trtd56/practical_nlp_course_4

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: line-corporation/line-distilbert-base-japanese
+tags:
+- generated_from_trainer
+model-index:
+- name: my_aio_model
+  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. -->
+
+# my_aio_model
+
+This model is a fine-tuned version of [line-corporation/line-distilbert-base-japanese](https://huggingface.co/line-corporation/line-distilbert-base-japanese) on the None dataset.
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 500
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "line-corporation/line-distilbert-base-japanese",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForMultipleChoice"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_hidden_states": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 32768
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20576269a6d39f4b523dbdf203f126457b71ea435d0326ea54f5172dddf7c932
+size 274729204

runs/Feb09_01-29-44_de106f0f94ca/events.out.tfevents.1707442184.de106f0f94ca.1001.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7791d2c04e3651612395acda23caf36f07263d0f048951c29a48750bf814d9
+size 6408

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfafc8c0662d9c8f39621a64c74260f2ad120310c8dd24886de2dddaf599b4e
+size 439391

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "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": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "line-corporation/line-distilbert-base-japanese--distilbert_japanese_tokenizer.DistilBertJapaneseTokenizer",
+      null
+    ]
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "do_subword_tokenize": true,
+  "do_word_tokenize": true,
+  "eos_token": "[SEP]",
+  "jumanpp_kwargs": null,
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "mecab_kwargs": {
+    "mecab_dic": "unidic_lite"
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "subword_tokenizer_type": "sentencepiece",
+  "sudachi_kwargs": null,
+  "tokenize_chinese_chars": false,
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "unk_token": "<unk>",
+  "word_tokenizer_type": "mecab"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b2db9adc83abe63aae89eeb37e60dabbe04520551b82f901034ec9d5012175
+size 4600