CocoRoF commited on
Commit
2dd86cc
·
verified ·
1 Parent(s): 764634a

Training in progress, step 2500, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CocoRoF/KoModernBERT-base-mlm-v04-retry-model-chp05",
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": 10000.0,
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": "4.48.2",
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 sha256:3dc83da414bac75b82e0faabe85965bc1ed69e5ee0e1802d37cfd4c377a0bf0c
3
+ size 368988278
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:579b6a1a47db2bcdaf49967b9a546edf75edc79ff1ff2dcb1a994076fe643add
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:e442211737ccc9094723c53ccf5cc299f428d2455400cdd11b257d7edd84528c
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 +1,1791 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.1808154778049001,
5
+ "eval_steps": 2500,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0007232619112196004,
13
+ "grad_norm": 16.890625,
14
+ "learning_rate": 9.99994349538668e-07,
15
+ "loss": 24.7314,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0014465238224392009,
20
+ "grad_norm": 16.96875,
21
+ "learning_rate": 9.999886990773362e-07,
22
+ "loss": 25.1718,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0021697857336588013,
27
+ "grad_norm": 15.609375,
28
+ "learning_rate": 9.999830486160042e-07,
29
+ "loss": 25.0494,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.0028930476448784017,
34
+ "grad_norm": 15.890625,
35
+ "learning_rate": 9.999773981546724e-07,
36
+ "loss": 25.5317,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.003616309556098002,
41
+ "grad_norm": 16.328125,
42
+ "learning_rate": 9.999717476933404e-07,
43
+ "loss": 24.9466,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.0043395714673176026,
48
+ "grad_norm": 16.203125,
49
+ "learning_rate": 9.999660972320084e-07,
50
+ "loss": 25.3166,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.0050628333785372025,
55
+ "grad_norm": 14.34375,
56
+ "learning_rate": 9.999604467706766e-07,
57
+ "loss": 24.963,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.005786095289756803,
62
+ "grad_norm": 15.9609375,
63
+ "learning_rate": 9.999547963093446e-07,
64
+ "loss": 25.2256,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.006509357200976403,
69
+ "grad_norm": 16.34375,
70
+ "learning_rate": 9.999491458480128e-07,
71
+ "loss": 25.5734,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.007232619112196004,
76
+ "grad_norm": 16.65625,
77
+ "learning_rate": 9.999434953866808e-07,
78
+ "loss": 25.0955,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.007955881023415604,
83
+ "grad_norm": 16.453125,
84
+ "learning_rate": 9.99937844925349e-07,
85
+ "loss": 25.173,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.008679142934635205,
90
+ "grad_norm": 15.8125,
91
+ "learning_rate": 9.99932194464017e-07,
92
+ "loss": 24.9289,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.009402404845854806,
97
+ "grad_norm": 16.3125,
98
+ "learning_rate": 9.99926544002685e-07,
99
+ "loss": 25.1639,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.010125666757074405,
104
+ "grad_norm": 16.65625,
105
+ "learning_rate": 9.999208935413532e-07,
106
+ "loss": 25.2427,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.010848928668294006,
111
+ "grad_norm": 16.46875,
112
+ "learning_rate": 9.999152430800212e-07,
113
+ "loss": 25.4152,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.011572190579513607,
118
+ "grad_norm": 16.640625,
119
+ "learning_rate": 9.999095926186894e-07,
120
+ "loss": 25.3004,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.012295452490733206,
125
+ "grad_norm": 16.1875,
126
+ "learning_rate": 9.999039421573574e-07,
127
+ "loss": 25.122,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.013018714401952807,
132
+ "grad_norm": 16.96875,
133
+ "learning_rate": 9.998982916960254e-07,
134
+ "loss": 25.1076,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.013741976313172408,
139
+ "grad_norm": 17.03125,
140
+ "learning_rate": 9.998926412346936e-07,
141
+ "loss": 25.7121,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.014465238224392009,
146
+ "grad_norm": 17.203125,
147
+ "learning_rate": 9.998869907733616e-07,
148
+ "loss": 24.9972,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.015188500135611608,
153
+ "grad_norm": 16.015625,
154
+ "learning_rate": 9.998813403120298e-07,
155
+ "loss": 25.1666,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.01591176204683121,
160
+ "grad_norm": 16.328125,
161
+ "learning_rate": 9.998756898506978e-07,
162
+ "loss": 25.0473,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.016635023958050808,
167
+ "grad_norm": 17.3125,
168
+ "learning_rate": 9.998700393893658e-07,
169
+ "loss": 25.1476,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.01735828586927041,
174
+ "grad_norm": 16.125,
175
+ "learning_rate": 9.99864388928034e-07,
176
+ "loss": 25.5306,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.01808154778049001,
181
+ "grad_norm": 15.53125,
182
+ "learning_rate": 9.99858738466702e-07,
183
+ "loss": 25.268,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.018804809691709612,
188
+ "grad_norm": 15.9609375,
189
+ "learning_rate": 9.998530880053702e-07,
190
+ "loss": 25.2015,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.01952807160292921,
195
+ "grad_norm": 16.3125,
196
+ "learning_rate": 9.998474375440382e-07,
197
+ "loss": 25.0597,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.02025133351414881,
202
+ "grad_norm": 15.7578125,
203
+ "learning_rate": 9.998417870827062e-07,
204
