Hugging Face's logo

duyphu
/
f095bd87-5a84-4fc9-bac9-d2b59b5ca171

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
f095bd87-5a84-4fc9-bac9-d2b59b5ca171
File size: 3,438 Bytes 
66d1de1
 
 
ce39f7b
58b8330
ce39f7b
66d1de1
 
 
 
 
 
 
58b8330
 
 
66d1de1
58b8330
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
903f7d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a959c71
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce39f7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66d1de1
 
 
58b8330
66d1de1
 
58b8330
66d1de1
 
 
 
 
 
 
ce39f7b
66d1de1
 
 
 
ce39f7b
66d1de1
 
 
 
 
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": 0.0249003984063745,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00049800796812749,
      "eval_loss": NaN,
      "eval_runtime": 58.1469,
      "eval_samples_per_second": 14.549,
      "eval_steps_per_second": 7.275,
      "step": 1
    },
    {
      "epoch": 0.00249003984063745,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0049800796812749,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0049800796812749,
      "eval_loss": NaN,
      "eval_runtime": 57.1906,
      "eval_samples_per_second": 14.793,
      "eval_steps_per_second": 7.396,
      "step": 10
    },
    {
      "epoch": 0.007470119521912351,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0099601593625498,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0099601593625498,
      "eval_loss": NaN,
      "eval_runtime": 57.1667,
      "eval_samples_per_second": 14.799,
      "eval_steps_per_second": 7.399,
      "step": 20
    },
    {
      "epoch": 0.01245019920318725,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.014940239043824702,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.014940239043824702,
      "eval_loss": NaN,
      "eval_runtime": 57.1546,
      "eval_samples_per_second": 14.802,
      "eval_steps_per_second": 7.401,
      "step": 30
    },
    {
      "epoch": 0.01743027888446215,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.4787,
      "step": 35
    },
    {
      "epoch": 0.0199203187250996,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0199203187250996,
      "eval_loss": NaN,
      "eval_runtime": 57.1473,
      "eval_samples_per_second": 14.804,
      "eval_steps_per_second": 7.402,
      "step": 40
    },
    {
      "epoch": 0.022410358565737053,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0249003984063745,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0249003984063745,
      "eval_loss": NaN,
      "eval_runtime": 57.0746,
      "eval_samples_per_second": 14.823,
      "eval_steps_per_second": 7.411,
      "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": 1.0368684474236928e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}