CocoRoF commited on
Commit
ae6364d
·
verified ·
1 Parent(s): 07af1ce

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CocoRoF/KoModernBERT-large-mlm-v3",
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:c71a7729ac4a2d1a47e86393840dc65c758773a0098e1237ae0e7077cfb8ae0e
3
+ size 791869518
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f7191baea0d93efcc055c1b3e98f679be63211ee15b418d2aa66ffeebc8979e
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 sha256:74386f26f36ed67f56395205881e5db2d0c28ffcbeed50dd95b28771d2dac588
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 sha256:41c88f9de084200454883a13c3717941ea3fd433e2f8735507fc30611f9c5501
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 sha256:965b00d4cb4710ebab57c8787b9925bb3f77b8eeba94a186ec4bc1c2f326ef3f
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:d5dc374b8b9a4c45c950f9d136feab85a767081fa59f0c7d68ed3a62060c4949
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 sha256:5c7c212fb779217f1edac0baf44f67b608eefc1e0e4e3f5a9dd7eb557032c1bc
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 sha256:86e1effd626ce1e95dd68a0c8089fe19218f2b24dfe9e45ed2cab1c0ebc10ba1
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 sha256:799cc83f60dfc1c4243cfd6403592112414a2eec494e6832f10221c96ff62c20
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 sha256:586777c398770c3255d3a1f48c7fef44ea9d89117c627c9ea490e16bfd9a49ba
3
+ size 15984
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74977310703748551c5dc1da92b0842afc2c410245fb89bf45d068c870d5fe6
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 +1,1449 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.2815860333327467,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0014079301666637335,
13
+ "grad_norm": 114.625,
14
+ "learning_rate": 2.8089887640449436e-08,
15
+ "loss": 85.8853,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.002815860333327467,
20
+ "grad_norm": 111.6875,
21
+ "learning_rate": 5.617977528089887e-08,
22
+ "loss": 85.9658,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.0042237904999912,
27
+ "grad_norm": 112.0625,
28
+ "learning_rate": 8.426966292134831e-08,
29
+ "loss": 84.4067,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.005631720666654934,
34
+ "grad_norm": 114.375,
35
+ "learning_rate": 1.1235955056179774e-07,
36
+ "loss": 85.7776,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.007039650833318667,
41
+ "grad_norm": 110.25,
42
+ "learning_rate": 1.4044943820224718e-07,
43
+ "loss": 83.5889,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.0084475809999824,
48
+ "grad_norm": 112.375,
49
+ "learning_rate": 1.6853932584269663e-07,
50
+ "loss": 84.3387,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.009855511166646135,
55
+ "grad_norm": 109.5625,
56
+ "learning_rate": 1.9662921348314607e-07,
57
+ "loss": 84.4387,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.011263441333309868,
62
+ "grad_norm": 114.8125,
63
+ "learning_rate": 2.2471910112359549e-07,
64
+ "loss": 83.7717,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.012671371499973601,
69
+ "grad_norm": 110.875,
70
+ "learning_rate": 2.5280898876404493e-07,
71
+ "loss": 83.5306,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.014079301666637335,
76
+ "grad_norm": 106.3125,
77
+ "learning_rate": 2.8089887640449437e-07,
78
+ "loss": 83.6832,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.015487231833301068,
83
+ "grad_norm": 112.25,
84
+ "learning_rate": 3.0898876404494376e-07,
85
+ "loss": 83.6929,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.0168951619999648,
90
+ "grad_norm": 111.8125,
91
+ "learning_rate": 3.3707865168539325e-07,
92
+ "loss": 84.1018,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.018303092166628534,
97
+ "grad_norm": 109.3125,
98
+ "learning_rate": 3.651685393258427e-07,
99
+ "loss": 84.1149,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.01971102233329227,
104
+ "grad_norm": 109.875,
105
+ "learning_rate": 3.9325842696629214e-07,
106
+ "loss": 82.8841,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.021118952499956004,
111
+ "grad_norm": 107.9375,
112
+ "learning_rate": 4.2134831460674153e-07,
113
+ "loss": 84.9085,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.022526882666619737,
118
+ "grad_norm": 113.875,
119
+ "learning_rate": 4.4943820224719097e-07,
120
+ "loss": 83.177,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.02393481283328347,
125
+ "grad_norm": 112.5625,
126
+ "learning_rate": 4.775280898876405e-07,
127
+ "loss": 84.905,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.025342742999947203,
132
