Hugging Face's logo

mrm8488
/
legal-longformer-base-8192-spanish

Fill-Mask
Transformers
PyTorch
TensorBoard
Spanish
roberta
Long documents
longformer
robertalex
spanish
legal
Inference Endpoints
Model card Files Metrics Community
1
mrm8488 commited on
Commit
79b243c
·
1 Parent(s): dc885dc

Upload the model

Browse files
Files changed (14) hide show
  1. config.json +42 -0
  2. merges.txt +0 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. runs/Nov11_14-57-50_0f644eee1dfa/1668178677.4586718/events.out.tfevents.1668178677.0f644eee1dfa.1214.1 +3 -0
  7. runs/Nov11_14-57-50_0f644eee1dfa/events.out.tfevents.1668178677.0f644eee1dfa.1214.0 +3 -0
  8. scheduler.pt +3 -0
  9. special_tokens_map.json +51 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +66 -0
  12. trainer_state.json +706 -0
  13. training_args.bin +3 -0
  14. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/longformer-legal-es-8192",
3
+ "architectures": [
4
+ "RobertaLongForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_window": [
8
+ 512,
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "bos_token_id": 0,
22
+ "classifier_dropout": null,
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "layer_norm_eps": 1e-05,
31
+ "max_position_embeddings": 8194,
32
+ "model_type": "roberta",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.25.0.dev0",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "vocab_size": 52000
42
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53f3e5311ef0760967f220a2acffe9d9d57055f019a05b0608c61263f50de4c5
3
+ size 1055556377
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f7ca86a35c23e553fa9e5677417e7a1ed90a1e80ea3565541022a3d0a42a7b
3
+ size 612923291
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec38c1fd974818cf1151176944cc30da6c3068ad517c372608ee8b7628925ae
3
+ size 14503
runs/Nov11_14-57-50_0f644eee1dfa/1668178677.4586718/events.out.tfevents.1668178677.0f644eee1dfa.1214.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc7dd91032dbbbd62cbfc4e9eb40d5d31231494817e9e70e02a6a279b836f8a
3
+ size 5570
runs/Nov11_14-57-50_0f644eee1dfa/events.out.tfevents.1668178677.0f644eee1dfa.1214.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4630907a44ec3ed4637ad5788c388f788805bd8af174b7376afdff8fef6d670
3
+ size 23325
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6205d4af5d22096b33add4758c3a8dfeaa0873875f1a9fb654dfe6eca7b590
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "max_len": 512,
37
+ "model_max_length": 8192,
38
+ "name_or_path": "/content/drive/MyDrive/longformer-legal-es-8192",
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "special_tokens_map_file": null,
56
+ "tokenizer_class": "RobertaTokenizer",
57
+ "trim_offsets": true,
58
+ "unk_token": {
59
+ "__type": "AddedToken",
60
+ "content": "<unk>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ }
66
+ }
trainer_state.json ADDED
@@ -0,0 +1,706 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.20020782442644267,
5
+ "global_step": 1150,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 6.000000000000001e-07,
13
+ "loss": 2.8988,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 1.2000000000000002e-06,
19
+ "loss": 2.9604,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 1.8e-06,
25
+ "loss": 2.8234,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 2.4000000000000003e-06,
