Hugging Face's logo

ardaspear
/
92194c17-572e-4ec0-8aaf-90d295e9ba55

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
92194c17-572e-4ec0-8aaf-90d295e9ba55
File size: 3,165 Bytes 
5bb4602
 
 
a79e4a2
5bb4602
a79e4a2
5bb4602
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8512412
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8323d9d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43dafd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a79e4a2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5bb4602
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a79e4a2
5bb4602
 
 
 
 
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
137
138
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0074211502782931356,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002968460111317254,
      "eval_loss": NaN,
      "eval_runtime": 423.8224,
      "eval_samples_per_second": 13.388,
      "eval_steps_per_second": 1.675,
      "step": 1
    },
    {
      "epoch": 0.0008905380333951762,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.001484230055658627,
      "eval_loss": NaN,
      "eval_runtime": 424.3722,
      "eval_samples_per_second": 13.37,
      "eval_steps_per_second": 1.673,
      "step": 5
    },
    {
      "epoch": 0.0017810760667903525,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.002671614100185529,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.002968460111317254,
      "eval_loss": NaN,
      "eval_runtime": 424.248,
      "eval_samples_per_second": 13.374,
      "eval_steps_per_second": 1.674,
      "step": 10
    },
    {
      "epoch": 0.003562152133580705,
      "grad_norm": NaN,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0044526901669758815,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0044526901669758815,
      "eval_loss": NaN,
      "eval_runtime": 424.023,
      "eval_samples_per_second": 13.381,
      "eval_steps_per_second": 1.674,
      "step": 15
    },
    {
      "epoch": 0.005343228200371058,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.005936920222634508,
      "eval_loss": NaN,
      "eval_runtime": 423.9902,
      "eval_samples_per_second": 13.382,
      "eval_steps_per_second": 1.675,
      "step": 20
    },
    {
      "epoch": 0.006233766233766234,
      "grad_norm": NaN,
      "learning_rate": 8.247240241650918e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.00712430426716141,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0074211502782931356,
      "eval_loss": NaN,
      "eval_runtime": 424.5104,
      "eval_samples_per_second": 13.366,
      "eval_steps_per_second": 1.673,
      "step": 25
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.625636096219546e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}