Hugging Face's logo

tmnam
/
vihealthbert-w_unsup-SynPD

Fill-Mask
Transformers
Safetensors
roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
vihealthbert-w_unsup-SynPD
File size: 4,653 Bytes 
7a69197
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
172
173
 
{
  "best_metric": 0.6450457483325106,
  "best_model_checkpoint": "output/pretraining/vihealthbert-w_unsup-SynPD/lr3e-5_wr0.1_wd0.0/checkpoint-18000",
  "epoch": 3.101843873858349,
  "eval_steps": 2000,
  "global_step": 18000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017232465965879716,
      "grad_norm": 35.608882904052734,
      "learning_rate": 5.169739789763915e-09,
      "loss": 10.7382,
      "step": 1
    },
    {
      "epoch": 0.34464931931759435,
      "grad_norm": 4.884454250335693,
      "learning_rate": 1.033947957952783e-05,
      "loss": 5.8543,
      "step": 2000
    },
    {
      "epoch": 0.34464931931759435,
      "eval_accuracy": 0.3950195480446223,
      "eval_loss": 3.896709680557251,
      "eval_runtime": 24.6709,
      "eval_samples_per_second": 396.175,
      "eval_steps_per_second": 24.766,
      "step": 2000
    },
    {
      "epoch": 0.6892986386351887,
      "grad_norm": 5.278345108032227,
      "learning_rate": 2.067895915905566e-05,
      "loss": 3.4544,
      "step": 4000
    },
    {
      "epoch": 0.6892986386351887,
      "eval_accuracy": 0.530626322082222,
      "eval_loss": 2.811899423599243,
      "eval_runtime": 24.6443,
      "eval_samples_per_second": 396.602,
      "eval_steps_per_second": 24.793,
      "step": 4000
    },
    {
      "epoch": 1.033947957952783,
      "grad_norm": 4.731122016906738,
      "learning_rate": 2.988684014015739e-05,
      "loss": 2.8312,
      "step": 6000
    },
    {
      "epoch": 1.033947957952783,
      "eval_accuracy": 0.5771132321637026,
      "eval_loss": 2.4039628505706787,
      "eval_runtime": 24.6266,
      "eval_samples_per_second": 396.889,
      "eval_steps_per_second": 24.811,
      "step": 6000
    },
    {
      "epoch": 1.3785972772703774,
      "grad_norm": 12.213573455810547,
      "learning_rate": 2.873800907576541e-05,
      "loss": 2.5914,
      "step": 8000
    },
    {
      "epoch": 1.3785972772703774,
      "eval_accuracy": 0.5349752225383133,
      "eval_loss": 2.6481692790985107,
      "eval_runtime": 24.6033,
      "eval_samples_per_second": 397.264,
      "eval_steps_per_second": 24.834,
      "step": 8000
    },
    {
      "epoch": 1.7232465965879717,
      "grad_norm": 5.172228813171387,
      "learning_rate": 2.758917801137343e-05,
      "loss": 2.5649,
      "step": 10000
    },
    {
      "epoch": 1.7232465965879717,
      "eval_accuracy": 0.6087076297937304,
      "eval_loss": 2.13348388671875,
      "eval_runtime": 24.6211,
      "eval_samples_per_second": 396.976,
      "eval_steps_per_second": 24.816,
      "step": 10000
    },
    {
      "epoch": 2.067895915905566,
      "grad_norm": 4.871993064880371,
      "learning_rate": 2.6440346946981447e-05,
      "loss": 2.2749,
      "step": 12000
    },
    {
      "epoch": 2.067895915905566,
      "eval_accuracy": 0.6281529792701336,
      "eval_loss": 1.9895449876785278,
      "eval_runtime": 24.453,
      "eval_samples_per_second": 399.705,
      "eval_steps_per_second": 24.987,
      "step": 12000
    },
    {
      "epoch": 2.4125452352231607,
      "grad_norm": 8.037242889404297,
      "learning_rate": 2.5291515882589467e-05,
      "loss": 2.1572,
      "step": 14000
    },
    {
      "epoch": 2.4125452352231607,
      "eval_accuracy": 0.6353159252095423,
      "eval_loss": 1.9312896728515625,
      "eval_runtime": 24.4658,
      "eval_samples_per_second": 399.496,
      "eval_steps_per_second": 24.974,
      "step": 14000
    },
    {
      "epoch": 2.757194554540755,
      "grad_norm": 4.320974349975586,
      "learning_rate": 2.4142684818197487e-05,
      "loss": 2.1009,
      "step": 16000
    },
    {
      "epoch": 2.757194554540755,
      "eval_accuracy": 0.6428579553856829,
      "eval_loss": 1.864585280418396,
      "eval_runtime": 24.4545,
      "eval_samples_per_second": 399.68,
      "eval_steps_per_second": 24.985,
      "step": 16000
    },
    {
      "epoch": 3.101843873858349,
      "grad_norm": 4.6416168212890625,
      "learning_rate": 2.2993853753805504e-05,
      "loss": 2.0609,
      "step": 18000
    },
    {
      "epoch": 3.101843873858349,
      "eval_accuracy": 0.6450457483325106,
      "eval_loss": 1.8571828603744507,
      "eval_runtime": 24.4634,
      "eval_samples_per_second": 399.535,
      "eval_steps_per_second": 24.976,
      "step": 18000
    }
  ],
  "logging_steps": 2000,
  "max_steps": 58030,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 2000,
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}