31
+ "loss": 2.7224,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 3e-06,
37
+ "loss": 2.6824,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 3.6e-06,
43
+ "loss": 2.5884,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "learning_rate": 4.2000000000000004e-06,
49
+ "loss": 2.4736,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.01,
54
+ "learning_rate": 4.800000000000001e-06,
55
+ "loss": 2.3262,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.02,
60
+ "learning_rate": 5.4e-06,
61
+ "loss": 2.3179,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.02,
66
+ "learning_rate": 6e-06,
67
+ "loss": 2.3003,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.02,
72
+ "learning_rate": 6.6e-06,
73
+ "loss": 2.2296,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.02,
78
+ "learning_rate": 7.2e-06,
79
+ "loss": 2.1433,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "learning_rate": 7.8e-06,
85
+ "loss": 2.1452,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.02,
90
+ "learning_rate": 8.400000000000001e-06,
91
+ "loss": 2.078,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.03,
96
+ "learning_rate": 9e-06,
97
+ "loss": 2.0396,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.03,
102
+ "learning_rate": 9.600000000000001e-06,
103
+ "loss": 2.0853,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.03,
108
+ "learning_rate": 1.02e-05,
109
+ "loss": 2.0704,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.03,
114
+ "learning_rate": 1.08e-05,
115
+ "loss": 1.9803,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.03,
120
+ "learning_rate": 1.1400000000000001e-05,
121
+ "loss": 2.0011,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.03,
126
+ "learning_rate": 1.2e-05,
127
+ "loss": 1.93,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.04,
132
+ "learning_rate": 1.26e-05,
133
+ "loss": 1.9777,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 0.04,
138
+ "learning_rate": 1.32e-05,
139
+ "loss": 1.8732,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 0.04,
144
+ "learning_rate": 1.3800000000000002e-05,
145
+ "loss": 1.8803,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 0.04,
150
+ "learning_rate": 1.44e-05,
151
+ "loss": 1.8258,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 0.04,
156
+ "learning_rate": 1.5e-05,
157
+ "loss": 1.8486,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 0.05,
162
+ "learning_rate": 1.56e-05,
163
+ "loss": 1.8054,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 0.05,
168
+ "learning_rate": 1.62e-05,
169
+ "loss": 1.8284,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 0.05,
174
+ "learning_rate": 1.6800000000000002e-05,
175
+ "loss": 1.7647,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 0.05,
180
+ "learning_rate": 1.74e-05,
181
+ "loss": 1.7801,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 0.05,
186
+ "learning_rate": 1.8e-05,
187
+ "loss": 1.7765,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 0.05,
192
+ "learning_rate": 1.86e-05,
193
+ "loss": 1.7285,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 0.06,
198
+ "learning_rate": 1.9200000000000003e-05,
199
+ "loss": 1.7652,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 0.06,
204
+ "learning_rate": 1.98e-05,
205
