Donnyed commited on
Commit
0515984
·
verified ·
1 Parent(s): 626b9df

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # LLM_Detector_Preview_model
2
+
3
+ **Preview release of an LLM-generated text detector.**
4
+
5
+ ## Model Description
6
+ This model is designed to classify text as Human, Mixed, or AI-generated. It is based on a sequence classification architecture and was trained on a mix of human and AI-generated texts. The model can be used for document, sentence, and token-level analysis.
7
+
8
+ - **Architecture:** ModernBERT (or compatible Transformer)
9
+ - **Labels:**
10
+ - 0: Human
11
+ - 1: Mixed
12
+ - 2: AI
13
+
14
+ ## Intended Use
15
+ - **For research and curiosity only.**
16
+ - Not for academic, legal, medical, or high-stakes use.
17
+ - Results are easy to bypass and may be unreliable.
18
+
19
+ ## Limitations & Warnings
20
+ - This model is **experimental** and not clinically accurate.
21
+ - It can produce false positives and false negatives.
22
+ - Simple paraphrasing or editing can fool the detector.
23
+ - Do not use for academic integrity, hiring, or legal decisions.
24
+
25
+ ## How It Works
26
+ The model analyzes text and predicts the likelihood of it being human-written, mixed, or AI-generated. It uses statistical patterns learned from training data, but these patterns are not foolproof and can be circumvented.
27
+
28
+ ## Example Usage
29
+ ```python
30
+ from transformers import AutoTokenizer, AutoModelForSequenceClassification
31
+ import torch
32
+
33
+ tokenizer = AutoTokenizer.from_pretrained('Donnyed/LLM_Detector_Preview_model')
34
+ model = AutoModelForSequenceClassification.from_pretrained('Donnyed/LLM_Detector_Preview_model')
35
+
36
+ text = "Paste your text here."
37
+ inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
38
+ with torch.no_grad():
39
+ outputs = model(**inputs)
40
+ probs = torch.softmax(outputs.logits, dim=1)
41
+ pred = torch.argmax(probs, dim=1).item()
42
+ print('Prediction:', pred)
43
+ print('Probabilities:', probs)
44
+ ```
45
+
46
+ ## Files Included
47
+ - `model.safetensors` — Model weights
48
+ - `config.json` — Model configuration
49
+ - `tokenizer.json`, `tokenizer_config.json`, `special_tokens_map.json` — Tokenizer files
50
+
51
+ ## License
52
+ Specify your license here (e.g., Apache 2.0, MIT, etc.)
53
+
54
+ ---
55
+ **Maintainer:** [your-username](https://huggingface.co/your-username)
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ModernBertForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 50281,
8
+ "classifier_activation": "gelu",
9
+ "classifier_bias": false,
10
+ "classifier_dropout": 0.0,
11
+ "classifier_pooling": "mean",
12
+ "cls_token_id": 50281,
13
+ "decoder_bias": true,
14
+ "deterministic_flash_attn": false,
15
+ "embedding_dropout": 0.0,
16
+ "eos_token_id": 50282,
17
+ "global_attn_every_n_layers": 3,
18
+ "global_rope_theta": 160000.0,
19
+ "gradient_checkpointing": false,
