aai520-group6
/

distilbert-finetuned-uncased-squad_v2

@@ -1,281 +1,132 @@
 ---
-language: en
-license: mit
-model_details: "\n        ## Abstract\n        This model, 'distilbert-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\
-  \ 'distilbert-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 10 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        "
 model-index:
-- name: distilbert-finetuned-uncased
-  results:
-  - task:
-      type: question-answering
-    dataset:
-      name: SQuAD v2
-      type: squad_v2
-    metrics:
-    - type: Exact
-      value: 100.0
-    - type: F1
-      value: 100.0
-    - type: Total
-      value: 2
-    - type: Hasans Exact
-      value: 100.0
-    - type: Hasans F1
-      value: 100.0
-    - type: Hasans Total
-      value: 2
-    - type: Best Exact
-      value: 100.0
-    - type: Best Exact Thresh
-      value: 0.967875599861145
-    - type: Best F1
-      value: 100.0
-    - type: Best F1 Thresh
-      value: 0.967875599861145
-    - type: Total Time In Seconds
-      value: 0.02787837800019588
-    - type: Samples Per Second
-      value: 71.74018517095749
-    - type: Latency In Seconds
-      value: 0.01393918900009794
 ---
-# 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]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** en
-- **License:** mit
-- **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 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]

 ---
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
 model-index:
+- name: distilbert-finetuned-uncased-squad_v2
+  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. -->
+# distilbert-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: 1.2617
+## 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: 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: 10
+### Training results
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.6437        | 0.39  | 100  | 2.1780          |
+| 2.1596        | 0.78  | 200  | 1.6557          |
+| 1.8138        | 1.18  | 300  | 1.5683          |
+| 1.6987        | 1.57  | 400  | 1.5076          |
+| 1.6586        | 1.96  | 500  | 1.5350          |
+| 1.5957        | 1.18  | 600  | 1.4431          |
+| 1.5825        | 1.37  | 700  | 1.4955          |
+| 1.5523        | 1.57  | 800  | 1.4444          |
+| 1.5346        | 1.76  | 900  | 1.3930          |
+| 1.5098        | 1.96  | 1000 | 1.4285          |
+| 1.4632        | 2.16  | 1100 | 1.3630          |
+| 1.4468        | 2.35  | 1200 | 1.3710          |
+| 1.4343        | 2.55  | 1300 | 1.3422          |
+| 1.4225        | 2.75  | 1400 | 1.3971          |
+| 1.408         | 2.94  | 1500 | 1.4355          |
+| 1.3609        | 3.14  | 1600 | 1.3332          |
+| 1.3398        | 3.33  | 1700 | 1.3792          |
+| 1.3224        | 3.53  | 1800 | 1.4172          |
+| 1.3152        | 3.73  | 1900 | 1.3956          |
+| 1.3141        | 3.92  | 2000 | 1.3748          |
+| 1.3085        | 2.06  | 2100 | 1.3949          |
+| 1.3325        | 2.16  | 2200 | 1.4870          |
+| 1.3162        | 2.26  | 2300 | 1.4565          |
+| 1.2936        | 2.35  | 2400 | 1.4496          |
+| 1.2648        | 2.45  | 2500 | 1.2868          |
+| 1.2531        | 2.55  | 2600 | 1.5094          |
+| 1.2599        | 2.65  | 2700 | 1.3451          |
+| 1.2545        | 2.75  | 2800 | 1.4071          |
+| 1.2461        | 2.84  | 2900 | 1.3378          |
+| 1.2038        | 2.94  | 3000 | 1.2946          |
+| 1.1677        | 3.04  | 3100 | 1.4802          |
+| 1.103         | 3.14  | 3200 | 1.3580          |
+| 1.1205        | 3.24  | 3300 | 1.3819          |
+| 1.095         | 3.33  | 3400 | 1.4336          |
+| 1.0896        | 3.43  | 3500 | 1.4963          |
+| 1.0856        | 3.53  | 3600 | 1.3384          |
+| 1.0652        | 3.63  | 3700 | 1.3583          |
+| 1.0859        | 3.73  | 3800 | 1.4140          |
+| 1.058         | 3.83  | 3900 | 1.2617          |
+| 1.0724        | 3.92  | 4000 | 1.3552          |
+| 1.0509        | 4.02  | 4100 | 1.2971          |
+| 0.97          | 4.12  | 4200 | 1.3268          |
+| 0.95          | 4.22  | 4300 | 1.3754          |
+| 0.9337        | 4.32  | 4400 | 1.3687          |
+| 0.977         | 4.41  | 4500 | 1.3613          |
+| 0.9484        | 4.51  | 4600 | 1.5139          |
+| 0.9739        | 4.61  | 4700 | 1.2861          |
+| 0.955         | 4.71  | 4800 | 1.3667          |
+| 0.9536        | 4.81  | 4900 | 1.3180          |
+| 0.9541        | 4.9   | 5000 | 1.4611          |
+| 0.9462        | 5.0   | 5100 | 1.4067          |
+| 0.8728        | 5.1   | 5200 | 1.3490          |
+| 0.8646        | 5.2   | 5300 | 1.4631          |
+| 0.8683        | 5.3   | 5400 | 1.4978          |
+| 0.8571        | 5.39  | 5500 | 1.5814          |
+| 0.8475        | 5.49  | 5600 | 1.5535          |
+| 0.8653        | 5.59  | 5700 | 1.4938          |
+| 0.8664        | 5.69  | 5800 | 1.4141          |
+| 0.889         | 5.79  | 5900 | 1.4487          |
+| 0.8601        | 5.88  | 6000 | 1.4722          |
+| 0.8645        | 5.98  | 6100 | 1.5843          |
+| 0.785         | 6.08  | 6200 | 1.6028          |
+| 0.7711        | 6.18  | 6300 | 1.6271          |
+| 0.8056        | 6.28  | 6400 | 1.5399          |
+| 0.8087        | 6.37  | 6500 | 1.4927          |
+| 0.7859        | 6.47  | 6600 | 1.4677          |
+| 0.7896        | 6.57  | 6700 | 1.4780          |
+| 0.7971        | 6.67  | 6800 | 1.5110          |
+| 0.7952        | 6.77  | 6900 | 1.5459          |
+| 0.7971        | 6.87  | 7000 | 1.5282          |
+| 0.7908        | 6.96  | 7100 | 1.4799          |
+| 0.7456        | 7.06  | 7200 | 1.6487          |
+| 0.7236        | 7.16  | 7300 | 1.6543          |
+| 0.7484        | 7.26  | 7400 | 1.6202          |
+### Framework versions
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