+ "grad_norm": 111.125,
133
+ "learning_rate": 5.056179775280899e-07,
134
+ "loss": 83.7053,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.026750673166610936,
139
+ "grad_norm": 110.3125,
140
+ "learning_rate": 5.337078651685392e-07,
141
+ "loss": 84.249,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 0.02815860333327467,
146
+ "grad_norm": 115.0,
147
+ "learning_rate": 5.617977528089887e-07,
148
+ "loss": 83.1926,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 0.029566533499938402,
153
+ "grad_norm": 113.25,
154
+ "learning_rate": 5.898876404494381e-07,
155
+ "loss": 84.164,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 0.030974463666602135,
160
+ "grad_norm": 112.9375,
161
+ "learning_rate": 6.179775280898875e-07,
162
+ "loss": 83.7127,
163
+ "step": 110
164
+ },
165
+ {
166
+ "epoch": 0.03238239383326587,
167
+ "grad_norm": 114.5,
168
+ "learning_rate": 6.460674157303371e-07,
169
+ "loss": 85.8182,
170
+ "step": 115
171
+ },
172
+ {
173
+ "epoch": 0.0337903239999296,
174
+ "grad_norm": 114.125,
175
+ "learning_rate": 6.741573033707865e-07,
176
+ "loss": 86.1688,
177
+ "step": 120
178
+ },
179
+ {
180
+ "epoch": 0.035198254166593335,
181
+ "grad_norm": 108.6875,
182
+ "learning_rate": 7.02247191011236e-07,
183
+ "loss": 83.0914,
184
+ "step": 125
185
+ },
186
+ {
187
+ "epoch": 0.03660618433325707,
188
+ "grad_norm": 109.75,
189
+ "learning_rate": 7.303370786516854e-07,
190
+ "loss": 86.4069,
191
+ "step": 130
192
+ },
193
+ {
194
+ "epoch": 0.0380141144999208,
195
+ "grad_norm": 111.8125,
196
+ "learning_rate": 7.584269662921348e-07,
197
+ "loss": 85.471,
198
+ "step": 135
199
+ },
200
+ {
201
+ "epoch": 0.03942204466658454,
202
+ "grad_norm": 109.75,
203
+ "learning_rate": 7.865168539325843e-07,
204
+ "loss": 84.2073,
205
+ "step": 140
206
+ },
207
+ {
208
+ "epoch": 0.040829974833248274,
209
+ "grad_norm": 112.6875,
210
+ "learning_rate": 8.146067415730337e-07,
211
+ "loss": 85.0642,
212
+ "step": 145
213
+ },
214
+ {
215
+ "epoch": 0.04223790499991201,
216
+ "grad_norm": 112.5,
217
+ "learning_rate": 8.426966292134831e-07,
218
+ "loss": 86.0327,
219
+ "step": 150
220
+ },
221
+ {
222
+ "epoch": 0.04364583516657574,
223
+ "grad_norm": 111.625,
224
+ "learning_rate": 8.707865168539326e-07,
225
+ "loss": 86.5769,
226
+ "step": 155
227
+ },
228
+ {
229
+ "epoch": 0.04505376533323947,
230
+ "grad_norm": 110.1875,
231
+ "learning_rate": 8.988764044943819e-07,
232
+ "loss": 87.2292,
233
+ "step": 160
234
+ },
235
+ {
236
+ "epoch": 0.046461695499903206,
237
+ "grad_norm": 108.4375,
238
+ "learning_rate": 9.269662921348314e-07,
239
+ "loss": 87.8398,
240
+ "step": 165
241
+ },
242
+ {
243
+ "epoch": 0.04786962566656694,
244
+ "grad_norm": 107.5,
245
+ "learning_rate": 9.55056179775281e-07,
246
+ "loss": 87.6348,
247
+ "step": 170
248
+ },
249
+ {
250
+ "epoch": 0.04927755583323067,
251
+ "grad_norm": 115.625,
252
+ "learning_rate": 9.831460674157302e-07,
253
+ "loss": 87.7073,
254
+ "step": 175
255
+ },
256
+ {
257
+ "epoch": 0.050685485999894406,
258
+ "grad_norm": 115.125,
259
+ "learning_rate": 1.0112359550561797e-06,
260
+ "loss": 86.4599,
261
+ "step": 180
262
+ },
263
+ {
264
+ "epoch": 0.05209341616655814,
265
+ "grad_norm": 109.625,
266
+ "learning_rate": 1.0393258426966292e-06,
267
+ "loss": 85.6867,
268
+ "step": 185
269
+ },
270
+ {
271
+ "epoch": 0.05350134633322187,
272
+ "grad_norm": 111.1875,
273
+ "learning_rate": 1.0674157303370785e-06,
274
+ "loss": 88.4886,
275
+ "step": 190
276
+ },
277
+ {
278
+ "epoch": 0.054909276499885605,
279
+ "grad_norm": 113.6875,
280
+ "learning_rate": 1.095505617977528e-06,
281
+ "loss": 89.7883,
282
+ "step": 195
283
+ },
284
+ {
285
+ "epoch": 0.05631720666654934,
286
+ "grad_norm": 112.1875,
287
+ "learning_rate": 1.1235955056179775e-06,
288
+ "loss": 86.8666,
289
+ "step": 200
290
+ },
291
+ {
292
+ "epoch": 0.05772513683321307,
293
+ "grad_norm": 113.875,
294
+ "learning_rate": 1.151685393258427e-06,
295
+ "loss": 88.1594,
296
+ "step": 205
297
+ },
298
+ {
299
+ "epoch": 0.059133066999876804,
300
+ "grad_norm": 112.5625,
301
+ "learning_rate": 1.1797752808988763e-06,
302
+ "loss": 87.9299,
303
+ "step": 210
304
+ },
305
+ {
306
+ "epoch": 0.06054099716654054,
307
+ "grad_norm": 111.1875,
308
+ "learning_rate": 1.2078651685393258e-06,
309
+ "loss": 88.8051,
310
+ "step": 215
311
+ },
312
+ {
313
+ "epoch": 0.06194892733320427,
314
+ "grad_norm": 108.125,
315
+ "learning_rate": 1.235955056179775e-06,
316
+ "loss": 86.5864,
317
+ "step": 220
318
+ },
319
+ {
320
+ "epoch": 0.06335685749986801,
321
+ "grad_norm": 115.5625,
322
+ "learning_rate": 1.2640449438202247e-06,
323