20
+ "hidden_activation": "gelu",
21
+ "hidden_size": 1024,
22
+ "id2label": {
23
+ "0": "human",
24
+ "1": "mixed",
25
+ "2": "ai"
26
+ },
27
+ "initializer_cutoff_factor": 2.0,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 2624,
30
+ "label2id": {
31
+ "ai": 2,
32
+ "human": 0,
33
+ "mixed": 1
34
+ },
35
+ "layer_norm_eps": 1e-05,
36
+ "local_attention": 128,
37
+ "local_rope_theta": 10000.0,
38
+ "max_position_embeddings": 8192,
39
+ "mlp_bias": false,
40
+ "mlp_dropout": 0.0,
41
+ "model_type": "modernbert",
42
+ "norm_bias": false,
43
+ "norm_eps": 1e-05,
44
+ "num_attention_heads": 16,
45
+ "num_hidden_layers": 28,
46
+ "pad_token_id": 50283,
47
+ "position_embedding_type": "absolute",
48
+ "problem_type": "single_label_classification",
49
+ "repad_logits_with_grad": false,
50
+ "sep_token_id": 50282,
51
+ "sparse_pred_ignore_index": -100,
52
+ "sparse_prediction": false,
53
+ "torch_dtype": "bfloat16",
54
+ "transformers_version": "4.51.3",
55
+ "vocab_size": 50368
56
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dc3efe4de763a327ec58d9c8f6d7012649f11100d4367b5a06e250b959fa254
3
+ size 791687022
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e64b364674c8010d26ec3b17a7f8c89955ec8acc61a4bf54f53506b6cc77a5
3
+ size 1583486330
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2531a8a7ef4c8a8f472f2989d224f0a3d84308b9088a3720a96ae2d7c2d731f5
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6033e9e4ce3dc02ef5261b09746694f3abef55120ce0aa9f297d6e2ada4f8996
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 8192,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizer",
944
+ "unk_token": "[UNK]"
945
+ }
trainer_state.json ADDED
@@ -0,0 +1,487 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1100,
3
+ "best_metric": 0.8458904558156242,
4
+ "best_model_checkpoint": "modernbert-ai-detector\\checkpoint-1000",
5
+ "epoch": 0.6327445293962563,
6
+ "eval_steps": 100,
7
+ "global_step": 1200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.026364355391510677,
14
+ "grad_norm": 58.5,
15
+ "learning_rate": 2.5843881856540085e-06,
16
+ "loss": 2.6514,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.052728710783021354,
21
+ "grad_norm": 38.0,
22
+ "learning_rate": 5.221518987341772e-06,
23
+ "loss": 2.4826,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.052728710783021354,
28
+ "eval_accuracy": 0.3540233562629979,
29
+ "eval_f1_ai": 0.1182551168079388,
30
+ "eval_f1_human": 0.3140407288317256,
31
+ "eval_f1_macro": 0.2998623455656316,
32
+ "eval_f1_micro": 0.3540233562629979,
33
+ "eval_f1_mixed": 0.46729119105723055,
34
+ "eval_f1_weighted": 0.35779828876973646,
35
+ "eval_loss": 1.1378378868103027,
36
+ "eval_precision_ai": 0.12716763005780346,
37
+ "eval_precision_human": 0.26479891549932216,
38
+ "eval_precision_mixed": 0.5093530118414278,
39
+ "eval_precision_weighted": 0.37081108952953074,
40
+ "eval_recall_ai": 0.11051004636785162,
41
