mrm8488 commited on
Commit
bebf678
1 Parent(s): 8e92993

Initial commit from mrm8488

Browse files
config.json ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "decoder_start_token_id": null,
16
+ "diversity_penalty": 0.0,
17
+ "do_sample": false,
18
+ "early_stopping": false,
19
+ "encoder_no_repeat_ngram_size": 0,
20
+ "eos_token_id": null,
21
+ "finetuning_task": null,
22
+ "forced_bos_token_id": null,
23
+ "forced_eos_token_id": null,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
+ "is_decoder": true,
35
+ "is_encoder_decoder": false,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1
39
+ },
40
+ "layer_norm_eps": 1e-12,
41
+ "length_penalty": 1.0,
42
+ "max_length": 20,
43
+ "max_position_embeddings": 512,
44
+ "min_length": 0,
45
+ "model_type": "bert",
46
+ "no_repeat_ngram_size": 0,
47
+ "num_attention_heads": 12,
48
+ "num_beam_groups": 1,
49
+ "num_beams": 1,
50
+ "num_hidden_layers": 12,
51
+ "num_return_sequences": 1,
52
+ "output_attentions": false,
53
+ "output_hidden_states": false,
54
+ "output_past": true,
55
+ "output_scores": false,
56
+ "pad_token_id": 1,
57
+ "position_embedding_type": "absolute",
58
+ "prefix": null,
59
+ "pruned_heads": {},
60
+ "remove_invalid_values": false,
61
+ "repetition_penalty": 1.0,
62
+ "return_dict": true,
63
+ "return_dict_in_generate": false,
64
+ "sep_token_id": null,
65
+ "task_specific_params": null,
66
+ "temperature": 1.0,
67
+ "tie_encoder_decoder": false,
68
+ "tie_word_embeddings": true,
69
+ "tokenizer_class": null,
70
+ "top_k": 50,
71
+ "top_p": 1.0,
72
+ "torchscript": false,
73
+ "transformers_version": "4.6.0.dev0",
74
+ "type_vocab_size": 2,
75
+ "use_bfloat16": false,
76
+ "use_cache": true,
77
+ "vocab_size": 31002
78
+ },
79
+ "decoder_start_token_id": 4,
80
+ "early_stopping": true,
81
+ "encoder": {
82
+ "_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
83
+ "add_cross_attention": false,
84
+ "architectures": [
85
+ "BertForMaskedLM"
86
+ ],
87
+ "attention_probs_dropout_prob": 0.1,
88
+ "bad_words_ids": null,
89
+ "bos_token_id": null,
90
+ "chunk_size_feed_forward": 0,
91
+ "decoder_start_token_id": null,
92
+ "diversity_penalty": 0.0,
93
+ "do_sample": false,
94
+ "early_stopping": false,
95
+ "encoder_no_repeat_ngram_size": 0,
96
+ "eos_token_id": null,
97
+ "finetuning_task": null,
98
+ "forced_bos_token_id": null,
99
+ "forced_eos_token_id": null,
100
+ "gradient_checkpointing": false,
101
+ "hidden_act": "gelu",
102
+ "hidden_dropout_prob": 0.1,
103
+ "hidden_size": 768,
104
+ "id2label": {
105
+ "0": "LABEL_0",
106
+ "1": "LABEL_1"
107
+ },
108
+ "initializer_range": 0.02,
109
+ "intermediate_size": 3072,
110
+ "is_decoder": false,
111
+ "is_encoder_decoder": false,
112
+ "label2id": {
113
+ "LABEL_0": 0,
114
+ "LABEL_1": 1
115
+ },
116
+ "layer_norm_eps": 1e-12,
117
+ "length_penalty": 1.0,
118
+ "max_length": 20,
119
+ "max_position_embeddings": 512,
120
+ "min_length": 0,
121
+ "model_type": "bert",
122
+ "no_repeat_ngram_size": 0,
123
+ "num_attention_heads": 12,
124
+ "num_beam_groups": 1,
125
+ "num_beams": 1,
126
+ "num_hidden_layers": 12,
127
+ "num_return_sequences": 1,
128
+ "output_attentions": false,
129
+ "output_hidden_states": false,
130
+ "output_past": true,
131
+ "output_scores": false,
132
+ "pad_token_id": 1,
133
+ "position_embedding_type": "absolute",
134
+ "prefix": null,
135
+ "pruned_heads": {},
136
+ "remove_invalid_values": false,
137
+ "repetition_penalty": 1.0,
138
+ "return_dict": true,
139
+ "return_dict_in_generate": false,
140
+ "sep_token_id": null,
141
+ "task_specific_params": null,
142
+ "temperature": 1.0,
143
+ "tie_encoder_decoder": false,
144
+ "tie_word_embeddings": true,
145
+ "tokenizer_class": null,
146
+ "top_k": 50,
147
+ "top_p": 1.0,
148
+ "torchscript": false,
149
+ "transformers_version": "4.6.0.dev0",
150
+ "type_vocab_size": 2,
151
+ "use_bfloat16": false,
152
+ "use_cache": true,
153
+ "vocab_size": 31002
154
+ },
155
+ "eos_token_id": 5,
156
