Upload BERT LoRA Shakespeare Q&A model with documentation

README.md

@@ -1,10 +1,48 @@
----
-license: mit
-datasets:
-- Hananguyen12/shakespeare-QA-plays
-language:
-- en
-base_model:
-- google-bert/bert-base-uncased
-pipeline_tag: text-generation
----
+# BERT LoRA Shakespeare Q&A Model
+
+This model is fine-tuned using LoRA (Low-Rank Adaptation) on BERT Base Uncased for Shakespeare question answering.
+
+## Usage
+
+```python
+from transformers import BertTokenizerFast, BertForQuestionAnswering
+from peft import PeftModel
+
+# Load model
+tokenizer = BertTokenizerFast.from_pretrained("bert-base-uncased")
+base_model = BertForQuestionAnswering.from_pretrained("bert-base-uncased")
+model = PeftModel.from_pretrained(base_model, "Hananguyen12/bert-base-uncase-lora-shakespeare-plays")
+
+# Ask questions
+question = "Who is Romeo?"
+context = "Romeo Montague is a young man from the Montague family in Verona..."
+
+inputs = tokenizer(question, context, return_tensors="pt")
+outputs = model(**inputs)
+
+start_idx = outputs.start_logits.argmax()
+end_idx = outputs.end_logits.argmax()
+answer = tokenizer.decode(inputs['input_ids'][0][start_idx:end_idx+1])
+```
+
+## Model Details
+
+- **Base Model**: bert-base-uncased
+- **Fine-tuning**: LoRA adaptation
+- **Domain**: Shakespeare's works
+- **Task**: Extractive Question Answering
+
+## Training Data
+
+Trained on comprehensive Shakespeare Q&A dataset covering:
+- Character analysis
+- Plot understanding  
+- Thematic questions
+- Literary interpretation
+
+## Use Cases
+
+- Educational tools for Shakespeare studies
+- Literature analysis
+- Student homework assistance
+- Digital humanities research

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bert-base-uncased",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "qa_outputs"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense",
+    "value",
+    "key",
+    "query"
+  ],
+  "task_type": "QUESTION_ANS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b16611379ae538eb71018b956197573da92632a59901e16b414323613d112b
+size 10643320

bert_lora_training_report.json

@@ -0,0 +1,112 @@
+{
+  "configuration": {
+    "base_model_name": "bert-base-uncased",
+    "max_length": 512,
+    "batch_size": 4,
+    "gradient_accumulation_steps": 4,
+    "effective_batch_size": 16,
+    "learning_rate": 0.0002,
+    "num_epochs": 4,
+    "warmup_steps": 500,
+    "weight_decay": 0.01,
+    "dataset_path": "/content/shakespeare_training_data.json",
+    "used_all_data": true,
+    "lora_config": {
+      "r": 16,
+      "alpha": 32,
+      "dropout": 0.1,
+      "target_modules": [
+        "query",
+        "key",
+        "value",
+        "dense"
+      ]
+    }
+  },
+  "dataset_statistics": {
+    "total_examples": 6032,
+    "train_examples": 5127,
+    "val_examples": 603,
+    "test_examples": 302,
+    "question_types": {
+      "factual": 4425,
+      "quote": 1520,
+      "analysis": 75,
+      "summary": 12
+    }
+  },
+  "model_statistics": {
+    "base_model": "bert-base-uncased",
+    "total_parameters": 111548932,
+    "trainable_parameters": 2655746,
+    "trainable_percentage": 2.3807901630111528,
+    "parameter_efficiency": "2,655,746 trainable out of 111,548,932 total",
+    "base_model_path": "/content/shakespeare-bert-base-model",
+    "lora_adapter_path": "/content/shakespeare-bert-qa-lora"
+  },
+  "training_statistics": {
+    "start_time": "2025-06-04T19:18:02.140488",
+    "end_time": "2025-06-04T19:30:15.267651",
+    "training_time_seconds": 733.127163,
+    "training_time_formatted": "0:12:13.127163",
+    "final_train_loss": 0.7214135336356,
+    "total_steps": 1284,
+    "epochs_completed": 4,
+    "examples_trained": 5127,
+    "lora_config": {
+      "r": 16,
+      "alpha": 32,
+      "dropout": 0.1,
+      "target_modules": [
+        "query",
+        "key",
+        "value",
+        "dense"
+      ]
+    },
+    "model_config": {
+      "base_model": "bert-base-uncased",
+      "max_length": 512,
+      "effective_batch_size": 16,
+      "learning_rate": 0.0002
+    },
+    "test_evaluation": {
+      "eval_loss": 0.18932627141475677,
+      "eval_exact_match": 0.8609271523178808,
+      "eval_start_accuracy": 1.0,
+      "eval_end_accuracy": 0.8609271523178808,
+      "eval_start_f1": 1.0,
+      "eval_end_f1": 0.8286722954302209,
+      "eval_avg_f1": 0.9143361477151104,
+      "eval_runtime": 3.9174,
+      "eval_samples_per_second": 77.093,
+      "eval_steps_per_second": 19.401,
+      "epoch": 4.0
+    },
+    "validation_evaluation": {
+      "eval_loss": 0.19166630506515503,
+      "eval_exact_match": 0.8590381426202321,
+      "eval_start_accuracy": 1.0,
+      "eval_end_accuracy": 0.8590381426202321,
+      "eval_start_f1": 1.0,
+      "eval_end_f1": 0.8252087537483971,
+      "eval_avg_f1": 0.9126043768741985,
+      "eval_runtime": 7.7871,
+      "eval_samples_per_second": 77.436,
+      "eval_steps_per_second": 19.391,
+      "epoch": 4.0
+    }
+  },
+  "system_information": {
+    "device": "cuda",
+    "cuda_available": true,
+    "gpu_name": "Tesla T4",
+    "gpu_memory_gb": 15.828320256,
+    "pytorch_version": "2.6.0+cu124",
+    "transformers_version": "4.35.0+",
+    "peft_enabled": true
+  },
+  "report_generated": "2025-06-04T19:30:27.650635",
+  "colab_environment": true,
+  "model_type": "BERT-Base-Uncased with LoRA"
+}

checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: bert-base-uncased
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-1000/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bert-base-uncased",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "qa_outputs"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense",
+    "value",
+    "key",
+    "query"
+  ],
+  "task_type": "QUESTION_ANS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b16611379ae538eb71018b956197573da92632a59901e16b414323613d112b
+size 10643320

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5173fd70c71efbe19fccdf09c4928d3e667fb22846aa2eed9c8ada814dd6630a
+size 21368634

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8e133e8e50367b83a4bbfae02188298dfa3084d23e76001194f918eb9638b0
+size 14244

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a5daf94830c53f36991f383d35ebc45e5fc6cca0a3c978fe46396fd326e34f
+size 988

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c3e85129328986e1292064393da1c488da3ec20da9baf79bd436ef2c0981fd
+size 1064

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-1000/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": true,
+  "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]"
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.191666379570961,
+  "best_model_checkpoint": "/content/shakespeare-bert-qa-lora/checkpoint-1000",
+  "epoch": 3.1154446177847115,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.31201248049922,
+      "grad_norm": 6.9100189208984375,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 5.4426,
+      "step": 100
+    },
+    {
+      "epoch": 0.62402496099844,
+      "grad_norm": 2.527374029159546,
+      "learning_rate": 7.920000000000001e-05,
+      "loss": 1.0745,
+      "step": 200
+    },
+    {
+      "epoch": 0.9360374414976599,
+      "grad_norm": 2.013089895248413,
+      "learning_rate": 0.0001192,
+      "loss": 0.4128,
+      "step": 300
+    },
+    {
+      "epoch": 1.2464898595943839,
+      "grad_norm": 1.5375763177871704,
+      "learning_rate": 0.00015920000000000002,
+      "loss": 0.3497,
+      "step": 400
+    },
+    {
+      "epoch": 1.5585023400936038,
+      "grad_norm": 2.152944564819336,
+      "learning_rate": 0.00019920000000000002,
+      "loss": 0.3406,
+      "step": 500
+    },
+    {
+      "epoch": 1.5585023400936038,
+      "eval_avg_f1": 0.9042045713643392,
+      "eval_end_accuracy": 0.7761194029850746,
+      "eval_end_f1": 0.8084091427286784,
+      "eval_exact_match": 0.7761194029850746,
+      "eval_loss": 0.2963466942310333,
+      "eval_runtime": 7.7314,
+      "eval_samples_per_second": 77.994,
+      "eval_start_accuracy": 1.0,
+      "eval_start_f1": 1.0,
+      "eval_steps_per_second": 19.531,
+      "step": 500
+    },
+    {
+      "epoch": 1.8705148205928237,
+      "grad_norm": 1.5345109701156616,
+      "learning_rate": 0.000175,
+      "loss": 0.3057,
+      "step": 600
+    },
+    {
+      "epoch": 2.1809672386895476,
+      "grad_norm": 1.14028000831604,
+      "learning_rate": 0.00014948979591836736,
+      "loss": 0.2606,
+      "step": 700
+    },
+    {
+      "epoch": 2.4929797191887677,
+      "grad_norm": 1.651394009590149,
+      "learning_rate": 0.0001239795918367347,
+      "loss": 0.2355,
+      "step": 800
+    },
+    {
+      "epoch": 2.8049921996879874,
+      "grad_norm": 0.7826488018035889,
+      "learning_rate": 9.846938775510204e-05,
+      "loss": 0.2111,
+      "step": 900
+    },
+    {
+      "epoch": 3.1154446177847115,
+      "grad_norm": 1.4387627840042114,
+      "learning_rate": 7.29591836734694e-05,
+      "loss": 0.1877,
+      "step": 1000
+    },
+    {
+      "epoch": 3.1154446177847115,
+      "eval_avg_f1": 0.9126043768741985,
+      "eval_end_accuracy": 0.8590381426202321,
+      "eval_end_f1": 0.8252087537483971,
+      "eval_exact_match": 0.8590381426202321,
+      "eval_loss": 0.191666379570961,
+      "eval_runtime": 7.7266,
+      "eval_samples_per_second": 78.042,
+      "eval_start_accuracy": 1.0,
+      "eval_start_f1": 1.0,
+      "eval_steps_per_second": 19.543,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1284,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4304008044539904.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bba849b6b88964ccf383701afd448640f5554fbd63e1966437a60e450070b2e
+size 5304

