Alfahluzi commited on
Commit
7cc068b
1 Parent(s): 66114a2

initial commit bert2bert-extreme-dropout-0.5-lr-5e-05-batchsize-4-encmaxlen-2048-decmaxlen-512

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - id_liputan6
6
+ model-index:
7
+ - name: bert2bert-extreme-dropout-0.5-lr-5e-05-batchsize-4-encmaxlen-2048-decmaxlen-512
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # bert2bert-extreme-dropout-0.5-lr-5e-05-batchsize-4-encmaxlen-2048-decmaxlen-512
15
+
16
+ This model is a fine-tuned version of [](https://huggingface.co/) on the id_liputan6 dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 9.2760
19
+ - R1 Precision: 0.0
20
+ - R1 Recall: 0.0
21
+ - R1 Fmeasure: 0.0
22
+ - R2 Precision: 0.0
23
+ - R2 Recall: 0.0
24
+ - R2 Fmeasure: 0.0
25
+ - Rl Precision: 0.0
26
+ - Rl Recall: 0.0
27
+ - Rl Fmeasure: 0.0
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 5e-05
47
+ - train_batch_size: 1
48
+ - eval_batch_size: 1
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 5
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | R1 Precision | R1 Recall | R1 Fmeasure | R2 Precision | R2 Recall | R2 Fmeasure | Rl Precision | Rl Recall | Rl Fmeasure |
58
+ |:-------------:|:-----:|:----:|:---------------:|:------------:|:---------:|:-----------:|:------------:|:---------:|:-----------:|:------------:|:---------:|:-----------:|
59
+ | No log | 1.0 | 8 | 9.7200 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
60
+ | No log | 2.0 | 16 | 9.5455 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
61
+ | No log | 3.0 | 24 | 9.3678 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
62
+ | No log | 4.0 | 32 | 9.2887 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
63
+ | No log | 5.0 | 40 | 9.2760 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.38.2
69
+ - Pytorch 2.2.1+cu121
70
+ - Datasets 2.18.0
71
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "indolem/indobert-base-uncased",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.5,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": 0,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "eos_token_ids": 0,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "hidden_act": "gelu",
30
+ "hidden_dropout_prob": 0.5,
31
+ "hidden_size": 768,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "is_decoder": true,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 512,
48
+ "min_length": 0,
49
+ "model_type": "bert",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_attention_heads": 12,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 12,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_past": true,
59
+ "output_scores": false,
60
+ "pad_token_id": 0,
61
+ "position_embedding_type": "absolute",
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "sep_token_id": null,
70
+ "suppress_tokens": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tf_legacy_loss": false,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": null,
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": null,
80
+ "torchscript": false,
81
+ "type_vocab_size": 2,
82
+ "typical_p": 1.0,
83
+ "use_bfloat16": false,
84
+ "use_cache": true,
85
+ "vocab_size": 31923
86
+ },
87
+ "decoder_start_token_id": 3,
88
+ "encoder": {
89
+ "_name_or_path": "indolem/indobert-base-uncased",
90
+ "add_cross_attention": false,
91
+ "architectures": [
92
+ "BertForMaskedLM"
93
+ ],
94
+ "attention_probs_dropout_prob": 0.5,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": 0,
98
+ "chunk_size_feed_forward": 0,
99
+ "classifier_dropout": null,
100
+ "cross_attention_hidden_size": null,
101
+ "decoder_start_token_id": null,
102
+ "diversity_penalty": 0.0,
103
+ "do_sample": false,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "eos_token_ids": 0,
108
+ "exponential_decay_length_penalty": null,
109
+ "finetuning_task": null,
110
+ "forced_bos_token_id": null,
111
+ "forced_eos_token_id": null,
112
+ "hidden_act": "gelu",
113
+ "hidden_dropout_prob": 0.5,