+ "loss": 25.3037,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.020974595425368413,
209
+ "grad_norm": 15.6484375,
210
+ "learning_rate": 9.998361366213744e-07,
211
+ "loss": 25.0957,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.021697857336588012,
216
+ "grad_norm": 16.609375,
217
+ "learning_rate": 9.998304861600424e-07,
218
+ "loss": 25.1532,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.02242111924780761,
223
+ "grad_norm": 16.75,
224
+ "learning_rate": 9.998248356987106e-07,
225
+ "loss": 25.0866,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.023144381159027214,
230
+ "grad_norm": 16.125,
231
+ "learning_rate": 9.998191852373786e-07,
232
+ "loss": 25.4455,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.023867643070246813,
237
+ "grad_norm": 16.140625,
238
+ "learning_rate": 9.998135347760468e-07,
239
+ "loss": 25.4253,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.024590904981466412,
244
+ "grad_norm": 16.671875,
245
+ "learning_rate": 9.998078843147148e-07,
246
+ "loss": 24.9265,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.025314166892686014,
251
+ "grad_norm": 16.71875,
252
+ "learning_rate": 9.998022338533828e-07,
253
+ "loss": 25.2683,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.026037428803905614,
258
+ "grad_norm": 16.703125,
259
+ "learning_rate": 9.99796583392051e-07,
260
+ "loss": 25.2497,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.026760690715125216,
265
+ "grad_norm": 15.8515625,
266
+ "learning_rate": 9.99790932930719e-07,
267
+ "loss": 25.099,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.027483952626344815,
272
+ "grad_norm": 16.28125,
273
+ "learning_rate": 9.997852824693872e-07,
274
+ "loss": 25.7413,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.028207214537564414,
279
+ "grad_norm": 15.7109375,
280
+ "learning_rate": 9.997796320080552e-07,
281
+ "loss": 24.8872,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.028930476448784017,
286
+ "grad_norm": 16.421875,
287
+ "learning_rate": 9.997739815467232e-07,
288
+ "loss": 25.2099,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.029653738360003616,
293
+ "grad_norm": 16.0,
294
+ "learning_rate": 9.997683310853914e-07,
295
+ "loss": 25.1945,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.030377000271223215,
300
+ "grad_norm": 15.390625,
301
+ "learning_rate": 9.997626806240594e-07,
302
+ "loss": 24.9576,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.031100262182442818,
307
+ "grad_norm": 15.3359375,
308
+ "learning_rate": 9.997570301627277e-07,
309
+ "loss": 24.7866,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.03182352409366242,
314
+ "grad_norm": 16.296875,
315
+ "learning_rate": 9.997513797013957e-07,
316
+ "loss": 25.3049,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.03254678600488202,
321
+ "grad_norm": 16.765625,
322
+ "learning_rate": 9.997457292400636e-07,
323
+ "loss": 25.151,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.033270047916101615,
328
+ "grad_norm": 15.3515625,
329
+ "learning_rate": 9.997400787787319e-07,
330
+ "loss": 25.0841,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.03399330982732122,
335
+ "grad_norm": 16.453125,
336
+ "learning_rate": 9.997344283173999e-07,
337
+ "loss": 25.2712,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.03471657173854082,
342
+ "grad_norm": 14.78125,
343
+ "learning_rate": 9.99728777856068e-07,
344
+ "loss": 24.8674,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.035439833649760416,
349
+ "grad_norm": 16.171875,
350
+ "learning_rate": 9.99723127394736e-07,
351
+ "loss": 25.2065,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.03616309556098002,
356
+ "grad_norm": 16.625,
357
+ "learning_rate": 9.99717476933404e-07,
358
+ "loss": 25.0951,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.03688635747219962,
363
+ "grad_norm": 15.8828125,
364
+ "learning_rate": 9.997118264720723e-07,
365
+ "loss": 25.1455,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.037609619383419224,
370
+ "grad_norm": 15.6953125,
371
+ "learning_rate": 9.997061760107403e-07,
372
+ "loss": 25.313,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.03833288129463882,
377
+ "grad_norm": 16.46875,
378
+ "learning_rate": 9.997005255494085e-07,
379
+ "loss": 24.8546,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.03905614320585842,
384
+ "grad_norm": 16.0625,
385
+ "learning_rate": 9.996948750880765e-07,
386
+ "loss": 25.1006,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.039779405117078025,
391
+ "grad_norm": 16.34375,
392
+ "learning_rate": 9.996892246267447e-07,
393
+ "loss": 25.1469,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.04050266702829762,
398
+ "grad_norm": 15.6328125,
399
+ "learning_rate": 9.996835741654127e-07,
400
+ "loss": 25.0277,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.04122592893951722,
405
+ "grad_norm": 15.328125,
406
+ "learning_rate": 9.996779237040807e-07,
407
+ "loss": 25.2235,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.041949190850736826,
412
+ "grad_norm": 15.7265625,
413
+ "learning_rate": 9.996722732427489e-07,
414
+ "loss": 25.3082,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.04267245276195642,
419
+ "grad_norm": 16.328125,
420
+ "learning_rate": 9.996666227814169e-07,
421
+ "loss": 25.329,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.043395714673176024,
426
+ "grad_norm": 17.1875,
427
+ "learning_rate": 9.99660972320085e-07,
428
+ "loss": 25.3133,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.044118976584395626,
433
+ "grad_norm": 16.578125,
434