+ "loss": 89.1844,
324
+ "step": 225
325
+ },
326
+ {
327
+ "epoch": 0.06476478766653174,
328
+ "grad_norm": 112.875,
329
+ "learning_rate": 1.2921348314606742e-06,
330
+ "loss": 89.5238,
331
+ "step": 230
332
+ },
333
+ {
334
+ "epoch": 0.06617271783319548,
335
+ "grad_norm": 111.1875,
336
+ "learning_rate": 1.3202247191011235e-06,
337
+ "loss": 89.9019,
338
+ "step": 235
339
+ },
340
+ {
341
+ "epoch": 0.0675806479998592,
342
+ "grad_norm": 114.0625,
343
+ "learning_rate": 1.348314606741573e-06,
344
+ "loss": 89.5135,
345
+ "step": 240
346
+ },
347
+ {
348
+ "epoch": 0.06898857816652294,
349
+ "grad_norm": 111.9375,
350
+ "learning_rate": 1.3764044943820223e-06,
351
+ "loss": 89.6118,
352
+ "step": 245
353
+ },
354
+ {
355
+ "epoch": 0.07039650833318667,
356
+ "grad_norm": 113.875,
357
+ "learning_rate": 1.404494382022472e-06,
358
+ "loss": 89.3294,
359
+ "step": 250
360
+ },
361
+ {
362
+ "epoch": 0.07180443849985041,
363
+ "grad_norm": 108.6875,
364
+ "learning_rate": 1.4325842696629213e-06,
365
+ "loss": 91.4349,
366
+ "step": 255
367
+ },
368
+ {
369
+ "epoch": 0.07321236866651414,
370
+ "grad_norm": 115.125,
371
+ "learning_rate": 1.4606741573033708e-06,
372
+ "loss": 89.6878,
373
+ "step": 260
374
+ },
375
+ {
376
+ "epoch": 0.07462029883317788,
377
+ "grad_norm": 111.3125,
378
+ "learning_rate": 1.48876404494382e-06,
379
+ "loss": 91.3542,
380
+ "step": 265
381
+ },
382
+ {
383
+ "epoch": 0.0760282289998416,
384
+ "grad_norm": 114.0625,
385
+ "learning_rate": 1.5168539325842696e-06,
386
+ "loss": 90.9409,
387
+ "step": 270
388
+ },
389
+ {
390
+ "epoch": 0.07743615916650534,
391
+ "grad_norm": 110.875,
392
+ "learning_rate": 1.544943820224719e-06,
393
+ "loss": 91.2244,
394
+ "step": 275
395
+ },
396
+ {
397
+ "epoch": 0.07884408933316908,
398
+ "grad_norm": 114.125,
399
+ "learning_rate": 1.5730337078651686e-06,
400
+ "loss": 90.888,
401
+ "step": 280
402
+ },
403
+ {
404
+ "epoch": 0.08025201949983281,
405
+ "grad_norm": 113.4375,
406
+ "learning_rate": 1.6011235955056178e-06,
407
+ "loss": 91.2134,
408
+ "step": 285
409
+ },
410
+ {
411
+ "epoch": 0.08165994966649655,
412
+ "grad_norm": 108.375,
413
+ "learning_rate": 1.6292134831460673e-06,
414
+ "loss": 91.87,
415
+ "step": 290
416
+ },
417
+ {
418
+ "epoch": 0.08306787983316027,
419
+ "grad_norm": 108.6875,
420
+ "learning_rate": 1.6573033707865166e-06,
421
+ "loss": 91.9418,
422
+ "step": 295
423
+ },
424
+ {
425
+ "epoch": 0.08447580999982401,
426
+ "grad_norm": 108.1875,
427
+ "learning_rate": 1.6853932584269661e-06,
428
+ "loss": 91.6362,
429
+ "step": 300
430
+ },
431
+ {
432
+ "epoch": 0.08588374016648774,
433
+ "grad_norm": 114.9375,
434
+ "learning_rate": 1.7134831460674158e-06,
435
+ "loss": 92.6335,
436
+ "step": 305
437
+ },
438
+ {
439
+ "epoch": 0.08729167033315148,
440
+ "grad_norm": 107.1875,
441
+ "learning_rate": 1.741573033707865e-06,
442
+ "loss": 92.5334,
443
+ "step": 310
444
+ },
445
+ {
446
+ "epoch": 0.0886996004998152,
447
+ "grad_norm": 114.6875,
448
+ "learning_rate": 1.7696629213483146e-06,
449
+ "loss": 91.7963,
450
+ "step": 315
451
+ },
452
+ {
453
+ "epoch": 0.09010753066647895,
454
+ "grad_norm": 109.1875,
455
+ "learning_rate": 1.7977528089887639e-06,
456
+ "loss": 92.5923,
457
+ "step": 320
458
+ },
459
+ {
460
+ "epoch": 0.09151546083314267,
461
+ "grad_norm": 114.9375,
462
+ "learning_rate": 1.8258426966292134e-06,
463
+ "loss": 93.9665,
464
+ "step": 325
465
+ },
466
+ {
467
+ "epoch": 0.09292339099980641,
468
+ "grad_norm": 118.1875,
469
+ "learning_rate": 1.8539325842696629e-06,
470
+ "loss": 91.7156,
471
+ "step": 330
472
+ },
473
+ {
474
+ "epoch": 0.09433132116647014,
475
+ "grad_norm": 116.0,
476
+ "learning_rate": 1.8820224719101124e-06,
477
+ "loss": 94.3289,
478
+ "step": 335
479
+ },
480
+ {
481
+ "epoch": 0.09573925133313388,
482
+ "grad_norm": 116.75,
483
+ "learning_rate": 1.910112359550562e-06,
484
+ "loss": 94.187,
485
+ "step": 340
486
+ },
487
+ {
488
+ "epoch": 0.0971471814997976,
489
+ "grad_norm": 111.875,
490
+ "learning_rate": 1.938202247191011e-06,
491
+ "loss": 93.7581,
492
+ "step": 345
493
+ },
494
+ {
495
+ "epoch": 0.09855511166646135,
496
+ "grad_norm": 114.9375,
497
+ "learning_rate": 1.9662921348314604e-06,
498
+ "loss": 93.413,
499
+ "step": 350
500
+ },
501
+ {
502
+ "epoch": 0.09996304183312507,
503
+ "grad_norm": 112.625,
504
+ "learning_rate": 1.99438202247191e-06,
505
+ "loss": 94.2749,
506
+ "step": 355
507
+ },
508
+ {
509
+ "epoch": 0.10137097199978881,
510
+ "grad_norm": 107.6875,
511
+ "learning_rate": 1.9974960876369326e-06,
512
+ "loss": 94.6595,
513
+ "step": 360
514
+ },
515
+ {
516
