Hugging Face's logo

kk-aivio
/
6421ca1c-5cdc-4037-9260-fedc225e1de7

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
6421ca1c-5cdc-4037-9260-fedc225e1de7
File size: 2,973 Bytes 
fb599a1
 
 
322a19b
fb599a1
322a19b
fb599a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d65f2b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
da7daa5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
322a19b
 
 
 
 
 
 
fb599a1
 
 
 
 
 
 
 
 
 
 
 
 
 
322a19b
fb599a1
 
 
 
322a19b
fb599a1
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015435671837616732,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015435671837616733,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00015435671837616733,
      "eval_loss": NaN,
      "eval_runtime": 151.0933,
      "eval_samples_per_second": 18.055,
      "eval_steps_per_second": 9.028,
      "step": 1
    },
    {
      "epoch": 0.00030871343675233467,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00046307015512850195,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00046307015512850195,
      "eval_loss": NaN,
      "eval_runtime": 149.908,
      "eval_samples_per_second": 18.198,
      "eval_steps_per_second": 9.099,
      "step": 3
    },
    {
      "epoch": 0.0006174268735046693,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0007717835918808366,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0009261403102570039,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0009261403102570039,
      "eval_loss": NaN,
      "eval_runtime": 94.272,
      "eval_samples_per_second": 28.938,
      "eval_steps_per_second": 14.469,
      "step": 6
    },
    {
      "epoch": 0.0010804970286331713,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0012348537470093387,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0013892104653855058,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0013892104653855058,
      "eval_loss": NaN,
      "eval_runtime": 86.9665,
      "eval_samples_per_second": 31.368,
      "eval_steps_per_second": 15.684,
      "step": 9
    },
    {
      "epoch": 0.0015435671837616732,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 908428792823808.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}