Hugging Face's logo

dzanbek
/
7429339f-5099-4696-950d-cf15dec61567

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7429339f-5099-4696-950d-cf15dec61567
File size: 3,060 Bytes 
f81acbe
 
 
7d41742
f81acbe
7d41742
f81acbe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d4c3e17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7d41742
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f81acbe
 
 
 
 
 
 
 
 
 
 
 
 
 
7d41742
f81acbe
 
 
 
7d41742
f81acbe
 
 
 
 
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": 0.013185364245687286,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004395121415229096,
      "eval_loss": NaN,
      "eval_runtime": 173.6869,
      "eval_samples_per_second": 5.516,
      "eval_steps_per_second": 2.758,
      "step": 1
    },
    {
      "epoch": 0.0013185364245687286,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0026370728491374573,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0035160971321832766,
      "eval_loss": NaN,
      "eval_runtime": 173.7934,
      "eval_samples_per_second": 5.512,
      "eval_steps_per_second": 2.756,
      "step": 8
    },
    {
      "epoch": 0.003955609273706186,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0052741456982749145,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.006592682122843643,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.007032194264366553,
      "eval_loss": NaN,
      "eval_runtime": 174.3985,
      "eval_samples_per_second": 5.493,
      "eval_steps_per_second": 2.747,
      "step": 16
    },
    {
      "epoch": 0.007911218547412372,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.009229754971981101,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.010548291396549829,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.010548291396549829,
      "eval_loss": NaN,
      "eval_runtime": 174.3686,
      "eval_samples_per_second": 5.494,
      "eval_steps_per_second": 2.747,
      "step": 24
    },
    {
      "epoch": 0.011866827821118558,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.013185364245687286,
      "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": 1.924493834452992e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}