+ "epoch": 0.10277890216645254,
517
+ "grad_norm": 115.125,
518
+ "learning_rate": 1.9943661971830985e-06,
519
+ "loss": 94.8831,
520
+ "step": 365
521
+ },
522
+ {
523
+ "epoch": 0.10418683233311628,
524
+ "grad_norm": 111.9375,
525
+ "learning_rate": 1.9912363067292643e-06,
526
+ "loss": 94.5983,
527
+ "step": 370
528
+ },
529
+ {
530
+ "epoch": 0.10559476249978002,
531
+ "grad_norm": 113.875,
532
+ "learning_rate": 1.98810641627543e-06,
533
+ "loss": 96.0132,
534
+ "step": 375
535
+ },
536
+ {
537
+ "epoch": 0.10700269266644374,
538
+ "grad_norm": 111.8125,
539
+ "learning_rate": 1.984976525821596e-06,
540
+ "loss": 96.9668,
541
+ "step": 380
542
+ },
543
+ {
544
+ "epoch": 0.10841062283310748,
545
+ "grad_norm": 109.5625,
546
+ "learning_rate": 1.981846635367762e-06,
547
+ "loss": 94.2092,
548
+ "step": 385
549
+ },
550
+ {
551
+ "epoch": 0.10981855299977121,
552
+ "grad_norm": 113.6875,
553
+ "learning_rate": 1.9787167449139278e-06,
554
+ "loss": 93.9071,
555
+ "step": 390
556
+ },
557
+ {
558
+ "epoch": 0.11122648316643495,
559
+ "grad_norm": 113.625,
560
+ "learning_rate": 1.9755868544600936e-06,
561
+ "loss": 94.9607,
562
+ "step": 395
563
+ },
564
+ {
565
+ "epoch": 0.11263441333309868,
566
+ "grad_norm": 110.75,
567
+ "learning_rate": 1.9724569640062595e-06,
568
+ "loss": 92.9988,
569
+ "step": 400
570
+ },
571
+ {
572
+ "epoch": 0.11404234349976242,
573
+ "grad_norm": 114.25,
574
+ "learning_rate": 1.9693270735524258e-06,
575
+ "loss": 95.0537,
576
+ "step": 405
577
+ },
578
+ {
579
+ "epoch": 0.11545027366642614,
580
+ "grad_norm": 110.9375,
581
+ "learning_rate": 1.9661971830985916e-06,
582
+ "loss": 94.5083,
583
+ "step": 410
584
+ },
585
+ {
586
+ "epoch": 0.11685820383308988,
587
+ "grad_norm": 113.375,
588
+ "learning_rate": 1.9630672926447575e-06,
589
+ "loss": 94.8912,
590
+ "step": 415
591
+ },
592
+ {
593
+ "epoch": 0.11826613399975361,
594
+ "grad_norm": 112.125,
595
+ "learning_rate": 1.9599374021909234e-06,
596
+ "loss": 95.3204,
597
+ "step": 420
598
+ },
599
+ {
600
+ "epoch": 0.11967406416641735,
601
+ "grad_norm": 113.625,
602
+ "learning_rate": 1.9568075117370892e-06,
603
+ "loss": 95.2065,
604
+ "step": 425
605
+ },
606
+ {
607
+ "epoch": 0.12108199433308107,
608
+ "grad_norm": 111.5625,
609
+ "learning_rate": 1.953677621283255e-06,
610
+ "loss": 94.5451,
611
+ "step": 430
612
+ },
613
+ {
614
+ "epoch": 0.12248992449974482,
615
+ "grad_norm": 108.75,
616
+ "learning_rate": 1.950547730829421e-06,
617
+ "loss": 95.1698,
618
+ "step": 435
619
+ },
620
+ {
621
+ "epoch": 0.12389785466640854,
622
+ "grad_norm": 107.9375,
623
+ "learning_rate": 1.947417840375587e-06,
624
+ "loss": 94.7059,
625
+ "step": 440
626
+ },
627
+ {
628
+ "epoch": 0.12530578483307228,
629
+ "grad_norm": 108.875,
630
+ "learning_rate": 1.9442879499217527e-06,
631
+ "loss": 94.4242,
632
+ "step": 445
633
+ },
634
+ {
635
+ "epoch": 0.12671371499973602,
636
+ "grad_norm": 110.875,
637
+ "learning_rate": 1.9411580594679185e-06,
638
+ "loss": 95.4208,
639
+ "step": 450
640
+ },
641
+ {
642
+ "epoch": 0.12812164516639973,
643
+ "grad_norm": 112.4375,
644
+ "learning_rate": 1.9380281690140844e-06,
645
+ "loss": 96.0422,
646
+ "step": 455
647
+ },
648
+ {
649
+ "epoch": 0.12952957533306347,
650
+ "grad_norm": 111.25,
651
+ "learning_rate": 1.9348982785602502e-06,
652
+ "loss": 93.9782,
653
+ "step": 460
654
+ },
655
+ {
656
+ "epoch": 0.1309375054997272,
657
+ "grad_norm": 112.4375,
658
+ "learning_rate": 1.931768388106416e-06,
659
+ "loss": 93.49,
660
+ "step": 465
661
+ },
662
+ {
663
+ "epoch": 0.13234543566639095,
664
+ "grad_norm": 111.25,
665
+ "learning_rate": 1.928638497652582e-06,
666
+ "loss": 93.6705,
667
+ "step": 470
668
+ },
669
+ {
670
+ "epoch": 0.1337533658330547,
671
+ "grad_norm": 109.75,
672
+ "learning_rate": 1.925508607198748e-06,
673
+ "loss": 94.0692,
674
+ "step": 475
675
+ },
676
+ {
677
+ "epoch": 0.1351612959997184,
678
+ "grad_norm": 106.875,
679
+ "learning_rate": 1.922378716744914e-06,
680
+ "loss": 94.4334,
681
+ "step": 480
682
+ },
683
+ {
684
+ "epoch": 0.13656922616638215,
685
+ "grad_norm": 110.4375,
686
+ "learning_rate": 1.9192488262910796e-06,
687
+ "loss": 95.9341,
688
+ "step": 485
689
+ },
690
+ {
691
+ "epoch": 0.13797715633304589,
692
+ "grad_norm": 108.5,
693
+ "learning_rate": 1.9161189358372454e-06,
694
+ "loss": 94.6785,
695
+ "step": 490
696
+ },
697
+ {
698
+ "epoch": 0.13938508649970963,
699
+ "grad_norm": 109.5,
700
+ "learning_rate": 1.9129890453834113e-06,
701
+ "loss": 95.5102,
702
+ "step": 495
703
+ },
704
+ {
705
+ "epoch": 0.14079301666637334,
706
+ "grad_norm": 110.3125,
707
