Pclanglais commited on
Commit
39a7ec8
·
verified ·
1 Parent(s): 0b808fd

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "law_commentary",
24
+ "1": "sociology",
25
+ "2": "biography",
26
+ "3": "literary_criticism",
27
+ "4": "theatre_play",
28
+ "5": "novel",
29
+ "6": "law,_decree_and_rules",
30
+ "7": "economics",
31
+ "8": "court_transcripts",
32
+ "9": "biology_and_medicine",
33
+ "10": "lists_and_bibliographies",
34
+ "11": "history",
35
+ "12": "philosophy",
36
+ "13": "political_news",
37
+ "14": "other_science",
38
+ "15": "political_science",
39
+ "16": "foreign_news",
40
+ "17": "advertising",
41
+ "18": "dictionary",
42
+ "19": "crime_news",
43
+ "20": "art_criticism",
44
+ "21": "music_criticism"
45
+ },
46
+ "initializer_cutoff_factor": 2.0,
47
+ "initializer_range": 0.02,
48
+ "intermediate_size": 2624,
49
+ "label2id": {
50
+ "advertising": 17,
51
+ "art_criticism": 20,
52
+ "biography": 2,
53
+ "biology_and_medicine": 9,
54
+ "court_transcripts": 8,
55
+ "crime_news": 19,
56
+ "dictionary": 18,
57
+ "economics": 7,
58
+ "foreign_news": 16,
59
+ "history": 11,
60
+ "law,_decree_and_rules": 6,
61
+ "law_commentary": 0,
62
+ "lists_and_bibliographies": 10,
63
+ "literary_criticism": 3,
64
+ "music_criticism": 21,
65
+ "novel": 5,
66
+ "other_science": 14,
67
+ "philosophy": 12,
68
+ "political_news": 13,
69
+ "political_science": 15,
70
+ "sociology": 1,
71
+ "theatre_play": 4
72
+ },
73
+ "layer_norm_eps": 1e-05,
74
+ "local_attention": 128,
75
+ "local_rope_theta": 10000.0,
76
+ "max_position_embeddings": 8192,
77
+ "mlp_bias": false,
78
+ "mlp_dropout": 0.0,
79
+ "model_type": "modernbert",
80
+ "norm_bias": false,
81
+ "norm_eps": 1e-05,
82
+ "num_attention_heads": 16,
83
+ "num_hidden_layers": 28,
84
+ "pad_token_id": 50283,
85
+ "position_embedding_type": "absolute",
86
+ "problem_type": "multi_label_classification",
87
+ "reference_compile": true,
88
+ "repad_logits_with_grad": false,
89
+ "sep_token_id": 50282,
90
+ "sparse_pred_ignore_index": -100,
91
+ "sparse_prediction": false,
92
+ "torch_dtype": "float32",
93
+ "transformers_version": "4.50.0",
94
+ "vocab_size": 50368
95
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1458cc7939031f0c91573f1be8c68d4c85d3e3bcb78b92ba495e3414d433507
3
+ size 1583433640
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c776ba1eaca66b8c2e21b58fb4c5c51a7f6b44fcf76bb5fcd3f081c46b51d6c
3
+ size 3166977146
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:858c634d5b8d5f008377efe3b75b82acf0b2b96b4b1dba4c22a037b110b4a98b
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf4ad97994be8bff20314a44f8a69b58c988e0d3f933e610bf4fb3e369ec719
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 +1,2909 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 203490,
3
+ "best_metric": 0.6936652741069145,
4
+ "best_model_checkpoint": "modernbert-heritage-category/checkpoint-203490",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 203490,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.007371369600471768,
14
+ "grad_norm": 1.2525012493133545,
15
+ "learning_rate": 1.995105410585287e-05,
16
+ "loss": 0.1758,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.014742739200943536,
21
+ "grad_norm": 0.9046939611434937,
22
+ "learning_rate": 1.990200992677773e-05,
23
+ "loss": 0.1536,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.022114108801415303,
28
+ "grad_norm": 1.5520201921463013,
29
+ "learning_rate": 1.9852867462774585e-05,
30
+ "loss": 0.1429,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.02948547840188707,
35
+ "grad_norm": 2.7046384811401367,
36
+ "learning_rate": 1.980372499877144e-05,
37
+ "loss": 0.1292,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.03685684800235884,
42
+ "grad_norm": 0.7337467670440674,
43
+ "learning_rate": 1.9754582534768295e-05,
44
+ "loss": 0.1229,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.044228217602830605,
49
+ "grad_norm": 0.6729874610900879,
50
+ "learning_rate": 1.970544007076515e-05,
51
+ "loss": 0.1193,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.05159958720330237,
56
+ "grad_norm": 6.235721111297607,
57
+ "learning_rate": 1.9656592461546026e-05,
58
+ "loss": 0.1182,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.05897095680377414,
63
+ "grad_norm": 0.02936830371618271,
64
+ "learning_rate": 1.9607449997542877e-05,
65
+ "loss": 0.1183,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.06634232640424591,
70
+ "grad_norm": 0.028409462422132492,
71
+ "learning_rate": 1.9558307533539732e-05,
72
+ "loss": 0.1164,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 0.07371369600471768,
77
+ "grad_norm": 4.09944486618042,
78
+ "learning_rate": 1.9509165069536587e-05,
79
+ "loss": 0.1053,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 0.08108506560518944,
84
+ "grad_norm": 3.7119829654693604,
85
+ "learning_rate": 1.9460022605533442e-05,
86
+ "loss": 0.1118,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.08845643520566121,
91
+ "grad_norm": 1.3968170881271362,
92
+ "learning_rate": 1.9410880141530297e-05,
93
+ "loss": 0.1092,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 0.09582780480613298,
98
+ "grad_norm": 1.2682095766067505,
99
+ "learning_rate": 1.9361737677527152e-05,
100
+ "loss": 0.107,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 0.10319917440660474,
105
+ "grad_norm": 1.898970127105713,
106
+ "learning_rate": 1.9312595213524007e-05,
107
+ "loss": 0.106,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 0.11057054400707651,
112
+ "grad_norm": 1.1229842901229858,
113
+ "learning_rate": 1.9263452749520862e-05,
114
+ "loss": 0.1066,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 0.11794191360754828,
119
+ "grad_norm": 1.5770803689956665,
120
+ "learning_rate": 1.9214310285517717e-05,
121
+ "loss": 0.1008,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 0.12531328320802004,
126
+ "grad_norm": 2.80481219291687,
127
+ "learning_rate": 1.9165167821514572e-05,
128
+ "loss": 0.1115,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 0.13268465280849182,
133
+ "grad_norm": 0.8099410533905029,
134
+ "learning_rate": 1.9116025357511427e-05,
135
+ "loss": 0.0979,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 0.1400560224089636,
140
+ "grad_norm": 2.5966243743896484,
141
+ "learning_rate": 1.9066882893508282e-05,
142
+ "loss": 0.1111,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 0.14742739200943536,
147
+ "grad_norm": 0.39728572964668274,
148
+ "learning_rate": 1.9017740429505137e-05,
149
+ "loss": 0.1014,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 0.15479876160990713,
154
+ "grad_norm": 0.4020085334777832,
155
+ "learning_rate": 1.896869625043e-05,
156
+ "loss": 0.0956,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 0.16217013121037888,
161
+ "grad_norm": 1.247157335281372,
162
+ "learning_rate": 1.891955378642685e-05,
163
+ "loss": 0.1054,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 0.16954150081085065,
168
+ "grad_norm": 0.4768887758255005,
169
+ "learning_rate": 1.8870411322423706e-05,
170
+ "loss": 0.0981,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 0.17691287041132242,
175
+ "grad_norm": 2.418336868286133,
176
+ "learning_rate": 1.882126885842056e-05,
177
+ "loss": 0.0936,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 0.1842842400117942,
182
+ "grad_norm": 0.27637165784835815,
183
+ "learning_rate": 1.877212639441742e-05,
184
+ "loss": 0.0975,
185
+ "step": 12500
186
+ },
187
+ {
188
+ "epoch": 0.19165560961226596,
189
+ "grad_norm": 0.23639962077140808,
190
+ "learning_rate": 1.8722983930414275e-05,
191
+ "loss": 0.0915,
192
+ "step": 13000
193
+ },
194
+ {
195
+ "epoch": 0.19902697921273774,
196
+ "grad_norm": 0.8892920017242432,
197
+ "learning_rate": 1.8673841466411126e-05,
198
+ "loss": 0.1,
199
+ "step": 13500
200
+ },
201
+ {
202
+ "epoch": 0.20639834881320948,
203
+ "grad_norm": 3.2099547386169434,
204
+ "learning_rate": 1.862469900240798e-05,
205
+ "loss": 0.0965,
206
+ "step": 14000
207
+ },
208
+ {
209
+ "epoch": 0.21376971841368125,
210
+ "grad_norm": 0.9265658259391785,
211
+ "learning_rate": 1.8575556538404836e-05,
212
+ "loss": 0.0988,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 0.22114108801415303,
217
+ "grad_norm": 1.8521679639816284,
218
+ "learning_rate": 1.8526414074401695e-05,
219
+ "loss": 0.0951,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 0.2285124576146248,
224
+ "grad_norm": 2.191715717315674,
225
+ "learning_rate": 1.8477369895326553e-05,
226
+ "loss": 0.1037,
227
+ "step": 15500
228
+ },
229
+ {
230
+ "epoch": 0.23588382721509657,
231
+ "grad_norm": 0.10625209659337997,
232
+ "learning_rate": 1.8428227431323408e-05,
233
+ "loss": 0.093,
234
+ "step": 16000
235
+ },
236
+ {
237
+ "epoch": 0.24325519681556834,
238
+ "grad_norm": 4.059609413146973,
239
+ "learning_rate": 1.8379084967320263e-05,
240
+ "loss": 0.0931,
241
+ "step": 16500
242
+ },
243
+ {
244
+ "epoch": 0.2506265664160401,
245
+ "grad_norm": 0.341007798910141,
246
+ "learning_rate": 1.8329942503317118e-05,
247
+ "loss": 0.0877,
248
+ "step": 17000
249
+ },
250
+ {
251
+ "epoch": 0.2579979360165119,
252
+ "grad_norm": 0.16973993182182312,
253
+ "learning_rate": 1.8280800039313973e-05,
254
+ "loss": 0.0981,
255
+ "step": 17500
256
+ },
257
+ {
258
+ "epoch": 0.26536930561698363,
259
+ "grad_norm": 0.20512279868125916,
260
+ "learning_rate": 1.8231657575310828e-05,
261
+ "loss": 0.0944,
262
+ "step": 18000
263
+ },
264
+ {
265
+ "epoch": 0.27274067521745543,
266
+ "grad_norm": 5.859679222106934,
267
+ "learning_rate": 1.818251511130768e-05,
268
+ "loss": 0.0952,
269
+ "step": 18500
270
+ },
271
+ {
272
+ "epoch": 0.2801120448179272,
273
+ "grad_norm": 0.06838594377040863,
274
+ "learning_rate": 1.8133470932232545e-05,
275
+ "loss": 0.0891,
276
+ "step": 19000
277
+ },
278
+ {
279
+ "epoch": 0.2874834144183989,
280
+ "grad_norm": 1.6491619348526,
281
+ "learning_rate": 1.80843284682294e-05,
282
+ "loss": 0.095,
283
+ "step": 19500
284
