CocoRoF commited on
Commit
fe8a71f
·
verified ·
1 Parent(s): 3f10f7e

Training in progress, step 9931, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "x2bee/KoModernBERT-base-mlm-v02-ckp01",
3
+ "architectures": [
4
+ "ModernBertForMaskedLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 1152,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 22,
37
+ "pad_token_id": 50283,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": false,
40
+ "repad_logits_with_grad": false,
41
+ "sep_token_id": 50282,
42
+ "sparse_pred_ignore_index": -100,
43
+ "sparse_prediction": false,
44
+ "torch_dtype": "float16",
45
+ "transformers_version": "4.48.0",
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:e44ca357aee33f0c4d77f6283b1039050b3b7ab63acb733b0943c04c3dcd383d
3
+ size 368988278
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf2ed4278033136ed85db98ede9a42075dac27c8de0866c7d2f2fdc4114aff8
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 sha256:69bcb5a0833345d8383f742fc9fcb902b5c0cae43ce63aee4b910dcd39dcda65
3
+ size 15920
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae392ec6232cbf9da21d6ed12bc8247d0d24e7f3a3606acd23be00f3e8bbfc5
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:cbf3e7ca9991a58b0b16574a3c653483c551c270aa05aba06c162ea593f7b0f2
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:c695bebf6bcb75cbe26378bfe0ab7e2a33c49f713b9d6e4d10632b24322977e7
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:d5ebb13c71265c5464c9aa9bb9b66f07764d73befe6cd63a2aaf8e781bf0a374
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 sha256:12cc6e245e189be568c8dfd43a4dd8f04bb3dbd9f17f41458107935d2c2a6a9d
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 sha256:36086646e9a8f76fea69f8a227112e83bb63524964ccdfb82f4cdad88b90e5e4
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 sha256:9b44153bacf860d0ca6ce4c6b9380a199feab8a72ca613e6745bfb671b02c4e4
3
+ size 15984
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403f43b20707fbdd1c781cdcb70c570b1debcb96cf3e00b550211ddfce6ea77f
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 +1,1443 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 3000,
6
+ "global_step": 9931,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0050347397039573055,
13
+ "grad_norm": 28.6875,
14
+ "learning_rate": 7.866954072722124e-10,
15
+ "loss": 25.5771,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.010069479407914611,
20
+ "grad_norm": 25.671875,
21
+ "learning_rate": 1.5733908145444248e-09,
22
+ "loss": 25.4662,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.015104219111871917,
27
+ "grad_norm": 22.171875,
28
+ "learning_rate": 2.360086221816637e-09,
29
+ "loss": 25.2219,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.020138958815829222,
34
+ "grad_norm": 24.40625,
35
+ "learning_rate": 3.1467816290888496e-09,
36
+ "loss": 24.9302,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.025173698519786528,
41
+ "grad_norm": 24.296875,
42
+ "learning_rate": 3.933477036361062e-09,
43
+ "loss": 24.7105,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.030208438223743833,
48
+ "grad_norm": 23.890625,
49
+ "learning_rate": 4.720172443633274e-09,
50
+ "loss": 24.403,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.03524317792770114,
55
+ "grad_norm": 23.125,
56
+ "learning_rate": 5.506867850905486e-09,
57
+ "loss": 24.2281,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.040277917631658444,
62
+ "grad_norm": 23.828125,
63
+ "learning_rate": 6.293563258177699e-09,
64
+ "loss": 24.0123,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.04531265733561575,
69
+ "grad_norm": 26.859375,
70
+ "learning_rate": 7.080258665449911e-09,
71
+ "loss": 23.7867,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.050347397039573055,
76
+ "grad_norm": 23.78125,
77
+ "learning_rate": 7.866954072722123e-09,
78
+ "loss": 23.7771,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.05538213674353036,
83
+ "grad_norm": 23.625,
84
+ "learning_rate": 8.653649479994334e-09,
85
+ "loss": 23.6351,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.060416876447487666,
90
+ "grad_norm": 21.953125,
91
+ "learning_rate": 9.440344887266548e-09,
92
+ "loss": 23.5309,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.06545161615144497,
97
+ "grad_norm": 21.921875,
98
+ "learning_rate": 1.0227040294538761e-08,
99
+ "loss": 23.405,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.07048635585540228,
104
+ "grad_norm": 21.265625,
105
+ "learning_rate": 1.1013735701810972e-08,
106
+ "loss": 23.2201,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.07552109555935958,
111
+ "grad_norm": 23.890625,
112
+ "learning_rate": 1.1800431109083184e-08,
113