+ "learning_rate": 1.909859154929577e-06,
708
+ "loss": 93.6705,
709
+ "step": 500
710
+ },
711
+ {
712
+ "epoch": 0.14079301666637334,
713
+ "eval_loss": 2.953507661819458,
714
+ "eval_runtime": 174.8095,
715
+ "eval_samples_per_second": 1094.883,
716
+ "eval_steps_per_second": 34.22,
717
+ "step": 500
718
+ },
719
+ {
720
+ "epoch": 0.14220094683303708,
721
+ "grad_norm": 116.3125,
722
+ "learning_rate": 1.9067292644757434e-06,
723
+ "loss": 93.6612,
724
+ "step": 505
725
+ },
726
+ {
727
+ "epoch": 0.14360887699970082,
728
+ "grad_norm": 107.5625,
729
+ "learning_rate": 1.9035993740219093e-06,
730
+ "loss": 93.6054,
731
+ "step": 510
732
+ },
733
+ {
734
+ "epoch": 0.14501680716636456,
735
+ "grad_norm": 107.4375,
736
+ "learning_rate": 1.900469483568075e-06,
737
+ "loss": 93.6585,
738
+ "step": 515
739
+ },
740
+ {
741
+ "epoch": 0.14642473733302827,
742
+ "grad_norm": 111.3125,
743
+ "learning_rate": 1.8973395931142408e-06,
744
+ "loss": 93.5845,
745
+ "step": 520
746
+ },
747
+ {
748
+ "epoch": 0.147832667499692,
749
+ "grad_norm": 109.8125,
750
+ "learning_rate": 1.8942097026604067e-06,
751
+ "loss": 96.1556,
752
+ "step": 525
753
+ },
754
+ {
755
+ "epoch": 0.14924059766635575,
756
+ "grad_norm": 112.3125,
757
+ "learning_rate": 1.8910798122065727e-06,
758
+ "loss": 95.0694,
759
+ "step": 530
760
+ },
761
+ {
762
+ "epoch": 0.1506485278330195,
763
+ "grad_norm": 108.0625,
764
+ "learning_rate": 1.8879499217527386e-06,
765
+ "loss": 94.7092,
766
+ "step": 535
767
+ },
768
+ {
769
+ "epoch": 0.1520564579996832,
770
+ "grad_norm": 107.0,
771
+ "learning_rate": 1.8848200312989044e-06,
772
+ "loss": 92.7553,
773
+ "step": 540
774
+ },
775
+ {
776
+ "epoch": 0.15346438816634694,
777
+ "grad_norm": 110.4375,
778
+ "learning_rate": 1.8816901408450703e-06,
779
+ "loss": 95.0633,
780
+ "step": 545
781
+ },
782
+ {
783
+ "epoch": 0.15487231833301068,
784
+ "grad_norm": 105.8125,
785
+ "learning_rate": 1.8785602503912362e-06,
786
+ "loss": 93.2634,
787
+ "step": 550
788
+ },
789
+ {
790
+ "epoch": 0.15628024849967442,
791
+ "grad_norm": 109.9375,
792
+ "learning_rate": 1.8754303599374022e-06,
793
+ "loss": 94.7607,
794
+ "step": 555
795
+ },
796
+ {
797
+ "epoch": 0.15768817866633816,
798
+ "grad_norm": 107.8125,
799
+ "learning_rate": 1.872300469483568e-06,
800
+ "loss": 94.321,
801
+ "step": 560
802
+ },
803
+ {
804
+ "epoch": 0.15909610883300188,
805
+ "grad_norm": 104.5625,
806
+ "learning_rate": 1.8691705790297338e-06,
807
+ "loss": 94.108,
808
+ "step": 565
809
+ },
810
+ {
811
+ "epoch": 0.16050403899966562,
812
+ "grad_norm": 106.25,
813
+ "learning_rate": 1.8660406885758996e-06,
814
+ "loss": 94.7094,
815
+ "step": 570
816
+ },
817
+ {
818
+ "epoch": 0.16191196916632936,
819
+ "grad_norm": 103.8125,
820
+ "learning_rate": 1.8629107981220657e-06,
821
+ "loss": 95.3564,
822
+ "step": 575
823
+ },
824
+ {
825
+ "epoch": 0.1633198993329931,
826
+ "grad_norm": 109.375,
827
+ "learning_rate": 1.8597809076682315e-06,
828
+ "loss": 94.0117,
829
+ "step": 580
830
+ },
831
+ {
832
+ "epoch": 0.1647278294996568,
833
+ "grad_norm": 111.0,
834
+ "learning_rate": 1.8566510172143974e-06,
835
+ "loss": 94.3991,
836
+ "step": 585
837
+ },
838
+ {
839
+ "epoch": 0.16613575966632055,
840
+ "grad_norm": 107.9375,
841
+ "learning_rate": 1.8535211267605633e-06,
842
+ "loss": 93.3577,
843
+ "step": 590
844
+ },
845
+ {
846
+ "epoch": 0.1675436898329843,
847
+ "grad_norm": 113.0,
848
+ "learning_rate": 1.8503912363067291e-06,
849
+ "loss": 92.6764,
850
+ "step": 595
851
+ },
852
+ {
853
+ "epoch": 0.16895161999964803,
854
+ "grad_norm": 108.875,
855
+ "learning_rate": 1.8472613458528952e-06,
856
+ "loss": 93.5743,
857
+ "step": 600
858
+ },
859
+ {
860
+ "epoch": 0.17035955016631174,
861
+ "grad_norm": 110.75,
862
+ "learning_rate": 1.844131455399061e-06,
863
+ "loss": 95.4879,
864
+ "step": 605
865
+ },
866
+ {
867
+ "epoch": 0.17176748033297548,
868
+ "grad_norm": 108.1875,
869
+ "learning_rate": 1.841001564945227e-06,
870
+ "loss": 94.0815,
871
+ "step": 610
872
+ },
873
+ {
874
+ "epoch": 0.17317541049963922,
875
+ "grad_norm": 107.6875,
876
+ "learning_rate": 1.8378716744913928e-06,
877
+ "loss": 93.5862,
878
+ "step": 615
879
+ },
880
+ {
881
+ "epoch": 0.17458334066630296,
882
+ "grad_norm": 110.6875,
883
+ "learning_rate": 1.8347417840375584e-06,
884
+ "loss": 94.7766,
885
+ "step": 620
886
+ },
887
+ {
888
+ "epoch": 0.17599127083296667,
889
+ "grad_norm": 107.75,
890
+ "learning_rate": 1.8316118935837245e-06,
891
+ "loss": 93.7132,
892
+ "step": 625
893
+ },
894
+ {
895
+ "epoch": 0.1773992009996304,
896
+ "grad_norm": 108.5,
897
+ "learning_rate": 1.8284820031298904e-06,
