Hugging Face's logo

infogep
/
3e928d22-a0e1-4be3-8660-44a541808eac

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
3e928d22-a0e1-4be3-8660-44a541808eac
File size: 3,129 Bytes 
f4e57bc
 
 
08e8026
f4e57bc
08e8026
f4e57bc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
08e8026
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f4e57bc
 
 
 
 
 
 
 
 
 
 
 
 
 
08e8026
f4e57bc
 
 
 
 
 
 
 
 
 
 
 
 
08e8026
f4e57bc
 
 
 
 
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
137
 
{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.05393743257820928,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005393743257820927,
      "eval_loss": NaN,
      "eval_runtime": 14.1111,
      "eval_samples_per_second": 55.347,
      "eval_steps_per_second": 13.89,
      "step": 1
    },
    {
      "epoch": 0.005393743257820928,
      "grad_norm": NaN,
      "learning_rate": 5.05e-06,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.010787486515641856,
      "grad_norm": NaN,
      "learning_rate": 1.01e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.016181229773462782,
      "grad_norm": NaN,
      "learning_rate": 9.323076923076924e-06,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.021574973031283712,
      "grad_norm": NaN,
      "learning_rate": 8.546153846153847e-06,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.02696871628910464,
      "grad_norm": NaN,
      "learning_rate": 7.76923076923077e-06,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.02696871628910464,
      "eval_loss": NaN,
      "eval_runtime": 13.1829,
      "eval_samples_per_second": 59.243,
      "eval_steps_per_second": 14.868,
      "step": 50
    },
    {
      "epoch": 0.032362459546925564,
      "grad_norm": NaN,
      "learning_rate": 6.992307692307692e-06,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.037756202804746494,
      "grad_norm": NaN,
      "learning_rate": 6.215384615384615e-06,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.043149946062567425,
      "grad_norm": NaN,
      "learning_rate": 5.438461538461538e-06,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.04854368932038835,
      "grad_norm": NaN,
      "learning_rate": 4.661538461538462e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.05393743257820928,
      "grad_norm": NaN,
      "learning_rate": 3.884615384615385e-06,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.05393743257820928,
      "eval_loss": NaN,
      "eval_runtime": 13.1871,
      "eval_samples_per_second": 59.225,
      "eval_steps_per_second": 14.863,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5054876362997760.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}