Model save

README.md

@@ -20,15 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
 
-Dataset: [dair-ai/emotion](https://huggingface.co/datasets/dair-ai/emotion)
-
 ## Model description
 
-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
+More information needed
 
 ## Intended uses & limitations
 
@@ -36,34 +30,7 @@ More information needed
 
 ## Training and evaluation data
 
-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%
-
-*************
-
-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: 25
-
-Accuracy (Eval dataset and predict) for a sample of 2000: 79.95%
-
-*************
-
-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: 40
-
- Accuracy (Eval dataset and predict) for a sample of 2000: 80.70%
-
-*************
+More information needed
 
 ## Training procedure
 
@@ -79,7 +46,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 40
+- num_epochs: 100
 
 ### Training results