Hugging Face's logo

kk-aivio
/
f4d4e27f-01aa-48f5-b2a7-faaf6cf8f49d

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
f4d4e27f-01aa-48f5-b2a7-faaf6cf8f49d
File size: 3,207 Bytes 
9834b70
 
 
1658df1
9834b70
1658df1
9834b70
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
be36774
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48b69e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1658df1
 
 
 
 
 
 
9834b70
 
 
 
 
 
 
 
 
 
 
 
 
 
1658df1
9834b70
 
 
 
1658df1
9834b70
 
 
 
 
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": 0.0010375865736297373,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010375865736297373,
      "grad_norm": 1.1433764696121216,
      "learning_rate": 2e-05,
      "loss": 2.1367,
      "step": 1
    },
    {
      "epoch": 0.00010375865736297373,
      "eval_loss": 2.0775890350341797,
      "eval_runtime": 82.1221,
      "eval_samples_per_second": 49.414,
      "eval_steps_per_second": 24.707,
      "step": 1
    },
    {
      "epoch": 0.00020751731472594745,
      "grad_norm": 1.1961828470230103,
      "learning_rate": 4e-05,
      "loss": 2.0164,
      "step": 2
    },
    {
      "epoch": 0.00031127597208892115,
      "grad_norm": 1.2340922355651855,
      "learning_rate": 6e-05,
      "loss": 2.1282,
      "step": 3
    },
    {
      "epoch": 0.00031127597208892115,
      "eval_loss": 2.074273109436035,
      "eval_runtime": 81.5877,
      "eval_samples_per_second": 49.738,
      "eval_steps_per_second": 24.869,
      "step": 3
    },
    {
      "epoch": 0.0004150346294518949,
      "grad_norm": 1.0359632968902588,
      "learning_rate": 8e-05,
      "loss": 1.933,
      "step": 4
    },
    {
      "epoch": 0.0005187932868148687,
      "grad_norm": 1.3015316724777222,
      "learning_rate": 0.0001,
      "loss": 2.0539,
      "step": 5
    },
    {
      "epoch": 0.0006225519441778423,
      "grad_norm": 1.0627121925354004,
      "learning_rate": 0.00012,
      "loss": 2.1394,
      "step": 6
    },
    {
      "epoch": 0.0006225519441778423,
      "eval_loss": 2.040466070175171,
      "eval_runtime": 81.4488,
      "eval_samples_per_second": 49.823,
      "eval_steps_per_second": 24.911,
      "step": 6
    },
    {
      "epoch": 0.000726310601540816,
      "grad_norm": 1.152351975440979,
      "learning_rate": 0.00014,
      "loss": 1.9755,
      "step": 7
    },
    {
      "epoch": 0.0008300692589037898,
      "grad_norm": 1.0372527837753296,
      "learning_rate": 0.00016,
      "loss": 1.7394,
      "step": 8
    },
    {
      "epoch": 0.0009338279162667636,
      "grad_norm": 1.0806152820587158,
      "learning_rate": 0.00018,
      "loss": 1.8651,
      "step": 9
    },
    {
      "epoch": 0.0009338279162667636,
      "eval_loss": 1.97881281375885,
      "eval_runtime": 81.6516,
      "eval_samples_per_second": 49.699,
      "eval_steps_per_second": 24.849,
      "step": 9
    },
    {
      "epoch": 0.0010375865736297373,
      "grad_norm": 0.955893337726593,
      "learning_rate": 0.0002,
      "loss": 1.7457,
      "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": 126879383420928.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}