+ },
285
+ {
286
+ "epoch": 0.2948547840188707,
287
+ "grad_norm": 0.21653395891189575,
288
+ "learning_rate": 1.8035186004226252e-05,
289
+ "loss": 0.0925,
290
+ "step": 20000
291
+ },
292
+ {
293
+ "epoch": 0.30222615361934246,
294
+ "grad_norm": 0.1839127540588379,
295
+ "learning_rate": 1.7986043540223107e-05,
296
+ "loss": 0.0874,
297
+ "step": 20500
298
+ },
299
+ {
300
+ "epoch": 0.30959752321981426,
301
+ "grad_norm": 1.7096320390701294,
302
+ "learning_rate": 1.7936901076219962e-05,
303
+ "loss": 0.0921,
304
+ "step": 21000
305
+ },
306
+ {
307
+ "epoch": 0.316968892820286,
308
+ "grad_norm": 0.013913823291659355,
309
+ "learning_rate": 1.788775861221682e-05,
310
+ "loss": 0.0879,
311
+ "step": 21500
312
+ },
313
+ {
314
+ "epoch": 0.32434026242075775,
315
+ "grad_norm": 2.2390196323394775,
316
+ "learning_rate": 1.7838616148213672e-05,
317
+ "loss": 0.0988,
318
+ "step": 22000
319
+ },
320
+ {
321
+ "epoch": 0.33171163202122955,
322
+ "grad_norm": 1.1112462282180786,
323
+ "learning_rate": 1.7789473684210527e-05,
324
+ "loss": 0.0906,
325
+ "step": 22500
326
+ },
327
+ {
328
+ "epoch": 0.3390830016217013,
329
+ "grad_norm": 2.3240630626678467,
330
+ "learning_rate": 1.774042950513539e-05,
331
+ "loss": 0.0919,
332
+ "step": 23000
333
+ },
334
+ {
335
+ "epoch": 0.3464543712221731,
336
+ "grad_norm": 0.31203529238700867,
337
+ "learning_rate": 1.7691287041132244e-05,
338
+ "loss": 0.0886,
339
+ "step": 23500
340
+ },
341
+ {
342
+ "epoch": 0.35382574082264484,
343
+ "grad_norm": 0.002407611347734928,
344
+ "learning_rate": 1.76421445771291e-05,
345
+ "loss": 0.0892,
346
+ "step": 24000
347
+ },
348
+ {
349
+ "epoch": 0.36119711042311664,
350
+ "grad_norm": 0.23297803103923798,
351
+ "learning_rate": 1.7593002113125954e-05,
352
+ "loss": 0.0894,
353
+ "step": 24500
354
+ },
355
+ {
356
+ "epoch": 0.3685684800235884,
357
+ "grad_norm": 0.5540401339530945,
358
+ "learning_rate": 1.754385964912281e-05,
359
+ "loss": 0.0905,
360
+ "step": 25000
361
+ },
362
+ {
363
+ "epoch": 0.37593984962406013,
364
+ "grad_norm": 1.9130643606185913,
365
+ "learning_rate": 1.749481547004767e-05,
366
+ "loss": 0.0906,
367
+ "step": 25500
368
+ },
369
+ {
370
+ "epoch": 0.38331121922453193,
371
+ "grad_norm": 0.23371170461177826,
372
+ "learning_rate": 1.7445673006044523e-05,
373
+ "loss": 0.0925,
374
+ "step": 26000
375
+ },
376
+ {
377
+ "epoch": 0.3906825888250037,
378
+ "grad_norm": 0.16552847623825073,
379
+ "learning_rate": 1.7396530542041378e-05,
380
+ "loss": 0.088,
381
+ "step": 26500
382
+ },
383
+ {
384
+ "epoch": 0.3980539584254755,
385
+ "grad_norm": 0.008411018177866936,
386
+ "learning_rate": 1.7347388078038233e-05,
387
+ "loss": 0.0946,
388
+ "step": 27000
389
+ },
390
+ {
391
+ "epoch": 0.4054253280259472,
392
+ "grad_norm": 0.6356103420257568,
393
+ "learning_rate": 1.729824561403509e-05,
394
+ "loss": 0.0869,
395
+ "step": 27500
396
+ },
397
+ {
398
+ "epoch": 0.41279669762641896,
399
+ "grad_norm": 0.8396435379981995,
400
+ "learning_rate": 1.724920143495995e-05,
401
+ "loss": 0.0933,
402
+ "step": 28000
403
+ },
404
+ {
405
+ "epoch": 0.42016806722689076,
406
+ "grad_norm": 5.201042652130127,
407
+ "learning_rate": 1.7200157255884812e-05,
408
+ "loss": 0.0878,
409
+ "step": 28500
410
+ },
411
+ {
412
+ "epoch": 0.4275394368273625,
413
+ "grad_norm": 1.2198799848556519,
414
+ "learning_rate": 1.7151014791881667e-05,
415
+ "loss": 0.0837,
416
+ "step": 29000
417
+ },
418
+ {
419
+ "epoch": 0.4349108064278343,
420
+ "grad_norm": 1.1107237339019775,
421
+ "learning_rate": 1.7101872327878522e-05,
422
+ "loss": 0.0898,
423
+ "step": 29500
424
+ },
425
+ {
426
+ "epoch": 0.44228217602830605,
427
+ "grad_norm": 0.47166362404823303,
428
+ "learning_rate": 1.705282814880338e-05,
429
+ "loss": 0.083,
430
+ "step": 30000
431
+ },
432
+ {
433
+ "epoch": 0.44965354562877785,
434
+ "grad_norm": 0.9816909432411194,
435
+ "learning_rate": 1.7003685684800236e-05,
436
+ "loss": 0.0861,
437
+ "step": 30500
438
+ },
439
+ {
440
+ "epoch": 0.4570249152292496,
441
+ "grad_norm": 0.10324009507894516,
442
+ "learning_rate": 1.6954543220797094e-05,
443
+ "loss": 0.0942,
444
+ "step": 31000
445
+ },
446
+ {
447
+ "epoch": 0.46439628482972134,
448
+ "grad_norm": 0.42705604434013367,
449
+ "learning_rate": 1.6905400756793946e-05,
450
+ "loss": 0.0826,
451
+ "step": 31500
452
+ },
453
+ {
454
+ "epoch": 0.47176765443019314,
455
+ "grad_norm": 1.8074253797531128,
456
+ "learning_rate": 1.68562582927908e-05,
457
+ "loss": 0.0853,
458
+ "step": 32000
459
+ },
460
+ {
461
+ "epoch": 0.4791390240306649,
462
+ "grad_norm": 1.1949777603149414,
463
+ "learning_rate": 1.6807115828787656e-05,
464
+ "loss": 0.0936,
465
+ "step": 32500
466
+ },
467
+ {
468
+ "epoch": 0.4865103936311367,
469
+ "grad_norm": 1.8849105834960938,
470
+ "learning_rate": 1.675797336478451e-05,
471
+ "loss": 0.0849,
472
+ "step": 33000
473
+ },
474
+ {
475
+ "epoch": 0.49388176323160843,
476
+ "grad_norm": 2.1948788166046143,
477
+ "learning_rate": 1.670883090078137e-05,
478
+ "loss": 0.083,
479
+ "step": 33500
480
+ },
481
+ {
482
+ "epoch": 0.5012531328320802,
483
+ "grad_norm": 1.5681918859481812,
484
+ "learning_rate": 1.665968843677822e-05,
485
+ "loss": 0.0845,
486
+ "step": 34000
487
+ },
488
+ {
489
+ "epoch": 0.508624502432552,
490
+ "grad_norm": 1.447178840637207,
491
+ "learning_rate": 1.6610545972775076e-05,
492
+ "loss": 0.0883,
493
+ "step": 34500
494
+ },
495
+ {
496
+ "epoch": 0.5159958720330238,
497
+ "grad_norm": 0.678683876991272,
498
+ "learning_rate": 1.6561501793699938e-05,
499
+ "loss": 0.0901,
500
+ "step": 35000
501
+ },
502
+ {
503
+ "epoch": 0.5233672416334955,
504
+ "grad_norm": 1.585949420928955,
505
+ "learning_rate": 1.6512359329696793e-05,
506
+ "loss": 0.0893,
507
+ "step": 35500
508
+ },
509
+ {
510
+ "epoch": 0.5307386112339673,
511
+ "grad_norm": 2.8461952209472656,
512
+ "learning_rate": 1.6463216865693648e-05,
513
+ "loss": 0.0846,
514
+ "step": 36000
515
+ },
516
+ {
517
+ "epoch": 0.5381099808344391,
518
+ "grad_norm": 0.08873996883630753,
519
+ "learning_rate": 1.6414074401690503e-05,
520
+ "loss": 0.0838,
521
+ "step": 36500
522
+ },
523
+ {
524
+ "epoch": 0.5454813504349109,
525
+ "grad_norm": 0.08909033238887787,
526
+ "learning_rate": 1.6364931937687354e-05,
527
+ "loss": 0.0835,
528
+ "step": 37000
529
+ },
530
+ {
531
+ "epoch": 0.5528527200353825,
532
+ "grad_norm": 0.01679537631571293,
533
+ "learning_rate": 1.6315789473684213e-05,
534
+ "loss": 0.0826,
535
+ "step": 37500
536
+ },
537
+ {
538
+ "epoch": 0.5602240896358543,
539
+ "grad_norm": 0.018643999472260475,
540
+ "learning_rate": 1.6266647009681068e-05,
541
+ "loss": 0.0891,
542
+ "step": 38000
543
+ },
544
+ {
545
+ "epoch": 0.5675954592363261,
546
+ "grad_norm": 3.226288080215454,
547
+ "learning_rate": 1.6217504545677923e-05,
548
+ "loss": 0.0927,
549
+ "step": 38500
550
+ },
551
+ {
552
+ "epoch": 0.5749668288367978,
553
+ "grad_norm": 6.410881042480469,
554
+ "learning_rate": 1.6168362081674774e-05,
555
+ "loss": 0.0826,
556
+ "step": 39000
557
+ },
558
+ {
559
+ "epoch": 0.5823381984372696,
560
+ "grad_norm": 2.421131134033203,
561
+ "learning_rate": 1.611921961767163e-05,
562
+ "loss": 0.0854,
563
+ "step": 39500
564
+ },
565
+ {
566
+ "epoch": 0.5897095680377414,
567
+ "grad_norm": 0.012708733789622784,
568
+ "learning_rate": 1.6070077153668488e-05,
569
+ "loss": 0.0841,
570
+ "step": 40000
571
+ },
572
+ {
573
+ "epoch": 0.5970809376382131,
574
+ "grad_norm": 5.636229515075684,
575
+ "learning_rate": 1.6021032974593347e-05,
576
+ "loss": 0.0794,
577
+ "step": 40500
578
+ },
579
+ {
580
+ "epoch": 0.6044523072386849,
581
+ "grad_norm": 1.866571307182312,
582
+ "learning_rate": 1.59718905105902e-05,
583
+ "loss": 0.0836,
584
+ "step": 41000
585
+ },
586
+ {
587
+ "epoch": 0.6118236768391567,
588
+ "grad_norm": 1.0771315097808838,
589
+ "learning_rate": 1.5922748046587057e-05,
590
+ "loss": 0.0782,
591
+ "step": 41500
592
+ },
593
+ {
594
+ "epoch": 0.6191950464396285,
595
+ "grad_norm": 0.09344267845153809,
596
+ "learning_rate": 1.587360558258391e-05,
597
+ "loss": 0.0891,
598
+ "step": 42000
599
+ },
600
+ {
601
+ "epoch": 0.6265664160401002,
602
+ "grad_norm": 2.4186413288116455,
603
+ "learning_rate": 1.5824463118580767e-05,
604
+ "loss": 0.0907,
605
+ "step": 42500
606
+ },
607
+ {
608
+ "epoch": 0.633937785640572,
609
+ "grad_norm": 0.09242186695337296,
610
+ "learning_rate": 1.577532065457762e-05,
611
+ "loss": 0.081,
612
+ "step": 43000
613
+ },
614
+ {
615
+ "epoch": 0.6413091552410438,
616
+ "grad_norm": 0.09285570681095123,
617
+ "learning_rate": 1.572637476043049e-05,
618
+ "loss": 0.0902,
619
+ "step": 43500
620
+ },
621
+ {
622
+ "epoch": 0.6486805248415155,
623
+ "grad_norm": 1.1049730777740479,
624
+ "learning_rate": 1.5677232296427346e-05,
625
+ "loss": 0.081,
626
+ "step": 44000
627
+ },
628
+ {
629
+ "epoch": 0.6560518944419873,
630
+ "grad_norm": 0.1485988050699234,
631
+ "learning_rate": 1.5628089832424197e-05,
632
+ "loss": 0.0834,
633
+ "step": 44500
634
+ },
635
+ {
636
+ "epoch": 0.6634232640424591,
637
+ "grad_norm": 1.4170334339141846,
638
+ "learning_rate": 1.5578947368421052e-05,
639
+ "loss": 0.08,
640
+ "step": 45000
641
+ },
642
+ {
643
+ "epoch": 0.6707946336429309,
644
+ "grad_norm": 2.51129150390625,
645
+ "learning_rate": 1.5529903189345914e-05,
646
+ "loss": 0.0881,
647
+ "step": 45500
648
+ },
649
+ {
650
+ "epoch": 0.6781660032434026,
651
+ "grad_norm": 0.0491604208946228,
652
+ "learning_rate": 1.548076072534277e-05,
653
+ "loss": 0.0845,
654
+ "step": 46000
655
+ },
656
+ {
657
+ "epoch": 0.6855373728438744,
658
+ "grad_norm": 0.09064287692308426,
659
+ "learning_rate": 1.5431618261339624e-05,
660
+ "loss": 0.0838,
661
+ "step": 46500
662
+ },
663
+ {
664
+ "epoch": 0.6929087424443462,
665
+ "grad_norm": 1.6225173473358154,
666
+ "learning_rate": 1.538247579733648e-05,
667
+ "loss": 0.0806,
668
+ "step": 47000
669
+ },
670
+ {
671
+ "epoch": 0.7002801120448179,
672
+ "grad_norm": 0.025229327380657196,