+ "eval_recall_human": 0.3857801184990125,
42
+ "eval_recall_mixed": 0.4316463059918557,
43
+ "eval_recall_weighted": 0.3540233562629979,
44
+ "eval_runtime": 201.6513,
45
+ "eval_samples_per_second": 61.998,
46
+ "eval_steps_per_second": 1.939,
47
+ "step": 100
48
+ },
49
+ {
50
+ "epoch": 0.07909306617453203,
51
+ "grad_norm": 30.625,
52
+ "learning_rate": 7.858649789029536e-06,
53
+ "loss": 2.1667,
54
+ "step": 150
55
+ },
56
+ {
57
+ "epoch": 0.10545742156604271,
58
+ "grad_norm": 30.25,
59
+ "learning_rate": 1.04957805907173e-05,
60
+ "loss": 1.9264,
61
+ "step": 200
62
+ },
63
+ {
64
+ "epoch": 0.10545742156604271,
65
+ "eval_accuracy": 0.560550311950088,
66
+ "eval_f1_ai": 0.2870420995079278,
67
+ "eval_f1_human": 0.08250526949713942,
68
+ "eval_f1_macro": 0.35789350580335344,
69
+ "eval_f1_micro": 0.560550311950088,
70
+ "eval_f1_mixed": 0.7041331484049931,
71
+ "eval_f1_weighted": 0.46673616146948954,
72
+ "eval_loss": 0.9078124165534973,
73
+ "eval_precision_ai": 0.49065420560747663,
74
+ "eval_precision_human": 0.4840989399293286,
75
+ "eval_precision_mixed": 0.5691990313032559,
76
+ "eval_precision_weighted": 0.5322602945815579,
77
+ "eval_recall_ai": 0.20285935085007728,
78
+ "eval_recall_human": 0.04509545753785385,
79
+ "eval_recall_mixed": 0.9229203025014543,
80
+ "eval_recall_weighted": 0.560550311950088,
81
+ "eval_runtime": 211.1463,
82
+ "eval_samples_per_second": 59.21,
83
+ "eval_steps_per_second": 1.852,
84
+ "step": 200
85
+ },
86
+ {
87
+ "epoch": 0.1318217769575534,
88
+ "grad_norm": 24.875,
89
+ "learning_rate": 1.3132911392405065e-05,
90
+ "loss": 1.768,
91
+ "step": 250
92
+ },
93
+ {
94
+ "epoch": 0.15818613234906406,
95
+ "grad_norm": 49.75,
96
+ "learning_rate": 1.5770042194092827e-05,
97
+ "loss": 1.6275,
98
+ "step": 300
99
+ },
100
+ {
101
+ "epoch": 0.15818613234906406,
102
+ "eval_accuracy": 0.6739721644536875,
103
+ "eval_f1_ai": 0.75,
104
+ "eval_f1_human": 0.20677177565262342,
105
+ "eval_f1_macro": 0.5733127667382775,
106
+ "eval_f1_micro": 0.6739721644536875,
107
+ "eval_f1_mixed": 0.763166524562209,
108
+ "eval_f1_weighted": 0.625236416359176,
109
+ "eval_loss": 0.7546337842941284,
110
+ "eval_precision_ai": 0.6690909090909091,
111
+ "eval_precision_human": 0.4813477737665463,
112
+ "eval_precision_mixed": 0.6950185163062955,
113
+ "eval_precision_weighted": 0.6377290935492025,
114
+ "eval_recall_ai": 0.8531684698608965,
115
+ "eval_recall_human": 0.1316655694535879,
116
+ "eval_recall_mixed": 0.8461314717859221,
117
+ "eval_recall_weighted": 0.6739721644536875,
118
+ "eval_runtime": 215.6745,
119
+ "eval_samples_per_second": 57.967,
120
+ "eval_steps_per_second": 1.813,
121
+ "step": 300
122
+ },
123
+ {
124
+ "epoch": 0.18455048774057475,
125
+ "grad_norm": 14.25,
126
+ "learning_rate": 1.8407172995780592e-05,
127
+ "loss": 1.5471,
128
+ "step": 350
129
+ },
130
+ {
131
+ "epoch": 0.21091484313208542,
132
+ "grad_norm": 21.875,
133
+ "learning_rate": 2.1044303797468356e-05,
