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

README.md

@@ -0,0 +1,71 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- id_liputan6
+model-index:
+- name: bert2bert-extreme-dropout-0.5-lr-5e-05-batchsize-4-encmaxlen-2048-decmaxlen-512
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bert2bert-extreme-dropout-0.5-lr-5e-05-batchsize-4-encmaxlen-2048-decmaxlen-512
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the id_liputan6 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 9.2760
+- R1 Precision: 0.0
+- R1 Recall: 0.0
+- R1 Fmeasure: 0.0
+- R2 Precision: 0.0
+- R2 Recall: 0.0
+- R2 Fmeasure: 0.0
+- Rl Precision: 0.0
+- Rl Recall: 0.0
+- Rl Fmeasure: 0.0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | R1 Precision | R1 Recall | R1 Fmeasure | R2 Precision | R2 Recall | R2 Fmeasure | Rl Precision | Rl Recall | Rl Fmeasure |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:---------:|:-----------:|:------------:|:---------:|:-----------:|:------------:|:---------:|:-----------:|
+| 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         |
+| 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         |
+| 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         |
+| 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         |
+| 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         |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,176 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "indolem/indobert-base-uncased",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.5,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "eos_token_ids": 0,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.5,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 31923
+  },
+  "decoder_start_token_id": 3,
+  "encoder": {
+    "_name_or_path": "indolem/indobert-base-uncased",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.5,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "eos_token_ids": 0,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.5,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 2048,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 31923
+  },
+  "eos_token_id": 4,
+  "is_encoder_decoder": true,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 3,
+  "eos_token_id": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7407492f609bd3bf9f105c2c766f7c8566d14859e5026d067cf60df825b230bc
+size 1002850732

runs/Mar14_05-43-49_2a825b39c9b9/events.out.tfevents.1710395030.2a825b39c9b9.401.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f2b17d052d34acfb8d2cce80285747dfb4a08a72a0421346df90d2ff86d6c81
+size 8934

runs/Mar14_05-45-02_2a825b39c9b9/events.out.tfevents.1710395102.2a825b39c9b9.401.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e0e3a6e528ad6f3c466a4146de652b2d7247031c1afcaea59a4bfd3d03a179
+size 8934

runs/Mar14_05-47-23_2a825b39c9b9/events.out.tfevents.1710395243.2a825b39c9b9.401.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4166cbbe5335eed93ec3d274e68b7de5c4f0fc70f39fe940df305f31cd2a64ea
+size 8935

runs/Mar14_05-47-30_2a825b39c9b9/events.out.tfevents.1710395251.2a825b39c9b9.401.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed060d201516798df16c0abfcdba39a9e6e8fac03b2e13b3da41a88a0029b39
+size 8935

runs/Mar14_06-02-21_2a825b39c9b9/events.out.tfevents.1710396141.2a825b39c9b9.401.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3859d2d65b131f006a81682b14fb134202576284aeb3d0b8c3f791dee01ba9a6
+size 8934

runs/Mar14_06-04-46_2a825b39c9b9/events.out.tfevents.1710396287.2a825b39c9b9.401.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3046fb21dafd4e5188bb7176fb73ac2d6f8bb062ece5b797b676da08398518ef
+size 8934

runs/Mar14_06-06-12_2a825b39c9b9/events.out.tfevents.1710396373.2a825b39c9b9.401.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9185225ef0ec1af99c601101d0dce3024bfdd25bdb2115c3d56e27ee2eba32
+size 8280

runs/Mar14_06-07-07_2a825b39c9b9/events.out.tfevents.1710396428.2a825b39c9b9.401.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b66333802b436f273f642f8e49fb12ca23adfe898c1657828c852d906817c1
+size 8280

runs/Mar14_06-07-35_2a825b39c9b9/events.out.tfevents.1710396456.2a825b39c9b9.401.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058e75cb8a1f7e66a462eb9cb19932b88013de8af820419dea9f35bcc5f7ff3b
+size 8280

runs/Mar14_06-09-44_2a825b39c9b9/events.out.tfevents.1710396584.2a825b39c9b9.11101.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b15a35d6c9075707f42b691312a3c616665a2fd4be04df58764e0903457981
+size 8953

runs/Mar14_06-13-00_2a825b39c9b9/events.out.tfevents.1710396780.2a825b39c9b9.12232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe71bc1cf52f0db20c1ee243bd662adc27836c7468f1eaf47444ae66671afd98
+size 13004

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f7a02174fdb25847e97f989079962080f41caa990769c13b7b41862f9b8f3b
+size 5176