End of training

README.md

@@ -1,49 +1,60 @@
 ---
-license: mit
+library_name: transformers
+license: apache-2.0
+base_model: distilbert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: my_awesome_qa_model
+  results: []
 ---
-# Question Answering Chatbot using Hugging Face Transformers
 
-This project fine-tunes a question answering model using the Hugging Face Transformers library and SQuAD dataset.  
-It also includes a simple chat wrapper that allows users to ask questions interactively based on a given context.
+<!-- 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. -->
 
----
+# my_awesome_qa_model
 
-## 📚 Project Overview
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8753
 
-- Fine-tunes a pretrained DistilBERT model (`distilbert-base-cased-distilled-squad`) on the SQuAD dataset.
-- Implements a chat interface where users can ask free-form questions related to a specific context.
-- Publishes the fine-tuned model to Hugging Face Hub.
+## Model description
 
----
+More information needed
 
-## 🚀 Notebook Workflow
+## Intended uses & limitations
 
-1. **Setup**  
-   Install required libraries and disable TensorFlow backend to ensure PyTorch is used.
+More information needed
 
-2. **Dataset Loading and Preprocessing**  
-   Load the SQuAD dataset, tokenize the questions and contexts, and prepare input tensors.
+## Training and evaluation data
 
-3. **Model Fine-tuning**  
-   Fine-tune the pretrained model for 3 epochs using the Hugging Face `Trainer` API.
+More information needed
 
-4. **Push to Hugging Face Hub**  
-   Upload the trained model and tokenizer to your Hugging Face profile.
+## Training procedure
 
-5. **Chatbot Interface**  
-   Implement a simple wrapper allowing users to ask questions about a given context.
+### Training hyperparameters
 
----
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
 
-## 🛠️ Requirements
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 250  | 2.3563          |
+| 2.7737        | 2.0   | 500  | 1.9792          |
+| 2.7737        | 3.0   | 750  | 1.8753          |
 
-- Python 3.8+
-- `transformers`
-- `datasets`
-- `torch`
-- `wandb` (optional, for experiment tracking)
 
-Install requirements in Colab or locally:
+### Framework versions
 
-```bash
-pip install transformers datasets torch wandb
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

runs/May12_14-32-41_29d1e8ae1181/events.out.tfevents.1747060365.29d1e8ae1181.477.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f84662b0b969f9103076e6b0e48684cca092193849e9646ad3b948d85c9896a
-size 5610
+oid sha256:0f83e1e5ec089e00e0fce413a47667ade733fd4405336c00b237539c3a88479d
+size 6235