CocoRoF commited on
Commit
ad1db1b
·
verified ·
1 Parent(s): 6f5bd3e

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CocoRoF/ModernBERT-SimCSE-multitask_v03-distill",
3
+ "architectures": [
4
+ "ModernBertForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "id2label": {
24
+ "0": "LABEL_0"
25
+ },
26
+ "initializer_cutoff_factor": 2.0,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 1152,
29
+ "label2id": {
30
+ "LABEL_0": 0
31
+ },
32
+ "layer_norm_eps": 1e-05,
33
+ "local_attention": 128,
34
+ "local_rope_theta": 10000.0,
35
+ "max_position_embeddings": 8192,
36
+ "mlp_bias": false,
37
+ "mlp_dropout": 0.0,
38
+ "model_type": "modernbert",
39
+ "norm_bias": false,
40
+ "norm_eps": 1e-05,
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 22,
43
+ "pad_token_id": 50283,
44
+ "position_embedding_type": "absolute",
45
+ "reference_compile": false,
46
+ "repad_logits_with_grad": false,
47
+ "sep_token_id": 50282,
48
+ "sparse_pred_ignore_index": -100,
49
+ "sparse_prediction": false,
50
+ "torch_dtype": "float32",
51
+ "transformers_version": "4.48.3",
52
+ "vocab_size": 95663
53
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d6a9d3ebca0d2aa5bd79a9a0e7bd207d897aae33349d2ce940036e318c1ec8
3
+ size 737582948
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f87ab46a6d2e79706f4fbe9fab91adf1477c99f4e0a7ec5f75fd40df615452fc
3
+ size 1475256250
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f99282350613e429cc69953b863d56105d536f5994263fde97538456bb3000
3
+ size 15920
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c8e1d946ba83bf3a34c9b9606f617f045822f020742ab633b0707282a5ac42
3
+ size 15920
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e84807914087fe0fd995a689f151c86b757423627822411444b9f188d50bd5
3
+ size 15920
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b88af1a24067f0248670d9c42407469e3fcc7704b65c56b620b655889b18ea
3
+ size 15920
last-checkpoint/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9cccb129f7a918379d00fbc001591b1903a6f2fd3f318d64b901f9201c19921
3
+ size 15920
last-checkpoint/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b802e10b209cb2de39b2c15a32755b7555ed71516138fb18c5e279efab9c7197
3
+ size 15920
last-checkpoint/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8b5aa49772e33f50b29b0fd061a33b2394fe60a163a40446db087c6b9a7604c
3
+ size 15920
last-checkpoint/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de347184da2fe5a573cc1da6289024d6851835f08845bb06d584d2d3b75d44d8
3
+ size 15920
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55a2d553ce27e21e090108a87a87774fc29dad5edfb555fad1255b51499af6ca
3
+ size 1000
last-checkpoint/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
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,952 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "95580": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "95581": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "95582": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "95583": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "95584": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "95585": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "95586": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "95587": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "95588": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "95589": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "95590": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "95591": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "95592": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "95593": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "95594": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "95595": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "95596": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "95597": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "95598": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "95599": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "95600": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "95601": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "95602": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "95603": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "95604": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "95605": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "95606": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "95607": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "95608": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "95609": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "95610": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "95611": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "95612": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "95613": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "95614": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "95615": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "95616": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "95617": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "95618": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "95619": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "95620": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "95621": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "95622": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "95623": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "95624": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "95625": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "95626": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "95627": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "95628": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "95629": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "95630": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "95631": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "95632": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "95633": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "95634": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "95635": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "95636": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "95637": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "95638": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "95639": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "95640": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "95641": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "95642": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "95643": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "95644": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "95645": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "95646": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "95647": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "95648": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "95649": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "95650": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "95651": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "95652": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "95653": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "95654": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "95655": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "95656": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "95657": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "95658": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "95659": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "95660": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "95661": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "95662": {
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
+ "max_length": 2048,
937
+ "model_input_names": [
938
+ "input_ids",
939
+ "attention_mask"
940
+ ],
941
+ "model_max_length": 2048,
942
+ "pad_to_multiple_of": null,
943
+ "pad_token": "[PAD]",
944
+ "pad_token_type_id": 0,
945
+ "padding_side": "right",
946
+ "sep_token": "[SEP]",
947
+ "stride": 0,
948
+ "tokenizer_class": "PreTrainedTokenizerFast",
949
+ "truncation_side": "right",
950
+ "truncation_strategy": "longest_first",
951
+ "unk_token": "[UNK]"
952
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,733 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5091568680488154,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005091568680488154,
13
+ "grad_norm": 0.7564847469329834,
14
+ "learning_rate": 4.9999857936989376e-05,
15
+ "loss": 0.6957,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.010183137360976308,
20
+ "grad_norm": 0.3457886576652527,
21
+ "learning_rate": 4.999971587397875e-05,
22
+ "loss": 0.6941,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.015274706041464463,
27
+ "grad_norm": 0.2739073932170868,
28
+ "learning_rate": 4.999957381096812e-05,
29
+ "loss": 0.6921,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.020366274721952616,
34
+ "grad_norm": 0.2826838195323944,
35
+ "learning_rate": 4.9999431747957495e-05,
36
+ "loss": 0.6932,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.02545784340244077,
41
+ "grad_norm": 0.1553473025560379,
42
+ "learning_rate": 4.999928968494687e-05,
43
+ "loss": 0.6933,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.030549412082928926,
48
+ "grad_norm": 0.17130891978740692,
49
+ "learning_rate": 4.9999147621936234e-05,
50
+ "loss": 0.6916,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.03564098076341708,
55
+ "grad_norm": 0.1938512623310089,
56
+ "learning_rate": 4.999900555892561e-05,
57
+ "loss": 0.6919,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.04073254944390523,
62
+ "grad_norm": 0.2490479201078415,
63
+ "learning_rate": 4.999886349591498e-05,
64
+ "loss": 0.6907,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.04582411812439339,
69
+ "grad_norm": 0.20010128617286682,
70
+ "learning_rate": 4.9998721432904354e-05,
71
+ "loss": 0.691,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.05091568680488154,
76
+ "grad_norm": 0.16262651979923248,
77
+ "learning_rate": 4.999857936989373e-05,
78
+ "loss": 0.6917,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.056007255485369695,
83
+ "grad_norm": 0.21441149711608887,
84
+ "learning_rate": 4.999843730688309e-05,
85
+ "loss": 0.6872,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.06109882416585785,
90
+ "grad_norm": 0.20518313348293304,
91
+ "learning_rate": 4.9998295243872466e-05,
92
+ "loss": 0.6899,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.06619039284634601,
97
+ "grad_norm": 0.2965710759162903,
98
+ "learning_rate": 4.999815318086184e-05,
99
+ "loss": 0.6869,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.07128196152683416,