134
+ "loss": 1.4071,
135
+ "step": 400
136
+ },
137
+ {
138
+ "epoch": 0.21091484313208542,
139
+ "eval_accuracy": 0.6927691569348904,
140
+ "eval_f1_ai": 0.7882645141260478,
141
+ "eval_f1_human": 0.3710217755443886,
142
+ "eval_f1_macro": 0.639632496479439,
143
+ "eval_f1_micro": 0.6927691569348904,
144
+ "eval_f1_mixed": 0.7596111997678805,
145
+ "eval_f1_weighted": 0.6711149677064479,
146
+ "eval_loss": 0.6714780926704407,
147
+ "eval_precision_ai": 0.6587960560456668,
148
+ "eval_precision_human": 0.5097813578826237,
149
+ "eval_precision_mixed": 0.7577424023154848,
150
+ "eval_precision_weighted": 0.6770050165265453,
151
+ "eval_recall_ai": 0.9810664605873262,
152
+ "eval_recall_human": 0.2916392363396972,
153
+ "eval_recall_mixed": 0.7614892379290285,
154
+ "eval_recall_weighted": 0.6927691569348904,
155
+ "eval_runtime": 198.7063,
156
+ "eval_samples_per_second": 62.917,
157
+ "eval_steps_per_second": 1.968,
158
+ "step": 400
159
+ },
160
+ {
161
+ "epoch": 0.2372791985235961,
162
+ "grad_norm": 77.0,
163
+ "learning_rate": 2.3681434599156117e-05,
164
+ "loss": 1.3628,
165
+ "step": 450
166
+ },
167
+ {
168
+ "epoch": 0.2636435539151068,
169
+ "grad_norm": 30.5,
170
+ "learning_rate": 2.6318565400843882e-05,
171
+ "loss": 1.2541,
172
+ "step": 500
173
+ },
174
+ {
175
+ "epoch": 0.2636435539151068,
176
+ "eval_accuracy": 0.7350023996160614,
177
+ "eval_f1_ai": 0.8567004988818167,
178
+ "eval_f1_human": 0.30513595166163143,
179
+ "eval_f1_macro": 0.654182029936718,
180
+ "eval_f1_micro": 0.7350023996160614,
181
+ "eval_f1_mixed": 0.8007096392667061,
182
+ "eval_f1_weighted": 0.6918751713207526,
183
+ "eval_loss": 0.588551938533783,
184
+ "eval_precision_ai": 0.772093023255814,
185
+ "eval_precision_human": 0.6488222698072805,
186
+ "eval_precision_mixed": 0.7303128371089536,
187
+ "eval_precision_weighted": 0.7191593239339089,
188
+ "eval_recall_ai": 0.9621329211746522,
189
+ "eval_recall_human": 0.19947333772218565,
190
+ "eval_recall_mixed": 0.8861256544502618,
191
+ "eval_recall_weighted": 0.7350023996160614,
192
+ "eval_runtime": 200.2569,
193
+ "eval_samples_per_second": 62.43,
194
+ "eval_steps_per_second": 1.952,
195
+ "step": 500
196
+ },
197
+ {
198
+ "epoch": 0.29000790930661746,
199
+ "grad_norm": 57.25,
200
+ "learning_rate": 2.8955696202531646e-05,
201
+ "loss": 1.2181,
202
+ "step": 550
203
+ },
204
+ {
205
+ "epoch": 0.3163722646981281,
206
+ "grad_norm": 46.5,
207
+ "learning_rate": 3.159282700421941e-05,
208
+ "loss": 1.305,
209
+ "step": 600
210
+ },
211
+ {
212
+ "epoch": 0.3163722646981281,
213
+ "eval_accuracy": 0.7118860982242842,
214
+ "eval_f1_ai": 0.863129435620142,
215
+ "eval_f1_human": 0.563509072724675,
216
+ "eval_f1_macro": 0.7167971002003201,
217
+ "eval_f1_micro": 0.7118860982242842,
218
+ "eval_f1_mixed": 0.723752792256143,
219
+ "eval_f1_weighted": 0.7136653128999944,
220
+ "eval_loss": 0.5719289779663086,
221
