Hugging Face's logo

goatrider
/
layout1500

Token Classification
Transformers
Safetensors
layoutlmv3
Inference Endpoints
Model card Files Community
layout1500
File size: 7,718 Bytes 
517b39d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
 
{
  "best_metric": 0.55,
  "best_model_checkpoint": "test\\checkpoint-1500",
  "epoch": 1000.0,
  "eval_steps": 100,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 50.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.264135479927063,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.6603,
      "eval_samples_per_second": 0.429,
      "eval_steps_per_second": 0.215,
      "step": 100
    },
    {
      "epoch": 100.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.3265936374664307,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.6509,
      "eval_samples_per_second": 0.43,
      "eval_steps_per_second": 0.215,
      "step": 200
    },
    {
      "epoch": 150.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.4988499879837036,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.6202,
      "eval_samples_per_second": 0.433,
      "eval_steps_per_second": 0.216,
      "step": 300
    },
    {
      "epoch": 200.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.6139302253723145,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.7737,
      "eval_samples_per_second": 0.419,
      "eval_steps_per_second": 0.209,
      "step": 400
    },
    {
      "epoch": 250.0,
      "grad_norm": 0.14490167796611786,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.3046,
      "step": 500
    },
    {
      "epoch": 250.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.6872639656066895,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.6336,
      "eval_samples_per_second": 0.432,
      "eval_steps_per_second": 0.216,
      "step": 500
    },
    {
      "epoch": 300.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.7239123582839966,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.5649,
      "eval_samples_per_second": 0.438,
      "eval_steps_per_second": 0.219,
      "step": 600
    },
    {
      "epoch": 350.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.7806979417800903,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.4489,
      "eval_samples_per_second": 0.45,
      "eval_steps_per_second": 0.225,
      "step": 700
    },
    {
      "epoch": 400.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.8008891344070435,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.4619,
      "eval_samples_per_second": 0.448,
      "eval_steps_per_second": 0.224,
      "step": 800
    },
    {
      "epoch": 450.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.8712844848632812,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.4231,
      "eval_samples_per_second": 0.452,
      "eval_steps_per_second": 0.226,
      "step": 900
    },
    {
      "epoch": 500.0,
      "grad_norm": 0.03944549337029457,
      "learning_rate": 5e-06,
      "loss": 0.0081,
      "step": 1000
    },
    {
      "epoch": 500.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.9119956493377686,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.9883,
      "eval_samples_per_second": 0.401,
      "eval_steps_per_second": 0.2,
      "step": 1000
    },
    {
      "epoch": 550.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 1.947400450706482,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.9564,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.202,
      "step": 1100
    },
    {
      "epoch": 600.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.939751386642456,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.9517,
      "eval_samples_per_second": 0.404,
      "eval_steps_per_second": 0.202,
      "step": 1200
    },
    {
      "epoch": 650.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.9685324430465698,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 4.9434,
      "eval_samples_per_second": 0.405,
      "eval_steps_per_second": 0.202,
      "step": 1300
    },
    {
      "epoch": 700.0,
      "eval_accuracy": 0.6,
      "eval_f1": 0.5365853658536585,
      "eval_loss": 1.9726978540420532,
      "eval_precision": 0.5238095238095238,
      "eval_recall": 0.55,
      "eval_runtime": 5.0891,
      "eval_samples_per_second": 0.393,
      "eval_steps_per_second": 0.196,
      "step": 1400
    },
    {
      "epoch": 750.0,
      "grad_norm": 0.0346556194126606,
      "learning_rate": 2.5e-06,
      "loss": 0.0044,
      "step": 1500
    },
    {
      "epoch": 750.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 1.9932883977890015,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 5.166,
      "eval_samples_per_second": 0.387,
      "eval_steps_per_second": 0.194,
      "step": 1500
    },
    {
      "epoch": 800.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 2.012096643447876,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 5.144,
      "eval_samples_per_second": 0.389,
      "eval_steps_per_second": 0.194,
      "step": 1600
    },
    {
      "epoch": 850.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 2.0032660961151123,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 5.175,
      "eval_samples_per_second": 0.386,
      "eval_steps_per_second": 0.193,
      "step": 1700
    },
    {
      "epoch": 900.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 2.017909288406372,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.7769,
      "eval_samples_per_second": 0.419,
      "eval_steps_per_second": 0.209,
      "step": 1800
    },
    {
      "epoch": 950.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 2.016812324523926,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.6461,
      "eval_samples_per_second": 0.43,
      "eval_steps_per_second": 0.215,
      "step": 1900
    },
    {
      "epoch": 1000.0,
      "grad_norm": 0.030378883704543114,
      "learning_rate": 0.0,
      "loss": 0.0034,
      "step": 2000
    },
    {
      "epoch": 1000.0,
      "eval_accuracy": 0.6333333333333333,
      "eval_f1": 0.55,
      "eval_loss": 2.0183417797088623,
      "eval_precision": 0.55,
      "eval_recall": 0.55,
      "eval_runtime": 4.7632,
      "eval_samples_per_second": 0.42,
      "eval_steps_per_second": 0.21,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1000,
  "save_steps": 500,
  "total_flos": 796315622400000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}