+ "learning_rate": 9.99655321858753e-07,
435
+ "loss": 25.2397,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.04484223849561522,
440
+ "grad_norm": 16.46875,
441
+ "learning_rate": 9.99649671397421e-07,
442
+ "loss": 25.2219,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.045565500406834825,
447
+ "grad_norm": 16.484375,
448
+ "learning_rate": 9.996440209360893e-07,
449
+ "loss": 25.2115,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.04628876231805443,
454
+ "grad_norm": 16.296875,
455
+ "learning_rate": 9.996383704747575e-07,
456
+ "loss": 24.9097,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.04701202422927402,
461
+ "grad_norm": 16.171875,
462
+ "learning_rate": 9.996327200134255e-07,
463
+ "loss": 25.3739,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.047735286140493625,
468
+ "grad_norm": 16.453125,
469
+ "learning_rate": 9.996270695520935e-07,
470
+ "loss": 25.4334,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.04845854805171323,
475
+ "grad_norm": 16.625,
476
+ "learning_rate": 9.996214190907615e-07,
477
+ "loss": 25.3735,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.049181809962932824,
482
+ "grad_norm": 16.546875,
483
+ "learning_rate": 9.996157686294297e-07,
484
+ "loss": 25.2253,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.049905071874152426,
489
+ "grad_norm": 15.953125,
490
+ "learning_rate": 9.99610118168098e-07,
491
+ "loss": 25.3197,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.05062833378537203,
496
+ "grad_norm": 16.046875,
497
+ "learning_rate": 9.99604467706766e-07,
498
+ "loss": 25.0905,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.05135159569659163,
503
+ "grad_norm": 16.90625,
504
+ "learning_rate": 9.99598817245434e-07,
505
+ "loss": 25.5284,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.05207485760781123,
510
+ "grad_norm": 15.7421875,
511
+ "learning_rate": 9.99593166784102e-07,
512
+ "loss": 25.1216,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.05279811951903083,
517
+ "grad_norm": 16.5625,
518
+ "learning_rate": 9.995875163227701e-07,
519
+ "loss": 25.3238,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.05352138143025043,
524
+ "grad_norm": 16.046875,
525
+ "learning_rate": 9.995818658614383e-07,
526
+ "loss": 25.0432,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.05424464334147003,
531
+ "grad_norm": 16.0625,
532
+ "learning_rate": 9.995762154001063e-07,
533
+ "loss": 24.9606,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.05496790525268963,
538
+ "grad_norm": 17.4375,
539
+ "learning_rate": 9.995705649387743e-07,
540
+ "loss": 25.1405,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.05569116716390923,
545
+ "grad_norm": 16.3125,
546
+ "learning_rate": 9.995649144774425e-07,
547
+ "loss": 24.8765,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.05641442907512883,
552
+ "grad_norm": 17.390625,
553
+ "learning_rate": 9.995592640161105e-07,
554
+ "loss": 24.962,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.05713769098634843,
559
+ "grad_norm": 17.109375,
560
+ "learning_rate": 9.995536135547785e-07,
561
+ "loss": 25.0881,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.057860952897568034,
566
+ "grad_norm": 16.4375,
567
+ "learning_rate": 9.995479630934467e-07,
568
+ "loss": 25.4495,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.05858421480878763,
573
+ "grad_norm": 16.46875,
574
+ "learning_rate": 9.99542312632115e-07,
575
+ "loss": 25.3541,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.05930747672000723,
580
+ "grad_norm": 16.125,
581
+ "learning_rate": 9.99536662170783e-07,
582
+ "loss": 25.2303,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.060030738631226835,
587
+ "grad_norm": 16.625,
588
+ "learning_rate": 9.99531011709451e-07,
589
+ "loss": 24.929,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.06075400054244643,
594
+ "grad_norm": 15.59375,
595
+ "learning_rate": 9.99525361248119e-07,
596
+ "loss": 25.0334,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.06147726245366603,
601
+ "grad_norm": 16.5625,
602
+ "learning_rate": 9.995197107867871e-07,
603
+ "loss": 25.4058,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.062200524364885636,
608
+ "grad_norm": 16.390625,
609
+ "learning_rate": 9.995140603254554e-07,
610
+ "loss": 24.9176,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.06292378627610523,
615
+ "grad_norm": 15.96875,
616
+ "learning_rate": 9.995084098641234e-07,
617
+ "loss": 25.4821,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.06364704818732483,
622
+ "grad_norm": 15.5625,
623
+ "learning_rate": 9.995027594027914e-07,
624
+ "loss": 25.2232,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.06437031009854444,
629
+ "grad_norm": 16.140625,
630
+ "learning_rate": 9.994971089414593e-07,
631
+ "loss": 25.2073,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.06509357200976404,
636
+ "grad_norm": 16.96875,
637
+ "learning_rate": 9.994914584801276e-07,
638
+ "loss": 24.9354,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.06581683392098364,
643
+ "grad_norm": 15.890625,
644
+ "learning_rate": 9.994858080187958e-07,
645
+ "loss": 25.2106,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.06654009583220323,
650
+ "grad_norm": 15.875,
651
+ "learning_rate": 9.994801575574638e-07,
652
+ "loss": 25.3214,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.06726335774342283,
657
+ "grad_norm": 17.21875,
658
+ "learning_rate": 9.994745070961318e-07,
659
+ "loss": 25.1286,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.06798661965464244,
664
+ "grad_norm": 15.75,
665
