Hugging Face's logo

kk-aivio
/
05ce96ba-5768-4c1a-920d-1860ba7f43c0

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
05ce96ba-5768-4c1a-920d-1860ba7f43c0
File size: 2,950 Bytes 
00f4e92
 
 
52d7f3c
00f4e92
52d7f3c
00f4e92
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33c2751
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80b3d49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52d7f3c
 
 
 
 
 
 
00f4e92
 
 
 
 
 
 
 
 
 
 
 
 
 
52d7f3c
00f4e92
 
 
 
52d7f3c
00f4e92
 
 
 
 
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": 0.021299254526091587,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002129925452609159,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.002129925452609159,
      "eval_loss": NaN,
      "eval_runtime": 7.2388,
      "eval_samples_per_second": 27.353,
      "eval_steps_per_second": 13.676,
      "step": 1
    },
    {
      "epoch": 0.004259850905218318,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.006389776357827476,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.006389776357827476,
      "eval_loss": NaN,
      "eval_runtime": 6.1103,
      "eval_samples_per_second": 32.404,
      "eval_steps_per_second": 16.202,
      "step": 3
    },
    {
      "epoch": 0.008519701810436636,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.010649627263045794,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.012779552715654952,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.012779552715654952,
      "eval_loss": NaN,
      "eval_runtime": 6.1412,
      "eval_samples_per_second": 32.241,
      "eval_steps_per_second": 16.121,
      "step": 6
    },
    {
      "epoch": 0.014909478168264111,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.01703940362087327,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.019169329073482427,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.019169329073482427,
      "eval_loss": NaN,
      "eval_runtime": 6.1645,
      "eval_samples_per_second": 32.119,
      "eval_steps_per_second": 16.06,
      "step": 9
    },
    {
      "epoch": 0.021299254526091587,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1752669785948160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}