update model card README.md

README.md

@@ -1,33 +1,67 @@
 ---
-language: en
-tags:
-- text-generation
 license: apache-2.0
-widget:
-- text: "Maximize your bedroom space without sacrificing style with the storage bed."
-- text: "Handcrafted of solid acacia in weathered gray, our round Jozy drop-leaf dining table is a space-saving."
-- text: "Our plush and luxurious Emmett modular sofa brings custom comfort to your living space."
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: product_description_generator
+  results: []
 ---
 
-## GPT2-Home
+<!-- 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. -->
+
+# product_description_generator
+
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.0241
+- Rouge1: 0.1639
+- Rouge2: 0.0
+- Rougel: 0.1337
+- Rougelsum: 0.1357
+- Gen Len: 11.4
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
 
-This model is fine-tuned using GPT-2 on amazon home products metadata. 
-It can generate descriptions for your **home** products by getting a text prompt.
+### Training hyperparameters
 
-### Model description
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+- mixed_precision_training: Native AMP
 
+### Training results
 
-[GPT-2](https://openai.com/blog/better-language-models/) is a large [transformer](https://arxiv.org/abs/1706.03762)-based language model with 1.5 billion parameters, trained on a dataset of 8 million web pages. GPT-2 is trained with a simple objective: predict the next word, given all of the previous words within some text. The diversity of the dataset causes this simple goal to contain naturally occurring demonstrations of many tasks across diverse domains. GPT-2 is a direct scale-up of GPT, with more than 10X the parameters and trained on more than 10X the amount of data.
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| No log        | 1.0   | 6    | 4.2311          | 0.1365 | 0.0    | 0.1103 | 0.1102    | 12.1    |
+| No log        | 2.0   | 12   | 4.1437          | 0.1668 | 0.0    | 0.1321 | 0.1332    | 13.2    |
+| No log        | 3.0   | 18   | 4.0572          | 0.143  | 0.0    | 0.1152 | 0.1152    | 11.8    |
+| No log        | 4.0   | 24   | 4.0241          | 0.1639 | 0.0    | 0.1337 | 0.1357    | 11.4    |
 
 
-### How to use
-For best experience and clean outputs, you can use Live Demo mentioned above, also you can use the notebook mentioned in my [GitHub](https://github.com/HamidRezaAttar/GPT2-Home)
+### Framework versions
 
-You can use this model directly with a pipeline for text generation.
-```python
->>> from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
->>> tokenizer = AutoTokenizer.from_pretrained("bprateek/product_description_generator")
->>> model = AutoModelForCausalLM.from_pretrained("bprateek/product_description_generator")
->>> generator = pipeline('text-generation', model, tokenizer=tokenizer, config={'max_length':100})
->>> generated_text = generator("This bed is very comfortable.")
-```
+- Transformers 4.28.1
+- Pytorch 2.0.0+cu118
+- Datasets 2.12.0
+- Tokenizers 0.13.3