CocoRoF commited on
Commit
261bbea
·
verified ·
1 Parent(s): 84c0b61

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "answerdotai/ModernBERT-Large-Instruct",
3
+ "architectures": [
4
+ "ModernBertForMaskedLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 1024,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 2624,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 16,
36
+ "num_hidden_layers": 28,
37
+ "pad_token_id": 50283,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": true,
40
+ "repad_logits_with_grad": false,
41
+ "sep_token_id": 50282,
42
+ "sparse_pred_ignore_index": -100,
43
+ "sparse_prediction": false,
44
+ "torch_dtype": "float16",
45
+ "transformers_version": "4.49.0",
46
+ "vocab_size": 50368
47
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68287c18f880a50ea1f55ab9e918f690ebd87aaf716c5e066f0052277de8c1fd
3
+ size 791781368
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d401706fe0db31f3a43b074a2e6bb9f0530ba55c63bbda7473480ffbc1acd15b
3
+ size 2375487866
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25a66bce66c09652383a0839fbbe1e8187db02fbdfb7a47d70ae88b467cd642
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 sha256:1c1a9c65c2869356282cad6b4a0f7dff7f4dd68ab3d9d216c72b7d6cb524f860
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:c3447ca6cc16e14aea98b2269a3aa4e5446a87729acbfec0746d24b1cbb51286
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 +1,946 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "|||IP_ADDRESS|||",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": false
11
+ },
12
+ "1": {
13
+ "content": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50254": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50277": {
205
+ "content": "|||EMAIL_ADDRESS|||",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50278": {
213
+ "content": "|||PHONE_NUMBER|||",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50279": {
221
+ "content": "<|endoftext|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "50280": {
229
+ "content": "[UNK]",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "50281": {
237
+ "content": "[CLS]",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "50282": {
245
+ "content": "[SEP]",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "50283": {
253
+ "content": "[PAD]",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "50284": {
261
+ "content": "[MASK]",
262
+ "lstrip": true,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "50285": {
269
+ "content": "[unused0]",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50286": {
277
+ "content": "[unused1]",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50287": {
285
+ "content": "[unused2]",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50288": {
293
+ "content": "[unused3]",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50289": {
301
+ "content": "[unused4]",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50290": {
309
+ "content": "[unused5]",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "50291": {
317
+ "content": "[unused6]",
318
+ "lstrip": false,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ },
324
+ "50292": {
325
+ "content": "[unused7]",
326
+ "lstrip": false,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ },
332
+ "50293": {
333
+ "content": "[unused8]",
334
+ "lstrip": false,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": false
339
+ },
340
+ "50294": {
341
+ "content": "[unused9]",
342
+ "lstrip": false,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": false
347
+ },
348
+ "50295": {
349
+ "content": "[unused10]",
350
+ "lstrip": false,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": false
355
+ },
356
+ "50296": {
357
+ "content": "[unused11]",
358
+ "lstrip": false,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false
363
+ },
364
+ "50297": {
365
+ "content": "[unused12]",
366
+ "lstrip": false,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": false
371
+ },
372
+ "50298": {
373
+ "content": "[unused13]",
374
+ "lstrip": false,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": false
379
+ },
380
+ "50299": {
381
+ "content": "[unused14]",
382
+ "lstrip": false,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": false
387
+ },
388
+ "50300": {
389
+ "content": "[unused15]",
390
+ "lstrip": false,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": false
395
+ },
396
+ "50301": {
397
+ "content": "[unused16]",
398
+ "lstrip": false,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": false
403
+ },
404
+ "50302": {
405
+ "content": "[unused17]",
406
+ "lstrip": false,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "50303": {
413
+ "content": "[unused18]",
414
+ "lstrip": false,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "50304": {
421
+ "content": "[unused19]",
422
+ "lstrip": false,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "50305": {
429
+ "content": "[unused20]",
430
+ "lstrip": false,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ },
436
+ "50306": {
437
+ "content": "[unused21]",
438
+ "lstrip": false,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": false
443
+ },
444
+ "50307": {
445
+ "content": "[unused22]",
446
+ "lstrip": false,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": false
451
+ },
452
+ "50308": {
453
+ "content": "[unused23]",
454
+ "lstrip": false,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": false
459
+ },
460
+ "50309": {
461
+ "content": "[unused24]",
462
+ "lstrip": false,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": false
467
+ },
468
+ "50310": {
469
+ "content": "[unused25]",
470
+ "lstrip": false,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": false
475
+ },
476
+ "50311": {
477
+ "content": "[unused26]",
478
+ "lstrip": false,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": false
483
+ },
484
+ "50312": {
485
+ "content": "[unused27]",
486
+ "lstrip": false,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": false
491
+ },
492
+ "50313": {
493
+ "content": "[unused28]",
494
+ "lstrip": false,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": false
499
+ },
500
+ "50314": {
501
+ "content": "[unused29]",
502
