CocoRoF commited on
Commit
610fd0a
·
verified ·
1 Parent(s): ce738f2

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "x2bee/KoModernBERT-base-v02",
3
+ "architectures": [
4
+ "ModernBERTSimCSE"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 768,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 1152,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 22,
37
+ "pad_token_id": 50283,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": false,
40
+ "repad_logits_with_grad": false,
41
+ "sep_token_id": 50282,
42
+ "sparse_pred_ignore_index": -100,
43
+ "sparse_prediction": false,
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.48.3",
46
+ "vocab_size": 95663
47
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9e1bcee7f011fef03e2175c8251f4452754d982e429b6f1c85c49ad3df80dd
3
+ size 738367848
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7edaedb3fab405157cc63ab8b3d7262e165878db58ddc86f23c506a7b06f9617
3
+ size 1476823354
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06fea830cf5ad73ec00d500ea6fb952740ac936f18e93fa2d32abde1ea3ead92
3
+ size 15984
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be561d1df19be227394d8ea607c54262a06c9bf880af0aa5e04a52596a2a6cb0
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 sha256:03f3e24417a59435f5a8450a4aeb0f09cc92734b5c3b45a0701b2c043c415c05
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 sha256:2bea02744c29f30024590ab1629a0e7b7dabbf1e8476456c2e7c5ce46dc35c28
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 sha256:041be966454b60c86af576fc1eb7f34189114689abff8f9622b947110f7334c8
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:b85766f6596d15a810177d77dd259d9b50588cf100ec5f8ebff5fed881d57957
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 sha256:8be75d04b1ebe614241b88fd010a5dda1b7bf703c00c6ebe310ca07975830fe7
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 sha256:4699833a7ab4cb692996ef7567f934c0bac79d6a067963a873f89a38e412bd48
3
+ size 15984
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:452f0ce45a0532872d3dafca4ac6f3ac9310f686f3f3a2026b82609fe1ad92b0
3
+ size 1000
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "95580": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "95581": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "95582": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "95583": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "95584": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "95585": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "95586": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "95587": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "95588": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "95589": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "95590": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "95591": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "95592": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "95593": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "95594": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "95595": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "95596": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "95597": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "95598": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "95599": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "95600": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "95601": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "95602": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "95603": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "95604": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "95605": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "95606": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "95607": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "95608": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "95609": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "95610": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "95611": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "95612": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "95613": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "95614": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "95615": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "95616": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "95617": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "95618": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "95619": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "95620": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "95621": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "95622": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "95623": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "95624": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "95625": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "95626": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "95627": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "95628": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "95629": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "95630": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "95631": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "95632": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "95633": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "95634": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "95635": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "95636": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "95637": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "95638": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "95639": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "95640": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "95641": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "95642": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "95643": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "95644": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "95645": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "95646": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "95647": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "95648": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "95649": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "95650": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "95651": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "95652": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "95653": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "95654": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "95655": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "95656": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "95657": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "95658": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "95659": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "95660": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "95661": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "95662": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 1000000000000000019884624838656,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizerFast",
944
+ "unk_token": "[UNK]"
945
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,797 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9372071227741331,
5
+ "eval_steps": 250,
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": 0.00937207122774133,
13
+ "grad_norm": 0.573442816734314,
14
+ "learning_rate": 9.999926781765732e-06,
15
+ "loss": 1.312,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.01874414245548266,
20
+ "grad_norm": 1.0577057600021362,
21
+ "learning_rate": 9.999853563531462e-06,
22
+ "loss": 1.2611,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.028116213683223992,
27
+ "grad_norm": 1.358649492263794,
28
+ "learning_rate": 9.999780345297193e-06,
29
+ "loss": 1.1822,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.03748828491096532,
34
+ "grad_norm": 1.7219270467758179,
35
+ "learning_rate": 9.999707127062924e-06,
36
+ "loss": 1.062,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.046860356138706656,
41
+ "grad_norm": 1.7191277742385864,
42
+ "learning_rate": 9.999633908828655e-06,
43
+ "loss": 0.9325,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.056232427366447985,
48
+ "grad_norm": 1.6047089099884033,
49
+ "learning_rate": 9.999560690594387e-06,
50
+ "loss": 0.7909,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.06560449859418932,
55
+ "grad_norm": 1.1597000360488892,
56
+ "learning_rate": 9.999487472360118e-06,
57
+ "loss": 0.6858,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.07497656982193064,
62
+ "grad_norm": 1.4232110977172852,
63
+ "learning_rate": 9.999414254125849e-06,
64
+ "loss": 0.6554,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.08434864104967198,
69
+ "grad_norm": 1.3652020692825317,
70
+ "learning_rate": 9.99934103589158e-06,
71
+ "loss": 0.5937,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.09372071227741331,
76
+ "grad_norm": 1.299221396446228,
77
+ "learning_rate": 9.99926781765731e-06,
78
+ "loss": 0.5778,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.10309278350515463,
83
+ "grad_norm": 1.367699146270752,
84
+ "learning_rate": 9.99919459942304e-06,
85
+ "loss": 0.5562,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.11246485473289597,
90
+ "grad_norm": 1.2190635204315186,
91
+ "learning_rate": 9.999121381188772e-06,
92
+ "loss": 0.5259,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.1218369259606373,
97
+ "grad_norm": 1.1808373928070068,
98
+ "learning_rate": 9.999048162954504e-06,
99
+ "loss": 0.5158,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.13120899718837864,
104
+ "grad_norm": 1.5956122875213623,
105
+ "learning_rate": 9.998974944720235e-06,
106
+ "loss": 0.4877,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.14058106841611998,
111
+ "grad_norm": 1.2425106763839722,
112
+ "learning_rate": 9.998901726485964e-06,
113
+ "loss": 0.4858,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.14995313964386128,
118
+ "grad_norm": 1.284425139427185,
119
+ "learning_rate": 9.998828508251696e-06,
120
+ "loss": 0.4426,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.15932521087160262,
125
+ "grad_norm": 1.4248498678207397,
126
+ "learning_rate": 9.998755290017427e-06,
127
+ "loss": 0.4644,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.16869728209934395,
132
+ "grad_norm": 2.5712969303131104,
133
