cite-text-analysis commited on
Commit
fc2ac9e
1 Parent(s): baa7edc

Upload folder using huggingface_hub

Browse files
training_checkpoints/checkpoint-2464/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 30522
3
+ }
training_checkpoints/checkpoint-2464/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nlpaueb/legal-bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_ids": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "positive",
15
+ "1": "negative",
16
+ "2": "neutral",
17
+ "3": "rel_by_party"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "negative": 1,
23
+ "neutral": 2,
24
+ "positive": 0,
25
+ "rel_by_party": 3
26
+ },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "output_past": true,
33
+ "pad_token_id": 30522,
34
+ "position_embedding_type": "absolute",
35
+ "problem_type": "single_label_classification",
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.40.2",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 30523
41
+ }
training_checkpoints/checkpoint-2464/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d3f3dc9c6e72db7ba3c1d15654969bba711dc22517c5dd51672049556f70a4
3
+ size 437967872
training_checkpoints/checkpoint-2464/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6036a3ff5cd6ea73fcbf82e80279c7888536c450e4fc69551f9078fa2edd0535
3
+ size 876056826
training_checkpoints/checkpoint-2464/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14def76d9a465eb7c7b8c88eb9fb477fba82bbe2823ee721e9f617fef6bcf6b
3
+ size 14244
training_checkpoints/checkpoint-2464/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11996043b68640f1454b8144d16f83260f66208aaf3d2eecc3f7ef74a99b97c
3
+ size 1064
training_checkpoints/checkpoint-2464/special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "sep_token": "[SEP]",
12
+ "unk_token": "[UNK]"
13
+ }
training_checkpoints/checkpoint-2464/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
training_checkpoints/checkpoint-2464/tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30522": {
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "clean_up_tokenization_spaces": true,
53
+ "cls_token": "[CLS]",
54
+ "do_basic_tokenize": true,
55
+ "do_lower_case": true,
56
+ "mask_token": "[MASK]",
57
+ "model_max_length": 512,
58
+ "never_split": null,
59
+ "pad_token": "<pad>",
60
+ "sep_token": "[SEP]",
61
+ "strip_accents": null,
62
+ "tokenize_chinese_chars": true,
63
+ "tokenizer_class": "BertTokenizer",
64
+ "unk_token": "[UNK]"
65
+ }
training_checkpoints/checkpoint-2464/trainer_state.json ADDED
@@ -0,0 +1,291 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6764229637898442,
3
+ "best_model_checkpoint": "case-analysis-legal-bert-base-uncased/checkpoint-2464",
4
+ "epoch": 11.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2464,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.6570155902004454,
14
+ "eval_f1_macro": 0.4081263564022185,
15
+ "eval_f1_micro": 0.6570155902004454,
16
+ "eval_f1_weighted": 0.6166399839312825,
17
+ "eval_loss": 1.0114229917526245,
18
+ "eval_macro_fpr": 0.19475132363363487,
19
+ "eval_macro_sensitivity": 0.40746667217255456,
20
+ "eval_macro_specificity": 0.8324392236563901,
21
+ "eval_precision": 0.6178816225558943,
22
+ "eval_precision_macro": 0.4664000256488353,
23
+ "eval_recall": 0.6570155902004454,
24
+ "eval_recall_macro": 0.40746667217255456,
25
+ "eval_runtime": 7.3199,
26
