Hugging Face's logo

kk-aivio
/
2a8bb866-0d1d-48c6-a279-c8d2380e04e8

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
2a8bb866-0d1d-48c6-a279-c8d2380e04e8
File size: 2,968 Bytes 
8b7c587
 
 
6833172
8b7c587
6833172
8b7c587
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84d04db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dc5f60a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6833172
 
 
 
 
 
 
8b7c587
 
 
 
 
 
 
 
 
 
 
 
 
 
6833172
8b7c587
 
 
 
6833172
8b7c587
 
 
 
 
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": 0.0016256197675363732,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001625619767536373,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0001625619767536373,
      "eval_loss": NaN,
      "eval_runtime": 113.9994,
      "eval_samples_per_second": 22.728,
      "eval_steps_per_second": 11.368,
      "step": 1
    },
    {
      "epoch": 0.0003251239535072746,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.000487685930260912,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.000487685930260912,
      "eval_loss": NaN,
      "eval_runtime": 112.0424,
      "eval_samples_per_second": 23.125,
      "eval_steps_per_second": 11.567,
      "step": 3
    },
    {
      "epoch": 0.0006502479070145493,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0008128098837681866,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.000975371860521824,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.000975371860521824,
      "eval_loss": NaN,
      "eval_runtime": 112.2149,
      "eval_samples_per_second": 23.09,
      "eval_steps_per_second": 11.549,
      "step": 6
    },
    {
      "epoch": 0.0011379338372754612,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0013004958140290985,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.001463057790782736,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.001463057790782736,
      "eval_loss": NaN,
      "eval_runtime": 112.0886,
      "eval_samples_per_second": 23.116,
      "eval_steps_per_second": 11.562,
      "step": 9
    },
    {
      "epoch": 0.0016256197675363732,
      "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": 2875349476048896.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}