+ "loss": 1.7792,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 0.06,
210
+ "learning_rate": 2.04e-05,
211
+ "loss": 1.7661,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 0.06,
216
+ "learning_rate": 2.1e-05,
217
+ "loss": 1.7171,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 0.06,
222
+ "learning_rate": 2.16e-05,
223
+ "loss": 1.7829,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 0.06,
228
+ "learning_rate": 2.22e-05,
229
+ "loss": 1.752,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 0.07,
234
+ "learning_rate": 2.2800000000000002e-05,
235
+ "loss": 1.6864,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 0.07,
240
+ "learning_rate": 2.3400000000000003e-05,
241
+ "loss": 1.7163,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 0.07,
246
+ "learning_rate": 2.4e-05,
247
+ "loss": 1.7071,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 0.07,
252
+ "learning_rate": 2.4599999999999998e-05,
253
+ "loss": 1.7115,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 0.07,
258
+ "learning_rate": 2.52e-05,
259
+ "loss": 1.7248,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 0.07,
264
+ "learning_rate": 2.58e-05,
265
+ "loss": 1.6862,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 0.08,
270
+ "learning_rate": 2.64e-05,
271
+ "loss": 1.6393,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 0.08,
276
+ "learning_rate": 2.7000000000000002e-05,
277
+ "loss": 1.6815,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 0.08,
282
+ "learning_rate": 2.7600000000000003e-05,
283
+ "loss": 1.6933,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 0.08,
288
+ "learning_rate": 2.8199999999999998e-05,
289
+ "loss": 1.6984,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 0.08,
294
+ "learning_rate": 2.88e-05,
295
+ "loss": 1.6677,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 0.09,
300
+ "learning_rate": 2.94e-05,
301
+ "loss": 1.6683,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 0.09,
306
+ "learning_rate": 3e-05,
307
+ "loss": 1.6234,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 0.09,
312
+ "learning_rate": 2.9880000000000002e-05,
313
+ "loss": 1.6206,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 0.09,
318
+ "learning_rate": 2.976e-05,
319
+ "loss": 1.6712,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 0.09,
324
+ "learning_rate": 2.964e-05,
325
+ "loss": 1.652,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 0.09,
330
+ "learning_rate": 2.9520000000000002e-05,
331
+ "loss": 1.6202,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 0.1,
336
+ "learning_rate": 2.94e-05,
337
+ "loss": 1.6745,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 0.1,
342
+ "learning_rate": 2.928e-05,
343
+ "loss": 1.6772,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 0.1,
348
+ "learning_rate": 2.916e-05,
349
+ "loss": 1.6238,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 0.1,
354
+ "learning_rate": 2.904e-05,
355
+ "loss": 1.5743,
356
+ "step": 580
357
+ },
358
+ {
359
+ "epoch": 0.1,
360
+ "learning_rate": 2.892e-05,
361
+ "loss": 1.6013,
362
+ "step": 590
363
+ },
364
+ {
365
+ "epoch": 0.1,
366
+ "learning_rate": 2.88e-05,
367
+ "loss": 1.5846,
368
+ "step": 600
369
+ },
370
+ {
371
+ "epoch": 0.11,
372
+ "learning_rate": 2.868e-05,
373
+ "loss": 1.6274,
374
+ "step": 610
375
+ },
376
+ {
377
+ "epoch": 0.11,
378
