Hugging Face's logo

tuanna08go
/
a7fd50e2-e74c-47a2-aac1-75642c65d0a3

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
a7fd50e2-e74c-47a2-aac1-75642c65d0a3
File size: 3,475 Bytes 
d564c4d
 
 
2bf73b3
ff8acbb
2bf73b3
d564c4d
 
 
 
 
 
 
ff8acbb
 
 
d564c4d
ff8acbb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c033edc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0cf7c0c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2bf73b3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d564c4d
 
 
ff8acbb
d564c4d
 
ff8acbb
d564c4d
 
 
 
 
 
 
2bf73b3
d564c4d
 
 
 
2bf73b3
d564c4d
 
 
 
 
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": 0.004011794676348464,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.023589352696929e-05,
      "eval_loss": NaN,
      "eval_runtime": 358.6886,
      "eval_samples_per_second": 14.631,
      "eval_steps_per_second": 7.316,
      "step": 1
    },
    {
      "epoch": 0.00040117946763484647,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0008023589352696929,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0008023589352696929,
      "eval_loss": NaN,
      "eval_runtime": 304.5922,
      "eval_samples_per_second": 17.23,
      "eval_steps_per_second": 8.615,
      "step": 10
    },
    {
      "epoch": 0.0012035384029045392,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0016047178705393859,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0016047178705393859,
      "eval_loss": NaN,
      "eval_runtime": 212.5377,
      "eval_samples_per_second": 24.692,
      "eval_steps_per_second": 12.346,
      "step": 20
    },
    {
      "epoch": 0.002005897338174232,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0024070768058090785,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0024070768058090785,
      "eval_loss": NaN,
      "eval_runtime": 140.4237,
      "eval_samples_per_second": 37.373,
      "eval_steps_per_second": 18.686,
      "step": 30
    },
    {
      "epoch": 0.0028082562734439253,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0032094357410787718,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0032094357410787718,
      "eval_loss": NaN,
      "eval_runtime": 129.5231,
      "eval_samples_per_second": 40.518,
      "eval_steps_per_second": 20.259,
      "step": 40
    },
    {
      "epoch": 0.003610615208713618,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.004011794676348464,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.004011794676348464,
      "eval_loss": NaN,
      "eval_runtime": 130.1808,
      "eval_samples_per_second": 40.313,
      "eval_steps_per_second": 20.157,
      "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": 1621491292569600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}