Hugging Face's logo

tum-nlp
/
neural-news-discriminator-RoBERTa-fa

Text Classification
Transformers
Safetensors
Persian
roberta
Inference Endpoints
Model card Files Community
cmykk commited on
Commit
123060d
•
1 Parent(s): c78d80d

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +28 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +285 -0
  7. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "problem_type": "single_label_classification",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.36.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50265
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5338d024671da054e1d987671fca0be70fd1518f3d6d8869a6729f7ad7296df0
3
+ size 498612824
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788f76268e2c99012d06ec11a15a41f0d021037edd34c094ffdd1ae5c8fed23d
3
+ size 685336698
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:991e43ac880e77aebf04614d32b64496de373d179b23ef29fce160acf7668ee9
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eefcc220674693d0d348a2a1a1c09f5b976d4796d4b77f910dcbd95bab2dcf70
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,285 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "./fa_results/checkpoint-600",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1050,
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": 0.9975,
14
+ "eval_classification_report": {
15
+ "accuracy": 0.9975,
16
+ "macro avg": {
17
+ "f1-score": 0.9974999843749024,
18
+ "precision": 0.9975124378109452,
19
+ "recall": 0.9975,
20
+ "support": 800.0
21
+ },
22
+ "neural": {
23
+ "f1-score": 0.9974937343358395,
24
+ "precision": 1.0,
25
+ "recall": 0.995,
26
+ "support": 400.0
27
+ },
28
+ "real": {
29
+ "f1-score": 0.9975062344139651,
30
+ "precision": 0.9950248756218906,
31
+ "recall": 1.0,
32
+ "support": 400.0
33
+ },
34
+ "weighted avg": {
35
+ "f1-score": 0.9974999843749024,
36
+ "precision": 0.9975124378109453,
37
+ "recall": 0.9975,
38
+ "support": 800.0
39
+ }
40
+ },
41
+ "eval_loss": 0.017120858654379845,
42
+ "eval_runtime": 34.7129,
43
+ "eval_samples_per_second": 23.046,
44
+ "eval_steps_per_second": 1.44,
45
+ "step": 150
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_accuracy": 0.99875,
50
+ "eval_classification_report": {
51
+ "accuracy": 0.99875,
52
+ "macro avg": {
53
+ "f1-score": 0.9987499980468719,
54
+ "precision": 0.9987531172069826,
55
+ "recall": 0.99875,
56
+ "support": 800.0
57
+ },
58
+ "neural": {
59
+ "f1-score": 0.9987484355444306,
60
+ "precision": 1.0,
61
+ "recall": 0.9975,
62
+ "support": 400.0
63
+ },
64
+ "real": {
65
+ "f1-score": 0.9987515605493134,
66
+ "precision": 0.9975062344139651,
67
+ "recall": 1.0,
68
+ "support": 400.0
69
+ },
70
+ "weighted avg": {
71
+ "f1-score": 0.998749998046872,
72
+ "precision": 0.9987531172069825,
73
+ "recall": 0.99875,
74
+ "support": 800.0
75
+ }
76
+ },
77
+ "eval_loss": 0.010303272865712643,
78
+ "eval_runtime": 34.6871,
79
+ "eval_samples_per_second": 23.063,
80
+ "eval_steps_per_second": 1.441,
81
+ "step": 300
82
+ },
83
+ {
84
+ "epoch": 3.0,
85
+ "eval_accuracy": 0.99625,
86
+ "eval_classification_report": {
87
+ "accuracy": 0.99625,
88
+ "macro avg": {
89
+ "f1-score": 0.9962499472648834,
90
+ "precision": 0.9962779156327544,
91
+ "recall": 0.9962500000000001,
92
+ "support": 800.0
93
+ },
94
+ "neural": {
95
+ "f1-score": 0.9962358845671266,
96
+ "precision": 1.0,
97
+ "recall": 0.9925,
98
+ "support": 400.0
99
+ },
100
+ "real": {
101
+ "f1-score": 0.9962640099626401,
102
+ "precision": 0.9925558312655087,
103
+ "recall": 1.0,
104
+ "support": 400.0
105
+ },
106
+ "weighted avg": {
107
+ "f1-score": 0.9962499472648834,
108
+ "precision": 0.9962779156327544,
109
+ "recall": 0.99625,
110
+ "support": 800.0
111
+ }
112
+ },
113
+ "eval_loss": 0.016219044104218483,
114
+ "eval_runtime": 29.5456,
115
+ "eval_samples_per_second": 27.077,
