Model save

README.md

@@ -1,281 +1,78 @@
 ---
-language: en
-license: mit
-model_details: "\n        ## Abstract\n        This model, 'bert-finetuned-uncased',\
-  \ is a question-answering chatbot trained on the SQuAD dataset, demonstrating competency\
-  \ in building conversational AI using recent advances in natural language processing.\
-  \ It utilizes a BERT model fine-tuned for extractive question answering.\n\n   \
-  \     ## Data Collection and Preprocessing\n        The model was trained on the\
-  \ Stanford Question Answering Dataset (SQuAD), which contains over 100,000 question-answer\
-  \ pairs based on Wikipedia articles. The data preprocessing involved tokenizing\
-  \ context paragraphs and questions, truncating sequences to fit BERT's max length,\
-  \ and adding special tokens to mark question and paragraph segments.\n\n       \
-  \ ## Model Architecture and Training\n        The architecture is based on the BERT\
-  \ transformer model, which was pretrained on large unlabeled text corpora. For this\
-  \ project, the BERT base model was fine-tuned on SQuAD for extractive question answering,\
-  \ with additional output layers for predicting the start and end indices of the\
-  \ answer span.\n\n        ## SQuAD 2.0 Dataset\n        SQuAD 2.0 combines the existing\
-  \ SQuAD data with over 50,000 unanswerable questions written adversarially by crowdworkers\
-  \ to look similar to answerable ones. This version of the dataset challenges models\
-  \ to not only produce answers when possible but also determine when no answer is\
-  \ supported by the paragraph and abstain from answering.\n        "
-intended_use: "\n        - Answering questions from the squad_v2 dataset.\n      \
-  \  - Developing question-answering systems within the scope of the aai520-project.\n\
-  \        - Research and experimentation in the NLP question-answering domain.\n\
-  \        "
-limitations_and_bias: "\n        The model inherits limitations and biases from the\
-  \ 'bert-base-uncased' model, as it was trained on the same foundational data. \n\
-  \        It may underperform on questions that are ambiguous or too far outside\
-  \ the scope of the topics covered in the squad_v2 dataset. \n        Additionally,\
-  \ the model may reflect societal biases present in its training data.\n        "
-ethical_considerations: "\n        This model should not be used for making critical\
-  \ decisions without human oversight, \n        as it can generate incorrect or biased\
-  \ answers, especially for topics not covered in the training data. \n        Users\
-  \ should also consider the ethical implications of using AI in decision-making processes\
-  \ and the potential for perpetuating biases.\n        "
-evaluation: "\n        The model was evaluated on the squad_v2 dataset using various\
-  \ metrics. These metrics, along with their corresponding scores, \n        are detailed\
-  \ in the 'eval_results' section. The evaluation process ensured a comprehensive\
-  \ assessment of the model's performance \n        in question-answering scenarios.\n\
-  \        "
-training: "\n        The model was trained over 4 epochs with a learning rate of 2e-05,\
-  \ using a batch size of 64. \n        The training utilized a cross-entropy loss\
-  \ function and the AdamW optimizer, with gradient accumulation over 4 steps.\n \
-  \       "
-tips_and_tricks: "\n        For optimal performance, questions should be clear, concise,\
-  \ and grammatically correct. \n        The model performs best on questions related\
-  \ to topics covered in the squad_v2 dataset. \n        It is advisable to pre-process\
-  \ text for consistency in encoding and punctuation, and to manage expectations for\
-  \ questions on topics outside the training data.\n        "
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
 model-index:
-- name: bert-finetuned-uncased
-  results:
-  - task:
-      type: question-answering
-    dataset:
-      name: SQuAD v2
-      type: squad_v2
-    metrics:
-    - type: Exact
-      value: 28.594289564558242
-    - type: F1
-      value: 32.86661007615217
-    - type: Total
-      value: 11873
-    - type: Hasans Exact
-      value: 52.260458839406205
-    - type: Hasans F1
-      value: 60.817351793885734
-    - type: Hasans Total
-      value: 5928
-    - type: Noans Exact
-      value: 4.995794785534062
-    - type: Noans F1
-      value: 4.995794785534062
-    - type: Noans Total
-      value: 5945
-    - type: Best Exact
-      value: 50.11370336056599
-    - type: Best Exact Thresh
-      value: 0.0
-    - type: Best F1
-      value: 50.11370336056599
-    - type: Best F1 Thresh
-      value: 0.0
+- name: bert-finetuned-uncased-squad_v2
+  results: []
 ---
 
