Hugging Face's logo

jamil117
/
llama3

PEFT
TensorBoard
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Metrics Community
llama3
File size: 2,882 Bytes 
d8e0d55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 0.9890895485877991,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.709,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.568547248840332,
      "learning_rate": 4.951963201008076e-05,
      "loss": 0.1543,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.757222056388855,
      "learning_rate": 4.721114089947181e-05,
      "loss": 0.1166,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.0231865644454956,
      "learning_rate": 4.316650805085068e-05,
      "loss": 0.1208,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6902381777763367,
      "learning_rate": 3.770188363116324e-05,
      "loss": 0.092,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.7536186575889587,
      "learning_rate": 3.1244411954180676e-05,
      "loss": 0.0878,
      "step": 60
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.343789279460907,
      "learning_rate": 2.429884359310328e-05,
      "loss": 0.0798,
      "step": 70
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.6155710816383362,
      "learning_rate": 1.7408081372259632e-05,
      "loss": 0.093,
      "step": 80
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.4667530655860901,
      "learning_rate": 1.1110744174509952e-05,
      "loss": 0.0705,
      "step": 90
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.176645278930664,
      "learning_rate": 5.899065604459814e-06,
      "loss": 0.0577,
      "step": 100
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.32808709144592285,
      "learning_rate": 2.1804183734670277e-06,
      "loss": 0.058,
      "step": 110
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.5392273664474487,
      "learning_rate": 2.454718665888589e-07,
      "loss": 0.0863,
      "step": 120
    },
    {
      "epoch": 1.0,
      "step": 125,
      "total_flos": 3934658943516672.0,
      "train_loss": 0.13944334506988526,
      "train_runtime": 795.412,
      "train_samples_per_second": 1.257,
      "train_steps_per_second": 0.157
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3934658943516672.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}