+ "learning_rate": 9.994688566347998e-07,
666
+ "loss": 25.0482,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.06870988156586204,
671
+ "grad_norm": 15.71875,
672
+ "learning_rate": 9.99463206173468e-07,
673
+ "loss": 24.9044,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.06943314347708164,
678
+ "grad_norm": 16.796875,
679
+ "learning_rate": 9.994575557121362e-07,
680
+ "loss": 25.3312,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.07015640538830124,
685
+ "grad_norm": 16.28125,
686
+ "learning_rate": 9.994519052508042e-07,
687
+ "loss": 25.1329,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.07087966729952083,
692
+ "grad_norm": 15.5546875,
693
+ "learning_rate": 9.994462547894722e-07,
694
+ "loss": 25.5721,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.07160292921074043,
699
+ "grad_norm": 17.359375,
700
+ "learning_rate": 9.994406043281404e-07,
701
+ "loss": 25.4597,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.07232619112196004,
706
+ "grad_norm": 16.03125,
707
+ "learning_rate": 9.994349538668084e-07,
708
+ "loss": 25.1876,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.07304945303317964,
713
+ "grad_norm": 15.4921875,
714
+ "learning_rate": 9.994293034054766e-07,
715
+ "loss": 24.6817,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.07377271494439924,
720
+ "grad_norm": 16.96875,
721
+ "learning_rate": 9.994236529441446e-07,
722
+ "loss": 25.1883,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.07449597685561885,
727
+ "grad_norm": 16.984375,
728
+ "learning_rate": 9.994180024828128e-07,
729
+ "loss": 24.8092,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.07521923876683845,
734
+ "grad_norm": 16.078125,
735
+ "learning_rate": 9.994123520214808e-07,
736
+ "loss": 25.0968,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.07594250067805804,
741
+ "grad_norm": 16.296875,
742
+ "learning_rate": 9.994067015601488e-07,
743
+ "loss": 25.0758,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.07666576258927764,
748
+ "grad_norm": 15.4375,
749
+ "learning_rate": 9.99401051098817e-07,
750
+ "loss": 25.3673,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.07738902450049724,
755
+ "grad_norm": 16.8125,
756
+ "learning_rate": 9.99395400637485e-07,
757
+ "loss": 25.293,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.07811228641171684,
762
+ "grad_norm": 15.3828125,
763
+ "learning_rate": 9.993897501761532e-07,
764
+ "loss": 25.3697,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.07883554832293645,
769
+ "grad_norm": 15.3125,
770
+ "learning_rate": 9.993840997148212e-07,
771
+ "loss": 25.3813,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.07955881023415605,
776
+ "grad_norm": 15.7890625,
777
+ "learning_rate": 9.993784492534892e-07,
778
+ "loss": 25.0103,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.08028207214537564,
783
+ "grad_norm": 17.609375,
784
+ "learning_rate": 9.993727987921572e-07,
785
+ "loss": 25.3168,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.08100533405659524,
790
+ "grad_norm": 17.765625,
791
+ "learning_rate": 9.993671483308254e-07,
792
+ "loss": 24.9627,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.08172859596781484,
797
+ "grad_norm": 17.265625,
798
+ "learning_rate": 9.993614978694936e-07,
799
+ "loss": 25.0904,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.08245185787903445,
804
+ "grad_norm": 15.6015625,
805
+ "learning_rate": 9.993558474081616e-07,
806
+ "loss": 25.0091,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.08317511979025405,
811
+ "grad_norm": 16.78125,
812
+ "learning_rate": 9.993501969468296e-07,
813
+ "loss": 25.1542,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.08389838170147365,
818
+ "grad_norm": 17.421875,
819
+ "learning_rate": 9.993445464854976e-07,
820
+ "loss": 25.0688,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.08462164361269324,
825
+ "grad_norm": 16.046875,
826
+ "learning_rate": 9.993388960241658e-07,
827
+ "loss": 24.9462,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.08534490552391284,
832
+ "grad_norm": 15.8125,
833
+ "learning_rate": 9.99333245562834e-07,
834
+ "loss": 25.2823,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.08606816743513244,
839
+ "grad_norm": 16.828125,
840
+ "learning_rate": 9.99327595101502e-07,
841
+ "loss": 25.2765,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.08679142934635205,
846
+ "grad_norm": 16.125,
847
+ "learning_rate": 9.9932194464017e-07,
848
+ "loss": 24.7678,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.08751469125757165,
853
+ "grad_norm": 16.28125,
854
+ "learning_rate": 9.993162941788382e-07,
855
+ "loss": 25.295,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.08823795316879125,
860
+ "grad_norm": 17.890625,
861
+ "learning_rate": 9.993106437175062e-07,
862
+ "loss": 25.3306,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.08896121508001086,
867
+ "grad_norm": 17.21875,
868
+ "learning_rate": 9.993049932561744e-07,
869
+ "loss": 24.9049,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.08968447699123044,
874
+ "grad_norm": 17.390625,
875
+ "learning_rate": 9.992993427948424e-07,
876
+ "loss": 24.8557,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.09040773890245005,
881
+ "grad_norm": 17.171875,
882
+ "learning_rate": 9.992936923335106e-07,
883
+ "loss": 24.8911,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.09113100081366965,
888
+ "grad_norm": 15.7890625,
889
+ "learning_rate": 9.992880418721786e-07,
890
+ "loss": 25.025,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.09185426272488925,
895
+ "grad_norm": 16.140625,
896