+ "is_encoder_decoder": true,
157
+ "length_penalty": 2.0,
158
+ "max_length": 256,
159
+ "min_length": 8,
160
+ "model_type": "encoder-decoder",
161
+ "no_repeat_ngram_size": 3,
162
+ "num_beams": 4,
163
+ "pad_token_id": 1,
164
+ "tie_encoder_decoder": true,
165
+ "vocab_size": 31002
166
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb15df5bf1da17e35070b8cfacc783053ffbc2b7453d3058b0bf2aecdecd1a44
3
+ size 555561637
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "name_or_path": "dccuchile/bert-base-spanish-wwm-cased", "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/9848a00af462c42dfb4ec88ef438fbab5256330f7f6f50badc48d277f9367d49.f982506b52498d4adb4bd491f593dc92b2ef6be61bfdbe9d30f53f963f9f5b66", "tokenizer_file": "/root/.cache/huggingface/transformers/44de7af89c157bf67367a71105165d92bebe0585543739a918e3870d25484c27.6a099cd4b12bf7db174fffe48b004eb919c325f108e0c36176a0fe0ad1848d31"}
trainer_state.json ADDED
@@ -0,0 +1,892 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 12.886142983230362,
5
+ "global_step": 73000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 4.975482985191724e-05,
13
+ "loss": 5.0818,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.18,
18
+ "learning_rate": 4.9509659703834464e-05,
19
+ "loss": 4.0909,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.26,
24
+ "learning_rate": 4.926448955575169e-05,
25
+ "loss": 3.4691,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.35,
30
+ "learning_rate": 4.9019319407668926e-05,
31
+ "loss": 2.6149,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.44,
36
+ "learning_rate": 4.8774149259586154e-05,
37
+ "loss": 1.9173,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.53,
42
+ "learning_rate": 4.852897911150339e-05,
43
+ "loss": 1.5632,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.62,
48
+ "learning_rate": 4.8283808963420616e-05,
49
+ "loss": 1.4404,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.71,
54
+ "learning_rate": 4.8038638815337844e-05,
55
+ "loss": 1.3445,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.79,
60
+ "learning_rate": 4.779346866725508e-05,
61
+ "loss": 1.2212,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.88,
66
+ "learning_rate": 4.7548298519172305e-05,
67
+ "loss": 1.1768,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.97,
72
+ "learning_rate": 4.730312837108954e-05,
73
+ "loss": 1.1509,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.06,
78
+ "learning_rate": 4.705795822300677e-05,
79
+ "loss": 0.9679,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.15,
84
+ "learning_rate": 4.6812788074924e-05,
85
+ "loss": 0.8976,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.24,
90
+ "learning_rate": 4.656761792684123e-05,
91
+ "loss": 0.8739,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.32,
96
+ "learning_rate": 4.632244777875846e-05,
97
+ "loss": 0.8976,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.41,
102
+ "learning_rate": 4.607727763067569e-05,
103
+ "loss": 0.8516,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.5,
108
+ "learning_rate": 4.5832107482592926e-05,
109
+ "loss": 0.8655,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.59,
114
+ "learning_rate": 4.558693733451015e-05,
115
+ "loss": 0.8692,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.68,
120
+ "learning_rate": 4.534176718642738e-05,
121
+ "loss": 0.8289,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.77,
126
+ "learning_rate": 4.5096597038344615e-05,
127
+ "loss": 0.8132,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.85,
132
+ "learning_rate": 4.485142689026184e-05,
133
+ "loss": 0.7894,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.94,
138
+ "learning_rate": 4.460625674217908e-05,
139
+ "loss": 0.796,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 2.03,
144
+ "learning_rate": 4.4361086594096305e-05,
145
+ "loss": 0.7169,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 2.12,
150
+ "learning_rate": 4.411591644601353e-05,
151
