Hugging Face's logo

nlpie
/
modernalbert-large-v1.0

Fill-Mask
Transformers
PyTorch
TensorBoard
Safetensors
ModernALBERT
custom_code
Model card Files
xet
 Metrics Community
mohammadmahdinouri commited on
Commit
e8ed5b8
·
verified ·
1 Parent(s): 3bf3ebb

checkpoint-2000

Browse files
Files changed (21) hide show
  1. config.json +36 -0
  2. last-checkpoint/config.json +36 -0
  3. last-checkpoint/optimizer.pt +3 -0
  4. last-checkpoint/pytorch_model.bin +3 -0
  5. last-checkpoint/rng_state_0.pth +3 -0
  6. last-checkpoint/rng_state_1.pth +3 -0
  7. last-checkpoint/rng_state_2.pth +3 -0
  8. last-checkpoint/rng_state_3.pth +3 -0
  9. last-checkpoint/scheduler.pt +3 -0
  10. last-checkpoint/special_tokens_map.json +37 -0
  11. last-checkpoint/tokenizer.json +0 -0
  12. last-checkpoint/tokenizer_config.json +945 -0
  13. last-checkpoint/trainer_state.json +1434 -0
  14. last-checkpoint/training_args.bin +3 -0
  15. pytorch_model.bin +3 -0
  16. runs/Sep16_13-28-46_nid006603/events.out.tfevents.1758022141.nid006603.208166.0 +3 -0
  17. runs/Sep16_22-37-21_nid007081/events.out.tfevents.1758055057.nid007081.55404.0 +3 -0
  18. runs/Sep17_11-23-31_nid007191/events.out.tfevents.1758101018.nid007191.214208.0 +3 -0
  19. runs/Sep17_11-29-28_nid007081/events.out.tfevents.1758101384.nid007081.193734.0 +3 -0
  20. runs/Sep17_19-36-25_nid007121/events.out.tfevents.1758130601.nid007121.254584.0 +3 -0
  21. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_reduction": 16,
3
+ "architectures": [
4
+ "DistillationWrapper"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "embedding_size": 128,
10
+ "expert_intermediate_size": 4096,
11
+ "group_depth": 4,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 1024,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 2624,
17
+ "layer_norm_eps": 1e-06,
18
+ "load_balancing_loss_coef": 0.2,
19
+ "lora_alpha": 32,
20
+ "lora_rank": 16,
21
+ "max_position_embeddings": 8192,
22
+ "model_type": "ModernALBERT",
23
+ "num_attention_heads": 16,
24
+ "num_expert_modules": 4,
25
+ "num_experts": 8,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 0,
28
+ "router_jitter_noise": 0.01,
29
+ "top_k": 2,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.51.3",
32
+ "use_adapter": true,
33
+ "use_cache": true,
34
+ "use_moa": true,
35
+ "vocab_size": 50368
36
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_reduction": 16,
3
+ "architectures": [
4
+ "DistillationWrapper"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "embedding_size": 128,
10
+ "expert_intermediate_size": 4096,
11
+ "group_depth": 4,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 1024,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 2624,
17
+ "layer_norm_eps": 1e-06,
18
+ "load_balancing_loss_coef": 0.2,
19
+ "lora_alpha": 32,
20
+ "lora_rank": 16,
21
+ "max_position_embeddings": 8192,
22
+ "model_type": "ModernALBERT",
23
+ "num_attention_heads": 16,
24
+ "num_expert_modules": 4,
25
+ "num_experts": 8,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 0,
28
+ "router_jitter_noise": 0.01,
29
+ "top_k": 2,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.51.3",
32
+ "use_adapter": true,
33
+ "use_cache": true,
34
+ "use_moa": true,
35
+ "vocab_size": 50368
36
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b37e141dcdb8bd62663f71ecb50f210ddac4be94be739c01e9bc43b5bf48ea2
3
+ size 715030586
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b9486fa94e8fc79a7b7df41977075097e10373b9426abe8b458045a6fbf276
3
+ size 1032262338
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df346f322145e99e6c7a2560380461374329dd0875f98ff2a69e98e51db537d6
3
+ size 14960
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af55682455c46a9a1184a5757963d1a9c65b1ddcd1b4343f37b493e607a85d42
3
+ size 14960
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1636d7f288fbac99ed2049a6376b5fda19162ad4af718eae263bdc743ee12343
3
+ size 14960
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc61dd4a01f7d5e9b4c830655b1ed6b7d929386352f94e37af06558f106406c1
3
+ size 14960
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872c726365daf12f7d58f92d96ad26f9372f1682e327b5b5c31d94a58ae3862e
3
+ size 1064
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
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
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": 1024,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizer",
944
+ "unk_token": "[UNK]"
945
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,1434 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.0038999468632239884,
6
+ "eval_steps": 500,
7
+ "global_step": 2000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.9499734316119942e-05,
14
+ "grad_norm": 964.0,
15
+ "learning_rate": 9e-06,
16
+ "loss": 230.4845,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 3.8999468632239884e-05,
21
+ "grad_norm": 126.5,
22
+ "learning_rate": 1.9e-05,
23
+ "loss": 183.9275,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 5.849920294835983e-05,
28
+ "grad_norm": 40.25,
