Hugging Face's logo

DunnBC22
/
mpnet-base-apple_iphone_se_reviews

Text Classification
Transformers
PyTorch
TensorBoard
English
mpnet
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
2
DunnBC22 commited on
Commit
5e8403d
·
1 Parent(s): 0fddf1e

All Dunn!!!

Browse files
Files changed (3) hide show
  1. all_results.json +7 -0
  2. train_results.json +7 -0
  3. trainer_state.json +265 -0
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.29725947360523414,
4
+ "train_runtime": 45565.3514,
5
+ "train_samples_per_second": 0.853,
6
+ "train_steps_per_second": 0.013
7
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.29725947360523414,
4
+ "train_runtime": 45565.3514,
5
+ "train_samples_per_second": 0.853,
6
+ "train_steps_per_second": 0.013
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 610,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 1.99672131147541e-05,
13
+ "loss": 1.602,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.2,
18
+ "learning_rate": 1.918032786885246e-05,
19
+ "loss": 1.1275,
20
+ "step": 25
21
+ },
22
+ {
23
+ "epoch": 0.41,
24
+ "learning_rate": 1.836065573770492e-05,
25
+ "loss": 0.8491,
26
+ "step": 50
27
+ },
28
+ {
29
+ "epoch": 0.61,
30
+ "learning_rate": 1.7540983606557377e-05,
31
+ "loss": 0.6927,
32
+ "step": 75
33
+ },
34
+ {
35
+ "epoch": 0.82,
36
+ "learning_rate": 1.6721311475409837e-05,
37
+ "loss": 0.5194,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 1.0,
42
+ "eval_Macro F1": 0.32887477005548477,
43
+ "eval_Macro Precision": 0.30312399537255397,
44
+ "eval_Macro Recall": 0.3855245821114833,
45
+ "eval_Micro F1": 0.8327328872876993,
46
+ "eval_Micro Precision": 0.8327328872876995,
47
+ "eval_Micro Recall": 0.8327328872876995,
48
+ "eval_Weighted F1": 0.7993487616471537,
49
+ "eval_Weighted Precision": 0.7948115677222908,
50
+ "eval_Weighted Recall": 0.8327328872876995,
51
+ "eval_accuracy": 0.8327328872876995,
52
+ "eval_loss": 0.40684521198272705,
53
+ "eval_runtime": 611.8394,
54
+ "eval_samples_per_second": 3.176,
55
+ "eval_steps_per_second": 0.051,
56
+ "step": 122
57
+ },
58
+ {
59
+ "epoch": 1.02,
60
+ "learning_rate": 1.5901639344262295e-05,
61
+ "loss": 0.4588,
62
+ "step": 125
63
+ },
64
+ {
65
+ "epoch": 1.23,
66
+ "learning_rate": 1.5081967213114754e-05,
67
+ "loss": 0.3681,
68
+ "step": 150
69
+ },
70
+ {
71
+ "epoch": 1.43,
72
+ "learning_rate": 1.4262295081967214e-05,
73
+ "loss": 0.3334,
74
+ "step": 175
75
+ },
76
+ {
77
+ "epoch": 1.64,
78
+ "learning_rate": 1.3442622950819673e-05,
79
+ "loss": 0.2953,
80
+ "step": 200
81
+ },
82
+ {
83
+ "epoch": 1.84,
84
+ "learning_rate": 1.2622950819672132e-05,
85
+ "loss": 0.264,
86
+ "step": 225
87
+ },
88
+ {
89
+ "epoch": 2.0,
90
+ "eval_Macro F1": 0.45598935385523764,
91
+ "eval_Macro Precision": 0.4341074208614427,
92
+ "eval_Macro Recall": 0.5088583722111778,
93
+ "eval_Micro F1": 0.8836850231600618,
94
+ "eval_Micro Precision": 0.8836850231600618,
95
+ "eval_Micro Recall": 0.8836850231600618,
96
+ "eval_Weighted F1": 0.8644885072415942,
97
+ "eval_Weighted Precision": 0.8529605097109872,
98
+ "eval_Weighted Recall": 0.8836850231600618,
99
+ "eval_accuracy": 0.8836850231600618,
100
+ "eval_loss": 0.2356589287519455,
101
+ "eval_runtime": 610.0352,
102
+ "eval_samples_per_second": 3.185,
103
+ "eval_steps_per_second": 0.051,
104
+ "step": 244
105
+ },
106
+ {
107
+ "epoch": 2.05,
108
+ "learning_rate": 1.1803278688524591e-05,
109
+ "loss": 0.2659,
110
+ "step": 250
111
+ },
112
+ {
113
+ "epoch": 2.25,
114
+ "learning_rate": 1.0983606557377052e-05,
115
+ "loss": 0.2027,
116
+ "step": 275
117
+ },
118
+ {
119
+ "epoch": 2.46,
120
+ "learning_rate": 1.0163934426229509e-05,
121
+ "loss": 0.1936,
122
+ "step": 300
123
+ },
124
+ {
125
+ "epoch": 2.66,
126
+ "learning_rate": 9.344262295081968e-06,
127
+ "loss": 0.1722,
128
