CocoRoF commited on
Commit
d861b81
·
verified ·
1 Parent(s): 685251c

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CocoRoF/KoModernBERT-base-mlm-v04-retry-model-chp11",
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": 768,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 1152,
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": 12,
36
+ "num_hidden_layers": 22,
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": "4.48.3",
46
+ "vocab_size": 95663
47
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:062f7ceb18e2b2e72f6b7c8405ecb67263d54f0d4feb0f5eac0e684ec2f23971
3
+ size 368988278
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db8cd66fc71141c0b406bfab946f66ed691afc3687a00f256e1edfcb3c6a4b4
3
+ size 1107079290
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:dec3ff97eb925dbd3ffacc4075520e0cc49b74019f1ef7de583f66588d258b1c
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
+ "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
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 1000000000000000019884624838656,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizerFast",
944
+ "unk_token": "[UNK]"
945
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.46719420679183576,
5
+ "eval_steps": 2000,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002335971033959179,
13
+ "grad_norm": 73.6875,
14
+ "learning_rate": 9.999954375607375e-07,
15
+ "loss": 107.9787,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.004671942067918358,
20
+ "grad_norm": 73.25,
21
+ "learning_rate": 9.99990875121475e-07,
22
+ "loss": 103.9372,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.007007913101877537,
27
+ "grad_norm": 59.53125,
28
+ "learning_rate": 9.999863126822123e-07,
29
+ "loss": 100.6365,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.009343884135836715,
34
+ "grad_norm": 60.3125,
35
+ "learning_rate": 9.999817502429498e-07,
36
+ "loss": 100.6602,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.011679855169795894,
41
+ "grad_norm": 59.1875,
42
+ "learning_rate": 9.999771878036874e-07,
43
+ "loss": 100.0208,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.014015826203755074,
48
+ "grad_norm": 55.53125,
49
+ "learning_rate": 9.999726253644248e-07,
50
+ "loss": 98.8471,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.016351797237714252,
55
+ "grad_norm": 55.3125,
56
+ "learning_rate": 9.999680629251621e-07,
57
+ "loss": 99.5175,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.01868776827167343,
62
+ "grad_norm": 58.53125,
63
+ "learning_rate": 9.999635004858997e-07,
64
+ "loss": 98.5395,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.02102373930563261,
69
+ "grad_norm": 59.8125,
70
+ "learning_rate": 9.999589380466373e-07,
71
+ "loss": 98.9192,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.023359710339591788,
76
+ "grad_norm": 63.78125,
77
+ "learning_rate": 9.999543756073747e-07,
78
+ "loss": 97.6611,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.02569568137355097,
83
+ "grad_norm": 58.9375,
84
+ "learning_rate": 9.99949813168112e-07,
85
+ "loss": 97.8031,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.028031652407510148,
90
+ "grad_norm": 59.1875,
91
+ "learning_rate": 9.999452507288496e-07,
92
+ "loss": 98.0507,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.030367623441469326,
97
+ "grad_norm": 51.15625,
98
+ "learning_rate": 9.999406882895872e-07,
99
+ "loss": 96.8367,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.032703594475428505,
104
+ "grad_norm": 56.09375,
105
+ "learning_rate": 9.999361258503245e-07,
106
+ "loss": 96.7883,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.035039565509387686,
111
+ "grad_norm": 54.9375,
112
+ "learning_rate": 9.99931563411062e-07,
113
+ "loss": 97.7532,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.03737553654334686,
118
+ "grad_norm": 61.21875,
119
+ "learning_rate": 9.999270009717995e-07,
120
+ "loss": 97.0359,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.03971150757730604,
125
+ "grad_norm": 60.5625,
126
+ "learning_rate": 9.99922438532537e-07,
127
+ "loss": 96.5724,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.04204747861126522,
132
+ "grad_norm": 52.625,
133
+ "learning_rate": 9.999178760932744e-07,
134
+ "loss": 97.048,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.0443834496452244,
139
+ "grad_norm": 57.53125,
140
+ "learning_rate": 9.999133136540118e-07,
141
+ "loss": 96.4664,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.046719420679183575,
