Hugging Face's logo

dzanbek
/
3b71b44e-7e35-4d0c-add1-9c6d1e59e39a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
3b71b44e-7e35-4d0c-add1-9c6d1e59e39a
File size: 3,251 Bytes 
d9aac89
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.17777777777777778,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005925925925925926,
      "eval_loss": 15.121915817260742,
      "eval_runtime": 9.8278,
      "eval_samples_per_second": 7.224,
      "eval_steps_per_second": 3.663,
      "step": 1
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 13.326007843017578,
      "learning_rate": 6e-05,
      "loss": 15.0493,
      "step": 3
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 23.55678939819336,
      "learning_rate": 0.00012,
      "loss": 13.5722,
      "step": 6
    },
    {
      "epoch": 0.047407407407407405,
      "eval_loss": 7.749727725982666,
      "eval_runtime": 9.0799,
      "eval_samples_per_second": 7.819,
      "eval_steps_per_second": 3.965,
      "step": 8
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 26.799129486083984,
      "learning_rate": 0.00018,
      "loss": 9.4622,
      "step": 9
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 9.160043716430664,
      "learning_rate": 0.00019510565162951537,
      "loss": 5.7567,
      "step": 12
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 6.911787509918213,
      "learning_rate": 0.00017071067811865476,
      "loss": 4.5565,
      "step": 15
    },
    {
      "epoch": 0.09481481481481481,
      "eval_loss": 4.17349910736084,
      "eval_runtime": 9.0339,
      "eval_samples_per_second": 7.859,
      "eval_steps_per_second": 3.985,
      "step": 16
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 5.684746265411377,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.1979,
      "step": 18
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 7.674033164978027,
      "learning_rate": 8.435655349597689e-05,
      "loss": 4.2213,
      "step": 21
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 7.858697414398193,
      "learning_rate": 4.12214747707527e-05,
      "loss": 4.0256,
      "step": 24
    },
    {
      "epoch": 0.14222222222222222,
      "eval_loss": 3.9667611122131348,
      "eval_runtime": 9.1522,
      "eval_samples_per_second": 7.758,
      "eval_steps_per_second": 3.933,
      "step": 24
    },
    {
      "epoch": 0.16,
      "grad_norm": 6.60933256149292,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.9633,
      "step": 27
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 6.702687740325928,
      "learning_rate": 0.0,
      "loss": 3.9846,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}