First commit

README.md

@@ -0,0 +1,48 @@
+---
+license: cc-by-sa-4.0
+tags:
+  - generated_from_trainer
+model-index:
+  - name: bert-finetuned-japanese-sentiment
+    results: []
+---
+  
+# bert-finetuned-japanese-sentiment
+
+This model is a fine-tuned version of [cl-tohoku/bert-base-japanese-v2](https://huggingface.co/cl-tohoku/bert-base-japanese-v2) on product amazon reviews japanese dataset.
+
+## Model description
+
+Model Train for amazon reviews Japanese sentence sentiments.
+
+Sentiment analysis is a common task in natural language processing. It consists of classifying the polarity of a given text at the sentence or document level. For instance, the sentence "The food is good" has a positive sentiment, while the sentence "The food is bad" has a negative sentiment.
+
+In this model, we fine-tuned a BERT model on a Japanese sentiment analysis dataset. The dataset contains 20,000 sentences extracted from Amazon reviews. Each sentence is labeled as positive, neutral, or negative. The model was trained for 5 epochs with a batch size of 16.
+
+## Training and evaluation data
+
+- Epochs: 6
+- Training Loss: 0.087600
+- Validation Loss: 1.028876
+- Accuracy: 0.813202
+- Precision: 0.712440
+- Recall: 0.756031
+- F1: 0.728455
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Framework versions
+
+- Transformers 4.27.4
+- Pytorch 2.0.0+cu118
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "./bert-finetuned-japanese-sentiment/checkpoint-4404",
+  "architectures": ["BertForSequenceClassification"],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32768
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf042046750453f140b5317bf6cb23075a07921517ac501e811b48a48dacc816
+size 889793669

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad0b66493a21d1441c1787401e5a9e7a79c72146b74fbf08b3f545bbc4c9e5f
+size 444910709

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e69b56de0287f4d88be75fca668f1b029d445f3b42118020e7d9ee96ec2378a
+size 14511

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c322d2567b6c72aeeb0cb69573b15e2f3f59cbef5d004b969261a3432d18cb
+size 627

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 +1,21 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "do_subword_tokenize": true,
+  "do_word_tokenize": true,
+  "jumanpp_kwargs": null,
+  "mask_token": "[MASK]",
+  "mecab_kwargs": {
+    "mecab_dic": "unidic_lite"
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "subword_tokenizer_type": "wordpiece",
+  "sudachi_kwargs": null,
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "unk_token": "[UNK]",
+  "word_tokenizer_type": "mecab"
+}

trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.5450584888458252,
+  "best_model_checkpoint": "bert-finetuned-japanese-sentiment/checkpoint-474",
+  "epoch": 6.0,
+  "global_step": 2844,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8157940210817349,
+      "eval_f1": 0.7272032479349645,
+      "eval_loss": 0.5450584888458252,
+      "eval_precision": 0.7101173006557553,
+      "eval_recall": 0.7530568561281469,
+      "eval_runtime": 84.5162,
+      "eval_samples_per_second": 68.472,
+      "eval_steps_per_second": 2.142,
+      "step": 474
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.789029535864979e-05,
+      "loss": 0.3251,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8261620874373596,
+      "eval_f1": 0.7413523368662124,
+      "eval_loss": 0.5779568552970886,
+      "eval_precision": 0.7270594811474224,
+      "eval_recall": 0.7636775589314819,
+      "eval_runtime": 84.8717,
+      "eval_samples_per_second": 68.185,
+      "eval_steps_per_second": 2.133,
+      "step": 948
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.578059071729958e-05,
+      "loss": 0.2209,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8156212199758078,
+      "eval_f1": 0.7283195708625394,
+      "eval_loss": 0.6474512219429016,
+      "eval_precision": 0.7140241339852836,
+      "eval_recall": 0.7508970192749587,
+      "eval_runtime": 84.4623,
+      "eval_samples_per_second": 68.516,
+      "eval_steps_per_second": 2.143,
+      "step": 1422
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 1.3670886075949368e-05,
+      "loss": 0.1636,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8107827890098497,
+      "eval_f1": 0.7287062118529598,
+      "eval_loss": 0.8141492605209351,
+      "eval_precision": 0.7155878847825652,
+      "eval_recall": 0.7576050434353393,
+      "eval_runtime": 84.7752,
+      "eval_samples_per_second": 68.263,
+      "eval_steps_per_second": 2.135,
+      "step": 1896
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 1.1561181434599158e-05,
+      "loss": 0.114,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8123379989631934,
+      "eval_f1": 0.7293509360093955,
+      "eval_loss": 0.9643709063529968,
+      "eval_precision": 0.7212611749404146,
+      "eval_recall": 0.7546179503626446,
+      "eval_runtime": 84.2684,
+      "eval_samples_per_second": 68.673,
+      "eval_steps_per_second": 2.148,
+      "step": 2370
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 9.451476793248946e-06,
+      "loss": 0.0876,
+      "step": 2500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8132020044928288,
+      "eval_f1": 0.7284553808496855,
+      "eval_loss": 1.028875708580017,
+      "eval_precision": 0.7124400203988301,
+      "eval_recall": 0.7560308594078071,
+      "eval_runtime": 84.9239,
+      "eval_samples_per_second": 68.143,
+      "eval_steps_per_second": 2.131,
+      "step": 2844
+    }
+  ],
+  "max_steps": 4740,
+  "num_train_epochs": 10,
+  "total_flos": 1.074326001547428e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f3068e345d163d29e1041105fe8f5d676c41a1ede098f9b1074d73330e4cf25
+size 3707