+ "loss": 0.5873,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.21,
156
+ "learning_rate": 4.387074629793077e-05,
157
+ "loss": 0.5975,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.29,
162
+ "learning_rate": 4.3625576149847994e-05,
163
+ "loss": 0.6024,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.38,
168
+ "learning_rate": 4.338040600176523e-05,
169
+ "loss": 0.5982,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.47,
174
+ "learning_rate": 4.3135235853682456e-05,
175
+ "loss": 0.6028,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 2.56,
180
+ "learning_rate": 4.2890065705599684e-05,
181
+ "loss": 0.6075,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 2.65,
186
+ "learning_rate": 4.264489555751692e-05,
187
+ "loss": 0.5916,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.74,
192
+ "learning_rate": 4.2399725409434146e-05,
193
+ "loss": 0.6201,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 2.82,
198
+ "learning_rate": 4.215455526135138e-05,
199
+ "loss": 0.5912,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 2.91,
204
+ "learning_rate": 4.1909385113268615e-05,
205
+ "loss": 0.586,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 3.0,
210
+ "learning_rate": 4.1664214965185836e-05,
211
+ "loss": 0.6191,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 3.09,
216
+ "learning_rate": 4.141904481710307e-05,
217
+ "loss": 0.4129,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 3.18,
222
+ "learning_rate": 4.1173874669020304e-05,
223
+ "loss": 0.4322,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 3.27,
228
+ "learning_rate": 4.092870452093753e-05,
229
+ "loss": 0.439,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 3.35,
234
+ "learning_rate": 4.0683534372854766e-05,
235
+ "loss": 0.4423,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 3.44,
240
+ "learning_rate": 4.0438364224771994e-05,
241
+ "loss": 0.4428,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 3.53,
246
+ "learning_rate": 4.019319407668922e-05,
247
+ "loss": 0.4441,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 3.62,
252
+ "learning_rate": 3.9948023928606456e-05,
253
+ "loss": 0.4499,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 3.71,
258
+ "learning_rate": 3.9702853780523683e-05,
259
+ "loss": 0.4561,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 3.8,
264
+ "learning_rate": 3.945768363244092e-05,
265
+ "loss": 0.4601,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 3.88,
270
+ "learning_rate": 3.9212513484358145e-05,
271
+ "loss": 0.455,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 3.97,
276
+ "learning_rate": 3.896734333627537e-05,
277
+ "loss": 0.4718,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 4.06,
282
+ "learning_rate": 3.872217318819261e-05,
283
+ "loss": 0.3575,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 4.15,
288
+ "learning_rate": 3.8477003040109835e-05,
289
+ "loss": 0.3211,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 4.24,
294
+ "learning_rate": 3.823183289202707e-05,
295
+ "loss": 0.3413,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 4.32,
300
+ "learning_rate": 3.7986662743944304e-05,
301
+ "loss": 0.3325,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 4.41,
306
+ "learning_rate": 3.7741492595861525e-05,
307
+ "loss": 0.3552,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 4.5,
312
+ "learning_rate": 3.749632244777876e-05,
313
+ "loss": 0.3475,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 4.59,
318
+ "learning_rate": 3.725115229969599e-05,
319
+ "loss": 0.3617,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 4.68,
324
+ "learning_rate": 3.700598215161322e-05,
325
+ "loss": 0.3457,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 4.77,
330
+ "learning_rate": 3.6760812003530455e-05,
331
+ "loss": 0.3658,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 4.85,
336
+ "learning_rate": 3.651564185544768e-05,
337
+ "loss": 0.348,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 4.94,
