Hugging Face's logo

jssky
/
6c2b4015-818d-4703-aeda-00bb540e60c1

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
6c2b4015-818d-4703-aeda-00bb540e60c1
File size: 3,009 Bytes 
691f62c
 
 
8e0699d
691f62c
8e0699d
691f62c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2dec5cb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
152e2a2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8e0699d
 
 
 
 
 
 
691f62c
 
 
 
 
 
 
 
 
 
 
 
 
 
8e0699d
691f62c
 
 
 
8e0699d
691f62c
 
 
 
 
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": 0.016129032258064516,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016129032258064516,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.9049,
      "step": 1
    },
    {
      "epoch": 0.0016129032258064516,
      "eval_loss": 9.502001762390137,
      "eval_runtime": 24.5704,
      "eval_samples_per_second": 42.49,
      "eval_steps_per_second": 5.332,
      "step": 1
    },
    {
      "epoch": 0.0032258064516129032,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.5029,
      "step": 2
    },
    {
      "epoch": 0.004838709677419355,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.5036,
      "step": 3
    },
    {
      "epoch": 0.004838709677419355,
      "eval_loss": 9.502001762390137,
      "eval_runtime": 23.8929,
      "eval_samples_per_second": 43.695,
      "eval_steps_per_second": 5.483,
      "step": 3
    },
    {
      "epoch": 0.0064516129032258064,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.4681,
      "step": 4
    },
    {
      "epoch": 0.008064516129032258,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.3615,
      "step": 5
    },
    {
      "epoch": 0.00967741935483871,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.3141,
      "step": 6
    },
    {
      "epoch": 0.00967741935483871,
      "eval_loss": 9.502001762390137,
      "eval_runtime": 23.8738,
      "eval_samples_per_second": 43.73,
      "eval_steps_per_second": 5.487,
      "step": 6
    },
    {
      "epoch": 0.01129032258064516,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.2474,
      "step": 7
    },
    {
      "epoch": 0.012903225806451613,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.5729,
      "step": 8
    },
    {
      "epoch": 0.014516129032258065,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.5663,
      "step": 9
    },
    {
      "epoch": 0.014516129032258065,
      "eval_loss": 9.502001762390137,
      "eval_runtime": 23.8764,
      "eval_samples_per_second": 43.725,
      "eval_steps_per_second": 5.487,
      "step": 9
    },
    {
      "epoch": 0.016129032258064516,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.5635,
      "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": 2.95105726513152e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}