Hugging Face's logo

WKLI22
/
phi-1_5-finetuned-med-text-high

PEFT
TensorBoard
Safetensors
phi
custom_code
Model card Files Metrics Community
phi-1_5-finetuned-med-text-high
File size: 3,001 Bytes 
139d2d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 808,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 0.4402466118335724,
      "learning_rate": 0.00019876883405951377,
      "loss": 1.5784,
      "step": 50
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.5029518604278564,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.4446,
      "step": 100
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.5096282958984375,
      "learning_rate": 0.0001891006524188368,
      "loss": 1.4047,
      "step": 150
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.508622407913208,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.3806,
      "step": 200
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.6428921222686768,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.2506,
      "step": 250
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.6709182262420654,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.254,
      "step": 300
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.6514674425125122,
      "learning_rate": 0.00014539904997395468,
      "loss": 1.2417,
      "step": 350
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.7174981236457825,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.252,
      "step": 400
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.8790501952171326,
      "learning_rate": 0.0001156434465040231,
      "loss": 1.0917,
      "step": 450
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.9474716186523438,
      "learning_rate": 0.0001,
      "loss": 1.072,
      "step": 500
    },
    {
      "epoch": 2.72,
      "grad_norm": 0.86595219373703,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.0909,
      "step": 550
    },
    {
      "epoch": 2.97,
      "grad_norm": 0.8805217742919922,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.0807,
      "step": 600
    },
    {
      "epoch": 3.22,
      "grad_norm": 0.9318429231643677,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.9672,
      "step": 650
    },
    {
      "epoch": 3.47,
      "grad_norm": 1.0167059898376465,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.9215,
      "step": 700
    },
    {
      "epoch": 3.71,
      "grad_norm": 1.0535578727722168,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.9481,
      "step": 750
    },
    {
      "epoch": 3.96,
      "grad_norm": 1.0781499147415161,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.9456,
      "step": 800
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.051029971828736e+16,
  "train_batch_size": 7,
  "trial_name": null,
  "trial_params": null
}