146
+ "grad_norm": 52.875,
147
+ "learning_rate": 9.999087512147494e-07,
148
+ "loss": 96.2538,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.04905539171314276,
153
+ "grad_norm": 63.71875,
154
+ "learning_rate": 9.99904188775487e-07,
155
+ "loss": 95.9222,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.05139136274710194,
160
+ "grad_norm": 54.8125,
161
+ "learning_rate": 9.998996263362243e-07,
162
+ "loss": 96.0401,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.053727333781061114,
167
+ "grad_norm": 55.0625,
168
+ "learning_rate": 9.998950638969619e-07,
169
+ "loss": 96.3144,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.056063304815020296,
174
+ "grad_norm": 53.5625,
175
+ "learning_rate": 9.998905014576992e-07,
176
+ "loss": 95.5121,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.05839927584897947,
181
+ "grad_norm": 52.59375,
182
+ "learning_rate": 9.998859390184368e-07,
183
+ "loss": 95.5379,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.06073524688293865,
188
+ "grad_norm": 51.875,
189
+ "learning_rate": 9.998813765791742e-07,
190
+ "loss": 94.811,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.06307121791689783,
195
+ "grad_norm": 54.46875,
196
+ "learning_rate": 9.998768141399118e-07,
197
+ "loss": 95.986,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.06540718895085701,
202
+ "grad_norm": 55.1875,
203
+ "learning_rate": 9.998722517006491e-07,
204
+ "loss": 95.3928,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.06774315998481618,
209
+ "grad_norm": 56.625,
210
+ "learning_rate": 9.998676892613867e-07,
211
+ "loss": 94.6728,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.07007913101877537,
216
+ "grad_norm": 55.09375,
217
+ "learning_rate": 9.99863126822124e-07,
218
+ "loss": 95.4789,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.07241510205273455,
223
+ "grad_norm": 61.96875,
224
+ "learning_rate": 9.998585643828616e-07,
225
+ "loss": 95.9337,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.07475107308669372,
230
+ "grad_norm": 55.34375,
231
+ "learning_rate": 9.99854001943599e-07,
232
+ "loss": 94.6639,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.0770870441206529,
237
+ "grad_norm": 55.3125,
238
+ "learning_rate": 9.998494395043366e-07,
239
+ "loss": 95.4775,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.07942301515461209,
244
+ "grad_norm": 51.65625,
245
+ "learning_rate": 9.99844877065074e-07,
246
+ "loss": 94.9841,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.08175898618857126,
251
+ "grad_norm": 55.5,
252
+ "learning_rate": 9.998403146258115e-07,
253
+ "loss": 94.7989,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.08409495722253044,
258
+ "grad_norm": 51.21875,
259
+ "learning_rate": 9.998357521865489e-07,
260
+ "loss": 93.6134,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.08643092825648963,
265
+ "grad_norm": 62.40625,
266
+ "learning_rate": 9.998311897472865e-07,
267
+ "loss": 95.1199,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.0887668992904488,
272
+ "grad_norm": 48.125,
273
+ "learning_rate": 9.998266273080238e-07,
274
+ "loss": 93.7213,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.09110287032440798,
279
+ "grad_norm": 53.125,
280
+ "learning_rate": 9.998220648687614e-07,
281
+ "loss": 94.9632,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.09343884135836715,
286
+ "grad_norm": 49.96875,
287
+ "learning_rate": 9.99817502429499e-07,
288
+ "loss": 93.9266,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.09577481239232634,
293
+ "grad_norm": 49.46875,
294
+ "learning_rate": 9.998129399902363e-07,
295
+ "loss": 95.0468,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.09811078342628551,
300
+ "grad_norm": 50.59375,
301
+ "learning_rate": 9.99808377550974e-07,
302
+ "loss": 93.5313,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.10044675446024469,
307
+ "grad_norm": 54.90625,
308
+ "learning_rate": 9.998038151117113e-07,
309
+ "loss": 94.5912,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.10278272549420388,
314
+ "grad_norm": 50.96875,
315
+ "learning_rate": 9.997992526724488e-07,
316
+ "loss": 93.7903,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.10511869652816305,
321
+ "grad_norm": 52.5,
322
+ "learning_rate": 9.997946902331862e-07,
323
+ "loss": 93.5428,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.10745466756212223,
328
+ "grad_norm": 50.90625,
329
+ "learning_rate": 9.997901277939238e-07,
330
