pierreguillou commited on
Commit
dfe0a77
1 Parent(s): 2c27c8a

Delete checkpoint-6600/trainer_state.json

Browse files
Files changed (1) hide show
  1. checkpoint-6600/trainer_state.json +0 -358
checkpoint-6600/trainer_state.json DELETED
@@ -1,358 +0,0 @@
1
- {
2
- "best_metric": 0.7336375680847931,
3
- "best_model_checkpoint": "DocLayNet/layout-xlm-base-finetuned-DocLayNet-base_lines_ml384-v1/checkpoint-6300",
4
- "epoch": 2.7420024927295388,
5
- "global_step": 6600,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.12,
12
- "eval_accuracy": 0.8412902144953226,
13
- "eval_f1": 0.13109765966400155,
14
- "eval_loss": 0.5185014605522156,
15
- "eval_precision": 0.14371894960965223,
16
- "eval_recall": 0.1205141938939475,
17
- "eval_runtime": 363.2958,
18
- "eval_samples_per_second": 5.648,
19
- "eval_steps_per_second": 0.355,
20
- "step": 300
21
- },
22
- {
23
- "epoch": 0.21,
24
- "learning_rate": 1.372060857538036e-05,
25
- "loss": 0.9231,
26
- "step": 500
27
- },
28
- {
29
- "epoch": 0.25,
30
- "eval_accuracy": 0.8751371332529899,
31
- "eval_f1": 0.5030902012034086,
32
- "eval_loss": 0.4107707738876343,
33
- "eval_precision": 0.4636655625815517,
34
- "eval_recall": 0.5498422900672499,
35
- "eval_runtime": 366.1838,
36
- "eval_samples_per_second": 5.604,
37
- "eval_steps_per_second": 0.352,
38
- "step": 600
39
- },
40
- {
41
- "epoch": 0.37,
42
- "eval_accuracy": 0.8887072454995973,
43
- "eval_f1": 0.520614670919107,
44
- "eval_loss": 0.3911038935184479,
45
- "eval_precision": 0.5076044552496184,
46
- "eval_recall": 0.5343093495209189,
47
- "eval_runtime": 358.5079,
48
- "eval_samples_per_second": 5.724,
49
- "eval_steps_per_second": 0.36,
50
- "step": 900
51
- },
52
- {
53
- "epoch": 0.42,
54
- "learning_rate": 1.9159741458910434e-05,
55
- "loss": 0.369,
56
- "step": 1000
57
- },
58
- {
59
- "epoch": 0.5,
60
- "eval_accuracy": 0.8723944681931917,
61
- "eval_f1": 0.5365372697053354,
62
- "eval_loss": 0.41175082325935364,
63
- "eval_precision": 0.5093875367745386,
64
- "eval_recall": 0.5667440338034875,
65
- "eval_runtime": 370.2231,
66
- "eval_samples_per_second": 5.543,
67
- "eval_steps_per_second": 0.348,
68
- "step": 1200
69
- },
70
- {
71
- "epoch": 0.62,
72
- "learning_rate": 1.7620806401969838e-05,
73
- "loss": 0.2737,
74
- "step": 1500
75
- },
76
- {
77
- "epoch": 0.62,
78
- "eval_accuracy": 0.8960354303687331,
79
- "eval_f1": 0.6032919847328244,
80
- "eval_loss": 0.33280590176582336,
81
- "eval_precision": 0.6045538755752107,
82
- "eval_recall": 0.6020353508302089,
83
- "eval_runtime": 369.9685,
84
- "eval_samples_per_second": 5.546,
85
- "eval_steps_per_second": 0.349,
86
- "step": 1500
87
- },
88
- {
89
- "epoch": 0.75,
90
- "eval_accuracy": 0.9185901350526106,
91
- "eval_f1": 0.640386343216532,
92
- "eval_loss": 0.2983764410018921,
93
- "eval_precision": 0.6061765800244512,
94
- "eval_recall": 0.6786883294649765,
95
- "eval_runtime": 366.7561,
96
- "eval_samples_per_second": 5.595,
97
- "eval_steps_per_second": 0.352,
98
- "step": 1800
99
- },
100
- {
101
- "epoch": 0.83,
102
- "learning_rate": 1.6084949215143123e-05,
103
- "loss": 0.2542,
104
- "step": 2000
105
- },
106
- {
107
- "epoch": 0.87,
108
- "eval_accuracy": 0.9162879176822183,
109
- "eval_f1": 0.6593356503902912,
110
- "eval_loss": 0.3114674985408783,
111
- "eval_precision": 0.6323842832941691,
112
- "eval_recall": 0.6886865440695114,
113
- "eval_runtime": 356.8285,
114
- "eval_samples_per_second": 5.751,
115
