Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+checkpoint-*/
+.ipynb_checkpoints

README.md

@@ -0,0 +1,125 @@
+---
+library_name: transformers
+base_model: bert-base-chinese
+tags:
+- generated_from_trainer
+datasets:
+- cmrc2018
+model-index:
+- name: chinese_qa
+  results: []
+---
+
+# bert-base-chinese-finetuned-cmrc2018
+
+This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on the CMRC2018 (Chinese Machine Reading Comprehension) dataset.
+
+## Model Description
+
+This is a BERT-based extractive question answering model for Chinese text. The model is designed to locate and extract answer spans from given contexts in response to questions.
+
+Key Features:
+- Base Model: bert-base-chinese
+- Task: Extractive Question Answering
+- Language: Chinese
+- Training Dataset: CMRC2018
+
+## Performance Metrics
+
+Evaluation results on the test set:
+- Exact Match: 59.708
+- F1 Score: 60.0723
+- Number of evaluation samples: 6,254
+- Evaluation speed: 283.054 samples/second
+
+## Intended Uses & Limitations
+
+### Intended Uses
+- Chinese reading comprehension tasks
+- Answer extraction from given documents
+- Context-based question answering systems
+
+### Limitations
+- Only supports extractive QA (cannot generate new answers)
+- Answers must be present in the context
+- Does not support multi-hop reasoning
+- Cannot handle unanswerable questions
+
+## Training Details
+
+### Training Hyperparameters
+- Learning rate: 3e-05
+- Train batch size: 12
+- Eval batch size: 8
+- Seed: 42
+- Optimizer: AdamW (betas=(0.9,0.999), epsilon=1e-08)
+- LR scheduler: linear
+- Number of epochs: 5.0
+
+### Training Results
+- Training time: 892.86 seconds
+- Training samples: 18,960
+- Training speed: 106.175 samples/second
+- Training loss: 0.5625
+
+### Framework Versions
+- Transformers: 4.47.0.dev0
+- Pytorch: 2.5.1+cu124
+- Datasets: 3.1.0
+- Tokenizers: 20.3
+
+## Usage
+
+```python
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer
+
+# Load model and tokenizer
+model = AutoModelForQuestionAnswering.from_pretrained("real-jiakai/bert-base-chinese-finetuned-cmrc2018")
+tokenizer = AutoTokenizer.from_pretrained("real-jiakai/bert-base-chinese-finetuned-cmrc2018")
+
+# Prepare inputs
+question = "Your question in Chinese"
+context = "Context text in Chinese"
+
+# Tokenize inputs
+inputs = tokenizer(
+    question,
+    context,
+    return_tensors="pt",
+    max_length=384,
+    truncation=True,
+    return_offsets_mapping=True
+)
+
+# Get answer
+outputs = model(**inputs)
+start_logits = outputs.start_logits
+end_logits = outputs.end_logits
+```
+
+## Citation
+
+If you use this model, please cite the CMRC2018 dataset:
+
+```bibtex
+@inproceedings{cui-emnlp2019-cmrc2018,
+    title = "A Span-Extraction Dataset for {C}hinese Machine Reading Comprehension",
+    author = "Cui, Yiming  and
+      Liu, Ting  and
+      Che, Wanxiang  and
+      Xiao, Li  and
+      Chen, Zhipeng  and
+      Ma, Wentao  and
+      Wang, Shijin  and
+      Hu, Guoping",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
+    month = nov,
+    year = "2019",
+    address = "Hong Kong, China",
+    publisher = "Association for Computational Linguistics",
+    url = "https://www.aclweb.org/anthology/D19-1600",
+    doi = "10.18653/v1/D19-1600",
+    pages = "5886--5891",
+}
+
+```

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_exact_match": 59.70798384591488,
+    "eval_f1": 60.07226438260921,
+    "eval_runtime": 22.0947,
+    "eval_samples": 6254,
+    "eval_samples_per_second": 283.054,
+    "eval_steps_per_second": 35.393,
+    "total_flos": 1.85781994039296e+16,
+    "train_loss": 0.5625110177148747,
+    "train_runtime": 892.8635,
+    "train_samples": 18960,
+    "train_samples_per_second": 106.175,
+    "train_steps_per_second": 8.848
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-chinese",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd8518d93bc9911d4827c78f194a9c50a9b54db76f917f40c4cfd92a7eab4fc
+size 15944496

