jeevana/GenerativeQnASystem

1---2license: mit3base_model: gpt24tags:5- generated_from_trainer6model-index:7- name: GenerativeQnASystem8  results: []9---10 11<!-- This model card has been generated automatically according to the information the Trainer had access to. You12should probably proofread and complete it, then remove this comment. -->13 14# GenerativeQnASystem15 16This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.17It achieves the following results on the evaluation set:18- Loss: 2.757619 20## Model description21 22More information needed23 24## Intended uses & limitations25 26More information needed27 28## Training and evaluation data29 30More information needed31 32## Training procedure33 34### Training hyperparameters35 36The following hyperparameters were used during training:37- learning_rate: 5e-0538- train_batch_size: 239- eval_batch_size: 240- seed: 4241- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0842- lr_scheduler_type: linear43- num_epochs: 244 45### Training results46 47| Training Loss | Epoch | Step | Validation Loss |48|:-------------:|:-----:|:----:|:---------------:|49| No log        | 0.35  | 100  | 2.8787          |50| No log        | 0.71  | 200  | 2.8137          |51| No log        | 1.06  | 300  | 2.7626          |52| No log        | 1.42  | 400  | 2.7541          |53| 2.4388        | 1.77  | 500  | 2.7576          |54 55 56### Framework versions57 58- Transformers 4.36.259- Pytorch 2.1.0+cu12160- Datasets 2.16.161- Tokenizers 0.15.062