Hugging Face's logo

mgfrantz
/
deberta_v3_finetuned_predicting_effective_arguments

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
deberta-v2
Inference Endpoints
Model card Files Metrics Community
1
mgfrantz commited on
Commit
8fdedac
•
1 Parent(s): 7265fb2

commit files to HF hub

Browse files
Files changed (36) hide show
  1. added_tokens.json +3 -0
  2. checkpoint-10000/added_tokens.json +3 -0
  3. checkpoint-10000/config.json +45 -0
  4. checkpoint-10000/optimizer.pt +3 -0
  5. checkpoint-10000/pytorch_model.bin +3 -0
  6. checkpoint-10000/rng_state.pth +3 -0
  7. checkpoint-10000/scaler.pt +3 -0
  8. checkpoint-10000/scheduler.pt +3 -0
  9. checkpoint-10000/special_tokens_map.json +9 -0
  10. checkpoint-10000/spm.model +3 -0
  11. checkpoint-10000/tokenizer.json +0 -0
  12. checkpoint-10000/tokenizer_config.json +18 -0
  13. checkpoint-10000/trainer_state.json +296 -0
  14. checkpoint-10000/training_args.bin +3 -0
  15. checkpoint-2000/added_tokens.json +3 -0
  16. checkpoint-2000/config.json +45 -0
  17. checkpoint-2000/optimizer.pt +3 -0
  18. checkpoint-2000/pytorch_model.bin +3 -0
  19. checkpoint-2000/rng_state.pth +3 -0
  20. checkpoint-2000/scaler.pt +3 -0
  21. checkpoint-2000/scheduler.pt +3 -0
  22. checkpoint-2000/special_tokens_map.json +9 -0
  23. checkpoint-2000/spm.model +3 -0
  24. checkpoint-2000/tokenizer.json +0 -0
  25. checkpoint-2000/tokenizer_config.json +18 -0
  26. checkpoint-2000/trainer_state.json +72 -0
  27. checkpoint-2000/training_args.bin +3 -0
  28. config.json +45 -0
  29. pytorch_model.bin +3 -0
  30. runs/Jul03_17-16-15_8a98c40ff775/1656868588.8381069/events.out.tfevents.1656868588.8a98c40ff775.71.1 +3 -0
  31. runs/Jul03_17-16-15_8a98c40ff775/events.out.tfevents.1656868588.8a98c40ff775.71.0 +3 -0
  32. special_tokens_map.json +9 -0
  33. spm.model +3 -0
  34. tokenizer.json +0 -0
  35. tokenizer_config.json +18 -0
  36. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-10000/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-10000/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta-v2",
26
+ "norm_rel_ebd": "layer_norm",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_dropout": 0,
31
+ "pooler_hidden_act": "gelu",
32
+ "pooler_hidden_size": 768,
33
+ "pos_att_type": [
34
+ "p2c",
35
+ "c2p"
36
+ ],
37
+ "position_biased_input": false,
38
+ "position_buckets": 256,
39
+ "relative_attention": true,
40
+ "share_att_key": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.20.1",
43
+ "type_vocab_size": 0,
44
+ "vocab_size": 128100
45
+ }
checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a71038f71294ce4bea3278ad481be4f7813e2bdc40702821a0c36c8fbf2b3bf0
3
+ size 1475512665
checkpoint-10000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec9015c37d875002cc65e6ee1eea456f1901cfec172c12336855961046aa649d
3
+ size 737770027
checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7d4a3cc28f7bedaf263d0aaa9d44d8e8dbbb9318d984a9f15d4b64025950ca
3
+ size 14503
checkpoint-10000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0efbbbbf577f80c6508c5320fd27b2a182a4c5a083ba7b8c862c224c4c39e5ea
3
+ size 559
checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4417a71fdc6b2b190384e77f425c104230eb51d1e5affb60e61f3daefae553d3
3
+ size 623