+ "eval_precision_ai": 0.766966966966967,
222
+ "eval_precision_human": 0.4978540772532189,
223
+ "eval_precision_mixed": 0.8393782383419689,
224
+ "eval_precision_weighted": 0.7413978534670587,
225
+ "eval_recall_ai": 0.9868624420401855,
226
+ "eval_recall_human": 0.6491112574061882,
227
+ "eval_recall_mixed": 0.6361256544502618,
228
+ "eval_recall_weighted": 0.7118860982242842,
229
+ "eval_runtime": 201.8683,
230
+ "eval_samples_per_second": 61.931,
231
+ "eval_steps_per_second": 1.937,
232
+ "step": 600
233
+ },
234
+ {
235
+ "epoch": 0.3427366200896388,
236
+ "grad_norm": 40.25,
237
+ "learning_rate": 3.422995780590718e-05,
238
+ "loss": 1.1546,
239
+ "step": 650
240
+ },
241
+ {
242
+ "epoch": 0.3691009754811495,
243
+ "grad_norm": 19.375,
244
+ "learning_rate": 3.686708860759494e-05,
245
+ "loss": 1.1359,
246
+ "step": 700
247
+ },
248
+ {
249
+ "epoch": 0.3691009754811495,
250
+ "eval_accuracy": 0.7633978563429851,
251
+ "eval_f1_ai": 0.9003927168868261,
252
+ "eval_f1_human": 0.6369589977220956,
253
+ "eval_f1_macro": 0.7701658728773962,
254
+ "eval_f1_micro": 0.7633978563429851,
255
+ "eval_f1_mixed": 0.7731459040232671,
256
+ "eval_f1_weighted": 0.7663932988679265,
257
+ "eval_loss": 0.5114254355430603,
258
+ "eval_precision_ai": 0.8367617783676178,
259
+ "eval_precision_human": 0.5612142498745609,
260
+ "eval_precision_mixed": 0.8696837513631407,
261
+ "eval_precision_weighted": 0.7879102421938303,
262
+ "eval_recall_ai": 0.9744976816074189,
263
+ "eval_recall_human": 0.7363396971691902,
264
+ "eval_recall_mixed": 0.6958987783595113,
265
+ "eval_recall_weighted": 0.7633978563429851,
266
+ "eval_runtime": 212.8928,
267
+ "eval_samples_per_second": 58.724,
268
+ "eval_steps_per_second": 1.837,
269
+ "step": 700
270
+ },
271
+ {
272
+ "epoch": 0.39546533087266017,
273
+ "grad_norm": 23.125,
274
+ "learning_rate": 3.95042194092827e-05,
275
+ "loss": 1.0872,
276
+ "step": 750
277
+ },
278
+ {
279
+ "epoch": 0.42182968626417083,
280
+ "grad_norm": 157.0,
281
+ "learning_rate": 4.214135021097047e-05,
282
+ "loss": 0.9872,
283
+ "step": 800
284
+ },
285
+ {
286
+ "epoch": 0.42182968626417083,
287
+ "eval_accuracy": 0.8017917133258678,
288
+ "eval_f1_ai": 0.9022680412371133,
289
+ "eval_f1_human": 0.6192686096157416,
290
+ "eval_f1_macro": 0.7856376091542879,
291
+ "eval_f1_micro": 0.8017917133258678,
292
+ "eval_f1_mixed": 0.8353761766100088,
293
+ "eval_f1_weighted": 0.7967088719488636,
294
+ "eval_loss": 0.4510592222213745,
295
+ "eval_precision_ai": 0.9672855879752431,
296
+ "eval_precision_human": 0.7100893997445722,
297
+ "eval_precision_mixed": 0.7816499809910024,
298
+ "eval_precision_weighted": 0.8026885272274894,
299
+ "eval_recall_ai": 0.8454404945904173,
300
+ "eval_recall_human": 0.5490454246214614,
301
+ "eval_recall_mixed": 0.8970331588132635,
302
+ "eval_recall_weighted": 0.8017917133258678,
303
+ "eval_runtime": 206.8504,
304
+ "eval_samples_per_second": 60.44,
305
+ "eval_steps_per_second": 1.89,