+ "learning_rate": 2.856e-05,
379
+ "loss": 1.6018,
380
+ "step": 620
381
+ },
382
+ {
383
+ "epoch": 0.11,
384
+ "learning_rate": 2.844e-05,
385
+ "loss": 1.5927,
386
+ "step": 630
387
+ },
388
+ {
389
+ "epoch": 0.11,
390
+ "learning_rate": 2.832e-05,
391
+ "loss": 1.5887,
392
+ "step": 640
393
+ },
394
+ {
395
+ "epoch": 0.11,
396
+ "learning_rate": 2.8199999999999998e-05,
397
+ "loss": 1.5446,
398
+ "step": 650
399
+ },
400
+ {
401
+ "epoch": 0.11,
402
+ "learning_rate": 2.8080000000000002e-05,
403
+ "loss": 1.6083,
404
+ "step": 660
405
+ },
406
+ {
407
+ "epoch": 0.12,
408
+ "learning_rate": 2.7960000000000003e-05,
409
+ "loss": 1.575,
410
+ "step": 670
411
+ },
412
+ {
413
+ "epoch": 0.12,
414
+ "learning_rate": 2.784e-05,
415
+ "loss": 1.6243,
416
+ "step": 680
417
+ },
418
+ {
419
+ "epoch": 0.12,
420
+ "learning_rate": 2.7720000000000002e-05,
421
+ "loss": 1.5957,
422
+ "step": 690
423
+ },
424
+ {
425
+ "epoch": 0.12,
426
+ "learning_rate": 2.7600000000000003e-05,
427
+ "loss": 1.5684,
428
+ "step": 700
429
+ },
430
+ {
431
+ "epoch": 0.12,
432
+ "learning_rate": 2.748e-05,
433
+ "loss": 1.5778,
434
+ "step": 710
435
+ },
436
+ {
437
+ "epoch": 0.13,
438
+ "learning_rate": 2.7360000000000002e-05,
439
+ "loss": 1.6025,
440
+ "step": 720
441
+ },
442
+ {
443
+ "epoch": 0.13,
444
+ "learning_rate": 2.724e-05,
445
+ "loss": 1.56,
446
+ "step": 730
447
+ },
448
+ {
449
+ "epoch": 0.13,
450
+ "learning_rate": 2.712e-05,
451
+ "loss": 1.5475,
452
+ "step": 740
453
+ },
454
+ {
455
+ "epoch": 0.13,
456
+ "learning_rate": 2.7000000000000002e-05,
457
+ "loss": 1.5322,
458
+ "step": 750
459
+ },
460
+ {
461
+ "epoch": 0.13,
462
+ "learning_rate": 2.688e-05,
463
+ "loss": 1.5708,
464
+ "step": 760
465
+ },
466
+ {
467
+ "epoch": 0.13,
468
+ "learning_rate": 2.676e-05,
469
+ "loss": 1.5688,
470
+ "step": 770
471
+ },
472
+ {
473
+ "epoch": 0.14,
474
+ "learning_rate": 2.6640000000000002e-05,
475
+ "loss": 1.5407,
476
+ "step": 780
477
+ },
478
+ {
479
+ "epoch": 0.14,
480
+ "learning_rate": 2.652e-05,
481
+ "loss": 1.4945,
482
+ "step": 790
483
+ },
484
+ {
485
+ "epoch": 0.14,
486
+ "learning_rate": 2.64e-05,
487
+ "loss": 1.5536,
488
+ "step": 800
489
+ },
490
+ {
491
+ "epoch": 0.14,
492
+ "learning_rate": 2.628e-05,
493
+ "loss": 1.5501,
494
+ "step": 810
495
+ },
496
+ {
497
+ "epoch": 0.14,
498
+ "learning_rate": 2.616e-05,
499
+ "loss": 1.5184,
500
+ "step": 820
501
+ },
502
+ {
503
+ "epoch": 0.14,
504
+ "learning_rate": 2.604e-05,
505
+ "loss": 1.5046,
506
+ "step": 830
507
+ },
508
+ {
509
+ "epoch": 0.15,
510
+ "learning_rate": 2.592e-05,
511
+ "loss": 1.5529,
512
+ "step": 840
513
+ },
514
+ {
515
+ "epoch": 0.15,
516
+ "learning_rate": 2.58e-05,
517
+ "loss": 1.5006,
518
+ "step": 850
519
+ },
520
+ {
521
+ "epoch": 0.15,
522
+ "learning_rate": 2.568e-05,
523
+ "loss": 1.4979,
524
+ "step": 860
525
+ },
526
+ {
527
+ "epoch": 0.15,
528
+ "learning_rate": 2.556e-05,
529
+ "loss": 1.5288,
530
+ "step": 870
531
+ },
532
+ {
533
+ "epoch": 0.15,
534
+ "learning_rate": 2.544e-05,
535
+ "loss": 1.5924,
536
+ "step": 880
537
+ },
538
+ {
539
+ "epoch": 0.15,
540
+ "learning_rate": 2.5319999999999998e-05,
541
+ "loss": 1.5031,
542
+ "step": 890
543
+ },
544
+ {
545
+ "epoch": 0.16,
546
+ "learning_rate": 2.52e-05,
547
+ "loss": 1.5628,
548
+ "step": 900
549
+ },
550
