fjrmhri commited on
Commit
fe20b64
·
verified ·
1 Parent(s): 603667a

Upload folder using huggingface_hub

Browse files
calibration.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_threshold": 0.1,
3
+ "metric": "f1",
4
+ "label_positive": "Hoaks",
5
+ "search_min": 0.1,
6
+ "search_max": 0.9,
7
+ "search_steps": 81,
8
+ "best_f1": 1.0
9
+ }
checkpoint-1593/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "eos_token_ids": 0,
12
+ "finetuning_task": null,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "Fakta",
18
+ "1": "Hoaks"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "is_decoder": false,
23
+ "label2id": {
24
+ "Fakta": 0,
25
+ "Hoaks": 1
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": 0,
34
+ "problem_type": "single_label_classification",
35
+ "pruned_heads": {},
36
+ "tie_word_embeddings": true,
37
+ "torchscript": false,
38
+ "transformers_version": "5.0.0",
39
+ "type_vocab_size": 2,
40
+ "use_bfloat16": false,
41
+ "use_cache": false,
42
+ "vocab_size": 31923
43
+ }
checkpoint-1593/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faaea826fd410785295e7e74b48b50922cc882289a606b6025954dc55570c98b
3
+ size 442262496
checkpoint-1593/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:437f24acf4830d091012be80f212a6e2cb0ac0763802c92d3643cc1e901a3e4a
3
+ size 884649355
checkpoint-1593/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c881801a5043f6b432318467d9e2db0af6f3a94f45bc42101b516a2ccb0bdf
3
+ size 14645
checkpoint-1593/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c9662bc288999521ed5671542e8c8cf91eec180ae55f24038ecae9632b54e0
3
+ size 1383
checkpoint-1593/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:421e39764c682ffee8f8e1b3a477bb1f842280370cff69826ff49e606a0b07a1
3
+ size 1465
checkpoint-1593/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1593/tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
checkpoint-1593/trainer_state.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 531,
3
+ "best_metric": 1.0,
4
+ "best_model_checkpoint": "indobert_hoax_model_v1/checkpoint-531",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1593,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0942507068803016,
14
+ "grad_norm": 0.025504156947135925,
15
+ "learning_rate": 1.938480853735091e-05,
16
+ "loss": 0.40942169189453126,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.1885014137606032,
21
+ "grad_norm": 0.00925072468817234,
22
+ "learning_rate": 1.8757062146892657e-05,
23
+ "loss": 0.004794828295707702,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.2827521206409048,
28
+ "grad_norm": 0.006939134560525417,
29
+ "learning_rate": 1.8129315756434402e-05,
30
+ "loss": 0.0003143295645713806,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.3770028275212064,
35
+ "grad_norm": 0.004664056468755007,
36
+ "learning_rate": 1.7501569365976147e-05,
37
+ "loss": 0.000814964473247528,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.471253534401508,
42
+ "grad_norm": 0.0034358210396021605,
43
+ "learning_rate": 1.6873822975517892e-05,
44
+ "loss": 0.00017160281538963317,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.5655042412818096,
49
+ "grad_norm": 0.0030382247641682625,
50
+ "learning_rate": 1.6246076585059637e-05,
51
+ "loss": 0.00013164788484573364,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.6597549481621112,
56
+ "grad_norm": 0.0024455576203763485,
57
+ "learning_rate": 1.5618330194601382e-05,
58
+ "loss": 0.00011968448758125306,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.7540056550424128,
63
+ "grad_norm": 0.003451043274253607,
64
+ "learning_rate": 1.4990583804143128e-05,
65
+ "loss": 9.312465786933899e-05,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.8482563619227145,
70
+ "grad_norm": 0.0018449603812769055,
71
+ "learning_rate": 1.4362837413684871e-05,
72
+ "loss": 8.048981428146362e-05,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.942507068803016,
77
+ "grad_norm": 0.0017622335581108928,