+ "lstrip": false,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": false
507
+ },
508
+ "50315": {
509
+ "content": "[unused30]",
510
+ "lstrip": false,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": false
515
+ },
516
+ "50316": {
517
+ "content": "[unused31]",
518
+ "lstrip": false,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": false
523
+ },
524
+ "50317": {
525
+ "content": "[unused32]",
526
+ "lstrip": false,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": false
531
+ },
532
+ "50318": {
533
+ "content": "[unused33]",
534
+ "lstrip": false,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": false
539
+ },
540
+ "50319": {
541
+ "content": "[unused34]",
542
+ "lstrip": false,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": false
547
+ },
548
+ "50320": {
549
+ "content": "[unused35]",
550
+ "lstrip": false,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": false
555
+ },
556
+ "50321": {
557
+ "content": "[unused36]",
558
+ "lstrip": false,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": false
563
+ },
564
+ "50322": {
565
+ "content": "[unused37]",
566
+ "lstrip": false,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": false
571
+ },
572
+ "50323": {
573
+ "content": "[unused38]",
574
+ "lstrip": false,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": false
579
+ },
580
+ "50324": {
581
+ "content": "[unused39]",
582
+ "lstrip": false,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": false
587
+ },
588
+ "50325": {
589
+ "content": "[unused40]",
590
+ "lstrip": false,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": false
595
+ },
596
+ "50326": {
597
+ "content": "[unused41]",
598
+ "lstrip": false,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": false
603
+ },
604
+ "50327": {
605
+ "content": "[unused42]",
606
+ "lstrip": false,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": false
611
+ },
612
+ "50328": {
613
+ "content": "[unused43]",
614
+ "lstrip": false,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": false
619
+ },
620
+ "50329": {
621
+ "content": "[unused44]",
622
+ "lstrip": false,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": false
627
+ },
628
+ "50330": {
629
+ "content": "[unused45]",
630
+ "lstrip": false,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": false
635
+ },
636
+ "50331": {
637
+ "content": "[unused46]",
638
+ "lstrip": false,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": false
643
+ },
644
+ "50332": {
645
+ "content": "[unused47]",
646
+ "lstrip": false,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": false
651
+ },
652
+ "50333": {
653
+ "content": "[unused48]",
654
+ "lstrip": false,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": false
659
+ },
660
+ "50334": {
661
+ "content": "[unused49]",
662
+ "lstrip": false,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": false
667
+ },
668
+ "50335": {
669
+ "content": "[unused50]",
670
+ "lstrip": false,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": false
675
+ },
676
+ "50336": {
677
+ "content": "[unused51]",
678
+ "lstrip": false,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": false
683
+ },
684
+ "50337": {
685
+ "content": "[unused52]",
686
+ "lstrip": false,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": false
691
+ },
692
+ "50338": {
693
+ "content": "[unused53]",
694
+ "lstrip": false,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": false
699
+ },
700
+ "50339": {
701
+ "content": "[unused54]",
702
+ "lstrip": false,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": false
707
+ },
708
+ "50340": {
709
+ "content": "[unused55]",
710
+ "lstrip": false,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": false
715
+ },
716
+ "50341": {
717
+ "content": "[unused56]",
718
+ "lstrip": false,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": false
723
+ },
724
+ "50342": {
725
+ "content": "[unused57]",
726
+ "lstrip": false,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": false
731
+ },
732
+ "50343": {
733
+ "content": "[unused58]",
734
+ "lstrip": false,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": false
739
+ },
740
+ "50344": {
741
+ "content": "[unused59]",
742
+ "lstrip": false,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": false
747
+ },
748
+ "50345": {
749
+ "content": "[unused60]",
750
+ "lstrip": false,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": false
755
+ },
756
+ "50346": {
757
+ "content": "[unused61]",
758
+ "lstrip": false,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": false
763
+ },
764
+ "50347": {
765
+ "content": "[unused62]",
766
+ "lstrip": false,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": false
771
+ },
772
+ "50348": {
773
+ "content": "[unused63]",
774
+ "lstrip": false,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": false
779
+ },
780
+ "50349": {
781
+ "content": "[unused64]",
782
+ "lstrip": false,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": false
787
+ },
788
+ "50350": {
789
+ "content": "[unused65]",
790
+ "lstrip": false,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": false
795
+ },
796
+ "50351": {
797
+ "content": "[unused66]",
798
+ "lstrip": false,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": false
803
+ },
804
+ "50352": {
805
+ "content": "[unused67]",
806
+ "lstrip": false,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": false
811
+ },
812
+ "50353": {
813
+ "content": "[unused68]",
814
+ "lstrip": false,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": false
819
+ },
820
+ "50354": {
821
+ "content": "[unused69]",
822
+ "lstrip": false,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": false
827
+ },
828
+ "50355": {
829
+ "content": "[unused70]",
830
+ "lstrip": false,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": false
835
+ },
836
+ "50356": {
837
+ "content": "[unused71]",
838
+ "lstrip": false,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": false
843
+ },
844
+ "50357": {
845
+ "content": "[unused72]",
846
+ "lstrip": false,
847
+ "normalized": true,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": false
851
+ },
852
+ "50358": {
853