673
+ "learning_rate": 1.5333333333333334e-05,
674
+ "loss": 0.0852,
675
+ "step": 47500
676
+ },
677
+ {
678
+ "epoch": 0.7076514816452897,
679
+ "grad_norm": 1.561880350112915,
680
+ "learning_rate": 1.528419086933019e-05,
681
+ "loss": 0.0819,
682
+ "step": 48000
683
+ },
684
+ {
685
+ "epoch": 0.7150228512457615,
686
+ "grad_norm": 0.024792635813355446,
687
+ "learning_rate": 1.5235048405327044e-05,
688
+ "loss": 0.0844,
689
+ "step": 48500
690
+ },
691
+ {
692
+ "epoch": 0.7223942208462333,
693
+ "grad_norm": 0.2325647473335266,
694
+ "learning_rate": 1.51859059413239e-05,
695
+ "loss": 0.0786,
696
+ "step": 49000
697
+ },
698
+ {
699
+ "epoch": 0.729765590446705,
700
+ "grad_norm": 1.0401220321655273,
701
+ "learning_rate": 1.5136763477320754e-05,
702
+ "loss": 0.0753,
703
+ "step": 49500
704
+ },
705
+ {
706
+ "epoch": 0.7371369600471768,
707
+ "grad_norm": 2.6318838596343994,
708
+ "learning_rate": 1.5087621013317608e-05,
709
+ "loss": 0.0793,
710
+ "step": 50000
711
+ },
712
+ {
713
+ "epoch": 0.7445083296476486,
714
+ "grad_norm": 0.15695439279079437,
715
+ "learning_rate": 1.5038478549314463e-05,
716
+ "loss": 0.085,
717
+ "step": 50500
718
+ },
719
+ {
720
+ "epoch": 0.7518796992481203,
721
+ "grad_norm": 0.006814942229539156,
722
+ "learning_rate": 1.498933608531132e-05,
723
+ "loss": 0.0819,
724
+ "step": 51000
725
+ },
726
+ {
727
+ "epoch": 0.7592510688485921,
728
+ "grad_norm": 2.0822718143463135,
729
+ "learning_rate": 1.4940193621308174e-05,
730
+ "loss": 0.0798,
731
+ "step": 51500
732
+ },
733
+ {
734
+ "epoch": 0.7666224384490639,
735
+ "grad_norm": 0.06762377172708511,
736
+ "learning_rate": 1.4891149442233035e-05,
737
+ "loss": 0.0793,
738
+ "step": 52000
739
+ },
740
+ {
741
+ "epoch": 0.7739938080495357,
742
+ "grad_norm": 1.627299189567566,
743
+ "learning_rate": 1.484200697822989e-05,
744
+ "loss": 0.08,
745
+ "step": 52500
746
+ },
747
+ {
748
+ "epoch": 0.7813651776500073,
749
+ "grad_norm": 0.8819578289985657,
750
+ "learning_rate": 1.4792864514226743e-05,
751
+ "loss": 0.0897,
752
+ "step": 53000
753
+ },
754
+ {
755
+ "epoch": 0.7887365472504791,
756
+ "grad_norm": 3.7201988697052,
757
+ "learning_rate": 1.4743722050223598e-05,
758
+ "loss": 0.0787,
759
+ "step": 53500
760
+ },
761
+ {
762
+ "epoch": 0.796107916850951,
763
+ "grad_norm": 2.0705556869506836,
764
+ "learning_rate": 1.4694677871148462e-05,
765
+ "loss": 0.0897,
766
+ "step": 54000
767
+ },
768
+ {
769
+ "epoch": 0.8034792864514226,
770
+ "grad_norm": 0.08984575420618057,
771
+ "learning_rate": 1.4645535407145315e-05,
772
+ "loss": 0.0875,
773
+ "step": 54500
774
+ },
775
+ {
776
+ "epoch": 0.8108506560518944,
777
+ "grad_norm": 0.5264925956726074,
778
+ "learning_rate": 1.459639294314217e-05,
779
+ "loss": 0.081,
780
+ "step": 55000
781
+ },
782
+ {
783
+ "epoch": 0.8182220256523662,
784
+ "grad_norm": 0.7385400533676147,
785
+ "learning_rate": 1.4547250479139025e-05,
786
+ "loss": 0.0804,
787
+ "step": 55500
788
+ },
789
+ {
790
+ "epoch": 0.8255933952528379,
791
+ "grad_norm": 0.04134887456893921,
792
+ "learning_rate": 1.449810801513588e-05,
793
+ "loss": 0.0797,
794
+ "step": 56000
795
+ },
796
+ {
797
+ "epoch": 0.8329647648533097,
798
+ "grad_norm": 0.03769136965274811,
799
+ "learning_rate": 1.4448965551132734e-05,
800
+ "loss": 0.084,
801
+ "step": 56500
802
+ },
803
+ {
804
+ "epoch": 0.8403361344537815,
805
+ "grad_norm": 0.2623615264892578,
806
+ "learning_rate": 1.4399921372057597e-05,
807
+ "loss": 0.0821,
808
+ "step": 57000
809
+ },
810
+ {
811
+ "epoch": 0.8477075040542533,
812
+ "grad_norm": 2.0235373973846436,
813
+ "learning_rate": 1.435077890805445e-05,
814
+ "loss": 0.0806,
815
+ "step": 57500
816
+ },
817
+ {
818
+ "epoch": 0.855078873654725,
819
+ "grad_norm": 0.32753029465675354,
820
+ "learning_rate": 1.4301636444051306e-05,
821
+ "loss": 0.0828,
822
+ "step": 58000
823
+ },
824
+ {
825
+ "epoch": 0.8624502432551968,
826
+ "grad_norm": 2.255500316619873,
827
+ "learning_rate": 1.425249398004816e-05,
828
+ "loss": 0.0804,
829
+ "step": 58500
830
+ },
831
+ {
832
+ "epoch": 0.8698216128556686,
833
+ "grad_norm": 2.8162291049957275,
834
+ "learning_rate": 1.4203449800973021e-05,
835
+ "loss": 0.0827,
836
+ "step": 59000
837
+ },
838
+ {
839
+ "epoch": 0.8771929824561403,
840
+ "grad_norm": 0.41316208243370056,
841
+ "learning_rate": 1.4154307336969876e-05,
842
+ "loss": 0.0753,
843
+ "step": 59500
844
+ },
845
+ {
846
+ "epoch": 0.8845643520566121,
847
+ "grad_norm": 1.9982844591140747,
848
+ "learning_rate": 1.4105164872966733e-05,
849
+ "loss": 0.0854,
850
+ "step": 60000
851
+ },
852
+ {
853
+ "epoch": 0.8919357216570839,
854
+ "grad_norm": 1.8432923555374146,
855
+ "learning_rate": 1.4056022408963586e-05,
856
+ "loss": 0.077,
857
+ "step": 60500
858
+ },
859
+ {
860
+ "epoch": 0.8993070912575557,
861
+ "grad_norm": 3.33919620513916,
862
+ "learning_rate": 1.4006879944960441e-05,
863
+ "loss": 0.082,
864
+ "step": 61000
865
+ },
866
+ {
867
+ "epoch": 0.9066784608580274,
868
+ "grad_norm": 3.227517604827881,
869
+ "learning_rate": 1.3957737480957296e-05,
870
+ "loss": 0.0785,
871
+ "step": 61500
872
+ },
873
+ {
874
+ "epoch": 0.9140498304584992,
875
+ "grad_norm": 0.014868408441543579,
876
+ "learning_rate": 1.3908595016954151e-05,
877
+ "loss": 0.0741,
878
+ "step": 62000
879
+ },
880
+ {
881
+ "epoch": 0.921421200058971,
882
+ "grad_norm": 0.06270582973957062,
883
+ "learning_rate": 1.3859452552951008e-05,
884
+ "loss": 0.0786,
885
+ "step": 62500
886
+ },
887
+ {
888
+ "epoch": 0.9287925696594427,
889
+ "grad_norm": 0.06437293440103531,
890
+ "learning_rate": 1.3810310088947861e-05,
891
+ "loss": 0.076,
892
+ "step": 63000
893
+ },
894
+ {
895
+ "epoch": 0.9361639392599145,
896
+ "grad_norm": 0.9199370741844177,
897
+ "learning_rate": 1.3761167624944716e-05,
898
+ "loss": 0.0815,
899
+ "step": 63500
900
+ },
901
+ {
902
+ "epoch": 0.9435353088603863,
903
+ "grad_norm": 0.020321089774370193,
904
+ "learning_rate": 1.3712123445869577e-05,
905
+ "loss": 0.0837,
906
+ "step": 64000
907
+ },
908
+ {
909
+ "epoch": 0.9509066784608581,
910
+ "grad_norm": 2.2705533504486084,
911
+ "learning_rate": 1.3662980981866432e-05,
912
+ "loss": 0.0871,
913
+ "step": 64500
914
+ },
915
+ {
916
+ "epoch": 0.9582780480613298,
917
+ "grad_norm": 0.027517901733517647,
918
+ "learning_rate": 1.3613838517863287e-05,
919
+ "loss": 0.0755,
920
+ "step": 65000
921
+ },
922
+ {
923
+ "epoch": 0.9656494176618016,
924
+ "grad_norm": 1.307394027709961,
925
+ "learning_rate": 1.3564696053860143e-05,
926
+ "loss": 0.0764,
927
+ "step": 65500
928
+ },
929
+ {
930
+ "epoch": 0.9730207872622734,
931
+ "grad_norm": 2.4579734802246094,
932
+ "learning_rate": 1.3515553589856995e-05,
933
+ "loss": 0.0782,
934
+ "step": 66000
935
+ },
936
+ {
937
+ "epoch": 0.9803921568627451,
938
+ "grad_norm": 13.52622127532959,
939
+ "learning_rate": 1.3466411125853852e-05,
940
+ "loss": 0.0704,
941
+ "step": 66500
942
+ },
943
+ {
944
+ "epoch": 0.9877635264632169,
945
+ "grad_norm": 0.32894331216812134,
946
+ "learning_rate": 1.3417268661850707e-05,
947
+ "loss": 0.0838,
948
+ "step": 67000
949
+ },
950
+ {
951
+ "epoch": 0.9951348960636887,
952
+ "grad_norm": 0.08820515871047974,
953
+ "learning_rate": 1.3368126197847562e-05,
954
+ "loss": 0.0792,
955
+ "step": 67500
956
+ },
957
+ {
958
+ "epoch": 1.0,
959
+ "eval_accuracy": 0.6063492063492063,
960
+ "eval_f1": 0.6658804318243672,
961
+ "eval_loss": 0.07707133144140244,
962
+ "eval_roc_auc": 0.8010158538939403,
963
+ "eval_runtime": 92.2448,
964
+ "eval_samples_per_second": 64.882,
965
+ "eval_steps_per_second": 64.882,
966
+ "step": 67830
967
+ },
968
+ {
969
+ "epoch": 1.0025062656641603,
970
+ "grad_norm": 1.2780104875564575,
971
+ "learning_rate": 1.3318983733844415e-05,
972
+ "loss": 0.0722,
973
+ "step": 68000
974
+ },
975
+ {
976
+ "epoch": 1.0098776352646321,
977
+ "grad_norm": 0.016919715330004692,
978
+ "learning_rate": 1.3269939554769277e-05,
979
+ "loss": 0.0544,
980
+ "step": 68500
981
+ },
982
+ {
983
+ "epoch": 1.017249004865104,
984
+ "grad_norm": 0.0008094881195574999,
985
+ "learning_rate": 1.3220797090766134e-05,
986
+ "loss": 0.0589,
987
+ "step": 69000
988
+ },
989
+ {
990
+ "epoch": 1.0246203744655757,
991
+ "grad_norm": 0.06712741404771805,
992
+ "learning_rate": 1.3171752911690994e-05,
993
+ "loss": 0.0692,
994
+ "step": 69500
995
+ },
996
+ {
997
+ "epoch": 1.0319917440660475,
998
+ "grad_norm": 1.4024405479431152,
999
+ "learning_rate": 1.3122610447687849e-05,
1000
+ "loss": 0.0577,
1001
+ "step": 70000
1002
+ },
1003
+ {
1004
+ "epoch": 1.0393631136665193,
1005
+ "grad_norm": 3.811220407485962,
1006
+ "learning_rate": 1.3073467983684702e-05,
1007
+ "loss": 0.0598,
1008
+ "step": 70500
1009
+ },
1010
+ {
1011
+ "epoch": 1.046734483266991,
1012
+ "grad_norm": 0.061250410974025726,
1013
+ "learning_rate": 1.3024325519681557e-05,
1014
+ "loss": 0.064,
1015
+ "step": 71000
1016
+ },
1017
+ {
1018
+ "epoch": 1.0541058528674627,
1019
+ "grad_norm": 2.3042991161346436,
1020
+ "learning_rate": 1.2975183055678412e-05,
1021
+ "loss": 0.0646,
1022
+ "step": 71500
1023
+ },
1024
+ {
1025
+ "epoch": 1.0614772224679345,
1026
+ "grad_norm": 0.32951870560646057,
1027
+ "learning_rate": 1.2926040591675269e-05,
1028
+ "loss": 0.0668,
1029
+ "step": 72000
1030
+ },
1031
+ {
1032
+ "epoch": 1.0688485920684063,
1033
+ "grad_norm": 0.013675130903720856,
1034
+ "learning_rate": 1.2876898127672122e-05,
1035
+ "loss": 0.0576,
1036
+ "step": 72500
1037
+ },
1038
+ {
1039
+ "epoch": 1.0762199616688781,
1040
+ "grad_norm": 2.3298966884613037,
1041
+ "learning_rate": 1.2827755663668977e-05,
1042
+ "loss": 0.0583,
1043
+ "step": 73000
1044
+ },
1045
+ {
1046
+ "epoch": 1.08359133126935,
1047
+ "grad_norm": 0.04673844203352928,
1048
+ "learning_rate": 1.2778809769521845e-05,
1049
+ "loss": 0.0697,
1050
+ "step": 73500
1051
+ },
1052
+ {
1053
+ "epoch": 1.0909627008698215,
1054
+ "grad_norm": 1.1629608869552612,
1055
+ "learning_rate": 1.27296673055187e-05,