898
+ "loss": 95.441,
899
+ "step": 630
900
+ },
901
+ {
902
+ "epoch": 0.17880713116629415,
903
+ "grad_norm": 109.875,
904
+ "learning_rate": 1.8253521126760562e-06,
905
+ "loss": 94.4422,
906
+ "step": 635
907
+ },
908
+ {
909
+ "epoch": 0.1802150613329579,
910
+ "grad_norm": 108.9375,
911
+ "learning_rate": 1.822222222222222e-06,
912
+ "loss": 92.7065,
913
+ "step": 640
914
+ },
915
+ {
916
+ "epoch": 0.1816229914996216,
917
+ "grad_norm": 108.0,
918
+ "learning_rate": 1.819092331768388e-06,
919
+ "loss": 95.6058,
920
+ "step": 645
921
+ },
922
+ {
923
+ "epoch": 0.18303092166628535,
924
+ "grad_norm": 113.4375,
925
+ "learning_rate": 1.815962441314554e-06,
926
+ "loss": 93.1739,
927
+ "step": 650
928
+ },
929
+ {
930
+ "epoch": 0.18443885183294909,
931
+ "grad_norm": 105.375,
932
+ "learning_rate": 1.8128325508607199e-06,
933
+ "loss": 94.3629,
934
+ "step": 655
935
+ },
936
+ {
937
+ "epoch": 0.18584678199961283,
938
+ "grad_norm": 109.3125,
939
+ "learning_rate": 1.8097026604068857e-06,
940
+ "loss": 93.1163,
941
+ "step": 660
942
+ },
943
+ {
944
+ "epoch": 0.18725471216627657,
945
+ "grad_norm": 109.75,
946
+ "learning_rate": 1.8065727699530516e-06,
947
+ "loss": 91.9717,
948
+ "step": 665
949
+ },
950
+ {
951
+ "epoch": 0.18866264233294028,
952
+ "grad_norm": 107.0,
953
+ "learning_rate": 1.8034428794992173e-06,
954
+ "loss": 93.1724,
955
+ "step": 670
956
+ },
957
+ {
958
+ "epoch": 0.19007057249960402,
959
+ "grad_norm": 111.125,
960
+ "learning_rate": 1.8003129890453833e-06,
961
+ "loss": 93.8705,
962
+ "step": 675
963
+ },
964
+ {
965
+ "epoch": 0.19147850266626776,
966
+ "grad_norm": 106.6875,
967
+ "learning_rate": 1.7971830985915492e-06,
968
+ "loss": 95.3723,
969
+ "step": 680
970
+ },
971
+ {
972
+ "epoch": 0.1928864328329315,
973
+ "grad_norm": 105.75,
974
+ "learning_rate": 1.794053208137715e-06,
975
+ "loss": 94.0826,
976
+ "step": 685
977
+ },
978
+ {
979
+ "epoch": 0.1942943629995952,
980
+ "grad_norm": 108.8125,
981
+ "learning_rate": 1.790923317683881e-06,
982
+ "loss": 93.8173,
983
+ "step": 690
984
+ },
985
+ {
986
+ "epoch": 0.19570229316625895,
987
+ "grad_norm": 108.5625,
988
+ "learning_rate": 1.7877934272300468e-06,
989
+ "loss": 93.0598,
990
+ "step": 695
991
+ },
992
+ {
993
+ "epoch": 0.1971102233329227,
994
+ "grad_norm": 105.1875,
995
+ "learning_rate": 1.7846635367762128e-06,
996
+ "loss": 93.9662,
997
+ "step": 700
998
+ },
999
+ {
1000
+ "epoch": 0.19851815349958643,
1001
+ "grad_norm": 109.0625,
1002
+ "learning_rate": 1.7815336463223787e-06,
1003
+ "loss": 91.824,
1004
+ "step": 705
1005
+ },
1006
+ {
1007
+ "epoch": 0.19992608366625014,
1008
+ "grad_norm": 109.625,
1009
+ "learning_rate": 1.7784037558685446e-06,
1010
+ "loss": 93.3993,
1011
+ "step": 710
1012
+ },
1013
+ {
1014
+ "epoch": 0.20133401383291388,
1015
+ "grad_norm": 108.125,
1016
+ "learning_rate": 1.7752738654147104e-06,
1017
+ "loss": 92.4667,
1018
+ "step": 715
1019
+ },
1020
+ {
1021
+ "epoch": 0.20274194399957762,
1022
+ "grad_norm": 111.0,
1023
+ "learning_rate": 1.7721439749608763e-06,
1024
+ "loss": 92.8489,
1025
+ "step": 720
1026
+ },
1027
+ {
1028
+ "epoch": 0.20414987416624136,
1029
+ "grad_norm": 109.125,
1030
+ "learning_rate": 1.7690140845070422e-06,
1031
+ "loss": 93.2275,
1032
+ "step": 725
1033
+ },
1034
+ {
1035
+ "epoch": 0.20555780433290508,
1036
+ "grad_norm": 108.0625,
1037
+ "learning_rate": 1.765884194053208e-06,
1038
+ "loss": 92.2952,
1039
+ "step": 730
1040
+ },
1041
+ {
1042
+ "epoch": 0.20696573449956882,
1043
+ "grad_norm": 107.375,
1044
+ "learning_rate": 1.7627543035993739e-06,
1045
+ "loss": 93.8364,
1046
+ "step": 735
1047
+ },
1048
+ {
1049
+ "epoch": 0.20837366466623256,
1050
+ "grad_norm": 110.0625,
1051
+ "learning_rate": 1.7596244131455397e-06,
1052
+ "loss": 93.7801,
1053
+ "step": 740
1054
+ },
1055
+ {
1056
+ "epoch": 0.2097815948328963,
1057
+ "grad_norm": 109.8125,
1058
+ "learning_rate": 1.7564945226917056e-06,
1059
+ "loss": 93.1315,
1060
+ "step": 745
1061
+ },
1062
+ {
1063
+ "epoch": 0.21118952499956004,
1064
+ "grad_norm": 111.0625,
1065
+ "learning_rate": 1.7533646322378717e-06,
1066
+ "loss": 91.7111,
1067
+ "step": 750
1068
+ },
1069
+ {
1070
+ "epoch": 0.21259745516622375,
1071
+ "grad_norm": 108.25,
1072
+ "learning_rate": 1.7502347417840375e-06,
1073
+ "loss": 93.8666,
1074
+ "step": 755
1075
+ },
1076
+ {
1077
+ "epoch": 0.2140053853328875,
1078
+ "grad_norm": 108.875,
1079
+ "learning_rate": 1.7471048513302034e-06,
1080
+ "loss": 91.9754,
1081
+ "step": 760
1082
+ },
1083
+ {
1084
+ "epoch": 0.21541331549955123,
1085
+ "grad_norm": 108.0,
1086
+ "learning_rate": 1.7439749608763693e-06,