114
+ "hidden_size": 768,
115
+ "id2label": {
116
+ "0": "LABEL_0",
117
+ "1": "LABEL_1"
118
+ },
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 3072,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "layer_norm_eps": 1e-12,
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "max_position_embeddings": 2048,
131
+ "min_length": 0,
132
+ "model_type": "bert",
133
+ "no_repeat_ngram_size": 0,
134
+ "num_attention_heads": 12,
135
+ "num_beam_groups": 1,
136
+ "num_beams": 1,
137
+ "num_hidden_layers": 12,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_past": true,
142
+ "output_scores": false,
143
+ "pad_token_id": 0,
144
+ "position_embedding_type": "absolute",
145
+ "prefix": null,
146
+ "problem_type": null,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": null,
163
+ "torchscript": false,
164
+ "type_vocab_size": 2,
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false,
167
+ "use_cache": true,
168
+ "vocab_size": 31923
169
+ },
170
+ "eos_token_id": 4,
171
+ "is_encoder_decoder": true,
172
+ "model_type": "encoder-decoder",
173
+ "pad_token_id": 0,
174
+ "torch_dtype": "float32",
175
+ "transformers_version": "4.38.2"
176
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 3,
4
+ "eos_token_id": 4,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7407492f609bd3bf9f105c2c766f7c8566d14859e5026d067cf60df825b230bc
3
+ size 1002850732
runs/Mar14_05-43-49_2a825b39c9b9/events.out.tfevents.1710395030.2a825b39c9b9.401.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2b17d052d34acfb8d2cce80285747dfb4a08a72a0421346df90d2ff86d6c81
3
+ size 8934
runs/Mar14_05-45-02_2a825b39c9b9/events.out.tfevents.1710395102.2a825b39c9b9.401.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e0e3a6e528ad6f3c466a4146de652b2d7247031c1afcaea59a4bfd3d03a179
3
+ size 8934
runs/Mar14_05-47-23_2a825b39c9b9/events.out.tfevents.1710395243.2a825b39c9b9.401.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4166cbbe5335eed93ec3d274e68b7de5c4f0fc70f39fe940df305f31cd2a64ea
3
+ size 8935
runs/Mar14_05-47-30_2a825b39c9b9/events.out.tfevents.1710395251.2a825b39c9b9.401.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed060d201516798df16c0abfcdba39a9e6e8fac03b2e13b3da41a88a0029b39
3
+ size 8935
runs/Mar14_06-02-21_2a825b39c9b9/events.out.tfevents.1710396141.2a825b39c9b9.401.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3859d2d65b131f006a81682b14fb134202576284aeb3d0b8c3f791dee01ba9a6
3
+ size 8934
runs/Mar14_06-04-46_2a825b39c9b9/events.out.tfevents.1710396287.2a825b39c9b9.401.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3046fb21dafd4e5188bb7176fb73ac2d6f8bb062ece5b797b676da08398518ef
3
+ size 8934
runs/Mar14_06-06-12_2a825b39c9b9/events.out.tfevents.1710396373.2a825b39c9b9.401.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd9185225ef0ec1af99c601101d0dce3024bfdd25bdb2115c3d56e27ee2eba32
3
+ size 8280
runs/Mar14_06-07-07_2a825b39c9b9/events.out.tfevents.1710396428.2a825b39c9b9.401.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b66333802b436f273f642f8e49fb12ca23adfe898c1657828c852d906817c1
3
+ size 8280
runs/Mar14_06-07-35_2a825b39c9b9/events.out.tfevents.1710396456.2a825b39c9b9.401.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058e75cb8a1f7e66a462eb9cb19932b88013de8af820419dea9f35bcc5f7ff3b
3
+ size 8280
runs/Mar14_06-09-44_2a825b39c9b9/events.out.tfevents.1710396584.2a825b39c9b9.11101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b15a35d6c9075707f42b691312a3c616665a2fd4be04df58764e0903457981
3
+ size 8953
runs/Mar14_06-13-00_2a825b39c9b9/events.out.tfevents.1710396780.2a825b39c9b9.12232.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe71bc1cf52f0db20c1ee243bd662adc27836c7468f1eaf47444ae66671afd98
3
+ size 13004
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[MASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24f7a02174fdb25847e97f989079962080f41caa990769c13b7b41862f9b8f3b
3
+ size 5176
vocab.txt ADDED
The diff for this file is too large to render. See raw diff