pintaro/bert-base-japanese-v3-output-jcommonsenseqa

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: cl-tohoku/bert-base-japanese-v3
+tags:
+- generated_from_trainer
+datasets:
+- jglue
+metrics:
+- accuracy
+model-index:
+- name: output_jcommonsenseqa
+  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. -->
+
+# output_jcommonsenseqa
+
+This model is a fine-tuned version of [cl-tohoku/bert-base-japanese-v3](https://huggingface.co/cl-tohoku/bert-base-japanese-v3) on the jglue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5267
+- Accuracy: 0.8302
+
+## 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: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.231         | 1.0   | 280  | 0.5796          | 0.8239   |
+| 0.3484        | 2.0   | 560  | 0.4979          | 0.8239   |
+| 0.2421        | 3.0   | 840  | 0.5267          | 0.8302   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "cl-tohoku/bert-base-japanese-v3",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32768
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a929dcfd85fa09fcdf2d53acbe5a92c26fbbcbada5818ca24bffdb498e8ca4
+size 444855292

runs/Dec05_12-25-02_171b8fafe8e6/events.out.tfevents.1701779354.171b8fafe8e6.255.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8daa69a8769445594baa0a6a63ae4dfb97ec3045bd5522ff62e5db473c077ab
+size 4591

runs/Dec05_12-35-56_171b8fafe8e6/events.out.tfevents.1701779762.171b8fafe8e6.255.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2452de45ee6f8c799c27f365f8f03035b33e1ebf94e0d3632546bae1d74ccda8
+size 4591

runs/Dec05_12-35-56_171b8fafe8e6/events.out.tfevents.1701780105.171b8fafe8e6.255.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba06be523983120693219b67eb9df96bb47910b6f01e2a0d5e2b333ed851703b
+size 6228

runs/Dec05_12-35-56_171b8fafe8e6/events.out.tfevents.1701780491.171b8fafe8e6.255.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9229aaf3b801416c9a02a828dabb3745170361176c9dbeeabe0aa6b51fae4ef3
+size 411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d6092649e7b8defcf4376bd99d7470d8ad6efa0f597879e58fd44cfa252afb
+size 4600