CocoRoF commited on
Commit
97158ed
·
verified ·
1 Parent(s): 76c1deb

Training in progress, step 500, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CocoRoF/KoModernBERT-large-mlm-v8",
3
+ "architectures": [
4
+ "ModernBertForMaskedLM"
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": 1024,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 2624,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 16,
36
+ "num_hidden_layers": 28,
37
+ "pad_token_id": 50283,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": false,
40
+ "repad_logits_with_grad": false,
41
+ "sep_token_id": 50282,
42
+ "sparse_pred_ignore_index": -100,
43
+ "sparse_prediction": false,
44
+ "torch_dtype": "float16",
45
+ "transformers_version": "4.49.0",
46
+ "vocab_size": 50411
47
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa115a9b44eddd31239249af967a9cc68c05d2e90e11fed79b56ff0bcbe835bb
3
+ size 791869518
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc218283c198560bdfa85f3ab5c42a23aac9930dbda514ca712373372068b858
3
+ size 2375752250
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d3f197f6c6558fa8056324f1563ab9e957255f5a1a959362aa4eed7a9545db
3
+ size 15984
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c1a9c65c2869356282cad6b4a0f7dff7f4dd68ab3d9d216c72b7d6cb524f860
3
+ size 15984
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896febe768e17bae5022a95960c041f6425783774ec8859d99d3b149063b1bf9
3
+ size 15984
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac482d57e966585467c8ef44dae2869bf7e5d92886f69c11ed7bccc34c07efe
3
+ size 15984
last-checkpoint/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f27d227a20dc320ac283e0938fb2f6e5b475829a583f8c44d1a16a8c828307
3
+ size 15984
last-checkpoint/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d05a7106aaeaec4b81704e3f4a998b5123cf9342a6733bd9fd2d578e99108c3b
3
+ size 15984
last-checkpoint/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94120d8d88502ec8d8b623ec7550315caca003b44fcffbb5767ab0de91baefe
3
+ size 15984
last-checkpoint/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:332e4d901be380f740b5d8578f7b80ef1865c7fba83bc288c8a35852205cc668
3
+ size 15984
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ac6dc5dc1f7c6772a7fe1da65c3c395e23b56d006497e0dee9efefb278bb143
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 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50328": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50329": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50330": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50331": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50332": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50333": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50334": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50335": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50336": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50337": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50338": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50339": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50340": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50341": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50342": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50343": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50344": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50345": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50346": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50347": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50348": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50349": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50350": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50351": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50352": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50353": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50354": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50355": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50356": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50357": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50358": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50359": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50360": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50361": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50362": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50363": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50364": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50365": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50366": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50367": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50368": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50369": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50370": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50371": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50372": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50373": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50374": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50375": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50376": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50377": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50378": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50379": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50380": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50381": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50382": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50383": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50384": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50385": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50386": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50387": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50388": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50389": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50390": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50391": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50392": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50393": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50394": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50395": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50396": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50397": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50398": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50399": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50400": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50401": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50402": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50403": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50404": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50405": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50406": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50407": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50408": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50409": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50410": {
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
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,741 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.362499433594635,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.00362499433594635,
13
+ "grad_norm": 138.0,
14
+ "learning_rate": 1.0869565217391305e-07,
15
+ "loss": 117.3129,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.0072499886718927,
20
+ "grad_norm": 117.875,
21
+ "learning_rate": 2.173913043478261e-07,
22
+ "loss": 114.987,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.01087498300783905,
27
+ "grad_norm": 115.8125,
28
+ "learning_rate": 3.2608695652173915e-07,
29
+ "loss": 112.9424,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.0144999773437854,
34
+ "grad_norm": 111.75,
35
+ "learning_rate": 4.347826086956522e-07,
36
+ "loss": 111.7335,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.01812497167973175,
41
+ "grad_norm": 101.6875,
42
+ "learning_rate": 5.434782608695653e-07,
43
+ "loss": 108.2753,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.0217499660156781,
48
+ "grad_norm": 105.75,
49
+ "learning_rate": 6.521739130434783e-07,
50
+ "loss": 108.8031,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.02537496035162445,
55
+ "grad_norm": 102.25,
56
+ "learning_rate": 7.608695652173913e-07,
57
+ "loss": 106.3006,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.0289999546875708,
62
+ "grad_norm": 109.8125,
63
+ "learning_rate": 8.695652173913044e-07,
64
+ "loss": 105.7198,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.032624949023517154,
69
+ "grad_norm": 104.8125,
70
+ "learning_rate": 9.782608695652175e-07,
71
+ "loss": 105.453,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.0362499433594635,
76
+ "grad_norm": 104.25,
77
+ "learning_rate": 1.0869565217391306e-06,
78
+ "loss": 103.4564,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.039874937695409854,
83
+ "grad_norm": 102.4375,
84
+ "learning_rate": 1.1956521739130436e-06,
85
+ "loss": 104.0079,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.0434999320313562,
90
+ "grad_norm": 104.5625,
91
+ "learning_rate": 1.3043478260869566e-06,
92
+ "loss": 102.2786,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.047124926367302554,
97
+ "grad_norm": 111.6875,
98
+ "learning_rate": 1.4130434782608697e-06,
99
+ "loss": 103.5031,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.0507499207032489,
104
+ "grad_norm": 109.5625,
105
+ "learning_rate": 1.5217391304347827e-06,
106
+ "loss": 100.9987,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.054374915039195254,
111
+ "grad_norm": 108.125,
112
+ "learning_rate": 1.6304347826086955e-06,
113
+ "loss": 102.5049,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.0579999093751416,
118
+ "grad_norm": 107.5,
119
+ "learning_rate": 1.7391304347826088e-06,
120
+ "loss": 100.2175,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.061624903711087954,
125
+ "grad_norm": 106.875,
126
+ "learning_rate": 1.8478260869565216e-06,
127
+ "loss": 102.2802,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.06524989804703431,
132
+ "grad_norm": 108.5,
133
+ "learning_rate": 1.956521739130435e-06,
134
+ "loss": 100.3301,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.06887489238298065,
139
+ "grad_norm": 108.125,
140
+ "learning_rate": 2.0652173913043476e-06,
141
+ "loss": 99.986,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 0.072499886718927,
146
+ "grad_norm": 109.9375,