+ "loss": 94.4597,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.1097906385960814,
335
+ "grad_norm": 49.46875,
336
+ "learning_rate": 9.997855653546612e-07,
337
+ "loss": 94.1416,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.11212660963004059,
342
+ "grad_norm": 52.53125,
343
+ "learning_rate": 9.997810029153987e-07,
344
+ "loss": 93.9781,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.11446258066399977,
349
+ "grad_norm": 51.0,
350
+ "learning_rate": 9.99776440476136e-07,
351
+ "loss": 94.0498,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.11679855169795894,
356
+ "grad_norm": 50.21875,
357
+ "learning_rate": 9.997718780368737e-07,
358
+ "loss": 92.6403,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.11913452273191813,
363
+ "grad_norm": 49.03125,
364
+ "learning_rate": 9.99767315597611e-07,
365
+ "loss": 92.5467,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.1214704937658773,
370
+ "grad_norm": 54.71875,
371
+ "learning_rate": 9.997627531583486e-07,
372
+ "loss": 92.8119,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.12380646479983648,
377
+ "grad_norm": 48.40625,
378
+ "learning_rate": 9.99758190719086e-07,
379
+ "loss": 93.4688,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.12614243583379567,
384
+ "grad_norm": 53.40625,
385
+ "learning_rate": 9.997536282798235e-07,
386
+ "loss": 93.5298,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.12847840686775483,
391
+ "grad_norm": 47.96875,
392
+ "learning_rate": 9.99749065840561e-07,
393
+ "loss": 93.2207,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.13081437790171402,
398
+ "grad_norm": 56.0,
399
+ "learning_rate": 9.997445034012985e-07,
400
+ "loss": 93.1208,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.1331503489356732,
405
+ "grad_norm": 54.53125,
406
+ "learning_rate": 9.997399409620359e-07,
407
+ "loss": 92.8771,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.13548631996963237,
412
+ "grad_norm": 64.6875,
413
+ "learning_rate": 9.997353785227734e-07,
414
+ "loss": 93.5443,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.13782229100359156,
419
+ "grad_norm": 53.6875,
420
+ "learning_rate": 9.997308160835108e-07,
421
+ "loss": 92.5809,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.14015826203755075,
426
+ "grad_norm": 49.53125,
427
+ "learning_rate": 9.997262536442484e-07,
428
+ "loss": 93.1532,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.1424942330715099,
433
+ "grad_norm": 59.9375,
434
+ "learning_rate": 9.99721691204986e-07,
435
+ "loss": 92.8726,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.1448302041054691,
440
+ "grad_norm": 54.25,
441
+ "learning_rate": 9.997171287657233e-07,
442
+ "loss": 92.0574,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.14716617513942828,
447
+ "grad_norm": 52.96875,
448
+ "learning_rate": 9.997125663264607e-07,
449
+ "loss": 93.3626,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.14950214617338745,
454
+ "grad_norm": 52.875,
455
+ "learning_rate": 9.997080038871982e-07,
456
+ "loss": 92.2334,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.15183811720734663,
461
+ "grad_norm": 49.46875,
462
+ "learning_rate": 9.997034414479358e-07,
463
+ "loss": 94.0112,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.1541740882413058,
468
+ "grad_norm": 49.5,
469
+ "learning_rate": 9.996988790086732e-07,
470
+ "loss": 92.2169,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.15651005927526498,
475
+ "grad_norm": 48.84375,
476
+ "learning_rate": 9.996943165694106e-07,
477
+ "loss": 93.1208,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.15884603030922417,
482
+ "grad_norm": 47.8125,
483
+ "learning_rate": 9.996897541301481e-07,
484
+ "loss": 92.4204,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.16118200134318333,
489
+ "grad_norm": 52.1875,
490
+ "learning_rate": 9.996851916908857e-07,
491
+ "loss": 92.2801,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.16351797237714252,
496
+ "grad_norm": 51.84375,
497
+ "learning_rate": 9.99680629251623e-07,
498
+ "loss": 92.815,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.1658539434111017,
503
+ "grad_norm": 50.40625,
504
+ "learning_rate": 9.996760668123604e-07,
505
+ "loss": 93.1973,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.16818991444506087,
510
+ "grad_norm": 49.84375,
511
+ "learning_rate": 9.99671504373098e-07,
512
+ "loss": 93.101,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.17052588547902006,
517
+ "grad_norm": 50.5,
518
+ "learning_rate": 9.996669419338356e-07,
519
