End of training

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+license: cc-by-sa-4.0
+base_model: cl-tohoku/bert-base-japanese-whole-word-masking
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: test_trainer
+  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. -->
+
+# test_trainer
+
+This model is a fine-tuned version of [cl-tohoku/bert-base-japanese-whole-word-masking](https://huggingface.co/cl-tohoku/bert-base-japanese-whole-word-masking) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2071
+- Accuracy: 0.7405
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| No log        | 0.0935 | 200  | 0.2734          | 0.5675   |
+| No log        | 0.1871 | 400  | 0.2632          | 0.5931   |
+| 0.3013        | 0.2806 | 600  | 0.2381          | 0.6531   |
+| 0.3013        | 0.3742 | 800  | 0.2324          | 0.6814   |
+| 0.2601        | 0.4677 | 1000 | 0.2241          | 0.7087   |
+| 0.2601        | 0.5613 | 1200 | 0.2163          | 0.7229   |
+| 0.2601        | 0.6548 | 1400 | 0.2173          | 0.7299   |
+| 0.2511        | 0.7484 | 1600 | 0.2115          | 0.7343   |
+| 0.2511        | 0.8419 | 1800 | 0.2073          | 0.7387   |
+| 0.2369        | 0.9355 | 2000 | 0.2071          | 0.7405   |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "cl-tohoku/bert-base-japanese-whole-word-masking",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "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": "multi_label_classification",
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e993dfaa86c27416208e1801a37d335df99cd4785e1e5d9fcb50ce811d56e3
+size 442517520

runs/Jan08_08-49-05_0c1f9937a000/events.out.tfevents.1736326148.0c1f9937a000.1321.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb115470f89de626665ddf713cd5fb3c834f3d4376c948da0210be5053e9fb85
+size 9849

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 200,
+  "global_step": 2138,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09354536950420954,
+      "eval_accuracy": 0.5675198587819947,
+      "eval_loss": 0.2734091877937317,
+      "eval_runtime": 34.6483,
+      "eval_samples_per_second": 32.7,
+      "eval_steps_per_second": 4.098,
+      "step": 200
+    },
+    {
+      "epoch": 0.18709073900841908,
+      "eval_accuracy": 0.5931156222418358,
+      "eval_loss": 0.26319071650505066,
+      "eval_runtime": 34.4168,
+      "eval_samples_per_second": 32.92,
+      "eval_steps_per_second": 4.126,
+      "step": 400
+    },
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 1.4175031185150146,
+      "learning_rate": 3.8306828811973814e-05,
+      "loss": 0.3013,
+      "step": 500
+    },
+    {
+      "epoch": 0.2806361085126286,
+      "eval_accuracy": 0.6531332744924978,
+      "eval_loss": 0.23808303475379944,
+      "eval_runtime": 34.3229,
+      "eval_samples_per_second": 33.01,
+      "eval_steps_per_second": 4.137,
+      "step": 600
+    },
+    {
+      "epoch": 0.37418147801683815,
+      "eval_accuracy": 0.6813768755516328,
+      "eval_loss": 0.23240724205970764,
+      "eval_runtime": 34.4109,
+      "eval_samples_per_second": 32.926,
+      "eval_steps_per_second": 4.127,
+      "step": 800
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 1.147978663444519,
+      "learning_rate": 2.6613657623947615e-05,
+      "loss": 0.2601,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "eval_accuracy": 0.7087378640776699,
+      "eval_loss": 0.22413863241672516,
+      "eval_runtime": 34.4403,
+      "eval_samples_per_second": 32.898,
+      "eval_steps_per_second": 4.123,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5612722170252572,
+      "eval_accuracy": 0.7228596646072374,
+      "eval_loss": 0.21633104979991913,
+      "eval_runtime": 34.4165,
+      "eval_samples_per_second": 32.92,
+      "eval_steps_per_second": 4.126,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6548175865294668,
+      "eval_accuracy": 0.7299205648720212,
+      "eval_loss": 0.2173129767179489,
+      "eval_runtime": 34.4021,
+      "eval_samples_per_second": 32.934,
+      "eval_steps_per_second": 4.128,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 1.139875054359436,
+      "learning_rate": 1.492048643592142e-05,
+      "loss": 0.2511,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7483629560336763,
+      "eval_accuracy": 0.7343336275375111,
+      "eval_loss": 0.21151894330978394,
+      "eval_runtime": 34.2231,
+      "eval_samples_per_second": 33.106,
+      "eval_steps_per_second": 4.149,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8419083255378859,
+      "eval_accuracy": 0.7387466902030009,
+      "eval_loss": 0.20728972554206848,
+      "eval_runtime": 34.4015,
+      "eval_samples_per_second": 32.935,
+      "eval_steps_per_second": 4.128,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 1.2337602376937866,
+      "learning_rate": 3.2273152478952295e-06,
+      "loss": 0.2369,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "eval_accuracy": 0.7405119152691968,
+      "eval_loss": 0.2070828378200531,
+      "eval_runtime": 34.3972,
+      "eval_samples_per_second": 32.939,
+      "eval_steps_per_second": 4.128,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "step": 2138,
+      "total_flos": 4500493926531072.0,
+      "train_loss": 0.2609621320961791,
+      "train_runtime": 2347.8803,
+      "train_samples_per_second": 7.285,
+      "train_steps_per_second": 0.911
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4500493926531072.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c941c5b0b631cddcd303800e3f24afa1795da14dfc232e9d5092a526e2362094
+size 5304