-# Model Card for Model ID
+<!-- 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. -->
 
-<!-- Provide a quick summary of what the model is/does. -->
+# bert-finetuned-uncased-squad_v2
 
+This model was trained from scratch on the squad_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1459
 
+## Model description
 
-## Model Details
+More information needed
 
-### Model Description
+## Intended uses & limitations
 
-<!-- Provide a longer summary of what this model is. -->
+More information needed
 
+## Training and evaluation data
 
+More information needed
 
-- **Developed by:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** en
-- **License:** mit
-- **Finetuned from model [optional]:** [More Information Needed]
+## Training procedure
 
-### Model Sources [optional]
+### Training hyperparameters
 
-<!-- Provide the basic links for the model. -->
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+### Training results
 
-## Uses
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.2307        | 0.2   | 100  | 1.8959          |
+| 1.9581        | 0.39  | 200  | 1.4856          |
+| 1.6358        | 0.59  | 300  | 1.3948          |
+| 1.4964        | 0.78  | 400  | 1.2934          |
+| 1.4169        | 0.98  | 500  | 1.2605          |
+| 1.327         | 1.18  | 600  | 1.2218          |
+| 1.2763        | 1.37  | 700  | 1.2539          |
+| 1.2755        | 1.57  | 800  | 1.2090          |
+| 1.251         | 1.76  | 900  | 1.2041          |
+| 1.229         | 1.96  | 1000 | 1.2159          |
+| 1.1921        | 2.16  | 1100 | 1.1828          |
+| 1.1926        | 2.35  | 1200 | 1.2120          |
+| 1.1606        | 2.55  | 1300 | 1.1737          |
+| 1.1486        | 2.75  | 1400 | 1.1469          |
+| 1.1195        | 2.94  | 1500 | 1.1459          |
+| 1.0883        | 3.14  | 1600 | 1.1570          |
+| 1.0526        | 3.33  | 1700 | 1.1771          |
+| 1.0611        | 3.53  | 1800 | 1.1740          |
+| 1.0521        | 3.73  | 1900 | 1.1596          |
+| 1.0476        | 3.92  | 2000 | 1.1538          |
 
-<!-- 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 Data 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 Data 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
 
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/bert-finetuned-uncased/checkpoint-1000",
+  "_name_or_path": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/bert-finetuned-uncased/checkpoint-2000",
   "architectures": [
     "BertForQuestionAnswering"
   ],

metrics.json

@@ -1,12 +1,12 @@
 {
-    "exact": 27.878379516550154,
-    "f1": 32.12991628283337,
+    "exact": 28.594289564558242,
+    "f1": 32.86661007615217,
     "total": 11873,
-    "HasAns_exact": 50.40485829959514,
-    "HasAns_f1": 58.920124160944766,
+    "HasAns_exact": 52.260458839406205,
+    "HasAns_f1": 60.817351793885734,
     "HasAns_total": 5928,
-    "NoAns_exact": 5.416316232127839,
-    "NoAns_f1": 5.416316232127839,
+    "NoAns_exact": 4.995794785534062,
+    "NoAns_f1": 4.995794785534062,
     "NoAns_total": 5945,
     "best_exact": 50.11370336056599,
     "best_exact_thresh": 0.0,

tokenizer.json

@@ -3,13 +3,11 @@
   "truncation": {
     "direction": "Right",
     "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
+    "strategy": "OnlySecond",
+    "stride": 128
   },
   "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
+    "strategy": "BatchLongest",
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 0,

