Hugging Face's logo

duyphu
/
172d238a-6806-4501-be69-252347e60e83

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
172d238a-6806-4501-be69-252347e60e83
File size: 3,486 Bytes 
3d8e3c9
 
 
bd8c24e
814d92e
bd8c24e
3d8e3c9
 
 
 
 
 
 
814d92e
 
 
3d8e3c9
814d92e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7e3c491
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f26a961
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bd8c24e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3d8e3c9
 
 
814d92e
3d8e3c9
 
814d92e
3d8e3c9
 
 
 
 
 
 
bd8c24e
3d8e3c9
 
 
 
bd8c24e
3d8e3c9
 
 
 
 
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": 0.0010926155577529269,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.1852311155058537e-05,
      "eval_loss": NaN,
      "eval_runtime": 680.7093,
      "eval_samples_per_second": 28.307,
      "eval_steps_per_second": 14.154,
      "step": 1
    },
    {
      "epoch": 0.00010926155577529269,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00021852311155058537,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00021852311155058537,
      "eval_loss": NaN,
      "eval_runtime": 675.8531,
      "eval_samples_per_second": 28.511,
      "eval_steps_per_second": 14.256,
      "step": 10
    },
    {
      "epoch": 0.00032778466732587806,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00043704622310117075,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.00043704622310117075,
      "eval_loss": NaN,
      "eval_runtime": 675.8123,
      "eval_samples_per_second": 28.512,
      "eval_steps_per_second": 14.257,
      "step": 20
    },
    {
      "epoch": 0.0005463077788764634,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0006555693346517561,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0006555693346517561,
      "eval_loss": NaN,
      "eval_runtime": 674.8796,
      "eval_samples_per_second": 28.552,
      "eval_steps_per_second": 14.277,
      "step": 30
    },
    {
      "epoch": 0.0007648308904270488,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0008740924462023415,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0008740924462023415,
      "eval_loss": NaN,
      "eval_runtime": 674.2638,
      "eval_samples_per_second": 28.578,
      "eval_steps_per_second": 14.29,
      "step": 40
    },
    {
      "epoch": 0.000983354001977634,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0010926155577529269,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0010926155577529269,
      "eval_loss": NaN,
      "eval_runtime": 672.0205,
      "eval_samples_per_second": 28.673,
      "eval_steps_per_second": 14.337,
      "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": 549810661490688.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}