342
+ "learning_rate": 3.627047170736491e-05,
343
+ "loss": 0.3547,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 5.03,
348
+ "learning_rate": 3.6025301559282145e-05,
349
+ "loss": 0.3103,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 5.12,
354
+ "learning_rate": 3.578013141119937e-05,
355
+ "loss": 0.2441,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 5.21,
360
+ "learning_rate": 3.553496126311661e-05,
361
+ "loss": 0.2516,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 5.3,
366
+ "learning_rate": 3.528979111503384e-05,
367
+ "loss": 0.261,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 5.38,
372
+ "learning_rate": 3.504462096695106e-05,
373
+ "loss": 0.2665,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 5.47,
378
+ "learning_rate": 3.4799450818868296e-05,
379
+ "loss": 0.2585,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 5.56,
384
+ "learning_rate": 3.4554280670785524e-05,
385
+ "loss": 0.2794,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 5.65,
390
+ "learning_rate": 3.430911052270276e-05,
391
+ "loss": 0.2757,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 5.74,
396
+ "learning_rate": 3.406394037461999e-05,
397
+ "loss": 0.289,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 5.83,
402
+ "learning_rate": 3.3818770226537214e-05,
403
+ "loss": 0.2775,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 5.91,
408
+ "learning_rate": 3.357360007845445e-05,
409
+ "loss": 0.282,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 6.0,
414
+ "learning_rate": 3.332842993037168e-05,
415
+ "loss": 0.28,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 6.09,
420
+ "learning_rate": 3.308325978228891e-05,
421
+ "loss": 0.193,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 6.18,
426
+ "learning_rate": 3.2838089634206144e-05,
427
+ "loss": 0.1936,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 6.27,
432
+ "learning_rate": 3.259291948612337e-05,
433
+ "loss": 0.2037,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 6.35,
438
+ "learning_rate": 3.23477493380406e-05,
439
+ "loss": 0.2154,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 6.44,
444
+ "learning_rate": 3.2102579189957834e-05,
445
+ "loss": 0.2103,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 6.53,
450
+ "learning_rate": 3.185740904187506e-05,
451
+ "loss": 0.216,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 6.62,
456
+ "learning_rate": 3.1612238893792296e-05,
457
+ "loss": 0.2115,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 6.71,
462
+ "learning_rate": 3.1367068745709523e-05,
463
+ "loss": 0.226,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 6.8,
468
+ "learning_rate": 3.112189859762675e-05,
469
+ "loss": 0.2232,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 6.88,
474
+ "learning_rate": 3.0876728449543985e-05,
475
+ "loss": 0.2272,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 6.97,
480
+ "learning_rate": 3.063155830146121e-05,
481
+ "loss": 0.2344,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 7.06,
486
+ "learning_rate": 3.0386388153378447e-05,
487
+ "loss": 0.1742,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 7.15,
492
+ "learning_rate": 3.014121800529568e-05,
493
+ "loss": 0.1587,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 7.24,
498
+ "learning_rate": 2.9896047857212906e-05,
499
+ "loss": 0.1653,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 7.33,
504
+ "learning_rate": 2.9650877709130137e-05,
505
+ "loss": 0.1679,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 7.41,
510
+ "learning_rate": 2.9405707561047368e-05,
511
+ "loss": 0.1728,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 7.5,
516
+ "learning_rate": 2.91605374129646e-05,
517
+ "loss": 0.1729,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 7.59,
522
+ "learning_rate": 2.8915367264881833e-05,
523
+ "loss": 0.1737,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 7.68,
528