+ "loss": 23.2961,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.08055583526331689,
118
+ "grad_norm": 20.859375,
119
+ "learning_rate": 1.2587126516355398e-08,
120
+ "loss": 23.3068,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.0855905749672742,
125
+ "grad_norm": 21.234375,
126
+ "learning_rate": 1.3373821923627609e-08,
127
+ "loss": 23.0151,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.0906253146712315,
132
+ "grad_norm": 21.859375,
133
+ "learning_rate": 1.4160517330899822e-08,
134
+ "loss": 23.0405,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.0956600543751888,
139
+ "grad_norm": 25.3125,
140
+ "learning_rate": 1.4947212738172034e-08,
141
+ "loss": 22.9393,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.10069479407914611,
146
+ "grad_norm": 23.65625,
147
+ "learning_rate": 1.5733908145444247e-08,
148
+ "loss": 22.8635,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.10572953378310342,
153
+ "grad_norm": 21.609375,
154
+ "learning_rate": 1.6520603552716456e-08,
155
+ "loss": 22.8879,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.11076427348706072,
160
+ "grad_norm": 22.671875,
161
+ "learning_rate": 1.730729895998867e-08,
162
+ "loss": 22.8493,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.11579901319101803,
167
+ "grad_norm": 20.625,
168
+ "learning_rate": 1.8093994367260884e-08,
169
+ "loss": 22.8345,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.12083375289497533,
174
+ "grad_norm": 24.859375,
175
+ "learning_rate": 1.8880689774533097e-08,
176
+ "loss": 22.698,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.12586849259893262,
181
+ "grad_norm": 21.734375,
182
+ "learning_rate": 1.966738518180531e-08,
183
+ "loss": 22.5749,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.13090323230288994,
188
+ "grad_norm": 20.328125,
189
+ "learning_rate": 2.0454080589077522e-08,
190
+ "loss": 22.501,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.13593797200684724,
195
+ "grad_norm": 18.21875,
196
+ "learning_rate": 2.124077599634973e-08,
197
+ "loss": 22.5212,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.14097271171080455,
202
+ "grad_norm": 21.71875,
203
+ "learning_rate": 2.2027471403621943e-08,
204
+ "loss": 22.382,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.14600745141476185,
209
+ "grad_norm": 21.15625,
210
+ "learning_rate": 2.2814166810894156e-08,
211
+ "loss": 22.3512,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.15104219111871917,
216
+ "grad_norm": 21.234375,
217
+ "learning_rate": 2.360086221816637e-08,
218
+ "loss": 22.4326,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.15607693082267646,
223
+ "grad_norm": 23.34375,
224
+ "learning_rate": 2.438755762543858e-08,
225
+ "loss": 22.3669,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.16111167052663378,
230
+ "grad_norm": 27.390625,
231
+ "learning_rate": 2.5174253032710797e-08,
232
+ "loss": 22.1896,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.16614641023059107,
237
+ "grad_norm": 23.703125,
238
+ "learning_rate": 2.5960948439983006e-08,
239
+ "loss": 22.1401,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.1711811499345484,
244
+ "grad_norm": 21.3125,
245
+ "learning_rate": 2.6747643847255218e-08,
246
+ "loss": 22.0221,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.17621588963850568,
251
+ "grad_norm": 23.59375,
252
+ "learning_rate": 2.753433925452743e-08,
253
+ "loss": 22.1581,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.181250629342463,
258
+ "grad_norm": 22.96875,
259
+ "learning_rate": 2.8321034661799643e-08,
260
+ "loss": 22.0211,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.1862853690464203,
265
+ "grad_norm": 21.34375,
266
+ "learning_rate": 2.9107730069071856e-08,
267
+ "loss": 22.0172,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.1913201087503776,
272
+ "grad_norm": 21.5625,
273
+ "learning_rate": 2.989442547634407e-08,
274
+ "loss": 21.9346,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.1963548484543349,
279
+ "grad_norm": 23.4375,
280
+ "learning_rate": 3.068112088361628e-08,
281
+ "loss": 22.0178,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.20138958815829222,
286
+ "grad_norm": 19.234375,
287
+ "learning_rate": 3.1467816290888493e-08,
288
+ "loss": 21.8406,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.2064243278622495,
293
+ "grad_norm": 23.53125,
294
+ "learning_rate": 3.2254511698160706e-08,
295
+ "loss": 21.8947,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.21145906756620683,
300
+ "grad_norm": 25.53125,
301
+ "learning_rate": 3.304120710543291e-08,
302
+ "loss": 21.847,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.21649380727016412,
307
