Hugging Face's logo

enoriega
/
kw_pubmed_1000_0.00006

Fill-Mask
Transformers
PyTorch
bert
Inference Endpoints
Model card Files Community
kw_pubmed_1000_0.00006
File size: 5,020 Bytes 
3887554
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
 
{
  "best_metric": 0.3793538836642285,
  "best_model_checkpoint": "/xdisk/msurdeanu/enoriega/kw_pubmed/kw_pubmed_1000_0.00006/checkpoint-12",
  "epoch": 1.1524390243902438,
  "global_step": 52,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "eval_accuracy": 0.3767850923023337,
      "eval_loss": 3.902531385421753,
      "eval_runtime": 16.573,
      "eval_samples_per_second": 603.393,
      "eval_steps_per_second": 18.886,
      "step": 4
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.8666666666666665e-05,
      "loss": 4.0323,
      "step": 5
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.37399860675722746,
      "eval_loss": 3.8996994495391846,
      "eval_runtime": 16.5623,
      "eval_samples_per_second": 603.78,
      "eval_steps_per_second": 18.898,
      "step": 8
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.7333333333333336e-05,
      "loss": 3.4655,
      "step": 10
    },
    {
      "epoch": 0.26,
      "eval_accuracy": 0.3793538836642285,
      "eval_loss": 3.9113454818725586,
      "eval_runtime": 16.5561,
      "eval_samples_per_second": 604.006,
      "eval_steps_per_second": 18.905,
      "step": 12
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.6e-05,
      "loss": 3.1532,
      "step": 15
    },
    {
      "epoch": 0.35,
      "eval_accuracy": 0.3754353883664229,
      "eval_loss": 3.9654853343963623,
      "eval_runtime": 16.5341,
      "eval_samples_per_second": 604.812,
      "eval_steps_per_second": 18.931,
      "step": 16
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.466666666666667e-05,
      "loss": 2.9457,
      "step": 20
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.3714733542319749,
      "eval_loss": 4.051833629608154,
      "eval_runtime": 16.5251,
      "eval_samples_per_second": 605.14,
      "eval_steps_per_second": 18.941,
      "step": 20
    },
    {
      "epoch": 0.52,
      "eval_accuracy": 0.36964472309299895,
      "eval_loss": 4.067558765411377,
      "eval_runtime": 16.4933,
      "eval_samples_per_second": 606.306,
      "eval_steps_per_second": 18.977,
      "step": 24
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.36e-05,
      "loss": 2.7639,
      "step": 25
    },
    {
      "epoch": 0.61,
      "eval_accuracy": 0.3722570532915361,
      "eval_loss": 4.092674255371094,
      "eval_runtime": 16.5366,
      "eval_samples_per_second": 604.721,
      "eval_steps_per_second": 18.928,
      "step": 28
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.2266666666666665e-05,
      "loss": 2.6542,
      "step": 30
    },
    {
      "epoch": 0.7,
      "eval_accuracy": 0.37169104841518635,
      "eval_loss": 4.114505290985107,
      "eval_runtime": 16.541,
      "eval_samples_per_second": 604.559,
      "eval_steps_per_second": 18.923,
      "step": 32
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.0933333333333336e-05,
      "loss": 2.5371,
      "step": 35
    },
    {
      "epoch": 0.78,
      "eval_accuracy": 0.3714733542319749,
      "eval_loss": 4.133761882781982,
      "eval_runtime": 16.5877,
      "eval_samples_per_second": 602.858,
      "eval_steps_per_second": 18.869,
      "step": 36
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.96e-05,
      "loss": 2.4884,
      "step": 40
    },
    {
      "epoch": 0.87,
      "eval_accuracy": 0.3642894461859979,
      "eval_loss": 4.216277599334717,
      "eval_runtime": 16.5043,
      "eval_samples_per_second": 605.903,
      "eval_steps_per_second": 18.965,
      "step": 40
    },
    {
      "epoch": 0.96,
      "eval_accuracy": 0.36920933472657613,
      "eval_loss": 4.178205490112305,
      "eval_runtime": 16.5055,
      "eval_samples_per_second": 605.86,
      "eval_steps_per_second": 18.963,
      "step": 44
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.826666666666666e-05,
      "loss": 2.3936,
      "step": 45
    },
    {
      "epoch": 1.07,
      "eval_accuracy": 0.3670323928944619,
      "eval_loss": 4.243963718414307,
      "eval_runtime": 16.5457,
      "eval_samples_per_second": 604.386,
      "eval_steps_per_second": 18.917,
      "step": 48
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.693333333333334e-05,
      "loss": 2.694,
      "step": 50
    },
    {
      "epoch": 1.15,
      "eval_accuracy": 0.36733716475095785,
      "eval_loss": 4.244164943695068,
      "eval_runtime": 16.5637,
      "eval_samples_per_second": 603.731,
      "eval_steps_per_second": 18.897,
      "step": 52
    },
    {
      "epoch": 1.15,
      "step": 52,
      "total_flos": 3.18987289303776e+16,
      "train_loss": 2.8869726932965794,
      "train_runtime": 1925.7546,
      "train_samples_per_second": 953.779,
      "train_steps_per_second": 0.117
    }
  ],
  "max_steps": 225,
  "num_train_epochs": 5,
  "total_flos": 3.18987289303776e+16,
  "trial_name": null,
  "trial_params": null
}