306
+ "step": 800
307
+ },
308
+ {
309
+ "epoch": 0.4481940416556815,
310
+ "grad_norm": 46.0,
311
+ "learning_rate": 4.477848101265823e-05,
312
+ "loss": 0.9952,
313
+ "step": 850
314
+ },
315
+ {
316
+ "epoch": 0.4745583970471922,
317
+ "grad_norm": 23.375,
318
+ "learning_rate": 4.7415611814346e-05,
319
+ "loss": 0.8916,
320
+ "step": 900
321
+ },
322
+ {
323
+ "epoch": 0.4745583970471922,
324
+ "eval_accuracy": 0.826427771556551,
325
+ "eval_f1_ai": 0.9497544389875331,
326
+ "eval_f1_human": 0.712417340191036,
327
+ "eval_f1_macro": 0.8327089451194482,
328
+ "eval_f1_micro": 0.826427771556551,
329
+ "eval_f1_mixed": 0.8359550561797753,
330
+ "eval_f1_weighted": 0.8294925079101134,
331
+ "eval_loss": 0.39986124634742737,
332
+ "eval_precision_ai": 0.9290465631929047,
333
+ "eval_precision_human": 0.6434828776214494,
334
+ "eval_precision_mixed": 0.8946757339525626,
335
+ "eval_precision_weighted": 0.8407505866593362,
336
+ "eval_recall_ai": 0.9714064914992272,
337
+ "eval_recall_human": 0.7978933508887426,
338
+ "eval_recall_mixed": 0.7844677137870855,
339
+ "eval_recall_weighted": 0.826427771556551,
340
+ "eval_runtime": 209.7976,
341
+ "eval_samples_per_second": 59.591,
342
+ "eval_steps_per_second": 1.864,
343
+ "step": 900
344
+ },
345
+ {
346
+ "epoch": 0.5009227524387029,
347
+ "grad_norm": 68.5,
348
+ "learning_rate": 4.9994139709329584e-05,
349
+ "loss": 0.899,
350
+ "step": 950
351
+ },
352
+ {
353
+ "epoch": 0.5272871078302136,
354
+ "grad_norm": 24.5,
355
+ "learning_rate": 4.970112517580872e-05,
356
+ "loss": 0.8748,
357
+ "step": 1000
358
+ },
359
+ {
360
+ "epoch": 0.5272871078302136,
361
+ "eval_accuracy": 0.8299472084466485,
362
+ "eval_f1_ai": 0.943791329904482,
363
+ "eval_f1_human": 0.727299016772701,
364
+ "eval_f1_macro": 0.8360557403613388,
365
+ "eval_f1_micro": 0.8299472084466485,
366
+ "eval_f1_mixed": 0.8370768744068333,
367
+ "eval_f1_weighted": 0.8324913584362222,
368
+ "eval_loss": 0.3658604323863983,
369
+ "eval_precision_ai": 0.8995098039215687,
370
+ "eval_precision_human": 0.64853017019082,
371
+ "eval_precision_mixed": 0.9174757281553398,
372
+ "eval_precision_weighted": 0.8484025864969482,
373
+ "eval_recall_ai": 0.9926584234930448,
374
+ "eval_recall_human": 0.8278472679394339,
375
+ "eval_recall_mixed": 0.7696335078534031,
376
+ "eval_recall_weighted": 0.8299472084466485,
377
+ "eval_runtime": 204.603,
378
+ "eval_samples_per_second": 61.104,
379
+ "eval_steps_per_second": 1.911,
380
+ "step": 1000
381
+ },
382
+ {
383
+ "epoch": 0.5536514632217242,
384
+ "grad_norm": 51.75,
385
+ "learning_rate": 4.940811064228786e-05,
386
+ "loss": 0.7453,
387
+ "step": 1050
388
+ },
389
+ {
390
+ "epoch": 0.5800158186132349,
391
+ "grad_norm": 34.5,
392
+ "learning_rate": 4.9115096108766995e-05,
393
+ "loss": 0.8091,
394
+ "step": 1100
395
+ },
396
+ {
397
+ "epoch": 0.5800158186132349,
398
+ "eval_accuracy": 0.8637817949128139,
399