+ "eval_samples_per_second": 61.34,
27
+ "eval_steps_per_second": 7.787,
28
+ "eval_weighted_fpr": 0.1482194417709336,
29
+ "eval_weighted_sensitivity": 0.6570155902004454,
30
+ "eval_weighted_specificity": 0.6727413044251147,
31
+ "step": 224
32
+ },
33
+ {
34
+ "epoch": 2.0,
35
+ "eval_accuracy": 0.7750556792873051,
36
+ "eval_f1_macro": 0.5658663855845003,
37
+ "eval_f1_micro": 0.775055679287305,
38
+ "eval_f1_weighted": 0.7564492543508543,
39
+ "eval_loss": 0.764952540397644,
40
+ "eval_macro_fpr": 0.10943701020063132,
41
+ "eval_macro_sensitivity": 0.5805958747135218,
42
+ "eval_macro_specificity": 0.9039084791647444,
43
+ "eval_precision": 0.7425093237919278,
44
+ "eval_precision_macro": 0.5566158325717437,
45
+ "eval_recall": 0.7750556792873051,
46
+ "eval_recall_macro": 0.5805958747135218,
47
+ "eval_runtime": 30.7218,
48
+ "eval_samples_per_second": 14.615,
49
+ "eval_steps_per_second": 1.855,
50
+ "eval_weighted_fpr": 0.08820960698689956,
51
+ "eval_weighted_sensitivity": 0.7750556792873051,
52
+ "eval_weighted_specificity": 0.8405782373716723,
53
+ "step": 448
54
+ },
55
+ {
56
+ "epoch": 2.232142857142857,
57
+ "grad_norm": 9.53757095336914,
58
+ "learning_rate": 4.631696428571429e-05,
59
+ "loss": 0.7677,
60
+ "step": 500
61
+ },
62
+ {
63
+ "epoch": 3.0,
64
+ "eval_accuracy": 0.7817371937639198,
65
+ "eval_f1_macro": 0.5707248076329534,
66
+ "eval_f1_micro": 0.7817371937639198,
67
+ "eval_f1_weighted": 0.7678448816993292,
68
+ "eval_loss": 0.7341566681861877,
69
+ "eval_macro_fpr": 0.10409605667370833,
70
+ "eval_macro_sensitivity": 0.5967117805353099,
71
+ "eval_macro_specificity": 0.9083046086144851,
72
+ "eval_precision": 0.7694906286035585,
73
+ "eval_precision_macro": 0.5673619923602318,
74
+ "eval_recall": 0.7817371937639198,
75
+ "eval_recall_macro": 0.5967117805353099,
76
+ "eval_runtime": 32.9882,
77
+ "eval_samples_per_second": 13.611,
78
+ "eval_steps_per_second": 1.728,
79
+ "eval_weighted_fpr": 0.08514335360556038,
80
+ "eval_weighted_sensitivity": 0.7817371937639198,
81
+ "eval_weighted_specificity": 0.8514812406940205,
82
+ "step": 672
83
+ },
84
+ {
85
+ "epoch": 4.0,
86
+ "eval_accuracy": 0.8173719376391982,
87
+ "eval_f1_macro": 0.5903876477694423,
88
+ "eval_f1_micro": 0.8173719376391981,
89
+ "eval_f1_weighted": 0.7920921547144288,
90
+ "eval_loss": 0.7967568635940552,
91
+ "eval_macro_fpr": 0.09654289346260755,
92
+ "eval_macro_sensitivity": 0.5892796922208687,
93
+ "eval_macro_specificity": 0.9135512326349768,
94
+ "eval_precision": 0.776630887817645,
95
+ "eval_precision_macro": 0.6035747039094435,
96
+ "eval_recall": 0.8173719376391982,
97
+ "eval_recall_macro": 0.5892796922208687,
98
+ "eval_runtime": 31.5737,
99
+ "eval_samples_per_second": 14.221,
100
+ "eval_steps_per_second": 1.805,
101
+ "eval_weighted_fpr": 0.06931530008453085,
102
+ "eval_weighted_sensitivity": 0.8173719376391982,
103
+ "eval_weighted_specificity": 0.836832992900709,
104
+ "step": 896
105
+ },
106
+ {
107
+ "epoch": 4.464285714285714,
108
+ "grad_norm": 0.4865407943725586,
109
+ "learning_rate": 4.260416666666667e-05,
110
+ "loss": 0.482,
111
+ "step": 1000
112
+ },
113
+ {
114
+ "epoch": 5.0,
115
+ "eval_accuracy": 0.8084632516703786,
116
+ "eval_f1_macro": 0.6140549414742963,
117
+ "eval_f1_micro": 0.8084632516703786,
118
+ "eval_f1_weighted": 0.7940411816552344,
119
+ "eval_loss": 0.8170605301856995,