+ "learning_rate": 9.992823914108466e-07,
897
+ "loss": 25.0636,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.09257752463610885,
902
+ "grad_norm": 16.4375,
903
+ "learning_rate": 9.992767409495148e-07,
904
+ "loss": 25.3049,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.09330078654732846,
909
+ "grad_norm": 16.90625,
910
+ "learning_rate": 9.992710904881828e-07,
911
+ "loss": 25.2396,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.09402404845854805,
916
+ "grad_norm": 17.046875,
917
+ "learning_rate": 9.99265440026851e-07,
918
+ "loss": 25.1375,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.09474731036976765,
923
+ "grad_norm": 16.1875,
924
+ "learning_rate": 9.99259789565519e-07,
925
+ "loss": 25.2109,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.09547057228098725,
930
+ "grad_norm": 17.171875,
931
+ "learning_rate": 9.99254139104187e-07,
932
+ "loss": 25.2515,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.09619383419220685,
937
+ "grad_norm": 16.515625,
938
+ "learning_rate": 9.992484886428553e-07,
939
+ "loss": 25.175,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.09691709610342646,
944
+ "grad_norm": 16.84375,
945
+ "learning_rate": 9.992428381815233e-07,
946
+ "loss": 24.7771,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.09764035801464606,
951
+ "grad_norm": 17.390625,
952
+ "learning_rate": 9.992371877201915e-07,
953
+ "loss": 25.2527,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.09836361992586565,
958
+ "grad_norm": 15.9375,
959
+ "learning_rate": 9.992315372588595e-07,
960
+ "loss": 25.0993,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.09908688183708525,
965
+ "grad_norm": 16.359375,
966
+ "learning_rate": 9.992258867975275e-07,
967
+ "loss": 25.0632,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.09981014374830485,
972
+ "grad_norm": 15.578125,
973
+ "learning_rate": 9.992202363361957e-07,
974
+ "loss": 25.05,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.10053340565952446,
979
+ "grad_norm": 15.5234375,
980
+ "learning_rate": 9.992145858748637e-07,
981
+ "loss": 25.2352,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.10125666757074406,
986
+ "grad_norm": 15.8203125,
987
+ "learning_rate": 9.992089354135319e-07,
988
+ "loss": 25.1623,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.10197992948196366,
993
+ "grad_norm": 15.9140625,
994
+ "learning_rate": 9.992032849521999e-07,
995
+ "loss": 25.0429,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.10270319139318326,
1000
+ "grad_norm": 16.40625,
1001
+ "learning_rate": 9.991976344908679e-07,
1002
+ "loss": 25.2809,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.10342645330440285,
1007
+ "grad_norm": 15.5703125,
1008
+ "learning_rate": 9.99191984029536e-07,
1009
+ "loss": 25.3832,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.10414971521562245,
1014
+ "grad_norm": 16.71875,
1015
+ "learning_rate": 9.99186333568204e-07,
1016
+ "loss": 25.2036,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.10487297712684206,
1021
+ "grad_norm": 16.421875,
1022
+ "learning_rate": 9.991806831068723e-07,
1023
+ "loss": 25.1681,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.10559623903806166,
1028
+ "grad_norm": 16.484375,
1029
+ "learning_rate": 9.991750326455403e-07,
1030
+ "loss": 25.2005,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.10631950094928126,
1035
+ "grad_norm": 16.359375,
1036
+ "learning_rate": 9.991693821842085e-07,
1037
+ "loss": 24.7779,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.10704276286050086,
1042
+ "grad_norm": 15.9140625,
1043
+ "learning_rate": 9.991637317228765e-07,
1044
+ "loss": 24.9989,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.10776602477172045,
1049
+ "grad_norm": 15.984375,
1050
+ "learning_rate": 9.991580812615445e-07,
1051
+ "loss": 25.0596,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.10848928668294006,
1056
+ "grad_norm": 15.3046875,
1057
+ "learning_rate": 9.991524308002127e-07,
1058
+ "loss": 25.118,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.10921254859415966,
1063
+ "grad_norm": 17.5625,
1064
+ "learning_rate": 9.991467803388807e-07,
1065
+ "loss": 25.5828,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.10993581050537926,
1070
+ "grad_norm": 15.6328125,
1071
+ "learning_rate": 9.99141129877549e-07,
1072
+ "loss": 24.9299,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.11065907241659886,
1077
+ "grad_norm": 16.46875,
1078
+ "learning_rate": 9.99135479416217e-07,
1079
+ "loss": 25.4944,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.11138233432781847,
1084
+ "grad_norm": 15.84375,
1085
+ "learning_rate": 9.99129828954885e-07,
1086
+ "loss": 25.2725,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.11210559623903806,
1091
+ "grad_norm": 15.9453125,
1092
+ "learning_rate": 9.99124178493553e-07,
1093
+ "loss": 25.2005,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.11282885815025766,
1098
+ "grad_norm": 16.40625,
1099
+ "learning_rate": 9.99118528032221e-07,
1100
+ "loss": 25.009,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.11355212006147726,
1105
+ "grad_norm": 16.0,
1106
+ "learning_rate": 9.991128775708893e-07,
1107
+ "loss": 24.7517,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.11427538197269686,
1112
+ "grad_norm": 16.09375,
1113
+ "learning_rate": 9.991072271095573e-07,
1114
+ "loss": 25.5721,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.11499864388391647,
1119
+ "grad_norm": 16.84375,
1120
+ "learning_rate": 9.991015766482253e-07,
1121
+ "loss": 24.9795,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.11572190579513607,