104
+ "grad_norm": 0.269436776638031,
105
+ "learning_rate": 4.999801111785121e-05,
106
+ "loss": 0.6893,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.07637353020732231,
111
+ "grad_norm": 0.2355806529521942,
112
+ "learning_rate": 4.9997869054840585e-05,
113
+ "loss": 0.688,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.08146509888781046,
118
+ "grad_norm": 0.2859913408756256,
119
+ "learning_rate": 4.999772699182996e-05,
120
+ "loss": 0.6882,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.08655666756829862,
125
+ "grad_norm": 0.22986085712909698,
126
+ "learning_rate": 4.999758492881933e-05,
127
+ "loss": 0.6892,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.09164823624878678,
132
+ "grad_norm": 0.1777602881193161,
133
+ "learning_rate": 4.9997442865808705e-05,
134
+ "loss": 0.6891,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.09673980492927493,
139
+ "grad_norm": 0.24697603285312653,
140
+ "learning_rate": 4.999730080279808e-05,
141
+ "loss": 0.6901,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.10183137360976308,
146
+ "grad_norm": 0.24384862184524536,
147
+ "learning_rate": 4.9997158739787444e-05,
148
+ "loss": 0.6864,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.10692294229025123,
153
+ "grad_norm": 0.22532877326011658,
154
+ "learning_rate": 4.999701667677682e-05,
155
+ "loss": 0.6925,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.11201451097073939,
160
+ "grad_norm": 0.33894965052604675,
161
+ "learning_rate": 4.999687461376619e-05,
162
+ "loss": 0.69,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.11710607965122755,
167
+ "grad_norm": 0.1438864767551422,
168
+ "learning_rate": 4.9996732550755563e-05,
169
+ "loss": 0.6905,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.1221976483317157,
174
+ "grad_norm": 0.1356513947248459,
175
+ "learning_rate": 4.9996590487744937e-05,
176
+ "loss": 0.6895,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.12728921701220386,
181
+ "grad_norm": 0.11220791190862656,
182
+ "learning_rate": 4.999644842473431e-05,
183
+ "loss": 0.6889,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.13238078569269202,
188
+ "grad_norm": 0.18669378757476807,
189
+ "learning_rate": 4.999630636172368e-05,
190
+ "loss": 0.6877,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.13747235437318017,
195
+ "grad_norm": 0.24448029696941376,
196
+ "learning_rate": 4.9996164298713056e-05,
197
+ "loss": 0.6821,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.14256392305366833,
202
+ "grad_norm": 0.33900442719459534,
203
+ "learning_rate": 4.999602223570243e-05,
204
+ "loss": 0.6825,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.14765549173415646,
209
+ "grad_norm": 0.20542432367801666,
210
+ "learning_rate": 4.99958801726918e-05,
211
+ "loss": 0.6835,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.15274706041464461,
216
+ "grad_norm": 0.17819932103157043,
217
+ "learning_rate": 4.9995738109681175e-05,
218
+ "loss": 0.6875,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.15783862909513277,
223
+ "grad_norm": 0.16522936522960663,
224
+ "learning_rate": 4.999559604667055e-05,
225
+ "loss": 0.6868,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.16293019777562093,
230
+ "grad_norm": 0.1356010138988495,
231
+ "learning_rate": 4.9995453983659915e-05,
232
+ "loss": 0.6888,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.16802176645610908,
237
+ "grad_norm": 0.20955336093902588,
238
+ "learning_rate": 4.999531192064929e-05,
239
+ "loss": 0.6827,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.17311333513659724,
244
+ "grad_norm": 0.14871099591255188,
245
+ "learning_rate": 4.9995169857638654e-05,
246
+ "loss": 0.687,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.1782049038170854,
251
+ "grad_norm": 0.1207965835928917,
252
+ "learning_rate": 4.999502779462803e-05,
253
+ "loss": 0.6871,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.18329647249757355,
258
+ "grad_norm": 0.25459375977516174,
259
+ "learning_rate": 4.99948857316174e-05,
260
+ "loss": 0.6879,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.1883880411780617,
265
+ "grad_norm": 0.12454749643802643,
266
+ "learning_rate": 4.9994743668606773e-05,
267
+ "loss": 0.689,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.19347960985854987,
272
+ "grad_norm": 0.13212984800338745,
273
+ "learning_rate": 4.9994601605596147e-05,
274
+ "loss": 0.6827,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.19857117853903802,
279
+ "grad_norm": 0.15493592619895935,
280
+ "learning_rate": 4.999445954258552e-05,
281
+ "loss": 0.6916,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.20366274721952615,
286
+ "grad_norm": 0.1339859962463379,
287
+ "learning_rate": 4.999431747957489e-05,
288
+ "loss": 0.6862,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.2087543159000143,
293
+ "grad_norm": 0.17246641218662262,
294
+ "learning_rate": 4.9994175416564266e-05,
295
+ "loss": 0.6915,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.21384588458050247,
300
+ "grad_norm": 0.09907015413045883,
301
+ "learning_rate": 4.999403335355364e-05,
302
+ "loss": 0.6884,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.21893745326099062,
307
+ "grad_norm": 0.13688722252845764,
308
+ "learning_rate": 4.999389129054301e-05,
309
+ "loss": 0.6894,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.22402902194147878,
314
