Hugging Face's logo

duyphu
/
660f867d-baee-4abd-9487-c2ad0474acd4

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
660f867d-baee-4abd-9487-c2ad0474acd4
File size: 3,453 Bytes 
47a0081
 
 
4ad2b1a
68a16c7
4ad2b1a
47a0081
 
 
 
 
 
 
68a16c7
 
 
47a0081
68a16c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50a4b83
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
263e801
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4ad2b1a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47a0081
 
 
68a16c7
47a0081
 
68a16c7
47a0081
 
 
 
 
 
 
4ad2b1a
47a0081
 
 
 
4ad2b1a
47a0081
 
 
 
 
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": 0.04684937924572499,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009369875849144999,
      "eval_loss": NaN,
      "eval_runtime": 17.6298,
      "eval_samples_per_second": 25.525,
      "eval_steps_per_second": 12.762,
      "step": 1
    },
    {
      "epoch": 0.004684937924572499,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.009369875849144999,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.009369875849144999,
      "eval_loss": NaN,
      "eval_runtime": 16.9764,
      "eval_samples_per_second": 26.507,
      "eval_steps_per_second": 13.254,
      "step": 10
    },
    {
      "epoch": 0.014054813773717497,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.018739751698289998,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.018739751698289998,
      "eval_loss": NaN,
      "eval_runtime": 17.0285,
      "eval_samples_per_second": 26.426,
      "eval_steps_per_second": 13.213,
      "step": 20
    },
    {
      "epoch": 0.023424689622862496,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.028109627547434995,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.028109627547434995,
      "eval_loss": NaN,
      "eval_runtime": 16.8511,
      "eval_samples_per_second": 26.704,
      "eval_steps_per_second": 13.352,
      "step": 30
    },
    {
      "epoch": 0.03279456547200749,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.037479503396579995,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.037479503396579995,
      "eval_loss": NaN,
      "eval_runtime": 16.9617,
      "eval_samples_per_second": 26.53,
      "eval_steps_per_second": 13.265,
      "step": 40
    },
    {
      "epoch": 0.0421644413211525,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.04684937924572499,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.04684937924572499,
      "eval_loss": NaN,
      "eval_runtime": 16.8986,
      "eval_samples_per_second": 26.629,
      "eval_steps_per_second": 13.315,
      "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
}