Hugging Face's logo

duyphu
/
087f4980-23ca-4a35-b4a2-322c389428bc

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
087f4980-23ca-4a35-b4a2-322c389428bc
File size: 3,447 Bytes 
921c956
 
 
e267198
6b736c8
e267198
921c956
 
 
 
 
 
 
6b736c8
 
 
921c956
6b736c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bbb5590
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cd51075
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e267198
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
921c956
 
 
6b736c8
921c956
 
6b736c8
921c956
 
 
 
 
 
 
e267198
921c956
 
 
 
e267198
921c956
 
 
 
 
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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05755395683453238,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011510791366906475,
      "eval_loss": NaN,
      "eval_runtime": 19.145,
      "eval_samples_per_second": 19.117,
      "eval_steps_per_second": 9.559,
      "step": 1
    },
    {
      "epoch": 0.0057553956834532375,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.011510791366906475,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.011510791366906475,
      "eval_loss": NaN,
      "eval_runtime": 18.0771,
      "eval_samples_per_second": 20.247,
      "eval_steps_per_second": 10.123,
      "step": 10
    },
    {
      "epoch": 0.017266187050359712,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.02302158273381295,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.02302158273381295,
      "eval_loss": NaN,
      "eval_runtime": 18.2152,
      "eval_samples_per_second": 20.093,
      "eval_steps_per_second": 10.047,
      "step": 20
    },
    {
      "epoch": 0.02877697841726619,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2632,
      "step": 25
    },
    {
      "epoch": 0.034532374100719423,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.034532374100719423,
      "eval_loss": NaN,
      "eval_runtime": 18.1734,
      "eval_samples_per_second": 20.139,
      "eval_steps_per_second": 10.07,
      "step": 30
    },
    {
      "epoch": 0.04028776978417266,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0460431654676259,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0460431654676259,
      "eval_loss": NaN,
      "eval_runtime": 18.2472,
      "eval_samples_per_second": 20.058,
      "eval_steps_per_second": 10.029,
      "step": 40
    },
    {
      "epoch": 0.051798561151079135,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.05755395683453238,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.05755395683453238,
      "eval_loss": NaN,
      "eval_runtime": 18.19,
      "eval_samples_per_second": 20.121,
      "eval_steps_per_second": 10.06,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "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": 6383805728292864.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}