manandey commited on
Commit
8898a3d
1 Parent(s): 3511073

upload files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0582bec6ed6606c76c854e7696e32ab6179215f11570ad2f21c21d11d3c4661
3
+ size 111345664
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73da78b082a7f33e627a2df0b3d7892283aaf8a6643ebf4c27530ec118d31df
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4160982482f3f0b7ac64721302e69f822b630e5fa016fd98a99174656f487867
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "name_or_path": "microsoft/deberta-v3-base",
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "special_tokens_map_file": null,
13
+ "split_by_punct": false,
14
+ "tokenizer_class": "DebertaV2Tokenizer",
15
+ "unk_token": "[UNK]",
16
+ "vocab_type": "spm"
17
+ }
trainer_state.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.09626218676567078,
3
+ "best_model_checkpoint": "checkpoint/checkpoint-300000",
4
+ "epoch": 0.8551077008149176,
5
+ "global_step": 300000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 1.942992819945672e-05,
13
+ "loss": 0.0499,
14
+ "step": 10000
15
+ },
16
+ {
17
+ "epoch": 0.06,
18
+ "learning_rate": 1.8859856398913445e-05,
19
+ "loss": 0.0274,
20
+ "step": 20000
21
+ },
22
+ {
23
+ "epoch": 0.09,
24
+ "learning_rate": 1.8289784598370164e-05,
25
+ "loss": 0.0244,
26
+ "step": 30000
27
+ },
28
+ {
29
+ "epoch": 0.11,
30
+ "learning_rate": 1.7719712797826888e-05,
31
+ "loss": 0.0218,
32
+ "step": 40000
33
+ },
34
+ {
35
+ "epoch": 0.14,
36
+ "learning_rate": 1.714964099728361e-05,
37
+ "loss": 0.0208,
38
+ "step": 50000
39
+ },
40
+ {
41
+ "epoch": 0.14,
42
+ "eval_accuracy": 0.9703630265572595,
43
+ "eval_f1": 0.9697362965196742,
44
+ "eval_loss": 0.19255024194717407,
45
+ "eval_precision": 0.9906862367555316,
46
+ "eval_recall": 0.949654059527074,
47
+ "eval_runtime": 7138.3308,
48
+ "eval_samples_per_second": 53.13,
49
+ "eval_steps_per_second": 6.641,
50
+ "step": 50000
51
+ },
52
+ {
53
+ "epoch": 0.17,
54
+ "learning_rate": 1.657956919674033e-05,
55
+ "loss": 0.018,
56
+ "step": 60000
57
+ },
58
+ {
59
+ "epoch": 0.2,
60
+ "learning_rate": 1.600949739619705e-05,
61
+ "loss": 0.0173,
62
+ "step": 70000
63
+ },
64
+ {
65
+ "epoch": 0.23,
66
+ "learning_rate": 1.5439425595653774e-05,
67
+ "loss": 0.0182,
68
+ "step": 80000
69
+ },
70
+ {
71
+ "epoch": 0.26,
72
+ "learning_rate": 1.4869353795110495e-05,
73
+ "loss": 0.0168,
74
+ "step": 90000
75
+ },
76
+ {
77
+ "epoch": 0.29,
78
+ "learning_rate": 1.4299281994567218e-05,
79
+ "loss": 0.0152,
80
+ "step": 100000
81
+ },
82
+ {
83
+ "epoch": 0.29,
84
+ "eval_accuracy": 0.9694269833568883,
85
+ "eval_f1": 0.9686356296001752,
86
+ "eval_loss": 0.26416775584220886,
87
+ "eval_precision": 0.9943740662782754,
88
+ "eval_recall": 0.9441960048094163,
89
+ "eval_runtime": 7120.7469,
90
+ "eval_samples_per_second": 53.261,
91
+ "eval_steps_per_second": 6.658,
92
+ "step": 100000
93
+ },
94
+ {
95
+ "epoch": 0.31,
96
+ "learning_rate": 1.3729210194023938e-05,
97
+ "loss": 0.0167,
98
+ "step": 110000
99
+ },
100
+ {
101
+ "epoch": 0.34,
102
+ "learning_rate": 1.315913839348066e-05,
103
+ "loss": 0.0143,
104
+ "step": 120000
105
+ },
106
+ {
107
+ "epoch": 0.37,
108
+ "learning_rate": 1.2589066592937383e-05,
109
+ "loss": 0.0151,
110
+ "step": 130000
111
+ },
112
+ {
113
+ "epoch": 0.4,
114
+ "learning_rate": 1.2018994792394103e-05,
115
+ "loss": 0.0127,
116
+ "step": 140000
117
+ },
118
+ {
119
+ "epoch": 0.43,
120
+ "learning_rate": 1.1448922991850824e-05,
121
+ "loss": 0.0129,
122
+ "step": 150000
123
+ },
124
+ {
125
+ "epoch": 0.43,
126
+ "eval_accuracy": 0.9814399772185542,
127