1056
+ "loss": 0.0621,
1057
+ "step": 74000
1058
+ },
1059
+ {
1060
+ "epoch": 1.0983340704702933,
1061
+ "grad_norm": 0.06381271779537201,
1062
+ "learning_rate": 1.2680524841515553e-05,
1063
+ "loss": 0.0629,
1064
+ "step": 74500
1065
+ },
1066
+ {
1067
+ "epoch": 1.105705440070765,
1068
+ "grad_norm": 0.00508810393512249,
1069
+ "learning_rate": 1.2631382377512408e-05,
1070
+ "loss": 0.065,
1071
+ "step": 75000
1072
+ },
1073
+ {
1074
+ "epoch": 1.113076809671237,
1075
+ "grad_norm": 4.200405597686768,
1076
+ "learning_rate": 1.2582239913509265e-05,
1077
+ "loss": 0.0704,
1078
+ "step": 75500
1079
+ },
1080
+ {
1081
+ "epoch": 1.1204481792717087,
1082
+ "grad_norm": 0.18736723065376282,
1083
+ "learning_rate": 1.253309744950612e-05,
1084
+ "loss": 0.0683,
1085
+ "step": 76000
1086
+ },
1087
+ {
1088
+ "epoch": 1.1278195488721805,
1089
+ "grad_norm": 0.09223194420337677,
1090
+ "learning_rate": 1.2483954985502975e-05,
1091
+ "loss": 0.0557,
1092
+ "step": 76500
1093
+ },
1094
+ {
1095
+ "epoch": 1.1351909184726523,
1096
+ "grad_norm": 5.287250518798828,
1097
+ "learning_rate": 1.2434812521499828e-05,
1098
+ "loss": 0.0643,
1099
+ "step": 77000
1100
+ },
1101
+ {
1102
+ "epoch": 1.1425622880731239,
1103
+ "grad_norm": 1.283521294593811,
1104
+ "learning_rate": 1.2385670057496683e-05,
1105
+ "loss": 0.0584,
1106
+ "step": 77500
1107
+ },
1108
+ {
1109
+ "epoch": 1.1499336576735957,
1110
+ "grad_norm": 3.34344220161438,
1111
+ "learning_rate": 1.233652759349354e-05,
1112
+ "loss": 0.0673,
1113
+ "step": 78000
1114
+ },
1115
+ {
1116
+ "epoch": 1.1573050272740675,
1117
+ "grad_norm": 0.23046046495437622,
1118
+ "learning_rate": 1.2287385129490395e-05,
1119
+ "loss": 0.0605,
1120
+ "step": 78500
1121
+ },
1122
+ {
1123
+ "epoch": 1.1646763968745393,
1124
+ "grad_norm": 0.0487230159342289,
1125
+ "learning_rate": 1.2238242665487248e-05,
1126
+ "loss": 0.0672,
1127
+ "step": 79000
1128
+ },
1129
+ {
1130
+ "epoch": 1.172047766475011,
1131
+ "grad_norm": 0.0587400384247303,
1132
+ "learning_rate": 1.2189100201484103e-05,
1133
+ "loss": 0.0635,
1134
+ "step": 79500
1135
+ },
1136
+ {
1137
+ "epoch": 1.1794191360754829,
1138
+ "grad_norm": 0.3049776256084442,
1139
+ "learning_rate": 1.2140056022408964e-05,
1140
+ "loss": 0.0587,
1141
+ "step": 80000
1142
+ },
1143
+ {
1144
+ "epoch": 1.1867905056759547,
1145
+ "grad_norm": 0.5761535167694092,
1146
+ "learning_rate": 1.2091011843333826e-05,
1147
+ "loss": 0.0706,
1148
+ "step": 80500
1149
+ },
1150
+ {
1151
+ "epoch": 1.1941618752764263,
1152
+ "grad_norm": 2.524258852005005,
1153
+ "learning_rate": 1.2041967664258686e-05,
1154
+ "loss": 0.0607,
1155
+ "step": 81000
1156
+ },
1157
+ {
1158
+ "epoch": 1.201533244876898,
1159
+ "grad_norm": 0.026634838432073593,
1160
+ "learning_rate": 1.1992825200255543e-05,
1161
+ "loss": 0.0581,
1162
+ "step": 81500
1163
+ },
1164
+ {
1165
+ "epoch": 1.2089046144773699,
1166
+ "grad_norm": 0.39337214827537537,
1167
+ "learning_rate": 1.1943682736252398e-05,
1168
+ "loss": 0.0652,
1169
+ "step": 82000
1170
+ },
1171
+ {
1172
+ "epoch": 1.2162759840778417,
1173
+ "grad_norm": 1.8906174898147583,
1174
+ "learning_rate": 1.1894540272249251e-05,
1175
+ "loss": 0.0659,
1176
+ "step": 82500
1177
+ },
1178
+ {
1179
+ "epoch": 1.2236473536783135,
1180
+ "grad_norm": 0.011290138587355614,
1181
+ "learning_rate": 1.1845397808246106e-05,
1182
+ "loss": 0.0615,
1183
+ "step": 83000
1184
+ },
1185
+ {
1186
+ "epoch": 1.2310187232787853,
1187
+ "grad_norm": 0.5536847114562988,
1188
+ "learning_rate": 1.1796255344242961e-05,
1189
+ "loss": 0.0666,
1190
+ "step": 83500
1191
+ },
1192
+ {
1193
+ "epoch": 1.238390092879257,
1194
+ "grad_norm": 0.0035450158175081015,
1195
+ "learning_rate": 1.1747112880239818e-05,
1196
+ "loss": 0.0597,
1197
+ "step": 84000
1198
+ },
1199
+ {
1200
+ "epoch": 1.2457614624797286,
1201
+ "grad_norm": 0.005579414777457714,
1202
+ "learning_rate": 1.1697970416236671e-05,
1203
+ "loss": 0.0545,
1204
+ "step": 84500
1205
+ },
1206
+ {
1207
+ "epoch": 1.2531328320802004,
1208
+ "grad_norm": 0.10251569747924805,
1209
+ "learning_rate": 1.1648926237161533e-05,
1210
+ "loss": 0.0652,
1211
+ "step": 85000
1212
+ },
1213
+ {
1214
+ "epoch": 1.2605042016806722,
1215
+ "grad_norm": 3.2004494667053223,
1216
+ "learning_rate": 1.1599783773158386e-05,
1217
+ "loss": 0.0546,
1218
+ "step": 85500
1219
+ },
1220
+ {
1221
+ "epoch": 1.267875571281144,
1222
+ "grad_norm": 1.5647473335266113,
1223
+ "learning_rate": 1.1550641309155241e-05,
1224
+ "loss": 0.0661,
1225
+ "step": 86000
1226
+ },
1227
+ {
1228
+ "epoch": 1.2752469408816158,
1229
+ "grad_norm": 2.5646321773529053,
1230
+ "learning_rate": 1.1501498845152096e-05,
1231
+ "loss": 0.0616,
1232
+ "step": 86500
1233
+ },
1234
+ {
1235
+ "epoch": 1.2826183104820876,
1236
+ "grad_norm": 0.008838827721774578,
1237
+ "learning_rate": 1.1452356381148953e-05,
1238
+ "loss": 0.0643,
1239
+ "step": 87000
1240
+ },
1241
+ {
1242
+ "epoch": 1.2899896800825594,
1243
+ "grad_norm": 0.27586570382118225,
1244
+ "learning_rate": 1.1403213917145805e-05,
1245
+ "loss": 0.0651,
1246
+ "step": 87500
1247
+ },
1248
+ {
1249
+ "epoch": 1.297361049683031,
1250
+ "grad_norm": 2.2683589458465576,
1251
+ "learning_rate": 1.1354071453142661e-05,
1252
+ "loss": 0.0613,
1253
+ "step": 88000
1254
+ },
1255
+ {
1256
+ "epoch": 1.3047324192835028,
1257
+ "grad_norm": 0.0017950567416846752,
1258
+ "learning_rate": 1.1305027274067524e-05,
1259
+ "loss": 0.0616,
1260
+ "step": 88500
1261
+ },
1262
+ {
1263
+ "epoch": 1.3121037888839746,
1264
+ "grad_norm": 0.03913048282265663,
1265
+ "learning_rate": 1.1255884810064377e-05,
1266
+ "loss": 0.0627,
1267
+ "step": 89000
1268
+ },
1269
+ {
1270
+ "epoch": 1.3194751584844464,
1271
+ "grad_norm": 5.085097312927246,
1272
+ "learning_rate": 1.1206742346061232e-05,
1273
+ "loss": 0.0648,
1274
+ "step": 89500
1275
+ },
1276
+ {
1277
+ "epoch": 1.3268465280849182,
1278
+ "grad_norm": 0.04779289662837982,
1279
+ "learning_rate": 1.1157599882058089e-05,
1280
+ "loss": 0.0666,
1281
+ "step": 90000
1282
+ },
1283
+ {
1284
+ "epoch": 1.33421789768539,
1285
+ "grad_norm": 0.01123060006648302,
1286
+ "learning_rate": 1.1108457418054944e-05,
1287
+ "loss": 0.0618,
1288
+ "step": 90500
1289
+ },
1290
+ {
1291
+ "epoch": 1.3415892672858618,
1292
+ "grad_norm": 1.5869191884994507,
1293
+ "learning_rate": 1.1059314954051797e-05,
1294
+ "loss": 0.066,
1295
+ "step": 91000
1296
+ },
1297
+ {
1298
+ "epoch": 1.3489606368863334,
1299
+ "grad_norm": 0.00517408037558198,
1300
+ "learning_rate": 1.1010172490048652e-05,
1301
+ "loss": 0.062,
1302
+ "step": 91500
1303
+ },
1304
+ {
1305
+ "epoch": 1.3563320064868052,
1306
+ "grad_norm": 0.09691867977380753,
1307
+ "learning_rate": 1.0961030026045507e-05,
1308
+ "loss": 0.0606,
1309
+ "step": 92000
1310
+ },
1311
+ {
1312
+ "epoch": 1.363703376087277,
1313
+ "grad_norm": 3.3921549320220947,
1314
+ "learning_rate": 1.0911887562042362e-05,
1315
+ "loss": 0.0643,
1316
+ "step": 92500
1317
+ },
1318
+ {
1319
+ "epoch": 1.3710747456877488,
1320
+ "grad_norm": 2.874007225036621,
1321
+ "learning_rate": 1.0862843382967222e-05,
1322
+ "loss": 0.0622,
1323
+ "step": 93000
1324
+ },
1325
+ {
1326
+ "epoch": 1.3784461152882206,
1327
+ "grad_norm": 0.03864584490656853,
1328
+ "learning_rate": 1.0813897488820091e-05,
1329
+ "loss": 0.0582,
1330
+ "step": 93500
1331
+ },
1332
+ {
1333
+ "epoch": 1.3858174848886924,
1334
+ "grad_norm": 0.12044321745634079,
1335
+ "learning_rate": 1.0764755024816945e-05,
1336
+ "loss": 0.0672,
1337
+ "step": 94000
1338
+ },
1339
+ {
1340
+ "epoch": 1.3931888544891642,
1341
+ "grad_norm": 3.673576593399048,
1342
+ "learning_rate": 1.07156125608138e-05,
1343
+ "loss": 0.0619,
1344
+ "step": 94500
1345
+ },
1346
+ {
1347
+ "epoch": 1.4005602240896358,
1348
+ "grad_norm": 0.023468611761927605,
1349
+ "learning_rate": 1.0666470096810655e-05,
1350
+ "loss": 0.0567,
1351
+ "step": 95000
1352
+ },
1353
+ {
1354
+ "epoch": 1.4079315936901076,
1355
+ "grad_norm": 1.5474720001220703,
1356
+ "learning_rate": 1.061732763280751e-05,
1357
+ "loss": 0.057,
1358
+ "step": 95500
1359
+ },
1360
+ {
1361
+ "epoch": 1.4153029632905794,
1362
+ "grad_norm": 0.4061996340751648,
1363
+ "learning_rate": 1.0568185168804366e-05,
1364
+ "loss": 0.0551,
1365
+ "step": 96000
1366
+ },
1367
+ {
1368
+ "epoch": 1.4226743328910512,
1369
+ "grad_norm": 1.828468918800354,
1370
+ "learning_rate": 1.0519042704801218e-05,
1371
+ "loss": 0.0642,
1372
+ "step": 96500
1373
+ },
1374
+ {
1375
+ "epoch": 1.430045702491523,
1376
+ "grad_norm": 0.006184196099638939,
1377
+ "learning_rate": 1.0469900240798075e-05,
1378
+ "loss": 0.0562,
1379
+ "step": 97000
1380
+ },
1381
+ {
1382
+ "epoch": 1.4374170720919948,
1383
+ "grad_norm": 0.8913156390190125,
1384
+ "learning_rate": 1.0420856061722935e-05,
1385
+ "loss": 0.0626,
1386
+ "step": 97500
1387
+ },
1388
+ {
1389
+ "epoch": 1.4447884416924666,
1390
+ "grad_norm": 0.08904910832643509,
1391
+ "learning_rate": 1.037171359771979e-05,
1392
+ "loss": 0.0558,
1393
+ "step": 98000
1394
+ },
1395
+ {
1396
+ "epoch": 1.4521598112929381,
1397
+ "grad_norm": 0.1683080941438675,
1398
+ "learning_rate": 1.0322571133716645e-05,
1399
+ "loss": 0.0644,
1400
+ "step": 98500
1401
+ },
1402
+ {
1403
+ "epoch": 1.45953118089341,
1404
+ "grad_norm": 0.4399701654911041,
1405
+ "learning_rate": 1.0273428669713502e-05,
1406
+ "loss": 0.0608,
1407
+ "step": 99000
1408
+ },
1409
+ {
1410
+ "epoch": 1.4669025504938817,
1411
+ "grad_norm": 9.481819152832031,
1412
+ "learning_rate": 1.0224286205710354e-05,
1413
+ "loss": 0.0597,
1414
+ "step": 99500
1415
+ },
1416
+ {
1417
+ "epoch": 1.4742739200943535,
1418
+ "grad_norm": 0.10929368436336517,
1419
+ "learning_rate": 1.017514374170721e-05,
1420
+ "loss": 0.0616,
1421
+ "step": 100000
1422
+ },
1423
+ {
1424
+ "epoch": 1.4816452896948253,
1425
+ "grad_norm": 0.0035255183465778828,
1426
+ "learning_rate": 1.0126001277704065e-05,
1427
+ "loss": 0.0593,
1428
+ "step": 100500
1429
+ },
1430
