Hugging Face's logo

Yuvrajg2107
/
roberta-base-cpp1

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Community
Yuvrajg2107 commited on
Commit
0bb2c18
·
verified ·
1 Parent(s): 888bf16

Copying last-checkpoint/trainer_state.json from Yuvrajg2107/roberta-base-cpp

Browse files
Files changed (1) hide show
  1. last-checkpoint/trainer_state.json +264 -0
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 9000,
3
+ "best_metric": 0.04935265704989433,
4
+ "best_model_checkpoint": "./training_output/checkpoint-9000",
5
+ "epoch": 0.5,
6
+ "eval_steps": 1000,
7
+ "global_step": 10000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.025,
14
+ "grad_norm": 0.8834348917007446,
15
+ "learning_rate": 1.9501000000000002e-05,
16
+ "loss": 0.1437,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.05,
21
+ "grad_norm": 9.513919830322266,
22
+ "learning_rate": 1.9001e-05,
23
+ "loss": 0.1085,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.05,
28
+ "eval_accuracy": 0.91835,
29
+ "eval_loss": 0.10802757740020752,
30
+ "eval_runtime": 381.1922,
31
+ "eval_samples_per_second": 52.467,
32
+ "eval_steps_per_second": 3.279,
33
+ "step": 1000
34
+ },
35
+ {
36
+ "epoch": 0.075,
37
+ "grad_norm": 0.013394818641245365,
38
+ "learning_rate": 1.8501e-05,
39
+ "loss": 0.0965,
40
+ "step": 1500
41
+ },
42
+ {
43
+ "epoch": 0.1,
44
+ "grad_norm": 0.017180055379867554,
45
+ "learning_rate": 1.8001000000000003e-05,
46
+ "loss": 0.0716,
47
+ "step": 2000
48
+ },
49
+ {
50
+ "epoch": 0.1,
51
+ "eval_accuracy": 0.8473,
52
+ "eval_loss": 0.25237375497817993,
53
+ "eval_runtime": 381.1616,
54
+ "eval_samples_per_second": 52.471,
55
+ "eval_steps_per_second": 3.279,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 0.125,
60
+ "grad_norm": 0.017619747668504715,
61
+ "learning_rate": 1.7501e-05,
62
+ "loss": 0.0658,
63
+ "step": 2500
64
+ },
65
+ {
66
+ "epoch": 0.15,
67
+ "grad_norm": 0.527113676071167,
68
+ "learning_rate": 1.7001000000000002e-05,
69
+ "loss": 0.0615,
70
+ "step": 3000
71
+ },
72
+ {
73
+ "epoch": 0.15,
74
+ "eval_accuracy": 0.9299,
75
+ "eval_loss": 0.11818733811378479,
76
+ "eval_runtime": 381.4889,
77
+ "eval_samples_per_second": 52.426,
78
+ "eval_steps_per_second": 3.277,
79
+ "step": 3000
80
+ },
81
+ {
82
+ "epoch": 0.175,
83
+ "grad_norm": 140.78282165527344,
84
+ "learning_rate": 1.6501e-05,
85
+ "loss": 0.056,
86
+ "step": 3500
87
+ },
88
+ {
89
+ "epoch": 0.2,
90
+ "grad_norm": 0.9989501237869263,
91
+ "learning_rate": 1.6001e-05,
92
+ "loss": 0.0648,
93
+ "step": 4000
94
+ },
95
+ {
96
+ "epoch": 0.2,
97
+ "eval_accuracy": 0.9498,
98
+ "eval_loss": 0.07567641884088516,
99
+ "eval_runtime": 380.8034,
100
+ "eval_samples_per_second": 52.521,
101
+ "eval_steps_per_second": 3.283,
102
+ "step": 4000
103
+ },
104
+ {
105
+ "epoch": 0.225,
106
+ "grad_norm": 0.01812303625047207,
107
+ "learning_rate": 1.5501000000000003e-05,
108
+ "loss": 0.0487,
109
+ "step": 4500
110
+ },
111
+ {
112
+ "epoch": 0.25,
113
+ "grad_norm": 0.05552659556269646,
114
+ "learning_rate": 1.5001000000000001e-05,
115
+ "loss": 0.0522,
116
+ "step": 5000
117
+ },
118
+ {
119
+ "epoch": 0.25,
120
+ "eval_accuracy": 0.92725,
121
+ "eval_loss": 0.12006673216819763,
122
+ "eval_runtime": 380.6188,
123
+ "eval_samples_per_second": 52.546,
124
+ "eval_steps_per_second": 3.284,
125
+ "step": 5000
126
+ },
127
+ {
128