+ "eval_f1": 0.9811897565811801,
128
+ "eval_loss": 0.14654095470905304,
129
+ "eval_precision": 0.9945986358440376,
130
+ "eval_recall": 0.9681376168076444,
131
+ "eval_runtime": 7098.6821,
132
+ "eval_samples_per_second": 53.426,
133
+ "eval_steps_per_second": 6.678,
134
+ "step": 150000
135
+ },
136
+ {
137
+ "epoch": 0.46,
138
+ "learning_rate": 1.0878851191307547e-05,
139
+ "loss": 0.0166,
140
+ "step": 160000
141
+ },
142
+ {
143
+ "epoch": 0.48,
144
+ "learning_rate": 1.0308779390764267e-05,
145
+ "loss": 0.0133,
146
+ "step": 170000
147
+ },
148
+ {
149
+ "epoch": 0.51,
150
+ "learning_rate": 9.738707590220989e-06,
151
+ "loss": 0.0117,
152
+ "step": 180000
153
+ },
154
+ {
155
+ "epoch": 0.54,
156
+ "learning_rate": 9.168635789677712e-06,
157
+ "loss": 0.0104,
158
+ "step": 190000
159
+ },
160
+ {
161
+ "epoch": 0.57,
162
+ "learning_rate": 8.598563989134432e-06,
163
+ "loss": 0.0111,
164
+ "step": 200000
165
+ },
166
+ {
167
+ "epoch": 0.57,
168
+ "eval_accuracy": 0.9705159575590103,
169
+ "eval_f1": 0.9696535478373199,
170
+ "eval_loss": 0.31930962204933167,
171
+ "eval_precision": 0.9988705619233995,
172
+ "eval_recall": 0.9420971586474571,
173
+ "eval_runtime": 7105.0574,
174
+ "eval_samples_per_second": 53.378,
175
+ "eval_steps_per_second": 6.672,
176
+ "step": 200000
177
+ },
178
+ {
179
+ "epoch": 0.6,
180
+ "learning_rate": 8.028492188591153e-06,
181
+ "loss": 0.0103,
182
+ "step": 210000
183
+ },
184
+ {
185
+ "epoch": 0.63,
186
+ "learning_rate": 7.4584203880478754e-06,
187
+ "loss": 0.0113,
188
+ "step": 220000
189
+ },
190
+ {
191
+ "epoch": 0.66,
192
+ "learning_rate": 6.888348587504596e-06,
193
+ "loss": 0.0083,
194
+ "step": 230000
195
+ },
196
+ {
197
+ "epoch": 0.68,
198
+ "learning_rate": 6.3182767869613184e-06,
199
+ "loss": 0.008,
200
+ "step": 240000
201
+ },
202
+ {
203
+ "epoch": 0.71,
204
+ "learning_rate": 5.74820498641804e-06,
205
+ "loss": 0.008,
206
+ "step": 250000
207
+ },
208
+ {
209
+ "epoch": 0.71,
210
+ "eval_accuracy": 0.976308878435674,
211
+ "eval_f1": 0.9758237027270649,
212
+ "eval_loss": 0.20410259068012238,
213
+ "eval_precision": 0.996225627276573,
214
+ "eval_recall": 0.9562406395679963,
215
+ "eval_runtime": 7119.7261,
216
+ "eval_samples_per_second": 53.268,
217
+ "eval_steps_per_second": 6.659,
218
+ "step": 250000
219
+ },
220
+ {
221
+ "epoch": 0.74,
222
+ "learning_rate": 5.178133185874762e-06,
223
+ "loss": 0.0086,
224
+ "step": 260000
225
+ },
226
+ {
227
+ "epoch": 0.77,
228
+ "learning_rate": 4.608061385331483e-06,
229
+ "loss": 0.0067,
230
+ "step": 270000
231
+ },
232
+ {
233
+ "epoch": 0.8,
234
+ "learning_rate": 4.0379895847882044e-06,
235
+ "loss": 0.007,
236
+ "step": 280000
237
+ },
238
+ {
239
+ "epoch": 0.83,
240
+ "learning_rate": 3.467917784244926e-06,
241
+ "loss": 0.0059,
242
+ "step": 290000
243
+ },
244
+ {
245
+ "epoch": 0.86,
246
+ "learning_rate": 2.8978459837016474e-06,
247
+ "loss": 0.0061,
248
+ "step": 300000
249
+ },
250
+ {
251
+ "epoch": 0.86,
252
+ "eval_accuracy": 0.9880529246735714,
253
+ "eval_f1": 0.9879724036876487,
254
+ "eval_loss": 0.09626218676567078,
255
+ "eval_precision": 0.9946763305164922,
256
+ "eval_recall": 0.9813582382348598,
257
+ "eval_runtime": 7136.9095,
258
+ "eval_samples_per_second": 53.14,
259
+ "eval_steps_per_second": 6.643,
260
+ "step": 300000
261
+ }
262
+ ],
263
+ "max_steps": 350833,
264
+ "num_train_epochs": 1,
265
+ "total_flos": 2.7489826686811325e+17,
266
+ "trial_name": null,
267
+ "trial_params": null
268
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db37a27b318488e5617d37a01966b6608b0f36b9b17dcd71e29f79af2c4e226e
3
+ size 3451