Update README.md

README.md

@@ -22,7 +22,11 @@ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https
 
 ## Model description
 
-More information needed
+Article: https://ai.plainenglish.io/fine-tuning-the-mistral-7b-instruct-v0-1-model-with-the-emotion-dataset-c84c50b553dc
+
+Fine tunning: https://github.com/frank-morales2020/MLxDL/blob/main/FineTuning_Mistral_7b_hfdeployment_dataset_Emotion.ipynb
+
+Evaluation: https://github.com/frank-morales2020/MLxDL/blob/main/FineTunning_Testing_For_EmotionQADataset.ipynb
 
 ## Intended uses & limitations
 
@@ -30,7 +34,27 @@ More information needed
 
 ## Training and evaluation data
 
-More information needed
+Evaluation: https://github.com/frank-morales2020/MLxDL/blob/main/FineTunning_Testing_For_EmotionQADataset.ipynb
+
+
+The following hyperparameters were used during training: 
+learning_rate: 0.0002 train_batch_size: 3 eval_batch_size: 8 seed: 42 
+gradient_accumulation_steps: 2 total_train_batch_size: 6 
+optimizer: Adam with betas=(0.9,0.999) 
+and epsilon=1e-08 lr_scheduler_type: constant lr_scheduler_warmup_ratio: 0.03 
+
+
+num_epochs: 1
+Accuracy (Eval dataset and predict) for a sample of 2000: 59.45%
+
+num_epochs: 25
+Accuracy (Eval dataset and predict) for a sample of 2000: 79.95%
+
+num_epochs: 40
+Accuracy (Eval dataset and predict) for a sample of 2000: 80.70%
+
+num_epochs: 40
+Accuracy (Eval dataset and predict) for a sample of 2000: 80%
 
 ## Training procedure