+ "loss": 92.027,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.17286185651297925,
524
+ "grad_norm": 47.625,
525
+ "learning_rate": 9.99662379494573e-07,
526
+ "loss": 92.048,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.1751978275469384,
531
+ "grad_norm": 58.28125,
532
+ "learning_rate": 9.996578170553103e-07,
533
+ "loss": 93.1853,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.1775337985808976,
538
+ "grad_norm": 73.875,
539
+ "learning_rate": 9.996532546160479e-07,
540
+ "loss": 91.2014,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.1798697696148568,
545
+ "grad_norm": 50.8125,
546
+ "learning_rate": 9.996486921767855e-07,
547
+ "loss": 92.475,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.18220574064881595,
552
+ "grad_norm": 50.15625,
553
+ "learning_rate": 9.996441297375228e-07,
554
+ "loss": 92.3456,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.18454171168277514,
559
+ "grad_norm": 51.3125,
560
+ "learning_rate": 9.996395672982602e-07,
561
+ "loss": 92.1092,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.1868776827167343,
566
+ "grad_norm": 53.25,
567
+ "learning_rate": 9.996350048589978e-07,
568
+ "loss": 92.2168,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.1892136537506935,
573
+ "grad_norm": 49.96875,
574
+ "learning_rate": 9.996304424197353e-07,
575
+ "loss": 91.5845,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.19154962478465268,
580
+ "grad_norm": 51.96875,
581
+ "learning_rate": 9.996258799804727e-07,
582
+ "loss": 92.4014,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.19388559581861184,
587
+ "grad_norm": 52.65625,
588
+ "learning_rate": 9.9962131754121e-07,
589
+ "loss": 91.9784,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.19622156685257103,
594
+ "grad_norm": 55.59375,
595
+ "learning_rate": 9.996167551019476e-07,
596
+ "loss": 92.1067,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.19855753788653022,
601
+ "grad_norm": 54.8125,
602
+ "learning_rate": 9.996121926626852e-07,
603
+ "loss": 92.2285,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.20089350892048938,
608
+ "grad_norm": 48.21875,
609
+ "learning_rate": 9.996076302234226e-07,
610
+ "loss": 92.6478,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.20322947995444857,
615
+ "grad_norm": 49.65625,
616
+ "learning_rate": 9.9960306778416e-07,
617
+ "loss": 91.2663,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.20556545098840776,
622
+ "grad_norm": 51.78125,
623
+ "learning_rate": 9.995985053448975e-07,
624
+ "loss": 91.9975,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.20790142202236692,
629
+ "grad_norm": 56.21875,
630
+ "learning_rate": 9.99593942905635e-07,
631
+ "loss": 91.8558,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.2102373930563261,
636
+ "grad_norm": 48.21875,
637
+ "learning_rate": 9.995893804663725e-07,
638
+ "loss": 92.5588,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.2125733640902853,
643
+ "grad_norm": 51.6875,
644
+ "learning_rate": 9.995848180271098e-07,
645
+ "loss": 91.8372,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.21490933512424445,
650
+ "grad_norm": 49.6875,
651
+ "learning_rate": 9.995802555878474e-07,
652
+ "loss": 91.0599,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.21724530615820364,
657
+ "grad_norm": 51.09375,
658
+ "learning_rate": 9.99575693148585e-07,
659
+ "loss": 92.0935,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.2195812771921628,
664
+ "grad_norm": 51.0,
665
+ "learning_rate": 9.995711307093223e-07,
666
+ "loss": 92.2526,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.221917248226122,
671
+ "grad_norm": 55.09375,
672
+ "learning_rate": 9.995665682700597e-07,
673
+ "loss": 91.4987,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.22425321926008118,
678
+ "grad_norm": 48.875,
679
+ "learning_rate": 9.995620058307973e-07,
680
+ "loss": 91.7583,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.22658919029404034,
685
+ "grad_norm": 54.28125,
686
+ "learning_rate": 9.995574433915349e-07,
687
+ "loss": 92.9723,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.22892516132799953,
692
+ "grad_norm": 47.375,
693
+ "learning_rate": 9.995528809522722e-07,
694
+ "loss": 91.1949,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.23126113236195872,
699
+ "grad_norm": 48.1875,
700
+ "learning_rate": 9.995483185130098e-07,
701
+ "loss": 91.6117,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.23359710339591788,
706
+ "grad_norm": 49.1875,
707
+ "learning_rate": 9.995437560737472e-07,
