Hugging Face's logo

kokovova
/
7d8264c0-1221-4895-93fd-59d0aeba6a21

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
7d8264c0-1221-4895-93fd-59d0aeba6a21
File size: 3,300 Bytes 
dbe2faf
 
 
22eaf81
dbe2faf
22eaf81
dbe2faf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65240a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22eaf81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dbe2faf
 
 
 
 
 
 
 
 
 
 
 
 
 
22eaf81
dbe2faf
 
 
 
22eaf81
dbe2faf
 
 
 
 
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": 0.00487904045537711,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016263468184590365,
      "eval_loss": 0.6653284430503845,
      "eval_runtime": 324.3776,
      "eval_samples_per_second": 7.981,
      "eval_steps_per_second": 3.992,
      "step": 1
    },
    {
      "epoch": 0.0004879040455377109,
      "grad_norm": 0.656542956829071,
      "learning_rate": 6e-05,
      "loss": 2.8969,
      "step": 3
    },
    {
      "epoch": 0.0009758080910754218,
      "grad_norm": 0.7154726982116699,
      "learning_rate": 0.00012,
      "loss": 2.6609,
      "step": 6
    },
    {
      "epoch": 0.0013010774547672292,
      "eval_loss": 0.6452193260192871,
      "eval_runtime": 324.1104,
      "eval_samples_per_second": 7.988,
      "eval_steps_per_second": 3.996,
      "step": 8
    },
    {
      "epoch": 0.0014637121366131327,
      "grad_norm": 0.733124315738678,
      "learning_rate": 0.00018,
      "loss": 2.5338,
      "step": 9
    },
    {
      "epoch": 0.0019516161821508437,
      "grad_norm": 1.2633097171783447,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.7224,
      "step": 12
    },
    {
      "epoch": 0.002439520227688555,
      "grad_norm": 0.614086389541626,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.7872,
      "step": 15
    },
    {
      "epoch": 0.0026021549095344584,
      "eval_loss": 0.6183476448059082,
      "eval_runtime": 323.9576,
      "eval_samples_per_second": 7.992,
      "eval_steps_per_second": 3.997,
      "step": 16
    },
    {
      "epoch": 0.0029274242732262655,
      "grad_norm": 0.567788302898407,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.1966,
      "step": 18
    },
    {
      "epoch": 0.0034153283187639766,
      "grad_norm": 0.8114487528800964,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.3838,
      "step": 21
    },
    {
      "epoch": 0.0039032323643016873,
      "grad_norm": 0.5942605137825012,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.5547,
      "step": 24
    },
    {
      "epoch": 0.0039032323643016873,
      "eval_loss": 0.6068182587623596,
      "eval_runtime": 324.2749,
      "eval_samples_per_second": 7.984,
      "eval_steps_per_second": 3.994,
      "step": 24
    },
    {
      "epoch": 0.004391136409839398,
      "grad_norm": 0.7476170063018799,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.3127,
      "step": 27
    },
    {
      "epoch": 0.00487904045537711,
      "grad_norm": 0.6413885354995728,
      "learning_rate": 0.0,
      "loss": 2.3178,
      "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": 2.85652348305408e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}