+ "content": "[unused73]",
854
+ "lstrip": false,
855
+ "normalized": true,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": false
859
+ },
860
+ "50359": {
861
+ "content": "[unused74]",
862
+ "lstrip": false,
863
+ "normalized": true,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": false
867
+ },
868
+ "50360": {
869
+ "content": "[unused75]",
870
+ "lstrip": false,
871
+ "normalized": true,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": false
875
+ },
876
+ "50361": {
877
+ "content": "[unused76]",
878
+ "lstrip": false,
879
+ "normalized": true,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": false
883
+ },
884
+ "50362": {
885
+ "content": "[unused77]",
886
+ "lstrip": false,
887
+ "normalized": true,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": false
891
+ },
892
+ "50363": {
893
+ "content": "[unused78]",
894
+ "lstrip": false,
895
+ "normalized": true,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": false
899
+ },
900
+ "50364": {
901
+ "content": "[unused79]",
902
+ "lstrip": false,
903
+ "normalized": true,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": false
907
+ },
908
+ "50365": {
909
+ "content": "[unused80]",
910
+ "lstrip": false,
911
+ "normalized": true,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": false
915
+ },
916
+ "50366": {
917
+ "content": "[unused81]",
918
+ "lstrip": false,
919
+ "normalized": true,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": false
923
+ },
924
+ "50367": {
925
+ "content": "[unused82]",
926
+ "lstrip": false,
927
+ "normalized": true,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": false
931
+ }
932
+ },
933
+ "clean_up_tokenization_spaces": true,
934
+ "cls_token": "[CLS]",
935
+ "extra_special_tokens": {},
936
+ "mask_token": "[MASK]",
937
+ "model_input_names": [
938
+ "input_ids",
939
+ "attention_mask"
940
+ ],
941
+ "model_max_length": 1000000000000000019884624838656,
942
+ "pad_token": "[PAD]",
943
+ "sep_token": "[SEP]",
944
+ "tokenizer_class": "PreTrainedTokenizer",
945
+ "unk_token": "[UNK]"
946
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1441 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.4381101025451459,
5
+ "eval_steps": 1000,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0021905505127257294,
13
+ "grad_norm": 13096.0,
14
+ "learning_rate": 4.366812227074236e-07,
15
+ "loss": 742.6802,
16
+ "step": 5
17
+ },
18
+ {
19
+ "epoch": 0.004381101025451459,
20
+ "grad_norm": 90.625,
21
+ "learning_rate": 8.733624454148472e-07,
22
+ "loss": 111.4364,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.006571651538177188,
27
+ "grad_norm": 64.625,
28
+ "learning_rate": 1.3100436681222709e-06,
29
+ "loss": 44.6282,
30
+ "step": 15
31
+ },
32
+ {
33
+ "epoch": 0.008762202050902917,
34
+ "grad_norm": 56.09375,
35
+ "learning_rate": 1.7467248908296944e-06,
36
+ "loss": 44.0656,
37
+ "step": 20
38
+ },
39
+ {
40
+ "epoch": 0.010952752563628647,
41
+ "grad_norm": 40.4375,
42
+ "learning_rate": 2.183406113537118e-06,
43
+ "loss": 41.889,
44
+ "step": 25
45
+ },
46
+ {
47
+ "epoch": 0.013143303076354376,
48
+ "grad_norm": 50.6875,
49
+ "learning_rate": 2.6200873362445417e-06,
50
+ "loss": 40.9611,
51
+ "step": 30
52
+ },
53
+ {
54
+ "epoch": 0.015333853589080106,
55
+ "grad_norm": 34.125,
56
+ "learning_rate": 3.0567685589519653e-06,
57
+ "loss": 40.9319,
58
+ "step": 35
59
+ },
60
+ {
61
+ "epoch": 0.017524404101805835,
62
+ "grad_norm": 37.34375,
63
+ "learning_rate": 3.493449781659389e-06,
64
+ "loss": 41.2922,
65
+ "step": 40
66
+ },
67
+ {
68
+ "epoch": 0.019714954614531564,
69
+ "grad_norm": 30.140625,
70
+ "learning_rate": 3.930131004366812e-06,
71
+ "loss": 39.5204,
72
+ "step": 45
73
+ },
74
+ {
75
+ "epoch": 0.021905505127257294,
76
+ "grad_norm": 30.953125,
77
+ "learning_rate": 4.366812227074236e-06,
78
+ "loss": 39.9045,
79
+ "step": 50
80
+ },
81
+ {
82
+ "epoch": 0.024096055639983023,
83
+ "grad_norm": 30.453125,
84
+ "learning_rate": 4.80349344978166e-06,
85
+ "loss": 40.7265,
86
+ "step": 55
87
+ },
88
+ {
89
+ "epoch": 0.026286606152708752,
90
+ "grad_norm": 32.65625,
91
+ "learning_rate": 5.2401746724890834e-06,
92
+ "loss": 39.5216,
93
+ "step": 60
94
+ },
95
+ {
96
+ "epoch": 0.028477156665434482,
97
+ "grad_norm": 4284.0,
98
+ "learning_rate": 5.676855895196507e-06,
99
+ "loss": 50.5946,
100
+ "step": 65
101
+ },
102
+ {
103
+ "epoch": 0.03066770717816021,
104
+ "grad_norm": 1012.0,
105
+ "learning_rate": 6.1135371179039305e-06,
106
+ "loss": 55.345,
107
+ "step": 70
108
+ },
109
+ {
110
+ "epoch": 0.03285825769088594,
111
+ "grad_norm": 662.5,
112
+ "learning_rate": 6.550218340611354e-06,
113
+ "loss": 72.4566,
114
+ "step": 75
115
+ },
116
+ {
117
+ "epoch": 0.03504880820361167,
118
+ "grad_norm": 92.875,
119
+ "learning_rate": 6.986899563318778e-06,
120
+ "loss": 50.0984,
121
+ "step": 80
122
+ },
123
+ {
124
+ "epoch": 0.0372393587163374,
125
+ "grad_norm": 33.5,
126
+ "learning_rate": 7.423580786026201e-06,
127
+ "loss": 42.5405,
128
+ "step": 85
129
+ },
130
+ {
131
+ "epoch": 0.03942990922906313,
132
+ "grad_norm": 32.3125,
133
+ "learning_rate": 7.860262008733624e-06,
134
+ "loss": 40.9513,
135
+ "step": 90
136
+ },
137
+ {
138
+ "epoch": 0.04162045974178886,
139
+ "grad_norm": 73.125,
140
+ "learning_rate": 8.296943231441049e-06,
141
+ "loss": 39.5486,
142
+ "step": 95
143
+ },
144
+ {
145
+ "epoch": 0.04381101025451459,
146
+ "grad_norm": 36.5625,
147
+ "learning_rate": 8.733624454148473e-06,
148
+ "loss": 38.6845,
149
+ "step": 100
150
+ },
151
+ {
152
+ "epoch": 0.04600156076724032,
153
+ "grad_norm": 28.875,
154
+ "learning_rate": 9.170305676855896e-06,
155
+ "loss": 40.9694,
156
+ "step": 105
157
+ },
158
+ {
159
+ "epoch": 0.048192111279966046,
160
+ "grad_norm": 30.09375,
161
+ "learning_rate": 9.60698689956332e-06,
162
+ "loss": 40.6168,
163
+ "step": 110
164
+ },
165
+ {
166
+ "epoch": 0.050382661792691776,
167
+ "grad_norm": 28.40625,
168
+ "learning_rate": 1.0043668122270742e-05,
169
+ "loss": 39.6493,
170
+ "step": 115
171
+ },
172
+ {
173
+ "epoch": 0.052573212305417505,
174
+ "grad_norm": 33.90625,
175
+ "learning_rate": 1.0480349344978167e-05,
176
+ "loss": 38.692,
177
+ "step": 120
178
+ },
179
+ {
180
