Hugging Face's logo

dimasik1987
/
046af7c5-985e-4829-8a22-5ec259958bab

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
046af7c5-985e-4829-8a22-5ec259958bab
File size: 3,235 Bytes 
6f7e15a
 
 
9c74701
6f7e15a
9c74701
6f7e15a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e24fa15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9c74701
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f7e15a
 
 
 
 
 
 
 
 
 
 
 
 
 
9c74701
6f7e15a
 
 
 
9c74701
6f7e15a
 
 
 
 
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": 0.06666666666666667,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022222222222222222,
      "eval_loss": 13.001398086547852,
      "eval_runtime": 5.8352,
      "eval_samples_per_second": 32.561,
      "eval_steps_per_second": 16.28,
      "step": 1
    },
    {
      "epoch": 0.006666666666666667,
      "grad_norm": 34.67473602294922,
      "learning_rate": 6e-05,
      "loss": 12.9449,
      "step": 3
    },
    {
      "epoch": 0.013333333333333334,
      "grad_norm": 25.128501892089844,
      "learning_rate": 0.00012,
      "loss": 12.6226,
      "step": 6
    },
    {
      "epoch": 0.017777777777777778,
      "eval_loss": 11.73355484008789,
      "eval_runtime": 5.8384,
      "eval_samples_per_second": 32.543,
      "eval_steps_per_second": 16.272,
      "step": 8
    },
    {
      "epoch": 0.02,
      "grad_norm": 14.999642372131348,
      "learning_rate": 0.00018,
      "loss": 11.906,
      "step": 9
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 7.970412254333496,
      "learning_rate": 0.00019510565162951537,
      "loss": 11.296,
      "step": 12
    },
    {
      "epoch": 0.03333333333333333,
      "grad_norm": 9.736292839050293,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.8208,
      "step": 15
    },
    {
      "epoch": 0.035555555555555556,
      "eval_loss": 10.455474853515625,
      "eval_runtime": 5.9526,
      "eval_samples_per_second": 31.919,
      "eval_steps_per_second": 15.959,
      "step": 16
    },
    {
      "epoch": 0.04,
      "grad_norm": 5.3760600090026855,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.4623,
      "step": 18
    },
    {
      "epoch": 0.04666666666666667,
      "grad_norm": 3.8492417335510254,
      "learning_rate": 8.435655349597689e-05,
      "loss": 10.1835,
      "step": 21
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 3.4258408546447754,
      "learning_rate": 4.12214747707527e-05,
      "loss": 10.0263,
      "step": 24
    },
    {
      "epoch": 0.05333333333333334,
      "eval_loss": 9.956049919128418,
      "eval_runtime": 5.8907,
      "eval_samples_per_second": 32.254,
      "eval_steps_per_second": 16.127,
      "step": 24
    },
    {
      "epoch": 0.06,
      "grad_norm": 3.2378265857696533,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 9.9196,
      "step": 27
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 3.3411707878112793,
      "learning_rate": 0.0,
      "loss": 9.8884,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7907297722368.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}