147
+ "learning_rate": 2.173913043478261e-06,
148
+ "loss": 101.1288,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 0.07612488105487335,
153
+ "grad_norm": 111.1875,
154
+ "learning_rate": 2.282608695652174e-06,
155
+ "loss": 99.3183,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 0.07974987539081971,
160
+ "grad_norm": 107.5625,
161
+ "learning_rate": 2.391304347826087e-06,
162
+ "loss": 99.5069,
163
+ "step": 110
164
+ },
165
+ {
166
+ "epoch": 0.08337486972676605,
167
+ "grad_norm": 103.9375,
168
+ "learning_rate": 2.5e-06,
169
+ "loss": 99.9877,
170
+ "step": 115
171
+ },
172
+ {
173
+ "epoch": 0.0869998640627124,
174
+ "grad_norm": 108.4375,
175
+ "learning_rate": 2.6086956521739132e-06,
176
+ "loss": 100.5115,
177
+ "step": 120
178
+ },
179
+ {
180
+ "epoch": 0.09062485839865875,
181
+ "grad_norm": 104.9375,
182
+ "learning_rate": 2.7173913043478263e-06,
183
+ "loss": 98.9701,
184
+ "step": 125
185
+ },
186
+ {
187
+ "epoch": 0.09424985273460511,
188
+ "grad_norm": 112.9375,
189
+ "learning_rate": 2.8260869565217393e-06,
190
+ "loss": 99.0897,
191
+ "step": 130
192
+ },
193
+ {
194
+ "epoch": 0.09787484707055145,
195
+ "grad_norm": 111.75,
196
+ "learning_rate": 2.9347826086956523e-06,
197
+ "loss": 99.9607,
198
+ "step": 135
199
+ },
200
+ {
201
+ "epoch": 0.1014998414064978,
202
+ "grad_norm": 112.0,
203
+ "learning_rate": 2.9951651893634165e-06,
204
+ "loss": 99.9585,
205
+ "step": 140
206
+ },
207
+ {
208
+ "epoch": 0.10512483574244415,
209
+ "grad_norm": 107.1875,
210
+ "learning_rate": 2.983078162771958e-06,
211
+ "loss": 99.4564,
212
+ "step": 145
213
+ },
214
+ {
215
+ "epoch": 0.10874983007839051,
216
+ "grad_norm": 104.1875,
217
+ "learning_rate": 2.9709911361804994e-06,
218
+ "loss": 98.2848,
219
+ "step": 150
220
+ },
221
+ {
222
+ "epoch": 0.11237482441433685,
223
+ "grad_norm": 107.0,
224
+ "learning_rate": 2.958904109589041e-06,
225
+ "loss": 99.0036,
226
+ "step": 155
227
+ },
228
+ {
229
+ "epoch": 0.1159998187502832,
230
+ "grad_norm": 100.8125,
231
+ "learning_rate": 2.9468170829975827e-06,
232
+ "loss": 99.8976,
233
+ "step": 160
234
+ },
235
+ {
236
+ "epoch": 0.11962481308622955,
237
+ "grad_norm": 108.75,
238
+ "learning_rate": 2.934730056406124e-06,
239
+ "loss": 99.9953,
240
+ "step": 165
241
+ },
242
+ {
243
+ "epoch": 0.12324980742217591,
244
+ "grad_norm": 107.4375,
245
+ "learning_rate": 2.9226430298146656e-06,
246
+ "loss": 99.2312,
247
+ "step": 170
248
+ },
249
+ {
250
+ "epoch": 0.12687480175812224,
251
+ "grad_norm": 103.25,
252
+ "learning_rate": 2.910556003223207e-06,
253
+ "loss": 98.0048,
254
+ "step": 175
255
+ },
256
+ {
257
+ "epoch": 0.13049979609406862,
258
+ "grad_norm": 104.3125,
259
+ "learning_rate": 2.8984689766317485e-06,
260
+ "loss": 97.5375,
261
+ "step": 180
262
+ },
263
+ {
264
+ "epoch": 0.13412479043001496,
265
+ "grad_norm": 112.1875,
266
+ "learning_rate": 2.88638195004029e-06,
267
+ "loss": 98.1078,
268
+ "step": 185
269
+ },
270
+ {
271
+ "epoch": 0.1377497847659613,
272
+ "grad_norm": 101.75,
273
+ "learning_rate": 2.874294923448832e-06,
274
+ "loss": 99.2633,
275
+ "step": 190
276
+ },
277
+ {
278
+ "epoch": 0.14137477910190765,
279
+ "grad_norm": 99.3125,
280
+ "learning_rate": 2.8622078968573733e-06,
281
+ "loss": 98.5032,
282
+ "step": 195
283
+ },
284
+ {
285
+ "epoch": 0.144999773437854,
286
+ "grad_norm": 104.5,
287
+ "learning_rate": 2.8501208702659147e-06,
288
+ "loss": 98.2166,
289
+ "step": 200
290
+ },
291
+ {
292
+ "epoch": 0.14862476777380035,
293
+ "grad_norm": 105.25,
294
+ "learning_rate": 2.838033843674456e-06,
295
+ "loss": 97.2117,
296