78
+ "learning_rate": 1.3735091023226616e-05,
79
+ "loss": 7.07852840423584e-05,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 1.0,
84
+ "eval_accuracy": 1.0,
85
+ "eval_f1": 1.0,
86
+ "eval_loss": 9.576378033671062e-06,
87
+ "eval_precision": 1.0,
88
+ "eval_recall": 1.0,
89
+ "eval_runtime": 14.978,
90
+ "eval_samples_per_second": 366.27,
91
+ "eval_steps_per_second": 11.484,
92
+ "step": 531
93
+ },
94
+ {
95
+ "epoch": 1.0358152686145146,
96
+ "grad_norm": 0.0015032693045213819,
97
+ "learning_rate": 1.3107344632768361e-05,
98
+ "loss": 6.287907715886832e-05,
99
+ "step": 550
100
+ },
101
+ {
102
+ "epoch": 1.1300659754948161,
103
+ "grad_norm": 0.0013514097081497312,
104
+ "learning_rate": 1.2479598242310106e-05,
105
+ "loss": 5.725562572479248e-05,
106
+ "step": 600
107
+ },
108
+ {
109
+ "epoch": 1.2243166823751177,
110
+ "grad_norm": 0.0012397239916026592,
111
+ "learning_rate": 1.1851851851851852e-05,
112
+ "loss": 5.280032753944397e-05,
113
+ "step": 650
114
+ },
115
+ {
116
+ "epoch": 1.3185673892554195,
117
+ "grad_norm": 0.0012461590813472867,
118
+ "learning_rate": 1.1224105461393597e-05,
119
+ "loss": 4.774346947669983e-05,
120
+ "step": 700
121
+ },
122
+ {
123
+ "epoch": 1.412818096135721,
124
+ "grad_norm": 0.0010583893163129687,
125
+ "learning_rate": 1.0596359070935342e-05,
126
+ "loss": 4.465669393539429e-05,
127
+ "step": 750
128
+ },
129
+ {
130
+ "epoch": 1.5070688030160226,
131
+ "grad_norm": 0.0010236818343400955,
132
+ "learning_rate": 9.968612680477087e-06,
133
+ "loss": 4.121735692024231e-05,
134
+ "step": 800
135
+ },
136
+ {
137
+ "epoch": 1.6013195098963242,
138
+ "grad_norm": 57.616493225097656,
139
+ "learning_rate": 9.340866290018832e-06,
140
+ "loss": 0.006611879467964172,
141
+ "step": 850
142
+ },
143
+ {
144
+ "epoch": 1.6955702167766258,
145
+ "grad_norm": 0.001041750656440854,
146
+ "learning_rate": 8.713119899560577e-06,
147
+ "loss": 0.0017833974957466125,
148
+ "step": 900
149
+ },
150
+ {
151
+ "epoch": 1.7898209236569276,
152
+ "grad_norm": 0.0009882135782390833,
153
+ "learning_rate": 8.085373509102322e-06,
154
+ "loss": 4.2116045951843264e-05,
155
+ "step": 950
156
+ },
157
+ {
158
+ "epoch": 1.8840716305372291,
159
+ "grad_norm": 0.0009338518721051514,
160
+ "learning_rate": 7.4576271186440685e-06,
161
+ "loss": 3.5514235496521e-05,
162
+ "step": 1000
163
+ },
164
+ {
165
+ "epoch": 1.9783223374175307,
166
+ "grad_norm": 0.0009871515212580562,
167
+ "learning_rate": 6.829880728185814e-06,
168
+ "loss": 3.3619403839111326e-05,
169
+ "step": 1050
170
+ },
171
+ {
172
+ "epoch": 2.0,
173
+ "eval_accuracy": 1.0,
174
+ "eval_f1": 1.0,
175
+ "eval_loss": 4.904356046608882e-06,
176
+ "eval_precision": 1.0,
177
+ "eval_recall": 1.0,
178
+ "eval_runtime": 15.0517,
179
+ "eval_samples_per_second": 364.478,
180
+ "eval_steps_per_second": 11.427,
181
+ "step": 1062
182
+ },
183
+ {
184
+ "epoch": 2.071630537229029,
185
+ "grad_norm": 0.0008175307302735746,
186
+ "learning_rate": 6.202134337727559e-06,
187
+ "loss": 3.18763148970902e-05,
188
+ "step": 1100
189
+ },
190
+ {
191
+ "epoch": 2.1658812441093307,
192
+ "grad_norm": 0.0008202173048630357,
193
+ "learning_rate": 5.574387947269304e-06,
194
+ "loss": 3.0466020107269287e-05,
195
+ "step": 1150
196
+ },
197
+ {
198
+ "epoch": 2.2601319509896323,
199
+ "grad_norm": 0.0007742273737676442,
200
+ "learning_rate": 4.946641556811049e-06,
201
+ "loss": 2.9218792915344237e-05,
202
+ "step": 1200
203
+ },
204
+ {
205
+ "epoch": 2.354382657869934,
206
+ "grad_norm": 0.000745770987123251,
207
+ "learning_rate": 4.318895166352794e-06,
208
+ "loss": 2.858087420463562e-05,
209
+ "step": 1250
210
+ },
211
+ {
212
+ "epoch": 2.4486333647502354,
213
+ "grad_norm": 0.0007288759225048125,
214
+ "learning_rate": 3.6911487758945393e-06,
215
+ "loss": 2.7648359537124634e-05,
216
+ "step": 1300
217
+ },
218
+ {
219
+ "epoch": 2.542884071630537,
220
+ "grad_norm": 0.0006955668795853853,
221
+ "learning_rate": 3.0634023854362836e-06,