29
+ "learning_rate": 2.9000000000000004e-05,
30
+ "loss": 159.6557,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 7.799893726447977e-05,
35
+ "grad_norm": 39.25,
36
+ "learning_rate": 3.9e-05,
37
+ "loss": 152.3345,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 9.749867158059972e-05,
42
+ "grad_norm": 29.25,
43
+ "learning_rate": 4.9000000000000005e-05,
44
+ "loss": 148.5947,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.00011699840589671966,
49
+ "grad_norm": 55.75,
50
+ "learning_rate": 5.9e-05,
51
+ "loss": 144.9469,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0001364981402128396,
56
+ "grad_norm": 70.5,
57
+ "learning_rate": 6.900000000000001e-05,
58
+ "loss": 142.9858,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.00015599787452895953,
63
+ "grad_norm": 130.0,
64
+ "learning_rate": 7.9e-05,
65
+ "loss": 140.8121,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.00017549760884507949,
70
+ "grad_norm": 81.0,
71
+ "learning_rate": 8.9e-05,
72
+ "loss": 138.8253,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.00019499734316119944,
77
+ "grad_norm": 84.5,
78
+ "learning_rate": 9.900000000000001e-05,
79
+ "loss": 136.6046,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.00021449707747731936,
84
+ "grad_norm": 148.0,
85
+ "learning_rate": 0.000109,
86
+ "loss": 134.4724,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.00023399681179343931,
91
+ "grad_norm": 89.0,
92
+ "learning_rate": 0.00011899999999999999,
93
+ "loss": 132.2679,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.00025349654610955924,
98
+ "grad_norm": 69.0,
99
+ "learning_rate": 0.00012900000000000002,
100
+ "loss": 129.8039,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.0002729962804256792,
105
+ "grad_norm": 62.0,
106
+ "learning_rate": 0.00013900000000000002,
107
+ "loss": 127.2811,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.00029249601474179914,
112
+ "grad_norm": 110.5,
113
+ "learning_rate": 0.000149,
114
+ "loss": 125.1548,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.00031199574905791907,
119
+ "grad_norm": 97.5,
120
+ "learning_rate": 0.00015900000000000002,
121
+ "loss": 122.9106,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.00033149548337403905,
126
+ "grad_norm": 100.0,
127
+ "learning_rate": 0.00016900000000000002,
128
+ "loss": 119.3758,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.00035099521769015897,
133
+ "grad_norm": 110.0,
134
+ "learning_rate": 0.000179,
135
+ "loss": 117.1057,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.0003704949520062789,
140
+ "grad_norm": 62.75,
141
+ "learning_rate": 0.000189,
142
+ "loss": 115.1382,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.0003899946863223989,
147
+ "grad_norm": 95.5,
148
+ "learning_rate": 0.000199,
149
+ "loss": 112.5088,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.0004094944206385188,
154
+ "grad_norm": 73.5,
155
+ "learning_rate": 0.00020899999999999998,
156
+ "loss": 110.3889,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.0004289941549546387,
161
+ "grad_norm": 57.5,
162
+ "learning_rate": 0.000219,
163
+ "loss": 109.0307,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.0004484938892707587,
168
+ "grad_norm": 68.5,
169
+ "learning_rate": 0.000229,
170
+ "loss": 107.1398,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.00046799362358687863,
175
+ "grad_norm": 88.0,
176
+ "learning_rate": 0.00023899999999999998,
177
+ "loss": 105.1635,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.00048749335790299855,
182
+ "grad_norm": 60.5,
183
+ "learning_rate": 0.000249,
184
+ "loss": 103.5087,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.0005069930922191185,
189
+ "grad_norm": 56.5,
190
+ "learning_rate": 0.000259,
191
+ "loss": 101.9478,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.0005264928265352384,
196
+ "grad_norm": 103.5,
197
+ "learning_rate": 0.00026900000000000003,
198
+ "loss": 100.9195,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.0005459925608513584,
203
+ "grad_norm": 60.75,
204
+ "learning_rate": 0.000279,
205
+ "loss": 98.929,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.0005654922951674784,
210
+ "grad_norm": 87.0,
211
+ "learning_rate": 0.000289,
212
+ "loss": 97.4237,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.0005849920294835983,
217
+ "grad_norm": 66.0,
218
+ "learning_rate": 0.000299,
219
+ "loss": 95.8856,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.0006044917637997182,
224
+ "grad_norm": 69.0,
225
+ "learning_rate": 0.00030900000000000003,
226
+ "loss": 94.8032,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.0006239914981158381,
231
+ "grad_norm": 90.0,
232
+ "learning_rate": 0.000319,
233
+ "loss": 93.2709,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.0006434912324319581,
238
+ "grad_norm": 75.0,
239
+ "learning_rate": 0.00032900000000000003,
240
+ "loss": 91.8126,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.0006629909667480781,
245
+ "grad_norm": 65.5,