120
+ "eval_macro_fpr": 0.09903328320796416,
121
+ "eval_macro_sensitivity": 0.6038384641325818,
122
+ "eval_macro_specificity": 0.9107621964110777,
123
+ "eval_precision": 0.7852994506060567,
124
+ "eval_precision_macro": 0.6365555789178582,
125
+ "eval_recall": 0.8084632516703786,
126
+ "eval_recall_macro": 0.6038384641325818,
127
+ "eval_runtime": 33.691,
128
+ "eval_samples_per_second": 13.327,
129
+ "eval_steps_per_second": 1.692,
130
+ "eval_weighted_fpr": 0.07319148936170213,
131
+ "eval_weighted_sensitivity": 0.8084632516703786,
132
+ "eval_weighted_specificity": 0.8345855339739323,
133
+ "step": 1120
134
+ },
135
+ {
136
+ "epoch": 6.0,
137
+ "eval_accuracy": 0.8240534521158129,
138
+ "eval_f1_macro": 0.6314846316884821,
139
+ "eval_f1_micro": 0.8240534521158129,
140
+ "eval_f1_weighted": 0.8083544635272152,
141
+ "eval_loss": 0.8909738659858704,
142
+ "eval_macro_fpr": 0.087529695086195,
143
+ "eval_macro_sensitivity": 0.6358500402618049,
144
+ "eval_macro_specificity": 0.9211652121242622,
145
+ "eval_precision": 0.8028335761470152,
146
+ "eval_precision_macro": 0.6659870176540079,
147
+ "eval_recall": 0.8240534521158129,
148
+ "eval_recall_macro": 0.6358500402618049,
149
+ "eval_runtime": 32.5936,
150
+ "eval_samples_per_second": 13.776,
151
+ "eval_steps_per_second": 1.749,
152
+ "eval_weighted_fpr": 0.06644238856181665,
153
+ "eval_weighted_sensitivity": 0.8240534521158129,
154
+ "eval_weighted_specificity": 0.8606073963812356,
155
+ "step": 1344
156
+ },
157
+ {
158
+ "epoch": 6.696428571428571,
159
+ "grad_norm": 24.31475257873535,
160
+ "learning_rate": 3.888392857142857e-05,
161
+ "loss": 0.2993,
162
+ "step": 1500
163
+ },
164
+ {
165
+ "epoch": 7.0,
166
+ "eval_accuracy": 0.8040089086859689,
167
+ "eval_f1_macro": 0.6741993002516824,
168
+ "eval_f1_micro": 0.8040089086859689,
169
+ "eval_f1_weighted": 0.8067155865282774,
170
+ "eval_loss": 1.0094465017318726,
171
+ "eval_macro_fpr": 0.08913550870826559,
172
+ "eval_macro_sensitivity": 0.6773721773721774,
173
+ "eval_macro_specificity": 0.9217242184731483,
174
+ "eval_precision": 0.8108961670502116,
175
+ "eval_precision_macro": 0.6741723864688478,
176
+ "eval_recall": 0.8040089086859689,
177
+ "eval_recall_macro": 0.6773721773721774,
178
+ "eval_runtime": 33.2368,
179
+ "eval_samples_per_second": 13.509,
180
+ "eval_steps_per_second": 1.715,
181
+ "eval_weighted_fpr": 0.07514944491887275,
182
+ "eval_weighted_sensitivity": 0.8040089086859689,
183
+ "eval_weighted_specificity": 0.8828879652066246,
184
+ "step": 1568
185
+ },
186
+ {
187
+ "epoch": 8.0,
188
+ "eval_accuracy": 0.8106904231625836,
189
+ "eval_f1_macro": 0.6229381248976396,
190
+ "eval_f1_micro": 0.8106904231625834,
191
+ "eval_f1_weighted": 0.8016368957819484,
192
+ "eval_loss": 1.1504098176956177,
193
+ "eval_macro_fpr": 0.089652400577408,
194
+ "eval_macro_sensitivity": 0.6330299933241109,
195
+ "eval_macro_specificity": 0.9203722429802373,
196
+ "eval_precision": 0.7967862579587831,
197
+ "eval_precision_macro": 0.6227581659565835,
198
+ "eval_recall": 0.8106904231625836,
199
+ "eval_recall_macro": 0.6330299933241109,
200
+ "eval_runtime": 36.2257,
201
+ "eval_samples_per_second": 12.395,
202
+ "eval_steps_per_second": 1.573,
203
+ "eval_weighted_fpr": 0.07221750212404418,
204
+ "eval_weighted_sensitivity": 0.8106904231625836,
205
+ "eval_weighted_specificity": 0.8707985487583659,