metrics.json CHANGED Viewed

@@ -9,7 +9,7 @@
     "best_exact_thresh": 0.967875599861145,
     "best_f1": 100.0,
     "best_f1_thresh": 0.967875599861145,
-    "total_time_in_seconds": 0.03484977200002959,
-    "samples_per_second": 57.389184640814925,
-    "latency_in_seconds": 0.017424886000014794
 }

     "best_exact_thresh": 0.967875599861145,
     "best_f1": 100.0,
     "best_f1_thresh": 0.967875599861145,
+    "total_time_in_seconds": 0.02787837800019588,
+    "samples_per_second": 71.74018517095749,
+    "latency_in_seconds": 0.01393918900009794
 }

trainer_state.json CHANGED Viewed

@@ -1049,21 +1049,21 @@
       "step": 7400,
       "total_flos": 1.738708177538776e+17,
       "train_loss": 0.0,
-      "train_runtime": 0.8545,
-      "train_samples_per_second": 1527321.888,
-      "train_steps_per_second": 2984.353
     },
     {
       "epoch": 7.26,
       "eval_loss": 1.261675477027893,
-      "eval_runtime": 63.4844,
-      "eval_samples_per_second": 188.535,
-      "eval_steps_per_second": 1.481,
       "step": 7400
     }
   ],
   "logging_steps": 100,
-  "max_steps": 2550,
   "num_train_epochs": 10,
   "save_steps": 100,
   "total_flos": 1.738708177538776e+17,

       "step": 7400,
       "total_flos": 1.738708177538776e+17,
       "train_loss": 0.0,
+      "train_runtime": 0.6152,
+      "train_samples_per_second": 2121277.112,
+      "train_steps_per_second": 8289.858
     },
     {
       "epoch": 7.26,
       "eval_loss": 1.261675477027893,
+      "eval_runtime": 63.7101,
+      "eval_samples_per_second": 187.867,
+      "eval_steps_per_second": 2.951,
       "step": 7400
     }
   ],
   "logging_steps": 100,
+  "max_steps": 5100,
   "num_train_epochs": 10,
   "save_steps": 100,
   "total_flos": 1.738708177538776e+17,