+ "epoch": 0.054763762818143234,
181
+ "grad_norm": 24.046875,
182
+ "learning_rate": 1.0917030567685592e-05,
183
+ "loss": 39.2953,
184
+ "step": 125
185
+ },
186
+ {
187
+ "epoch": 0.056954313330868964,
188
+ "grad_norm": 50.1875,
189
+ "learning_rate": 1.1353711790393014e-05,
190
+ "loss": 39.2942,
191
+ "step": 130
192
+ },
193
+ {
194
+ "epoch": 0.05914486384359469,
195
+ "grad_norm": 25.578125,
196
+ "learning_rate": 1.179039301310044e-05,
197
+ "loss": 40.2007,
198
+ "step": 135
199
+ },
200
+ {
201
+ "epoch": 0.06133541435632042,
202
+ "grad_norm": 24.453125,
203
+ "learning_rate": 1.2227074235807861e-05,
204
+ "loss": 40.4033,
205
+ "step": 140
206
+ },
207
+ {
208
+ "epoch": 0.06352596486904616,
209
+ "grad_norm": 25.109375,
210
+ "learning_rate": 1.2663755458515286e-05,
211
+ "loss": 40.2883,
212
+ "step": 145
213
+ },
214
+ {
215
+ "epoch": 0.06571651538177188,
216
+ "grad_norm": 24.3125,
217
+ "learning_rate": 1.3100436681222708e-05,
218
+ "loss": 38.8529,
219
+ "step": 150
220
+ },
221
+ {
222
+ "epoch": 0.06790706589449762,
223
+ "grad_norm": 33.03125,
224
+ "learning_rate": 1.3537117903930132e-05,
225
+ "loss": 40.0824,
226
+ "step": 155
227
+ },
228
+ {
229
+ "epoch": 0.07009761640722334,
230
+ "grad_norm": 36.375,
231
+ "learning_rate": 1.3973799126637555e-05,
232
+ "loss": 40.8283,
233
+ "step": 160
234
+ },
235
+ {
236
+ "epoch": 0.07228816691994908,
237
+ "grad_norm": 32.375,
238
+ "learning_rate": 1.4410480349344979e-05,
239
+ "loss": 38.3279,
240
+ "step": 165
241
+ },
242
+ {
243
+ "epoch": 0.0744787174326748,
244
+ "grad_norm": 23.328125,
245
+ "learning_rate": 1.4847161572052402e-05,
246
+ "loss": 39.6786,
247
+ "step": 170
248
+ },
249
+ {
250
+ "epoch": 0.07666926794540053,
251
+ "grad_norm": 33.65625,
252
+ "learning_rate": 1.5283842794759826e-05,
253
+ "loss": 39.6196,
254
+ "step": 175
255
+ },
256
+ {
257
+ "epoch": 0.07885981845812626,
258
+ "grad_norm": 34.46875,
259
+ "learning_rate": 1.5720524017467248e-05,
260
+ "loss": 39.4438,
261
+ "step": 180
262
+ },
263
+ {
264
+ "epoch": 0.081050368970852,
265
+ "grad_norm": 38.03125,
266
+ "learning_rate": 1.6157205240174673e-05,
267
+ "loss": 39.3557,
268
+ "step": 185
269
+ },
270
+ {
271
+ "epoch": 0.08324091948357772,
272
+ "grad_norm": 45.59375,
273
+ "learning_rate": 1.6593886462882098e-05,
274
+ "loss": 39.7753,
275
+ "step": 190
276
+ },
277
+ {
278
+ "epoch": 0.08543146999630345,
279
+ "grad_norm": 42.0625,
280
+ "learning_rate": 1.703056768558952e-05,
281
+ "loss": 38.6387,
282
+ "step": 195
283
+ },
284
+ {
285
+ "epoch": 0.08762202050902917,
286
+ "grad_norm": 31.296875,
287
+ "learning_rate": 1.7467248908296945e-05,
288
+ "loss": 38.944,
289
+ "step": 200
290
+ },
291
+ {
292
+ "epoch": 0.08981257102175491,
293
+ "grad_norm": 23.0,
294
+ "learning_rate": 1.7903930131004367e-05,
295
+ "loss": 39.5787,
296
+ "step": 205
297
+ },
298
+ {
299
+ "epoch": 0.09200312153448063,
300
+ "grad_norm": 31.796875,
301
+ "learning_rate": 1.8340611353711792e-05,
302
+ "loss": 40.2236,
303
+ "step": 210
304
+ },
305
+ {
306
+ "epoch": 0.09419367204720637,
307
+ "grad_norm": 31.796875,
308
+ "learning_rate": 1.8777292576419214e-05,
309
+ "loss": 39.7339,
310
+ "step": 215
311
+ },
312
+ {
313
+ "epoch": 0.09638422255993209,
314
+ "grad_norm": 48.78125,
315
+ "learning_rate": 1.921397379912664e-05,
316
+ "loss": 41.8436,
317
+ "step": 220
318
+ },
319
+ {
320
+ "epoch": 0.09857477307265783,
321
+ "grad_norm": 385.25,
322
+ "learning_rate": 1.965065502183406e-05,
323
+ "loss": 44.5202,
324
+ "step": 225
325
+ },
326
+ {
327
+ "epoch": 0.10076532358538355,
328
+ "grad_norm": 39.03125,
329
+ "learning_rate": 1.9990258158792012e-05,
330
+ "loss": 45.2576,
331
+ "step": 230
332
+ },
333
+ {
334
+ "epoch": 0.10295587409810929,
335
+ "grad_norm": 29.96875,
336
+ "learning_rate": 1.994154895275207e-05,
337
+ "loss": 42.9545,
338
+ "step": 235
339
+ },
340
+ {
341
+ "epoch": 0.10514642461083501,
342
+ "grad_norm": 26.09375,
343
+ "learning_rate": 1.989283974671213e-05,
344
+ "loss": 41.42,
345
+ "step": 240
346
+ },
347
+ {
348
+ "epoch": 0.10733697512356075,
349
+ "grad_norm": 28.609375,
350
+ "learning_rate": 1.984413054067219e-05,
351
+ "loss": 40.9569,
352
+ "step": 245
353
+ },
354
+ {
355
+ "epoch": 0.10952752563628647,
356
+ "grad_norm": 45.03125,
357
+ "learning_rate": 1.979542133463225e-05,
358
+ "loss": 43.257,
359
+ "step": 250
360
+ },
361
+ {
362
+ "epoch": 0.1117180761490122,
363
+ "grad_norm": 31.65625,
364
+ "learning_rate": 1.9746712128592305e-05,
365
+ "loss": 43.1437,
366
+ "step": 255
367
+ },
368
+ {
369
+ "epoch": 0.11390862666173793,
370
+ "grad_norm": 24.5,
371
+ "learning_rate": 1.9698002922552364e-05,
372
+ "loss": 40.8937,
373
+ "step": 260
374
+ },
375
+ {
376
+ "epoch": 0.11609917717446366,
377
+ "grad_norm": 37.34375,
378
+ "learning_rate": 1.9649293716512423e-05,
379
+ "loss": 41.702,
380
+ "step": 265
381
+ },
382
+ {
383
+ "epoch": 0.11828972768718939,
384
+ "grad_norm": 28.078125,
385
+ "learning_rate": 1.960058451047248e-05,
386
+ "loss": 40.8823,
387
+ "step": 270
388
+ },
389
+ {
390
+ "epoch": 0.12048027819991512,
391
+ "grad_norm": 30.703125,
392
+ "learning_rate": 1.955187530443254e-05,
393
+ "loss": 41.0227,
394
+ "step": 275
395
+ },
396
+ {
397
+ "epoch": 0.12267082871264084,
398
+ "grad_norm": 28.703125,
399
+ "learning_rate": 1.9503166098392598e-05,
400
+ "loss": 41.8211,
401
+ "step": 280
402
+ },
403
+ {
404
+ "epoch": 0.12486137922536658,
405
+ "grad_norm": 40.5625,
406
+ "learning_rate": 1.9454456892352657e-05,
407
+ "loss": 40.5589,
408
+ "step": 285
409
+ },
410
+ {
411
+ "epoch": 0.12705192973809232,
412
+ "grad_norm": 32.625,
413
+ "learning_rate": 1.9405747686312716e-05,
414
+ "loss": 40.9865,
415
+ "step": 290
416
+ },
417
+ {
418
+ "epoch": 0.12924248025081803,
419
+ "grad_norm": 67.3125,
420
+ "learning_rate": 1.9357038480272775e-05,
421
+ "loss": 40.3525,
422
+ "step": 295
423
+ },
424
+ {
425
+ "epoch": 0.13143303076354376,
426
+ "grad_norm": 32.3125,
427
+ "learning_rate": 1.930832927423283e-05,
428
+ "loss": 40.1777,
429
+ "step": 300
430
+ },
431
+ {
432
+ "epoch": 0.1336235812762695,
433
+ "grad_norm": 24.765625,
434
+ "learning_rate": 1.925962006819289e-05,
435
+ "loss": 39.8659,