checkpoint-10000/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
+ }
checkpoint-10000/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-10000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10000/tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "name_or_path": "microsoft/deberta-v3-base",
8
+ "pad_token": "[PAD]",
9
+ "padding": true,
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "special_tokens_map_file": null,
13
+ "split_by_punct": false,
14
+ "tokenizer_class": "DebertaV2Tokenizer",
15
+ "truncation": true,
16
+ "unk_token": "[UNK]",
17
+ "vocab_type": "spm"
18
+ }
checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6859038472175598,
3
+ "best_model_checkpoint": "deberta_v3_finetuned_predicting_effective_arguments/checkpoint-2000",
4
+ "epoch": 4.835287009063444,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.24,
12
+ "learning_rate": 9.518375241779499e-06,
13
+ "loss": 0.8315,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.24,
18
+ "eval_loss": 0.7444673180580139,
19
+ "eval_runtime": 29.7252,
20
+ "eval_samples_per_second": 123.33,
21
+ "eval_steps_per_second": 30.849,
22
+ "step": 500
23
+ },
24
+ {
25
+ "epoch": 0.48,
26
+ "learning_rate": 9.034816247582205e-06,
27
+ "loss": 0.7232,
28
+ "step": 1000
29
+ },
30
+ {
31
+ "epoch": 0.48,
32
+ "eval_loss": 0.7441162467002869,
33
+ "eval_runtime": 29.4226,
34
+ "eval_samples_per_second": 124.598,
35
+ "eval_steps_per_second": 31.167,
36
+ "step": 1000
37
+ },
38
+ {
39
+ "epoch": 0.73,
40
+ "learning_rate": 8.552224371373308e-06,
41
+ "loss": 0.7269,
42
+ "step": 1500
43
+ },
44
+ {
45
+ "epoch": 0.73,
46
+ "eval_loss": 0.7453668117523193,
47
+ "eval_runtime": 29.5754,
48
+ "eval_samples_per_second": 123.955,
49
+ "eval_steps_per_second": 31.006,
50
+ "step": 1500
51
+ },
52
+ {
53
+ "epoch": 0.97,
54
+ "learning_rate": 8.068665377176016e-06,
55
+ "loss": 0.7185,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 0.97,
60
+ "eval_loss": 0.6859038472175598,
61
+ "eval_runtime": 29.569,
62
+ "eval_samples_per_second": 123.981,
63
+ "eval_steps_per_second": 31.012,
64
+ "step": 2000
65
+ },
66
+ {
67
+ "epoch": 1.21,
68
+ "learning_rate": 7.585106382978724e-06,
69
+ "loss": 0.6611,
70
+ "step": 2500
71
+ },
72
+ {
73
+ "epoch": 1.21,
74
+ "eval_loss": 0.6883463263511658,
75
+ "eval_runtime": 29.5377,
76
+ "eval_samples_per_second": 124.113,
77
+ "eval_steps_per_second": 31.045,
78
+ "step": 2500
79
+ },
80
+ {
81
+ "epoch": 1.45,
82
+ "learning_rate": 7.101547388781432e-06,
83
+ "loss": 0.6516,
84
+ "step": 3000
85
+ },
86
+ {
87
+ "epoch": 1.45,
88
+ "eval_loss": 0.7088809013366699,
89
+ "eval_runtime": 29.1585,
90
+ "eval_samples_per_second": 125.727,
91
+ "eval_steps_per_second": 31.449,
92
+ "step": 3000
93
+ },
94
+ {
95
+ "epoch": 1.69,
96
+ "learning_rate": 6.617988394584139e-06,
97
+ "loss": 0.6386,
98
+ "step": 3500
99
+ },
100
+ {
101
+ "epoch": 1.69,
102
+ "eval_loss": 0.6939310431480408,
103
+ "eval_runtime": 29.2346,
104
+ "eval_samples_per_second": 125.399,
105
+ "eval_steps_per_second": 31.367,
106
+ "step": 3500
107
+ },
108
+ {
109
+ "epoch": 1.93,
110
+ "learning_rate": 6.134429400386848e-06,
111
+ "loss": 0.6435,
112
+ "step": 4000
113
+ },
114
+ {
115
+ "epoch": 1.93,
116
+ "eval_loss": 0.6942200064659119,
