Upload 9 files
Browse files- config.json +185 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +76 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"EncoderDecoderModel"
|
4 |
+
],
|
5 |
+
"decoder": {
|
6 |
+
"_name_or_path": "indobenchmark/indobert-base-p1",
|
7 |
+
"_num_labels": 5,
|
8 |
+
"add_cross_attention": true,
|
9 |
+
"architectures": [
|
10 |
+
"BertModel"
|
11 |
+
],
|
12 |
+
"attention_probs_dropout_prob": 0.1,
|
13 |
+
"bad_words_ids": null,
|
14 |
+
"bos_token_id": null,
|
15 |
+
"chunk_size_feed_forward": 0,
|
16 |
+
"decoder_start_token_id": null,
|
17 |
+
"directionality": "bidi",
|
18 |
+
"diversity_penalty": 0.0,
|
19 |
+
"do_sample": false,
|
20 |
+
"early_stopping": false,
|
21 |
+
"eos_token_id": null,
|
22 |
+
"finetuning_task": null,
|
23 |
+
"gradient_checkpointing": false,
|
24 |
+
"hidden_act": "gelu",
|
25 |
+
"hidden_dropout_prob": 0.1,
|
26 |
+
"hidden_size": 768,
|
27 |
+
"id2label": {
|
28 |
+
"0": "LABEL_0",
|
29 |
+
"1": "LABEL_1",
|
30 |
+
"2": "LABEL_2",
|
31 |
+
"3": "LABEL_3",
|
32 |
+
"4": "LABEL_4"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"intermediate_size": 3072,
|
36 |
+
"is_decoder": true,
|
37 |
+
"is_encoder_decoder": false,
|
38 |
+
"label2id": {
|
39 |
+
"LABEL_0": 0,
|
40 |
+
"LABEL_1": 1,
|
41 |
+
"LABEL_2": 2,
|
42 |
+
"LABEL_3": 3,
|
43 |
+
"LABEL_4": 4
|
44 |
+
},
|
45 |
+
"layer_norm_eps": 1e-12,
|
46 |
+
"length_penalty": 1.0,
|
47 |
+
"max_length": 20,
|
48 |
+
"max_position_embeddings": 512,
|
49 |
+
"min_length": 0,
|
50 |
+
"model_type": "bert",
|
51 |
+
"no_repeat_ngram_size": 0,
|
52 |
+
"num_attention_heads": 12,
|
53 |
+
"num_beam_groups": 1,
|
54 |
+
"num_beams": 1,
|
55 |
+
"num_hidden_layers": 12,
|
56 |
+
"num_return_sequences": 1,
|
57 |
+
"output_attentions": false,
|
58 |
+
"output_hidden_states": false,
|
59 |
+
"output_past": true,
|
60 |
+
"output_scores": false,
|
61 |
+
"pad_token_id": 0,
|
62 |
+
"pooler_fc_size": 768,
|
63 |
+
"pooler_num_attention_heads": 12,
|
64 |
+
"pooler_num_fc_layers": 3,
|
65 |
+
"pooler_size_per_head": 128,
|
66 |
+
"pooler_type": "first_token_transform",
|
67 |
+
"position_embedding_type": "absolute",
|
68 |
+
"prefix": null,
|
69 |
+
"pruned_heads": {},
|
70 |
+
"repetition_penalty": 1.0,
|
71 |
+
"return_dict": true,
|
72 |
+
"return_dict_in_generate": false,
|
73 |
+
"sep_token_id": null,
|
74 |
+
"task_specific_params": null,
|
75 |
+
"temperature": 1.0,
|
76 |
+
"tie_encoder_decoder": false,
|
77 |
+
"tie_word_embeddings": true,
|
78 |
+
"tokenizer_class": null,
|
79 |
+
"top_k": 50,
|
80 |
+
"top_p": 1.0,
|
81 |
+
"torchscript": false,
|
82 |
+
"transformers_version": "4.2.1",
|
83 |
+
"type_vocab_size": 2,
|
84 |
+
"use_bfloat16": false,
|
85 |
+
"use_cache": true,
|
86 |
+
"vocab_size": 50000,
|
87 |
+
"xla_device": null
|
88 |
+
},
|
89 |
+
"decoder_start_token_id": 2,
|
90 |
+
"early_stopping": true,
|
91 |
+
"encoder": {
|
