test

bert-base-chinese-finetuning/README.md

@@ -0,0 +1,76 @@
+---
+language:
+- en
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+- f1
+model-index:
+- name: bert-base-chinese-finetuning
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MRPC
+      type: glue
+      args: mrpc
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7769607843137255
+    - name: F1
+      type: f1
+      value: 0.852988691437803
+---
+
+<!-- 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. -->
+
+# bert-base-chinese-finetuning
+
+This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on the GLUE MRPC dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4815
+- Accuracy: 0.7770
+- F1: 0.8530
+- Combined Score: 0.8150
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 1.12.1+cu102
+- Datasets 2.13.1
+- Tokenizers 0.13.3

bert-base-chinese-finetuning/all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.7769607843137255,
+    "eval_combined_score": 0.8149747378757642,
+    "eval_f1": 0.852988691437803,
+    "eval_loss": 0.48148372769355774,
+    "eval_runtime": 3.9329,
+    "eval_samples": 408,
+    "eval_samples_per_second": 103.74,
+    "eval_steps_per_second": 12.968,
+    "train_loss": 0.5635819445508238,
+    "train_runtime": 126.958,
+    "train_samples": 3668,
+    "train_samples_per_second": 28.891,
+    "train_steps_per_second": 3.615
+}

bert-base-chinese-finetuning/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "bert-base-chinese",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "finetuning_task": "mrpc",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

bert-base-chinese-finetuning/eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.7769607843137255,
+    "eval_combined_score": 0.8149747378757642,
+    "eval_f1": 0.852988691437803,
+    "eval_loss": 0.48148372769355774,
+    "eval_runtime": 3.9329,
+    "eval_samples": 408,
+    "eval_samples_per_second": 103.74,
+    "eval_steps_per_second": 12.968
+}

bert-base-chinese-finetuning/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af62195a69ec9c04f6b1856b5d494e372276c3eb681f6de4302b98e585b2bd6b
+size 409161773

bert-base-chinese-finetuning/special_tokens_map.json

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

bert-base-chinese-finetuning/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-chinese", "tokenizer_class": "BertTokenizer"}

bert-base-chinese-finetuning/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.5635819445508238,
+    "train_runtime": 126.958,
+    "train_samples": 3668,
+    "train_samples_per_second": 28.891,
+    "train_steps_per_second": 3.615
+}

bert-base-chinese-finetuning/trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 459,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 459,
+      "total_flos": 241272837765120.0,
+      "train_loss": 0.5635819445508238,
+      "train_runtime": 126.958,
+      "train_samples_per_second": 28.891,
+      "train_steps_per_second": 3.615
+    }
+  ],
+  "max_steps": 459,
+  "num_train_epochs": 1,
+  "total_flos": 241272837765120.0,
+  "trial_name": null,
+  "trial_params": null
+}

bert-base-chinese-finetuning/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a1444a3e932ea00517c178709712ee776c62bf36a8a01ad5d1f4b21643ddb93
+size 2991