+ "step": 205
297
+ },
298
+ {
299
+ "epoch": 0.1522497621097467,
300
+ "grad_norm": 101.1875,
301
+ "learning_rate": 2.8259468170829976e-06,
302
+ "loss": 97.9536,
303
+ "step": 210
304
+ },
305
+ {
306
+ "epoch": 0.15587475644569304,
307
+ "grad_norm": 97.4375,
308
+ "learning_rate": 2.813859790491539e-06,
309
+ "loss": 96.6339,
310
+ "step": 215
311
+ },
312
+ {
313
+ "epoch": 0.15949975078163942,
314
+ "grad_norm": 96.875,
315
+ "learning_rate": 2.8017727639000805e-06,
316
+ "loss": 96.5506,
317
+ "step": 220
318
+ },
319
+ {
320
+ "epoch": 0.16312474511758576,
321
+ "grad_norm": 101.125,
322
+ "learning_rate": 2.7896857373086224e-06,
323
+ "loss": 96.7369,
324
+ "step": 225
325
+ },
326
+ {
327
+ "epoch": 0.1667497394535321,
328
+ "grad_norm": 101.25,
329
+ "learning_rate": 2.777598710717164e-06,
330
+ "loss": 96.1206,
331
+ "step": 230
332
+ },
333
+ {
334
+ "epoch": 0.17037473378947846,
335
+ "grad_norm": 100.625,
336
+ "learning_rate": 2.7655116841257053e-06,
337
+ "loss": 96.422,
338
+ "step": 235
339
+ },
340
+ {
341
+ "epoch": 0.1739997281254248,
342
+ "grad_norm": 96.875,
343
+ "learning_rate": 2.7534246575342467e-06,
344
+ "loss": 96.8563,
345
+ "step": 240
346
+ },
347
+ {
348
+ "epoch": 0.17762472246137115,
349
+ "grad_norm": 98.625,
350
+ "learning_rate": 2.741337630942788e-06,
351
+ "loss": 96.0922,
352
+ "step": 245
353
+ },
354
+ {
355
+ "epoch": 0.1812497167973175,
356
+ "grad_norm": 102.5,
357
+ "learning_rate": 2.7292506043513296e-06,
358
+ "loss": 95.6746,
359
+ "step": 250
360
+ },
361
+ {
362
+ "epoch": 0.18487471113326384,
363
+ "grad_norm": 99.375,
364
+ "learning_rate": 2.717163577759871e-06,
365
+ "loss": 97.3913,
366
+ "step": 255
367
+ },
368
+ {
369
+ "epoch": 0.18849970546921022,
370
+ "grad_norm": 101.625,
371
+ "learning_rate": 2.705076551168413e-06,
372
+ "loss": 95.3053,
373
+ "step": 260
374
+ },
375
+ {
376
+ "epoch": 0.19212469980515656,
377
+ "grad_norm": 101.8125,
378
+ "learning_rate": 2.6929895245769544e-06,
379
+ "loss": 96.0484,
380
+ "step": 265
381
+ },
382
+ {
383
+ "epoch": 0.1957496941411029,
384
+ "grad_norm": 103.8125,
385
+ "learning_rate": 2.680902497985496e-06,
386
+ "loss": 95.5011,
387
+ "step": 270
388
+ },
389
+ {
390
+ "epoch": 0.19937468847704926,
391
+ "grad_norm": 100.9375,
392
+ "learning_rate": 2.6688154713940373e-06,
393
+ "loss": 95.9148,
394
+ "step": 275
395
+ },
396
+ {
397
+ "epoch": 0.2029996828129956,
398
+ "grad_norm": 100.25,
399
+ "learning_rate": 2.6567284448025787e-06,
400
+ "loss": 95.4637,
401
+ "step": 280
402
+ },
403
+ {
404
+ "epoch": 0.20662467714894195,
405
+ "grad_norm": 97.9375,
406
+ "learning_rate": 2.64464141821112e-06,
407
+ "loss": 95.4132,
408
+ "step": 285
409
+ },
410
+ {
411
+ "epoch": 0.2102496714848883,
412
+ "grad_norm": 95.75,
413
+ "learning_rate": 2.6325543916196616e-06,
414
+ "loss": 95.2729,
415
+ "step": 290
416
+ },
417
+ {
418
+ "epoch": 0.21387466582083464,
419
+ "grad_norm": 97.3125,
420
+ "learning_rate": 2.6204673650282035e-06,
421
+ "loss": 93.7039,
422
+ "step": 295
423
+ },
424
+ {
425
+ "epoch": 0.21749966015678102,
426
+ "grad_norm": 98.875,
427
+ "learning_rate": 2.608380338436745e-06,
428
+ "loss": 94.9171,
429
+ "step": 300
430
+ },
431
+ {
432
+ "epoch": 0.22112465449272736,
433
+ "grad_norm": 102.25,
434
+ "learning_rate": 2.5962933118452864e-06,
435
+ "loss": 94.2651,
436
+ "step": 305
437
+ },
438
+ {
439
+ "epoch": 0.2247496488286737,
440
+ "grad_norm": 97.5,
441
+ "learning_rate": 2.584206285253828e-06,
442
+ "loss": 95.5929,
443
+ "step": 310
444
+ },
445
+ {
446
+ "epoch": 0.22837464316462006,
447