1126
+ "grad_norm": 16.671875,
1127
+ "learning_rate": 9.990959261868935e-07,
1128
+ "loss": 25.0254,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.11644516770635567,
1133
+ "grad_norm": 15.4296875,
1134
+ "learning_rate": 9.990902757255615e-07,
1135
+ "loss": 24.8741,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.11716842961757526,
1140
+ "grad_norm": 15.1875,
1141
+ "learning_rate": 9.990846252642297e-07,
1142
+ "loss": 25.0707,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.11789169152879486,
1147
+ "grad_norm": 15.765625,
1148
+ "learning_rate": 9.990789748028977e-07,
1149
+ "loss": 25.1894,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.11861495344001446,
1154
+ "grad_norm": 16.640625,
1155
+ "learning_rate": 9.990733243415657e-07,
1156
+ "loss": 25.275,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.11933821535123407,
1161
+ "grad_norm": 15.9765625,
1162
+ "learning_rate": 9.99067673880234e-07,
1163
+ "loss": 25.5003,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.12006147726245367,
1168
+ "grad_norm": 15.390625,
1169
+ "learning_rate": 9.99062023418902e-07,
1170
+ "loss": 25.217,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.12078473917367327,
1175
+ "grad_norm": 15.6015625,
1176
+ "learning_rate": 9.990563729575701e-07,
1177
+ "loss": 24.9766,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.12150800108489286,
1182
+ "grad_norm": 16.28125,
1183
+ "learning_rate": 9.990507224962381e-07,
1184
+ "loss": 24.9016,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 0.12223126299611246,
1189
+ "grad_norm": 28.390625,
1190
+ "learning_rate": 9.990450720349063e-07,
1191
+ "loss": 25.5052,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 0.12295452490733207,
1196
+ "grad_norm": 16.71875,
1197
+ "learning_rate": 9.990394215735743e-07,
1198
+ "loss": 25.113,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 0.12367778681855167,
1203
+ "grad_norm": 15.9609375,
1204
+ "learning_rate": 9.990337711122423e-07,
1205
+ "loss": 25.0131,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 0.12440104872977127,
1210
+ "grad_norm": 16.328125,
1211
+ "learning_rate": 9.990281206509105e-07,
1212
+ "loss": 25.1244,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 0.12512431064099086,
1217
+ "grad_norm": 16.84375,
1218
+ "learning_rate": 9.990224701895785e-07,
1219
+ "loss": 25.1582,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 0.12584757255221046,
1224
+ "grad_norm": 16.625,
1225
+ "learning_rate": 9.990168197282468e-07,
1226
+ "loss": 25.0834,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 0.12657083446343007,
1231
+ "grad_norm": 15.8828125,
1232
+ "learning_rate": 9.990111692669147e-07,
1233
+ "loss": 25.0038,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 0.12729409637464967,
1238
+ "grad_norm": 16.609375,
1239
+ "learning_rate": 9.990055188055827e-07,
1240
+ "loss": 25.0728,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 0.12801735828586927,
1245
+ "grad_norm": 16.421875,
1246
+ "learning_rate": 9.98999868344251e-07,
1247
+ "loss": 25.295,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 0.12874062019708887,
1252
+ "grad_norm": 15.1015625,
1253
+ "learning_rate": 9.98994217882919e-07,
1254
+ "loss": 25.2353,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 0.12946388210830848,
1259
+ "grad_norm": 16.21875,
1260
+ "learning_rate": 9.989885674215872e-07,
1261
+ "loss": 25.2932,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 0.13018714401952808,
1266
+ "grad_norm": 15.7890625,
1267
+ "learning_rate": 9.989829169602552e-07,
1268
+ "loss": 25.425,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 0.13091040593074768,
1273
+ "grad_norm": 17.296875,
1274
+ "learning_rate": 9.989772664989232e-07,
1275
+ "loss": 24.8049,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 0.13163366784196728,
1280
+ "grad_norm": 16.1875,
1281
+ "learning_rate": 9.989716160375914e-07,
1282
+ "loss": 25.0513,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 0.13235692975318689,
1287
+ "grad_norm": 15.8828125,
1288
+ "learning_rate": 9.989659655762594e-07,
1289
+ "loss": 24.6162,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 0.13308019166440646,
1294
+ "grad_norm": 15.953125,
1295
+ "learning_rate": 9.989603151149276e-07,
1296
+ "loss": 25.2815,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 0.13380345357562606,
1301
+ "grad_norm": 15.8203125,
1302
+ "learning_rate": 9.989546646535956e-07,
1303
+ "loss": 24.9768,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 0.13452671548684567,
1308
+ "grad_norm": 16.6875,
1309
+ "learning_rate": 9.989490141922636e-07,
1310
+ "loss": 24.9111,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 0.13524997739806527,
1315
+ "grad_norm": 16.234375,
1316
+ "learning_rate": 9.989433637309318e-07,
1317
+ "loss": 25.027,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 0.13597323930928487,
1322
+ "grad_norm": 16.609375,
1323
+ "learning_rate": 9.989377132695998e-07,
1324
+ "loss": 24.7659,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 0.13669650122050447,
1329
+ "grad_norm": 15.546875,
1330
+ "learning_rate": 9.98932062808268e-07,
1331
+ "loss": 24.7565,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 0.13741976313172408,
1336
+ "grad_norm": 16.28125,
1337
+ "learning_rate": 9.98926412346936e-07,
1338
+ "loss": 25.4091,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 0.13814302504294368,
1343
+ "grad_norm": 17.0,
1344
+ "learning_rate": 9.989207618856042e-07,
1345
+ "loss": 25.1971,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 0.13886628695416328,