checkpoint-1284/README.md

@@ -0,0 +1,202 @@
+---
+base_model: bert-base-uncased
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-1284/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bert-base-uncased",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "qa_outputs"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense",
+    "value",
+    "key",
+    "query"
+  ],
+  "task_type": "QUESTION_ANS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1284/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71220968eee1d572c954a7a0d06a6c4d5e250a73d8c876734ea03636dfbc7f35
+size 10643320

checkpoint-1284/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6f76bfa4dd503d2ad6fd82788ff862dee28fccc272643dcaeb26b2bee49c23
+size 21368634

checkpoint-1284/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa725792df0f6729be172a27f31280daa032849a2a8181636ca9e61112bd582
+size 14244

checkpoint-1284/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3cc23737dd91e76790def9ca459508c4821d18ae9e08ba3345e3e71bf535ef4
+size 988

checkpoint-1284/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1dc5cd7244c4bca62646fa61fb5dd8e4d0db901c65534250a16cac353fbe68
+size 1064

checkpoint-1284/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-1284/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": true,
+  "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]"
+}

checkpoint-1284/trainer_state.json

@@ -0,0 +1,155 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.191666379570961,
+  "best_model_checkpoint": "/content/shakespeare-bert-qa-lora/checkpoint-1000",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1284,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.31201248049922,
+      "grad_norm": 6.9100189208984375,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 5.4426,
+      "step": 100
+    },
+    {
+      "epoch": 0.62402496099844,
+      "grad_norm": 2.527374029159546,
+      "learning_rate": 7.920000000000001e-05,
+      "loss": 1.0745,
+      "step": 200
+    },
+    {
+      "epoch": 0.9360374414976599,
+      "grad_norm": 2.013089895248413,
+      "learning_rate": 0.0001192,
+      "loss": 0.4128,
+      "step": 300
+    },
+    {
+      "epoch": 1.2464898595943839,
+      "grad_norm": 1.5375763177871704,
+      "learning_rate": 0.00015920000000000002,
+      "loss": 0.3497,
+      "step": 400
+    },
+    {
+      "epoch": 1.5585023400936038,
+      "grad_norm": 2.152944564819336,
+      "learning_rate": 0.00019920000000000002,
+      "loss": 0.3406,
+      "step": 500
+    },
+    {
+      "epoch": 1.5585023400936038,
+      "eval_avg_f1": 0.9042045713643392,
+      "eval_end_accuracy": 0.7761194029850746,
+      "eval_end_f1": 0.8084091427286784,
+      "eval_exact_match": 0.7761194029850746,
+      "eval_loss": 0.2963466942310333,
+      "eval_runtime": 7.7314,
+      "eval_samples_per_second": 77.994,
+      "eval_start_accuracy": 1.0,
+      "eval_start_f1": 1.0,
+      "eval_steps_per_second": 19.531,
+      "step": 500
+    },
+    {
+      "epoch": 1.8705148205928237,
+      "grad_norm": 1.5345109701156616,
+      "learning_rate": 0.000175,
+      "loss": 0.3057,
+      "step": 600
+    },
+    {
+      "epoch": 2.1809672386895476,
+      "grad_norm": 1.14028000831604,
+      "learning_rate": 0.00014948979591836736,
+      "loss": 0.2606,
+      "step": 700
+    },
+    {
+      "epoch": 2.4929797191887677,
+      "grad_norm": 1.651394009590149,
+      "learning_rate": 0.0001239795918367347,
+      "loss": 0.2355,
+      "step": 800
+    },
+    {
+      "epoch": 2.8049921996879874,
+      "grad_norm": 0.7826488018035889,
+      "learning_rate": 9.846938775510204e-05,
+      "loss": 0.2111,
+      "step": 900
+    },
+    {
+      "epoch": 3.1154446177847115,
+      "grad_norm": 1.4387627840042114,
+      "learning_rate": 7.29591836734694e-05,
+      "loss": 0.1877,
+      "step": 1000
+    },
+    {
+      "epoch": 3.1154446177847115,
+      "eval_avg_f1": 0.9126043768741985,
+      "eval_end_accuracy": 0.8590381426202321,
+      "eval_end_f1": 0.8252087537483971,
+      "eval_exact_match": 0.8590381426202321,
+      "eval_loss": 0.191666379570961,
+      "eval_runtime": 7.7266,
+      "eval_samples_per_second": 78.042,
+      "eval_start_accuracy": 1.0,
+      "eval_start_f1": 1.0,
+      "eval_steps_per_second": 19.543,
+      "step": 1000
+    },
+    {
+      "epoch": 3.427457098283931,
+      "grad_norm": 4.705386638641357,
+      "learning_rate": 4.744897959183674e-05,
+      "loss": 0.1589,
+      "step": 1100
+    },
+    {
+      "epoch": 3.7394695787831513,
+      "grad_norm": 2.636837959289551,
+      "learning_rate": 2.193877551020408e-05,
+      "loss": 0.1657,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1284,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5525987414851584.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1284/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bba849b6b88964ccf383701afd448640f5554fbd63e1966437a60e450070b2e
+size 5304

checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: bert-base-uncased
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-500/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bert-base-uncased",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "qa_outputs"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense",
+    "value",
+    "key",
+    "query"
+  ],
+  "task_type": "QUESTION_ANS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47111b2d1c7d83238873959d7bc155afaa62ab402b87c57b7dec9d15813fbc61
+size 10643320

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50630908cc02ef6b2c882d1290d3f02790010c3adc6227b07f0c2999c9b42429
+size 21368634

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c698830ec0817996c21897635410c57ba2e6997a37dbc3664f3770d8439c681e
+size 14244

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789026111f7b68779af7bced1cc170dcfd76442f791f81c6196055a5c0e766a1
+size 988

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8909540cd574fdc732f40630b7bb81a93f59c601469e2d3291fdc2086835eaf4
+size 1064

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-500/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": true,
+  "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]"
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_global_step": 500,
+  "best_metric": 0.2963466942310333,
+  "best_model_checkpoint": "/content/shakespeare-bert-qa-lora/checkpoint-500",
+  "epoch": 1.5585023400936038,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.31201248049922,
+      "grad_norm": 6.9100189208984375,
+      "learning_rate": 3.9200000000000004e-05,
+      "loss": 5.4426,
+      "step": 100
+    },
+    {
+      "epoch": 0.62402496099844,
+      "grad_norm": 2.527374029159546,
+      "learning_rate": 7.920000000000001e-05,
+      "loss": 1.0745,
+      "step": 200
+    },
+    {
+      "epoch": 0.9360374414976599,
+      "grad_norm": 2.013089895248413,
+      "learning_rate": 0.0001192,
+      "loss": 0.4128,
+      "step": 300
+    },
+    {
+      "epoch": 1.2464898595943839,
+      "grad_norm": 1.5375763177871704,
+      "learning_rate": 0.00015920000000000002,
+      "loss": 0.3497,
+      "step": 400
+    },
+    {
+      "epoch": 1.5585023400936038,
+      "grad_norm": 2.152944564819336,
+      "learning_rate": 0.00019920000000000002,
+      "loss": 0.3406,
+      "step": 500
+    },
+    {
+      "epoch": 1.5585023400936038,
+      "eval_avg_f1": 0.9042045713643392,
+      "eval_end_accuracy": 0.7761194029850746,
+      "eval_end_f1": 0.8084091427286784,
+      "eval_exact_match": 0.7761194029850746,
+      "eval_loss": 0.2963466942310333,
+      "eval_runtime": 7.7314,
+      "eval_samples_per_second": 77.994,
+      "eval_start_accuracy": 1.0,
+      "eval_start_f1": 1.0,
+      "eval_steps_per_second": 19.531,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1284,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2153216570707968.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bba849b6b88964ccf383701afd448640f5554fbd63e1966437a60e450070b2e
+size 5304

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": true,
+  "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]"
+}