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_exact_match": 59.70798384591488,
+    "eval_f1": 60.07226438260921,
+    "eval_runtime": 22.0947,
+    "eval_samples": 6254,
+    "eval_samples_per_second": 283.054,
+    "eval_steps_per_second": 35.393
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e90f2d2ba5c13181eaac2f1df4286544f64c846a0715733e34c4818e91d18fe8
+size 406737680

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 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.85781994039296e+16,
+    "train_loss": 0.5625110177148747,
+    "train_runtime": 892.8635,
+    "train_samples": 18960,
+    "train_samples_per_second": 106.175,
+    "train_steps_per_second": 8.848
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 7900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.31645569620253167,
+      "grad_norm": 16.740053176879883,
+      "learning_rate": 2.8101265822784812e-05,
+      "loss": 1.7983,
+      "step": 500
+    },
+    {
+      "epoch": 0.6329113924050633,
+      "grad_norm": 18.301847457885742,
+      "learning_rate": 2.620253164556962e-05,
+      "loss": 1.1858,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9493670886075949,
+      "grad_norm": 19.28789710998535,
+      "learning_rate": 2.430379746835443e-05,
+      "loss": 1.0645,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2658227848101267,
+      "grad_norm": 27.41464614868164,
+      "learning_rate": 2.240506329113924e-05,
+      "loss": 0.7401,
+      "step": 2000
+    },
+    {
+      "epoch": 1.5822784810126582,
+      "grad_norm": 22.102096557617188,
+      "learning_rate": 2.050632911392405e-05,
+      "loss": 0.7248,
+      "step": 2500
+    },
+    {
+      "epoch": 1.8987341772151898,
+      "grad_norm": 29.267433166503906,
+      "learning_rate": 1.860759493670886e-05,
+      "loss": 0.7217,
+      "step": 3000
+    },
+    {
+      "epoch": 2.2151898734177213,
+      "grad_norm": 14.63181209564209,
+      "learning_rate": 1.670886075949367e-05,
+      "loss": 0.4984,
+      "step": 3500
+    },
+    {
+      "epoch": 2.5316455696202533,
+      "grad_norm": 15.814390182495117,
+      "learning_rate": 1.4810126582278482e-05,
+      "loss": 0.4188,
+      "step": 4000
+    },
+    {
+      "epoch": 2.848101265822785,
+      "grad_norm": 14.612494468688965,
+      "learning_rate": 1.2911392405063291e-05,
+      "loss": 0.4127,
+      "step": 4500
+    },
+    {
+      "epoch": 3.1645569620253164,
+      "grad_norm": 39.51222229003906,
+      "learning_rate": 1.1012658227848103e-05,
+      "loss": 0.3182,
+      "step": 5000
+    },
+    {
+      "epoch": 3.481012658227848,
+      "grad_norm": 13.681534767150879,
+      "learning_rate": 9.113924050632912e-06,
+      "loss": 0.2268,
+      "step": 5500
+    },
+    {
+      "epoch": 3.7974683544303796,
+      "grad_norm": 11.261092185974121,
+      "learning_rate": 7.215189873417722e-06,
+      "loss": 0.2346,
+      "step": 6000
+    },
+    {
+      "epoch": 4.113924050632911,
+      "grad_norm": 19.033397674560547,
+      "learning_rate": 5.3164556962025316e-06,
+      "loss": 0.1939,
+      "step": 6500
+    },
+    {
+      "epoch": 4.430379746835443,
+      "grad_norm": 25.222740173339844,
+      "learning_rate": 3.4177215189873417e-06,
+      "loss": 0.1312,
+      "step": 7000
+    },
+    {
+      "epoch": 4.746835443037975,
+      "grad_norm": 19.743125915527344,
+      "learning_rate": 1.518987341772152e-06,
+      "loss": 0.1167,
+      "step": 7500
+    },
+    {
+      "epoch": 5.0,
+      "step": 7900,
+      "total_flos": 1.85781994039296e+16,
+      "train_loss": 0.5625110177148747,
+      "train_runtime": 892.8635,
+      "train_samples_per_second": 106.175,
+      "train_steps_per_second": 8.848
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.85781994039296e+16,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9f3a52d8ffe066ddc8a698d8d91df86a4c62a61449a6d1931eba6071252476
+size 5304