+ "grad_norm": 103.1875,
448
+ "learning_rate": 2.5721192586623693e-06,
449
+ "loss": 93.7398,
450
+ "step": 315
451
+ },
452
+ {
453
+ "epoch": 0.2319996375005664,
454
+ "grad_norm": 95.9375,
455
+ "learning_rate": 2.5600322320709107e-06,
456
+ "loss": 93.6436,
457
+ "step": 320
458
+ },
459
+ {
460
+ "epoch": 0.23562463183651275,
461
+ "grad_norm": 103.5625,
462
+ "learning_rate": 2.547945205479452e-06,
463
+ "loss": 95.239,
464
+ "step": 325
465
+ },
466
+ {
467
+ "epoch": 0.2392496261724591,
468
+ "grad_norm": 101.9375,
469
+ "learning_rate": 2.5358581788879936e-06,
470
+ "loss": 93.0672,
471
+ "step": 330
472
+ },
473
+ {
474
+ "epoch": 0.24287462050840544,
475
+ "grad_norm": 96.3125,
476
+ "learning_rate": 2.523771152296535e-06,
477
+ "loss": 93.4256,
478
+ "step": 335
479
+ },
480
+ {
481
+ "epoch": 0.24649961484435182,
482
+ "grad_norm": 96.75,
483
+ "learning_rate": 2.5116841257050765e-06,
484
+ "loss": 93.6135,
485
+ "step": 340
486
+ },
487
+ {
488
+ "epoch": 0.25012460918029816,
489
+ "grad_norm": 101.875,
490
+ "learning_rate": 2.499597099113618e-06,
491
+ "loss": 93.2672,
492
+ "step": 345
493
+ },
494
+ {
495
+ "epoch": 0.2537496035162445,
496
+ "grad_norm": 98.875,
497
+ "learning_rate": 2.4875100725221594e-06,
498
+ "loss": 92.7295,
499
+ "step": 350
500
+ },
501
+ {
502
+ "epoch": 0.25737459785219086,
503
+ "grad_norm": 98.4375,
504
+ "learning_rate": 2.475423045930701e-06,
505
+ "loss": 93.7394,
506
+ "step": 355
507
+ },
508
+ {
509
+ "epoch": 0.26099959218813723,
510
+ "grad_norm": 93.1875,
511
+ "learning_rate": 2.4633360193392423e-06,
512
+ "loss": 94.1141,
513
+ "step": 360
514
+ },
515
+ {
516
+ "epoch": 0.26462458652408355,
517
+ "grad_norm": 94.8125,
518
+ "learning_rate": 2.451248992747784e-06,
519
+ "loss": 92.5803,
520
+ "step": 365
521
+ },
522
+ {
523
+ "epoch": 0.2682495808600299,
524
+ "grad_norm": 94.1875,
525
+ "learning_rate": 2.4391619661563256e-06,
526
+ "loss": 93.6379,
527
+ "step": 370
528
+ },
529
+ {
530
+ "epoch": 0.27187457519597624,
531
+ "grad_norm": 99.0625,
532
+ "learning_rate": 2.427074939564867e-06,
533
+ "loss": 93.6082,
534
+ "step": 375
535
+ },
536
+ {
537
+ "epoch": 0.2754995695319226,
538
+ "grad_norm": 93.4375,
539
+ "learning_rate": 2.4149879129734085e-06,
540
+ "loss": 93.4951,
541
+ "step": 380
542
+ },
543
+ {
544
+ "epoch": 0.27912456386786894,
545
+ "grad_norm": 97.5625,
546
+ "learning_rate": 2.40290088638195e-06,
547
+ "loss": 93.0027,
548
+ "step": 385
549
+ },
550
+ {
551
+ "epoch": 0.2827495582038153,
552
+ "grad_norm": 92.8125,
553
+ "learning_rate": 2.3908138597904914e-06,
554
+ "loss": 92.4963,
555
+ "step": 390
556
+ },
557
+ {
558
+ "epoch": 0.2863745525397617,
559
+ "grad_norm": 98.0625,
560
+ "learning_rate": 2.378726833199033e-06,
561
+ "loss": 92.3384,
562
+ "step": 395
563
+ },
564
+ {
565
+ "epoch": 0.289999546875708,
566
+ "grad_norm": 97.25,
567
+ "learning_rate": 2.3666398066075747e-06,
568
+ "loss": 90.9909,
569
+ "step": 400
570
+ },
571
+ {
572
+ "epoch": 0.2936245412116544,
573
+ "grad_norm": 96.125,
574
+ "learning_rate": 2.354552780016116e-06,
575
+ "loss": 92.7515,
576
+ "step": 405
577
+ },
578
+ {
579
+ "epoch": 0.2972495355476007,
580
+ "grad_norm": 96.625,
581
+ "learning_rate": 2.3424657534246576e-06,
582
+ "loss": 92.0935,
583
+ "step": 410
584
+ },
585
+ {
586
+ "epoch": 0.30087452988354707,
587
+ "grad_norm": 94.5625,
588
+ "learning_rate": 2.330378726833199e-06,
589
+ "loss": 91.9012,
590
+ "step": 415
591
+ },
592
+ {
593
+ "epoch": 0.3044995242194934,
594
+ "grad_norm": 99.0625,
595
+ "learning_rate": 2.3182917002417405e-06,
596
+ "loss": 92.2002,