+ "grad_norm": 22.34375,
308
+ "learning_rate": 3.3827902512705124e-08,
309
+ "loss": 21.7869,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.22152854697412144,
314
+ "grad_norm": 20.8125,
315
+ "learning_rate": 3.461459791997734e-08,
316
+ "loss": 21.7937,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.22656328667807873,
321
+ "grad_norm": 24.140625,
322
+ "learning_rate": 3.5401293327249556e-08,
323
+ "loss": 21.6699,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.23159802638203605,
328
+ "grad_norm": 21.09375,
329
+ "learning_rate": 3.618798873452177e-08,
330
+ "loss": 21.7536,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.23663276608599335,
335
+ "grad_norm": 30.21875,
336
+ "learning_rate": 3.697468414179398e-08,
337
+ "loss": 21.5712,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.24166750578995067,
342
+ "grad_norm": 19.5625,
343
+ "learning_rate": 3.7761379549066193e-08,
344
+ "loss": 21.6019,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.24670224549390796,
349
+ "grad_norm": 20.234375,
350
+ "learning_rate": 3.8548074956338406e-08,
351
+ "loss": 21.4812,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.25173698519786525,
356
+ "grad_norm": 24.671875,
357
+ "learning_rate": 3.933477036361062e-08,
358
+ "loss": 21.3988,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.2567717249018226,
363
+ "grad_norm": 21.53125,
364
+ "learning_rate": 4.012146577088283e-08,
365
+ "loss": 21.335,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.2618064646057799,
370
+ "grad_norm": 21.046875,
371
+ "learning_rate": 4.0908161178155043e-08,
372
+ "loss": 21.4497,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.2668412043097372,
377
+ "grad_norm": 21.140625,
378
+ "learning_rate": 4.1694856585427256e-08,
379
+ "loss": 21.3434,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.27187594401369447,
384
+ "grad_norm": 21.8125,
385
+ "learning_rate": 4.248155199269946e-08,
386
+ "loss": 21.3044,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.2769106837176518,
391
+ "grad_norm": 20.75,
392
+ "learning_rate": 4.3268247399971674e-08,
393
+ "loss": 21.3128,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.2819454234216091,
398
+ "grad_norm": 21.890625,
399
+ "learning_rate": 4.405494280724389e-08,
400
+ "loss": 21.3736,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.2869801631255664,
405
+ "grad_norm": 24.9375,
406
+ "learning_rate": 4.48416382145161e-08,
407
+ "loss": 21.2371,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 0.2920149028295237,
412
+ "grad_norm": 21.75,
413
+ "learning_rate": 4.562833362178831e-08,
414
+ "loss": 21.2297,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 0.29704964253348104,
419
+ "grad_norm": 23.015625,
420
+ "learning_rate": 4.6415029029060524e-08,
421
+ "loss": 21.1849,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 0.30208438223743833,
426
+ "grad_norm": 35.15625,
427
+ "learning_rate": 4.720172443633274e-08,
428
+ "loss": 21.1206,
429
+ "step": 3000
430
+ },
431
+ {
432
+ "epoch": 0.30208438223743833,
433
+ "eval_loss": 2.6425445079803467,
434
+ "eval_runtime": 96.7996,
435
+ "eval_samples_per_second": 2764.609,
436
+ "eval_steps_per_second": 43.203,
437
+ "step": 3000
438
+ },
439
+ {
440
+ "epoch": 0.3071191219413956,
441
+ "grad_norm": 23.75,
442
+ "learning_rate": 4.798841984360495e-08,
443
+ "loss": 21.0509,
444
+ "step": 3050
445
+ },
446
+ {
447
+ "epoch": 0.3121538616453529,
448
+ "grad_norm": 22.0,
449
+ "learning_rate": 4.877511525087716e-08,
450
+ "loss": 21.0524,
451
+ "step": 3100
452
+ },
453
+ {
454
+ "epoch": 0.31718860134931026,
455
+ "grad_norm": 23.375,
456
+ "learning_rate": 4.956181065814938e-08,
457
+ "loss": 21.0385,
458
+ "step": 3150
459
+ },
460
+ {
461
+ "epoch": 0.32222334105326755,
462
+ "grad_norm": 26.25,
463
+ "learning_rate": 5.034850606542159e-08,
464
+ "loss": 21.0142,
465
+ "step": 3200
466
+ },
467
+ {
468
+ "epoch": 0.32725808075722485,
469
+ "grad_norm": 23.25,
470
+ "learning_rate": 5.11352014726938e-08,
471
+ "loss": 21.0465,
472
+ "step": 3250
473
+ },
474
+ {
475
+ "epoch": 0.33229282046118214,
476
+ "grad_norm": 23.953125,
477
+ "learning_rate": 5.192189687996601e-08,
478
+ "loss": 20.8655,
479
+ "step": 3300
480
+ },
481
+ {
482
+ "epoch": 0.3373275601651395,
483
+ "grad_norm": 21.890625,
484
+ "learning_rate": 5.2708592287238224e-08,
485
+ "loss": 20.9073,
486
+ "step": 3350
487
+ },
488
+ {
489
+ "epoch": 0.3423622998690968,
490
+ "grad_norm": 20.890625,
491
+ "learning_rate": 5.3495287694510437e-08,
492
+ "loss": 20.9968,
493
+ "step": 3400
494
+ },
495
+ {
496
+ "epoch": 0.34739703957305407,
497
+ "grad_norm": 22.859375,
498
+ "learning_rate": 5.428198310178265e-08,