708
+ "loss": 91.0056,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.23593307442987707,
713
+ "grad_norm": 51.46875,
714
+ "learning_rate": 9.995391936344847e-07,
715
+ "loss": 91.9323,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.23826904546383626,
720
+ "grad_norm": 47.875,
721
+ "learning_rate": 9.995346311952221e-07,
722
+ "loss": 91.1979,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.24060501649779542,
727
+ "grad_norm": 48.90625,
728
+ "learning_rate": 9.995300687559597e-07,
729
+ "loss": 91.2106,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.2429409875317546,
734
+ "grad_norm": 48.5,
735
+ "learning_rate": 9.99525506316697e-07,
736
+ "loss": 90.451,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.2452769585657138,
741
+ "grad_norm": 47.8125,
742
+ "learning_rate": 9.995209438774346e-07,
743
+ "loss": 90.8564,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.24761292959967296,
748
+ "grad_norm": 48.4375,
749
+ "learning_rate": 9.99516381438172e-07,
750
+ "loss": 91.9894,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.24994890063363215,
755
+ "grad_norm": 51.5,
756
+ "learning_rate": 9.995118189989096e-07,
757
+ "loss": 90.8876,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.25228487166759134,
762
+ "grad_norm": 48.34375,
763
+ "learning_rate": 9.99507256559647e-07,
764
+ "loss": 89.8074,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.2546208427015505,
769
+ "grad_norm": 49.71875,
770
+ "learning_rate": 9.995026941203845e-07,
771
+ "loss": 90.9951,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.25695681373550966,
776
+ "grad_norm": 48.25,
777
+ "learning_rate": 9.994981316811219e-07,
778
+ "loss": 91.1307,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.2592927847694689,
783
+ "grad_norm": 51.96875,
784
+ "learning_rate": 9.994935692418594e-07,
785
+ "loss": 90.8755,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.26162875580342804,
790
+ "grad_norm": 52.0625,
791
+ "learning_rate": 9.994890068025968e-07,
792
+ "loss": 90.3661,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.2639647268373872,
797
+ "grad_norm": 50.0625,
798
+ "learning_rate": 9.994844443633344e-07,
799
+ "loss": 91.0299,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.2663006978713464,
804
+ "grad_norm": 48.40625,
805
+ "learning_rate": 9.994798819240718e-07,
806
+ "loss": 90.4072,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.2686366689053056,
811
+ "grad_norm": 48.21875,
812
+ "learning_rate": 9.994753194848093e-07,
813
+ "loss": 90.3286,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.27097263993926474,
818
+ "grad_norm": 47.375,
819
+ "learning_rate": 9.994707570455467e-07,
820
+ "loss": 89.8693,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.27330861097322395,
825
+ "grad_norm": 47.71875,
826
+ "learning_rate": 9.994661946062843e-07,
827
+ "loss": 90.2988,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.2756445820071831,
832
+ "grad_norm": 48.375,
833
+ "learning_rate": 9.994616321670216e-07,
834
+ "loss": 90.7299,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.2779805530411423,
839
+ "grad_norm": 48.03125,
840
+ "learning_rate": 9.994570697277592e-07,
841
+ "loss": 90.5661,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.2803165240751015,
846
+ "grad_norm": 50.875,
847
+ "learning_rate": 9.994525072884968e-07,
848
+ "loss": 91.3686,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.28265249510906065,
853
+ "grad_norm": 56.40625,
854
+ "learning_rate": 9.994479448492341e-07,
855
+ "loss": 90.5123,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.2849884661430198,
860
+ "grad_norm": 47.75,
861
+ "learning_rate": 9.994433824099715e-07,
862
+ "loss": 90.0628,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.28732443717697903,
867
+ "grad_norm": 48.59375,
868
+ "learning_rate": 9.99438819970709e-07,
869
+ "loss": 91.5217,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.2896604082109382,
874
+ "grad_norm": 50.375,
875
+ "learning_rate": 9.994342575314467e-07,
876
+ "loss": 91.552,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.29199637924489735,
881
+ "grad_norm": 46.34375,
882
+ "learning_rate": 9.99429695092184e-07,
883
+ "loss": 90.1196,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.29433235027885657,
888
+ "grad_norm": 51.28125,
889
+ "learning_rate": 9.994251326529216e-07,
890
+ "loss": 90.6674,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.29666832131281573,
895
+ "grad_norm": 47.46875,
896