92 |
+
"_name_or_path": "indobenchmark/indobert-base-p1",
|
93 |
+
"_num_labels": 5,
|
94 |
+
"add_cross_attention": false,
|
95 |
+
"architectures": [
|
96 |
+
"BertModel"
|
97 |
+
],
|
98 |
+
"attention_probs_dropout_prob": 0.1,
|
99 |
+
"bad_words_ids": null,
|
100 |
+
"bos_token_id": null,
|
101 |
+
"chunk_size_feed_forward": 0,
|
102 |
+
"decoder_start_token_id": null,
|
103 |
+
"directionality": "bidi",
|
104 |
+
"diversity_penalty": 0.0,
|
105 |
+
"do_sample": false,
|
106 |
+
"early_stopping": false,
|
107 |
+
"eos_token_id": null,
|
108 |
+
"finetuning_task": null,
|
109 |
+
"gradient_checkpointing": false,
|
110 |
+
"hidden_act": "gelu",
|
111 |
+
"hidden_dropout_prob": 0.1,
|
112 |
+
"hidden_size": 768,
|
113 |
+
"id2label": {
|
114 |
+
"0": "LABEL_0",
|
115 |
+
"1": "LABEL_1",
|
116 |
+
"2": "LABEL_2",
|
117 |
+
"3": "LABEL_3",
|
118 |
+
"4": "LABEL_4"
|
119 |
+
},
|
120 |
+
"initializer_range": 0.02,
|
121 |
+
"intermediate_size": 3072,
|
122 |
+
"is_decoder": false,
|
123 |
+
"is_encoder_decoder": false,
|
124 |
+
"label2id": {
|
125 |
+
"LABEL_0": 0,
|
126 |
+
"LABEL_1": 1,
|
127 |
+
"LABEL_2": 2,
|
128 |
+
"LABEL_3": 3,
|
129 |
+
"LABEL_4": 4
|
130 |
+
},
|
131 |
+
"layer_norm_eps": 1e-12,
|
132 |
+
"length_penalty": 1.0,
|
133 |
+
"max_length": 20,
|
134 |
+
"max_position_embeddings": 512,
|
135 |
+
"min_length": 0,
|
136 |
+
"model_type": "bert",
|
137 |
+
"no_repeat_ngram_size": 0,
|
138 |
+
"num_attention_heads": 12,
|
139 |
+
"num_beam_groups": 1,
|
140 |
+
"num_beams": 1,
|
141 |
+
"num_hidden_layers": 12,
|
142 |
+
"num_return_sequences": 1,
|
143 |
+
"output_attentions": false,
|
144 |
+
"output_hidden_states": false,
|
145 |
+
"output_past": true,
|
146 |
+
"output_scores": false,
|
147 |
+
"pad_token_id": 0,
|
148 |
+
"pooler_fc_size": 768,
|
149 |
+
"pooler_num_attention_heads": 12,
|
150 |
+
"pooler_num_fc_layers": 3,
|
151 |
+
"pooler_size_per_head": 128,
|
152 |
+
"pooler_type": "first_token_transform",
|
153 |
+
"position_embedding_type": "absolute",
|
154 |
+
"prefix": null,
|
155 |
+
"pruned_heads": {},
|
156 |
+
"repetition_penalty": 1.0,
|
157 |
+
"return_dict": true,
|
158 |
+
"return_dict_in_generate": false,
|
159 |
+
"sep_token_id": null,
|
160 |
+
"task_specific_params": null,
|
161 |
+
"temperature": 1.0,
|
162 |
+
"tie_encoder_decoder": false,
|
163 |
+
"tie_word_embeddings": true,
|
164 |
+
"tokenizer_class": null,
|
165 |
+
"top_k": 50,
|
166 |
+
"top_p": 1.0,
|
167 |
+
"torchscript": false,
|
168 |
+
"transformers_version": "4.2.1",
|
169 |
+
"type_vocab_size": 2,
|
170 |
+
"use_bfloat16": false,
|
171 |
+
"use_cache": true,
|
172 |
+
"vocab_size": 50000,
|
173 |
+
"xla_device": null
|
174 |
+
},
|
175 |
+
"eos_token_id": 3,
|
176 |
+
"is_encoder_decoder": true,
|
177 |
+
"length_penalty": 2.0,
|
178 |
+
"max_length": 80,
|
179 |
+
"min_length": 3,
|
180 |
+
"model_type": "encoder-decoder",
|
181 |
+
"no_repeat_ngram_size": 3,