+ {
1431
+ "epoch": 1.4890166592952971,
1432
+ "grad_norm": 0.07139890640974045,
1433
+ "learning_rate": 1.007685881370092e-05,
1434
+ "loss": 0.0635,
1435
+ "step": 101000
1436
+ },
1437
+ {
1438
+ "epoch": 1.496388028895769,
1439
+ "grad_norm": 3.2497317790985107,
1440
+ "learning_rate": 1.0027716349697774e-05,
1441
+ "loss": 0.055,
1442
+ "step": 101500
1443
+ },
1444
+ {
1445
+ "epoch": 1.5037593984962405,
1446
+ "grad_norm": 0.16377945244312286,
1447
+ "learning_rate": 9.978573885694629e-06,
1448
+ "loss": 0.0602,
1449
+ "step": 102000
1450
+ },
1451
+ {
1452
+ "epoch": 1.5111307680967123,
1453
+ "grad_norm": 0.29184427857398987,
1454
+ "learning_rate": 9.929431421691485e-06,
1455
+ "loss": 0.0596,
1456
+ "step": 102500
1457
+ },
1458
+ {
1459
+ "epoch": 1.5185021376971841,
1460
+ "grad_norm": 0.14543047547340393,
1461
+ "learning_rate": 9.88028895768834e-06,
1462
+ "loss": 0.0593,
1463
+ "step": 103000
1464
+ },
1465
+ {
1466
+ "epoch": 1.525873507297656,
1467
+ "grad_norm": 4.776684284210205,
1468
+ "learning_rate": 9.831146493685194e-06,
1469
+ "loss": 0.0604,
1470
+ "step": 103500
1471
+ },
1472
+ {
1473
+ "epoch": 1.5332448768981277,
1474
+ "grad_norm": 3.4175798892974854,
1475
+ "learning_rate": 9.782102314610056e-06,
1476
+ "loss": 0.0622,
1477
+ "step": 104000
1478
+ },
1479
+ {
1480
+ "epoch": 1.5406162464985993,
1481
+ "grad_norm": 5.478698253631592,
1482
+ "learning_rate": 9.73295985060691e-06,
1483
+ "loss": 0.0582,
1484
+ "step": 104500
1485
+ },
1486
+ {
1487
+ "epoch": 1.5479876160990713,
1488
+ "grad_norm": 0.09877605736255646,
1489
+ "learning_rate": 9.683817386603766e-06,
1490
+ "loss": 0.0644,
1491
+ "step": 105000
1492
+ },
1493
+ {
1494
+ "epoch": 1.555358985699543,
1495
+ "grad_norm": 3.169551134109497,
1496
+ "learning_rate": 9.634674922600619e-06,
1497
+ "loss": 0.0672,
1498
+ "step": 105500
1499
+ },
1500
+ {
1501
+ "epoch": 1.5627303553000147,
1502
+ "grad_norm": 0.0030992806423455477,
1503
+ "learning_rate": 9.585532458597476e-06,
1504
+ "loss": 0.0654,
1505
+ "step": 106000
1506
+ },
1507
+ {
1508
+ "epoch": 1.5701017249004865,
1509
+ "grad_norm": 1.8882814645767212,
1510
+ "learning_rate": 9.536488279522336e-06,
1511
+ "loss": 0.0643,
1512
+ "step": 106500
1513
+ },
1514
+ {
1515
+ "epoch": 1.5774730945009583,
1516
+ "grad_norm": 0.02398967184126377,
1517
+ "learning_rate": 9.487345815519191e-06,
1518
+ "loss": 0.0677,
1519
+ "step": 107000
1520
+ },
1521
+ {
1522
+ "epoch": 1.58484446410143,
1523
+ "grad_norm": 0.010672827251255512,
1524
+ "learning_rate": 9.438203351516046e-06,
1525
+ "loss": 0.0637,
1526
+ "step": 107500
1527
+ },
1528
+ {
1529
+ "epoch": 1.5922158337019017,
1530
+ "grad_norm": 0.018269941210746765,
1531
+ "learning_rate": 9.389159172440906e-06,
1532
+ "loss": 0.0624,
1533
+ "step": 108000
1534
+ },
1535
+ {
1536
+ "epoch": 1.5995872033023737,
1537
+ "grad_norm": 1.7238303422927856,
1538
+ "learning_rate": 9.340016708437761e-06,
1539
+ "loss": 0.0595,
1540
+ "step": 108500
1541
+ },
1542
+ {
1543
+ "epoch": 1.6069585729028453,
1544
+ "grad_norm": 1.6856399774551392,
1545
+ "learning_rate": 9.290874244434616e-06,
1546
+ "loss": 0.0572,
1547
+ "step": 109000
1548
+ },
1549
+ {
1550
+ "epoch": 1.614329942503317,
1551
+ "grad_norm": 0.08445548266172409,
1552
+ "learning_rate": 9.241731780431471e-06,
1553
+ "loss": 0.0617,
1554
+ "step": 109500
1555
+ },
1556
+ {
1557
+ "epoch": 1.6217013121037889,
1558
+ "grad_norm": 2.7674472332000732,
1559
+ "learning_rate": 9.192589316428326e-06,
1560
+ "loss": 0.061,
1561
+ "step": 110000
1562
+ },
1563
+ {
1564
+ "epoch": 1.6290726817042607,
1565
+ "grad_norm": 6.365856647491455,
1566
+ "learning_rate": 9.143446852425181e-06,
1567
+ "loss": 0.0548,
1568
+ "step": 110500
1569
+ },
1570
+ {
1571
+ "epoch": 1.6364440513047325,
1572
+ "grad_norm": 1.224268913269043,
1573
+ "learning_rate": 9.094304388422036e-06,
1574
+ "loss": 0.0621,
1575
+ "step": 111000
1576
+ },
1577
+ {
1578
+ "epoch": 1.643815420905204,
1579
+ "grad_norm": 0.021649343892931938,
1580
+ "learning_rate": 9.045161924418891e-06,
1581
+ "loss": 0.0659,
1582
+ "step": 111500
1583
+ },
1584
+ {
1585
+ "epoch": 1.651186790505676,
1586
+ "grad_norm": 0.012330977246165276,
1587
+ "learning_rate": 8.996117745343752e-06,
1588
+ "loss": 0.0602,
1589
+ "step": 112000
1590
+ },
1591
+ {
1592
+ "epoch": 1.6585581601061476,
1593
+ "grad_norm": 0.6574206948280334,
1594
+ "learning_rate": 8.946975281340607e-06,
1595
+ "loss": 0.0617,
1596
+ "step": 112500
1597
+ },
1598
+ {
1599
+ "epoch": 1.6659295297066194,
1600
+ "grad_norm": 0.018540961667895317,
1601
+ "learning_rate": 8.897832817337462e-06,
1602
+ "loss": 0.0602,
1603
+ "step": 113000
1604
+ },
1605
+ {
1606
+ "epoch": 1.6733008993070912,
1607
+ "grad_norm": 5.6425557136535645,
1608
+ "learning_rate": 8.848690353334317e-06,
1609
+ "loss": 0.0597,
1610
+ "step": 113500
1611
+ },
1612
+ {
1613
+ "epoch": 1.680672268907563,
1614
+ "grad_norm": 2.435633420944214,
1615
+ "learning_rate": 8.799646174259177e-06,
1616
+ "loss": 0.0624,
1617
+ "step": 114000
1618
+ },
1619
+ {
1620
+ "epoch": 1.6880436385080348,
1621
+ "grad_norm": 1.5483721494674683,
1622
+ "learning_rate": 8.750503710256032e-06,
1623
+ "loss": 0.0614,
1624
+ "step": 114500
1625
+ },
1626
+ {
1627
+ "epoch": 1.6954150081085064,
1628
+ "grad_norm": 0.06437569856643677,
1629
+ "learning_rate": 8.701361246252887e-06,
1630
+ "loss": 0.0594,
1631
+ "step": 115000
1632
+ },
1633
+ {
1634
+ "epoch": 1.7027863777089784,
1635
+ "grad_norm": 0.29250073432922363,
1636
+ "learning_rate": 8.652218782249742e-06,
1637
+ "loss": 0.0559,
1638
+ "step": 115500
1639
+ },
1640
+ {
1641
+ "epoch": 1.71015774730945,
1642
+ "grad_norm": 0.5888819098472595,
1643
+ "learning_rate": 8.603076318246597e-06,
1644
+ "loss": 0.0659,
1645
+ "step": 116000
1646
+ },
1647
+ {
1648
+ "epoch": 1.7175291169099218,
1649
+ "grad_norm": 0.2926543354988098,
1650
+ "learning_rate": 8.55403213917146e-06,
1651
+ "loss": 0.063,
1652
+ "step": 116500
1653
+ },
1654
+ {
1655
+ "epoch": 1.7249004865103936,
1656
+ "grad_norm": 2.316805601119995,
1657
+ "learning_rate": 8.50498796009632e-06,
1658
+ "loss": 0.0544,
1659
+ "step": 117000
1660
+ },
1661
+ {
1662
+ "epoch": 1.7322718561108654,
1663
+ "grad_norm": 0.018379326909780502,
1664
+ "learning_rate": 8.455845496093175e-06,
1665
+ "loss": 0.0663,
1666
+ "step": 117500
1667
+ },
1668
+ {
1669
+ "epoch": 1.7396432257113372,
1670
+ "grad_norm": 0.014781077392399311,
1671
+ "learning_rate": 8.40670303209003e-06,
1672
+ "loss": 0.0573,
1673
+ "step": 118000
1674
+ },
1675
+ {
1676
+ "epoch": 1.7470145953118088,
1677
+ "grad_norm": 2.3919591903686523,
1678
+ "learning_rate": 8.357560568086885e-06,
1679
+ "loss": 0.0592,
1680
+ "step": 118500
1681
+ },
1682
+ {
1683
+ "epoch": 1.7543859649122808,
1684
+ "grad_norm": 2.7669119834899902,
1685
+ "learning_rate": 8.30841810408374e-06,
1686
+ "loss": 0.0644,
1687
+ "step": 119000
1688
+ },
1689
+ {
1690
+ "epoch": 1.7617573345127524,
1691
+ "grad_norm": 3.5739755630493164,
1692
+ "learning_rate": 8.259275640080595e-06,
1693
+ "loss": 0.0572,
1694
+ "step": 119500
1695
+ },
1696
+ {
1697
+ "epoch": 1.7691287041132242,
1698
+ "grad_norm": 0.4299847483634949,
1699
+ "learning_rate": 8.21013317607745e-06,
1700
+ "loss": 0.0664,
1701
+ "step": 120000
1702
+ },
1703
+ {
1704
+ "epoch": 1.776500073713696,
1705
+ "grad_norm": 0.9990677833557129,
1706
+ "learning_rate": 8.16108899700231e-06,
1707
+ "loss": 0.0638,
1708
+ "step": 120500
1709
+ },
1710
+ {
1711
+ "epoch": 1.7838714433141678,
1712
+ "grad_norm": 2.1424782276153564,
1713
+ "learning_rate": 8.111946532999165e-06,
1714
+ "loss": 0.0572,
1715
+ "step": 121000
1716
+ },
1717
+ {
1718
+ "epoch": 1.7912428129146396,
1719
+ "grad_norm": 4.301726341247559,
1720
+ "learning_rate": 8.06280406899602e-06,
1721
+ "loss": 0.0596,
1722
+ "step": 121500
1723
+ },
1724
+ {
1725
+ "epoch": 1.7986141825151112,
1726
+ "grad_norm": 8.399239540100098,
1727
+ "learning_rate": 8.013661604992875e-06,
1728
+ "loss": 0.0667,
1729
+ "step": 122000
1730
+ },
1731
+ {
1732
+ "epoch": 1.8059855521155832,
1733
+ "grad_norm": 0.00977667048573494,
1734
+ "learning_rate": 7.96451914098973e-06,
1735
+ "loss": 0.0596,
1736
+ "step": 122500
1737
+ },
1738
+ {
1739
+ "epoch": 1.8133569217160548,
1740
+ "grad_norm": 0.019315605983138084,
1741
+ "learning_rate": 7.915376676986585e-06,
1742
+ "loss": 0.0607,
1743
+ "step": 123000
1744
+ },
1745
+ {
1746
+ "epoch": 1.8207282913165266,
1747
+ "grad_norm": 0.011183898895978928,
1748
+ "learning_rate": 7.866332497911446e-06,
1749
+ "loss": 0.0656,
1750
+ "step": 123500
1751
+ },
1752
+ {
1753
+ "epoch": 1.8280996609169984,
1754
+ "grad_norm": 0.1689341515302658,
1755
+ "learning_rate": 7.8171900339083e-06,
1756
+ "loss": 0.0571,
1757
+ "step": 124000
1758
+ },
1759
+ {
1760
+ "epoch": 1.8354710305174702,
1761
+ "grad_norm": 7.370288848876953,
1762
+ "learning_rate": 7.768047569905156e-06,
1763
+ "loss": 0.0627,
1764
+ "step": 124500
1765
+ },
1766
+ {
1767
+ "epoch": 1.842842400117942,
1768
+ "grad_norm": 0.058736398816108704,
1769
+ "learning_rate": 7.719003390830016e-06,
1770
+ "loss": 0.0511,
1771
+ "step": 125000
1772
+ },
1773
+ {
1774
+ "epoch": 1.8502137697184136,
1775
+ "grad_norm": 0.014665275812149048,
1776
+ "learning_rate": 7.669860926826873e-06,
1777
+ "loss": 0.0624,
1778
+ "step": 125500
1779
+ },
1780
+ {
1781
+ "epoch": 1.8575851393188856,
1782
+ "grad_norm": 0.572428286075592,
1783
+ "learning_rate": 7.620718462823726e-06,
1784
+ "loss": 0.0607,
1785
+ "step": 126000
1786
+ },
1787
+ {
1788
+ "epoch": 1.8649565089193572,
1789
+ "grad_norm": 0.4777454733848572,
1790
+ "learning_rate": 7.571575998820582e-06,
1791
+ "loss": 0.0606,
1792
+ "step": 126500
1793
+ },
1794
+ {
1795
+ "epoch": 1.872327878519829,
1796
+ "grad_norm": 0.020159974694252014,
1797
+ "learning_rate": 7.522433534817436e-06,
1798
+ "loss": 0.0539,
1799
+ "step": 127000
1800
+ },
1801
+ {
1802
+ "epoch": 1.8796992481203008,
1803
+ "grad_norm": 0.010219153016805649,
