Hugging Face's logo

tuanna08go
/
c90b72b5-1d4e-41bb-b2f3-a7ede240ff67

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
c90b72b5-1d4e-41bb-b2f3-a7ede240ff67
File size: 2,729 Bytes 
305ae86
 
 
c869af1
c5eba45
c869af1
305ae86
 
 
 
 
 
 
c5eba45
 
 
305ae86
c5eba45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
358ef0f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
da0d3d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c869af1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
305ae86
 
 
c5eba45
305ae86
 
c5eba45
305ae86
 
 
 
 
 
 
c869af1
305ae86
 
 
 
c869af1
305ae86
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.039826753621745405,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007965350724349081,
      "eval_loss": NaN,
      "eval_runtime": 257.2896,
      "eval_samples_per_second": 32.873,
      "eval_steps_per_second": 4.112,
      "step": 1
    },
    {
      "epoch": 0.007965350724349082,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.007965350724349082,
      "eval_loss": NaN,
      "eval_runtime": 255.6607,
      "eval_samples_per_second": 33.083,
      "eval_steps_per_second": 4.138,
      "step": 10
    },
    {
      "epoch": 0.015930701448698164,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.015930701448698164,
      "eval_loss": NaN,
      "eval_runtime": 255.6473,
      "eval_samples_per_second": 33.085,
      "eval_steps_per_second": 4.139,
      "step": 20
    },
    {
      "epoch": 0.023896052173047244,
      "grad_norm": NaN,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.023896052173047244,
      "eval_loss": NaN,
      "eval_runtime": 255.6304,
      "eval_samples_per_second": 33.087,
      "eval_steps_per_second": 4.139,
      "step": 30
    },
    {
      "epoch": 0.03186140289739633,
      "grad_norm": NaN,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.03186140289739633,
      "eval_loss": NaN,
      "eval_runtime": 255.4691,
      "eval_samples_per_second": 33.108,
      "eval_steps_per_second": 4.141,
      "step": 40
    },
    {
      "epoch": 0.039826753621745405,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.039826753621745405,
      "eval_loss": NaN,
      "eval_runtime": 255.2592,
      "eval_samples_per_second": 33.135,
      "eval_steps_per_second": 4.145,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "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": 4.202905430340403e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}