499
+ "loss": 20.8051,
500
+ "step": 3450
501
+ },
502
+ {
503
+ "epoch": 0.35243177927701136,
504
+ "grad_norm": 21.109375,
505
+ "learning_rate": 5.506867850905486e-08,
506
+ "loss": 20.8349,
507
+ "step": 3500
508
+ },
509
+ {
510
+ "epoch": 0.3574665189809687,
511
+ "grad_norm": 22.46875,
512
+ "learning_rate": 5.5855373916327074e-08,
513
+ "loss": 20.8667,
514
+ "step": 3550
515
+ },
516
+ {
517
+ "epoch": 0.362501258684926,
518
+ "grad_norm": 23.015625,
519
+ "learning_rate": 5.6642069323599287e-08,
520
+ "loss": 20.7498,
521
+ "step": 3600
522
+ },
523
+ {
524
+ "epoch": 0.3675359983888833,
525
+ "grad_norm": 21.171875,
526
+ "learning_rate": 5.74287647308715e-08,
527
+ "loss": 20.7326,
528
+ "step": 3650
529
+ },
530
+ {
531
+ "epoch": 0.3725707380928406,
532
+ "grad_norm": 22.578125,
533
+ "learning_rate": 5.821546013814371e-08,
534
+ "loss": 20.6889,
535
+ "step": 3700
536
+ },
537
+ {
538
+ "epoch": 0.37760547779679793,
539
+ "grad_norm": 22.25,
540
+ "learning_rate": 5.9002155545415924e-08,
541
+ "loss": 20.8748,
542
+ "step": 3750
543
+ },
544
+ {
545
+ "epoch": 0.3826402175007552,
546
+ "grad_norm": 22.96875,
547
+ "learning_rate": 5.978885095268814e-08,
548
+ "loss": 20.6818,
549
+ "step": 3800
550
+ },
551
+ {
552
+ "epoch": 0.3876749572047125,
553
+ "grad_norm": 25.625,
554
+ "learning_rate": 6.057554635996034e-08,
555
+ "loss": 20.6082,
556
+ "step": 3850
557
+ },
558
+ {
559
+ "epoch": 0.3927096969086698,
560
+ "grad_norm": 22.0,
561
+ "learning_rate": 6.136224176723256e-08,
562
+ "loss": 20.5934,
563
+ "step": 3900
564
+ },
565
+ {
566
+ "epoch": 0.39774443661262715,
567
+ "grad_norm": 20.5625,
568
+ "learning_rate": 6.214893717450477e-08,
569
+ "loss": 20.6491,
570
+ "step": 3950
571
+ },
572
+ {
573
+ "epoch": 0.40277917631658444,
574
+ "grad_norm": 23.625,
575
+ "learning_rate": 6.293563258177699e-08,
576
+ "loss": 20.6252,
577
+ "step": 4000
578
+ },
579
+ {
580
+ "epoch": 0.40781391602054173,
581
+ "grad_norm": 26.953125,
582
+ "learning_rate": 6.372232798904919e-08,
583
+ "loss": 20.5366,
584
+ "step": 4050
585
+ },
586
+ {
587
+ "epoch": 0.412848655724499,
588
+ "grad_norm": 22.15625,
589
+ "learning_rate": 6.450902339632141e-08,
590
+ "loss": 20.5188,
591
+ "step": 4100
592
+ },
593
+ {
594
+ "epoch": 0.4178833954284564,
595
+ "grad_norm": 21.421875,
596
+ "learning_rate": 6.529571880359362e-08,
597
+ "loss": 20.4495,
598
+ "step": 4150
599
+ },
600
+ {
601
+ "epoch": 0.42291813513241366,
602
+ "grad_norm": 25.09375,
603
+ "learning_rate": 6.608241421086582e-08,
604
+ "loss": 20.5249,
605
+ "step": 4200
606
+ },
607
+ {
608
+ "epoch": 0.42795287483637096,
609
+ "grad_norm": 25.375,
610
+ "learning_rate": 6.686910961813804e-08,
611
+ "loss": 20.386,
612
+ "step": 4250
613
+ },
614
+ {
615
+ "epoch": 0.43298761454032825,
616
+ "grad_norm": 22.078125,
617
+ "learning_rate": 6.765580502541025e-08,
618
+ "loss": 20.2751,
619
+ "step": 4300
620
+ },
621
+ {
622
+ "epoch": 0.4380223542442856,
623
+ "grad_norm": 25.8125,
624
+ "learning_rate": 6.844250043268247e-08,
625
+ "loss": 20.2817,
626
+ "step": 4350
627
+ },
628
+ {
629
+ "epoch": 0.4430570939482429,
630
+ "grad_norm": 22.75,
631
+ "learning_rate": 6.922919583995467e-08,
632
+ "loss": 20.3044,
633
+ "step": 4400
634
+ },
635
+ {
636
+ "epoch": 0.4480918336522002,
637
+ "grad_norm": 23.28125,
638
+ "learning_rate": 7.00158912472269e-08,
639
+ "loss": 20.2628,
640
+ "step": 4450
641
+ },
642
+ {
643
+ "epoch": 0.45312657335615747,
644
+ "grad_norm": 22.96875,
645
+ "learning_rate": 7.080258665449911e-08,
646
+ "loss": 20.3045,
647
+ "step": 4500
648
+ },
649
+ {
650
+ "epoch": 0.4581613130601148,
651
+ "grad_norm": 23.796875,
652
+ "learning_rate": 7.158928206177133e-08,
653
+ "loss": 20.2352,
654
+ "step": 4550
655
+ },
656
+ {
657
+ "epoch": 0.4631960527640721,
658
+ "grad_norm": 25.265625,
659
+ "learning_rate": 7.237597746904354e-08,
660
+ "loss": 20.2659,
661
+ "step": 4600
662
+ },
663
+ {
664
+ "epoch": 0.4682307924680294,
665
+ "grad_norm": 24.578125,
666
+ "learning_rate": 7.316267287631576e-08,
667
+ "loss": 20.1321,
668
+ "step": 4650
669
+ },
670
+ {
671
+ "epoch": 0.4732655321719867,
672
+ "grad_norm": 25.90625,
673
+ "learning_rate": 7.394936828358796e-08,
674
+ "loss": 20.0429,
675
+ "step": 4700
676
+ },
677
+ {
678
+ "epoch": 0.47830027187594404,
679
+ "grad_norm": 21.71875,
680
+ "learning_rate": 7.473606369086017e-08,
681
+ "loss": 20.1437,
682
+ "step": 4750
683
+ },
684
+ {
685
+ "epoch": 0.48333501157990133,
686
+ "grad_norm": 23.046875,
687
+ "learning_rate": 7.552275909813239e-08,
688
+ "loss": 20.2228,
689
+ "step": 4800
690
+ },
691
+ {
692
+ "epoch": 0.4883697512838586,
693
+ "grad_norm": 21.1875,