+ "learning_rate": 9.99420570213659e-07,
897
+ "loss": 90.2552,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.2990042923467749,
902
+ "grad_norm": 47.1875,
903
+ "learning_rate": 9.994160077743965e-07,
904
+ "loss": 89.4563,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.30134026338073405,
909
+ "grad_norm": 48.375,
910
+ "learning_rate": 9.99411445335134e-07,
911
+ "loss": 89.6932,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.30367623441469327,
916
+ "grad_norm": 49.65625,
917
+ "learning_rate": 9.994068828958715e-07,
918
+ "loss": 90.6541,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.30601220544865243,
923
+ "grad_norm": 47.4375,
924
+ "learning_rate": 9.994023204566088e-07,
925
+ "loss": 90.2363,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.3083481764826116,
930
+ "grad_norm": 47.59375,
931
+ "learning_rate": 9.993977580173464e-07,
932
+ "loss": 89.9082,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.3106841475165708,
937
+ "grad_norm": 49.9375,
938
+ "learning_rate": 9.993931955780838e-07,
939
+ "loss": 90.5597,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.31302011855052997,
944
+ "grad_norm": 47.09375,
945
+ "learning_rate": 9.993886331388214e-07,
946
+ "loss": 89.9793,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.31535608958448913,
951
+ "grad_norm": 46.1875,
952
+ "learning_rate": 9.993840706995587e-07,
953
+ "loss": 89.6057,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.31769206061844835,
958
+ "grad_norm": 48.375,
959
+ "learning_rate": 9.993795082602963e-07,
960
+ "loss": 90.4494,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.3200280316524075,
965
+ "grad_norm": 47.84375,
966
+ "learning_rate": 9.993749458210337e-07,
967
+ "loss": 89.3954,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.32236400268636667,
972
+ "grad_norm": 51.5,
973
+ "learning_rate": 9.993703833817712e-07,
974
+ "loss": 88.9873,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.3246999737203259,
979
+ "grad_norm": 49.375,
980
+ "learning_rate": 9.993658209425086e-07,
981
+ "loss": 89.7105,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.32703594475428505,
986
+ "grad_norm": 48.21875,
987
+ "learning_rate": 9.993612585032462e-07,
988
+ "loss": 90.0021,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.3293719157882442,
993
+ "grad_norm": 48.75,
994
+ "learning_rate": 9.993566960639835e-07,
995
+ "loss": 90.7298,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.3317078868222034,
1000
+ "grad_norm": 48.0625,
1001
+ "learning_rate": 9.993521336247211e-07,
1002
+ "loss": 89.614,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.3340438578561626,
1007
+ "grad_norm": 47.6875,
1008
+ "learning_rate": 9.993475711854585e-07,
1009
+ "loss": 90.2349,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.33637982889012175,
1014
+ "grad_norm": 47.6875,
1015
+ "learning_rate": 9.99343008746196e-07,
1016
+ "loss": 89.0322,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.33871579992408096,
1021
+ "grad_norm": 52.875,
1022
+ "learning_rate": 9.993384463069336e-07,
1023
+ "loss": 91.0856,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.3410517709580401,
1028
+ "grad_norm": 45.84375,
1029
+ "learning_rate": 9.99333883867671e-07,
1030
+ "loss": 89.7295,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.3433877419919993,
1035
+ "grad_norm": 47.875,
1036
+ "learning_rate": 9.993293214284084e-07,
1037
+ "loss": 89.7628,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.3457237130259585,
1042
+ "grad_norm": 50.71875,
1043
+ "learning_rate": 9.99324758989146e-07,
1044
+ "loss": 89.6516,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.34805968405991766,
1049
+ "grad_norm": 49.5625,
1050
+ "learning_rate": 9.993201965498835e-07,
1051
+ "loss": 89.7199,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.3503956550938768,
1056
+ "grad_norm": 44.96875,
1057
+ "learning_rate": 9.993156341106209e-07,
1058
+ "loss": 89.6713,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.35273162612783604,
1063
+ "grad_norm": 49.03125,
1064
+ "learning_rate": 9.993110716713582e-07,
1065
+ "loss": 89.7211,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.3550675971617952,
1070
+ "grad_norm": 46.65625,
1071
+ "learning_rate": 9.993065092320958e-07,
1072
+ "loss": 89.7591,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.35740356819575436,
1077
+ "grad_norm": 46.40625,
1078
+ "learning_rate": 9.993019467928334e-07,
1079
+ "loss": 89.5946,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.3597395392297136,