+ "learning_rate": 9.998682071783158e-06,
134
+ "loss": 0.4363,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.1780693533270853,
139
+ "grad_norm": 1.572169542312622,
140
+ "learning_rate": 9.998608853548888e-06,
141
+ "loss": 0.4206,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.18744142455482662,
146
+ "grad_norm": 1.4508352279663086,
147
+ "learning_rate": 9.998535635314621e-06,
148
+ "loss": 0.4247,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.19681349578256796,
153
+ "grad_norm": 1.2668938636779785,
154
+ "learning_rate": 9.99846241708035e-06,
155
+ "loss": 0.4302,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.20618556701030927,
160
+ "grad_norm": 1.0630348920822144,
161
+ "learning_rate": 9.99838919884608e-06,
162
+ "loss": 0.3987,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.2155576382380506,
167
+ "grad_norm": 1.1395602226257324,
168
+ "learning_rate": 9.998315980611813e-06,
169
+ "loss": 0.3746,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.22492970946579194,
174
+ "grad_norm": 1.6570693254470825,
175
+ "learning_rate": 9.998242762377544e-06,
176
+ "loss": 0.3954,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.23430178069353327,
181
+ "grad_norm": 1.2213038206100464,
182
+ "learning_rate": 9.998169544143275e-06,
183
+ "loss": 0.3877,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.23430178069353327,
188
+ "eval_loss": 0.15415821969509125,
189
+ "eval_pearson_cosine": 0.7471039295196533,
190
+ "eval_pearson_dot": 0.6414342522621155,
191
+ "eval_pearson_euclidean": 0.739482581615448,
192
+ "eval_pearson_manhattan": 0.7393465042114258,
193
+ "eval_runtime": 29.8457,
194
+ "eval_samples_per_second": 50.258,
195
+ "eval_spearman_cosine": 0.7499078042299374,
196
+ "eval_spearman_dot": 0.6346699933138464,
197
+ "eval_spearman_euclidean": 0.7397365400334271,
198
+ "eval_spearman_manhattan": 0.7393369553461101,
199
+ "eval_steps_per_second": 6.299,
200
+ "step": 250
201
+ },
202
+ {
203
+ "epoch": 0.2436738519212746,
204
+ "grad_norm": 1.3511942625045776,
205
+ "learning_rate": 9.998096325909005e-06,
206
+ "loss": 0.3685,
207
+ "step": 260
208
+ },
209
+ {
210
+ "epoch": 0.2530459231490159,
211
+ "grad_norm": 1.3458188772201538,
212
+ "learning_rate": 9.998023107674736e-06,
213
+ "loss": 0.367,
214
+ "step": 270
215
+ },
216
+ {
217
+ "epoch": 0.2624179943767573,
218
+ "grad_norm": 1.424850344657898,
219
+ "learning_rate": 9.997949889440467e-06,
220
+ "loss": 0.3511,
221
+ "step": 280
222
+ },
223
+ {
224
+ "epoch": 0.2717900656044986,
225
+ "grad_norm": 1.4595459699630737,
226
+ "learning_rate": 9.997876671206198e-06,
227
+ "loss": 0.3389,
228
+ "step": 290
229
+ },
230
+ {
231
+ "epoch": 0.28116213683223995,
232
+ "grad_norm": 1.167495608329773,
233
+ "learning_rate": 9.997803452971928e-06,
234
+ "loss": 0.3335,
235
+ "step": 300
236
+ },
237
+ {
238
+ "epoch": 0.29053420805998126,
239
+ "grad_norm": 1.1749252080917358,
240
+ "learning_rate": 9.997730234737661e-06,
241
+ "loss": 0.3339,
242
+ "step": 310
243
+ },
244
+ {
245
+ "epoch": 0.29990627928772257,
246
+ "grad_norm": 1.2500739097595215,
247
+ "learning_rate": 9.99765701650339e-06,
248
+ "loss": 0.3215,
249
+ "step": 320
250
+ },
251
+ {
252
+ "epoch": 0.30927835051546393,
253
+ "grad_norm": 1.332942247390747,
254
+ "learning_rate": 9.99758379826912e-06,
255
+ "loss": 0.3093,
256
+ "step": 330
257
+ },
258
+ {
259
+ "epoch": 0.31865042174320524,
260
+ "grad_norm": 1.173511266708374,
261
+ "learning_rate": 9.997510580034853e-06,
262
+ "loss": 0.3234,
263
+ "step": 340
264
+ },
265