694
+ "learning_rate": 7.630945450540459e-08,
695
+ "loss": 20.1252,
696
+ "step": 4850
697
+ },
698
+ {
699
+ "epoch": 0.4934044909878159,
700
+ "grad_norm": 21.890625,
701
+ "learning_rate": 7.709614991267681e-08,
702
+ "loss": 20.0736,
703
+ "step": 4900
704
+ },
705
+ {
706
+ "epoch": 0.49843923069177326,
707
+ "grad_norm": 20.65625,
708
+ "learning_rate": 7.788284531994902e-08,
709
+ "loss": 20.0553,
710
+ "step": 4950
711
+ },
712
+ {
713
+ "epoch": 0.5034739703957305,
714
+ "grad_norm": 21.5,
715
+ "learning_rate": 7.866954072722124e-08,
716
+ "loss": 20.0629,
717
+ "step": 5000
718
+ },
719
+ {
720
+ "epoch": 0.5085087100996879,
721
+ "grad_norm": 22.390625,
722
+ "learning_rate": 7.945623613449344e-08,
723
+ "loss": 20.0789,
724
+ "step": 5050
725
+ },
726
+ {
727
+ "epoch": 0.5135434498036452,
728
+ "grad_norm": 24.96875,
729
+ "learning_rate": 8.024293154176566e-08,
730
+ "loss": 19.9527,
731
+ "step": 5100
732
+ },
733
+ {
734
+ "epoch": 0.5185781895076025,
735
+ "grad_norm": 32.1875,
736
+ "learning_rate": 8.102962694903787e-08,
737
+ "loss": 20.0024,
738
+ "step": 5150
739
+ },
740
+ {
741
+ "epoch": 0.5236129292115598,
742
+ "grad_norm": 28.796875,
743
+ "learning_rate": 8.181632235631009e-08,
744
+ "loss": 19.9463,
745
+ "step": 5200
746
+ },
747
+ {
748
+ "epoch": 0.5286476689155171,
749
+ "grad_norm": 22.859375,
750
+ "learning_rate": 8.260301776358229e-08,
751
+ "loss": 19.9707,
752
+ "step": 5250
753
+ },
754
+ {
755
+ "epoch": 0.5336824086194744,
756
+ "grad_norm": 23.46875,
757
+ "learning_rate": 8.338971317085451e-08,
758
+ "loss": 19.8411,
759
+ "step": 5300
760
+ },
761
+ {
762
+ "epoch": 0.5387171483234316,
763
+ "grad_norm": 25.03125,
764
+ "learning_rate": 8.417640857812672e-08,
765
+ "loss": 19.9652,
766
+ "step": 5350
767
+ },
768
+ {
769
+ "epoch": 0.5437518880273889,
770
+ "grad_norm": 21.65625,
771
+ "learning_rate": 8.496310398539892e-08,
772
+ "loss": 19.7365,
773
+ "step": 5400
774
+ },
775
+ {
776
+ "epoch": 0.5487866277313463,
777
+ "grad_norm": 21.5625,
778
+ "learning_rate": 8.574979939267114e-08,
779
+ "loss": 19.7931,
780
+ "step": 5450
781
+ },
782
+ {
783
+ "epoch": 0.5538213674353036,
784
+ "grad_norm": 21.484375,
785
+ "learning_rate": 8.653649479994335e-08,
786
+ "loss": 19.7417,
787
+ "step": 5500
788
+ },
789
+ {
790
+ "epoch": 0.5588561071392609,
791
+ "grad_norm": 23.546875,
792
+ "learning_rate": 8.732319020721557e-08,
793
+ "loss": 19.6592,
794
+ "step": 5550
795
+ },
796
+ {
797
+ "epoch": 0.5638908468432182,
798
+ "grad_norm": 21.78125,
799
+ "learning_rate": 8.810988561448777e-08,
800
+ "loss": 19.6256,
801
+ "step": 5600
802
+ },
803
+ {
804
+ "epoch": 0.5689255865471755,
805
+ "grad_norm": 24.6875,
806
+ "learning_rate": 8.889658102175999e-08,
807
+ "loss": 19.7998,
808
+ "step": 5650
809
+ },
810
+ {
811
+ "epoch": 0.5739603262511328,
812
+ "grad_norm": 33.0625,
813
+ "learning_rate": 8.96832764290322e-08,
814
+ "loss": 19.6983,
815
+ "step": 5700
816
+ },
817
+ {
818
+ "epoch": 0.5789950659550901,
819
+ "grad_norm": 23.03125,
820
+ "learning_rate": 9.046997183630442e-08,
821
+ "loss": 19.7832,
822
+ "step": 5750
823
+ },
824
+ {
825
+ "epoch": 0.5840298056590474,
826
+ "grad_norm": 24.796875,
827
+ "learning_rate": 9.125666724357662e-08,
828
+ "loss": 19.7117,
829
+ "step": 5800
830
+ },
831
+ {
832
+ "epoch": 0.5890645453630048,
833
+ "grad_norm": 23.109375,
834
+ "learning_rate": 9.204336265084884e-08,
835
+ "loss": 19.726,
836
+ "step": 5850
837
+ },
838
+ {
839
+ "epoch": 0.5940992850669621,
840
+ "grad_norm": 22.484375,
841
+ "learning_rate": 9.283005805812105e-08,
842
+ "loss": 19.6984,
843
+ "step": 5900
844
+ },
845
+ {
846
+ "epoch": 0.5991340247709194,
847
+ "grad_norm": 21.53125,
848
+ "learning_rate": 9.361675346539325e-08,
849
+ "loss": 19.7171,
850
+ "step": 5950
851
+ },
852
+ {
853
+ "epoch": 0.6041687644748767,
854
+ "grad_norm": 23.296875,
855
+ "learning_rate": 9.440344887266547e-08,
856
+ "loss": 19.5465,
857
+ "step": 6000
858
+ },
859
+ {
860
+ "epoch": 0.6041687644748767,
861
+ "eval_loss": 2.448728084564209,
862
+ "eval_runtime": 97.8245,
863
+ "eval_samples_per_second": 2735.644,
864
+ "eval_steps_per_second": 42.75,
865
+ "step": 6000
866
+ },
867
+ {
868
+ "epoch": 0.609203504178834,
869
+ "grad_norm": 24.5625,
870
+ "learning_rate": 9.519014427993768e-08,
871
+ "loss": 19.5921,
872
+ "step": 6050
873
+ },
874
+ {
875
+ "epoch": 0.6142382438827912,
876
+ "grad_norm": 23.28125,
877
+ "learning_rate": 9.59768396872099e-08,
878
+ "loss": 19.5556,
879
+ "step": 6100
880
+ },
881
+ {
882
+ "epoch": 0.6192729835867485,
883
+ "grad_norm": 23.671875,
884
+ "learning_rate": 9.67635350944821e-08,
885
+ "loss": 19.6202,
886
+ "step": 6150
