Hugging Face's logo

kostiantynk-out
/
ff76a77c-c397-46a4-ad6b-f51acccccfb9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
ff76a77c-c397-46a4-ad6b-f51acccccfb9
File size: 2,977 Bytes 
c3b16b2
 
 
2e76f7c
c3b16b2
2e76f7c
c3b16b2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3daa394
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
797cf26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2e76f7c
 
 
 
 
 
 
c3b16b2
 
 
 
 
 
 
 
 
 
 
 
 
 
2e76f7c
c3b16b2
 
 
 
2e76f7c
c3b16b2
 
 
 
 
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": 0.0006501633535425775,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.501633535425775e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 6.501633535425775e-05,
      "eval_loss": NaN,
      "eval_runtime": 518.0201,
      "eval_samples_per_second": 12.503,
      "eval_steps_per_second": 6.253,
      "step": 1
    },
    {
      "epoch": 0.0001300326707085155,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00019504900606277329,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00019504900606277329,
      "eval_loss": NaN,
      "eval_runtime": 516.4542,
      "eval_samples_per_second": 12.541,
      "eval_steps_per_second": 6.272,
      "step": 3
    },
    {
      "epoch": 0.000260065341417031,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00032508167677128876,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00039009801212554657,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00039009801212554657,
      "eval_loss": NaN,
      "eval_runtime": 516.4397,
      "eval_samples_per_second": 12.542,
      "eval_steps_per_second": 6.272,
      "step": 6
    },
    {
      "epoch": 0.0004551143474798043,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.000520130682834062,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 1.9925,
      "step": 8
    },
    {
      "epoch": 0.0005851470181883198,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0005851470181883198,
      "eval_loss": NaN,
      "eval_runtime": 516.3827,
      "eval_samples_per_second": 12.543,
      "eval_steps_per_second": 6.272,
      "step": 9
    },
    {
      "epoch": 0.0006501633535425775,
      "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": 5160473645285376.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}