222
+ "loss": 2.6850849390029908e-05,
223
+ "step": 1350
224
+ },
225
+ {
226
+ "epoch": 2.637134778510839,
227
+ "grad_norm": 0.0008982333238236606,
228
+ "learning_rate": 2.4356559949780288e-06,
229
+ "loss": 2.67539918422699e-05,
230
+ "step": 1400
231
+ },
232
+ {
233
+ "epoch": 2.7313854853911406,
234
+ "grad_norm": 0.0007632261258549988,
235
+ "learning_rate": 1.8079096045197741e-06,
236
+ "loss": 0.009577980637550354,
237
+ "step": 1450
238
+ },
239
+ {
240
+ "epoch": 2.825636192271442,
241
+ "grad_norm": 0.0007062007207423449,
242
+ "learning_rate": 1.1801632140615193e-06,
243
+ "loss": 2.928808331489563e-05,
244
+ "step": 1500
245
+ },
246
+ {
247
+ "epoch": 2.9198868991517437,
248
+ "grad_norm": 0.0006927906651981175,
249
+ "learning_rate": 5.524168236032643e-07,
250
+ "loss": 3.153368830680847e-05,
251
+ "step": 1550
252
+ },
253
+ {
254
+ "epoch": 3.0,
255
+ "eval_accuracy": 1.0,
256
+ "eval_f1": 1.0,
257
+ "eval_loss": 3.923106760339579e-06,
258
+ "eval_precision": 1.0,
259
+ "eval_recall": 1.0,
260
+ "eval_runtime": 14.9999,
261
+ "eval_samples_per_second": 365.736,
262
+ "eval_steps_per_second": 11.467,
263
+ "step": 1593
264
+ }
265
+ ],
266
+ "logging_steps": 50,
267
+ "max_steps": 1593,
268
+ "num_input_tokens_seen": 0,
269
+ "num_train_epochs": 3,
270
+ "save_steps": 500,
271
+ "stateful_callbacks": {
272
+ "EarlyStoppingCallback": {
273
+ "args": {
274
+ "early_stopping_patience": 2,
275
+ "early_stopping_threshold": 0.0
276
+ },
277
+ "attributes": {
278
+ "early_stopping_patience_counter": 2
279
+ }
280
+ },
281
+ "TrainerControl": {
282
+ "args": {
283
+ "should_epoch_stop": false,
284
+ "should_evaluate": false,
285
+ "should_log": false,
286
+ "should_save": true,
287
+ "should_training_stop": true
288
+ },
289
+ "attributes": {}
290
+ }
291
+ },
292
+ "total_flos": 9156166059882240.0,
293
+ "train_batch_size": 16,
294
+ "trial_name": null,
295
+ "trial_params": null
296
+ }
checkpoint-1593/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f676df1f995d2e951898cab3b204875d2d575006764aece503947f91b2cb32
3
+ size 5201
checkpoint-531/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "eos_token_ids": 0,
12
+ "finetuning_task": null,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "Fakta",
18
+ "1": "Hoaks"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "is_decoder": false,
23
+ "label2id": {
24
+ "Fakta": 0,
25
+ "Hoaks": 1
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": 0,
34
+ "problem_type": "single_label_classification",
35
+ "pruned_heads": {},
36
+ "tie_word_embeddings": true,
37
+ "torchscript": false,
38
+ "transformers_version": "5.0.0",
39
+ "type_vocab_size": 2,
40
+ "use_bfloat16": false,
41
+ "use_cache": false,
42
+ "vocab_size": 31923
43
+ }
checkpoint-531/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b396b6277d6f188259c7b75c16bf7c207c3b6889c55cdf7ffaf899231e2d2e
3
+ size 442262496
checkpoint-531/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7164489681a23db1559da4ab3171510e01403d7622b52b996a526d1894738e49
3
+ size 884649355
checkpoint-531/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:686ee9cfb0e42918c68e04b73776d55e6b6d4eaf551dbf3ef1126bc2c51725f6
3
+ size 14645
checkpoint-531/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e322181abdfec6897c2d485fa7e80bd163ae90600d28b78a1b00a68698638ab
3
+ size 1383
checkpoint-531/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474fa65124d72d7a999766a120408d3a32500870567f61081a02e8088ca27275
3
+ size 1465
checkpoint-531/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-531/tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
checkpoint-531/trainer_state.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 531,
3
+ "best_metric": 1.0,
4
+ "best_model_checkpoint": "indobert_hoax_model_v1/checkpoint-531",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 531,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0942507068803016,
14
+ "grad_norm": 0.025504156947135925,