117
+ "eval_runtime": 30.0324,
118
+ "eval_samples_per_second": 122.068,
119
+ "eval_steps_per_second": 30.534,
120
+ "step": 4000
121
+ },
122
+ {
123
+ "epoch": 2.18,
124
+ "learning_rate": 5.650870406189556e-06,
125
+ "loss": 0.5823,
126
+ "step": 4500
127
+ },
128
+ {
129
+ "epoch": 2.18,
130
+ "eval_loss": 0.771172821521759,
131
+ "eval_runtime": 29.4927,
132
+ "eval_samples_per_second": 124.302,
133
+ "eval_steps_per_second": 31.092,
134
+ "step": 4500
135
+ },
136
+ {
137
+ "epoch": 2.42,
138
+ "learning_rate": 5.167311411992263e-06,
139
+ "loss": 0.5652,
140
+ "step": 5000
141
+ },
142
+ {
143
+ "epoch": 2.42,
144
+ "eval_loss": 0.7315438985824585,
145
+ "eval_runtime": 28.9938,
146
+ "eval_samples_per_second": 126.441,
147
+ "eval_steps_per_second": 31.627,
148
+ "step": 5000
149
+ },
150
+ {
151
+ "epoch": 2.66,
152
+ "learning_rate": 4.683752417794971e-06,
153
+ "loss": 0.5701,
154
+ "step": 5500
155
+ },
156
+ {
157
+ "epoch": 2.66,
158
+ "eval_loss": 0.7429590225219727,
159
+ "eval_runtime": 29.2482,
160
+ "eval_samples_per_second": 125.341,
161
+ "eval_steps_per_second": 31.352,
162
+ "step": 5500
163
+ },
164
+ {
165
+ "epoch": 2.9,
166
+ "learning_rate": 4.20019342359768e-06,
167
+ "loss": 0.5583,
168
+ "step": 6000
169
+ },
170
+ {
171
+ "epoch": 2.9,
172
+ "eval_loss": 0.74286949634552,
173
+ "eval_runtime": 28.9549,
174
+ "eval_samples_per_second": 126.611,
175
+ "eval_steps_per_second": 31.67,
176
+ "step": 6000
177
+ },
178
+ {
179
+ "epoch": 3.14,
180
+ "learning_rate": 3.7176015473887818e-06,
181
+ "loss": 0.5145,
182
+ "step": 6500
183
+ },
184
+ {
185
+ "epoch": 3.14,
186
+ "eval_loss": 0.8086823225021362,
187
+ "eval_runtime": 29.0547,
188
+ "eval_samples_per_second": 126.176,
189
+ "eval_steps_per_second": 31.561,
190
+ "step": 6500
191
+ },
192
+ {
193
+ "epoch": 3.38,
194
+ "learning_rate": 3.23404255319149e-06,
195
+ "loss": 0.4795,
196
+ "step": 7000
197
+ },
198
+ {
199
+ "epoch": 3.38,
200
+ "eval_loss": 0.8026116490364075,
201
+ "eval_runtime": 28.8514,
202
+ "eval_samples_per_second": 127.065,
203
+ "eval_steps_per_second": 31.784,
204
+ "step": 7000
205
+ },
206
+ {
207
+ "epoch": 3.63,
208
+ "learning_rate": 2.7504835589941973e-06,
209
+ "loss": 0.4784,
210
+ "step": 7500
211
+ },
212
+ {
213
+ "epoch": 3.63,
214
+ "eval_loss": 0.7970021963119507,
215
+ "eval_runtime": 28.8445,
216
+ "eval_samples_per_second": 127.095,
217
+ "eval_steps_per_second": 31.791,
218
+ "step": 7500
219
+ },
220
+ {
221
+ "epoch": 3.87,
222
+ "learning_rate": 2.2669245647969055e-06,
223
+ "loss": 0.4793,
224
+ "step": 8000
225
+ },
226
+ {
227
+ "epoch": 3.87,
228
+ "eval_loss": 0.7971013784408569,
229
+ "eval_runtime": 29.079,
230
+ "eval_samples_per_second": 126.07,
231
+ "eval_steps_per_second": 31.535,
232
+ "step": 8000
233
+ },
234
+ {
235
+ "epoch": 4.11,
236
+ "learning_rate": 1.784332688588008e-06,
237
+ "loss": 0.4544,
238
+ "step": 8500
239
+ },
240
+ {
241
+ "epoch": 4.11,
242
+ "eval_loss": 0.8546438813209534,
243
+ "eval_runtime": 29.1238,
244
+ "eval_samples_per_second": 125.877,
245
+ "eval_steps_per_second": 31.486,
246
+ "step": 8500
247
+ },
248
+ {
249
+ "epoch": 4.35,
250
+ "learning_rate": 1.3007736943907157e-06,
251
+ "loss": 0.4115,
252
+ "step": 9000
253
+ },