+ "learning_rate": 2.8670197116799058e-05,
529
+ "loss": 0.181,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 7.77,
534
+ "learning_rate": 2.842502696871629e-05,
535
+ "loss": 0.1771,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 7.86,
540
+ "learning_rate": 2.817985682063352e-05,
541
+ "loss": 0.1818,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 7.94,
546
+ "learning_rate": 2.7934686672550754e-05,
547
+ "loss": 0.1847,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 8.03,
552
+ "learning_rate": 2.7689516524467985e-05,
553
+ "loss": 0.1643,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 8.12,
558
+ "learning_rate": 2.744434637638521e-05,
559
+ "loss": 0.1249,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 8.21,
564
+ "learning_rate": 2.7199176228302443e-05,
565
+ "loss": 0.1315,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 8.3,
570
+ "learning_rate": 2.6954006080219674e-05,
571
+ "loss": 0.1372,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 8.38,
576
+ "learning_rate": 2.6708835932136905e-05,
577
+ "loss": 0.1437,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 8.47,
582
+ "learning_rate": 2.6463665784054136e-05,
583
+ "loss": 0.1447,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 8.56,
588
+ "learning_rate": 2.6218495635971364e-05,
589
+ "loss": 0.1417,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 8.65,
594
+ "learning_rate": 2.5973325487888595e-05,
595
+ "loss": 0.1483,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 8.74,
600
+ "learning_rate": 2.5728155339805826e-05,
601
+ "loss": 0.1392,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 8.83,
606
+ "learning_rate": 2.5482985191723057e-05,
607
+ "loss": 0.1479,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 8.91,
612
+ "learning_rate": 2.5237815043640288e-05,
613
+ "loss": 0.1509,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 9.0,
618
+ "learning_rate": 2.499264489555752e-05,
619
+ "loss": 0.1498,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 9.09,
624
+ "learning_rate": 2.474747474747475e-05,
625
+ "loss": 0.1,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 9.18,
630
+ "learning_rate": 2.4502304599391977e-05,
631
+ "loss": 0.1103,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 9.27,
636
+ "learning_rate": 2.4257134451309212e-05,
637
+ "loss": 0.1057,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 9.36,
642
+ "learning_rate": 2.401196430322644e-05,
643
+ "loss": 0.1201,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 9.44,
648
+ "learning_rate": 2.376679415514367e-05,
649
+ "loss": 0.122,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 9.53,
654
+ "learning_rate": 2.35216240070609e-05,
655
+ "loss": 0.1172,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 9.62,
660
+ "learning_rate": 2.3276453858978132e-05,
661
+ "loss": 0.1173,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 9.71,
666
+ "learning_rate": 2.3031283710895363e-05,
667
+ "loss": 0.1149,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 9.8,
672
+ "learning_rate": 2.2786113562812594e-05,
673
+ "loss": 0.125,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 9.89,
678
+ "learning_rate": 2.2540943414729822e-05,
679
+ "loss": 0.1214,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 9.97,
684
+ "learning_rate": 2.2295773266647056e-05,
685
+ "loss": 0.1233,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 10.06,
690
+ "learning_rate": 2.2050603118564284e-05,
691
+ "loss": 0.0946,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 10.15,
696
+ "learning_rate": 2.1805432970481515e-05,
697
+ "loss": 0.0892,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 10.24,
702
+ "learning_rate": 2.1560262822398746e-05,
703
+ "loss": 0.0911,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 10.33,
708
+ "learning_rate": 2.1315092674315977e-05,
709
+ "loss": 0.0912,
710
+ "step": 58500
711
+ },
712
+ {
713
+ "epoch": 10.41,
714
+ "learning_rate": 2.1069922526233208e-05,
715