+ {
551
+ "epoch": 0.16,
552
+ "learning_rate": 2.508e-05,
553
+ "loss": 1.5173,
554
+ "step": 910
555
+ },
556
+ {
557
+ "epoch": 0.16,
558
+ "learning_rate": 2.4959999999999998e-05,
559
+ "loss": 1.5159,
560
+ "step": 920
561
+ },
562
+ {
563
+ "epoch": 0.16,
564
+ "learning_rate": 2.484e-05,
565
+ "loss": 1.4837,
566
+ "step": 930
567
+ },
568
+ {
569
+ "epoch": 0.16,
570
+ "learning_rate": 2.472e-05,
571
+ "loss": 1.528,
572
+ "step": 940
573
+ },
574
+ {
575
+ "epoch": 0.17,
576
+ "learning_rate": 2.4599999999999998e-05,
577
+ "loss": 1.5605,
578
+ "step": 950
579
+ },
580
+ {
581
+ "epoch": 0.17,
582
+ "learning_rate": 2.448e-05,
583
+ "loss": 1.4884,
584
+ "step": 960
585
+ },
586
+ {
587
+ "epoch": 0.17,
588
+ "learning_rate": 2.4360000000000004e-05,
589
+ "loss": 1.5194,
590
+ "step": 970
591
+ },
592
+ {
593
+ "epoch": 0.17,
594
+ "learning_rate": 2.4240000000000002e-05,
595
+ "loss": 1.5145,
596
+ "step": 980
597
+ },
598
+ {
599
+ "epoch": 0.17,
600
+ "learning_rate": 2.4120000000000003e-05,
601
+ "loss": 1.5127,
602
+ "step": 990
603
+ },
604
+ {
605
+ "epoch": 0.17,
606
+ "learning_rate": 2.4e-05,
607
+ "loss": 1.5129,
608
+ "step": 1000
609
+ },
610
+ {
611
+ "epoch": 0.18,
612
+ "learning_rate": 2.3880000000000002e-05,
613
+ "loss": 1.4943,
614
+ "step": 1010
615
+ },
616
+ {
617
+ "epoch": 0.18,
618
+ "learning_rate": 2.3760000000000003e-05,
619
+ "loss": 1.5653,
620
+ "step": 1020
621
+ },
622
+ {
623
+ "epoch": 0.18,
624
+ "learning_rate": 2.364e-05,
625
+ "loss": 1.5496,
626
+ "step": 1030
627
+ },
628
+ {
629
+ "epoch": 0.18,
630
+ "learning_rate": 2.3520000000000002e-05,
631
+ "loss": 1.5118,
632
+ "step": 1040
633
+ },
634
+ {
635
+ "epoch": 0.18,
636
+ "learning_rate": 2.3400000000000003e-05,
637
+ "loss": 1.4897,
638
+ "step": 1050
639
+ },
640
+ {
641
+ "epoch": 0.18,
642
+ "learning_rate": 2.328e-05,
643
+ "loss": 1.5305,
644
+ "step": 1060
645
+ },
646
+ {
647
+ "epoch": 0.19,
648
+ "learning_rate": 2.3160000000000002e-05,
649
+ "loss": 1.518,
650
+ "step": 1070
651
+ },
652
+ {
653
+ "epoch": 0.19,
654
+ "learning_rate": 2.304e-05,
655
+ "loss": 1.525,
656
+ "step": 1080
657
+ },
658
+ {
659
+ "epoch": 0.19,
660
+ "learning_rate": 2.292e-05,
661
+ "loss": 1.4876,
662
+ "step": 1090
663
+ },
664
+ {
665
+ "epoch": 0.19,
666
+ "learning_rate": 2.2800000000000002e-05,
667
+ "loss": 1.4853,
668
+ "step": 1100
669
+ },
670
+ {
671
+ "epoch": 0.19,
672
+ "learning_rate": 2.268e-05,
673
+ "loss": 1.5047,
674
+ "step": 1110
675
+ },
676
+ {
677
+ "epoch": 0.19,
678
+ "learning_rate": 2.256e-05,
679
+ "loss": 1.4842,
680
+ "step": 1120
681
+ },
682
+ {
683
+ "epoch": 0.2,
684
+ "learning_rate": 2.2440000000000002e-05,
685
+ "loss": 1.5162,
686
+ "step": 1130
687
+ },
688
+ {
689
+ "epoch": 0.2,
690
+ "learning_rate": 2.232e-05,
691
+ "loss": 1.5132,
692
+ "step": 1140
693
+ },
694
+ {
695
+ "epoch": 0.2,
696
+ "learning_rate": 2.22e-05,
697
+ "loss": 1.4743,
698
+ "step": 1150
699
+ }
700
+ ],
701
+ "max_steps": 3000,
702
+ "num_train_epochs": 1,
703
+ "total_flos": 1.93471168118784e+17,
704
+ "trial_name": null,
705
+ "trial_params": null
706
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76d38cdbb9756402229e56f2eac4be56919ef4ac65ac07e32ec64ba00037ab1
3
+ size 3439
vocab.json ADDED
The diff for this file is too large to render. See raw diff