1084
+ "grad_norm": 47.46875,
1085
+ "learning_rate": 9.992973843535708e-07,
1086
+ "loss": 89.3533,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.36207551026367274,
1091
+ "grad_norm": 66.75,
1092
+ "learning_rate": 9.992928219143081e-07,
1093
+ "loss": 88.915,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.3644114812976319,
1098
+ "grad_norm": 49.625,
1099
+ "learning_rate": 9.992882594750457e-07,
1100
+ "loss": 89.5318,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.36674745233159106,
1105
+ "grad_norm": 52.5,
1106
+ "learning_rate": 9.992836970357833e-07,
1107
+ "loss": 89.6842,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.3690834233655503,
1112
+ "grad_norm": 47.65625,
1113
+ "learning_rate": 9.992791345965206e-07,
1114
+ "loss": 89.9355,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.37141939439950944,
1119
+ "grad_norm": 47.34375,
1120
+ "learning_rate": 9.99274572157258e-07,
1121
+ "loss": 89.0862,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.3737553654334686,
1126
+ "grad_norm": 47.0,
1127
+ "learning_rate": 9.992700097179956e-07,
1128
+ "loss": 89.5908,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.3760913364674278,
1133
+ "grad_norm": 48.40625,
1134
+ "learning_rate": 9.992654472787332e-07,
1135
+ "loss": 90.0093,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.378427307501387,
1140
+ "grad_norm": 46.90625,
1141
+ "learning_rate": 9.992608848394705e-07,
1142
+ "loss": 89.8005,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.38076327853534614,
1147
+ "grad_norm": 46.53125,
1148
+ "learning_rate": 9.992563224002079e-07,
1149
+ "loss": 89.5087,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.38309924956930536,
1154
+ "grad_norm": 46.6875,
1155
+ "learning_rate": 9.992517599609455e-07,
1156
+ "loss": 89.3029,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.3854352206032645,
1161
+ "grad_norm": 48.0,
1162
+ "learning_rate": 9.99247197521683e-07,
1163
+ "loss": 89.3145,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.3877711916372237,
1168
+ "grad_norm": 47.5625,
1169
+ "learning_rate": 9.992426350824204e-07,
1170
+ "loss": 88.9554,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.3901071626711829,
1175
+ "grad_norm": 50.25,
1176
+ "learning_rate": 9.992380726431578e-07,
1177
+ "loss": 89.8971,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.39244313370514206,
1182
+ "grad_norm": 49.1875,
1183
+ "learning_rate": 9.992335102038953e-07,
1184
+ "loss": 88.8999,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 0.3947791047391012,
1189
+ "grad_norm": 47.6875,
1190
+ "learning_rate": 9.99228947764633e-07,
1191
+ "loss": 90.1073,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 0.39711507577306043,
1196
+ "grad_norm": 48.375,
1197
+ "learning_rate": 9.992243853253703e-07,
1198
+ "loss": 89.0198,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 0.3994510468070196,
1203
+ "grad_norm": 49.9375,
1204
+ "learning_rate": 9.992198228861076e-07,
1205
+ "loss": 89.9081,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 0.40178701784097876,
1210
+ "grad_norm": 48.6875,
1211
+ "learning_rate": 9.992152604468452e-07,
1212
+ "loss": 89.2711,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 0.40412298887493797,
1217
+ "grad_norm": 46.34375,
1218
+ "learning_rate": 9.992106980075828e-07,
1219
+ "loss": 89.0298,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 0.40645895990889713,
1224
+ "grad_norm": 46.65625,
1225
+ "learning_rate": 9.992061355683202e-07,
1226
+ "loss": 89.1033,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 0.4087949309428563,
1231
+ "grad_norm": 47.9375,
1232
+ "learning_rate": 9.992015731290577e-07,
1233
+ "loss": 89.7967,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 0.4111309019768155,
1238
+ "grad_norm": 47.53125,
1239
+ "learning_rate": 9.99197010689795e-07,
1240
+ "loss": 87.6053,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 0.41346687301077467,
1245
+ "grad_norm": 46.6875,
1246
+ "learning_rate": 9.991924482505327e-07,
1247
+ "loss": 89.5975,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 0.41580284404473383,
1252
+ "grad_norm": 50.90625,
1253
+ "learning_rate": 9.9918788581127e-07,
1254
+ "loss": 88.9577,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 0.41813881507869305,
1259
+ "grad_norm": 49.125,
1260
+ "learning_rate": 9.991833233720076e-07,
1261
+ "loss": 88.7783,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 0.4204747861126522,
1266
