Hugging Face's logo

kk-aivio
/
7d56fc0f-43d9-4556-907d-156f0a46ddbc

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7d56fc0f-43d9-4556-907d-156f0a46ddbc
File size: 3,223 Bytes 
7e199fa
 
 
9687dc3
7e199fa
9687dc3
7e199fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c0e153d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
827f765
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9687dc3
 
 
 
 
 
 
7e199fa
 
 
 
 
 
 
 
 
 
 
 
 
 
9687dc3
7e199fa
 
 
 
9687dc3
7e199fa
 
 
 
 
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": 0.00030028677386904494,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.0028677386904494e-05,
      "grad_norm": 0.2012191116809845,
      "learning_rate": 2e-05,
      "loss": 0.3476,
      "step": 1
    },
    {
      "epoch": 3.0028677386904494e-05,
      "eval_loss": 0.3906751573085785,
      "eval_runtime": 1045.4932,
      "eval_samples_per_second": 13.412,
      "eval_steps_per_second": 6.706,
      "step": 1
    },
    {
      "epoch": 6.005735477380899e-05,
      "grad_norm": 0.3361751139163971,
      "learning_rate": 4e-05,
      "loss": 0.5332,
      "step": 2
    },
    {
      "epoch": 9.008603216071348e-05,
      "grad_norm": 0.16664037108421326,
      "learning_rate": 6e-05,
      "loss": 0.282,
      "step": 3
    },
    {
      "epoch": 9.008603216071348e-05,
      "eval_loss": 0.38874995708465576,
      "eval_runtime": 1044.056,
      "eval_samples_per_second": 13.43,
      "eval_steps_per_second": 6.715,
      "step": 3
    },
    {
      "epoch": 0.00012011470954761798,
      "grad_norm": 0.283048540353775,
      "learning_rate": 8e-05,
      "loss": 0.3772,
      "step": 4
    },
    {
      "epoch": 0.00015014338693452247,
      "grad_norm": 0.6533939838409424,
      "learning_rate": 0.0001,
      "loss": 0.3009,
      "step": 5
    },
    {
      "epoch": 0.00018017206432142696,
      "grad_norm": 0.32610440254211426,
      "learning_rate": 0.00012,
      "loss": 0.4086,
      "step": 6
    },
    {
      "epoch": 0.00018017206432142696,
      "eval_loss": 0.3601542115211487,
      "eval_runtime": 1044.8592,
      "eval_samples_per_second": 13.42,
      "eval_steps_per_second": 6.71,
      "step": 6
    },
    {
      "epoch": 0.00021020074170833146,
      "grad_norm": 0.5947815179824829,
      "learning_rate": 0.00014,
      "loss": 0.3591,
      "step": 7
    },
    {
      "epoch": 0.00024022941909523595,
      "grad_norm": 0.3068762719631195,
      "learning_rate": 0.00016,
      "loss": 0.2623,
      "step": 8
    },
    {
      "epoch": 0.0002702580964821404,
      "grad_norm": 0.5450010895729065,
      "learning_rate": 0.00018,
      "loss": 0.2086,
      "step": 9
    },
    {
      "epoch": 0.0002702580964821404,
      "eval_loss": 0.23924924433231354,
      "eval_runtime": 1044.6169,
      "eval_samples_per_second": 13.423,
      "eval_steps_per_second": 6.712,
      "step": 9
    },
    {
      "epoch": 0.00030028677386904494,
      "grad_norm": 0.4637574851512909,
      "learning_rate": 0.0002,
      "loss": 0.3159,
      "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": 5540857302220800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}