+ "grad_norm": 0.1572660207748413,
315
+ "learning_rate": 4.9993749227532385e-05,
316
+ "loss": 0.6857,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.22912059062196694,
321
+ "grad_norm": 0.22315748035907745,
322
+ "learning_rate": 4.999360716452176e-05,
323
+ "loss": 0.6819,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.2342121593024551,
328
+ "grad_norm": 0.10592522472143173,
329
+ "learning_rate": 4.9993465101511125e-05,
330
+ "loss": 0.6886,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.23930372798294325,
335
+ "grad_norm": 0.10022767633199692,
336
+ "learning_rate": 4.99933230385005e-05,
337
+ "loss": 0.687,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.2443952966634314,
342
+ "grad_norm": 0.12280535697937012,
343
+ "learning_rate": 4.999318097548987e-05,
344
+ "loss": 0.6862,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.24948686534391956,
349
+ "grad_norm": 0.11044813692569733,
350
+ "learning_rate": 4.9993038912479244e-05,
351
+ "loss": 0.6889,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.2545784340244077,
356
+ "grad_norm": 0.13826850056648254,
357
+ "learning_rate": 4.999289684946862e-05,
358
+ "loss": 0.6875,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.2596700027048959,
363
+ "grad_norm": 0.10267098248004913,
364
+ "learning_rate": 4.999275478645799e-05,
365
+ "loss": 0.6877,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.26476157138538403,
370
+ "grad_norm": 0.08445768803358078,
371
+ "learning_rate": 4.999261272344736e-05,
372
+ "loss": 0.6879,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.2698531400658722,
377
+ "grad_norm": 0.1590685397386551,
378
+ "learning_rate": 4.999247066043673e-05,
379
+ "loss": 0.6872,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.27494470874636034,
384
+ "grad_norm": 0.1537754386663437,
385
+ "learning_rate": 4.99923285974261e-05,
386
+ "loss": 0.6812,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.2800362774268485,
391
+ "grad_norm": 0.12273769080638885,
392
+ "learning_rate": 4.9992186534415476e-05,
393
+ "loss": 0.6855,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.28512784610733666,
398
+ "grad_norm": 0.19177380204200745,
399
+ "learning_rate": 4.999204447140485e-05,
400
+ "loss": 0.6857,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.29021941478782476,
405
+ "grad_norm": 0.1194639578461647,
406
+ "learning_rate": 4.999190240839422e-05,
407
+ "loss": 0.6851,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.2953109834683129,
412
+ "grad_norm": 0.12458167970180511,
413
+ "learning_rate": 4.9991760345383595e-05,
414
+ "loss": 0.6875,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.30040255214880107,
419
+ "grad_norm": 0.15139921009540558,
420
+ "learning_rate": 4.999161828237297e-05,
421
+ "loss": 0.6843,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.30549412082928923,
426
+ "grad_norm": 0.13201646506786346,
427
+ "learning_rate": 4.9991476219362335e-05,
428
+ "loss": 0.688,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.3105856895097774,
433
+ "grad_norm": 0.10855768620967865,
434
+ "learning_rate": 4.999133415635171e-05,
435
+ "loss": 0.6859,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.31567725819026554,
440
+ "grad_norm": 0.14113789796829224,
441
+ "learning_rate": 4.999119209334108e-05,
442
+ "loss": 0.6858,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.3207688268707537,
447
+ "grad_norm": 0.19037926197052002,
448
+ "learning_rate": 4.9991050030330454e-05,
449
+ "loss": 0.6851,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.32586039555124185,
454
+ "grad_norm": 0.18522581458091736,
455
+ "learning_rate": 4.999090796731983e-05,
456
+ "loss": 0.6854,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.33095196423173,
461
+ "grad_norm": 0.24384431540966034,
462
+ "learning_rate": 4.99907659043092e-05,
463
+ "loss": 0.6852,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.33604353291221817,
468
+ "grad_norm": 0.21666169166564941,
469
+ "learning_rate": 4.999062384129857e-05,
470
+ "loss": 0.6836,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.3411351015927063,
475
+ "grad_norm": 0.1427813023328781,
476
+ "learning_rate": 4.9990481778287946e-05,
477
+ "loss": 0.6899,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.3462266702731945,
482
+ "grad_norm": 0.09287853538990021,
483
+ "learning_rate": 4.999033971527732e-05,
484
+ "loss": 0.6861,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.35131823895368264,
489
+ "grad_norm": 0.1490527093410492,
490
+ "learning_rate": 4.999019765226669e-05,
491
+ "loss": 0.6859,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.3564098076341708,
496
+ "grad_norm": 0.0858352780342102,
497
+ "learning_rate": 4.9990055589256066e-05,
498
+ "loss": 0.6888,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.36150137631465895,
503
+ "grad_norm": 0.15133963525295258,
504
+ "learning_rate": 4.998991352624544e-05,
505
+ "loss": 0.6837,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.3665929449951471,
510
+ "grad_norm": 0.14562425017356873,
511
+ "learning_rate": 4.9989771463234805e-05,
512
+ "loss": 0.6862,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.37168451367563526,
517
+ "grad_norm": 0.15240037441253662,
518
+ "learning_rate": 4.998962940022418e-05,
519
+ "loss": 0.6839,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.3767760823561234,
524
+ "grad_norm": 0.1231294646859169,
525
