Hugging Face's logo

phuongsuga
/
PBL6_AI_Model_Text_Image

TensorBoard
Safetensors
roberta
Model card Files
xet
 Metrics Community
PBL6_AI_Model_Text_Image
File size: 6,195 Bytes
ed416d1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
[
  {
    "loss": 1.0146,
    "grad_norm": 8.066655158996582,
    "learning_rate": 1.88259587020649e-05,
    "epoch": 0.5908419497784343,
    "step": 200
  },
  {
    "eval_loss": 0.6535171866416931,
    "eval_accuracy": 0.7455686853766618,
    "eval_precision": 0.7438951273666146,
    "eval_recall": 0.7635212365766714,
    "eval_f1": 0.7480569004890223,
    "eval_runtime": 4.1402,
    "eval_samples_per_second": 654.079,
    "eval_steps_per_second": 10.386,
    "epoch": 1.0,
    "step": 339
  },
  {
    "loss": 0.7183,
    "grad_norm": 8.033791542053223,
    "learning_rate": 1.7646017699115045e-05,
    "epoch": 1.1802067946824224,
    "step": 400
  },
  {
    "loss": 0.5841,
    "grad_norm": 7.553318500518799,
    "learning_rate": 1.6466076696165194e-05,
    "epoch": 1.7710487444608567,
    "step": 600
  },
  {
    "eval_loss": 0.5103763341903687,
    "eval_accuracy": 0.7961595273264401,
    "eval_precision": 0.7954926941267795,
    "eval_recall": 0.8145635466866111,
    "eval_f1": 0.8004633351993021,
    "eval_runtime": 4.2164,
    "eval_samples_per_second": 642.252,
    "eval_steps_per_second": 10.198,
    "epoch": 2.0,
    "step": 678
  },
  {
    "loss": 0.4924,
    "grad_norm": 11.982539176940918,
    "learning_rate": 1.528613569321534e-05,
    "epoch": 2.360413589364845,
    "step": 800
  },
  {
    "loss": 0.4396,
    "grad_norm": 10.420658111572266,
    "learning_rate": 1.410619469026549e-05,
    "epoch": 2.951255539143279,
    "step": 1000
  },
  {
    "eval_loss": 0.43686869740486145,
    "eval_accuracy": 0.8319793205317577,
    "eval_precision": 0.8322550154197035,
    "eval_recall": 0.8486163782995474,
    "eval_f1": 0.839237623407653,
    "eval_runtime": 4.2136,
    "eval_samples_per_second": 642.679,
    "eval_steps_per_second": 10.205,
    "epoch": 3.0,
    "step": 1017
  },
  {
    "loss": 0.3559,
    "grad_norm": 13.99537181854248,
    "learning_rate": 1.2926253687315635e-05,
    "epoch": 3.5406203840472674,
    "step": 1200
  },
  {
    "eval_loss": 0.40422186255455017,
    "eval_accuracy": 0.8545051698670606,
    "eval_precision": 0.8628044809228071,
    "eval_recall": 0.8634142412515072,
    "eval_f1": 0.8630242724646225,
    "eval_runtime": 4.206,
    "eval_samples_per_second": 643.836,
    "eval_steps_per_second": 10.223,
    "epoch": 4.0,
    "step": 1356
  },
  {
    "loss": 0.3394,
    "grad_norm": 14.122424125671387,
    "learning_rate": 1.1746312684365783e-05,
    "epoch": 4.129985228951256,
    "step": 1400
  },
  {
    "loss": 0.2889,
    "grad_norm": 10.866605758666992,
    "learning_rate": 1.056637168141593e-05,
    "epoch": 4.72082717872969,
    "step": 1600
  },
  {
    "eval_loss": 0.4265260100364685,
    "eval_accuracy": 0.8441654357459379,
    "eval_precision": 0.8441186724361562,
    "eval_recall": 0.8647582579749038,
    "eval_f1": 0.8517152790349632,
    "eval_runtime": 4.1986,
    "eval_samples_per_second": 644.981,
    "eval_steps_per_second": 10.242,
    "epoch": 5.0,
    "step": 1695