597
+ "step": 420
598
+ },
599
+ {
600
+ "epoch": 0.30812451855543976,
601
+ "grad_norm": 96.1875,
602
+ "learning_rate": 2.306204673650282e-06,
603
+ "loss": 91.8505,
604
+ "step": 425
605
+ },
606
+ {
607
+ "epoch": 0.3117495128913861,
608
+ "grad_norm": 97.4375,
609
+ "learning_rate": 2.2941176470588234e-06,
610
+ "loss": 91.5476,
611
+ "step": 430
612
+ },
613
+ {
614
+ "epoch": 0.31537450722733246,
615
+ "grad_norm": 94.5625,
616
+ "learning_rate": 2.2820306204673653e-06,
617
+ "loss": 91.3416,
618
+ "step": 435
619
+ },
620
+ {
621
+ "epoch": 0.31899950156327883,
622
+ "grad_norm": 97.9375,
623
+ "learning_rate": 2.2699435938759067e-06,
624
+ "loss": 91.7781,
625
+ "step": 440
626
+ },
627
+ {
628
+ "epoch": 0.32262449589922515,
629
+ "grad_norm": 97.8125,
630
+ "learning_rate": 2.257856567284448e-06,
631
+ "loss": 91.1466,
632
+ "step": 445
633
+ },
634
+ {
635
+ "epoch": 0.3262494902351715,
636
+ "grad_norm": 98.8125,
637
+ "learning_rate": 2.2457695406929896e-06,
638
+ "loss": 90.8318,
639
+ "step": 450
640
+ },
641
+ {
642
+ "epoch": 0.32987448457111784,
643
+ "grad_norm": 95.5625,
644
+ "learning_rate": 2.233682514101531e-06,
645
+ "loss": 92.1053,
646
+ "step": 455
647
+ },
648
+ {
649
+ "epoch": 0.3334994789070642,
650
+ "grad_norm": 95.375,
651
+ "learning_rate": 2.2215954875100725e-06,
652
+ "loss": 90.3236,
653
+ "step": 460
654
+ },
655
+ {
656
+ "epoch": 0.33712447324301054,
657
+ "grad_norm": 100.0625,
658
+ "learning_rate": 2.209508460918614e-06,
659
+ "loss": 90.7755,
660
+ "step": 465
661
+ },
662
+ {
663
+ "epoch": 0.3407494675789569,
664
+ "grad_norm": 94.9375,
665
+ "learning_rate": 2.197421434327156e-06,
666
+ "loss": 90.1338,
667
+ "step": 470
668
+ },
669
+ {
670
+ "epoch": 0.3443744619149033,
671
+ "grad_norm": 96.3125,
672
+ "learning_rate": 2.1853344077356973e-06,
673
+ "loss": 90.5398,
674
+ "step": 475
675
+ },
676
+ {
677
+ "epoch": 0.3479994562508496,
678
+ "grad_norm": 97.5,
679
+ "learning_rate": 2.1732473811442387e-06,
680
+ "loss": 90.215,
681
+ "step": 480
682
+ },
683
+ {
684
+ "epoch": 0.351624450586796,
685
+ "grad_norm": 94.0625,
686
+ "learning_rate": 2.16116035455278e-06,
687
+ "loss": 90.7786,
688
+ "step": 485
689
+ },
690
+ {
691
+ "epoch": 0.3552494449227423,
692
+ "grad_norm": 100.75,
693
+ "learning_rate": 2.1490733279613216e-06,
694
+ "loss": 90.7591,
695
+ "step": 490
696
+ },
697
+ {
698
+ "epoch": 0.35887443925868867,
699
+ "grad_norm": 99.0,
700
+ "learning_rate": 2.136986301369863e-06,
701
+ "loss": 90.2019,
702
+ "step": 495
703
+ },
704
+ {
705
+ "epoch": 0.362499433594635,
706
+ "grad_norm": 97.6875,
707
+ "learning_rate": 2.1248992747784045e-06,
708
+ "loss": 89.8916,
709
+ "step": 500
710
+ },
711
+ {
712
+ "epoch": 0.362499433594635,
713
+ "eval_loss": NaN,
714
+ "eval_runtime": 124.7816,
715
+ "eval_samples_per_second": 595.745,
716
+ "eval_steps_per_second": 37.241,
717
+ "step": 500
718
+ }
719
+ ],
720
+ "logging_steps": 5,
721
+ "max_steps": 1379,
722
+ "num_input_tokens_seen": 0,
723
+ "num_train_epochs": 1,
724
+ "save_steps": 500,
725
+ "stateful_callbacks": {
726
+ "TrainerControl": {
727
+ "args": {
728
+ "should_epoch_stop": false,
729
+ "should_evaluate": false,
730
+ "should_log": false,
731
+ "should_save": true,
732
+ "should_training_stop": false
733
+ },
734
+ "attributes": {}
735
+ }
736
+ },
737
+ "total_flos": 2.1661789963943936e+18,
738
+ "train_batch_size": 4,
739
+ "trial_name": null,
740
+ "trial_params": null
741
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c78c4834eb49f9e52370e453593db0bc34d80eba5b885ac9f3a982fb31e920c
3
+ size 5752