Hugging Face's logo

sigridjineth
/
ko-embedding-v1-preview-241130

Safetensors
xlm-roberta
Model card Files Community
sigridjineth commited on
Commit
571a747
·
verified ·
1 Parent(s): b19e754

Upload checkpoint-35/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-35/trainer_state.json +278 -0
checkpoint-35/trainer_state.json ADDED
@@ -0,0 +1,278 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 35,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14285714285714285,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 0,
15
+ "loss": 3.1568,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.2857142857142857,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 0,
22
+ "loss": 2.0929,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.42857142857142855,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 0,
29
+ "loss": 1.8548,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.5714285714285714,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 0,
36
+ "loss": 1.9561,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.7142857142857143,
41
+ "grad_norm": 31.57492020476853,
42
+ "learning_rate": 0.0,
43
+ "loss": 2.158,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.8571428571428571,
48
+ "grad_norm": 31.153859925878365,
49
+ "learning_rate": 2e-05,
50
+ "loss": 2.1095,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 1.0,
55
+ "grad_norm": 27.11565016529603,
56
+ "learning_rate": 2e-05,
57
+ "loss": 1.9969,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 1.1428571428571428,
62
+ "grad_norm": 11.963172987739094,
63
+ "learning_rate": 1.9393939393939395e-05,
64
+ "loss": 1.8882,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 1.2857142857142856,
69
+ "grad_norm": 12.547776129299391,
70
+ "learning_rate": 1.8787878787878792e-05,
71
+ "loss": 2.2821,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 1.4285714285714286,
76
+ "grad_norm": 13.995949840524457,
77
+ "learning_rate": 1.8181818181818182e-05,
78
+ "loss": 1.9093,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.5714285714285714,
83
+ "grad_norm": 32.10247036468728,
84
+ "learning_rate": 1.7575757575757576e-05,
85
+ "loss": 1.7738,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.7142857142857144,
90
+ "grad_norm": 12.920575409822058,
91
+ "learning_rate": 1.6969696969696972e-05,
92
+ "loss": 1.9714,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.8571428571428572,
97
+ "grad_norm": 12.06286747031755,
98
+ "learning_rate": 1.6363636363636366e-05,
99
+ "loss": 1.9296,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 2.0,
104
+ "grad_norm": 8.907029074340802,
105
+ "learning_rate": 1.575757575757576e-05,
106
+ "loss": 1.8614,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 2.142857142857143,
111
+ "grad_norm": 6.73971706849257,
112
+ "learning_rate": 1.5151515151515153e-05,
113
+ "loss": 1.6771,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 2.2857142857142856,
118
+ "grad_norm": 17.60219359166014,
119
+ "learning_rate": 1.4545454545454546e-05,
120
+ "loss": 1.8053,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 2.4285714285714284,
125
+ "grad_norm": 16.964715579903814,
126
+ "learning_rate": 1.3939393939393942e-05,
127
+ "loss": 1.6802,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 2.571428571428571,
132
+ "grad_norm": 17.69250115636477,
133
+ "learning_rate": 1.3333333333333333e-05,
134
+ "loss": 1.7371,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 2.7142857142857144,
139
+ "grad_norm": 15.007342258217257,
140
+ "learning_rate": 1.2727272727272728e-05,
141
+ "loss": 1.8895,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 2.857142857142857,
146
+ "grad_norm": 12.014421697915866,
147
+ "learning_rate": 1.2121212121212122e-05,
148
+ "loss": 1.74,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 3.0,
153
+ "grad_norm": 6.420645268892007,
154
+ "learning_rate": 1.1515151515151517e-05,
155
+ "loss": 1.646,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 3.142857142857143,
160
+ "grad_norm": 9.579171202930794,
161
+ "learning_rate": 1.0909090909090909e-05,
162
+ "loss": 1.783,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 3.2857142857142856,
167
+ "grad_norm": 9.480870311077393,
168
+ "learning_rate": 1.0303030303030304e-05,
169
+ "loss": 1.6975,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 3.4285714285714284,
174
+ "grad_norm": 11.085052433397502,
175
+ "learning_rate": 9.696969696969698e-06,
176
+ "loss": 1.5964,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 3.571428571428571,
181
+ "grad_norm": 10.405891481014418,
182
+ "learning_rate": 9.090909090909091e-06,
183
+ "loss": 1.8499,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 3.7142857142857144,
188
+ "grad_norm": 7.19377512459299,
189
+ "learning_rate": 8.484848484848486e-06,
190
+ "loss": 1.9397,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 3.857142857142857,
195
+ "grad_norm": 20.100305416386867,
196
+ "learning_rate": 7.87878787878788e-06,
197
+ "loss": 1.6575,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 4.0,
202
+ "grad_norm": 6.598534461792029,
203
+ "learning_rate": 7.272727272727273e-06,
204
+ "loss": 1.8201,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 4.142857142857143,
209
+ "grad_norm": 7.697231181333111,
210
+ "learning_rate": 6.666666666666667e-06,
211
+ "loss": 1.6547,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 4.285714285714286,
216
+ "grad_norm": 5.6666359994095865,
217
+ "learning_rate": 6.060606060606061e-06,
218
+ "loss": 1.6578,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 4.428571428571429,
223
+ "grad_norm": 9.64546505010074,
224
+ "learning_rate": 5.4545454545454545e-06,
225
+ "loss": 1.5213,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 4.571428571428571,
230
+ "grad_norm": 7.511399316368516,
231
+ "learning_rate": 4.848484848484849e-06,
232
+ "loss": 1.7394,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 4.714285714285714,
237
+ "grad_norm": 11.799130579067045,
238
+ "learning_rate": 4.242424242424243e-06,
239
+ "loss": 1.7876,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 4.857142857142857,
244
+ "grad_norm": 8.101541311297026,
245
+ "learning_rate": 3.6363636363636366e-06,
246
+ "loss": 1.7558,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 5.0,
251
+ "grad_norm": 11.45990563904692,
252
+ "learning_rate": 3.0303030303030305e-06,
253
+ "loss": 1.8384,
254
+ "step": 35
255
+ }
256
+ ],
257
+ "logging_steps": 1.0,
258
+ "max_steps": 35,
259
+ "num_input_tokens_seen": 0,
260
+ "num_train_epochs": 5,
261
+ "save_steps": 1000,
262
+ "stateful_callbacks": {
263
+ "TrainerControl": {
264
+ "args": {
265
+ "should_epoch_stop": false,
266
+ "should_evaluate": false,
267
+ "should_log": false,
268
+ "should_save": true,
269
+ "should_training_stop": true
270
+ },
271
+ "attributes": {}
272
+ }
273
+ },
274
+ "total_flos": 0.0,
275
+ "train_batch_size": 1,
276
+ "trial_name": null,
277
+ "trial_params": null
278
+ }