Hugging Face's logo

kk-aivio
/
64396017-4591-484f-b8c2-3d46714daea1

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
64396017-4591-484f-b8c2-3d46714daea1
File size: 2,962 Bytes 
b18ceeb
 
 
e499a3f
b18ceeb
e499a3f
b18ceeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9c4672a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dae2f9b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e499a3f
 
 
 
 
 
 
b18ceeb
 
 
 
 
 
 
 
 
 
 
 
 
 
e499a3f
b18ceeb
 
 
 
e499a3f
b18ceeb
 
 
 
 
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": 0.0071581961345740875,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007158196134574087,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0007158196134574087,
      "eval_loss": NaN,
      "eval_runtime": 17.4938,
      "eval_samples_per_second": 33.669,
      "eval_steps_per_second": 16.863,
      "step": 1
    },
    {
      "epoch": 0.0014316392269148174,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0021474588403722263,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0021474588403722263,
      "eval_loss": NaN,
      "eval_runtime": 15.4515,
      "eval_samples_per_second": 38.119,
      "eval_steps_per_second": 19.092,
      "step": 3
    },
    {
      "epoch": 0.002863278453829635,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0035790980672870437,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.004294917680744453,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.004294917680744453,
      "eval_loss": NaN,
      "eval_runtime": 15.6777,
      "eval_samples_per_second": 37.569,
      "eval_steps_per_second": 18.816,
      "step": 6
    },
    {
      "epoch": 0.005010737294201861,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00572655690765927,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.006442376521116679,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.006442376521116679,
      "eval_loss": NaN,
      "eval_runtime": 15.5926,
      "eval_samples_per_second": 37.774,
      "eval_steps_per_second": 18.919,
      "step": 9
    },
    {
      "epoch": 0.0071581961345740875,
      "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": 648596517027840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}