436
+ "step": 305
437
+ },
438
+ {
439
+ "epoch": 0.13581413178899523,
440
+ "grad_norm": 26.921875,
441
+ "learning_rate": 1.921091086215295e-05,
442
+ "loss": 41.8758,
443
+ "step": 310
444
+ },
445
+ {
446
+ "epoch": 0.13800468230172094,
447
+ "grad_norm": 30.34375,
448
+ "learning_rate": 1.9162201656113005e-05,
449
+ "loss": 40.2781,
450
+ "step": 315
451
+ },
452
+ {
453
+ "epoch": 0.14019523281444668,
454
+ "grad_norm": 100.1875,
455
+ "learning_rate": 1.9113492450073065e-05,
456
+ "loss": 38.3503,
457
+ "step": 320
458
+ },
459
+ {
460
+ "epoch": 0.14238578332717242,
461
+ "grad_norm": 30.6875,
462
+ "learning_rate": 1.9064783244033124e-05,
463
+ "loss": 41.6195,
464
+ "step": 325
465
+ },
466
+ {
467
+ "epoch": 0.14457633383989815,
468
+ "grad_norm": 31.53125,
469
+ "learning_rate": 1.9016074037993183e-05,
470
+ "loss": 40.62,
471
+ "step": 330
472
+ },
473
+ {
474
+ "epoch": 0.14676688435262386,
475
+ "grad_norm": 32.75,
476
+ "learning_rate": 1.8967364831953242e-05,
477
+ "loss": 48.5258,
478
+ "step": 335
479
+ },
480
+ {
481
+ "epoch": 0.1489574348653496,
482
+ "grad_norm": 21.390625,
483
+ "learning_rate": 1.8918655625913298e-05,
484
+ "loss": 41.4756,
485
+ "step": 340
486
+ },
487
+ {
488
+ "epoch": 0.15114798537807533,
489
+ "grad_norm": 31.734375,
490
+ "learning_rate": 1.8869946419873357e-05,
491
+ "loss": 40.7427,
492
+ "step": 345
493
+ },
494
+ {
495
+ "epoch": 0.15333853589080107,
496
+ "grad_norm": 47.53125,
497
+ "learning_rate": 1.8821237213833417e-05,
498
+ "loss": 40.1635,
499
+ "step": 350
500
+ },
501
+ {
502
+ "epoch": 0.15552908640352678,
503
+ "grad_norm": 25.46875,
504
+ "learning_rate": 1.8772528007793472e-05,
505
+ "loss": 40.0878,
506
+ "step": 355
507
+ },
508
+ {
509
+ "epoch": 0.15771963691625251,
510
+ "grad_norm": 29.828125,
511
+ "learning_rate": 1.872381880175353e-05,
512
+ "loss": 41.3363,
513
+ "step": 360
514
+ },
515
+ {
516
+ "epoch": 0.15991018742897825,
517
+ "grad_norm": 32.65625,
518
+ "learning_rate": 1.867510959571359e-05,
519
+ "loss": 40.1477,
520
+ "step": 365
521
+ },
522
+ {
523
+ "epoch": 0.162100737941704,
524
+ "grad_norm": 27.765625,
525
+ "learning_rate": 1.862640038967365e-05,
526
+ "loss": 39.9975,
527
+ "step": 370
528
+ },
529
+ {
530
+ "epoch": 0.1642912884544297,
531
+ "grad_norm": 21.671875,
532
+ "learning_rate": 1.857769118363371e-05,
533
+ "loss": 40.2893,
534
+ "step": 375
535
+ },
536
+ {
537
+ "epoch": 0.16648183896715543,
538
+ "grad_norm": 19.515625,
539
+ "learning_rate": 1.852898197759377e-05,
540
+ "loss": 38.7055,
541
+ "step": 380
542
+ },
543
+ {
544
+ "epoch": 0.16867238947988117,
545
+ "grad_norm": 162.625,
546
+ "learning_rate": 1.8480272771553824e-05,
547
+ "loss": 48.099,
548
+ "step": 385
549
+ },
550
+ {
551
+ "epoch": 0.1708629399926069,
552
+ "grad_norm": 29.8125,
553
+ "learning_rate": 1.8431563565513884e-05,
554
+ "loss": 48.3286,
555
+ "step": 390
556
+ },
557
+ {
558
+ "epoch": 0.1730534905053326,
559
+ "grad_norm": 34.5625,
560
+ "learning_rate": 1.8382854359473943e-05,
561
+ "loss": 40.6334,
562
+ "step": 395
563
+ },
564
+ {
565
+ "epoch": 0.17524404101805835,
566
+ "grad_norm": 20.9375,
567
+ "learning_rate": 1.8334145153434e-05,
568
+ "loss": 39.5327,
569
+ "step": 400
570
+ },
571
+ {
572
+ "epoch": 0.17743459153078409,
573
+ "grad_norm": 24.359375,
574
+ "learning_rate": 1.8285435947394058e-05,
575
+ "loss": 38.2548,
576
+ "step": 405
577
+ },
578
+ {
579
+ "epoch": 0.17962514204350982,
580
+ "grad_norm": 26.109375,
581
+ "learning_rate": 1.8236726741354117e-05,
582
+ "loss": 39.5699,
583
+ "step": 410
584
+ },
585
+ {
586
+ "epoch": 0.18181569255623553,
587
+ "grad_norm": 74.4375,
588
+ "learning_rate": 1.8188017535314176e-05,
589
+ "loss": 40.1855,
590
+ "step": 415
591
+ },
592
+ {
593
+ "epoch": 0.18400624306896127,
594
+ "grad_norm": 38.1875,
595
+ "learning_rate": 1.8139308329274236e-05,
596
+ "loss": 39.2502,
597
+ "step": 420
598
+ },
599
+ {
600
+ "epoch": 0.186196793581687,
601
+ "grad_norm": 19.75,
602
+ "learning_rate": 1.8090599123234295e-05,
603
+ "loss": 38.5868,
604
+ "step": 425
605
+ },
606
+ {
607
+ "epoch": 0.18838734409441274,
608
+ "grad_norm": 22.546875,
609
+ "learning_rate": 1.804188991719435e-05,
610
+ "loss": 38.2078,
611
+ "step": 430
612
+ },
613
+ {
614
+ "epoch": 0.19057789460713845,
615
+ "grad_norm": 32.96875,
616
+ "learning_rate": 1.799318071115441e-05,
617
+ "loss": 38.6803,
618
+ "step": 435
619
+ },
620
+ {
621
+ "epoch": 0.19276844511986418,
622
+ "grad_norm": 36.75,
623
+ "learning_rate": 1.794447150511447e-05,
624
+ "loss": 39.3906,
625
+ "step": 440
626
+ },
627
+ {
628
+ "epoch": 0.19495899563258992,
629
+ "grad_norm": 23.71875,
630
+ "learning_rate": 1.7895762299074525e-05,
631
+ "loss": 38.3763,
632
+ "step": 445
633
+ },
634
+ {
635
+ "epoch": 0.19714954614531566,
636
+ "grad_norm": 26.328125,
637
+ "learning_rate": 1.7847053093034584e-05,
638
+ "loss": 37.9731,
639
+ "step": 450
640
+ },
641
+ {
642
+ "epoch": 0.19934009665804137,
643
+ "grad_norm": 27.03125,
644
+ "learning_rate": 1.7798343886994643e-05,
645
+ "loss": 39.5706,
646
+ "step": 455
647
+ },
648
+ {
649
+ "epoch": 0.2015306471707671,
650
+ "grad_norm": 17.046875,
651
+ "learning_rate": 1.7749634680954703e-05,
652
+ "loss": 38.7336,
653
+ "step": 460
654
+ },
655
+ {
656
+ "epoch": 0.20372119768349284,
657
+ "grad_norm": 24.59375,
658
+ "learning_rate": 1.7700925474914762e-05,
659
+ "loss": 38.5834,
660
+ "step": 465
661
+ },
662
+ {
663
+ "epoch": 0.20591174819621857,
664
+ "grad_norm": 33.5625,
665
+ "learning_rate": 1.7652216268874818e-05,
666
+ "loss": 39.1163,
667
+ "step": 470
668
+ },
669
+ {
670
+ "epoch": 0.20810229870894428,
671
+ "grad_norm": 28.875,
672
+ "learning_rate": 1.7603507062834877e-05,
673
+ "loss": 39.7169,
674
+ "step": 475
675
+ },
676
+ {
677
+ "epoch": 0.21029284922167002,
678
+ "grad_norm": 26.0625,
679
+ "learning_rate": 1.7554797856794936e-05,
680
+ "loss": 38.2182,
681
+ "step": 480
682
+ },
683
+ {
684
+ "epoch": 0.21248339973439576,
685
+ "grad_norm": 25.265625,
686
+ "learning_rate": 1.7506088650754992e-05,
687
+ "loss": 38.4219,
688
+ "step": 485
689
+ },
690
+ {
691
+ "epoch": 0.2146739502471215,
692
+ "grad_norm": 40.53125,
693