254
+ {
255
+ "epoch": 4.35,
256
+ "eval_loss": 0.8430052995681763,
257
+ "eval_runtime": 29.3455,
258
+ "eval_samples_per_second": 124.926,
259
+ "eval_steps_per_second": 31.248,
260
+ "step": 9000
261
+ },
262
+ {
263
+ "epoch": 4.59,
264
+ "learning_rate": 8.172147001934237e-07,
265
+ "loss": 0.4192,
266
+ "step": 9500
267
+ },
268
+ {
269
+ "epoch": 4.59,
270
+ "eval_loss": 0.8553691506385803,
271
+ "eval_runtime": 30.0888,
272
+ "eval_samples_per_second": 121.839,
273
+ "eval_steps_per_second": 30.476,
274
+ "step": 9500
275
+ },
276
+ {
277
+ "epoch": 4.84,
278
+ "learning_rate": 3.3365570599613157e-07,
279
+ "loss": 0.4101,
280
+ "step": 10000
281
+ },
282
+ {
283
+ "epoch": 4.84,
284
+ "eval_loss": 0.863072395324707,
285
+ "eval_runtime": 29.1167,
286
+ "eval_samples_per_second": 125.907,
287
+ "eval_steps_per_second": 31.494,
288
+ "step": 10000
289
+ }
290
+ ],
291
+ "max_steps": 10340,
292
+ "num_train_epochs": 5,
293
+ "total_flos": 9148295382909930.0,
294
+ "trial_name": null,
295
+ "trial_params": null
296
+ }
checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c733ade4e8726b7d2050d20982a2b640dde2dd40f5221ce54a078013d218d18
3
+ size 3375
checkpoint-2000/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
checkpoint-2000/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta-v2",
26
+ "norm_rel_ebd": "layer_norm",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_dropout": 0,
31
+ "pooler_hidden_act": "gelu",
32
+ "pooler_hidden_size": 768,
33
+ "pos_att_type": [
34
+ "p2c",
35
+ "c2p"
36
+ ],
37
+ "position_biased_input": false,
38
+ "position_buckets": 256,
39
+ "relative_attention": true,
40
+ "share_att_key": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.20.1",
43
+ "type_vocab_size": 0,
44
+ "vocab_size": 128100
45
+ }
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473042aa6b50e90eeafe35a0eb6c00fdf7e8130b0c124e8e6bae633a7aaeb83e
3
+ size 1475512665
checkpoint-2000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152f4de359aa4e010c15c54e93a34fb1197afb81c06c241d2c177d699fd0641c
3
+ size 737770027
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7cb5f5ba70a378637f312cfcaa024819078650cf5a9b71109c9eef84768726b
3
+ size 14503
checkpoint-2000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9630290c2855c60ed3fcbed4eeefb978189ee21116d8c9e5613dc0cf8dde2d3
3
+ size 559
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33176767ded0ce16da286202ede558cb1cf892fa297e9e9cca486a46978b6600
3
+ size 623
checkpoint-2000/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
+ }
checkpoint-2000/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "name_or_path": "microsoft/deberta-v3-base",
8
+ "pad_token": "[PAD]",
9
+ "padding": true,
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "special_tokens_map_file": null,
13
+ "split_by_punct": false,
14
+ "tokenizer_class": "DebertaV2Tokenizer",
15
+ "truncation": true,
16
+ "unk_token": "[UNK]",
17
+ "vocab_type": "spm"
18
+ }
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6859038472175598,
3
+ "best_model_checkpoint": "deberta_v3_finetuned_predicting_effective_arguments/checkpoint-2000",
4
+ "epoch": 0.9667673716012085,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.24,
12
+ "learning_rate": 9.518375241779499e-06,
