Hugging Face's logo

Team-EVEN
/
krx_llama3.1_8b_instruct

Safetensors
llama
krx
Model card Files Community
krx_llama3.1_8b_instruct
File size: 2,696 Bytes 
fae1c1c
944d2cf
 
 
fae1c1c
944d2cf
fae1c1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
944d2cf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fae1c1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
944d2cf
fae1c1c
 
 
 
 
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
 
{
  "best_metric": 0.0754217654466629,
  "best_model_checkpoint": "/workspace/save/checkpoint-467",
  "epoch": 1.9985734664764623,
  "eval_steps": 500,
  "global_step": 467,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21398002853067047,
      "grad_norm": 4.1875,
      "learning_rate": 1.9916057044029887e-05,
      "loss": 0.126,
      "step": 50
    },
    {
      "epoch": 0.42796005706134094,
      "grad_norm": 2.28125,
      "learning_rate": 1.9651642858238914e-05,
      "loss": 0.0777,
      "step": 100
    },
    {
      "epoch": 0.6419400855920114,
      "grad_norm": 3.828125,
      "learning_rate": 1.921142770711075e-05,
      "loss": 0.0802,
      "step": 150
    },
    {
      "epoch": 0.8559201141226819,
      "grad_norm": 5.90625,
      "learning_rate": 1.860342994043941e-05,
      "loss": 0.072,
      "step": 200
    },
    {
      "epoch": 0.9971469329529244,
      "eval_loss": 0.0810636430978775,
      "eval_runtime": 182.3128,
      "eval_samples_per_second": 6.834,
      "eval_steps_per_second": 1.711,
      "step": 233
    },
    {
      "epoch": 1.0699001426533523,
      "grad_norm": 3.546875,
      "learning_rate": 1.783872400387872e-05,
      "loss": 0.0695,
      "step": 250
    },
    {
      "epoch": 1.2838801711840229,
      "grad_norm": 2.59375,
      "learning_rate": 1.693123872217086e-05,
      "loss": 0.0687,
      "step": 300
    },
    {
      "epoch": 1.4978601997146934,
      "grad_norm": 1.5,
      "learning_rate": 1.5897503590956808e-05,
      "loss": 0.0703,
      "step": 350
    },
    {
      "epoch": 1.7118402282453637,
      "grad_norm": 1.3671875,
      "learning_rate": 1.4756347698365871e-05,
      "loss": 0.0699,
      "step": 400
    },
    {
      "epoch": 1.925820256776034,
      "grad_norm": 1.4765625,
      "learning_rate": 1.3528556760411822e-05,
      "loss": 0.0673,
      "step": 450
    },
    {
      "epoch": 1.9985734664764623,
      "eval_loss": 0.0754217654466629,
      "eval_runtime": 181.3373,
      "eval_samples_per_second": 6.871,
      "eval_steps_per_second": 1.721,
      "step": 467
    }
  ],
  "logging_steps": 50,
  "max_steps": 1165,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0202365411202335e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}