+ "learning_rate": 1.745737944471505e-05,
694
+ "loss": 39.3143,
695
+ "step": 490
696
+ },
697
+ {
698
+ "epoch": 0.2168645007598472,
699
+ "grad_norm": 28.828125,
700
+ "learning_rate": 1.740867023867511e-05,
701
+ "loss": 38.7423,
702
+ "step": 495
703
+ },
704
+ {
705
+ "epoch": 0.21905505127257294,
706
+ "grad_norm": 19.84375,
707
+ "learning_rate": 1.735996103263517e-05,
708
+ "loss": 37.1676,
709
+ "step": 500
710
+ },
711
+ {
712
+ "epoch": 0.22124560178529867,
713
+ "grad_norm": 22.0625,
714
+ "learning_rate": 1.731125182659523e-05,
715
+ "loss": 38.0275,
716
+ "step": 505
717
+ },
718
+ {
719
+ "epoch": 0.2234361522980244,
720
+ "grad_norm": 45.5,
721
+ "learning_rate": 1.7262542620555288e-05,
722
+ "loss": 37.0928,
723
+ "step": 510
724
+ },
725
+ {
726
+ "epoch": 0.22562670281075012,
727
+ "grad_norm": 40.5625,
728
+ "learning_rate": 1.7213833414515344e-05,
729
+ "loss": 37.4132,
730
+ "step": 515
731
+ },
732
+ {
733
+ "epoch": 0.22781725332347585,
734
+ "grad_norm": 26.9375,
735
+ "learning_rate": 1.7165124208475403e-05,
736
+ "loss": 38.0051,
737
+ "step": 520
738
+ },
739
+ {
740
+ "epoch": 0.2300078038362016,
741
+ "grad_norm": 31.796875,
742
+ "learning_rate": 1.7116415002435462e-05,
743
+ "loss": 36.731,
744
+ "step": 525
745
+ },
746
+ {
747
+ "epoch": 0.23219835434892733,
748
+ "grad_norm": 24.328125,
749
+ "learning_rate": 1.7067705796395518e-05,
750
+ "loss": 36.7867,
751
+ "step": 530
752
+ },
753
+ {
754
+ "epoch": 0.23438890486165304,
755
+ "grad_norm": 28.390625,
756
+ "learning_rate": 1.7018996590355577e-05,
757
+ "loss": 38.4257,
758
+ "step": 535
759
+ },
760
+ {
761
+ "epoch": 0.23657945537437877,
762
+ "grad_norm": 33.5625,
763
+ "learning_rate": 1.6970287384315637e-05,
764
+ "loss": 38.0036,
765
+ "step": 540
766
+ },
767
+ {
768
+ "epoch": 0.2387700058871045,
769
+ "grad_norm": 36.125,
770
+ "learning_rate": 1.6921578178275696e-05,
771
+ "loss": 37.2956,
772
+ "step": 545
773
+ },
774
+ {
775
+ "epoch": 0.24096055639983024,
776
+ "grad_norm": 59.34375,
777
+ "learning_rate": 1.6872868972235755e-05,
778
+ "loss": 36.8695,
779
+ "step": 550
780
+ },
781
+ {
782
+ "epoch": 0.24315110691255595,
783
+ "grad_norm": 17.25,
784
+ "learning_rate": 1.6824159766195814e-05,
785
+ "loss": 36.5629,
786
+ "step": 555
787
+ },
788
+ {
789
+ "epoch": 0.2453416574252817,
790
+ "grad_norm": 26.875,
791
+ "learning_rate": 1.677545056015587e-05,
792
+ "loss": 36.3663,
793
+ "step": 560
794
+ },
795
+ {
796
+ "epoch": 0.24753220793800743,
797
+ "grad_norm": 29.59375,
798
+ "learning_rate": 1.672674135411593e-05,
799
+ "loss": 36.5514,
800
+ "step": 565
801
+ },
802
+ {
803
+ "epoch": 0.24972275845073316,
804
+ "grad_norm": 94.8125,
805
+ "learning_rate": 1.667803214807599e-05,
806
+ "loss": 37.2822,
807
+ "step": 570
808
+ },
809
+ {
810
+ "epoch": 0.25191330896345887,
811
+ "grad_norm": 25.921875,
812
+ "learning_rate": 1.6629322942036044e-05,
813
+ "loss": 37.0216,
814
+ "step": 575
815
+ },
816
+ {
817
+ "epoch": 0.25410385947618463,
818
+ "grad_norm": 29.46875,
819
+ "learning_rate": 1.6580613735996104e-05,
820
+ "loss": 36.9,
821
+ "step": 580
822
+ },
823
+ {
824
+ "epoch": 0.25629440998891034,
825
+ "grad_norm": 25.40625,
826
+ "learning_rate": 1.6531904529956163e-05,
827
+ "loss": 36.3711,
828
+ "step": 585
829
+ },
830
+ {
831
+ "epoch": 0.25848496050163605,
832
+ "grad_norm": 23.453125,
833
+ "learning_rate": 1.6483195323916222e-05,
834
+ "loss": 36.7133,
835
+ "step": 590
836
+ },
837
+ {
838
+ "epoch": 0.2606755110143618,
839
+ "grad_norm": 28.328125,
840
+ "learning_rate": 1.643448611787628e-05,
841
+ "loss": 36.4338,
842
+ "step": 595
843
+ },
844
+ {
845
+ "epoch": 0.2628660615270875,
846
+ "grad_norm": 31.875,
847
+ "learning_rate": 1.6385776911836337e-05,
848
+ "loss": 36.4187,
849
+ "step": 600
850
+ },
851
+ {
852
+ "epoch": 0.26505661203981323,
853
+ "grad_norm": 26.375,
854
+ "learning_rate": 1.6337067705796396e-05,
855
+ "loss": 37.0881,
856
+ "step": 605
857
+ },
858
+ {
859
+ "epoch": 0.267247162552539,
860
+ "grad_norm": 47.84375,
861
+ "learning_rate": 1.6288358499756456e-05,
862
+ "loss": 36.7284,
863
+ "step": 610
864
+ },
865
+ {
866
+ "epoch": 0.2694377130652647,
867
+ "grad_norm": 36.9375,
868
+ "learning_rate": 1.623964929371651e-05,
869
+ "loss": 35.6421,
870
+ "step": 615
871
+ },
872
+ {
873
+ "epoch": 0.27162826357799047,
874
+ "grad_norm": 44.9375,
875
+ "learning_rate": 1.619094008767657e-05,
876
+ "loss": 35.6973,
877
+ "step": 620
878
+ },
879
+ {
880
+ "epoch": 0.2738188140907162,
881
+ "grad_norm": 17.4375,
882
+ "learning_rate": 1.614223088163663e-05,
883
+ "loss": 35.1017,
884
+ "step": 625
885
+ },
886
+ {
887
+ "epoch": 0.2760093646034419,
888
+ "grad_norm": 30.0625,
889
+ "learning_rate": 1.609352167559669e-05,
890
+ "loss": 36.4951,
891
+ "step": 630
892
+ },
893
+ {
894
+ "epoch": 0.27819991511616765,
895
+ "grad_norm": 35.84375,
896
+ "learning_rate": 1.604481246955675e-05,
897
+ "loss": 35.1649,
898
+ "step": 635
899
+ },
900
+ {
901
+ "epoch": 0.28039046562889336,
902
+ "grad_norm": 25.703125,
903
+ "learning_rate": 1.5996103263516808e-05,
904
+ "loss": 34.9533,
905
+ "step": 640
906
+ },
907
+ {
908
+ "epoch": 0.28258101614161907,
909
+ "grad_norm": 41.28125,
910
+ "learning_rate": 1.5947394057476863e-05,
911
+ "loss": 34.6937,
912
+ "step": 645
913
+ },
914
+ {
915
+ "epoch": 0.28477156665434483,
916
+ "grad_norm": 27.390625,
917
+ "learning_rate": 1.5898684851436923e-05,
918
+ "loss": 36.1568,
919
+ "step": 650
920
+ },
921
+ {
922
+ "epoch": 0.28696211716707054,
923
+ "grad_norm": 24.828125,
924
+ "learning_rate": 1.5849975645396982e-05,
925
+ "loss": 34.8646,
926
+ "step": 655
927
+ },
928
+ {
929
+ "epoch": 0.2891526676797963,
930
+ "grad_norm": 29.734375,
931
+ "learning_rate": 1.5801266439357038e-05,
932
+ "loss": 35.4552,
933
+ "step": 660
934
+ },
935
+ {
936
+ "epoch": 0.291343218192522,
937
+ "grad_norm": 21.140625,
938
+ "learning_rate": 1.5752557233317097e-05,
939
+ "loss": 35.4214,
940
+ "step": 665
941
+ },
942
+ {
943
+ "epoch": 0.2935337687052477,
944
+ "grad_norm": 20.53125,
945
+ "learning_rate": 1.5703848027277156e-05,
946
+ "loss": 35.3401,
947
+ "step": 670
948
+ },
949
+ {
950
+ "epoch": 0.2957243192179735,
951