+ "eval_f1_ai": 0.9449456821948076,
400
+ "eval_f1_human": 0.7056443455391462,
401
+ "eval_f1_macro": 0.8458904558156242,
402
+ "eval_f1_micro": 0.8637817949128139,
403
+ "eval_f1_mixed": 0.8870813397129187,
404
+ "eval_f1_weighted": 0.8549702638885073,
405
+ "eval_loss": 0.32950422167778015,
406
+ "eval_precision_ai": 0.9025677101653183,
407
+ "eval_precision_human": 0.9154855643044619,
408
+ "eval_precision_mixed": 0.8368583956667527,
409
+ "eval_precision_weighted": 0.8695671658030227,
410
+ "eval_recall_ai": 0.991499227202473,
411
+ "eval_recall_human": 0.5740618828176431,
412
+ "eval_recall_mixed": 0.943717277486911,
413
+ "eval_recall_weighted": 0.8637817949128139,
414
+ "eval_runtime": 206.2487,
415
+ "eval_samples_per_second": 60.616,
416
+ "eval_steps_per_second": 1.896,
417
+ "step": 1100
418
+ },
419
+ {
420
+ "epoch": 0.6063801740047455,
421
+ "grad_norm": 80.0,
422
+ "learning_rate": 4.882208157524614e-05,
423
+ "loss": 0.7375,
424
+ "step": 1150
425
+ },
426
+ {
427
+ "epoch": 0.6327445293962563,
428
+ "grad_norm": 28.375,
429
+ "learning_rate": 4.8529067041725276e-05,
430
+ "loss": 0.7169,
431
+ "step": 1200
432
+ },
433
+ {
434
+ "epoch": 0.6327445293962563,
435
+ "eval_accuracy": 0.8502639577667573,
436
+ "eval_f1_ai": 0.866811861283297,
437
+ "eval_f1_human": 0.7657316148597423,
438
+ "eval_f1_macro": 0.8360143830281289,
439
+ "eval_f1_micro": 0.8502639577667573,
440
+ "eval_f1_mixed": 0.8754996729413475,
441
+ "eval_f1_weighted": 0.847027475131161,
442
+ "eval_loss": 0.39430809020996094,
443
+ "eval_precision_ai": 0.7651582372079266,
444
+ "eval_precision_human": 0.902591599642538,
445
+ "eval_precision_mixed": 0.8750544820572425,
446
+ "eval_precision_weighted": 0.8589967538180886,
447
+ "eval_recall_ai": 0.999613601236476,
448
+ "eval_recall_human": 0.6649111257406188,
449
+ "eval_recall_mixed": 0.8759453170447935,
450
+ "eval_recall_weighted": 0.8502639577667573,
451
+ "eval_runtime": 214.0168,
452
+ "eval_samples_per_second": 58.416,
453
+ "eval_steps_per_second": 1.827,
454
+ "step": 1200
455
+ }
456
+ ],
457
+ "logging_steps": 50,
458
+ "max_steps": 9480,
459
+ "num_input_tokens_seen": 0,
460
+ "num_train_epochs": 5,
461
+ "save_steps": 200,
462
+ "stateful_callbacks": {
463
+ "EarlyStoppingCallback": {
464
+ "args": {
465
+ "early_stopping_patience": 3,
466
+ "early_stopping_threshold": 0.0
467
+ },
468
+ "attributes": {
469
+ "early_stopping_patience_counter": 1
470
+ }
471
+ },
472
+ "TrainerControl": {
473
+ "args": {
474
+ "should_epoch_stop": false,
475
+ "should_evaluate": false,
476
+ "should_log": false,
477
+ "should_save": true,
478
+ "should_training_stop": false
479
+ },
480
+ "attributes": {}
481
+ }
482
+ },
483
+ "total_flos": 3.987622653354922e+16,
484
+ "train_batch_size": 16,
485
+ "trial_name": null,
486
+ "trial_params": null
487
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73fd23583f06ff88ce7655b9a2564db9f270a2e6ec23b8a8bb80bd69503a247
3
+ size 5304