Hugging Face's logo

dzanbek
/
69e69505-241c-4d0a-8917-71f936e3b1df

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
69e69505-241c-4d0a-8917-71f936e3b1df
File size: 3,039 Bytes 
36942a7
 
 
9241387
36942a7
9241387
36942a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3c0de85
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9241387
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36942a7
 
 
 
 
 
 
 
 
 
 
 
 
 
9241387
36942a7
 
 
 
9241387
36942a7
 
 
 
 
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": 0.09181331293037491,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00306044376434583,
      "eval_loss": NaN,
      "eval_runtime": 17.0319,
      "eval_samples_per_second": 8.102,
      "eval_steps_per_second": 4.051,
      "step": 1
    },
    {
      "epoch": 0.009181331293037491,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.018362662586074982,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.02448355011476664,
      "eval_loss": NaN,
      "eval_runtime": 16.1312,
      "eval_samples_per_second": 8.555,
      "eval_steps_per_second": 4.277,
      "step": 8
    },
    {
      "epoch": 0.02754399387911247,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.036725325172149964,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.045906656465187455,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.04896710022953328,
      "eval_loss": NaN,
      "eval_runtime": 16.2896,
      "eval_samples_per_second": 8.472,
      "eval_steps_per_second": 4.236,
      "step": 16
    },
    {
      "epoch": 0.05508798775822494,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.06426931905126243,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.07345065034429993,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.07345065034429993,
      "eval_loss": NaN,
      "eval_runtime": 16.3503,
      "eval_samples_per_second": 8.44,
      "eval_steps_per_second": 4.22,
      "step": 24
    },
    {
      "epoch": 0.08263198163733741,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.09181331293037491,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "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": 1.0128602129498112e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}