246
+ "learning_rate": 0.00033900000000000005,
247
+ "loss": 90.2314,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.000682490701064198,
252
+ "grad_norm": 55.75,
253
+ "learning_rate": 0.00034899999999999997,
254
+ "loss": 88.9011,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.0007019904353803179,
259
+ "grad_norm": 59.25,
260
+ "learning_rate": 0.000359,
261
+ "loss": 87.5898,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.0007214901696964379,
266
+ "grad_norm": 71.5,
267
+ "learning_rate": 0.000369,
268
+ "loss": 85.5659,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.0007409899040125578,
273
+ "grad_norm": 74.5,
274
+ "learning_rate": 0.000379,
275
+ "loss": 83.916,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.0007604896383286777,
280
+ "grad_norm": 95.5,
281
+ "learning_rate": 0.000389,
282
+ "loss": 81.7186,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.0007799893726447978,
287
+ "grad_norm": 67.0,
288
+ "learning_rate": 0.00039900000000000005,
289
+ "loss": 80.0784,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.0007994891069609177,
294
+ "grad_norm": 78.5,
295
+ "learning_rate": 0.00040899999999999997,
296
+ "loss": 79.0283,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.0008189888412770376,
301
+ "grad_norm": 83.5,
302
+ "learning_rate": 0.000419,
303
+ "loss": 77.3617,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.0008384885755931575,
308
+ "grad_norm": 60.0,
309
+ "learning_rate": 0.000429,
310
+ "loss": 75.7983,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.0008579883099092775,
315
+ "grad_norm": 108.0,
316
+ "learning_rate": 0.000439,
317
+ "loss": 74.956,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.0008774880442253974,
322
+ "grad_norm": 71.0,
323
+ "learning_rate": 0.000449,
324
+ "loss": 73.647,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.0008969877785415174,
329
+ "grad_norm": 113.0,
330
+ "learning_rate": 0.00045900000000000004,
331
+ "loss": 72.6851,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.0009164875128576373,
336
+ "grad_norm": 125.5,
337
+ "learning_rate": 0.00046899999999999996,
338
+ "loss": 71.5142,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.0009359872471737573,
343
+ "grad_norm": 66.5,
344
+ "learning_rate": 0.000479,
345
+ "loss": 70.1327,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.0009554869814898772,
350
+ "grad_norm": 71.0,
351
+ "learning_rate": 0.000489,
352
+ "loss": 68.8709,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.0009749867158059971,
357
+ "grad_norm": 69.0,
358
+ "learning_rate": 0.000499,
359
+ "loss": 68.0783,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.000994486450122117,
364
+ "grad_norm": 79.0,
365
+ "learning_rate": 0.0004999970740860908,
366
+ "loss": 67.2482,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.001013986184438237,
371
+ "grad_norm": 95.0,
372
+ "learning_rate": 0.0004999938230706361,
373
+ "loss": 66.5981,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.0010334859187543569,
378
+ "grad_norm": 59.0,
379
+ "learning_rate": 0.0004999905720551814,
380
+ "loss": 65.5961,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.0010529856530704768,
385
+ "grad_norm": 87.0,
386
+ "learning_rate": 0.0004999873210397267,
387
+ "loss": 64.4282,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.001072485387386597,
392
+ "grad_norm": 90.0,
393
+ "learning_rate": 0.0004999840700242721,
394
+ "loss": 63.8475,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.0010919851217027169,
399
+ "grad_norm": 54.5,
400
+ "learning_rate": 0.0004999808190088174,
401
+ "loss": 62.6886,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.0011114848560188368,
406
+ "grad_norm": 59.75,
407
+ "learning_rate": 0.0004999775679933627,
408
+ "loss": 62.2557,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.0011309845903349567,
413
+ "grad_norm": 54.25,
414
+ "learning_rate": 0.000499974316977908,
415
+ "loss": 61.4417,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.0011504843246510767,
420
+ "grad_norm": 54.5,
421
+ "learning_rate": 0.0004999710659624534,
422
+ "loss": 60.9353,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.0011699840589671966,
427
+ "grad_norm": 64.5,
428
+ "learning_rate": 0.0004999678149469987,
429
+ "loss": 60.5813,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.0011894837932833165,
434
+ "grad_norm": 72.5,
435
+ "learning_rate": 0.000499964563931544,
436
+ "loss": 59.5569,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.0012089835275994364,
441
+ "grad_norm": 56.25,
442
+ "learning_rate": 0.0004999613129160894,
443
+ "loss": 58.985,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.0012284832619155563,
448
+ "grad_norm": 46.25,
449
+ "learning_rate": 0.0004999580619006347,
450
+ "loss": 58.6021,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.0012479829962316763,
455
+ "grad_norm": 58.0,
456
+ "learning_rate": 0.00049995481088518,
457
+ "loss": 58.0797,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.0012674827305477962,