+ "learning_rate": 4.9989487337213544e-05,
526
+ "loss": 0.6868,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.3818676510366116,
531
+ "grad_norm": 0.14511612057685852,
532
+ "learning_rate": 4.998934527420292e-05,
533
+ "loss": 0.6816,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.38695921971709973,
538
+ "grad_norm": 0.1693543940782547,
539
+ "learning_rate": 4.998920321119229e-05,
540
+ "loss": 0.6843,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.3920507883975879,
545
+ "grad_norm": 0.09580985456705093,
546
+ "learning_rate": 4.9989061148181664e-05,
547
+ "loss": 0.6875,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.39714235707807605,
552
+ "grad_norm": 0.1047905758023262,
553
+ "learning_rate": 4.998891908517104e-05,
554
+ "loss": 0.6859,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.4022339257585642,
559
+ "grad_norm": 0.1090409904718399,
560
+ "learning_rate": 4.998877702216041e-05,
561
+ "loss": 0.6852,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.4073254944390523,
566
+ "grad_norm": 0.12578189373016357,
567
+ "learning_rate": 4.998863495914978e-05,
568
+ "loss": 0.6867,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.41241706311954046,
573
+ "grad_norm": 0.11900747567415237,
574
+ "learning_rate": 4.9988492896139156e-05,
575
+ "loss": 0.6814,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.4175086318000286,
580
+ "grad_norm": 0.11401454359292984,
581
+ "learning_rate": 4.998835083312853e-05,
582
+ "loss": 0.6899,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.4226002004805168,
587
+ "grad_norm": 0.1015952005982399,
588
+ "learning_rate": 4.99882087701179e-05,
589
+ "loss": 0.6865,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.42769176916100493,
594
+ "grad_norm": 0.16676318645477295,
595
+ "learning_rate": 4.9988066707107276e-05,
596
+ "loss": 0.6891,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.4327833378414931,
601
+ "grad_norm": 0.10982430726289749,
602
+ "learning_rate": 4.998792464409665e-05,
603
+ "loss": 0.6863,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.43787490652198124,
608
+ "grad_norm": 0.13861846923828125,
609
+ "learning_rate": 4.9987782581086015e-05,
610
+ "loss": 0.6898,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.4429664752024694,
615
+ "grad_norm": 0.09421814233064651,
616
+ "learning_rate": 4.998764051807539e-05,
617
+ "loss": 0.6861,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.44805804388295756,
622
+ "grad_norm": 0.14085189998149872,
623
+ "learning_rate": 4.998749845506476e-05,
624
+ "loss": 0.683,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.4531496125634457,
629
+ "grad_norm": 0.1671237349510193,
630
+ "learning_rate": 4.9987356392054134e-05,
631
+ "loss": 0.6835,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.45824118124393387,
636
+ "grad_norm": 0.13570742309093475,
637
+ "learning_rate": 4.998721432904351e-05,
638
+ "loss": 0.685,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.463332749924422,
643
+ "grad_norm": 0.10402018576860428,
644
+ "learning_rate": 4.998707226603288e-05,
645
+ "loss": 0.6872,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.4684243186049102,
650
+ "grad_norm": 0.10226580500602722,
651
+ "learning_rate": 4.9986930203022254e-05,
652
+ "loss": 0.6871,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.47351588728539834,
657
+ "grad_norm": 0.10132193565368652,
658
+ "learning_rate": 4.998678814001163e-05,
659
+ "loss": 0.6902,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.4786074559658865,
664
+ "grad_norm": 0.11389295756816864,
665
+ "learning_rate": 4.9986646077001e-05,
666
+ "loss": 0.6818,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.48369902464637465,
671
+ "grad_norm": 0.13445314764976501,
672
+ "learning_rate": 4.9986504013990366e-05,
673
+ "loss": 0.6882,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.4887905933268628,
678
+ "grad_norm": 0.08756639063358307,
679
+ "learning_rate": 4.998636195097974e-05,
680
+ "loss": 0.6893,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.49388216200735097,
685
+ "grad_norm": 0.08042973279953003,
686
+ "learning_rate": 4.998621988796911e-05,
687
+ "loss": 0.6891,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.4989737306878391,
692
+ "grad_norm": 0.10082978755235672,
693
+ "learning_rate": 4.9986077824958485e-05,
694
+ "loss": 0.6903,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.5040652993683272,
699
+ "grad_norm": 0.0936272069811821,
700
+ "learning_rate": 4.998593576194786e-05,
701
+ "loss": 0.6864,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.5091568680488154,
706
+ "grad_norm": 0.12317179143428802,
707
+ "learning_rate": 4.9985793698937225e-05,
708
+ "loss": 0.6856,
709
+ "step": 1000
710
+ }
711
+ ],
712
+ "logging_steps": 10,
713
+ "max_steps": 13748,
714
+ "num_input_tokens_seen": 0,
715
+ "num_train_epochs": 7,
716
+ "save_steps": 1000,
717
+ "stateful_callbacks": {
718
+ "TrainerControl": {
719
+ "args": {
720
+ "should_epoch_stop": false,
721
+ "should_evaluate": false,
722
+ "should_log": false,
723
+ "should_save": true,
724
+ "should_training_stop": false
725
+ },
726
+ "attributes": {}
727
+ }
728
+ },
729
+ "total_flos": 0.0,
730
+ "train_batch_size": 1,
731
+ "trial_name": null,
732
+ "trial_params": null
733
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b79bfef1c53cff3a705bdc64ad1e5c8877fd041fc051d68509af1adf3bd30f
3
+ size 5432