1804
+ "learning_rate": 7.473291070814291e-06,
1805
+ "loss": 0.0593,
1806
+ "step": 127500
1807
+ },
1808
+ {
1809
+ "epoch": 1.8870706177207726,
1810
+ "grad_norm": 1.854982614517212,
1811
+ "learning_rate": 7.424148606811146e-06,
1812
+ "loss": 0.0636,
1813
+ "step": 128000
1814
+ },
1815
+ {
1816
+ "epoch": 1.8944419873212444,
1817
+ "grad_norm": 0.6811599135398865,
1818
+ "learning_rate": 7.375006142808001e-06,
1819
+ "loss": 0.0598,
1820
+ "step": 128500
1821
+ },
1822
+ {
1823
+ "epoch": 1.901813356921716,
1824
+ "grad_norm": 0.2864709496498108,
1825
+ "learning_rate": 7.325863678804855e-06,
1826
+ "loss": 0.0604,
1827
+ "step": 129000
1828
+ },
1829
+ {
1830
+ "epoch": 1.909184726522188,
1831
+ "grad_norm": 0.030090967193245888,
1832
+ "learning_rate": 7.276721214801711e-06,
1833
+ "loss": 0.0602,
1834
+ "step": 129500
1835
+ },
1836
+ {
1837
+ "epoch": 1.9165560961226595,
1838
+ "grad_norm": 4.568465232849121,
1839
+ "learning_rate": 7.227578750798565e-06,
1840
+ "loss": 0.0571,
1841
+ "step": 130000
1842
+ },
1843
+ {
1844
+ "epoch": 1.9239274657231313,
1845
+ "grad_norm": 2.8999075889587402,
1846
+ "learning_rate": 7.17843628679542e-06,
1847
+ "loss": 0.0556,
1848
+ "step": 130500
1849
+ },
1850
+ {
1851
+ "epoch": 1.9312988353236031,
1852
+ "grad_norm": 2.021425485610962,
1853
+ "learning_rate": 7.129392107720282e-06,
1854
+ "loss": 0.0593,
1855
+ "step": 131000
1856
+ },
1857
+ {
1858
+ "epoch": 1.938670204924075,
1859
+ "grad_norm": 5.252723217010498,
1860
+ "learning_rate": 7.080249643717136e-06,
1861
+ "loss": 0.054,
1862
+ "step": 131500
1863
+ },
1864
+ {
1865
+ "epoch": 1.9460415745245467,
1866
+ "grad_norm": 8.669822692871094,
1867
+ "learning_rate": 7.031107179713991e-06,
1868
+ "loss": 0.0622,
1869
+ "step": 132000
1870
+ },
1871
+ {
1872
+ "epoch": 1.9534129441250183,
1873
+ "grad_norm": 2.219619035720825,
1874
+ "learning_rate": 6.981964715710846e-06,
1875
+ "loss": 0.0656,
1876
+ "step": 132500
1877
+ },
1878
+ {
1879
+ "epoch": 1.9607843137254903,
1880
+ "grad_norm": 0.023053865879774094,
1881
+ "learning_rate": 6.932822251707701e-06,
1882
+ "loss": 0.0628,
1883
+ "step": 133000
1884
+ },
1885
+ {
1886
+ "epoch": 1.968155683325962,
1887
+ "grad_norm": 0.3438442647457123,
1888
+ "learning_rate": 6.8836797877045555e-06,
1889
+ "loss": 0.0593,
1890
+ "step": 133500
1891
+ },
1892
+ {
1893
+ "epoch": 1.9755270529264337,
1894
+ "grad_norm": 0.0067783379927277565,
1895
+ "learning_rate": 6.834537323701411e-06,
1896
+ "loss": 0.0639,
1897
+ "step": 134000
1898
+ },
1899
+ {
1900
+ "epoch": 1.9828984225269055,
1901
+ "grad_norm": 1.7491209506988525,
1902
+ "learning_rate": 6.7853948596982655e-06,
1903
+ "loss": 0.0518,
1904
+ "step": 134500
1905
+ },
1906
+ {
1907
+ "epoch": 1.9902697921273773,
1908
+ "grad_norm": 0.0214830469340086,
1909
+ "learning_rate": 6.736448965551133e-06,
1910
+ "loss": 0.0499,
1911
+ "step": 135000
1912
+ },
1913
+ {
1914
+ "epoch": 1.9976411617278491,
1915
+ "grad_norm": 2.5241074562072754,
1916
+ "learning_rate": 6.687306501547988e-06,
1917
+ "loss": 0.0649,
1918
+ "step": 135500
1919
+ },
1920
+ {
1921
+ "epoch": 2.0,
1922
+ "eval_accuracy": 0.6497911445279866,
1923
+ "eval_f1": 0.6859684311502573,
1924
+ "eval_loss": 0.08295563608407974,
1925
+ "eval_roc_auc": 0.8222563704452553,
1926
+ "eval_runtime": 89.7963,
1927
+ "eval_samples_per_second": 66.651,
1928
+ "eval_steps_per_second": 66.651,
1929
+ "step": 135660
1930
+ },
1931
+ {
1932
+ "epoch": 2.0050125313283207,
1933
+ "grad_norm": 3.550609588623047,
1934
+ "learning_rate": 6.638164037544843e-06,
1935
+ "loss": 0.0348,
1936
+ "step": 136000
1937
+ },
1938
+ {
1939
+ "epoch": 2.0123839009287927,
1940
+ "grad_norm": 0.014567219652235508,
1941
+ "learning_rate": 6.589021573541698e-06,
1942
+ "loss": 0.034,
1943
+ "step": 136500
1944
+ },
1945
+ {
1946
+ "epoch": 2.0197552705292643,
1947
+ "grad_norm": 4.3217291831970215,
1948
+ "learning_rate": 6.539977394466559e-06,
1949
+ "loss": 0.0346,
1950
+ "step": 137000
1951
+ },
1952
+ {
1953
+ "epoch": 2.0271266401297363,
1954
+ "grad_norm": 0.12837082147598267,
1955
+ "learning_rate": 6.490834930463414e-06,
1956
+ "loss": 0.0402,
1957
+ "step": 137500
1958
+ },
1959
+ {
1960
+ "epoch": 2.034498009730208,
1961
+ "grad_norm": 0.08076170086860657,
1962
+ "learning_rate": 6.4416924664602685e-06,
1963
+ "loss": 0.0269,
1964
+ "step": 138000
1965
+ },
1966
+ {
1967
+ "epoch": 2.0418693793306795,
1968
+ "grad_norm": 0.004311998374760151,
1969
+ "learning_rate": 6.392550002457124e-06,
1970
+ "loss": 0.0273,
1971
+ "step": 138500
1972
+ },
1973
+ {
1974
+ "epoch": 2.0492407489311515,
1975
+ "grad_norm": 0.0007999803638085723,
1976
+ "learning_rate": 6.3434075384539785e-06,
1977
+ "loss": 0.0263,
1978
+ "step": 139000
1979
+ },
1980
+ {
1981
+ "epoch": 2.056612118531623,
1982
+ "grad_norm": 0.004331584554165602,
1983
+ "learning_rate": 6.294461644306846e-06,
1984
+ "loss": 0.0301,
1985
+ "step": 139500
1986
+ },
1987
+ {
1988
+ "epoch": 2.063983488132095,
1989
+ "grad_norm": 0.013063879683613777,
1990
+ "learning_rate": 6.245417465231706e-06,
1991
+ "loss": 0.03,
1992
+ "step": 140000
1993
+ },
1994
+ {
1995
+ "epoch": 2.0713548577325667,
1996
+ "grad_norm": 0.01823696680366993,
1997
+ "learning_rate": 6.196275001228562e-06,
1998
+ "loss": 0.0343,
1999
+ "step": 140500
2000
+ },
2001
+ {
2002
+ "epoch": 2.0787262273330387,
2003
+ "grad_norm": 7.280787944793701,
2004
+ "learning_rate": 6.147132537225416e-06,
2005
+ "loss": 0.0261,
2006
+ "step": 141000
2007
+ },
2008
+ {
2009
+ "epoch": 2.0860975969335103,
2010
+ "grad_norm": 0.0030333856120705605,
2011
+ "learning_rate": 6.097990073222272e-06,
2012
+ "loss": 0.0298,
2013
+ "step": 141500
2014
+ },
2015
+ {
2016
+ "epoch": 2.093468966533982,
2017
+ "grad_norm": Infinity,
2018
+ "learning_rate": 6.0489458941471335e-06,
2019
+ "loss": 0.0241,
2020
+ "step": 142000
2021
+ },
2022
+ {
2023
+ "epoch": 2.100840336134454,
2024
+ "grad_norm": 46.87717056274414,
2025
+ "learning_rate": 5.999803430143988e-06,
2026
+ "loss": 0.0352,
2027
+ "step": 142500
2028
+ },
2029
+ {
2030
+ "epoch": 2.1082117057349254,
2031
+ "grad_norm": 0.008375998586416245,
2032
+ "learning_rate": 5.9506609661408435e-06,
2033
+ "loss": 0.0283,
2034
+ "step": 143000
2035
+ },
2036
+ {
2037
+ "epoch": 2.1155830753353975,
2038
+ "grad_norm": 0.0009784572757780552,
2039
+ "learning_rate": 5.901518502137698e-06,
2040
+ "loss": 0.0271,
2041
+ "step": 143500
2042
+ },
2043
+ {
2044
+ "epoch": 2.122954444935869,
2045
+ "grad_norm": 0.0016769421054050326,
2046
+ "learning_rate": 5.852376038134553e-06,
2047
+ "loss": 0.0233,
2048
+ "step": 144000
2049
+ },
2050
+ {
2051
+ "epoch": 2.1303258145363406,
2052
+ "grad_norm": 0.006961928680539131,
2053
+ "learning_rate": 5.803233574131407e-06,
2054
+ "loss": 0.0294,
2055
+ "step": 144500
2056
+ },
2057
+ {
2058
+ "epoch": 2.1376971841368126,
2059
+ "grad_norm": 0.005140836350619793,
2060
+ "learning_rate": 5.754091110128263e-06,
2061
+ "loss": 0.039,
2062
+ "step": 145000
2063
+ },
2064
+ {
2065
+ "epoch": 2.1450685537372842,
2066
+ "grad_norm": 0.001053107320331037,
2067
+ "learning_rate": 5.704948646125117e-06,
2068
+ "loss": 0.0309,
2069
+ "step": 145500
2070
+ },
2071
+ {
2072
+ "epoch": 2.1524399233377562,
2073
+ "grad_norm": 0.0007632673368789256,
2074
+ "learning_rate": 5.655806182121973e-06,
2075
+ "loss": 0.0363,
2076
+ "step": 146000
2077
+ },
2078
+ {
2079
+ "epoch": 2.159811292938228,
2080
+ "grad_norm": 0.4370366036891937,
2081
+ "learning_rate": 5.606762003046833e-06,
2082
+ "loss": 0.0317,
2083
+ "step": 146500
2084
+ },
2085
+ {
2086
+ "epoch": 2.1671826625387,
2087
+ "grad_norm": 0.00013254112855065614,
2088
+ "learning_rate": 5.557619539043688e-06,
2089
+ "loss": 0.0284,
2090
+ "step": 147000
2091
+ },
2092
+ {
2093
+ "epoch": 2.1745540321391714,
2094
+ "grad_norm": 6.598239421844482,
2095
+ "learning_rate": 5.508477075040542e-06,
2096
+ "loss": 0.0269,
2097
+ "step": 147500
2098
+ },
2099
+ {
2100
+ "epoch": 2.181925401739643,
2101
+ "grad_norm": 0.021487107500433922,
2102
+ "learning_rate": 5.459334611037398e-06,
2103
+ "loss": 0.0382,
2104
+ "step": 148000
2105
+ },
2106
+ {
2107
+ "epoch": 2.189296771340115,
2108
+ "grad_norm": 11.90185546875,
2109
+ "learning_rate": 5.410192147034252e-06,
2110
+ "loss": 0.0372,
2111
+ "step": 148500
2112
+ },
2113
+ {
2114
+ "epoch": 2.1966681409405866,
2115
+ "grad_norm": 0.0010807571234181523,
2116
+ "learning_rate": 5.361049683031107e-06,
2117
+ "loss": 0.0294,
2118
+ "step": 149000
2119
+ },
2120
+ {
2121
+ "epoch": 2.2040395105410586,
2122
+ "grad_norm": 0.024999860674142838,
2123
+ "learning_rate": 5.311907219027963e-06,
2124
+ "loss": 0.031,
2125
+ "step": 149500
2126
+ },
2127
+ {
2128
+ "epoch": 2.21141088014153,
2129
+ "grad_norm": 0.011472758837044239,
2130
+ "learning_rate": 5.2628630399528235e-06,
2131
+ "loss": 0.0253,
2132
+ "step": 150000
2133
+ },
2134
+ {
2135
+ "epoch": 2.218782249742002,
2136
+ "grad_norm": 0.0003523350169416517,
2137
+ "learning_rate": 5.213720575949679e-06,
2138
+ "loss": 0.0312,
2139
+ "step": 150500
2140
+ },
2141
+ {
2142
+ "epoch": 2.226153619342474,
2143
+ "grad_norm": 0.00018138001905754209,
2144
+ "learning_rate": 5.1645781119465335e-06,
2145
+ "loss": 0.0306,
2146
+ "step": 151000
2147
+ },
2148
+ {
2149
+ "epoch": 2.2335249889429454,
2150
+ "grad_norm": 27.588563919067383,
2151
+ "learning_rate": 5.1154356479433885e-06,
2152
+ "loss": 0.0257,
2153
+ "step": 151500
2154
+ },
2155
+ {
2156
+ "epoch": 2.2408963585434174,
2157
+ "grad_norm": 0.0001788044028216973,
2158
+ "learning_rate": 5.066293183940243e-06,
2159
+ "loss": 0.0364,
2160
+ "step": 152000
2161
+ },
2162
+ {
2163
+ "epoch": 2.248267728143889,
2164
+ "grad_norm": 0.025098439306020737,
2165
+ "learning_rate": 5.017347289793111e-06,
2166
+ "loss": 0.033,
2167
+ "step": 152500
2168
+ },
2169
+ {
2170
+ "epoch": 2.255639097744361,
2171
+ "grad_norm": 0.028794238343834877,
2172
+ "learning_rate": 4.968204825789966e-06,
2173