462
+ "grad_norm": 46.75,
463
+ "learning_rate": 0.0004999515598697253,
464
+ "loss": 57.2254,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.0012869824648639161,
469
+ "grad_norm": 49.0,
470
+ "learning_rate": 0.0004999483088542707,
471
+ "loss": 57.0353,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.0013064821991800363,
476
+ "grad_norm": 56.25,
477
+ "learning_rate": 0.0004999450578388159,
478
+ "loss": 56.347,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.0013259819334961562,
483
+ "grad_norm": 68.0,
484
+ "learning_rate": 0.0004999418068233612,
485
+ "loss": 56.0373,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.0013454816678122761,
490
+ "grad_norm": 47.5,
491
+ "learning_rate": 0.0004999385558079065,
492
+ "loss": 55.4212,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.001364981402128396,
497
+ "grad_norm": 43.0,
498
+ "learning_rate": 0.0004999353047924519,
499
+ "loss": 54.8873,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.001384481136444516,
504
+ "grad_norm": 39.5,
505
+ "learning_rate": 0.0004999320537769972,
506
+ "loss": 54.7153,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.0014039808707606359,
511
+ "grad_norm": 35.25,
512
+ "learning_rate": 0.0004999288027615425,
513
+ "loss": 54.3177,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.0014234806050767558,
518
+ "grad_norm": 57.0,
519
+ "learning_rate": 0.0004999255517460879,
520
+ "loss": 54.0105,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.0014429803393928757,
525
+ "grad_norm": 54.25,
526
+ "learning_rate": 0.0004999223007306332,
527
+ "loss": 53.5363,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.0014624800737089957,
532
+ "grad_norm": 48.25,
533
+ "learning_rate": 0.0004999190497151785,
534
+ "loss": 52.9659,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.0014819798080251156,
539
+ "grad_norm": 38.25,
540
+ "learning_rate": 0.0004999157986997238,
541
+ "loss": 52.6807,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.0015014795423412355,
546
+ "grad_norm": 45.75,
547
+ "learning_rate": 0.0004999125476842692,
548
+ "loss": 52.4438,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.0015209792766573554,
553
+ "grad_norm": 47.75,
554
+ "learning_rate": 0.0004999092966688145,
555
+ "loss": 51.9504,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.0015404790109734756,
560
+ "grad_norm": 47.5,
561
+ "learning_rate": 0.0004999060456533598,
562
+ "loss": 51.6554,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.0015599787452895955,
567
+ "grad_norm": 54.5,
568
+ "learning_rate": 0.0004999027946379052,
569
+ "loss": 51.1988,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.0015794784796057154,
574
+ "grad_norm": 56.25,
575
+ "learning_rate": 0.0004998995436224505,
576
+ "loss": 50.92,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.0015989782139218354,
581
+ "grad_norm": 41.75,
582
+ "learning_rate": 0.0004998962926069958,
583
+ "loss": 50.5837,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.0016184779482379553,
588
+ "grad_norm": 37.25,
589
+ "learning_rate": 0.0004998930415915411,
590
+ "loss": 50.16,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.0016379776825540752,
595
+ "grad_norm": 35.25,
596
+ "learning_rate": 0.0004998897905760865,
597
+ "loss": 50.0232,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.0016574774168701951,
602
+ "grad_norm": 45.5,
603
+ "learning_rate": 0.0004998865395606318,
604
+ "loss": 49.5883,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.001676977151186315,
609
+ "grad_norm": 37.0,
610
+ "learning_rate": 0.0004998832885451771,
611
+ "loss": 49.4557,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.001696476885502435,
616
+ "grad_norm": 35.0,
617
+ "learning_rate": 0.0004998800375297225,
618
+ "loss": 49.0122,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.001715976619818555,
623
+ "grad_norm": 36.25,
624
+ "learning_rate": 0.0004998767865142678,
625
+ "loss": 48.807,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.0017354763541346748,
630
+ "grad_norm": 43.0,
631
+ "learning_rate": 0.0004998735354988131,
632
+ "loss": 48.5801,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.0017549760884507948,
637
+ "grad_norm": 41.25,
638
+ "learning_rate": 0.0004998702844833583,
639
+ "loss": 48.2749,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.001774475822766915,
644
+ "grad_norm": 37.0,
645
+ "learning_rate": 0.0004998670334679037,
646
+ "loss": 47.8618,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.0017939755570830348,
651
+ "grad_norm": 35.25,
652
+ "learning_rate": 0.000499863782452449,
653
+ "loss": 47.7078,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.0018134752913991547,
658
+ "grad_norm": 37.5,
659
+ "learning_rate": 0.0004998605314369943,
660
+ "loss": 47.3812,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.0018329750257152747,
665
+ "grad_norm": 33.25,
666
+ "learning_rate": 0.0004998572804215396,
667