206
+ "step": 1792
207
+ },
208
+ {
209
+ "epoch": 8.928571428571429,
210
+ "grad_norm": 0.21054323017597198,
211
+ "learning_rate": 3.516369047619048e-05,
212
+ "loss": 0.1367,
213
+ "step": 2000
214
+ },
215
+ {
216
+ "epoch": 9.0,
217
+ "eval_accuracy": 0.8062360801781737,
218
+ "eval_f1_macro": 0.6359771704966781,
219
+ "eval_f1_micro": 0.8062360801781738,
220
+ "eval_f1_weighted": 0.8044711013673843,
221
+ "eval_loss": 1.2533091306686401,
222
+ "eval_macro_fpr": 0.09482503678094849,
223
+ "eval_macro_sensitivity": 0.6224819165995636,
224
+ "eval_macro_specificity": 0.9164236762016751,
225
+ "eval_precision": 0.8059392062620114,
226
+ "eval_precision_macro": 0.6536979385970869,
227
+ "eval_recall": 0.8062360801781737,
228
+ "eval_recall_macro": 0.6224819165995636,
229
+ "eval_runtime": 30.7582,
230
+ "eval_samples_per_second": 14.598,
231
+ "eval_steps_per_second": 1.853,
232
+ "eval_weighted_fpr": 0.0741687979539642,
233
+ "eval_weighted_sensitivity": 0.8062360801781737,
234
+ "eval_weighted_specificity": 0.8594586246285271,
235
+ "step": 2016
236
+ },
237
+ {
238
+ "epoch": 10.0,
239
+ "eval_accuracy": 0.8173719376391982,
240
+ "eval_f1_macro": 0.6554404393882288,
241
+ "eval_f1_micro": 0.8173719376391981,
242
+ "eval_f1_weighted": 0.8137262031233367,
243
+ "eval_loss": 1.2516238689422607,
244
+ "eval_macro_fpr": 0.08727001865560947,
245
+ "eval_macro_sensitivity": 0.649889194006841,
246
+ "eval_macro_specificity": 0.9218678293458737,
247
+ "eval_precision": 0.8106611480963274,
248
+ "eval_precision_macro": 0.6620602008894919,
249
+ "eval_recall": 0.8173719376391982,
250
+ "eval_recall_macro": 0.649889194006841,
251
+ "eval_runtime": 34.0534,
252
+ "eval_samples_per_second": 13.185,
253
+ "eval_steps_per_second": 1.674,
254
+ "eval_weighted_fpr": 0.06931530008453085,
255
+ "eval_weighted_sensitivity": 0.8173719376391982,
256
+ "eval_weighted_specificity": 0.8700993797442969,
257
+ "step": 2240
258
+ },
259
+ {
260
+ "epoch": 11.0,
261
+ "eval_accuracy": 0.8262806236080178,
262
+ "eval_f1_macro": 0.6764229637898442,
263
+ "eval_f1_micro": 0.8262806236080178,
264
+ "eval_f1_weighted": 0.819522907157828,
265
+ "eval_loss": 1.3822201490402222,
266
+ "eval_macro_fpr": 0.08329902302757192,
267
+ "eval_macro_sensitivity": 0.669645007880302,
268
+ "eval_macro_specificity": 0.9243474796823474,
269
+ "eval_precision": 0.8204585488197453,
270
+ "eval_precision_macro": 0.7084622597280825,
271
+ "eval_recall": 0.8262806236080178,
272
+ "eval_recall_macro": 0.669645007880302,
273
+ "eval_runtime": 31.5236,
274
+ "eval_samples_per_second": 14.243,
275
+ "eval_steps_per_second": 1.808,
276
+ "eval_weighted_fpr": 0.0654911838790932,
277
+ "eval_weighted_sensitivity": 0.8262806236080178,
278
+ "eval_weighted_specificity": 0.8711092951213717,
279
+ "step": 2464
280
+ }
281
+ ],
282
+ "logging_steps": 500,
283
+ "max_steps": 6720,
284
+ "num_input_tokens_seen": 0,
285
+ "num_train_epochs": 30,
286
+ "save_steps": 500,
287
+ "total_flos": 5186538257252352.0,
288
+ "train_batch_size": 8,
289
+ "trial_name": null,
290
+ "trial_params": null
291
+ }
training_checkpoints/checkpoint-2464/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8124b12bb2d716832b587bea11323810e8fd3f54cf265a6935c0b9d891cdd1f6
3
+ size 5048
training_checkpoints/checkpoint-2464/vocab.txt ADDED
The diff for this file is too large to render. See raw diff