887
+ },
888
+ {
889
+ "epoch": 0.6243077232907058,
890
+ "grad_norm": 26.609375,
891
+ "learning_rate": 9.755023050175432e-08,
892
+ "loss": 19.5439,
893
+ "step": 6200
894
+ },
895
+ {
896
+ "epoch": 0.6293424629946631,
897
+ "grad_norm": 26.3125,
898
+ "learning_rate": 9.833692590902653e-08,
899
+ "loss": 19.4785,
900
+ "step": 6250
901
+ },
902
+ {
903
+ "epoch": 0.6343772026986205,
904
+ "grad_norm": 24.9375,
905
+ "learning_rate": 9.912362131629876e-08,
906
+ "loss": 19.4382,
907
+ "step": 6300
908
+ },
909
+ {
910
+ "epoch": 0.6394119424025778,
911
+ "grad_norm": 25.703125,
912
+ "learning_rate": 9.991031672357097e-08,
913
+ "loss": 19.4496,
914
+ "step": 6350
915
+ },
916
+ {
917
+ "epoch": 0.6444466821065351,
918
+ "grad_norm": 23.046875,
919
+ "learning_rate": 1.0069701213084319e-07,
920
+ "loss": 19.4539,
921
+ "step": 6400
922
+ },
923
+ {
924
+ "epoch": 0.6494814218104924,
925
+ "grad_norm": 23.203125,
926
+ "learning_rate": 1.0148370753811539e-07,
927
+ "loss": 19.4393,
928
+ "step": 6450
929
+ },
930
+ {
931
+ "epoch": 0.6545161615144497,
932
+ "grad_norm": 26.09375,
933
+ "learning_rate": 1.022704029453876e-07,
934
+ "loss": 19.3709,
935
+ "step": 6500
936
+ },
937
+ {
938
+ "epoch": 0.659550901218407,
939
+ "grad_norm": 23.46875,
940
+ "learning_rate": 1.0305709835265982e-07,
941
+ "loss": 19.4344,
942
+ "step": 6550
943
+ },
944
+ {
945
+ "epoch": 0.6645856409223643,
946
+ "grad_norm": 24.84375,
947
+ "learning_rate": 1.0384379375993202e-07,
948
+ "loss": 19.2581,
949
+ "step": 6600
950
+ },
951
+ {
952
+ "epoch": 0.6696203806263216,
953
+ "grad_norm": 24.0,
954
+ "learning_rate": 1.0463048916720424e-07,
955
+ "loss": 19.3535,
956
+ "step": 6650
957
+ },
958
+ {
959
+ "epoch": 0.674655120330279,
960
+ "grad_norm": 23.890625,
961
+ "learning_rate": 1.0541718457447645e-07,
962
+ "loss": 19.1846,
963
+ "step": 6700
964
+ },
965
+ {
966
+ "epoch": 0.6796898600342363,
967
+ "grad_norm": 22.875,
968
+ "learning_rate": 1.0620387998174867e-07,
969
+ "loss": 19.234,
970
+ "step": 6750
971
+ },
972
+ {
973
+ "epoch": 0.6847245997381936,
974
+ "grad_norm": 23.65625,
975
+ "learning_rate": 1.0699057538902087e-07,
976
+ "loss": 19.1321,
977
+ "step": 6800
978
+ },
979
+ {
980
+ "epoch": 0.6897593394421508,
981
+ "grad_norm": 21.328125,
982
+ "learning_rate": 1.0777727079629309e-07,
983
+ "loss": 19.3041,
984
+ "step": 6850
985
+ },
986
+ {
987
+ "epoch": 0.6947940791461081,
988
+ "grad_norm": 30.234375,
989
+ "learning_rate": 1.085639662035653e-07,
990
+ "loss": 19.2101,
991
+ "step": 6900
992
+ },
993
+ {
994
+ "epoch": 0.6998288188500654,
995
+ "grad_norm": 22.609375,
996
+ "learning_rate": 1.0935066161083752e-07,
997
+ "loss": 19.12,
998
+ "step": 6950
999
+ },
1000
+ {
1001
+ "epoch": 0.7048635585540227,
1002
+ "grad_norm": 22.921875,
1003
+ "learning_rate": 1.1013735701810972e-07,
1004
+ "loss": 19.211,
1005
+ "step": 7000
1006
+ },
1007
+ {
1008
+ "epoch": 0.70989829825798,
1009
+ "grad_norm": 27.5,
1010
+ "learning_rate": 1.1092405242538194e-07,
1011
+ "loss": 19.0585,
1012
+ "step": 7050
1013
+ },
1014
+ {
1015
+ "epoch": 0.7149330379619374,
1016
+ "grad_norm": 26.515625,
1017
+ "learning_rate": 1.1171074783265415e-07,
1018
+ "loss": 19.2151,
1019
+ "step": 7100
1020
+ },
1021
+ {
1022
+ "epoch": 0.7199677776658947,
1023
+ "grad_norm": 22.734375,
1024
+ "learning_rate": 1.1249744323992635e-07,
1025
+ "loss": 19.0144,
1026
+ "step": 7150
1027
+ },
1028
+ {
1029
+ "epoch": 0.725002517369852,
1030
+ "grad_norm": 23.359375,
1031
+ "learning_rate": 1.1328413864719857e-07,
1032
+ "loss": 19.1019,
1033
+ "step": 7200
1034
+ },
1035
+ {
1036
+ "epoch": 0.7300372570738093,
1037
+ "grad_norm": 28.09375,
1038
+ "learning_rate": 1.1407083405447078e-07,
1039
+ "loss": 19.1398,
1040
+ "step": 7250
1041
+ },
1042
+ {
1043
+ "epoch": 0.7350719967777666,
1044
+ "grad_norm": 24.09375,
1045
+ "learning_rate": 1.14857529461743e-07,
1046
+ "loss": 19.1944,
1047
+ "step": 7300
1048
+ },
1049
+ {
1050
+ "epoch": 0.7401067364817239,
1051
+ "grad_norm": 22.625,
1052
+ "learning_rate": 1.156442248690152e-07,
1053
+ "loss": 19.0951,
1054
+ "step": 7350
1055
+ },
1056
+ {
1057
+ "epoch": 0.7451414761856812,
1058
+ "grad_norm": 24.8125,
1059
+ "learning_rate": 1.1643092027628742e-07,
1060
+ "loss": 19.0727,
1061
+ "step": 7400
1062
+ },
1063
+ {
1064
+ "epoch": 0.7501762158896385,
1065
+ "grad_norm": 24.375,
1066
+ "learning_rate": 1.1721761568355963e-07,
1067
+ "loss": 19.1014,
1068
+ "step": 7450
1069
+ },
1070
+ {
1071
+ "epoch": 0.7552109555935959,
1072
+ "grad_norm": 22.4375,
1073
+ "learning_rate": 1.1800431109083185e-07,
1074
+ "loss": 18.9976,
1075
+ "step": 7500
1076
+ },
1077
+ {
1078
+ "epoch": 0.7602456952975531,