+ "loss": 47.2849,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.0018524747600313946,
672
+ "grad_norm": 43.5,
673
+ "learning_rate": 0.000499854029406085,
674
+ "loss": 46.8848,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.0018719744943475145,
679
+ "grad_norm": 32.0,
680
+ "learning_rate": 0.0004998507783906303,
681
+ "loss": 46.3907,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.0018914742286636344,
686
+ "grad_norm": 35.25,
687
+ "learning_rate": 0.0004998475273751756,
688
+ "loss": 46.3933,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.0019109739629797544,
693
+ "grad_norm": 35.75,
694
+ "learning_rate": 0.000499844276359721,
695
+ "loss": 46.0666,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.0019304736972958743,
700
+ "grad_norm": 40.0,
701
+ "learning_rate": 0.0004998410253442663,
702
+ "loss": 45.9599,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.0019499734316119942,
707
+ "grad_norm": 43.75,
708
+ "learning_rate": 0.0004998377743288116,
709
+ "loss": 45.652,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.0019694731659281144,
714
+ "grad_norm": 27.0,
715
+ "learning_rate": 0.000499834523313357,
716
+ "loss": 45.4481,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.001988972900244234,
721
+ "grad_norm": 53.5,
722
+ "learning_rate": 0.0004998312722979023,
723
+ "loss": 45.303,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.002008472634560354,
728
+ "grad_norm": 27.5,
729
+ "learning_rate": 0.0004998280212824476,
730
+ "loss": 44.9817,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.002027972368876474,
735
+ "grad_norm": 38.25,
736
+ "learning_rate": 0.0004998247702669929,
737
+ "loss": 44.7895,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.002047472103192594,
742
+ "grad_norm": 35.0,
743
+ "learning_rate": 0.0004998215192515383,
744
+ "loss": 44.4112,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.0020669718375087138,
749
+ "grad_norm": 29.25,
750
+ "learning_rate": 0.0004998182682360836,
751
+ "loss": 44.321,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.002086471571824834,
756
+ "grad_norm": 41.25,
757
+ "learning_rate": 0.0004998150172206289,
758
+ "loss": 44.0848,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.0021059713061409536,
763
+ "grad_norm": 31.875,
764
+ "learning_rate": 0.0004998117662051742,
765
+ "loss": 43.8365,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.0021254710404570738,
770
+ "grad_norm": 31.75,
771
+ "learning_rate": 0.0004998085151897196,
772
+ "loss": 43.6307,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.002144970774773194,
777
+ "grad_norm": 38.75,
778
+ "learning_rate": 0.0004998052641742649,
779
+ "loss": 43.4166,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.0021644705090893136,
784
+ "grad_norm": 28.625,
785
+ "learning_rate": 0.0004998020131588102,
786
+ "loss": 43.3833,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.0021839702434054338,
791
+ "grad_norm": 37.5,
792
+ "learning_rate": 0.0004997987621433556,
793
+ "loss": 43.1663,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.0022034699777215535,
798
+ "grad_norm": 34.0,
799
+ "learning_rate": 0.0004997955111279009,
800
+ "loss": 42.9925,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.0022229697120376736,
805
+ "grad_norm": 30.25,
806
+ "learning_rate": 0.0004997922601124461,
807
+ "loss": 42.8311,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.0022424694463537933,
812
+ "grad_norm": 35.25,
813
+ "learning_rate": 0.0004997890090969914,
814
+ "loss": 42.5871,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.0022619691806699135,
819
+ "grad_norm": 25.5,
820
+ "learning_rate": 0.0004997857580815368,
821
+ "loss": 42.4199,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.002281468914986033,
826
+ "grad_norm": 28.25,
827
+ "learning_rate": 0.0004997825070660821,
828
+ "loss": 42.3076,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.0023009686493021533,
833
+ "grad_norm": 40.25,
834
+ "learning_rate": 0.0004997792560506274,
835
+ "loss": 42.1746,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.002320468383618273,
840
+ "grad_norm": 35.75,
841
+ "learning_rate": 0.0004997760050351728,
842
+ "loss": 41.8518,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.002339968117934393,
847
+ "grad_norm": 30.125,
848
+ "learning_rate": 0.0004997727540197181,
849
+ "loss": 41.633,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.0023594678522505133,
854
+ "grad_norm": 37.25,
855
+ "learning_rate": 0.0004997695030042634,
856
+ "loss": 41.4918,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.002378967586566633,
861
+ "grad_norm": 28.625,
862
+ "learning_rate": 0.0004997662519888087,
863
+ "loss": 41.2557,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.002398467320882753,
868
+ "grad_norm": 39.25,
869
+ "learning_rate": 0.0004997630009733541,
870
+ "loss": 40.9695,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.002417967055198873,
875
+ "grad_norm": 36.75,
876
+ "learning_rate": 0.0004997597499578994,
877