+ {
266
+ "epoch": 0.3280224929709466,
267
+ "grad_norm": 1.3587061166763306,
268
+ "learning_rate": 9.997437361800584e-06,
269
+ "loss": 0.3285,
270
+ "step": 350
271
+ },
272
+ {
273
+ "epoch": 0.3373945641986879,
274
+ "grad_norm": 1.4196358919143677,
275
+ "learning_rate": 9.997364143566315e-06,
276
+ "loss": 0.3078,
277
+ "step": 360
278
+ },
279
+ {
280
+ "epoch": 0.3467666354264292,
281
+ "grad_norm": 1.1899330615997314,
282
+ "learning_rate": 9.997290925332045e-06,
283
+ "loss": 0.2952,
284
+ "step": 370
285
+ },
286
+ {
287
+ "epoch": 0.3561387066541706,
288
+ "grad_norm": 1.3728539943695068,
289
+ "learning_rate": 9.997217707097776e-06,
290
+ "loss": 0.2912,
291
+ "step": 380
292
+ },
293
+ {
294
+ "epoch": 0.3655107778819119,
295
+ "grad_norm": 1.6375203132629395,
296
+ "learning_rate": 9.997144488863507e-06,
297
+ "loss": 0.3153,
298
+ "step": 390
299
+ },
300
+ {
301
+ "epoch": 0.37488284910965325,
302
+ "grad_norm": 1.3330031633377075,
303
+ "learning_rate": 9.997071270629238e-06,
304
+ "loss": 0.2858,
305
+ "step": 400
306
+ },
307
+ {
308
+ "epoch": 0.38425492033739456,
309
+ "grad_norm": 1.2047045230865479,
310
+ "learning_rate": 9.99699805239497e-06,
311
+ "loss": 0.3004,
312
+ "step": 410
313
+ },
314
+ {
315
+ "epoch": 0.3936269915651359,
316
+ "grad_norm": 1.280134916305542,
317
+ "learning_rate": 9.9969248341607e-06,
318
+ "loss": 0.2819,
319
+ "step": 420
320
+ },
321
+ {
322
+ "epoch": 0.4029990627928772,
323
+ "grad_norm": 1.2952693700790405,
324
+ "learning_rate": 9.99685161592643e-06,
325
+ "loss": 0.2772,
326
+ "step": 430
327
+ },
328
+ {
329
+ "epoch": 0.41237113402061853,
330
+ "grad_norm": 1.1937365531921387,
331
+ "learning_rate": 9.996778397692162e-06,
332
+ "loss": 0.3024,
333
+ "step": 440
334
+ },
335
+ {
336
+ "epoch": 0.4217432052483599,
337
+ "grad_norm": 1.226347804069519,
338
+ "learning_rate": 9.996705179457893e-06,
339
+ "loss": 0.2844,
340
+ "step": 450
341
+ },
342
+ {
343
+ "epoch": 0.4311152764761012,
344
+ "grad_norm": 1.5503312349319458,
345
+ "learning_rate": 9.996631961223624e-06,
346
+ "loss": 0.2634,
347
+ "step": 460
348
+ },
349
+ {
350
+ "epoch": 0.44048734770384257,
351
+ "grad_norm": 1.4498707056045532,
352
+ "learning_rate": 9.996558742989355e-06,
353
+ "loss": 0.2697,
354
+ "step": 470
355
+ },
356
+ {
357
+ "epoch": 0.4498594189315839,
358
+ "grad_norm": 1.2823820114135742,
359
+ "learning_rate": 9.996485524755087e-06,
360
+ "loss": 0.2927,
361
+ "step": 480
362
+ },
363
+ {
364
+ "epoch": 0.4592314901593252,
365
+ "grad_norm": 1.1089231967926025,
366
+ "learning_rate": 9.996412306520816e-06,
367
+ "loss": 0.2669,
368
+ "step": 490
369
+ },
370
+ {
371
+ "epoch": 0.46860356138706655,
372
+ "grad_norm": 1.3862818479537964,
373
+ "learning_rate": 9.996339088286547e-06,
374
+ "loss": 0.2805,
375
+ "step": 500
376
+ },
377
+ {
378
+ "epoch": 0.46860356138706655,
379
+ "eval_loss": 0.11416644603013992,
380
+ "eval_pearson_cosine": 0.7577512264251709,
381
+ "eval_pearson_dot": 0.6366492509841919,
382
+ "eval_pearson_euclidean": 0.7618618011474609,
383
+ "eval_pearson_manhattan": 0.7619431614875793,
384
+ "eval_runtime": 22.679,
385
+ "eval_samples_per_second": 66.14,
386
+ "eval_spearman_cosine": 0.7643092952449725,
387
+ "eval_spearman_dot": 0.6341280960850315,
388
+ "eval_spearman_euclidean": 0.7653570734883524,
389
+ "eval_spearman_manhattan": 0.7652284643248553,
390
+ "eval_steps_per_second": 8.29,
391
+ "step": 500
392
+ },
393
+ {
394
+ "epoch": 0.47797563261480785,
395
+ "grad_norm": 1.079265832901001,
396
