Hugging Face's logo

jimboHsueh
/
HW3

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
HW3
File size: 2,520 Bytes 
4108e31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
138
139
140
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 12.1569,
      "step": 100
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 0.0485,
      "step": 200
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 5.1593,
      "step": 300
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 0.116,
      "step": 500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 0.2684,
      "step": 600
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 0.0943,
      "step": 700
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 29.8504,
      "step": 800
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 0.0173,
      "step": 900
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.6532,
      "step": 1000
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 0.6314,
      "step": 1100
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.0475,
      "step": 1200
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 1300
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002,
      "loss": 0.9073,
      "step": 1400
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 0.0704,
      "step": 1500
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 21.957,
      "step": 1600
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 1247.1927,
      "step": 1700
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 0.0146,
      "step": 1800
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0002,
      "loss": 0.6174,
      "step": 1900
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 1.1367,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 2500,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 1.907746799616e+17,
  "trial_name": null,
  "trial_params": null
}