+ "loss": 41.0831,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.002437466789514993,
882
+ "grad_norm": 38.5,
883
+ "learning_rate": 0.0004997564989424447,
884
+ "loss": 40.9227,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.0024569665238311127,
889
+ "grad_norm": 21.25,
890
+ "learning_rate": 0.00049975324792699,
891
+ "loss": 40.8114,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.002476466258147233,
896
+ "grad_norm": 40.0,
897
+ "learning_rate": 0.0004997499969115354,
898
+ "loss": 40.3053,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.0024959659924633525,
903
+ "grad_norm": 25.625,
904
+ "learning_rate": 0.0004997467458960807,
905
+ "loss": 40.1834,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.0025154657267794727,
910
+ "grad_norm": 24.0,
911
+ "learning_rate": 0.0004997434948806259,
912
+ "loss": 40.1098,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.0025349654610955924,
917
+ "grad_norm": 27.75,
918
+ "learning_rate": 0.0004997402438651713,
919
+ "loss": 40.3268,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.0025544651954117125,
924
+ "grad_norm": 26.125,
925
+ "learning_rate": 0.0004997369928497166,
926
+ "loss": 39.9018,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.0025739649297278322,
931
+ "grad_norm": 31.5,
932
+ "learning_rate": 0.0004997337418342619,
933
+ "loss": 39.8717,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.0025934646640439524,
938
+ "grad_norm": 38.0,
939
+ "learning_rate": 0.0004997304908188072,
940
+ "loss": 39.7441,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.0026129643983600725,
945
+ "grad_norm": 24.625,
946
+ "learning_rate": 0.0004997272398033526,
947
+ "loss": 39.1808,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.0026324641326761922,
952
+ "grad_norm": 29.375,
953
+ "learning_rate": 0.0004997239887878979,
954
+ "loss": 39.4477,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.0026519638669923124,
959
+ "grad_norm": 37.5,
960
+ "learning_rate": 0.0004997207377724432,
961
+ "loss": 39.5394,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.002671463601308432,
966
+ "grad_norm": 29.0,
967
+ "learning_rate": 0.0004997174867569886,
968
+ "loss": 38.9013,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.0026909633356245522,
973
+ "grad_norm": 30.625,
974
+ "learning_rate": 0.0004997142357415339,
975
+ "loss": 38.9672,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.002710463069940672,
980
+ "grad_norm": 25.5,
981
+ "learning_rate": 0.0004997109847260792,
982
+ "loss": 39.0183,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.002729962804256792,
987
+ "grad_norm": 27.0,
988
+ "learning_rate": 0.0004997077337106245,
989
+ "loss": 38.4409,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.002749462538572912,
994
+ "grad_norm": 31.25,
995
+ "learning_rate": 0.0004997044826951699,
996
+ "loss": 38.5942,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.002768962272889032,
1001
+ "grad_norm": 24.0,
1002
+ "learning_rate": 0.0004997012316797152,
1003
+ "loss": 38.5001,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.0027884620072051516,
1008
+ "grad_norm": 24.375,
1009
+ "learning_rate": 0.0004996979806642605,
1010
+ "loss": 38.3484,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.0028079617415212718,
1015
+ "grad_norm": 20.375,
1016
+ "learning_rate": 0.0004996947296488057,
1017
+ "loss": 38.1553,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.002827461475837392,
1022
+ "grad_norm": 28.375,
1023
+ "learning_rate": 0.0004996914786333511,
1024
+ "loss": 38.2732,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.0028469612101535116,
1029
+ "grad_norm": 32.0,
1030
+ "learning_rate": 0.0004996882276178964,
1031
+ "loss": 37.8929,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.0028664609444696318,
1036
+ "grad_norm": 26.875,
1037
+ "learning_rate": 0.0004996849766024417,
1038
+ "loss": 37.665,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.0028859606787857515,
1043
+ "grad_norm": 25.75,
1044
+ "learning_rate": 0.0004996817255869871,
1045
+ "loss": 37.6906,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.0029054604131018716,
1050
+ "grad_norm": 27.25,
1051
+ "learning_rate": 0.0004996784745715324,
1052
+ "loss": 37.6468,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.0029249601474179913,
1057
+ "grad_norm": 37.0,
1058
+ "learning_rate": 0.0004996752235560777,
1059
+ "loss": 37.5751,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.0029444598817341115,
1064
+ "grad_norm": 35.75,
1065
+ "learning_rate": 0.000499671972540623,
1066
+ "loss": 37.4205,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.002963959616050231,
1071
+ "grad_norm": 23.0,
1072
+ "learning_rate": 0.0004996687215251684,
1073
+ "loss": 37.0687,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.0029834593503663513,
1078
+ "grad_norm": 25.625,
1079
+ "learning_rate": 0.0004996654705097137,
1080
+ "loss": 37.1764,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.003002959084682471,
1085