1350
+ "grad_norm": 16.140625,
1351
+ "learning_rate": 9.989151114242722e-07,
1352
+ "loss": 25.1719,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 0.13958954886538288,
1357
+ "grad_norm": 15.640625,
1358
+ "learning_rate": 9.989094609629402e-07,
1359
+ "loss": 25.2595,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 0.1403128107766025,
1364
+ "grad_norm": 17.03125,
1365
+ "learning_rate": 9.989038105016084e-07,
1366
+ "loss": 25.1428,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 0.1410360726878221,
1371
+ "grad_norm": 16.03125,
1372
+ "learning_rate": 9.988981600402764e-07,
1373
+ "loss": 24.9586,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 0.14175933459904166,
1378
+ "grad_norm": 17.109375,
1379
+ "learning_rate": 9.988925095789446e-07,
1380
+ "loss": 25.2662,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 0.14248259651026127,
1385
+ "grad_norm": 17.03125,
1386
+ "learning_rate": 9.988868591176126e-07,
1387
+ "loss": 25.16,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 0.14320585842148087,
1392
+ "grad_norm": 16.5,
1393
+ "learning_rate": 9.988812086562806e-07,
1394
+ "loss": 25.2651,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 0.14392912033270047,
1399
+ "grad_norm": 16.421875,
1400
+ "learning_rate": 9.988755581949488e-07,
1401
+ "loss": 25.2441,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 0.14465238224392007,
1406
+ "grad_norm": 15.96875,
1407
+ "learning_rate": 9.988699077336168e-07,
1408
+ "loss": 25.0556,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 0.14537564415513968,
1413
+ "grad_norm": 16.53125,
1414
+ "learning_rate": 9.98864257272285e-07,
1415
+ "loss": 25.4167,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 0.14609890606635928,
1420
+ "grad_norm": 16.03125,
1421
+ "learning_rate": 9.98858606810953e-07,
1422
+ "loss": 25.1329,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 0.14682216797757888,
1427
+ "grad_norm": 16.109375,
1428
+ "learning_rate": 9.98852956349621e-07,
1429
+ "loss": 25.4823,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 0.14754542988879848,
1434
+ "grad_norm": 16.265625,
1435
+ "learning_rate": 9.988473058882892e-07,
1436
+ "loss": 25.0906,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 0.1482686918000181,
1441
+ "grad_norm": 16.53125,
1442
+ "learning_rate": 9.988416554269572e-07,
1443
+ "loss": 24.8343,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 0.1489919537112377,
1448
+ "grad_norm": 15.609375,
1449
+ "learning_rate": 9.988360049656254e-07,
1450
+ "loss": 25.3048,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 0.1497152156224573,
1455
+ "grad_norm": 17.4375,
1456
+ "learning_rate": 9.988303545042934e-07,
1457
+ "loss": 25.2774,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 0.1504384775336769,
1462
+ "grad_norm": 15.828125,
1463
+ "learning_rate": 9.988247040429616e-07,
1464
+ "loss": 25.2854,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 0.15116173944489647,
1469
+ "grad_norm": 16.390625,
1470
+ "learning_rate": 9.988190535816296e-07,
1471
+ "loss": 25.0215,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 0.15188500135611607,
1476
+ "grad_norm": 16.171875,
1477
+ "learning_rate": 9.988134031202976e-07,
1478
+ "loss": 25.2348,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 0.15260826326733568,
1483
+ "grad_norm": 15.34375,
1484
+ "learning_rate": 9.988077526589658e-07,
1485
+ "loss": 24.6356,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 0.15333152517855528,
1490
+ "grad_norm": 16.25,
1491
+ "learning_rate": 9.988021021976338e-07,
1492
+ "loss": 25.1007,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 0.15405478708977488,
1497
+ "grad_norm": 16.03125,
1498
+ "learning_rate": 9.98796451736302e-07,
1499
+ "loss": 24.9828,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 0.15477804900099448,
1504
+ "grad_norm": 16.5,
1505
+ "learning_rate": 9.9879080127497e-07,
1506
+ "loss": 25.0345,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 0.15550131091221409,
1511
+ "grad_norm": 17.15625,
1512
+ "learning_rate": 9.98785150813638e-07,
1513
+ "loss": 25.5867,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 0.1562245728234337,
1518
+ "grad_norm": 16.71875,
1519
+ "learning_rate": 9.987795003523062e-07,
1520
+ "loss": 25.3682,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 0.1569478347346533,
1525
+ "grad_norm": 17.015625,
1526
+ "learning_rate": 9.987738498909745e-07,
1527
+ "loss": 25.4203,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 0.1576710966458729,
1532
+ "grad_norm": 16.296875,
1533
+ "learning_rate": 9.987681994296424e-07,
1534
+ "loss": 24.7439,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 0.1583943585570925,
1539
+ "grad_norm": 16.203125,
1540
+ "learning_rate": 9.987625489683104e-07,
1541
+ "loss": 25.2626,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 0.1591176204683121,
1546
+ "grad_norm": 16.046875,
1547
+ "learning_rate": 9.987568985069784e-07,
1548
+ "loss": 25.3073,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 0.1598408823795317,
1553
+ "grad_norm": 15.953125,
1554
+ "learning_rate": 9.987512480456467e-07,
1555
+ "loss": 25.1684,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 0.16056414429075128,
1560
+ "grad_norm": 15.75,
1561
+ "learning_rate": 9.987455975843149e-07,
1562
+ "loss": 24.7415,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 0.16128740620197088,
1567
+ "grad_norm": 16.5,
1568
+ "learning_rate": 9.987399471229829e-07,
1569
+ "loss": 25.3286,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 0.16201066811319048,
1574
+ "grad_norm": 15.796875,
