Hugging Face's logo

chauhoang
/
f29a34a9-df38-a4f5-7e15-035109178bf7

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
f29a34a9-df38-a4f5-7e15-035109178bf7
File size: 3,488 Bytes 
e7c2371
 
 
89f30b4
504bf5e
89f30b4
e7c2371
 
 
 
 
 
 
504bf5e
 
 
e7c2371
504bf5e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c3ad35d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5e76dfa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89f30b4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e7c2371
 
 
504bf5e
e7c2371
 
504bf5e
e7c2371
 
 
 
 
 
 
89f30b4
e7c2371
 
 
 
89f30b4
e7c2371
 
 
 
 
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": 0.0004921465710918026,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.842931421836052e-06,
      "eval_loss": NaN,
      "eval_runtime": 2849.3854,
      "eval_samples_per_second": 15.013,
      "eval_steps_per_second": 7.507,
      "step": 1
    },
    {
      "epoch": 4.9214657109180254e-05,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 9.842931421836051e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 9.842931421836051e-05,
      "eval_loss": NaN,
      "eval_runtime": 2850.4135,
      "eval_samples_per_second": 15.008,
      "eval_steps_per_second": 7.504,
      "step": 10
    },
    {
      "epoch": 0.00014764397132754076,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00019685862843672102,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.00019685862843672102,
      "eval_loss": NaN,
      "eval_runtime": 2856.3579,
      "eval_samples_per_second": 14.976,
      "eval_steps_per_second": 7.488,
      "step": 20
    },
    {
      "epoch": 0.0002460732855459013,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0002952879426550815,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0002952879426550815,
      "eval_loss": NaN,
      "eval_runtime": 2845.9096,
      "eval_samples_per_second": 15.031,
      "eval_steps_per_second": 7.516,
      "step": 30
    },
    {
      "epoch": 0.0003445025997642618,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.00039371725687344203,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.00039371725687344203,
      "eval_loss": NaN,
      "eval_runtime": 2843.0673,
      "eval_samples_per_second": 15.046,
      "eval_steps_per_second": 7.523,
      "step": 40
    },
    {
      "epoch": 0.0004429319139826223,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0004921465710918026,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0004921465710918026,
      "eval_loss": NaN,
      "eval_runtime": 2837.9778,
      "eval_samples_per_second": 15.073,
      "eval_steps_per_second": 7.537,
      "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": 9671630055800832.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}