+ "grad_norm": 47.9375,
1267
+ "learning_rate": 9.99178760932745e-07,
1268
+ "loss": 89.6563,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 0.42281075714661137,
1273
+ "grad_norm": 46.90625,
1274
+ "learning_rate": 9.991741984934826e-07,
1275
+ "loss": 88.626,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 0.4251467281805706,
1280
+ "grad_norm": 46.71875,
1281
+ "learning_rate": 9.9916963605422e-07,
1282
+ "loss": 87.7213,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 0.42748269921452975,
1287
+ "grad_norm": 49.40625,
1288
+ "learning_rate": 9.991650736149575e-07,
1289
+ "loss": 88.2201,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 0.4298186702484889,
1294
+ "grad_norm": 46.40625,
1295
+ "learning_rate": 9.991605111756949e-07,
1296
+ "loss": 89.3786,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 0.43215464128244807,
1301
+ "grad_norm": 48.125,
1302
+ "learning_rate": 9.991559487364324e-07,
1303
+ "loss": 87.8735,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 0.4344906123164073,
1308
+ "grad_norm": 52.09375,
1309
+ "learning_rate": 9.991513862971698e-07,
1310
+ "loss": 89.6088,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 0.43682658335036645,
1315
+ "grad_norm": 48.875,
1316
+ "learning_rate": 9.991468238579074e-07,
1317
+ "loss": 88.5974,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 0.4391625543843256,
1322
+ "grad_norm": 46.3125,
1323
+ "learning_rate": 9.991422614186447e-07,
1324
+ "loss": 89.1903,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 0.4414985254182848,
1329
+ "grad_norm": 45.1875,
1330
+ "learning_rate": 9.991376989793823e-07,
1331
+ "loss": 88.6345,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 0.443834496452244,
1336
+ "grad_norm": 45.375,
1337
+ "learning_rate": 9.991331365401197e-07,
1338
+ "loss": 88.6808,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 0.44617046748620315,
1343
+ "grad_norm": 45.6875,
1344
+ "learning_rate": 9.991285741008573e-07,
1345
+ "loss": 88.9256,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 0.44850643852016236,
1350
+ "grad_norm": 45.53125,
1351
+ "learning_rate": 9.991240116615946e-07,
1352
+ "loss": 88.0677,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 0.4508424095541215,
1357
+ "grad_norm": 47.15625,
1358
+ "learning_rate": 9.991194492223322e-07,
1359
+ "loss": 89.2818,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 0.4531783805880807,
1364
+ "grad_norm": 46.28125,
1365
+ "learning_rate": 9.991148867830696e-07,
1366
+ "loss": 88.0857,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 0.4555143516220399,
1371
+ "grad_norm": 48.78125,
1372
+ "learning_rate": 9.991103243438071e-07,
1373
+ "loss": 89.0477,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 0.45785032265599906,
1378
+ "grad_norm": 48.90625,
1379
+ "learning_rate": 9.991057619045447e-07,
1380
+ "loss": 89.073,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 0.4601862936899582,
1385
+ "grad_norm": 48.25,
1386
+ "learning_rate": 9.99101199465282e-07,
1387
+ "loss": 89.1609,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 0.46252226472391744,
1392
+ "grad_norm": 52.0625,
1393
+ "learning_rate": 9.990966370260194e-07,
1394
+ "loss": 89.7074,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 0.4648582357578766,
1399
+ "grad_norm": 47.84375,
1400
+ "learning_rate": 9.99092074586757e-07,
1401
+ "loss": 88.3551,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 0.46719420679183576,
1406
+ "grad_norm": 45.875,
1407
+ "learning_rate": 9.990875121474946e-07,
1408
+ "loss": 89.2271,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 0.46719420679183576,
1413
+ "eval_loss": 1.3847792148590088,
1414
+ "eval_runtime": 136.4587,
1415
+ "eval_samples_per_second": 1647.4,
1416
+ "eval_steps_per_second": 51.488,
1417
+ "step": 2000
1418
+ }
1419
+ ],
1420
+ "logging_steps": 10,
1421
+ "max_steps": 4280,
1422
+ "num_input_tokens_seen": 0,
1423
+ "num_train_epochs": 1,
1424
+ "save_steps": 2000,
1425
+ "stateful_callbacks": {
1426
+ "TrainerControl": {
1427
+ "args": {
1428
+ "should_epoch_stop": false,
1429
+ "should_evaluate": false,
1430
+ "should_log": false,
1431
+ "should_save": true,
1432
+ "should_training_stop": false
1433
+ },
1434
+ "attributes": {}
1435
+ }
1436
+ },
1437
+ "total_flos": 5.52223315549225e+18,
1438
+ "train_batch_size": 4,
1439
+ "trial_name": null,
1440
+ "trial_params": null
1441
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219d75558cf31b305bec6127377b7946c8cc5684d3fae8d7eba3f7a0494a0290
3
+ size 5368