Hugging Face's logo

kk-aivio
/
736e19cf-58e0-4bd4-a4dc-220878dc59de

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
736e19cf-58e0-4bd4-a4dc-220878dc59de
File size: 2,955 Bytes 
05cb6d5
 
 
4f685ec
05cb6d5
4f685ec
05cb6d5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13ead34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f194fd6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4f685ec
 
 
 
 
 
 
05cb6d5
 
 
 
 
 
 
 
 
 
 
 
 
 
4f685ec
05cb6d5
 
 
 
4f685ec
05cb6d5
 
 
 
 
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": 0.004921259842519685,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004921259842519685,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0004921259842519685,
      "eval_loss": NaN,
      "eval_runtime": 6.1744,
      "eval_samples_per_second": 138.637,
      "eval_steps_per_second": 69.319,
      "step": 1
    },
    {
      "epoch": 0.000984251968503937,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0014763779527559055,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0014763779527559055,
      "eval_loss": NaN,
      "eval_runtime": 5.2274,
      "eval_samples_per_second": 163.753,
      "eval_steps_per_second": 81.876,
      "step": 3
    },
    {
      "epoch": 0.001968503937007874,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0024606299212598425,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.002952755905511811,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.002952755905511811,
      "eval_loss": NaN,
      "eval_runtime": 5.2696,
      "eval_samples_per_second": 162.44,
      "eval_steps_per_second": 81.22,
      "step": 6
    },
    {
      "epoch": 0.0034448818897637795,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.003937007874015748,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0044291338582677165,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0044291338582677165,
      "eval_loss": NaN,
      "eval_runtime": 5.2654,
      "eval_samples_per_second": 162.57,
      "eval_steps_per_second": 81.285,
      "step": 9
    },
    {
      "epoch": 0.004921259842519685,
      "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": 1740963840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}