Hugging Face's logo

tuanna08go
/
a7c81892-f441-469e-9e5c-36ef5a1e8f7f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
a7c81892-f441-469e-9e5c-36ef5a1e8f7f
File size: 2,702 Bytes 
4fe8af1
 
 
e98c035
b43ea13
e98c035
4fe8af1
 
 
 
 
 
 
b43ea13
 
 
4fe8af1
b43ea13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52c5223
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77a5069
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e98c035
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4fe8af1
 
 
b43ea13
4fe8af1
 
b43ea13
4fe8af1
 
 
 
 
 
 
e98c035
4fe8af1
 
 
 
e98c035
4fe8af1
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.43883708173340646,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00877674163466813,
      "eval_loss": NaN,
      "eval_runtime": 27.3419,
      "eval_samples_per_second": 28.089,
      "eval_steps_per_second": 3.511,
      "step": 1
    },
    {
      "epoch": 0.0877674163466813,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0877674163466813,
      "eval_loss": NaN,
      "eval_runtime": 26.7826,
      "eval_samples_per_second": 28.675,
      "eval_steps_per_second": 3.584,
      "step": 10
    },
    {
      "epoch": 0.1755348326933626,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.1755348326933626,
      "eval_loss": NaN,
      "eval_runtime": 26.5791,
      "eval_samples_per_second": 28.895,
      "eval_steps_per_second": 3.612,
      "step": 20
    },
    {
      "epoch": 0.2633022490400439,
      "grad_norm": NaN,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.2633022490400439,
      "eval_loss": NaN,
      "eval_runtime": 26.6585,
      "eval_samples_per_second": 28.809,
      "eval_steps_per_second": 3.601,
      "step": 30
    },
    {
      "epoch": 0.3510696653867252,
      "grad_norm": NaN,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.3510696653867252,
      "eval_loss": NaN,
      "eval_runtime": 26.5981,
      "eval_samples_per_second": 28.874,
      "eval_steps_per_second": 3.609,
      "step": 40
    },
    {
      "epoch": 0.43883708173340646,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.43883708173340646,
      "eval_loss": NaN,
      "eval_runtime": 26.5901,
      "eval_samples_per_second": 28.883,
      "eval_steps_per_second": 3.61,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.34826558652416e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}