1087
+ "loss": 94.4781,
1088
+ "step": 765
1089
+ },
1090
+ {
1091
+ "epoch": 0.21682124566621497,
1092
+ "grad_norm": 109.1875,
1093
+ "learning_rate": 1.7408450704225351e-06,
1094
+ "loss": 92.3431,
1095
+ "step": 770
1096
+ },
1097
+ {
1098
+ "epoch": 0.21822917583287868,
1099
+ "grad_norm": 108.0625,
1100
+ "learning_rate": 1.7377151799687012e-06,
1101
+ "loss": 93.1383,
1102
+ "step": 775
1103
+ },
1104
+ {
1105
+ "epoch": 0.21963710599954242,
1106
+ "grad_norm": 107.4375,
1107
+ "learning_rate": 1.7345852895148668e-06,
1108
+ "loss": 93.4093,
1109
+ "step": 780
1110
+ },
1111
+ {
1112
+ "epoch": 0.22104503616620616,
1113
+ "grad_norm": 107.875,
1114
+ "learning_rate": 1.7314553990610327e-06,
1115
+ "loss": 93.3635,
1116
+ "step": 785
1117
+ },
1118
+ {
1119
+ "epoch": 0.2224529663328699,
1120
+ "grad_norm": 109.0625,
1121
+ "learning_rate": 1.7283255086071986e-06,
1122
+ "loss": 90.5487,
1123
+ "step": 790
1124
+ },
1125
+ {
1126
+ "epoch": 0.2238608964995336,
1127
+ "grad_norm": 105.9375,
1128
+ "learning_rate": 1.7251956181533644e-06,
1129
+ "loss": 93.1931,
1130
+ "step": 795
1131
+ },
1132
+ {
1133
+ "epoch": 0.22526882666619735,
1134
+ "grad_norm": 109.5625,
1135
+ "learning_rate": 1.7220657276995305e-06,
1136
+ "loss": 93.2803,
1137
+ "step": 800
1138
+ },
1139
+ {
1140
+ "epoch": 0.2266767568328611,
1141
+ "grad_norm": 105.75,
1142
+ "learning_rate": 1.7189358372456964e-06,
1143
+ "loss": 92.0815,
1144
+ "step": 805
1145
+ },
1146
+ {
1147
+ "epoch": 0.22808468699952483,
1148
+ "grad_norm": 106.0625,
1149
+ "learning_rate": 1.7158059467918622e-06,
1150
+ "loss": 92.8134,
1151
+ "step": 810
1152
+ },
1153
+ {
1154
+ "epoch": 0.22949261716618855,
1155
+ "grad_norm": 105.0625,
1156
+ "learning_rate": 1.712676056338028e-06,
1157
+ "loss": 91.2653,
1158
+ "step": 815
1159
+ },
1160
+ {
1161
+ "epoch": 0.23090054733285229,
1162
+ "grad_norm": 107.4375,
1163
+ "learning_rate": 1.709546165884194e-06,
1164
+ "loss": 92.2337,
1165
+ "step": 820
1166
+ },
1167
+ {
1168
+ "epoch": 0.23230847749951603,
1169
+ "grad_norm": 105.75,
1170
+ "learning_rate": 1.70641627543036e-06,
1171
+ "loss": 91.8069,
1172
+ "step": 825
1173
+ },
1174
+ {
1175
+ "epoch": 0.23371640766617977,
1176
+ "grad_norm": 112.0,
1177
+ "learning_rate": 1.7032863849765259e-06,
1178
+ "loss": 90.8042,
1179
+ "step": 830
1180
+ },
1181
+ {
1182
+ "epoch": 0.23512433783284348,
1183
+ "grad_norm": 107.25,
1184
+ "learning_rate": 1.7001564945226915e-06,
1185
+ "loss": 92.4549,
1186
+ "step": 835
1187
+ },
1188
+ {
1189
+ "epoch": 0.23653226799950722,
1190
+ "grad_norm": 104.0625,
1191
+ "learning_rate": 1.6970266040688574e-06,
1192
+ "loss": 93.1807,
1193
+ "step": 840
1194
+ },
1195
+ {
1196
+ "epoch": 0.23794019816617096,
1197
+ "grad_norm": 108.75,
1198
+ "learning_rate": 1.6938967136150232e-06,
1199
+ "loss": 92.848,
1200
+ "step": 845
1201
+ },
1202
+ {
1203
+ "epoch": 0.2393481283328347,
1204
+ "grad_norm": 110.9375,
1205
+ "learning_rate": 1.6907668231611893e-06,
1206
+ "loss": 91.5934,
1207
+ "step": 850
1208
+ },
1209
+ {
1210
+ "epoch": 0.24075605849949844,
1211
+ "grad_norm": 105.1875,
1212
+ "learning_rate": 1.6876369327073552e-06,
1213
+ "loss": 91.8347,
1214
+ "step": 855
1215
+ },
1216
+ {
1217
+ "epoch": 0.24216398866616215,
1218
+ "grad_norm": 109.6875,
1219
+ "learning_rate": 1.684507042253521e-06,
1220
+ "loss": 91.4695,
1221
+ "step": 860
1222
+ },
1223
+ {
1224
+ "epoch": 0.2435719188328259,
1225
+ "grad_norm": 108.3125,
1226
+ "learning_rate": 1.681377151799687e-06,
1227
+ "loss": 92.2532,
1228
+ "step": 865
1229
+ },
1230
+ {
1231
+ "epoch": 0.24497984899948963,
1232
+ "grad_norm": 105.9375,
1233
+ "learning_rate": 1.678247261345853e-06,
1234
+ "loss": 91.6567,
1235
+ "step": 870
1236
+ },
1237
+ {
1238
+ "epoch": 0.24638777916615337,
1239
+ "grad_norm": 107.4375,
1240
+ "learning_rate": 1.6751173708920188e-06,
1241
+ "loss": 91.7404,
1242
+ "step": 875
1243
+ },
1244
+ {
1245
+ "epoch": 0.24779570933281708,
1246
+ "grad_norm": 108.125,
1247
+ "learning_rate": 1.6719874804381847e-06,
1248
+ "loss": 91.8094,
1249
+ "step": 880
1250
+ },
1251
+ {
1252
+ "epoch": 0.24920363949948082,
1253
+ "grad_norm": 105.8125,
1254
+ "learning_rate": 1.6688575899843503e-06,
1255
+ "loss": 91.615,
1256
+ "step": 885
1257
+ },
1258
+ {
1259
+ "epoch": 0.25061156966614456,
1260
+ "grad_norm": 108.0625,
1261
+ "learning_rate": 1.6657276995305162e-06,
1262
+ "loss": 93.0504,
1263
+ "step": 890
1264
+ },
1265
+ {
1266
+ "epoch": 0.2520194998328083,
1267
+ "grad_norm": 112.375,
1268
+ "learning_rate": 1.6625978090766823e-06,
1269
+ "loss": 91.0786,
1270