1079
+ "grad_norm": 23.359375,
1080
+ "learning_rate": 1.1879100649810405e-07,
1081
+ "loss": 19.0317,
1082
+ "step": 7550
1083
+ },
1084
+ {
1085
+ "epoch": 0.7652804350015104,
1086
+ "grad_norm": 22.59375,
1087
+ "learning_rate": 1.1957770190537627e-07,
1088
+ "loss": 19.0108,
1089
+ "step": 7600
1090
+ },
1091
+ {
1092
+ "epoch": 0.7703151747054677,
1093
+ "grad_norm": 28.8125,
1094
+ "learning_rate": 1.2036439731264848e-07,
1095
+ "loss": 18.9483,
1096
+ "step": 7650
1097
+ },
1098
+ {
1099
+ "epoch": 0.775349914409425,
1100
+ "grad_norm": 25.171875,
1101
+ "learning_rate": 1.2115109271992069e-07,
1102
+ "loss": 19.0207,
1103
+ "step": 7700
1104
+ },
1105
+ {
1106
+ "epoch": 0.7803846541133823,
1107
+ "grad_norm": 24.015625,
1108
+ "learning_rate": 1.2193778812719292e-07,
1109
+ "loss": 18.9183,
1110
+ "step": 7750
1111
+ },
1112
+ {
1113
+ "epoch": 0.7854193938173396,
1114
+ "grad_norm": 21.953125,
1115
+ "learning_rate": 1.2272448353446512e-07,
1116
+ "loss": 18.8943,
1117
+ "step": 7800
1118
+ },
1119
+ {
1120
+ "epoch": 0.7904541335212969,
1121
+ "grad_norm": 23.9375,
1122
+ "learning_rate": 1.2351117894173733e-07,
1123
+ "loss": 18.877,
1124
+ "step": 7850
1125
+ },
1126
+ {
1127
+ "epoch": 0.7954888732252543,
1128
+ "grad_norm": 23.796875,
1129
+ "learning_rate": 1.2429787434900954e-07,
1130
+ "loss": 18.7945,
1131
+ "step": 7900
1132
+ },
1133
+ {
1134
+ "epoch": 0.8005236129292116,
1135
+ "grad_norm": 23.484375,
1136
+ "learning_rate": 1.2508456975628177e-07,
1137
+ "loss": 18.8354,
1138
+ "step": 7950
1139
+ },
1140
+ {
1141
+ "epoch": 0.8055583526331689,
1142
+ "grad_norm": 23.84375,
1143
+ "learning_rate": 1.2587126516355397e-07,
1144
+ "loss": 18.9123,
1145
+ "step": 8000
1146
+ },
1147
+ {
1148
+ "epoch": 0.8105930923371262,
1149
+ "grad_norm": 22.8125,
1150
+ "learning_rate": 1.2665796057082618e-07,
1151
+ "loss": 18.7323,
1152
+ "step": 8050
1153
+ },
1154
+ {
1155
+ "epoch": 0.8156278320410835,
1156
+ "grad_norm": 22.4375,
1157
+ "learning_rate": 1.2744465597809839e-07,
1158
+ "loss": 18.7036,
1159
+ "step": 8100
1160
+ },
1161
+ {
1162
+ "epoch": 0.8206625717450408,
1163
+ "grad_norm": 23.953125,
1164
+ "learning_rate": 1.2823135138537062e-07,
1165
+ "loss": 18.7942,
1166
+ "step": 8150
1167
+ },
1168
+ {
1169
+ "epoch": 0.825697311448998,
1170
+ "grad_norm": 23.03125,
1171
+ "learning_rate": 1.2901804679264282e-07,
1172
+ "loss": 18.7461,
1173
+ "step": 8200
1174
+ },
1175
+ {
1176
+ "epoch": 0.8307320511529553,
1177
+ "grad_norm": 24.8125,
1178
+ "learning_rate": 1.2980474219991503e-07,
1179
+ "loss": 18.8245,
1180
+ "step": 8250
1181
+ },
1182
+ {
1183
+ "epoch": 0.8357667908569127,
1184
+ "grad_norm": 22.453125,
1185
+ "learning_rate": 1.3059143760718724e-07,
1186
+ "loss": 18.7245,
1187
+ "step": 8300
1188
+ },
1189
+ {
1190
+ "epoch": 0.84080153056087,
1191
+ "grad_norm": 23.609375,
1192
+ "learning_rate": 1.3137813301445947e-07,
1193
+ "loss": 18.7654,
1194
+ "step": 8350
1195
+ },
1196
+ {
1197
+ "epoch": 0.8458362702648273,
1198
+ "grad_norm": 22.078125,
1199
+ "learning_rate": 1.3216482842173165e-07,
1200
+ "loss": 18.6009,
1201
+ "step": 8400
1202
+ },
1203
+ {
1204
+ "epoch": 0.8508710099687846,
1205
+ "grad_norm": 23.015625,
1206
+ "learning_rate": 1.3295152382900388e-07,
1207
+ "loss": 18.7458,
1208
+ "step": 8450
1209
+ },
1210
+ {
1211
+ "epoch": 0.8559057496727419,
1212
+ "grad_norm": 24.578125,
1213
+ "learning_rate": 1.3373821923627609e-07,
1214
+ "loss": 18.7133,
1215
+ "step": 8500
1216
+ },
1217
+ {
1218
+ "epoch": 0.8609404893766992,
1219
+ "grad_norm": 20.953125,
1220
+ "learning_rate": 1.3452491464354832e-07,
1221
+ "loss": 18.6203,
1222
+ "step": 8550
1223
+ },
1224
+ {
1225
+ "epoch": 0.8659752290806565,
1226
+ "grad_norm": 28.0,
1227
+ "learning_rate": 1.353116100508205e-07,
1228
+ "loss": 18.6754,
1229
+ "step": 8600
1230
+ },
1231
+ {
1232
+ "epoch": 0.8710099687846138,
1233
+ "grad_norm": 23.390625,
1234
+ "learning_rate": 1.3609830545809273e-07,
1235
+ "loss": 18.5753,
1236
+ "step": 8650
1237
+ },
1238
+ {
1239
+ "epoch": 0.8760447084885712,
1240
+ "grad_norm": 21.296875,
1241
+ "learning_rate": 1.3688500086536494e-07,
1242
+ "loss": 18.5705,
1243
+ "step": 8700
1244
+ },
1245
+ {
1246
+ "epoch": 0.8810794481925285,
1247
+ "grad_norm": 22.875,
1248
+ "learning_rate": 1.3767169627263717e-07,
1249
+ "loss": 18.5268,
1250
+ "step": 8750
1251
+ },
1252
+ {
1253
+ "epoch": 0.8861141878964858,
1254
+ "grad_norm": 25.90625,
1255
+ "learning_rate": 1.3845839167990935e-07,
1256
+ "loss": 18.594,
1257
+ "step": 8800
1258
+ },
1259
+ {
1260
+ "epoch": 0.8911489276004431,
1261
+ "grad_norm": 24.171875,
1262
+ "learning_rate": 1.3924508708718158e-07,
1263
