Hugging Face's logo

kk-aivio
/
728203bf-631e-4ad4-a8c6-dbd0be4bfb6a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
728203bf-631e-4ad4-a8c6-dbd0be4bfb6a
File size: 2,975 Bytes 
a515c5d
 
 
ac16922
a515c5d
ac16922
a515c5d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a7c867a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f060f18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ac16922
 
 
 
 
 
 
a515c5d
 
 
 
 
 
 
 
 
 
 
 
 
 
ac16922
a515c5d
 
 
 
ac16922
a515c5d
 
 
 
 
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": 0.013951866062085804,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013951866062085804,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0013951866062085804,
      "eval_loss": NaN,
      "eval_runtime": 12.4465,
      "eval_samples_per_second": 24.264,
      "eval_steps_per_second": 12.132,
      "step": 1
    },
    {
      "epoch": 0.0027903732124171608,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.004185559818625741,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 1.9907,
      "step": 3
    },
    {
      "epoch": 0.004185559818625741,
      "eval_loss": NaN,
      "eval_runtime": 11.052,
      "eval_samples_per_second": 27.325,
      "eval_steps_per_second": 13.663,
      "step": 3
    },
    {
      "epoch": 0.0055807464248343215,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.006975933031042902,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 2.732,
      "step": 5
    },
    {
      "epoch": 0.008371119637251482,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.008371119637251482,
      "eval_loss": NaN,
      "eval_runtime": 11.1533,
      "eval_samples_per_second": 27.077,
      "eval_steps_per_second": 13.539,
      "step": 6
    },
    {
      "epoch": 0.009766306243460064,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 1.3876,
      "step": 7
    },
    {
      "epoch": 0.011161492849668643,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 3.5812,
      "step": 8
    },
    {
      "epoch": 0.012556679455877224,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 1.0287,
      "step": 9
    },
    {
      "epoch": 0.012556679455877224,
      "eval_loss": NaN,
      "eval_runtime": 11.1153,
      "eval_samples_per_second": 27.17,
      "eval_steps_per_second": 13.585,
      "step": 9
    },
    {
      "epoch": 0.013951866062085804,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.9319,
      "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": 2259350810787840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}