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2041057348251343,
-  "best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/bert-finetuned-uncased/checkpoint-900",
-  "epoch": 1.9607843137254903,
+  "best_metric": 1.1458996534347534,
+  "best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/bert-finetuned-uncased/checkpoint-1500",
+  "epoch": 4.0,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 2040,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -149,28 +149,168 @@
       "step": 1000
     },
     {
-      "epoch": 1.96,
-      "step": 1000,
-      "total_flos": 6.687707580928205e+16,
-      "train_loss": 0.0,
-      "train_runtime": 0.4984,
-      "train_samples_per_second": 523694.092,
-      "train_steps_per_second": 1023.287
+      "epoch": 2.16,
+      "learning_rate": 9.23529411764706e-06,
+      "loss": 1.1921,
+      "step": 1100
     },
     {
-      "epoch": 1.96,
-      "eval_loss": 1.204106092453003,
-      "eval_runtime": 16.8904,
-      "eval_samples_per_second": 708.629,
-      "eval_steps_per_second": 5.565,
-      "step": 1000
+      "epoch": 2.16,
+      "eval_loss": 1.1828099489212036,
+      "eval_runtime": 17.2866,
+      "eval_samples_per_second": 692.384,
+      "eval_steps_per_second": 10.875,
+      "step": 1100
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.254901960784314e-06,
+      "loss": 1.1926,
+      "step": 1200
+    },
+    {
+      "epoch": 2.35,
+      "eval_loss": 1.2119532823562622,
+      "eval_runtime": 17.2797,
+      "eval_samples_per_second": 692.663,
+      "eval_steps_per_second": 10.88,
+      "step": 1200
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.284313725490196e-06,
+      "loss": 1.1606,
+      "step": 1300
+    },
+    {
+      "epoch": 2.55,
+      "eval_loss": 1.1737300157546997,
+      "eval_runtime": 17.272,
+      "eval_samples_per_second": 692.971,
+      "eval_steps_per_second": 10.885,
+      "step": 1300
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.303921568627452e-06,
+      "loss": 1.1486,
+      "step": 1400
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 1.1468586921691895,
+      "eval_runtime": 17.2965,
+      "eval_samples_per_second": 691.99,
+      "eval_steps_per_second": 10.869,
+      "step": 1400
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 5.3235294117647064e-06,
+      "loss": 1.1195,
+      "step": 1500
+    },
+    {
+      "epoch": 2.94,
+      "eval_loss": 1.1458996534347534,
+      "eval_runtime": 17.2925,
+      "eval_samples_per_second": 692.148,
+      "eval_steps_per_second": 10.872,
+      "step": 1500
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 4.343137254901961e-06,
+      "loss": 1.0883,
+      "step": 1600
+    },
+    {
+      "epoch": 3.14,
+      "eval_loss": 1.1569820642471313,
+      "eval_runtime": 17.2745,
+      "eval_samples_per_second": 692.872,
+      "eval_steps_per_second": 10.883,
+      "step": 1600
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.3627450980392163e-06,
+      "loss": 1.0526,
+      "step": 1700
+    },
+    {
+      "epoch": 3.33,
+      "eval_loss": 1.177062749862671,
+      "eval_runtime": 17.2742,
+      "eval_samples_per_second": 692.885,
+      "eval_steps_per_second": 10.883,
+      "step": 1700
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 2.3823529411764705e-06,
+      "loss": 1.0611,
+      "step": 1800
+    },
+    {
+      "epoch": 3.53,
+      "eval_loss": 1.174006462097168,
+      "eval_runtime": 17.2639,
+      "eval_samples_per_second": 693.295,
+      "eval_steps_per_second": 10.89,
+      "step": 1800
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.4019607843137257e-06,
+      "loss": 1.0521,
+      "step": 1900
+    },
+    {
+      "epoch": 3.73,
+      "eval_loss": 1.1595549583435059,
+      "eval_runtime": 17.2716,
+      "eval_samples_per_second": 692.987,
+      "eval_steps_per_second": 10.885,
+      "step": 1900
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 4.2156862745098044e-07,
+      "loss": 1.0476,
+      "step": 2000
+    },
+    {
+      "epoch": 3.92,
+      "eval_loss": 1.1538442373275757,
+      "eval_runtime": 17.2708,
+      "eval_samples_per_second": 693.021,
+      "eval_steps_per_second": 10.885,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "step": 2040,
+      "total_flos": 1.3640004257727283e+17,
+      "train_loss": 0.5653368706796683,
+      "train_runtime": 1697.6888,
+      "train_samples_per_second": 307.484,
+      "train_steps_per_second": 1.202
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.1458996534347534,
+      "eval_runtime": 17.2641,
+      "eval_samples_per_second": 693.288,
+      "eval_steps_per_second": 10.89,
+      "step": 2040
     }
   ],
   "logging_steps": 100,
-  "max_steps": 510,
-  "num_train_epochs": 2,
+  "max_steps": 2040,
+  "num_train_epochs": 4,
   "save_steps": 100,
-  "total_flos": 6.687707580928205e+16,
+  "total_flos": 1.3640004257727283e+17,
   "trial_name": null,
   "trial_params": null
 }