+ "grad_norm": 57.25,
952
+ "learning_rate": 1.5655138821237215e-05,
953
+ "loss": 35.3161,
954
+ "step": 675
955
+ },
956
+ {
957
+ "epoch": 0.2979148697306992,
958
+ "grad_norm": 21.375,
959
+ "learning_rate": 1.5606429615197275e-05,
960
+ "loss": 34.5353,
961
+ "step": 680
962
+ },
963
+ {
964
+ "epoch": 0.3001054202434249,
965
+ "grad_norm": 19.28125,
966
+ "learning_rate": 1.5557720409157334e-05,
967
+ "loss": 34.1415,
968
+ "step": 685
969
+ },
970
+ {
971
+ "epoch": 0.30229597075615067,
972
+ "grad_norm": 46.0625,
973
+ "learning_rate": 1.550901120311739e-05,
974
+ "loss": 34.5647,
975
+ "step": 690
976
+ },
977
+ {
978
+ "epoch": 0.3044865212688764,
979
+ "grad_norm": 19.796875,
980
+ "learning_rate": 1.546030199707745e-05,
981
+ "loss": 35.0429,
982
+ "step": 695
983
+ },
984
+ {
985
+ "epoch": 0.30667707178160214,
986
+ "grad_norm": 79.375,
987
+ "learning_rate": 1.5411592791037505e-05,
988
+ "loss": 33.6274,
989
+ "step": 700
990
+ },
991
+ {
992
+ "epoch": 0.30886762229432785,
993
+ "grad_norm": 51.71875,
994
+ "learning_rate": 1.5362883584997564e-05,
995
+ "loss": 35.4228,
996
+ "step": 705
997
+ },
998
+ {
999
+ "epoch": 0.31105817280705356,
1000
+ "grad_norm": 27.234375,
1001
+ "learning_rate": 1.5314174378957623e-05,
1002
+ "loss": 35.1287,
1003
+ "step": 710
1004
+ },
1005
+ {
1006
+ "epoch": 0.3132487233197793,
1007
+ "grad_norm": 30.390625,
1008
+ "learning_rate": 1.5265465172917682e-05,
1009
+ "loss": 34.1134,
1010
+ "step": 715
1011
+ },
1012
+ {
1013
+ "epoch": 0.31543927383250503,
1014
+ "grad_norm": 27.359375,
1015
+ "learning_rate": 1.5216755966877742e-05,
1016
+ "loss": 34.4372,
1017
+ "step": 720
1018
+ },
1019
+ {
1020
+ "epoch": 0.31762982434523074,
1021
+ "grad_norm": 25.90625,
1022
+ "learning_rate": 1.51680467608378e-05,
1023
+ "loss": 34.7943,
1024
+ "step": 725
1025
+ },
1026
+ {
1027
+ "epoch": 0.3198203748579565,
1028
+ "grad_norm": 31.765625,
1029
+ "learning_rate": 1.5119337554797857e-05,
1030
+ "loss": 34.0021,
1031
+ "step": 730
1032
+ },
1033
+ {
1034
+ "epoch": 0.3220109253706822,
1035
+ "grad_norm": 32.625,
1036
+ "learning_rate": 1.5070628348757916e-05,
1037
+ "loss": 34.3029,
1038
+ "step": 735
1039
+ },
1040
+ {
1041
+ "epoch": 0.324201475883408,
1042
+ "grad_norm": 26.109375,
1043
+ "learning_rate": 1.5021919142717975e-05,
1044
+ "loss": 34.2254,
1045
+ "step": 740
1046
+ },
1047
+ {
1048
+ "epoch": 0.3263920263961337,
1049
+ "grad_norm": 32.65625,
1050
+ "learning_rate": 1.4973209936678033e-05,
1051
+ "loss": 34.6909,
1052
+ "step": 745
1053
+ },
1054
+ {
1055
+ "epoch": 0.3285825769088594,
1056
+ "grad_norm": 26.890625,
1057
+ "learning_rate": 1.4924500730638092e-05,
1058
+ "loss": 34.4121,
1059
+ "step": 750
1060
+ },
1061
+ {
1062
+ "epoch": 0.33077312742158516,
1063
+ "grad_norm": 28.453125,
1064
+ "learning_rate": 1.4875791524598151e-05,
1065
+ "loss": 34.1999,
1066
+ "step": 755
1067
+ },
1068
+ {
1069
+ "epoch": 0.33296367793431086,
1070
+ "grad_norm": 24.25,
1071
+ "learning_rate": 1.4827082318558209e-05,
1072
+ "loss": 34.5926,
1073
+ "step": 760
1074
+ },
1075
+ {
1076
+ "epoch": 0.3351542284470366,
1077
+ "grad_norm": 29.4375,
1078
+ "learning_rate": 1.4778373112518268e-05,
1079
+ "loss": 34.2804,
1080
+ "step": 765
1081
+ },
1082
+ {
1083
+ "epoch": 0.33734477895976234,
1084
+ "grad_norm": 36.125,
1085
+ "learning_rate": 1.4729663906478327e-05,
1086
+ "loss": 33.5547,
1087
+ "step": 770
1088
+ },
1089
+ {
1090
+ "epoch": 0.33953532947248805,
1091
+ "grad_norm": 19.875,
1092
+ "learning_rate": 1.4680954700438383e-05,
1093
+ "loss": 33.3131,
1094
+ "step": 775
1095
+ },
1096
+ {
1097
+ "epoch": 0.3417258799852138,
1098
+ "grad_norm": 37.09375,
1099
+ "learning_rate": 1.4632245494398442e-05,
1100
+ "loss": 33.288,
1101
+ "step": 780
1102
+ },
1103
+ {
1104
+ "epoch": 0.3439164304979395,
1105
+ "grad_norm": 32.09375,
1106
+ "learning_rate": 1.4583536288358501e-05,
1107
+ "loss": 34.4507,
1108
+ "step": 785
1109
+ },
1110
+ {
1111
+ "epoch": 0.3461069810106652,
1112
+ "grad_norm": 27.0625,
1113
+ "learning_rate": 1.4534827082318559e-05,
1114
+ "loss": 34.0287,
1115
+ "step": 790
1116
+ },
1117
+ {
1118
+ "epoch": 0.348297531523391,
1119
+ "grad_norm": 34.59375,
1120
+ "learning_rate": 1.4486117876278618e-05,
1121
+ "loss": 33.4372,
1122
+ "step": 795
1123
+ },
1124
+ {
1125
+ "epoch": 0.3504880820361167,
1126
+ "grad_norm": 33.84375,
1127
+ "learning_rate": 1.4437408670238677e-05,
1128
+ "loss": 33.7221,
1129
+ "step": 800
1130
+ },
1131
+ {
1132
+ "epoch": 0.3526786325488424,
1133
+ "grad_norm": 30.1875,
1134
+ "learning_rate": 1.4388699464198735e-05,
1135
+ "loss": 33.3108,
1136
+ "step": 805
1137
+ },
1138
+ {
1139
+ "epoch": 0.35486918306156817,
1140
+ "grad_norm": 39.8125,
1141
+ "learning_rate": 1.4339990258158794e-05,
1142
+ "loss": 33.231,
1143
+ "step": 810
1144
+ },
1145
+ {
1146
+ "epoch": 0.3570597335742939,
1147
+ "grad_norm": 30.296875,
1148
+ "learning_rate": 1.429128105211885e-05,
1149
+ "loss": 33.9207,
1150
+ "step": 815
1151
+ },
1152
+ {
1153
+ "epoch": 0.35925028408701964,
1154
+ "grad_norm": 23.484375,
1155
+ "learning_rate": 1.4242571846078909e-05,
1156
+ "loss": 33.4625,
1157
+ "step": 820
1158
+ },
1159
+ {
1160
+ "epoch": 0.36144083459974535,
1161
+ "grad_norm": 32.15625,
1162
+ "learning_rate": 1.4193862640038968e-05,
1163
+ "loss": 33.2117,
1164
+ "step": 825
1165
+ },
1166
+ {
1167
+ "epoch": 0.36363138511247106,
1168
+ "grad_norm": 548.5,
1169
+ "learning_rate": 1.4145153433999026e-05,
1170
+ "loss": 33.2816,
1171
+ "step": 830
1172
+ },
1173
+ {
1174
+ "epoch": 0.3658219356251968,
1175
+ "grad_norm": 46.03125,
1176
+ "learning_rate": 1.4096444227959085e-05,
1177
+ "loss": 32.2993,
1178
+ "step": 835
1179
+ },
1180
+ {
1181
+ "epoch": 0.36801248613792253,
1182
+ "grad_norm": 25.96875,
1183
+ "learning_rate": 1.4047735021919144e-05,
1184
+ "loss": 33.0793,
1185
+ "step": 840
1186
+ },
1187
+ {
1188
+ "epoch": 0.37020303665064824,
1189
+ "grad_norm": 45.6875,
1190
+ "learning_rate": 1.3999025815879202e-05,
1191
+ "loss": 32.4659,
1192
+ "step": 845
1193
+ },
1194
+ {
1195
+ "epoch": 0.372393587163374,
1196
+ "grad_norm": 48.03125,
1197
+ "learning_rate": 1.3950316609839261e-05,
1198
+ "loss": 32.3893,
1199
+ "step": 850