1575
+ "learning_rate": 9.987342966616509e-07,
1576
+ "loss": 24.9328,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 0.16273393002441008,
1581
+ "grad_norm": 15.90625,
1582
+ "learning_rate": 9.987286462003189e-07,
1583
+ "loss": 25.232,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 0.1634571919356297,
1588
+ "grad_norm": 15.65625,
1589
+ "learning_rate": 9.98722995738987e-07,
1590
+ "loss": 25.3422,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 0.1641804538468493,
1595
+ "grad_norm": 16.359375,
1596
+ "learning_rate": 9.98717345277655e-07,
1597
+ "loss": 25.1399,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 0.1649037157580689,
1602
+ "grad_norm": 15.375,
1603
+ "learning_rate": 9.987116948163233e-07,
1604
+ "loss": 25.268,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 0.1656269776692885,
1609
+ "grad_norm": 15.9765625,
1610
+ "learning_rate": 9.987060443549913e-07,
1611
+ "loss": 25.0909,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 0.1663502395805081,
1616
+ "grad_norm": 15.78125,
1617
+ "learning_rate": 9.987003938936595e-07,
1618
+ "loss": 24.9881,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 0.1670735014917277,
1623
+ "grad_norm": 15.7109375,
1624
+ "learning_rate": 9.986947434323275e-07,
1625
+ "loss": 25.1584,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 0.1677967634029473,
1630
+ "grad_norm": 16.6875,
1631
+ "learning_rate": 9.986890929709955e-07,
1632
+ "loss": 25.3915,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 0.1685200253141669,
1637
+ "grad_norm": 16.03125,
1638
+ "learning_rate": 9.986834425096637e-07,
1639
+ "loss": 25.0778,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 0.16924328722538648,
1644
+ "grad_norm": 16.5625,
1645
+ "learning_rate": 9.986777920483317e-07,
1646
+ "loss": 25.1175,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 0.16996654913660608,
1651
+ "grad_norm": 16.484375,
1652
+ "learning_rate": 9.986721415869999e-07,
1653
+ "loss": 25.0781,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 0.17068981104782568,
1658
+ "grad_norm": 16.359375,
1659
+ "learning_rate": 9.986664911256679e-07,
1660
+ "loss": 24.9664,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 0.1714130729590453,
1665
+ "grad_norm": 16.359375,
1666
+ "learning_rate": 9.986608406643359e-07,
1667
+ "loss": 25.2058,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 0.1721363348702649,
1672
+ "grad_norm": 16.765625,
1673
+ "learning_rate": 9.98655190203004e-07,
1674
+ "loss": 25.2812,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 0.1728595967814845,
1679
+ "grad_norm": 15.3046875,
1680
+ "learning_rate": 9.986495397416723e-07,
1681
+ "loss": 24.9085,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 0.1735828586927041,
1686
+ "grad_norm": 16.21875,
1687
+ "learning_rate": 9.986438892803403e-07,
1688
+ "loss": 25.5753,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 0.1743061206039237,
1693
+ "grad_norm": 15.8984375,
1694
+ "learning_rate": 9.986382388190083e-07,
1695
+ "loss": 24.8124,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 0.1750293825151433,
1700
+ "grad_norm": 16.53125,
1701
+ "learning_rate": 9.986325883576763e-07,
1702
+ "loss": 25.1711,
1703
+ "step": 2420
1704
+ },
1705
+ {
1706
+ "epoch": 0.1757526444263629,
1707
+ "grad_norm": 15.953125,
1708
+ "learning_rate": 9.986269378963445e-07,
1709
+ "loss": 25.014,
1710
+ "step": 2430
1711
+ },
1712
+ {
1713
+ "epoch": 0.1764759063375825,
1714
+ "grad_norm": 16.28125,
1715
+ "learning_rate": 9.986212874350127e-07,
1716
+ "loss": 25.099,
1717
+ "step": 2440
1718
+ },
1719
+ {
1720
+ "epoch": 0.1771991682488021,
1721
+ "grad_norm": 17.46875,
1722
+ "learning_rate": 9.986156369736807e-07,
1723
+ "loss": 25.3132,
1724
+ "step": 2450
1725
+ },
1726
+ {
1727
+ "epoch": 0.1779224301600217,
1728
+ "grad_norm": 16.96875,
1729
+ "learning_rate": 9.986099865123487e-07,
1730
+ "loss": 25.126,
1731
+ "step": 2460
1732
+ },
1733
+ {
1734
+ "epoch": 0.17864569207124129,
1735
+ "grad_norm": 16.796875,
1736
+ "learning_rate": 9.986043360510167e-07,
1737
+ "loss": 25.1885,
1738
+ "step": 2470
1739
+ },
1740
+ {
1741
+ "epoch": 0.1793689539824609,
1742
+ "grad_norm": 15.390625,
1743
+ "learning_rate": 9.98598685589685e-07,
1744
+ "loss": 25.0434,
1745
+ "step": 2480
1746
+ },
1747
+ {
1748
+ "epoch": 0.1800922158936805,
1749
+ "grad_norm": 15.8203125,
1750
+ "learning_rate": 9.985930351283531e-07,
1751
+ "loss": 25.4111,
1752
+ "step": 2490
1753
+ },
1754
+ {
1755
+ "epoch": 0.1808154778049001,
1756
+ "grad_norm": 15.4140625,
1757
+ "learning_rate": 9.985873846670211e-07,
1758
+ "loss": 24.7393,
1759
+ "step": 2500
1760
+ },
1761
+ {
1762
+ "epoch": 0.1808154778049001,
1763
+ "eval_loss": 1.5891753435134888,
1764
+ "eval_runtime": 361.4111,
1765
+ "eval_samples_per_second": 2008.956,
1766
+ "eval_steps_per_second": 31.391,
1767
+ "step": 2500
1768
+ }
1769
+ ],
1770
+ "logging_steps": 10,
1771
+ "max_steps": 13826,
1772
+ "num_input_tokens_seen": 0,
1773
+ "num_train_epochs": 1,
1774
+ "save_steps": 2500,
1775
+ "stateful_callbacks": {
1776
+ "TrainerControl": {
1777
+ "args": {
1778
+ "should_epoch_stop": false,
1779
+ "should_evaluate": false,
1780
+ "should_log": false,
1781
+ "should_save": true,
1782
+ "should_training_stop": false
1783
+ },
1784
+ "attributes": {}
1785
+ }
1786
+ },
1787
+ "total_flos": 3.492321391804416e+18,
1788
+ "train_batch_size": 16,
1789
+ "trial_name": null,
1790
+ "trial_params": null
1791
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1711d2e7adf103f41a22e313a32edacb355437c6524c884ae1accfee4913a2d
3
+ size 5368