13
+ "loss": 0.8315,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.24,
18
+ "eval_loss": 0.7444673180580139,
19
+ "eval_runtime": 29.7252,
20
+ "eval_samples_per_second": 123.33,
21
+ "eval_steps_per_second": 30.849,
22
+ "step": 500
23
+ },
24
+ {
25
+ "epoch": 0.48,
26
+ "learning_rate": 9.034816247582205e-06,
27
+ "loss": 0.7232,
28
+ "step": 1000
29
+ },
30
+ {
31
+ "epoch": 0.48,
32
+ "eval_loss": 0.7441162467002869,
33
+ "eval_runtime": 29.4226,
34
+ "eval_samples_per_second": 124.598,
35
+ "eval_steps_per_second": 31.167,
36
+ "step": 1000
37
+ },
38
+ {
39
+ "epoch": 0.73,
40
+ "learning_rate": 8.552224371373308e-06,
41
+ "loss": 0.7269,
42
+ "step": 1500
43
+ },
44
+ {
45
+ "epoch": 0.73,
46
+ "eval_loss": 0.7453668117523193,
47
+ "eval_runtime": 29.5754,
48
+ "eval_samples_per_second": 123.955,
49
+ "eval_steps_per_second": 31.006,
50
+ "step": 1500
51
+ },
52
+ {
53
+ "epoch": 0.97,
54
+ "learning_rate": 8.068665377176016e-06,
55
+ "loss": 0.7185,
56
+ "step": 2000
57
+ },
58
+ {
59
+ "epoch": 0.97,
60
+ "eval_loss": 0.6859038472175598,
61
+ "eval_runtime": 29.569,
62
+ "eval_samples_per_second": 123.981,
63
+ "eval_steps_per_second": 31.012,
64
+ "step": 2000
65
+ }
66
+ ],
67
+ "max_steps": 10340,
68
+ "num_train_epochs": 5,
69
+ "total_flos": 1822810502059560.0,
70
+ "trial_name": null,
71
+ "trial_params": null
72
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c733ade4e8726b7d2050d20982a2b640dde2dd40f5221ce54a078013d218d18
3
+ size 3375
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "LABEL_0": 0,
19
+ "LABEL_1": 1,
20
+ "LABEL_2": 2
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta-v2",
26
+ "norm_rel_ebd": "layer_norm",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_dropout": 0,
31
+ "pooler_hidden_act": "gelu",
32
+ "pooler_hidden_size": 768,
33
+ "pos_att_type": [
34
+ "p2c",
35
+ "c2p"
36
+ ],
37
+ "position_biased_input": false,
38
+ "position_buckets": 256,
39
+ "relative_attention": true,
40
+ "share_att_key": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.20.1",
43
+ "type_vocab_size": 0,
44
+ "vocab_size": 128100
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152f4de359aa4e010c15c54e93a34fb1197afb81c06c241d2c177d699fd0641c
3
+ size 737770027
runs/Jul03_17-16-15_8a98c40ff775/1656868588.8381069/events.out.tfevents.1656868588.8a98c40ff775.71.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a91a894342ce694eb4bb9fcf877374867217236e883fbbdd94ac75ace1877e2
3
+ size 5435
runs/Jul03_17-16-15_8a98c40ff775/events.out.tfevents.1656868588.8a98c40ff775.71.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3617a801c60d083a94daa04872ab8100ae1aa4bc27f09980a749aaf121cb98
3
+ size 12918
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 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "name_or_path": "microsoft/deberta-v3-base",
8
+ "pad_token": "[PAD]",
9
+ "padding": true,
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "special_tokens_map_file": null,
13
+ "split_by_punct": false,
14
+ "tokenizer_class": "DebertaV2Tokenizer",
15
+ "truncation": true,
16
+ "unk_token": "[UNK]",
17
+ "vocab_type": "spm"
18
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c733ade4e8726b7d2050d20982a2b640dde2dd40f5221ce54a078013d218d18
3
+ size 3375