116
+ "eval_steps_per_second": 1.692,
117
+ "step": 450
118
+ },
119
+ {
120
+ "epoch": 3.33,
121
+ "learning_rate": 5e-05,
122
+ "loss": 0.1112,
123
+ "step": 500
124
+ },
125
+ {
126
+ "epoch": 4.0,
127
+ "eval_accuracy": 1.0,
128
+ "eval_classification_report": {
129
+ "accuracy": 1.0,
130
+ "macro avg": {
131
+ "f1-score": 1.0,
132
+ "precision": 1.0,
133
+ "recall": 1.0,
134
+ "support": 800.0
135
+ },
136
+ "neural": {
137
+ "f1-score": 1.0,
138
+ "precision": 1.0,
139
+ "recall": 1.0,
140
+ "support": 400.0
141
+ },
142
+ "real": {
143
+ "f1-score": 1.0,
144
+ "precision": 1.0,
145
+ "recall": 1.0,
146
+ "support": 400.0
147
+ },
148
+ "weighted avg": {
149
+ "f1-score": 1.0,
150
+ "precision": 1.0,
151
+ "recall": 1.0,
152
+ "support": 800.0
153
+ }
154
+ },
155
+ "eval_loss": 0.00012144193169660866,
156
+ "eval_runtime": 22.7741,
157
+ "eval_samples_per_second": 35.128,
158
+ "eval_steps_per_second": 2.195,
159
+ "step": 600
160
+ },
161
+ {
162
+ "epoch": 5.0,
163
+ "eval_accuracy": 1.0,
164
+ "eval_classification_report": {
165
+ "accuracy": 1.0,
166
+ "macro avg": {
167
+ "f1-score": 1.0,
168
+ "precision": 1.0,
169
+ "recall": 1.0,
170
+ "support": 800.0
171
+ },
172
+ "neural": {
173
+ "f1-score": 1.0,
174
+ "precision": 1.0,
175
+ "recall": 1.0,
176
+ "support": 400.0
177
+ },
178
+ "real": {
179
+ "f1-score": 1.0,
180
+ "precision": 1.0,
181
+ "recall": 1.0,
182
+ "support": 400.0
183
+ },
184
+ "weighted avg": {
185
+ "f1-score": 1.0,
186
+ "precision": 1.0,
187
+ "recall": 1.0,
188
+ "support": 800.0
189
+ }
190
+ },
191
+ "eval_loss": 0.00027504810714162886,
192
+ "eval_runtime": 17.1164,
193
+ "eval_samples_per_second": 46.739,
194
+ "eval_steps_per_second": 2.921,
195
+ "step": 750
196
+ },
197
+ {
198
+ "epoch": 6.0,
199
+ "eval_accuracy": 1.0,
200
+ "eval_classification_report": {
201
+ "accuracy": 1.0,
202
+ "macro avg": {
203
+ "f1-score": 1.0,
204
+ "precision": 1.0,
205
+ "recall": 1.0,
206
+ "support": 800.0
207
+ },
208
+ "neural": {
209
+ "f1-score": 1.0,
210
+ "precision": 1.0,
211
+ "recall": 1.0,
212
+ "support": 400.0
213
+ },
214
+ "real": {
215
+ "f1-score": 1.0,
216
+ "precision": 1.0,
217
+ "recall": 1.0,
218
+ "support": 400.0
219
+ },
220
+ "weighted avg": {
221
+ "f1-score": 1.0,
222
+ "precision": 1.0,
223
+ "recall": 1.0,
224
+ "support": 800.0
225
+ }
226
+ },
227
+ "eval_loss": 0.00036392605397850275,
228
+ "eval_runtime": 22.6386,
229
+ "eval_samples_per_second": 35.338,
230
+ "eval_steps_per_second": 2.209,
231
+ "step": 900
232
+ },
233
+ {
234
+ "epoch": 6.67,
235
+ "learning_rate": 4.827586206896552e-05,
236
+ "loss": 0.0014,
237
+ "step": 1000
238
+ },
239
+ {
240
+ "epoch": 7.0,
241
+ "eval_accuracy": 1.0,
242
+ "eval_classification_report": {
243
+ "accuracy": 1.0,
244
+ "macro avg": {
245
+ "f1-score": 1.0,
246
+ "precision": 1.0,
247
+ "recall": 1.0,
248
+ "support": 800.0
249
+ },
250
+ "neural": {
251
+ "f1-score": 1.0,
252
+ "precision": 1.0,
253
+ "recall": 1.0,
254
+ "support": 400.0
255
+ },
256
+ "real": {
257
+ "f1-score": 1.0,
258
+ "precision": 1.0,
259
+ "recall": 1.0,
260
+ "support": 400.0
261
+ },
262
+ "weighted avg": {
263
+ "f1-score": 1.0,
264
+ "precision": 1.0,
265
+ "recall": 1.0,
266
+ "support": 800.0
267
+ }
268
+ },
269
+ "eval_loss": 0.0005032551125623286,
270
+ "eval_runtime": 22.5993,
271
+ "eval_samples_per_second": 35.399,
272
+ "eval_steps_per_second": 2.212,
273
+ "step": 1050
274
+ }
275
+ ],
276
+ "logging_steps": 500,
277
+ "max_steps": 15000,
278
+ "num_input_tokens_seen": 0,
279
+ "num_train_epochs": 100,
280
+ "save_steps": 500,
281
+ "total_flos": 4420265730048000.0,
282
+ "train_batch_size": 16,
283
+ "trial_name": null,
284
+ "trial_params": null
285
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f67e182e00b4994e4cdd73808416b0d75b368d0305ef9b345b2749c5756683c6
3
+ size 4664