+ "grad_norm": 25.5,
1086
+ "learning_rate": 0.000499662219494259,
1087
+ "loss": 37.2974,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.003022458818998591,
1092
+ "grad_norm": 20.625,
1093
+ "learning_rate": 0.0004996589684788044,
1094
+ "loss": 36.8222,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.003041958553314711,
1099
+ "grad_norm": 25.5,
1100
+ "learning_rate": 0.0004996557174633497,
1101
+ "loss": 36.8232,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.003061458287630831,
1106
+ "grad_norm": 26.5,
1107
+ "learning_rate": 0.000499652466447895,
1108
+ "loss": 36.6847,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.003080958021946951,
1113
+ "grad_norm": 29.625,
1114
+ "learning_rate": 0.0004996492154324403,
1115
+ "loss": 36.5772,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.003100457756263071,
1120
+ "grad_norm": 21.875,
1121
+ "learning_rate": 0.0004996459644169857,
1122
+ "loss": 36.3496,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.003119957490579191,
1127
+ "grad_norm": 21.5,
1128
+ "learning_rate": 0.000499642713401531,
1129
+ "loss": 36.4973,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.0031394572248953107,
1134
+ "grad_norm": 20.125,
1135
+ "learning_rate": 0.0004996394623860763,
1136
+ "loss": 36.0869,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.003158956959211431,
1141
+ "grad_norm": 32.75,
1142
+ "learning_rate": 0.0004996362113706217,
1143
+ "loss": 36.329,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.0031784566935275506,
1148
+ "grad_norm": 27.75,
1149
+ "learning_rate": 0.0004996329603551669,
1150
+ "loss": 35.9796,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.0031979564278436707,
1155
+ "grad_norm": 25.625,
1156
+ "learning_rate": 0.0004996297093397122,
1157
+ "loss": 36.1682,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.0032174561621597904,
1162
+ "grad_norm": 32.25,
1163
+ "learning_rate": 0.0004996264583242575,
1164
+ "loss": 35.8033,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.0032369558964759106,
1169
+ "grad_norm": 24.5,
1170
+ "learning_rate": 0.0004996232073088029,
1171
+ "loss": 35.9699,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.0032564556307920303,
1176
+ "grad_norm": 22.75,
1177
+ "learning_rate": 0.0004996199562933482,
1178
+ "loss": 35.5866,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.0032759553651081504,
1183
+ "grad_norm": 19.25,
1184
+ "learning_rate": 0.0004996167052778935,
1185
+ "loss": 35.4264,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.0032954550994242706,
1190
+ "grad_norm": 27.625,
1191
+ "learning_rate": 0.0004996134542624389,
1192
+ "loss": 35.5103,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.0033149548337403903,
1197
+ "grad_norm": 24.875,
1198
+ "learning_rate": 0.0004996102032469842,
1199
+ "loss": 35.3989,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.0033344545680565104,
1204
+ "grad_norm": 21.625,
1205
+ "learning_rate": 0.0004996069522315295,
1206
+ "loss": 35.3818,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.00335395430237263,
1211
+ "grad_norm": 24.375,
1212
+ "learning_rate": 0.0004996037012160748,
1213
+ "loss": 35.2239,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.0033734540366887503,
1218
+ "grad_norm": 30.625,
1219
+ "learning_rate": 0.0004996004502006202,
1220
+ "loss": 35.466,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.00339295377100487,
1225
+ "grad_norm": 22.75,
1226
+ "learning_rate": 0.0004995971991851655,
1227
+ "loss": 35.1158,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.00341245350532099,
1232
+ "grad_norm": 22.375,
1233
+ "learning_rate": 0.0004995939481697108,
1234
+ "loss": 34.8603,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.00343195323963711,
1239
+ "grad_norm": 34.0,
1240
+ "learning_rate": 0.0004995906971542562,
1241
+ "loss": 34.9983,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.00345145297395323,
1246
+ "grad_norm": 25.5,
1247
+ "learning_rate": 0.0004995874461388015,
1248
+ "loss": 34.6013,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.0034709527082693497,
1253
+ "grad_norm": 27.375,
1254
+ "learning_rate": 0.0004995841951233468,
1255
+ "loss": 34.6497,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.00349045244258547,
1260
+ "grad_norm": 20.0,
1261
+ "learning_rate": 0.0004995809441078921,
1262
+ "loss": 34.5907,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.0035099521769015895,
1267
+ "grad_norm": 23.0,
1268
+ "learning_rate": 0.0004995776930924375,
1269
+ "loss": 34.5397,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.0035294519112177096,
1274
+ "grad_norm": 27.375,
1275
+ "learning_rate": 0.0004995744420769828,
1276
+ "loss": 34.4106,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.00354895164553383,
1281
+ "grad_norm": 19.625,
1282
+ "learning_rate": 0.0004995711910615281,
1283
+ "loss": 34.304,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.0035684513798499495,
1288
+ "grad_norm": 38.25,
1289
+ "learning_rate": 0.0004995679400460735,