+ "step": 325
129
+ },
130
+ {
131
+ "epoch": 2.87,
132
+ "learning_rate": 8.524590163934427e-06,
133
+ "loss": 0.1601,
134
+ "step": 350
135
+ },
136
+ {
137
+ "epoch": 3.0,
138
+ "eval_Macro F1": 0.48630501934265596,
139
+ "eval_Macro Precision": 0.461020549786962,
140
+ "eval_Macro Recall": 0.5614892316744751,
141
+ "eval_Micro F1": 0.8975810602161606,
142
+ "eval_Micro Precision": 0.8975810602161606,
143
+ "eval_Micro Recall": 0.8975810602161606,
144
+ "eval_Weighted F1": 0.8774363233455805,
145
+ "eval_Weighted Precision": 0.8696699634040972,
146
+ "eval_Weighted Recall": 0.8975810602161606,
147
+ "eval_accuracy": 0.8975810602161606,
148
+ "eval_loss": 0.16468031704425812,
149
+ "eval_runtime": 610.8239,
150
+ "eval_samples_per_second": 3.181,
151
+ "eval_steps_per_second": 0.051,
152
+ "step": 366
153
+ },
154
+ {
155
+ "epoch": 3.07,
156
+ "learning_rate": 7.704918032786886e-06,
157
+ "loss": 0.1671,
158
+ "step": 375
159
+ },
160
+ {
161
+ "epoch": 3.28,
162
+ "learning_rate": 6.885245901639345e-06,
163
+ "loss": 0.1406,
164
+ "step": 400
165
+ },
166
+ {
167
+ "epoch": 3.48,
168
+ "learning_rate": 6.065573770491804e-06,
169
+ "loss": 0.1475,
170
+ "step": 425
171
+ },
172
+ {
173
+ "epoch": 3.69,
174
+ "learning_rate": 5.245901639344263e-06,
175
+ "loss": 0.1234,
176
+ "step": 450
177
+ },
178
+ {
179
+ "epoch": 3.89,
180
+ "learning_rate": 4.426229508196722e-06,
181
+ "loss": 0.1281,
182
+ "step": 475
183
+ },
184
+ {
185
+ "epoch": 4.0,
186
+ "eval_Macro F1": 0.7092696023153502,
187
+ "eval_Macro Precision": 0.6805589698473045,
188
+ "eval_Macro Recall": 0.7464438781750541,
189
+ "eval_Micro F1": 0.9423571796191457,
190
+ "eval_Micro Precision": 0.9423571796191457,
191
+ "eval_Micro Recall": 0.9423571796191457,
192
+ "eval_Weighted F1": 0.9322920914691559,
193
+ "eval_Weighted Precision": 0.924443268867862,
194
+ "eval_Weighted Recall": 0.9423571796191457,
195
+ "eval_accuracy": 0.9423571796191457,
196
+ "eval_loss": 0.13984337449073792,
197
+ "eval_runtime": 612.0896,
198
+ "eval_samples_per_second": 3.174,
199
+ "eval_steps_per_second": 0.051,
200
+ "step": 488
201
+ },
202
+ {
203
+ "epoch": 4.1,
204
+ "learning_rate": 3.6065573770491806e-06,
205
+ "loss": 0.1277,
206
+ "step": 500
207
+ },
208
+ {
209
+ "epoch": 4.3,
210
+ "learning_rate": 2.786885245901639e-06,
211
+ "loss": 0.123,
212
+ "step": 525
213
+ },
214
+ {
215
+ "epoch": 4.51,
216
+ "learning_rate": 1.9672131147540985e-06,
217
+ "loss": 0.1049,
218
+ "step": 550
219
+ },
220
+ {
221
+ "epoch": 4.71,
222
+ "learning_rate": 1.1475409836065575e-06,
223
+ "loss": 0.1091,
224
+ "step": 575
225
+ },
226
+ {
227
+ "epoch": 4.92,
228
+ "learning_rate": 3.278688524590164e-07,
229
+ "loss": 0.1175,
230
+ "step": 600
231
+ },
232
+ {
233
+ "epoch": 5.0,
234
+ "eval_Macro F1": 0.7242136777661108,
235
+ "eval_Macro Precision": 0.7007419659301912,
236
+ "eval_Macro Recall": 0.7593500405849569,
237
+ "eval_Micro F1": 0.9459598558929491,
238
+ "eval_Micro Precision": 0.9459598558929491,
239
+ "eval_Micro Recall": 0.9459598558929491,
240
+ "eval_Weighted F1": 0.9359769237564278,
241
+ "eval_Weighted Precision": 0.929023836280776,
242
+ "eval_Weighted Recall": 0.9459598558929491,
243
+ "eval_accuracy": 0.9459598558929491,
244
+ "eval_loss": 0.12987616658210754,
245
+ "eval_runtime": 610.6404,
246
+ "eval_samples_per_second": 3.182,
247
+ "eval_steps_per_second": 0.051,
248
+ "step": 610
249
+ },
250
+ {
251
+ "epoch": 5.0,
252
+ "step": 610,
253
+ "total_flos": 5490407137792500.0,
254
+ "train_loss": 0.29725947360523414,
255
+ "train_runtime": 45565.3514,
256
+ "train_samples_per_second": 0.853,
257
+ "train_steps_per_second": 0.013
258
+ }
259
+ ],
260
+ "max_steps": 610,
261
+ "num_train_epochs": 5,
262
+ "total_flos": 5490407137792500.0,
263
+ "trial_name": null,
264
+ "trial_params": null
265
+ }