+ "loss": 18.4483,
1264
+ "step": 8850
1265
+ },
1266
+ {
1267
+ "epoch": 0.8961836673044004,
1268
+ "grad_norm": 24.59375,
1269
+ "learning_rate": 1.400317824944538e-07,
1270
+ "loss": 18.548,
1271
+ "step": 8900
1272
+ },
1273
+ {
1274
+ "epoch": 0.9012184070083576,
1275
+ "grad_norm": 23.34375,
1276
+ "learning_rate": 1.40818477901726e-07,
1277
+ "loss": 18.3815,
1278
+ "step": 8950
1279
+ },
1280
+ {
1281
+ "epoch": 0.9062531467123149,
1282
+ "grad_norm": 21.953125,
1283
+ "learning_rate": 1.4160517330899822e-07,
1284
+ "loss": 18.5225,
1285
+ "step": 9000
1286
+ },
1287
+ {
1288
+ "epoch": 0.9062531467123149,
1289
+ "eval_loss": 2.3123230934143066,
1290
+ "eval_runtime": 96.9463,
1291
+ "eval_samples_per_second": 2760.426,
1292
+ "eval_steps_per_second": 43.137,
1293
+ "step": 9000
1294
+ },
1295
+ {
1296
+ "epoch": 0.9112878864162722,
1297
+ "grad_norm": 23.21875,
1298
+ "learning_rate": 1.4239186871627043e-07,
1299
+ "loss": 18.4194,
1300
+ "step": 9050
1301
+ },
1302
+ {
1303
+ "epoch": 0.9163226261202296,
1304
+ "grad_norm": 22.3125,
1305
+ "learning_rate": 1.4317856412354266e-07,
1306
+ "loss": 18.4873,
1307
+ "step": 9100
1308
+ },
1309
+ {
1310
+ "epoch": 0.9213573658241869,
1311
+ "grad_norm": 21.03125,
1312
+ "learning_rate": 1.4396525953081484e-07,
1313
+ "loss": 18.2763,
1314
+ "step": 9150
1315
+ },
1316
+ {
1317
+ "epoch": 0.9263921055281442,
1318
+ "grad_norm": 22.40625,
1319
+ "learning_rate": 1.4475195493808707e-07,
1320
+ "loss": 18.5129,
1321
+ "step": 9200
1322
+ },
1323
+ {
1324
+ "epoch": 0.9314268452321015,
1325
+ "grad_norm": 20.890625,
1326
+ "learning_rate": 1.4553865034535928e-07,
1327
+ "loss": 18.3831,
1328
+ "step": 9250
1329
+ },
1330
+ {
1331
+ "epoch": 0.9364615849360588,
1332
+ "grad_norm": 27.0625,
1333
+ "learning_rate": 1.463253457526315e-07,
1334
+ "loss": 18.405,
1335
+ "step": 9300
1336
+ },
1337
+ {
1338
+ "epoch": 0.9414963246400161,
1339
+ "grad_norm": 24.390625,
1340
+ "learning_rate": 1.471120411599037e-07,
1341
+ "loss": 18.3264,
1342
+ "step": 9350
1343
+ },
1344
+ {
1345
+ "epoch": 0.9465310643439734,
1346
+ "grad_norm": 21.734375,
1347
+ "learning_rate": 1.4789873656717592e-07,
1348
+ "loss": 18.3415,
1349
+ "step": 9400
1350
+ },
1351
+ {
1352
+ "epoch": 0.9515658040479307,
1353
+ "grad_norm": 28.890625,
1354
+ "learning_rate": 1.4868543197444813e-07,
1355
+ "loss": 18.3986,
1356
+ "step": 9450
1357
+ },
1358
+ {
1359
+ "epoch": 0.9566005437518881,
1360
+ "grad_norm": 22.859375,
1361
+ "learning_rate": 1.4947212738172034e-07,
1362
+ "loss": 18.3425,
1363
+ "step": 9500
1364
+ },
1365
+ {
1366
+ "epoch": 0.9616352834558454,
1367
+ "grad_norm": 24.515625,
1368
+ "learning_rate": 1.5025882278899254e-07,
1369
+ "loss": 18.4341,
1370
+ "step": 9550
1371
+ },
1372
+ {
1373
+ "epoch": 0.9666700231598027,
1374
+ "grad_norm": 21.734375,
1375
+ "learning_rate": 1.5104551819626477e-07,
1376
+ "loss": 18.3468,
1377
+ "step": 9600
1378
+ },
1379
+ {
1380
+ "epoch": 0.97170476286376,
1381
+ "grad_norm": 21.46875,
1382
+ "learning_rate": 1.5183221360353698e-07,
1383
+ "loss": 18.2916,
1384
+ "step": 9650
1385
+ },
1386
+ {
1387
+ "epoch": 0.9767395025677172,
1388
+ "grad_norm": 23.53125,
1389
+ "learning_rate": 1.5261890901080919e-07,
1390
+ "loss": 18.268,
1391
+ "step": 9700
1392
+ },
1393
+ {
1394
+ "epoch": 0.9817742422716745,
1395
+ "grad_norm": 24.78125,
1396
+ "learning_rate": 1.534056044180814e-07,
1397
+ "loss": 18.3326,
1398
+ "step": 9750
1399
+ },
1400
+ {
1401
+ "epoch": 0.9868089819756318,
1402
+ "grad_norm": 25.328125,
1403
+ "learning_rate": 1.5419229982535362e-07,
1404
+ "loss": 18.1188,
1405
+ "step": 9800
1406
+ },
1407
+ {
1408
+ "epoch": 0.9918437216795891,
1409
+ "grad_norm": 23.5625,
1410
+ "learning_rate": 1.5497899523262583e-07,
1411
+ "loss": 18.2302,
1412
+ "step": 9850
1413
+ },
1414
+ {
1415
+ "epoch": 0.9968784613835465,
1416
+ "grad_norm": 22.390625,
1417
+ "learning_rate": 1.5576569063989804e-07,
1418
+ "loss": 18.2507,
1419
+ "step": 9900
1420
+ }
1421
+ ],
1422
+ "logging_steps": 50,
1423
+ "max_steps": 9931,
1424
+ "num_input_tokens_seen": 0,
1425
+ "num_train_epochs": 1,
1426
+ "save_steps": 5000,
1427
+ "stateful_callbacks": {
1428
+ "TrainerControl": {
1429
+ "args": {
1430
+ "should_epoch_stop": false,
1431
+ "should_evaluate": false,
1432
+ "should_log": false,
1433
+ "should_save": true,
1434
+ "should_training_stop": true
1435
+ },
1436
+ "attributes": {}
1437
+ }
1438
+ },
1439
+ "total_flos": 1.7341121073617306e+18,
1440
+ "train_batch_size": 8,
1441
+ "trial_name": null,
1442
+ "trial_params": null
1443
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cf9edd9886bd7aa99ffa86bacfcd8de0fa19c7e1479d5ab8a86f7cedb19bb10
3
+ size 5304