+ "step": 895
1271
+ },
1272
+ {
1273
+ "epoch": 0.25342742999947204,
1274
+ "grad_norm": 107.875,
1275
+ "learning_rate": 1.6594679186228481e-06,
1276
+ "loss": 90.6298,
1277
+ "step": 900
1278
+ },
1279
+ {
1280
+ "epoch": 0.2548353601661358,
1281
+ "grad_norm": 106.1875,
1282
+ "learning_rate": 1.656338028169014e-06,
1283
+ "loss": 91.8793,
1284
+ "step": 905
1285
+ },
1286
+ {
1287
+ "epoch": 0.25624329033279947,
1288
+ "grad_norm": 110.5,
1289
+ "learning_rate": 1.6532081377151799e-06,
1290
+ "loss": 91.6597,
1291
+ "step": 910
1292
+ },
1293
+ {
1294
+ "epoch": 0.2576512204994632,
1295
+ "grad_norm": 106.125,
1296
+ "learning_rate": 1.6500782472613457e-06,
1297
+ "loss": 91.8785,
1298
+ "step": 915
1299
+ },
1300
+ {
1301
+ "epoch": 0.25905915066612695,
1302
+ "grad_norm": 106.0625,
1303
+ "learning_rate": 1.6469483568075118e-06,
1304
+ "loss": 90.6928,
1305
+ "step": 920
1306
+ },
1307
+ {
1308
+ "epoch": 0.2604670808327907,
1309
+ "grad_norm": 105.4375,
1310
+ "learning_rate": 1.6438184663536777e-06,
1311
+ "loss": 90.5155,
1312
+ "step": 925
1313
+ },
1314
+ {
1315
+ "epoch": 0.2618750109994544,
1316
+ "grad_norm": 105.4375,
1317
+ "learning_rate": 1.6406885758998435e-06,
1318
+ "loss": 91.1331,
1319
+ "step": 930
1320
+ },
1321
+ {
1322
+ "epoch": 0.26328294116611817,
1323
+ "grad_norm": 104.875,
1324
+ "learning_rate": 1.6375586854460094e-06,
1325
+ "loss": 92.0714,
1326
+ "step": 935
1327
+ },
1328
+ {
1329
+ "epoch": 0.2646908713327819,
1330
+ "grad_norm": 106.375,
1331
+ "learning_rate": 1.634428794992175e-06,
1332
+ "loss": 91.0242,
1333
+ "step": 940
1334
+ },
1335
+ {
1336
+ "epoch": 0.26609880149944565,
1337
+ "grad_norm": 108.6875,
1338
+ "learning_rate": 1.631298904538341e-06,
1339
+ "loss": 91.612,
1340
+ "step": 945
1341
+ },
1342
+ {
1343
+ "epoch": 0.2675067316661094,
1344
+ "grad_norm": 104.6875,
1345
+ "learning_rate": 1.628169014084507e-06,
1346
+ "loss": 90.1659,
1347
+ "step": 950
1348
+ },
1349
+ {
1350
+ "epoch": 0.26891466183277307,
1351
+ "grad_norm": 105.1875,
1352
+ "learning_rate": 1.6250391236306728e-06,
1353
+ "loss": 91.2171,
1354
+ "step": 955
1355
+ },
1356
+ {
1357
+ "epoch": 0.2703225919994368,
1358
+ "grad_norm": 107.375,
1359
+ "learning_rate": 1.6219092331768387e-06,
1360
+ "loss": 91.4,
1361
+ "step": 960
1362
+ },
1363
+ {
1364
+ "epoch": 0.27173052216610055,
1365
+ "grad_norm": 105.5625,
1366
+ "learning_rate": 1.6187793427230045e-06,
1367
+ "loss": 90.2747,
1368
+ "step": 965
1369
+ },
1370
+ {
1371
+ "epoch": 0.2731384523327643,
1372
+ "grad_norm": 113.0,
1373
+ "learning_rate": 1.6156494522691706e-06,
1374
+ "loss": 90.9026,
1375
+ "step": 970
1376
+ },
1377
+ {
1378
+ "epoch": 0.27454638249942803,
1379
+ "grad_norm": 108.8125,
1380
+ "learning_rate": 1.6125195618153365e-06,
1381
+ "loss": 90.2174,
1382
+ "step": 975
1383
+ },
1384
+ {
1385
+ "epoch": 0.27595431266609177,
1386
+ "grad_norm": 107.0625,
1387
+ "learning_rate": 1.6093896713615023e-06,
1388
+ "loss": 92.164,
1389
+ "step": 980
1390
+ },
1391
+ {
1392
+ "epoch": 0.2773622428327555,
1393
+ "grad_norm": 109.0,
1394
+ "learning_rate": 1.6062597809076682e-06,
1395
+ "loss": 90.952,
1396
+ "step": 985
1397
+ },
1398
+ {
1399
+ "epoch": 0.27877017299941925,
1400
+ "grad_norm": 109.3125,
1401
+ "learning_rate": 1.6031298904538339e-06,
1402
+ "loss": 91.6762,
1403
+ "step": 990
1404
+ },
1405
+ {
1406
+ "epoch": 0.28017810316608294,
1407
+ "grad_norm": 108.6875,
1408
+ "learning_rate": 1.6e-06,
1409
+ "loss": 89.3236,
1410
+ "step": 995
1411
+ },
1412
+ {
1413
+ "epoch": 0.2815860333327467,
1414
+ "grad_norm": 105.0,
1415
+ "learning_rate": 1.5968701095461658e-06,
1416
+ "loss": 89.8639,
1417
+ "step": 1000
1418
+ },
1419
+ {
1420
+ "epoch": 0.2815860333327467,
1421
+ "eval_loss": 2.838271141052246,
1422
+ "eval_runtime": 172.5248,
1423
+ "eval_samples_per_second": 1109.383,
1424
+ "eval_steps_per_second": 34.673,
1425
+ "step": 1000
1426
+ }
1427
+ ],
1428
+ "logging_steps": 5,
1429
+ "max_steps": 3551,
1430
+ "num_input_tokens_seen": 0,
1431
+ "num_train_epochs": 1,
1432
+ "save_steps": 500,
1433
+ "stateful_callbacks": {
1434
+ "TrainerControl": {
1435
+ "args": {
1436
+ "should_epoch_stop": false,
1437
+ "should_evaluate": false,
1438
+ "should_log": false,
1439
+ "should_save": true,
1440
+ "should_training_stop": false
1441
+ },
1442
+ "attributes": {}
1443
+ }
1444
+ },
1445
+ "total_flos": 4.332357992788787e+18,
1446
+ "train_batch_size": 4,
1447
+ "trial_name": null,
1448
+ "trial_params": null
1449
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60b40db795e654ff7cc6763d0a4e65ffde9f8eeb4a5da37c02cffa1d394588ed
3
+ size 5752