+ "loss": 0.0268,
2174
+ "step": 153000
2175
+ },
2176
+ {
2177
+ "epoch": 2.2630104673448326,
2178
+ "grad_norm": 0.0443144217133522,
2179
+ "learning_rate": 4.91906236178682e-06,
2180
+ "loss": 0.0277,
2181
+ "step": 153500
2182
+ },
2183
+ {
2184
+ "epoch": 2.2703818369453046,
2185
+ "grad_norm": 5.745356559753418,
2186
+ "learning_rate": 4.869919897783675e-06,
2187
+ "loss": 0.0319,
2188
+ "step": 154000
2189
+ },
2190
+ {
2191
+ "epoch": 2.277753206545776,
2192
+ "grad_norm": 0.01881660334765911,
2193
+ "learning_rate": 4.82077743378053e-06,
2194
+ "loss": 0.0321,
2195
+ "step": 154500
2196
+ },
2197
+ {
2198
+ "epoch": 2.2851245761462478,
2199
+ "grad_norm": 0.0014673862606287003,
2200
+ "learning_rate": 4.771634969777385e-06,
2201
+ "loss": 0.0325,
2202
+ "step": 155000
2203
+ },
2204
+ {
2205
+ "epoch": 2.2924959457467198,
2206
+ "grad_norm": 0.001017951057292521,
2207
+ "learning_rate": 4.72249250577424e-06,
2208
+ "loss": 0.0369,
2209
+ "step": 155500
2210
+ },
2211
+ {
2212
+ "epoch": 2.2998673153471914,
2213
+ "grad_norm": 0.0014965501613914967,
2214
+ "learning_rate": 4.673350041771095e-06,
2215
+ "loss": 0.0349,
2216
+ "step": 156000
2217
+ },
2218
+ {
2219
+ "epoch": 2.3072386849476634,
2220
+ "grad_norm": 0.0005304542719386518,
2221
+ "learning_rate": 4.6243058626959555e-06,
2222
+ "loss": 0.0303,
2223
+ "step": 156500
2224
+ },
2225
+ {
2226
+ "epoch": 2.314610054548135,
2227
+ "grad_norm": 0.0002412071480648592,
2228
+ "learning_rate": 4.575261683620817e-06,
2229
+ "loss": 0.0331,
2230
+ "step": 157000
2231
+ },
2232
+ {
2233
+ "epoch": 2.321981424148607,
2234
+ "grad_norm": 0.0006970348185859621,
2235
+ "learning_rate": 4.526119219617672e-06,
2236
+ "loss": 0.0343,
2237
+ "step": 157500
2238
+ },
2239
+ {
2240
+ "epoch": 2.3293527937490786,
2241
+ "grad_norm": 0.011668604798614979,
2242
+ "learning_rate": 4.476976755614527e-06,
2243
+ "loss": 0.0279,
2244
+ "step": 158000
2245
+ },
2246
+ {
2247
+ "epoch": 2.33672416334955,
2248
+ "grad_norm": 0.005698871333152056,
2249
+ "learning_rate": 4.427834291611382e-06,
2250
+ "loss": 0.0322,
2251
+ "step": 158500
2252
+ },
2253
+ {
2254
+ "epoch": 2.344095532950022,
2255
+ "grad_norm": 0.0057191732339560986,
2256
+ "learning_rate": 4.378691827608237e-06,
2257
+ "loss": 0.0314,
2258
+ "step": 159000
2259
+ },
2260
+ {
2261
+ "epoch": 2.3514669025504937,
2262
+ "grad_norm": 0.00243947422131896,
2263
+ "learning_rate": 4.329549363605092e-06,
2264
+ "loss": 0.0267,
2265
+ "step": 159500
2266
+ },
2267
+ {
2268
+ "epoch": 2.3588382721509658,
2269
+ "grad_norm": 0.00033369645825587213,
2270
+ "learning_rate": 4.280406899601947e-06,
2271
+ "loss": 0.0244,
2272
+ "step": 160000
2273
+ },
2274
+ {
2275
+ "epoch": 2.3662096417514373,
2276
+ "grad_norm": 0.023830311372876167,
2277
+ "learning_rate": 4.231264435598802e-06,
2278
+ "loss": 0.0283,
2279
+ "step": 160500
2280
+ },
2281
+ {
2282
+ "epoch": 2.3735810113519094,
2283
+ "grad_norm": 0.000461634888779372,
2284
+ "learning_rate": 4.182121971595656e-06,
2285
+ "loss": 0.0285,
2286
+ "step": 161000
2287
+ },
2288
+ {
2289
+ "epoch": 2.380952380952381,
2290
+ "grad_norm": 0.001816113363020122,
2291
+ "learning_rate": 4.132979507592511e-06,
2292
+ "loss": 0.03,
2293
+ "step": 161500
2294
+ },
2295
+ {
2296
+ "epoch": 2.3883237505528525,
2297
+ "grad_norm": 0.001825949759222567,
2298
+ "learning_rate": 4.083837043589366e-06,
2299
+ "loss": 0.0294,
2300
+ "step": 162000
2301
+ },
2302
+ {
2303
+ "epoch": 2.3956951201533245,
2304
+ "grad_norm": 9.502708435058594,
2305
+ "learning_rate": 4.034792864514227e-06,
2306
+ "loss": 0.0255,
2307
+ "step": 162500
2308
+ },
2309
+ {
2310
+ "epoch": 2.403066489753796,
2311
+ "grad_norm": 0.0001642414426896721,
2312
+ "learning_rate": 3.985650400511082e-06,
2313
+ "loss": 0.0255,
2314
+ "step": 163000
2315
+ },
2316
+ {
2317
+ "epoch": 2.410437859354268,
2318
+ "grad_norm": 5.004094123840332,
2319
+ "learning_rate": 3.936507936507936e-06,
2320
+ "loss": 0.0304,
2321
+ "step": 163500
2322
+ },
2323
+ {
2324
+ "epoch": 2.4178092289547397,
2325
+ "grad_norm": 0.1878451257944107,
2326
+ "learning_rate": 3.887365472504791e-06,
2327
+ "loss": 0.0236,
2328
+ "step": 164000
2329
+ },
2330
+ {
2331
+ "epoch": 2.4251805985552117,
2332
+ "grad_norm": 0.0004031589487567544,
2333
+ "learning_rate": 3.838223008501646e-06,
2334
+ "loss": 0.0316,
2335
+ "step": 164500
2336
+ },
2337
+ {
2338
+ "epoch": 2.4325519681556833,
2339
+ "grad_norm": 0.0004982321988791227,
2340
+ "learning_rate": 3.7890805444985013e-06,
2341
+ "loss": 0.0277,
2342
+ "step": 165000
2343
+ },
2344
+ {
2345
+ "epoch": 2.439923337756155,
2346
+ "grad_norm": 0.0037121805362403393,
2347
+ "learning_rate": 3.739938080495356e-06,
2348
+ "loss": 0.0303,
2349
+ "step": 165500
2350
+ },
2351
+ {
2352
+ "epoch": 2.447294707356627,
2353
+ "grad_norm": 0.0101530272513628,
2354
+ "learning_rate": 3.690795616492211e-06,
2355
+ "loss": 0.0371,
2356
+ "step": 166000
2357
+ },
2358
+ {
2359
+ "epoch": 2.4546660769570985,
2360
+ "grad_norm": 0.00018950540106743574,
2361
+ "learning_rate": 3.6416531524890663e-06,
2362
+ "loss": 0.0319,
2363
+ "step": 166500
2364
+ },
2365
+ {
2366
+ "epoch": 2.4620374465575705,
2367
+ "grad_norm": 0.8489145040512085,
2368
+ "learning_rate": 3.5925106884859213e-06,
2369
+ "loss": 0.0261,
2370
+ "step": 167000
2371
+ },
2372
+ {
2373
+ "epoch": 2.469408816158042,
2374
+ "grad_norm": 0.0013942194636911154,
2375
+ "learning_rate": 3.543368224482776e-06,
2376
+ "loss": 0.0283,
2377
+ "step": 167500
2378
+ },
2379
+ {
2380
+ "epoch": 2.476780185758514,
2381
+ "grad_norm": 0.4112614691257477,
2382
+ "learning_rate": 3.494225760479631e-06,
2383
+ "loss": 0.0332,
2384
+ "step": 168000
2385
+ },
2386
+ {
2387
+ "epoch": 2.4841515553589857,
2388
+ "grad_norm": 0.0010579220252111554,
2389
+ "learning_rate": 3.445181581404492e-06,
2390
+ "loss": 0.0288,
2391
+ "step": 168500
2392
+ },
2393
+ {
2394
+ "epoch": 2.4915229249594573,
2395
+ "grad_norm": 0.0012302091345191002,
2396
+ "learning_rate": 3.396137402329353e-06,
2397
+ "loss": 0.0272,
2398
+ "step": 169000
2399
+ },
2400
+ {
2401
+ "epoch": 2.4988942945599293,
2402
+ "grad_norm": 0.0008321187924593687,
2403
+ "learning_rate": 3.3470932232542143e-06,
2404
+ "loss": 0.0251,
2405
+ "step": 169500
2406
+ },
2407
+ {
2408
+ "epoch": 2.506265664160401,
2409
+ "grad_norm": 2.113279342651367,
2410
+ "learning_rate": 3.297950759251069e-06,
2411
+ "loss": 0.0306,
2412
+ "step": 170000
2413
+ },
2414
+ {
2415
+ "epoch": 2.513637033760873,
2416
+ "grad_norm": 0.030419809743762016,
2417
+ "learning_rate": 3.248808295247924e-06,
2418
+ "loss": 0.033,
2419
+ "step": 170500
2420
+ },
2421
+ {
2422
+ "epoch": 2.5210084033613445,
2423
+ "grad_norm": 0.002908308058977127,
2424
+ "learning_rate": 3.199665831244779e-06,
2425
+ "loss": 0.0333,
2426
+ "step": 171000
2427
+ },
2428
+ {
2429
+ "epoch": 2.5283797729618165,
2430
+ "grad_norm": 0.01623060740530491,
2431
+ "learning_rate": 3.1505233672416334e-06,
2432
+ "loss": 0.0347,
2433
+ "step": 171500
2434
+ },
2435
+ {
2436
+ "epoch": 2.535751142562288,
2437
+ "grad_norm": 0.0023743058554828167,
2438
+ "learning_rate": 3.1013809032384884e-06,
2439
+ "loss": 0.029,
2440
+ "step": 172000
2441
+ },
2442
+ {
2443
+ "epoch": 2.5431225121627596,
2444
+ "grad_norm": 0.0017329910770058632,
2445
+ "learning_rate": 3.0522384392353434e-06,
2446
+ "loss": 0.0399,
2447
+ "step": 172500
2448
+ },
2449
+ {
2450
+ "epoch": 2.5504938817632317,
2451
+ "grad_norm": 0.003035512287169695,
2452
+ "learning_rate": 3.003095975232199e-06,
2453
+ "loss": 0.0292,
2454
+ "step": 173000
2455
+ },
2456
+ {
2457
+ "epoch": 2.5578652513637032,
2458
+ "grad_norm": 0.016472771763801575,
2459
+ "learning_rate": 2.9539535112290534e-06,
2460
+ "loss": 0.0295,
2461
+ "step": 173500
2462
+ },
2463
+ {
2464
+ "epoch": 2.5652366209641753,
2465
+ "grad_norm": 0.19270442426204681,
2466
+ "learning_rate": 2.9048110472259084e-06,
2467
+ "loss": 0.0237,
2468
+ "step": 174000
2469
+ },
2470
+ {
2471
+ "epoch": 2.572607990564647,
2472
+ "grad_norm": 14.15371322631836,
2473
+ "learning_rate": 2.855668583222763e-06,
2474
+ "loss": 0.031,
2475
+ "step": 174500
2476
+ },
2477
+ {
2478
+ "epoch": 2.579979360165119,
2479
+ "grad_norm": 0.0006798787508159876,
2480
+ "learning_rate": 2.806526119219618e-06,
2481
+ "loss": 0.0348,
2482
+ "step": 175000
2483
+ },
2484
+ {
2485
+ "epoch": 2.5873507297655904,
2486
+ "grad_norm": 0.0007228073664009571,
2487
+ "learning_rate": 2.757383655216473e-06,
2488
+ "loss": 0.0266,
2489
+ "step": 175500
2490
+ },
2491
+ {
2492
+ "epoch": 2.594722099366062,
2493
+ "grad_norm": 0.003529267618432641,
2494
+ "learning_rate": 2.708339476141334e-06,
2495
+ "loss": 0.025,
2496
+ "step": 176000
2497
+ },
2498
+ {
2499
+ "epoch": 2.602093468966534,
2500
+ "grad_norm": 0.004369991831481457,
2501
+ "learning_rate": 2.659197012138189e-06,
2502
+ "loss": 0.0343,
2503
+ "step": 176500
2504
+ },
2505
+ {
2506
+ "epoch": 2.6094648385670056,
2507
+ "grad_norm": 0.0011527182068675756,
2508
+ "learning_rate": 2.610054548135044e-06,
2509
+ "loss": 0.0344,
2510
+ "step": 177000
2511
+ },
2512
+ {
2513
+ "epoch": 2.6168362081674776,
2514
+ "grad_norm": 0.0012939295265823603,
2515
+ "learning_rate": 2.5609120841318984e-06,
2516
+ "loss": 0.023,
2517
+ "step": 177500
2518
+ },
2519
+ {
2520
+ "epoch": 2.624207577767949,
2521
+ "grad_norm": 0.004880073014646769,
2522
+ "learning_rate": 2.5117696201287534e-06,
2523
+ "loss": 0.0226,
2524
+ "step": 178000
2525
+ },
2526
+ {
2527
+ "epoch": 2.6315789473684212,
2528
+ "grad_norm": 0.004119515884667635,
2529
+ "learning_rate": 2.4626271561256084e-06,
2530
+ "loss": 0.0217,
2531
+ "step": 178500
2532
+ },
2533
+ {
2534
+ "epoch": 2.638950316968893,
2535
+ "grad_norm": 0.0001360880269203335,
2536
+ "learning_rate": 2.4135829770504697e-06,
2537
+ "loss": 0.0318,
2538
+ "step": 179000
2539
+ },
2540
+ {
2541
+ "epoch": 2.6463216865693644,
2542
+ "grad_norm": 0.09521844983100891,
2543
+ "learning_rate": 2.3644405130473242e-06,