1290
+ "loss": 34.1244,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.0035879511141660696,
1295
+ "grad_norm": 22.25,
1296
+ "learning_rate": 0.0004995646890306188,
1297
+ "loss": 34.1788,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.0036074508484821893,
1302
+ "grad_norm": 22.75,
1303
+ "learning_rate": 0.0004995614380151641,
1304
+ "loss": 34.1838,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.0036269505827983095,
1309
+ "grad_norm": 20.5,
1310
+ "learning_rate": 0.0004995581869997094,
1311
+ "loss": 34.0839,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.003646450317114429,
1316
+ "grad_norm": 20.0,
1317
+ "learning_rate": 0.0004995549359842547,
1318
+ "loss": 33.8853,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.0036659500514305493,
1323
+ "grad_norm": 27.375,
1324
+ "learning_rate": 0.0004995516849688,
1325
+ "loss": 33.8864,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.003685449785746669,
1330
+ "grad_norm": 23.75,
1331
+ "learning_rate": 0.0004995484339533453,
1332
+ "loss": 33.8339,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.003704949520062789,
1337
+ "grad_norm": 18.0,
1338
+ "learning_rate": 0.0004995451829378906,
1339
+ "loss": 33.6811,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.003724449254378909,
1344
+ "grad_norm": 19.375,
1345
+ "learning_rate": 0.000499541931922436,
1346
+ "loss": 33.5165,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.003743948988695029,
1351
+ "grad_norm": 29.625,
1352
+ "learning_rate": 0.0004995386809069813,
1353
+ "loss": 33.7162,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.003763448723011149,
1358
+ "grad_norm": 19.125,
1359
+ "learning_rate": 0.0004995354298915266,
1360
+ "loss": 33.6939,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.003782948457327269,
1365
+ "grad_norm": 33.25,
1366
+ "learning_rate": 0.000499532178876072,
1367
+ "loss": 33.5068,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.003802448191643389,
1372
+ "grad_norm": 23.0,
1373
+ "learning_rate": 0.0004995289278606173,
1374
+ "loss": 33.4112,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.0038219479259595087,
1379
+ "grad_norm": 34.75,
1380
+ "learning_rate": 0.0004995256768451626,
1381
+ "loss": 33.1552,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.003841447660275629,
1386
+ "grad_norm": 23.125,
1387
+ "learning_rate": 0.0004995224258297079,
1388
+ "loss": 33.4376,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.0038609473945917486,
1393
+ "grad_norm": 18.875,
1394
+ "learning_rate": 0.0004995191748142533,
1395
+ "loss": 33.0372,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.0038804471289078687,
1400
+ "grad_norm": 20.875,
1401
+ "learning_rate": 0.0004995159237987986,
1402
+ "loss": 33.1252,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.0038999468632239884,
1407
+ "grad_norm": 26.0,
1408
+ "learning_rate": 0.0004995126727833439,
1409
+ "loss": 33.0097,
1410
+ "step": 2000
1411
+ }
1412
+ ],
1413
+ "logging_steps": 10,
1414
+ "max_steps": 1538481,
1415
+ "num_input_tokens_seen": 0,
1416
+ "num_train_epochs": 3,
1417
+ "save_steps": 1000,
1418
+ "stateful_callbacks": {
1419
+ "TrainerControl": {
1420
+ "args": {
1421
+ "should_epoch_stop": false,
1422
+ "should_evaluate": false,
1423
+ "should_log": false,
1424
+ "should_save": true,
1425
+ "should_training_stop": false
1426
+ },
1427
+ "attributes": {}
1428
+ }
1429
+ },
1430
+ "total_flos": 4.321165426127012e+18,
1431
+ "train_batch_size": 48,
1432
+ "trial_name": null,
1433
+ "trial_params": null
1434
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c5089c22c7f9818f28966bbddbad56d0afdd700886fc2481eb1228114e1c105
3
+ size 5432
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b9486fa94e8fc79a7b7df41977075097e10373b9426abe8b458045a6fbf276
3
+ size 1032262338
runs/Sep16_13-28-46_nid006603/events.out.tfevents.1758022141.nid006603.208166.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:409ff9e69becc0373bc9e6fdb4d87862ce67d1eaac85ec890fe60067c2f5177f
3
+ size 364278
runs/Sep16_22-37-21_nid007081/events.out.tfevents.1758055057.nid007081.55404.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7acdc4f03085e2343dfd59272ab71e31c4b31c8bec1be746b06ad834a39fadb0
3
+ size 426414
runs/Sep17_11-23-31_nid007191/events.out.tfevents.1758101018.nid007191.214208.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dfcb957eeeb8b30a4853a0550e5f2d8f957da386b1e8d793e699058a26f8f72
3
+ size 5973
runs/Sep17_11-29-28_nid007081/events.out.tfevents.1758101384.nid007081.193734.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e67029b744eef051aae6eea1141935a5d0ce066906dc528c04e4afc7f2b22a7
3
+ size 174136
runs/Sep17_19-36-25_nid007121/events.out.tfevents.1758130601.nid007121.254584.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7006eb2975cbac12a3db94bc66e7a724f0f1b9837f25ffa8b496665aaa8735f9
3
+ size 47489
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c5089c22c7f9818f28966bbddbad56d0afdd700886fc2481eb1228114e1c105
3
+ size 5432