  },
  {
    "loss": 0.2514,
    "grad_norm": 5.72359561920166,
    "learning_rate": 9.386430678466077e-06,
    "epoch": 5.310192023633678,
    "step": 1800
  },
  {
    "loss": 0.2464,
    "grad_norm": 9.600533485412598,
    "learning_rate": 8.206489675516224e-06,
    "epoch": 5.901033973412112,
    "step": 2000
  },
  {
    "eval_loss": 0.389065682888031,
    "eval_accuracy": 0.8626292466765141,
    "eval_precision": 0.8652231358736173,
    "eval_recall": 0.8783380417030334,
    "eval_f1": 0.8702889928876043,
    "eval_runtime": 4.2127,
    "eval_samples_per_second": 642.817,
    "eval_steps_per_second": 10.207,
    "epoch": 6.0,
    "step": 2034
  },
  {
    "loss": 0.211,
    "grad_norm": 17.138826370239258,
    "learning_rate": 7.026548672566372e-06,
    "epoch": 6.4903988183161,
    "step": 2200
  },
  {
    "eval_loss": 0.39963972568511963,
    "eval_accuracy": 0.8674298375184638,
    "eval_precision": 0.8702205064128979,
    "eval_recall": 0.8830179653015887,
    "eval_f1": 0.8754706796586051,
    "eval_runtime": 4.256,
    "eval_samples_per_second": 636.271,
    "eval_steps_per_second": 10.103,
    "epoch": 7.0,
    "step": 2373
  },
  {
    "loss": 0.1979,
    "grad_norm": 6.464990615844727,
    "learning_rate": 5.8466076696165195e-06,
    "epoch": 7.079763663220088,
    "step": 2400
  },
  {
    "loss": 0.1781,
    "grad_norm": 9.935137748718262,
    "learning_rate": 4.666666666666667e-06,
    "epoch": 7.670605612998523,
    "step": 2600
  },
  {
    "eval_loss": 0.4202274978160858,
    "eval_accuracy": 0.8707533234859675,
    "eval_precision": 0.8721032179023319,
    "eval_recall": 0.8847283016982879,
    "eval_f1": 0.8775633088032715,
    "eval_runtime": 4.21,
    "eval_samples_per_second": 643.232,
    "eval_steps_per_second": 10.214,
    "epoch": 8.0,
    "step": 2712
  },
  {
    "loss": 0.1651,
    "grad_norm": 9.050063133239746,
    "learning_rate": 3.4867256637168144e-06,
    "epoch": 8.259970457902511,
    "step": 2800
  },
  {
    "loss": 0.1541,
    "grad_norm": 11.100234985351562,
    "learning_rate": 2.306784660766962e-06,
    "epoch": 8.850812407680944,
    "step": 3000
  },
  {
    "eval_loss": 0.4208575487136841,
    "eval_accuracy": 0.869645494830133,
    "eval_precision": 0.8718772232277948,
    "eval_recall": 0.8837444901736863,
    "eval_f1": 0.877165841562759,
    "eval_runtime": 4.2122,
    "eval_samples_per_second": 642.888,
    "eval_steps_per_second": 10.208,
    "epoch": 9.0,
    "step": 3051
  },
  {
    "loss": 0.1452,
    "grad_norm": 9.718356132507324,
    "learning_rate": 1.1268436578171092e-06,
    "epoch": 9.440177252584933,
    "step": 3200
  },
  {
    "eval_loss": 0.4245568513870239,
    "eval_accuracy": 0.8670605612998523,
    "eval_precision": 0.8694463928962631,
    "eval_recall": 0.8819628066777028,
    "eval_f1": 0.8750774553354714,
    "eval_runtime": 4.2399,
    "eval_samples_per_second": 638.697,
    "eval_steps_per_second": 10.142,
    "epoch": 10.0,
    "step": 3390
  },
  {
    "train_runtime": 1402.4702,
    "train_samples_per_second": 154.442,
    "train_steps_per_second": 2.417,
    "total_flos": 1.42477194921984e+16,
    "train_loss": 0.34887106960150344,
    "epoch": 10.0,
    "step": 3390
  }
]