- "eval_steps_per_second": 0.362,
116
- "step": 2100
117
- },
118
- {
119
- "epoch": 1.0,
120
- "eval_accuracy": 0.919752052270062,
121
- "eval_f1": 0.6536656236030397,
122
- "eval_loss": 0.2877778708934784,
123
- "eval_precision": 0.6160408657643899,
124
- "eval_recall": 0.6961852050229126,
125
- "eval_runtime": 352.6194,
126
- "eval_samples_per_second": 5.819,
127
- "eval_steps_per_second": 0.366,
128
- "step": 2400
129
- },
130
- {
131
- "epoch": 1.04,
132
- "learning_rate": 1.4546014158202526e-05,
133
- "loss": 0.1938,
134
- "step": 2500
135
- },
136
- {
137
- "epoch": 1.12,
138
- "eval_accuracy": 0.9165257053918363,
139
- "eval_f1": 0.6752131725962951,
140
- "eval_loss": 0.34137091040611267,
141
- "eval_precision": 0.6672865694194223,
142
- "eval_recall": 0.6833303576742248,
143
- "eval_runtime": 349.7664,
144
- "eval_samples_per_second": 5.867,
145
- "eval_steps_per_second": 0.369,
146
- "step": 2700
147
- },
148
- {
149
- "epoch": 1.25,
150
- "learning_rate": 1.3007079101261929e-05,
151
- "loss": 0.1581,
152
- "step": 3000
153
- },
154
- {
155
- "epoch": 1.25,
156
- "eval_accuracy": 0.9193251152459752,
157
- "eval_f1": 0.6871282417320962,
158
- "eval_loss": 0.3610578179359436,
159
- "eval_precision": 0.6867605968729564,
160
- "eval_recall": 0.6874962804261144,
161
- "eval_runtime": 346.075,
162
- "eval_samples_per_second": 5.929,
163
- "eval_steps_per_second": 0.373,
164
- "step": 3000
165
- },
166
- {
167
- "epoch": 1.37,
168
- "eval_accuracy": 0.9256291916839153,
169
- "eval_f1": 0.6821629855293222,
170
- "eval_loss": 0.2762657403945923,
171
- "eval_precision": 0.6987891648982649,
172
- "eval_recall": 0.6663095875736476,
173
- "eval_runtime": 342.8929,
174
- "eval_samples_per_second": 5.984,
175
- "eval_steps_per_second": 0.376,
176
- "step": 3300
177
- },
178
- {
179
- "epoch": 1.45,
180
- "learning_rate": 1.1471221914435212e-05,
181
- "loss": 0.1428,
182
- "step": 3500
183
- },
184
- {
185
- "epoch": 1.5,
186
- "eval_accuracy": 0.9287285383081404,
187
- "eval_f1": 0.7083662914511712,
188
- "eval_loss": 0.306523859500885,
189
- "eval_precision": 0.7245907761249767,
190
- "eval_recall": 0.6928524668214009,
191
- "eval_runtime": 342.9768,
192
- "eval_samples_per_second": 5.983,
193
- "eval_steps_per_second": 0.376,
194
- "step": 3600
195
- },
196
- {
197
- "epoch": 1.62,
198
- "eval_accuracy": 0.9193764557741881,
199
- "eval_f1": 0.6812402542881132,
200
- "eval_loss": 0.29422909021377563,
201
- "eval_precision": 0.6865518283469326,
202
- "eval_recall": 0.6760102362673333,
203
- "eval_runtime": 340.2288,
204
- "eval_samples_per_second": 6.031,
205
- "eval_steps_per_second": 0.379,
206
- "step": 3900
207
- },
208
- {
209
- "epoch": 1.66,
210
- "learning_rate": 9.932286857494614e-06,
211
- "loss": 0.1025,
212
- "step": 4000
213
- },
214
- {
215
- "epoch": 1.74,
216
- "eval_accuracy": 0.9346597203832706,
217
- "eval_f1": 0.7223092684102689,
218
- "eval_loss": 0.2989632189273834,
219
- "eval_precision": 0.7315227342081172,
220
- "eval_recall": 0.7133250014878295,
221
- "eval_runtime": 368.8508,
222
- "eval_samples_per_second": 5.563,
223
- "eval_steps_per_second": 0.35,
224
- "step": 4200
225
- },
226
- {
227
- "epoch": 1.87,
228
- "learning_rate": 8.393351800554018e-06,
229
- "loss": 0.1225,
230
- "step": 4500
231
- },
232
- {
233
- "epoch": 1.87,
234
- "eval_accuracy": 0.9360324039797016,
235
- "eval_f1": 0.7047921954799842,
236
- "eval_loss": 0.2729274332523346,
237
- "eval_precision": 0.7248993457473578,