1200
+ },
1201
+ {
1202
+ "epoch": 0.3745841376760997,
1203
+ "grad_norm": 28.9375,
1204
+ "learning_rate": 1.390160740379932e-05,
1205
+ "loss": 32.7858,
1206
+ "step": 855
1207
+ },
1208
+ {
1209
+ "epoch": 0.3767746881888255,
1210
+ "grad_norm": 39.90625,
1211
+ "learning_rate": 1.3852898197759376e-05,
1212
+ "loss": 32.1438,
1213
+ "step": 860
1214
+ },
1215
+ {
1216
+ "epoch": 0.3789652387015512,
1217
+ "grad_norm": 51.34375,
1218
+ "learning_rate": 1.3804188991719435e-05,
1219
+ "loss": 32.3068,
1220
+ "step": 865
1221
+ },
1222
+ {
1223
+ "epoch": 0.3811557892142769,
1224
+ "grad_norm": 25.125,
1225
+ "learning_rate": 1.3755479785679495e-05,
1226
+ "loss": 32.0212,
1227
+ "step": 870
1228
+ },
1229
+ {
1230
+ "epoch": 0.38334633972700266,
1231
+ "grad_norm": 41.96875,
1232
+ "learning_rate": 1.3706770579639552e-05,
1233
+ "loss": 32.0489,
1234
+ "step": 875
1235
+ },
1236
+ {
1237
+ "epoch": 0.38553689023972837,
1238
+ "grad_norm": 36.25,
1239
+ "learning_rate": 1.3658061373599611e-05,
1240
+ "loss": 31.558,
1241
+ "step": 880
1242
+ },
1243
+ {
1244
+ "epoch": 0.3877274407524541,
1245
+ "grad_norm": 39.5625,
1246
+ "learning_rate": 1.360935216755967e-05,
1247
+ "loss": 31.9841,
1248
+ "step": 885
1249
+ },
1250
+ {
1251
+ "epoch": 0.38991799126517984,
1252
+ "grad_norm": 26.921875,
1253
+ "learning_rate": 1.3560642961519728e-05,
1254
+ "loss": 33.2559,
1255
+ "step": 890
1256
+ },
1257
+ {
1258
+ "epoch": 0.39210854177790555,
1259
+ "grad_norm": 49.65625,
1260
+ "learning_rate": 1.3511933755479787e-05,
1261
+ "loss": 33.6144,
1262
+ "step": 895
1263
+ },
1264
+ {
1265
+ "epoch": 0.3942990922906313,
1266
+ "grad_norm": 51.8125,
1267
+ "learning_rate": 1.3463224549439847e-05,
1268
+ "loss": 33.1955,
1269
+ "step": 900
1270
+ },
1271
+ {
1272
+ "epoch": 0.396489642803357,
1273
+ "grad_norm": 46.28125,
1274
+ "learning_rate": 1.3414515343399902e-05,
1275
+ "loss": 32.873,
1276
+ "step": 905
1277
+ },
1278
+ {
1279
+ "epoch": 0.39868019331608273,
1280
+ "grad_norm": 26.859375,
1281
+ "learning_rate": 1.3365806137359962e-05,
1282
+ "loss": 31.7345,
1283
+ "step": 910
1284
+ },
1285
+ {
1286
+ "epoch": 0.4008707438288085,
1287
+ "grad_norm": 34.1875,
1288
+ "learning_rate": 1.331709693132002e-05,
1289
+ "loss": 31.5948,
1290
+ "step": 915
1291
+ },
1292
+ {
1293
+ "epoch": 0.4030612943415342,
1294
+ "grad_norm": 21.265625,
1295
+ "learning_rate": 1.3268387725280078e-05,
1296
+ "loss": 31.6987,
1297
+ "step": 920
1298
+ },
1299
+ {
1300
+ "epoch": 0.4052518448542599,
1301
+ "grad_norm": 28.09375,
1302
+ "learning_rate": 1.3219678519240138e-05,
1303
+ "loss": 32.0258,
1304
+ "step": 925
1305
+ },
1306
+ {
1307
+ "epoch": 0.4074423953669857,
1308
+ "grad_norm": 108.375,
1309
+ "learning_rate": 1.3170969313200197e-05,
1310
+ "loss": 32.0971,
1311
+ "step": 930
1312
+ },
1313
+ {
1314
+ "epoch": 0.4096329458797114,
1315
+ "grad_norm": 28.53125,
1316
+ "learning_rate": 1.3122260107160254e-05,
1317
+ "loss": 32.1107,
1318
+ "step": 935
1319
+ },
1320
+ {
1321
+ "epoch": 0.41182349639243715,
1322
+ "grad_norm": 22.46875,
1323
+ "learning_rate": 1.3073550901120314e-05,
1324
+ "loss": 31.9156,
1325
+ "step": 940
1326
+ },
1327
+ {
1328
+ "epoch": 0.41401404690516286,
1329
+ "grad_norm": 17.734375,
1330
+ "learning_rate": 1.302484169508037e-05,
1331
+ "loss": 31.5545,
1332
+ "step": 945
1333
+ },
1334
+ {
1335
+ "epoch": 0.41620459741788857,
1336
+ "grad_norm": 23.25,
1337
+ "learning_rate": 1.2976132489040429e-05,
1338
+ "loss": 31.4469,
1339
+ "step": 950
1340
+ },
1341
+ {
1342
+ "epoch": 0.41839514793061433,
1343
+ "grad_norm": 34.84375,
1344
+ "learning_rate": 1.2927423283000488e-05,
1345
+ "loss": 31.7367,
1346
+ "step": 955
1347
+ },
1348
+ {
1349
+ "epoch": 0.42058569844334004,
1350
+ "grad_norm": 20.53125,
1351
+ "learning_rate": 1.2878714076960545e-05,
1352
+ "loss": 32.3651,
1353
+ "step": 960
1354
+ },
1355
+ {
1356
+ "epoch": 0.42277624895606575,
1357
+ "grad_norm": 21.546875,
1358
+ "learning_rate": 1.2830004870920605e-05,
1359
+ "loss": 32.3428,
1360
+ "step": 965
1361
+ },
1362
+ {
1363
+ "epoch": 0.4249667994687915,
1364
+ "grad_norm": 22.328125,
1365
+ "learning_rate": 1.2781295664880664e-05,
1366
+ "loss": 32.0113,
1367
+ "step": 970
1368
+ },
1369
+ {
1370
+ "epoch": 0.4271573499815172,
1371
+ "grad_norm": 26.34375,
1372
+ "learning_rate": 1.2732586458840721e-05,
1373
+ "loss": 31.9163,
1374
+ "step": 975
1375
+ },
1376
+ {
1377
+ "epoch": 0.429347900494243,
1378
+ "grad_norm": 22.171875,
1379
+ "learning_rate": 1.268387725280078e-05,
1380
+ "loss": 32.0345,
1381
+ "step": 980
1382
+ },
1383
+ {
1384
+ "epoch": 0.4315384510069687,
1385
+ "grad_norm": 106.3125,
1386
+ "learning_rate": 1.263516804676084e-05,
1387
+ "loss": 32.1245,
1388
+ "step": 985
1389
+ },
1390
+ {
1391
+ "epoch": 0.4337290015196944,
1392
+ "grad_norm": 21.1875,
1393
+ "learning_rate": 1.2586458840720897e-05,
1394
+ "loss": 32.4236,
1395
+ "step": 990
1396
+ },
1397
+ {
1398
+ "epoch": 0.43591955203242017,
1399
+ "grad_norm": 34.84375,
1400
+ "learning_rate": 1.2537749634680957e-05,
1401
+ "loss": 31.7463,
1402
+ "step": 995
1403
+ },
1404
+ {
1405
+ "epoch": 0.4381101025451459,
1406
+ "grad_norm": 34.875,
1407
+ "learning_rate": 1.2489040428641016e-05,
1408
+ "loss": 32.5371,
1409
+ "step": 1000
1410
+ },
1411
+ {
1412
+ "epoch": 0.4381101025451459,
1413
+ "eval_loss": NaN,
1414
+ "eval_runtime": 244.1573,
1415
+ "eval_samples_per_second": 1007.682,
1416
+ "eval_steps_per_second": 31.492,
1417
+ "step": 1000
1418
+ }
1419
+ ],
1420
+ "logging_steps": 5,
1421
+ "max_steps": 2282,
1422
+ "num_input_tokens_seen": 0,
1423
+ "num_train_epochs": 1,
1424
+ "save_steps": 1000,
1425
+ "stateful_callbacks": {
1426
+ "TrainerControl": {
1427
+ "args": {
1428
+ "should_epoch_stop": false,
1429
+ "should_evaluate": false,
1430
+ "should_log": false,
1431
+ "should_save": true,
1432
+ "should_training_stop": false
1433
+ },
1434
+ "attributes": {}
1435
+ }
1436
+ },
1437
+ "total_flos": 8.664715126584115e+18,
1438
+ "train_batch_size": 8,
1439
+ "trial_name": null,
1440
+ "trial_params": null
1441
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720dfc4a8bf8d5246821c427aeebf82b97f318ea02e4245c2f175949f870e340
3
+ size 5752