+ "loss": 0.0917,
716
+ "step": 59000
717
+ },
718
+ {
719
+ "epoch": 10.5,
720
+ "learning_rate": 2.0824752378150436e-05,
721
+ "loss": 0.0957,
722
+ "step": 59500
723
+ },
724
+ {
725
+ "epoch": 10.59,
726
+ "learning_rate": 2.0579582230067666e-05,
727
+ "loss": 0.0992,
728
+ "step": 60000
729
+ },
730
+ {
731
+ "epoch": 10.68,
732
+ "learning_rate": 2.03344120819849e-05,
733
+ "loss": 0.0973,
734
+ "step": 60500
735
+ },
736
+ {
737
+ "epoch": 10.77,
738
+ "learning_rate": 2.008924193390213e-05,
739
+ "loss": 0.1042,
740
+ "step": 61000
741
+ },
742
+ {
743
+ "epoch": 10.86,
744
+ "learning_rate": 1.984407178581936e-05,
745
+ "loss": 0.1027,
746
+ "step": 61500
747
+ },
748
+ {
749
+ "epoch": 10.94,
750
+ "learning_rate": 1.959890163773659e-05,
751
+ "loss": 0.1047,
752
+ "step": 62000
753
+ },
754
+ {
755
+ "epoch": 11.03,
756
+ "learning_rate": 1.935373148965382e-05,
757
+ "loss": 0.088,
758
+ "step": 62500
759
+ },
760
+ {
761
+ "epoch": 11.12,
762
+ "learning_rate": 1.9108561341571052e-05,
763
+ "loss": 0.0695,
764
+ "step": 63000
765
+ },
766
+ {
767
+ "epoch": 11.21,
768
+ "learning_rate": 1.886339119348828e-05,
769
+ "loss": 0.0733,
770
+ "step": 63500
771
+ },
772
+ {
773
+ "epoch": 11.3,
774
+ "learning_rate": 1.861822104540551e-05,
775
+ "loss": 0.0727,
776
+ "step": 64000
777
+ },
778
+ {
779
+ "epoch": 11.39,
780
+ "learning_rate": 1.8373050897322745e-05,
781
+ "loss": 0.0784,
782
+ "step": 64500
783
+ },
784
+ {
785
+ "epoch": 11.47,
786
+ "learning_rate": 1.8127880749239973e-05,
787
+ "loss": 0.076,
788
+ "step": 65000
789
+ },
790
+ {
791
+ "epoch": 11.56,
792
+ "learning_rate": 1.7882710601157204e-05,
793
+ "loss": 0.0814,
794
+ "step": 65500
795
+ },
796
+ {
797
+ "epoch": 11.65,
798
+ "learning_rate": 1.763754045307443e-05,
799
+ "loss": 0.0816,
800
+ "step": 66000
801
+ },
802
+ {
803
+ "epoch": 11.74,
804
+ "learning_rate": 1.7392370304991666e-05,
805
+ "loss": 0.0848,
806
+ "step": 66500
807
+ },
808
+ {
809
+ "epoch": 11.83,
810
+ "learning_rate": 1.7147200156908897e-05,
811
+ "loss": 0.0827,
812
+ "step": 67000
813
+ },
814
+ {
815
+ "epoch": 11.92,
816
+ "learning_rate": 1.6902030008826124e-05,
817
+ "loss": 0.0839,
818
+ "step": 67500
819
+ },
820
+ {
821
+ "epoch": 12.0,
822
+ "learning_rate": 1.6656859860743355e-05,
823
+ "loss": 0.0808,
824
+ "step": 68000
825
+ },
826
+ {
827
+ "epoch": 12.09,
828
+ "learning_rate": 1.641168971266059e-05,
829
+ "loss": 0.0545,
830
+ "step": 68500
831
+ },
832
+ {
833
+ "epoch": 12.18,
834
+ "learning_rate": 1.6166519564577817e-05,
835
+ "loss": 0.0593,
836
+ "step": 69000
837
+ },
838
+ {
839
+ "epoch": 12.27,
840
+ "learning_rate": 1.592134941649505e-05,
841
+ "loss": 0.0626,
842
+ "step": 69500
843
+ },
844
+ {
845
+ "epoch": 12.36,
846
+ "learning_rate": 1.5676179268412276e-05,
847
+ "loss": 0.0633,
848
+ "step": 70000
849
+ },
850
+ {
851
+ "epoch": 12.44,
852
+ "learning_rate": 1.543100912032951e-05,
853
+ "loss": 0.0673,
854
+ "step": 70500
855
+ },
856
+ {
857
+ "epoch": 12.53,
858
+ "learning_rate": 1.5185838972246741e-05,
859
+ "loss": 0.0661,
860
+ "step": 71000
861
+ },
862
+ {
863
+ "epoch": 12.62,
864
+ "learning_rate": 1.4940668824163969e-05,
865
+ "loss": 0.067,
866
+ "step": 71500
867
+ },
868
+ {
869
+ "epoch": 12.71,
870
+ "learning_rate": 1.4695498676081202e-05,
871
+ "loss": 0.0691,
872
+ "step": 72000
873
+ },
874
+ {
875
+ "epoch": 12.8,
876
+ "learning_rate": 1.4450328527998433e-05,
877
+ "loss": 0.0674,
878
+ "step": 72500
879
+ },
880
+ {
881
+ "epoch": 12.89,
882
+ "learning_rate": 1.4205158379915662e-05,
883
+ "loss": 0.067,
884
+ "step": 73000
885
+ }
886
+ ],
887
+ "max_steps": 101970,
888
+ "num_train_epochs": 18,
889
+ "total_flos": 1.2452822711842406e+17,
890
+ "trial_name": null,
891
+ "trial_params": null
892
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f88ee5c98b2a325c531a69bab2d8aa1905563a7a3f6d4e44ad57a59e6a4236b8
3
+ size 2479
vocab.txt ADDED
The diff for this file is too large to render. See raw diff