Hugging Face's logo

emilykang
/
medprob-physiology_lora

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
medprob-physiology_lora
File size: 4,080 Bytes 
569c59e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 27.586206896551722,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 0.12481689453125,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.6433,
      "step": 10
    },
    {
      "epoch": 2.7586206896551726,
      "grad_norm": 0.11810302734375,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.6101,
      "step": 20
    },
    {
      "epoch": 4.137931034482759,
      "grad_norm": 0.1224365234375,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.5938,
      "step": 30
    },
    {
      "epoch": 5.517241379310345,
      "grad_norm": 0.12646484375,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.58,
      "step": 40
    },
    {
      "epoch": 6.896551724137931,
      "grad_norm": 0.1378173828125,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.564,
      "step": 50
    },
    {
      "epoch": 8.275862068965518,
      "grad_norm": 0.150634765625,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.5522,
      "step": 60
    },
    {
      "epoch": 9.655172413793103,
      "grad_norm": 0.189453125,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.5496,
      "step": 70
    },
    {
      "epoch": 11.03448275862069,
      "grad_norm": 0.208984375,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.5279,
      "step": 80
    },
    {
      "epoch": 12.413793103448276,
      "grad_norm": 0.2149658203125,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.5211,
      "step": 90
    },
    {
      "epoch": 13.793103448275861,
      "grad_norm": 0.256103515625,
      "learning_rate": 0.0001,
      "loss": 0.5138,
      "step": 100
    },
    {
      "epoch": 15.172413793103448,
      "grad_norm": 0.2479248046875,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.5024,
      "step": 110
    },
    {
      "epoch": 16.551724137931036,
      "grad_norm": 0.276123046875,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.4982,
      "step": 120
    },
    {
      "epoch": 17.93103448275862,
      "grad_norm": 0.26318359375,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.4884,
      "step": 130
    },
    {
      "epoch": 19.310344827586206,
      "grad_norm": 0.276123046875,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.482,
      "step": 140
    },
    {
      "epoch": 20.689655172413794,
      "grad_norm": 0.271240234375,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.4791,
      "step": 150
    },
    {
      "epoch": 22.06896551724138,
      "grad_norm": 0.33056640625,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.4761,
      "step": 160
    },
    {
      "epoch": 23.448275862068964,
      "grad_norm": 0.27001953125,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.4733,
      "step": 170
    },
    {
      "epoch": 24.82758620689655,
      "grad_norm": 0.289794921875,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.4728,
      "step": 180
    },
    {
      "epoch": 26.20689655172414,
      "grad_norm": 0.273681640625,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.4683,
      "step": 190
    },
    {
      "epoch": 27.586206896551722,
      "grad_norm": 0.2841796875,
      "learning_rate": 0.0,
      "loss": 0.4744,
      "step": 200
    },
    {
      "epoch": 27.586206896551722,
      "step": 200,
      "total_flos": 4.059527895633101e+16,
      "train_loss": 0.5235269355773926,
      "train_runtime": 570.5675,
      "train_samples_per_second": 11.217,
      "train_steps_per_second": 0.351
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 29,
  "save_steps": 500,
  "total_flos": 4.059527895633101e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}