15
+ "learning_rate": 1.938480853735091e-05,
16
+ "loss": 0.40942169189453126,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.1885014137606032,
21
+ "grad_norm": 0.00925072468817234,
22
+ "learning_rate": 1.8757062146892657e-05,
23
+ "loss": 0.004794828295707702,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.2827521206409048,
28
+ "grad_norm": 0.006939134560525417,
29
+ "learning_rate": 1.8129315756434402e-05,
30
+ "loss": 0.0003143295645713806,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.3770028275212064,
35
+ "grad_norm": 0.004664056468755007,
36
+ "learning_rate": 1.7501569365976147e-05,
37
+ "loss": 0.000814964473247528,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.471253534401508,
42
+ "grad_norm": 0.0034358210396021605,
43
+ "learning_rate": 1.6873822975517892e-05,
44
+ "loss": 0.00017160281538963317,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.5655042412818096,
49
+ "grad_norm": 0.0030382247641682625,
50
+ "learning_rate": 1.6246076585059637e-05,
51
+ "loss": 0.00013164788484573364,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.6597549481621112,
56
+ "grad_norm": 0.0024455576203763485,
57
+ "learning_rate": 1.5618330194601382e-05,
58
+ "loss": 0.00011968448758125306,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.7540056550424128,
63
+ "grad_norm": 0.003451043274253607,
64
+ "learning_rate": 1.4990583804143128e-05,
65
+ "loss": 9.312465786933899e-05,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.8482563619227145,
70
+ "grad_norm": 0.0018449603812769055,
71
+ "learning_rate": 1.4362837413684871e-05,
72
+ "loss": 8.048981428146362e-05,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.942507068803016,
77
+ "grad_norm": 0.0017622335581108928,
78
+ "learning_rate": 1.3735091023226616e-05,
79
+ "loss": 7.07852840423584e-05,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 1.0,
84
+ "eval_accuracy": 1.0,
85
+ "eval_f1": 1.0,
86
+ "eval_loss": 9.576378033671062e-06,
87
+ "eval_precision": 1.0,
88
+ "eval_recall": 1.0,
89
+ "eval_runtime": 14.978,
90
+ "eval_samples_per_second": 366.27,
91
+ "eval_steps_per_second": 11.484,
92
+ "step": 531
93
+ }
94
+ ],
95
+ "logging_steps": 50,
96
+ "max_steps": 1593,
97
+ "num_input_tokens_seen": 0,
98
+ "num_train_epochs": 3,
99
+ "save_steps": 500,
100
+ "stateful_callbacks": {
101
+ "EarlyStoppingCallback": {
102
+ "args": {
103
+ "early_stopping_patience": 2,
104
+ "early_stopping_threshold": 0.0
105
+ },
106
+ "attributes": {
107
+ "early_stopping_patience_counter": 0
108
+ }
109
+ },
110
+ "TrainerControl": {
111
+ "args": {
112
+ "should_epoch_stop": false,
113
+ "should_evaluate": false,
114
+ "should_log": false,
115
+ "should_save": true,
116
+ "should_training_stop": false
117
+ },
118
+ "attributes": {}
119
+ }
120
+ },
121
+ "total_flos": 3048322465196160.0,
122
+ "train_batch_size": 16,
123
+ "trial_name": null,
124
+ "trial_params": null
125
+ }
checkpoint-531/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f676df1f995d2e951898cab3b204875d2d575006764aece503947f91b2cb32
3
+ size 5201
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "eos_token_ids": 0,
12
+ "finetuning_task": null,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "Fakta",
18
+ "1": "Hoaks"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "is_decoder": false,
23
+ "label2id": {
24
+ "Fakta": 0,
25
+ "Hoaks": 1
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": 0,
34
+ "problem_type": "single_label_classification",
35
+ "pruned_heads": {},
36
+ "tie_word_embeddings": true,
37
+ "torchscript": false,
38
+ "transformers_version": "5.0.0",
39
+ "type_vocab_size": 2,
40
+ "use_bfloat16": false,
41
+ "use_cache": false,
42
+ "vocab_size": 31923
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b587dcf3e0cc6439427c25520b6bcee639cf56c618db1a6fdd3ddd2f5d6c3662
3
+ size 442262496
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f676df1f995d2e951898cab3b204875d2d575006764aece503947f91b2cb32
3
+ size 5201