|
182 |
+
"num_beams": 8,
|
183 |
+
"pad_token_id": 0,
|
184 |
+
"vocab_size": 50000
|
185 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b23940db6d680ceb775a453beec3fa2d36578950efa1d3bd891f3f73c3653f0a
|
3 |
+
size 2213989099
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9faaa85f6b070ba172aeb043e21210ef0858ed204230a0686060043de01710b1
|
3 |
+
size 1109433529
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:270fefd369092a06397feb399766ee1f6488339bfc213573fcfc63cb832a2528
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "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": true, "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": null, "special_tokens_map_file": "/home/.cache/huggingface/transformers/b515a756d9ddf12a7a391ea596c488ac805f0576790934e590ce250a3e4ff056.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "indobenchmark/indobert-base-p1"}
|
trainer_state.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 62.5,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 6.25,
|
12 |
+
"learning_rate": 4.647887323943662e-05,
|
13 |
+
"loss": 6.5392,
|
14 |
+
"step": 50
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 12.5,
|
18 |
+
"learning_rate": 4.144869215291751e-05,
|
19 |
+
"loss": 4.3144,
|
20 |
+
"step": 100
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 18.75,
|
24 |
+
"learning_rate": 3.641851106639839e-05,
|
25 |
+
"loss": 3.1382,
|
26 |
+
"step": 150
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 25.0,
|
30 |
+
"learning_rate": 3.1388329979879276e-05,
|
31 |
+
"loss": 2.4028,
|
32 |
+
"step": 200
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 31.25,
|
36 |
+
"learning_rate": 2.6358148893360163e-05,
|
37 |
+
"loss": 1.856,
|
38 |
+
"step": 250
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 37.5,
|
42 |
+
"learning_rate": 2.1327967806841047e-05,
|
43 |
+
"loss": 1.4456,
|
44 |
+
"step": 300
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 43.75,
|
48 |
+
"learning_rate": 1.6297786720321935e-05,
|
49 |
+
"loss": 1.1454,
|
50 |
+
"step": 350
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 50.0,
|
54 |
+
"learning_rate": 1.1267605633802817e-05,
|
55 |
+
"loss": 0.935,
|
56 |
+
"step": 400
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 56.25,
|
60 |
+
"learning_rate": 6.237424547283703e-06,
|
61 |
+
"loss": 0.7969,
|
62 |
+
"step": 450
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 62.5,
|
66 |
+
"learning_rate": 1.2072434607645876e-06,
|
67 |
+
"loss": 0.721,
|
68 |
+
"step": 500
|
69 |
+
}
|
70 |
+
],
|
71 |
+
"max_steps": 512,
|
72 |
+
"num_train_epochs": 64,
|
73 |
+
"total_flos": 14782480903421952,
|
74 |
+
"trial_name": null,
|
75 |
+
"trial_params": null
|
76 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:634ff2b9e1ec912f965993898403d46551a77af1813c61d7c3d7559215212f95
|
3 |
+
size 2107
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|