238
- "eval_recall": 0.6857703981431887,
239
- "eval_runtime": 366.3118,
240
- "eval_samples_per_second": 5.602,
241
- "eval_steps_per_second": 0.352,
242
- "step": 4500
243
- },
244
- {
245
- "epoch": 1.99,
246
- "eval_accuracy": 0.9395776025594604,
247
- "eval_f1": 0.7221742349457059,
248
- "eval_loss": 0.2825567126274109,
249
- "eval_precision": 0.7496957663485557,
250
- "eval_recall": 0.6966017972981016,
251
- "eval_runtime": 379.1173,
252
- "eval_samples_per_second": 5.413,
253
- "eval_steps_per_second": 0.34,
254
- "step": 4800
255
- },
256
- {
257
- "epoch": 2.08,
258
- "learning_rate": 6.85441674361342e-06,
259
- "loss": 0.108,
260
- "step": 5000
261
- },
262
- {
263
- "epoch": 2.12,
264
- "eval_accuracy": 0.9301336475013375,
265
- "eval_f1": 0.7193125072581582,
266
- "eval_loss": 0.3070518672466278,
267
- "eval_precision": 0.7022277648659373,
268
- "eval_recall": 0.7372493007201095,
269
- "eval_runtime": 371.7164,
270
- "eval_samples_per_second": 5.52,
271
- "eval_steps_per_second": 0.347,
272
- "step": 5100
273
- },
274
- {
275
- "epoch": 2.24,
276
- "eval_accuracy": 0.9334356541053508,
277
- "eval_f1": 0.7243484735666419,
278
- "eval_loss": 0.29993483424186707,
279
- "eval_precision": 0.7250178869544479,
280
- "eval_recall": 0.7236802951853836,
281
- "eval_runtime": 373.5258,
282
- "eval_samples_per_second": 5.494,
283
- "eval_steps_per_second": 0.345,
284
- "step": 5400
285
- },
286
- {
287
- "epoch": 2.29,
288
- "learning_rate": 5.315481686672823e-06,
289
- "loss": 0.0799,
290
- "step": 5500
291
- },
292
- {
293
- "epoch": 2.37,
294
- "eval_accuracy": 0.9382346424267317,
295
- "eval_f1": 0.7253808324337292,
296
- "eval_loss": 0.2709857225418091,
297
- "eval_precision": 0.7310365669386522,
298
- "eval_recall": 0.7198119383443433,
299
- "eval_runtime": 362.6803,
300
- "eval_samples_per_second": 5.658,
301
- "eval_steps_per_second": 0.356,
302
- "step": 5700
303
- },
304
- {
305
- "epoch": 2.49,
306
- "learning_rate": 3.7765466297322255e-06,
307
- "loss": 0.0793,
308
- "step": 6000
309
- },
310
- {
311
- "epoch": 2.49,
312
- "eval_accuracy": 0.9328519933635612,
313
- "eval_f1": 0.7228055311809738,
314
- "eval_loss": 0.32012131810188293,
315
- "eval_precision": 0.7351963560260988,
316
- "eval_recall": 0.7108254478366959,
317
- "eval_runtime": 358.4508,
318
- "eval_samples_per_second": 5.725,
319
- "eval_steps_per_second": 0.36,
320
- "step": 6000
321
- },
322
- {
323
- "epoch": 2.62,
324
- "eval_accuracy": 0.9373375342495366,
325
- "eval_f1": 0.7336375680847931,
326
- "eval_loss": 0.30349481105804443,
327
- "eval_precision": 0.7259643398205338,
328
- "eval_recall": 0.7414747366541689,
329
- "eval_runtime": 356.5492,
330
- "eval_samples_per_second": 5.755,
331
- "eval_steps_per_second": 0.362,
332
- "step": 6300
333
- },
334
- {
335
- "epoch": 2.7,
336
- "learning_rate": 2.2376115727916285e-06,
337
- "loss": 0.0696,
338
- "step": 6500
339
- },
340
- {
341
- "epoch": 2.74,
342
- "eval_accuracy": 0.9373915769108134,
343
- "eval_f1": 0.7274848203870427,
344
- "eval_loss": 0.31372010707855225,
345
- "eval_precision": 0.7312687913409501,
346
- "eval_recall": 0.7237398083675534,
347
- "eval_runtime": 356.5844,
348
- "eval_samples_per_second": 5.755,
349
- "eval_steps_per_second": 0.362,
350
- "step": 6600
351
- }
352
- ],
353
- "max_steps": 7221,
354
- "num_train_epochs": 3,
355
- "total_flos": 2.1373139425089024e+16,
356
- "trial_name": null,
357
- "trial_params": null
358
- }