
eafea6e5-1d87-4eb2-a92d-8f29e493ec54
File size: 3,052 Bytes 
79f635b
 
 
1a9a48f
79f635b
1a9a48f
79f635b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f17974a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1a9a48f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79f635b
 
 
 
 
 
 
 
 
 
 
 
 
 
1a9a48f
79f635b
 
 
 
1a9a48f
79f635b
 
 
 
 
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": 0.023781212841854936,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007927070947284979,
      "eval_loss": NaN,
      "eval_runtime": 61.2857,
      "eval_samples_per_second": 8.681,
      "eval_steps_per_second": 4.34,
      "step": 1
    },
    {
      "epoch": 0.0023781212841854932,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0047562425683709865,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.006341656757827983,
      "eval_loss": NaN,
      "eval_runtime": 60.8856,
      "eval_samples_per_second": 8.738,
      "eval_steps_per_second": 4.369,
      "step": 8
    },
    {
      "epoch": 0.007134363852556481,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.009512485136741973,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.011890606420927468,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.012683313515655966,
      "eval_loss": NaN,
      "eval_runtime": 61.086,
      "eval_samples_per_second": 8.709,
      "eval_steps_per_second": 4.355,
      "step": 16
    },
    {
      "epoch": 0.014268727705112961,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.016646848989298454,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.019024970273483946,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.019024970273483946,
      "eval_loss": NaN,
      "eval_runtime": 61.1775,
      "eval_samples_per_second": 8.696,
      "eval_steps_per_second": 4.348,
      "step": 24
    },
    {
      "epoch": 0.02140309155766944,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.023781212841854936,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "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": 1.0722724854890496e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}