Hugging Face's logo

Rustem
/
distilroberta-base-trained

Fill-Mask
Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
Rustem commited on
Commit
c78def2
·
1 Parent(s): b43c199

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +250 -0
trainer_state.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.5,
5
+ "global_step": 17500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 1.9600000000000002e-05,
13
+ "loss": 1.558,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.2,
18
+ "learning_rate": 1.9200000000000003e-05,
19
+ "loss": 1.4467,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.3,
24
+ "learning_rate": 1.88e-05,
25
+ "loss": 1.4187,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.4,
30
+ "learning_rate": 1.8400000000000003e-05,
31
+ "loss": 1.4271,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.5,
36
+ "learning_rate": 1.8e-05,
37
+ "loss": 1.4207,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.6,
42
+ "learning_rate": 1.76e-05,
43
+ "loss": 1.4212,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.7,
48
+ "learning_rate": 1.72e-05,
49
+ "loss": 1.4041,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.8,
54
+ "learning_rate": 1.6800000000000002e-05,
55
+ "loss": 1.4028,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.9,
60
+ "learning_rate": 1.64e-05,
61
+ "loss": 1.3807,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.0,
66
+ "learning_rate": 1.6000000000000003e-05,
67
+ "loss": 1.3853,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.0,
72
+ "eval_loss": 1.2580437660217285,
73
+ "eval_runtime": 314.0588,
74
+ "eval_samples_per_second": 31.841,
75
+ "eval_steps_per_second": 3.98,
76
+ "step": 5000
77
+ },
78
+ {
79
+ "epoch": 1.1,
80
+ "learning_rate": 1.5600000000000003e-05,
81
+ "loss": 1.3783,
82
+ "step": 5500
83
+ },
84
+ {
85
+ "epoch": 1.2,
86
+ "learning_rate": 1.5200000000000002e-05,
87
+ "loss": 1.3674,
88
+ "step": 6000
89
+ },
90
+ {
91
+ "epoch": 1.3,
92
+ "learning_rate": 1.48e-05,
93
+ "loss": 1.369,
94
+ "step": 6500
95
+ },
96
+ {
97
+ "epoch": 1.4,
98
+ "learning_rate": 1.4400000000000001e-05,
99
+ "loss": 1.3729,
100
+ "step": 7000
101
+ },
102
+ {
103
+ "epoch": 1.5,
104
+ "learning_rate": 1.4e-05,
105
+ "loss": 1.3774,
106
+ "step": 7500
107
+ },
108
+ {
109
+ "epoch": 1.6,
110
+ "learning_rate": 1.3600000000000002e-05,
111
+ "loss": 1.3641,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 1.7,
116
+ "learning_rate": 1.3200000000000002e-05,
117
+ "loss": 1.3798,
118
+ "step": 8500
119
+ },
120
+ {
121
+ "epoch": 1.8,
122
+ "learning_rate": 1.2800000000000001e-05,
123
+ "loss": 1.3602,
124
+ "step": 9000
125
+ },
126
+ {
127
+ "epoch": 1.9,
128
+ "learning_rate": 1.2400000000000002e-05,
129
+ "loss": 1.3641,
130
+ "step": 9500
131
+ },
132
+ {
133
+ "epoch": 2.0,
134
+ "learning_rate": 1.2e-05,
135
+ "loss": 1.3537,
136
+ "step": 10000
137
+ },
138
+ {
139
+ "epoch": 2.0,
140
+ "eval_loss": 1.234650731086731,
141
+ "eval_runtime": 312.8974,
142
+ "eval_samples_per_second": 31.959,
143
+ "eval_steps_per_second": 3.995,
144
+ "step": 10000
145
+ },
146
+ {
147
+ "epoch": 2.1,
148
+ "learning_rate": 1.16e-05,
149
+ "loss": 1.3352,
150
+ "step": 10500
151
+ },
152
+ {
153
+ "epoch": 2.2,
154
+ "learning_rate": 1.1200000000000001e-05,
155
+ "loss": 1.3482,
156
+ "step": 11000
157
+ },
158
+ {
159
+ "epoch": 2.3,
160
+ "learning_rate": 1.0800000000000002e-05,
161
+ "loss": 1.3437,
162
+ "step": 11500
163
+ },
164
+ {
165
+ "epoch": 2.4,
166
+ "learning_rate": 1.04e-05,
167
+ "loss": 1.3391,
168
+ "step": 12000
169
+ },
170
+ {
171
+ "epoch": 2.5,
172
+ "learning_rate": 1e-05,
173
+ "loss": 1.3408,
174
+ "step": 12500
175
+ },
176
+ {
177
+ "epoch": 2.6,
178
+ "learning_rate": 9.600000000000001e-06,
179
+ "loss": 1.335,
180
+ "step": 13000
181
+ },
182
+ {
183
+ "epoch": 2.7,
184
+ "learning_rate": 9.200000000000002e-06,
185
+ "loss": 1.3334,
186
+ "step": 13500
187
+ },
188
+ {
189
+ "epoch": 2.8,
190
+ "learning_rate": 8.8e-06,
191
+ "loss": 1.3466,
192
+ "step": 14000
193
+ },
194
+ {
195
+ "epoch": 2.9,
196
+ "learning_rate": 8.400000000000001e-06,
197
+ "loss": 1.3279,
198
+ "step": 14500
199
+ },
200
+ {
201
+ "epoch": 3.0,
202
+ "learning_rate": 8.000000000000001e-06,
203
+ "loss": 1.3286,
204
+ "step": 15000
205
+ },
206
+ {
207
+ "epoch": 3.0,
208
+ "eval_loss": 1.2182681560516357,
209
+ "eval_runtime": 313.6417,
210
+ "eval_samples_per_second": 31.884,
211
+ "eval_steps_per_second": 3.985,
212
+ "step": 15000
213
+ },
214
+ {
215
+ "epoch": 3.1,
216
+ "learning_rate": 7.600000000000001e-06,
217
+ "loss": 1.3196,
218
+ "step": 15500
219
+ },
220
+ {
221
+ "epoch": 3.2,
222
+ "learning_rate": 7.2000000000000005e-06,
223
+ "loss": 1.3267,
224
+ "step": 16000
225
+ },
226
+ {
227
+ "epoch": 3.3,
228
+ "learning_rate": 6.800000000000001e-06,
229
+ "loss": 1.3224,
230
+ "step": 16500
231
+ },
232
+ {
233
+ "epoch": 3.4,
234
+ "learning_rate": 6.4000000000000006e-06,
235
+ "loss": 1.3191,
236
+ "step": 17000
237
+ },
238
+ {
239
+ "epoch": 3.5,
240
+ "learning_rate": 6e-06,
241
+ "loss": 1.3259,
242
+ "step": 17500
243
+ }
244
+ ],
245
+ "max_steps": 25000,
246
+ "num_train_epochs": 5,
247
+ "total_flos": 1.856705292288e+16,
248
+ "trial_name": null,
249
+ "trial_params": null
250
+ }