+ "learning_rate": 9.99626587005228e-06,
397
+ "loss": 0.2649,
398
+ "step": 510
399
+ },
400
+ {
401
+ "epoch": 0.4873477038425492,
402
+ "grad_norm": 1.3966060876846313,
403
+ "learning_rate": 9.99619265181801e-06,
404
+ "loss": 0.279,
405
+ "step": 520
406
+ },
407
+ {
408
+ "epoch": 0.4967197750702905,
409
+ "grad_norm": 1.197001576423645,
410
+ "learning_rate": 9.99611943358374e-06,
411
+ "loss": 0.263,
412
+ "step": 530
413
+ },
414
+ {
415
+ "epoch": 0.5060918462980318,
416
+ "grad_norm": 1.414509892463684,
417
+ "learning_rate": 9.996046215349472e-06,
418
+ "loss": 0.2816,
419
+ "step": 540
420
+ },
421
+ {
422
+ "epoch": 0.5154639175257731,
423
+ "grad_norm": 1.4723501205444336,
424
+ "learning_rate": 9.995972997115202e-06,
425
+ "loss": 0.2696,
426
+ "step": 550
427
+ },
428
+ {
429
+ "epoch": 0.5248359887535146,
430
+ "grad_norm": 1.1838375329971313,
431
+ "learning_rate": 9.995899778880933e-06,
432
+ "loss": 0.2686,
433
+ "step": 560
434
+ },
435
+ {
436
+ "epoch": 0.5342080599812559,
437
+ "grad_norm": 1.2640224695205688,
438
+ "learning_rate": 9.995826560646664e-06,
439
+ "loss": 0.2842,
440
+ "step": 570
441
+ },
442
+ {
443
+ "epoch": 0.5435801312089972,
444
+ "grad_norm": 1.2584717273712158,
445
+ "learning_rate": 9.995753342412395e-06,
446
+ "loss": 0.2505,
447
+ "step": 580
448
+ },
449
+ {
450
+ "epoch": 0.5529522024367385,
451
+ "grad_norm": 1.3276816606521606,
452
+ "learning_rate": 9.995680124178127e-06,
453
+ "loss": 0.2764,
454
+ "step": 590
455
+ },
456
+ {
457
+ "epoch": 0.5623242736644799,
458
+ "grad_norm": 1.5065838098526,
459
+ "learning_rate": 9.995606905943858e-06,
460
+ "loss": 0.2778,
461
+ "step": 600
462
+ },
463
+ {
464
+ "epoch": 0.5716963448922212,
465
+ "grad_norm": 1.1485587358474731,
466
+ "learning_rate": 9.995533687709588e-06,
467
+ "loss": 0.2533,
468
+ "step": 610
469
+ },
470
+ {
471
+ "epoch": 0.5810684161199625,
472
+ "grad_norm": 1.242677927017212,
473
+ "learning_rate": 9.99546046947532e-06,
474
+ "loss": 0.2549,
475
+ "step": 620
476
+ },
477
+ {
478
+ "epoch": 0.5904404873477038,
479
+ "grad_norm": 1.4471759796142578,
480
+ "learning_rate": 9.99538725124105e-06,
481
+ "loss": 0.2734,
482
+ "step": 630
483
+ },
484
+ {
485
+ "epoch": 0.5998125585754451,
486
+ "grad_norm": 1.3379895687103271,
487
+ "learning_rate": 9.99531403300678e-06,
488
+ "loss": 0.2551,
489
+ "step": 640
490
+ },
491
+ {
492
+ "epoch": 0.6091846298031866,
493
+ "grad_norm": 1.2373607158660889,
494
+ "learning_rate": 9.995240814772511e-06,
495
+ "loss": 0.2358,
496
+ "step": 650
497
+ },
498
+ {
499
+ "epoch": 0.6185567010309279,
500
+ "grad_norm": 1.2897976636886597,
501
+ "learning_rate": 9.995167596538242e-06,
502
+ "loss": 0.2572,
503
+ "step": 660
504
+ },
505
+ {
506
+ "epoch": 0.6279287722586692,
507
+ "grad_norm": 1.3715548515319824,
508
+ "learning_rate": 9.995094378303973e-06,
509
+ "loss": 0.2554,
510
+ "step": 670
511
+ },
512
+ {
513
+ "epoch": 0.6373008434864105,
514
+ "grad_norm": 1.3889539241790771,
515
+ "learning_rate": 9.995021160069704e-06,
516
+ "loss": 0.2502,
517
+ "step": 680
518
+ },
519
+ {
520
+ "epoch": 0.6466729147141518,
521
+ "grad_norm": 1.3987656831741333,
522
+ "learning_rate": 9.994947941835436e-06,
523
+ "loss": 0.2449,
524
+ "step": 690
525
+ },
526
+ {
527
+ "epoch": 0.6560449859418932,
528
+ "grad_norm": 1.4677623510360718,
529
+ "learning_rate": 9.994874723601167e-06,
530
+ "loss": 0.2438,
531
+ "step": 700
532
+ },
533
+ {
534
+ "epoch": 0.6654170571696345,
535
+ "grad_norm": 1.238258719444275,
536
+ "learning_rate": 9.994801505366898e-06,