2544
+ "loss": 0.0382,
2545
+ "step": 179500
2546
+ },
2547
+ {
2548
+ "epoch": 2.6536930561698364,
2549
+ "grad_norm": 0.0037165977992117405,
2550
+ "learning_rate": 2.3152980490441792e-06,
2551
+ "loss": 0.0277,
2552
+ "step": 180000
2553
+ },
2554
+ {
2555
+ "epoch": 2.661064425770308,
2556
+ "grad_norm": 0.0008691260009072721,
2557
+ "learning_rate": 2.2661555850410342e-06,
2558
+ "loss": 0.0322,
2559
+ "step": 180500
2560
+ },
2561
+ {
2562
+ "epoch": 2.66843579537078,
2563
+ "grad_norm": 1.0185267925262451,
2564
+ "learning_rate": 2.217111405965895e-06,
2565
+ "loss": 0.0287,
2566
+ "step": 181000
2567
+ },
2568
+ {
2569
+ "epoch": 2.6758071649712516,
2570
+ "grad_norm": 11.761468887329102,
2571
+ "learning_rate": 2.1679689419627505e-06,
2572
+ "loss": 0.0269,
2573
+ "step": 181500
2574
+ },
2575
+ {
2576
+ "epoch": 2.6831785345717236,
2577
+ "grad_norm": 0.00046698356163688004,
2578
+ "learning_rate": 2.118826477959605e-06,
2579
+ "loss": 0.0324,
2580
+ "step": 182000
2581
+ },
2582
+ {
2583
+ "epoch": 2.690549904172195,
2584
+ "grad_norm": 0.010263352654874325,
2585
+ "learning_rate": 2.0698805838124726e-06,
2586
+ "loss": 0.0239,
2587
+ "step": 182500
2588
+ },
2589
+ {
2590
+ "epoch": 2.6979212737726668,
2591
+ "grad_norm": 3.434927463531494,
2592
+ "learning_rate": 2.020738119809327e-06,
2593
+ "loss": 0.0335,
2594
+ "step": 183000
2595
+ },
2596
+ {
2597
+ "epoch": 2.705292643373139,
2598
+ "grad_norm": 0.00016977268387563527,
2599
+ "learning_rate": 1.971595655806182e-06,
2600
+ "loss": 0.0275,
2601
+ "step": 183500
2602
+ },
2603
+ {
2604
+ "epoch": 2.7126640129736104,
2605
+ "grad_norm": 0.0012544383062049747,
2606
+ "learning_rate": 1.922453191803037e-06,
2607
+ "loss": 0.0312,
2608
+ "step": 184000
2609
+ },
2610
+ {
2611
+ "epoch": 2.7200353825740824,
2612
+ "grad_norm": 0.0017481895629316568,
2613
+ "learning_rate": 1.8733107277998921e-06,
2614
+ "loss": 0.0244,
2615
+ "step": 184500
2616
+ },
2617
+ {
2618
+ "epoch": 2.727406752174554,
2619
+ "grad_norm": 0.001362023875117302,
2620
+ "learning_rate": 1.824168263796747e-06,
2621
+ "loss": 0.0242,
2622
+ "step": 185000
2623
+ },
2624
+ {
2625
+ "epoch": 2.734778121775026,
2626
+ "grad_norm": 0.0014405859401449561,
2627
+ "learning_rate": 1.775025799793602e-06,
2628
+ "loss": 0.0304,
2629
+ "step": 185500
2630
+ },
2631
+ {
2632
+ "epoch": 2.7421494913754976,
2633
+ "grad_norm": 0.0008861696696840227,
2634
+ "learning_rate": 1.7258833357904567e-06,
2635
+ "loss": 0.0278,
2636
+ "step": 186000
2637
+ },
2638
+ {
2639
+ "epoch": 2.749520860975969,
2640
+ "grad_norm": 0.12847045063972473,
2641
+ "learning_rate": 1.6767408717873115e-06,
2642
+ "loss": 0.0244,
2643
+ "step": 186500
2644
+ },
2645
+ {
2646
+ "epoch": 2.756892230576441,
2647
+ "grad_norm": 0.001703253947198391,
2648
+ "learning_rate": 1.6275984077841663e-06,
2649
+ "loss": 0.0356,
2650
+ "step": 187000
2651
+ },
2652
+ {
2653
+ "epoch": 2.7642636001769127,
2654
+ "grad_norm": 0.003184770466759801,
2655
+ "learning_rate": 1.5784559437810213e-06,
2656
+ "loss": 0.0234,
2657
+ "step": 187500
2658
+ },
2659
+ {
2660
+ "epoch": 2.7716349697773848,
2661
+ "grad_norm": 5.178366661071777,
2662
+ "learning_rate": 1.529313479777876e-06,
2663
+ "loss": 0.0272,
2664
+ "step": 188000
2665
+ },
2666
+ {
2667
+ "epoch": 2.7790063393778563,
2668
+ "grad_norm": 0.0035832468420267105,
2669
+ "learning_rate": 1.4801710157747309e-06,
2670
+ "loss": 0.0227,
2671
+ "step": 188500
2672
+ },
2673
+ {
2674
+ "epoch": 2.7863777089783284,
2675
+ "grad_norm": 0.007811425253748894,
2676
+ "learning_rate": 1.4311268366995923e-06,
2677
+ "loss": 0.03,
2678
+ "step": 189000
2679
+ },
2680
+ {
2681
+ "epoch": 2.7937490785788,
2682
+ "grad_norm": 12.170905113220215,
2683
+ "learning_rate": 1.3819843726964471e-06,
2684
+ "loss": 0.028,
2685
+ "step": 189500
2686
+ },
2687
+ {
2688
+ "epoch": 2.8011204481792715,
2689
+ "grad_norm": 0.0028726314194500446,
2690
+ "learning_rate": 1.3329401936213082e-06,
2691
+ "loss": 0.0303,
2692
+ "step": 190000
2693
+ },
2694
+ {
2695
+ "epoch": 2.8084918177797435,
2696
+ "grad_norm": 30.53835678100586,
2697
+ "learning_rate": 1.283797729618163e-06,
2698
+ "loss": 0.0321,
2699
+ "step": 190500
2700
+ },
2701
+ {
2702
+ "epoch": 2.815863187380215,
2703
+ "grad_norm": 0.006513836327940226,
2704
+ "learning_rate": 1.234655265615018e-06,
2705
+ "loss": 0.0235,
2706
+ "step": 191000
2707
+ },
2708
+ {
2709
+ "epoch": 2.823234556980687,
2710
+ "grad_norm": 7.619091510772705,
2711
+ "learning_rate": 1.185512801611873e-06,
2712
+ "loss": 0.0307,
2713
+ "step": 191500
2714
+ },
2715
+ {
2716
+ "epoch": 2.8306059265811587,
2717
+ "grad_norm": 0.005691774655133486,
2718
+ "learning_rate": 1.1363703376087278e-06,
2719
+ "loss": 0.0257,
2720
+ "step": 192000
2721
+ },
2722
+ {
2723
+ "epoch": 2.8379772961816307,
2724
+ "grad_norm": 2.5761618614196777,
2725
+ "learning_rate": 1.0872278736055828e-06,
2726
+ "loss": 0.0226,
2727
+ "step": 192500
2728
+ },
2729
+ {
2730
+ "epoch": 2.8453486657821023,
2731
+ "grad_norm": 0.00010429321264382452,
2732
+ "learning_rate": 1.0380854096024375e-06,
2733
+ "loss": 0.0242,
2734
+ "step": 193000
2735
+ },
2736
+ {
2737
+ "epoch": 2.852720035382574,
2738
+ "grad_norm": 0.02838067337870598,
2739
+ "learning_rate": 9.889429455992925e-07,
2740
+ "loss": 0.0287,
2741
+ "step": 193500
2742
+ },
2743
+ {
2744
+ "epoch": 2.860091404983046,
2745
+ "grad_norm": 0.12736959755420685,
2746
+ "learning_rate": 9.398004815961473e-07,
2747
+ "loss": 0.0256,
2748
+ "step": 194000
2749
+ },
2750
+ {
2751
+ "epoch": 2.8674627745835175,
2752
+ "grad_norm": 0.32672008872032166,
2753
+ "learning_rate": 8.907563025210085e-07,
2754
+ "loss": 0.0265,
2755
+ "step": 194500
2756
+ },
2757
+ {
2758
+ "epoch": 2.8748341441839895,
2759
+ "grad_norm": 0.000785826297942549,
2760
+ "learning_rate": 8.416138385178634e-07,
2761
+ "loss": 0.0339,
2762
+ "step": 195000
2763
+ },
2764
+ {
2765
+ "epoch": 2.882205513784461,
2766
+ "grad_norm": 6.065654754638672,
2767
+ "learning_rate": 7.924713745147182e-07,
2768
+ "loss": 0.0337,
2769
+ "step": 195500
2770
+ },
2771
+ {
2772
+ "epoch": 2.889576883384933,
2773
+ "grad_norm": 0.012824644334614277,
2774
+ "learning_rate": 7.433289105115731e-07,
2775
+ "loss": 0.0278,
2776
+ "step": 196000
2777
+ },
2778
+ {
2779
+ "epoch": 2.8969482529854047,
2780
+ "grad_norm": 0.011444471776485443,
2781
+ "learning_rate": 6.941864465084281e-07,
2782
+ "loss": 0.0368,
2783
+ "step": 196500
2784
+ },
2785
+ {
2786
+ "epoch": 2.9043196225858763,
2787
+ "grad_norm": 0.0061572156846523285,
2788
+ "learning_rate": 6.450439825052828e-07,
2789
+ "loss": 0.0289,
2790
+ "step": 197000
2791
+ },
2792
+ {
2793
+ "epoch": 2.9116909921863483,
2794
+ "grad_norm": 0.010506005957722664,
2795
+ "learning_rate": 5.95999803430144e-07,
2796
+ "loss": 0.022,
2797
+ "step": 197500
2798
+ },
2799
+ {
2800
+ "epoch": 2.91906236178682,
2801
+ "grad_norm": 0.00013557464990299195,
2802
+ "learning_rate": 5.468573394269989e-07,
2803
+ "loss": 0.0313,
2804
+ "step": 198000
2805
+ },
2806
+ {
2807
+ "epoch": 2.926433731387292,
2808
+ "grad_norm": 0.0008798382477834821,
2809
+ "learning_rate": 4.977148754238538e-07,
2810
+ "loss": 0.0302,
2811
+ "step": 198500
2812
+ },
2813
+ {
2814
+ "epoch": 2.9338051009877635,
2815
+ "grad_norm": 0.11164344847202301,
2816
+ "learning_rate": 4.485724114207086e-07,
2817
+ "loss": 0.0234,
2818
+ "step": 199000
2819
+ },
2820
+ {
2821
+ "epoch": 2.9411764705882355,
2822
+ "grad_norm": 17.183870315551758,
2823
+ "learning_rate": 3.9942994741756357e-07,
2824
+ "loss": 0.0294,
2825
+ "step": 199500
2826
+ },
2827
+ {
2828
+ "epoch": 2.948547840188707,
2829
+ "grad_norm": 14.767284393310547,
2830
+ "learning_rate": 3.502874834144184e-07,
2831
+ "loss": 0.0277,
2832
+ "step": 200000
2833
+ },
2834
+ {
2835
+ "epoch": 2.9559192097891787,
2836
+ "grad_norm": 0.0102895712479949,
2837
+ "learning_rate": 3.012433043392796e-07,
2838
+ "loss": 0.0307,
2839
+ "step": 200500
2840
+ },
2841
+ {
2842
+ "epoch": 2.9632905793896507,
2843
+ "grad_norm": 0.0019515061285346746,
2844
+ "learning_rate": 2.5210084033613445e-07,
2845
+ "loss": 0.0345,
2846
+ "step": 201000
2847
+ },
2848
+ {
2849
+ "epoch": 2.9706619489901223,
2850
+ "grad_norm": 0.5170195698738098,
2851
+ "learning_rate": 2.0295837633298937e-07,
2852
+ "loss": 0.0282,
2853
+ "step": 201500
2854
+ },
2855
+ {
2856
+ "epoch": 2.9780333185905943,
2857
+ "grad_norm": 0.00022552709560841322,
2858
+ "learning_rate": 1.5381591232984424e-07,
2859
+ "loss": 0.0294,
2860
+ "step": 202000
2861
+ },
2862
+ {
2863
+ "epoch": 2.985404688191066,
2864
+ "grad_norm": 0.004490272141993046,
2865
+ "learning_rate": 1.0467344832669911e-07,
2866
+ "loss": 0.0223,
2867
+ "step": 202500
2868
+ },
2869
+ {
2870
+ "epoch": 2.992776057791538,
2871
+ "grad_norm": 0.0005161833250895143,
2872
+ "learning_rate": 5.562926925156028e-08,
2873
+ "loss": 0.0247,
2874
+ "step": 203000
2875
+ },
2876
+ {
2877
+ "epoch": 3.0,
2878
+ "eval_accuracy": 0.6753550543024227,
2879
+ "eval_f1": 0.6936652741069145,
2880
+ "eval_loss": 0.12206839770078659,
2881
+ "eval_roc_auc": 0.833023672143383,
2882
+ "eval_runtime": 94.2338,
2883
+ "eval_samples_per_second": 63.512,
2884
+ "eval_steps_per_second": 63.512,
2885
+ "step": 203490
2886
+ }
2887
+ ],
2888
+ "logging_steps": 500,
2889
+ "max_steps": 203490,
2890
+ "num_input_tokens_seen": 0,
2891
+ "num_train_epochs": 3,
2892
+ "save_steps": 500,
2893
+ "stateful_callbacks": {
2894
+ "TrainerControl": {
2895
+ "args": {
2896
+ "should_epoch_stop": false,
2897
+ "should_evaluate": false,
2898
+ "should_log": false,
2899
+ "should_save": true,
2900
+ "should_training_stop": true
2901
+ },
2902
+ "attributes": {}
2903
+ }
2904
+ },
2905
+ "total_flos": 2.1521488766625792e+17,
2906
+ "train_batch_size": 1,
2907
+ "trial_name": null,
2908
+ "trial_params": null
2909
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea4a34b480f7d9f1c31be2100c448d02699c42747056e12a368bdd22a9b4f3c
3
+ size 5368