+ "epoch": 0.275,
129
+ "grad_norm": 0.14319103956222534,
130
+ "learning_rate": 1.4501e-05,
131
+ "loss": 0.0554,
132
+ "step": 5500
133
+ },
134
+ {
135
+ "epoch": 0.3,
136
+ "grad_norm": 0.012562028132379055,
137
+ "learning_rate": 1.4001e-05,
138
+ "loss": 0.0377,
139
+ "step": 6000
140
+ },
141
+ {
142
+ "epoch": 0.3,
143
+ "eval_accuracy": 0.95545,
144
+ "eval_loss": 0.08464282751083374,
145
+ "eval_runtime": 380.6212,
146
+ "eval_samples_per_second": 52.546,
147
+ "eval_steps_per_second": 3.284,
148
+ "step": 6000
149
+ },
150
+ {
151
+ "epoch": 0.325,
152
+ "grad_norm": 0.0012805273290723562,
153
+ "learning_rate": 1.3501000000000002e-05,
154
+ "loss": 0.0327,
155
+ "step": 6500
156
+ },
157
+ {
158
+ "epoch": 0.35,
159
+ "grad_norm": 0.024555200710892677,
160
+ "learning_rate": 1.3001000000000001e-05,
161
+ "loss": 0.0447,
162
+ "step": 7000
163
+ },
164
+ {
165
+ "epoch": 0.35,
166
+ "eval_accuracy": 0.93225,
167
+ "eval_loss": 0.10355959832668304,
168
+ "eval_runtime": 380.8232,
169
+ "eval_samples_per_second": 52.518,
170
+ "eval_steps_per_second": 3.282,
171
+ "step": 7000
172
+ },
173
+ {
174
+ "epoch": 0.375,
175
+ "grad_norm": 0.10476179420948029,
176
+ "learning_rate": 1.2501000000000001e-05,
177
+ "loss": 0.0379,
178
+ "step": 7500
179
+ },
180
+ {
181
+ "epoch": 0.4,
182
+ "grad_norm": 0.16991844773292542,
183
+ "learning_rate": 1.2001e-05,
184
+ "loss": 0.0421,
185
+ "step": 8000
186
+ },
187
+ {
188
+ "epoch": 0.4,
189
+ "eval_accuracy": 0.89145,
190
+ "eval_loss": 0.1804238110780716,
191
+ "eval_runtime": 380.9125,
192
+ "eval_samples_per_second": 52.505,
193
+ "eval_steps_per_second": 3.282,
194
+ "step": 8000
195
+ },
196
+ {
197
+ "epoch": 0.425,
198
+ "grad_norm": 0.017685526981949806,
199
+ "learning_rate": 1.1501e-05,
200
+ "loss": 0.0384,
201
+ "step": 8500
202
+ },
203
+ {
204
+ "epoch": 0.45,
205
+ "grad_norm": 16.736478805541992,
206
+ "learning_rate": 1.1001000000000002e-05,
207
+ "loss": 0.0364,
208
+ "step": 9000
209
+ },
210
+ {
211
+ "epoch": 0.45,
212
+ "eval_accuracy": 0.96285,
213
+ "eval_loss": 0.04935265704989433,
214
+ "eval_runtime": 380.5923,
215
+ "eval_samples_per_second": 52.55,
216
+ "eval_steps_per_second": 3.284,
217
+ "step": 9000
218
+ },
219
+ {
220
+ "epoch": 0.475,
221
+ "grad_norm": 0.08418703079223633,
222
+ "learning_rate": 1.0501000000000002e-05,
223
+ "loss": 0.0262,
224
+ "step": 9500
225
+ },
226
+ {
227
+ "epoch": 0.5,
228
+ "grad_norm": 0.19593098759651184,
229
+ "learning_rate": 1.0001000000000001e-05,
230
+ "loss": 0.0301,
231
+ "step": 10000
232
+ },
233
+ {
234
+ "epoch": 0.5,
235
+ "eval_accuracy": 0.9689,
236
+ "eval_loss": 0.05831901729106903,
237
+ "eval_runtime": 380.4459,
238
+ "eval_samples_per_second": 52.57,
239
+ "eval_steps_per_second": 3.286,
240
+ "step": 10000
241
+ }
242
+ ],
243
+ "logging_steps": 500,
244
+ "max_steps": 20000,
245
+ "num_input_tokens_seen": 0,
246
+ "num_train_epochs": 1,
247
+ "save_steps": 1000,
248
+ "stateful_callbacks": {
249
+ "TrainerControl": {
250
+ "args": {
251
+ "should_epoch_stop": false,
252
+ "should_evaluate": false,
253
+ "should_log": false,
254
+ "should_save": true,
255
+ "should_training_stop": false
256
+ },
257
+ "attributes": {}
258
+ }
259
+ },
260
+ "total_flos": 1.05244422144e+16,
261
+ "train_batch_size": 2,
262
+ "trial_name": null,
263
+ "trial_params": null
264
+ }