537
+ "loss": 0.2609,
538
+ "step": 710
539
+ },
540
+ {
541
+ "epoch": 0.6747891283973758,
542
+ "grad_norm": 1.2697819471359253,
543
+ "learning_rate": 9.994728287132628e-06,
544
+ "loss": 0.2685,
545
+ "step": 720
546
+ },
547
+ {
548
+ "epoch": 0.6841611996251171,
549
+ "grad_norm": 1.1607269048690796,
550
+ "learning_rate": 9.99465506889836e-06,
551
+ "loss": 0.2342,
552
+ "step": 730
553
+ },
554
+ {
555
+ "epoch": 0.6935332708528584,
556
+ "grad_norm": 1.2666348218917847,
557
+ "learning_rate": 9.99458185066409e-06,
558
+ "loss": 0.2308,
559
+ "step": 740
560
+ },
561
+ {
562
+ "epoch": 0.7029053420805998,
563
+ "grad_norm": 1.252940058708191,
564
+ "learning_rate": 9.99450863242982e-06,
565
+ "loss": 0.2331,
566
+ "step": 750
567
+ },
568
+ {
569
+ "epoch": 0.7029053420805998,
570
+ "eval_loss": 0.09498214721679688,
571
+ "eval_pearson_cosine": 0.7673527002334595,
572
+ "eval_pearson_dot": 0.6584292054176331,
573
+ "eval_pearson_euclidean": 0.7682392001152039,
574
+ "eval_pearson_manhattan": 0.7685161232948303,
575
+ "eval_runtime": 21.4883,
576
+ "eval_samples_per_second": 69.805,
577
+ "eval_spearman_cosine": 0.7771628917615258,
578
+ "eval_spearman_dot": 0.6570265964452069,
579
+ "eval_spearman_euclidean": 0.7740883932373563,
580
+ "eval_spearman_manhattan": 0.7747253819422362,
581
+ "eval_steps_per_second": 8.749,
582
+ "step": 750
583
+ },
584
+ {
585
+ "epoch": 0.7122774133083412,
586
+ "grad_norm": 1.204959750175476,
587
+ "learning_rate": 9.994435414195553e-06,
588
+ "loss": 0.2514,
589
+ "step": 760
590
+ },
591
+ {
592
+ "epoch": 0.7216494845360825,
593
+ "grad_norm": 2.5355069637298584,
594
+ "learning_rate": 9.994362195961284e-06,
595
+ "loss": 0.2473,
596
+ "step": 770
597
+ },
598
+ {
599
+ "epoch": 0.7310215557638238,
600
+ "grad_norm": 1.2129027843475342,
601
+ "learning_rate": 9.994288977727013e-06,
602
+ "loss": 0.2302,
603
+ "step": 780
604
+ },
605
+ {
606
+ "epoch": 0.7403936269915652,
607
+ "grad_norm": 1.109953761100769,
608
+ "learning_rate": 9.994215759492745e-06,
609
+ "loss": 0.2264,
610
+ "step": 790
611
+ },
612
+ {
613
+ "epoch": 0.7497656982193065,
614
+ "grad_norm": 1.443888545036316,
615
+ "learning_rate": 9.994142541258476e-06,
616
+ "loss": 0.2372,
617
+ "step": 800
618
+ },
619
+ {
620
+ "epoch": 0.7591377694470478,
621
+ "grad_norm": 1.3083347082138062,
622
+ "learning_rate": 9.994069323024207e-06,
623
+ "loss": 0.2417,
624
+ "step": 810
625
+ },
626
+ {
627
+ "epoch": 0.7685098406747891,
628
+ "grad_norm": 1.0919073820114136,
629
+ "learning_rate": 9.993996104789938e-06,
630
+ "loss": 0.2331,
631
+ "step": 820
632
+ },
633
+ {
634
+ "epoch": 0.7778819119025304,
635
+ "grad_norm": 1.3770041465759277,
636
+ "learning_rate": 9.993922886555668e-06,
637
+ "loss": 0.2692,
638
+ "step": 830
639
+ },
640
+ {
641
+ "epoch": 0.7872539831302718,
642
+ "grad_norm": 1.2099621295928955,
643
+ "learning_rate": 9.993849668321399e-06,
644
+ "loss": 0.2279,
645
+ "step": 840
646
+ },
647
+ {
648
+ "epoch": 0.7966260543580131,
649
+ "grad_norm": 1.1606112718582153,
650
+ "learning_rate": 9.99377645008713e-06,
651
+ "loss": 0.2474,
652
+ "step": 850
653
+ },
654
+ {
655
+ "epoch": 0.8059981255857545,
656
+ "grad_norm": 1.472863793373108,
657
+ "learning_rate": 9.993703231852862e-06,
658
+ "loss": 0.2298,
659
+ "step": 860
660
+ },
661
+ {
662
+ "epoch": 0.8153701968134958,
663
+ "grad_norm": 1.2455284595489502,
664
+ "learning_rate": 9.993630013618593e-06,
665
+ "loss": 0.2371,
666
+ "step": 870
667
+ },
668
+ {
669
+ "epoch": 0.8247422680412371,
670
+ "grad_norm": 1.3777674436569214,
671
+ "learning_rate": 9.993556795384324e-06,
672
+ "loss": 0.2434,
673
+ "step": 880
674
+ },
675
+ {
676
+ "epoch": 0.8341143392689785,
677
+ "grad_norm": 0.9551514983177185,
678
+ "learning_rate": 9.993483577150055e-06,
679
+ "loss": 0.2074,
680
+ "step": 890
681
+ },
682
+ {
683
+ "epoch": 0.8434864104967198,
684
+ "grad_norm": 1.0588115453720093,
685
+ "learning_rate": 9.993410358915785e-06,
686
+ "loss": 0.2162,
687
+ "step": 900
688
+ },
689
+ {
690
+ "epoch": 0.8528584817244611,
691
+ "grad_norm": 1.3450068235397339,
692
+ "learning_rate": 9.993337140681516e-06,
693
+ "loss": 0.2272,
694
+ "step": 910
695
+ },
696
+ {
697
+ "epoch": 0.8622305529522024,
698
+ "grad_norm": 1.6997965574264526,
699
+ "learning_rate": 9.993263922447247e-06,
700
+ "loss": 0.2315,
701
+ "step": 920
702
+ },
703
+ {
704
+ "epoch": 0.8716026241799437,
705
+ "grad_norm": 1.2186520099639893,
706
+ "learning_rate": 9.993190704212978e-06,
707
+ "loss": 0.2426,
708
+ "step": 930
709
+ },
710
+ {
711
+ "epoch": 0.8809746954076851,
712
+ "grad_norm": 1.0515309572219849,
713
+ "learning_rate": 9.99311748597871e-06,
714
+ "loss": 0.2328,
715
+ "step": 940
716
+ },
717
+ {
718
+ "epoch": 0.8903467666354264,
719
+ "grad_norm": 1.29239821434021,
720
+ "learning_rate": 9.993044267744439e-06,
721
+ "loss": 0.2263,
722
+ "step": 950
723
+ },
724
+ {
725
+ "epoch": 0.8997188378631678,
726
+ "grad_norm": 1.7695139646530151,
727
+ "learning_rate": 9.99297104951017e-06,
728
+ "loss": 0.2466,
729
+ "step": 960
730
+ },
731
+ {
732
+ "epoch": 0.9090909090909091,
733
+ "grad_norm": 1.359837293624878,
734
+ "learning_rate": 9.992897831275902e-06,
735
+ "loss": 0.2215,
736
+ "step": 970
737
+ },
738
+ {
739
+ "epoch": 0.9184629803186504,
740
+ "grad_norm": 1.2525417804718018,
741
+ "learning_rate": 9.992824613041633e-06,
742
+ "loss": 0.2295,
743
+ "step": 980
744
+ },
745
+ {
746
+ "epoch": 0.9278350515463918,
747
+ "grad_norm": 1.2337384223937988,
748
+ "learning_rate": 9.992751394807364e-06,
749
+ "loss": 0.2101,
750
+ "step": 990
751
+ },
752
+ {
753
+ "epoch": 0.9372071227741331,
754
+ "grad_norm": 1.1121580600738525,
755
+ "learning_rate": 9.992678176573095e-06,
756
+ "loss": 0.2455,
757
+ "step": 1000
758
+ },
759
+ {
760
+ "epoch": 0.9372071227741331,
761
+ "eval_loss": 0.09235719591379166,
762
+ "eval_pearson_cosine": 0.7676932215690613,
763
+ "eval_pearson_dot": 0.6569437980651855,
764
+ "eval_pearson_euclidean": 0.7712024450302124,
765
+ "eval_pearson_manhattan": 0.7713895440101624,
766
+ "eval_runtime": 21.9039,
767
+ "eval_samples_per_second": 68.481,
768
+ "eval_spearman_cosine": 0.7780572781571132,
769
+ "eval_spearman_dot": 0.6557682135268442,
770
+ "eval_spearman_euclidean": 0.7775782712174545,
771
+ "eval_spearman_manhattan": 0.7778181970888292,
772
+ "eval_steps_per_second": 8.583,
773
+ "step": 1000
774
+ }
775
+ ],
776
+ "logging_steps": 10,
777
+ "max_steps": 10670,
778
+ "num_input_tokens_seen": 0,
779
+ "num_train_epochs": 10,
780
+ "save_steps": 1000,
781
+ "stateful_callbacks": {
782
+ "TrainerControl": {
783
+ "args": {
784
+ "should_epoch_stop": false,
785
+ "should_evaluate": false,
786
+ "should_log": false,
787
+ "should_save": true,
788
+ "should_training_stop": false
789
+ },
790
+ "attributes": {}
791
+ }
792
+ },
793
+ "total_flos": 0.0,
794
+ "train_batch_size": 2,
795
+ "trial_name": null,
796
+ "trial_params": null
797
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986c671205084881efce8a461314c3045b1655c63a42ab6586fc473d0bd8dd7e
3
+ size 5368