Updated README.md

Improve text format and clean some useless data

README.md

@@ -1,41 +1,55 @@
 ---
 language: es
+
 tags:
 - sagemaker
 - roberta
 - ruperta
 - TextClassification
+
 license: apache-2.0
+
 datasets:
 - IMDbreviews_es
+
 model-index:
 - name: RuPERTa_base_sentiment_analysis_es
+
   results:
-  - task: 
+  - task:
+   
       name: Sentiment Analysis
+      
       type: sentiment-analysis
-    dataset:
+  - dataset:
+  
       name: "IMDb Reviews in Spanish" 
+      
       type: IMDbreviews_es
-    metrics:
-       - name: Accuracy
-         type: accuracy
+      
+  - metrics:
+       - name: Accuracy,
+         type: accuracy,
          value: 0.881866
-       - name: F1 Score
-         type: f1
+         
+       - name: F1 Score,
+         type: f1,
          value: 0.008272
-       - name: Precision
-         type: precision
+         
+       - name: Precision,
+         type: precision,
          value: 0.858605
-       - name: Recall
-         type: recall
+         
+       - name: Recall,
+         type: recall,
          value: 0.920062
+         
 ## `RuPERTa_base_sentiment_analysis_es`
 
 This model was trained using Amazon SageMaker and the new Hugging Face Deep Learning container.
 
 The base model is RuPERTa-base (uncased) which is a RoBERTa model trained on a uncased version of big Spanish corpus.
-It was trained by mrm8488, Manuel Romero.
+It was trained by mrm8488, Manuel Romero. It is fine-tuned for a sentiment analysis task.
 
 ## Hyperparameters
 
@@ -53,23 +67,18 @@ It was trained by mrm8488, Manuel Romero.
     "train_batch_size": "32",
     "train_filename": "\"train_data.pt\"",
     "val_filename": "\"val_data.pt\""
-}
-
-
-## Usage
+    }
 
-## Results
+## Evaluation results
 
 epoch = 1.0
+
 eval_accuracy = 0.8629333333333333
+
 eval_f1 = 0.8648790746582545
+
 eval_loss = 0.3160930573940277
-eval_mem_cpu_alloc_delta = 0
-eval_mem_cpu_peaked_delta = 0
-eval_mem_gpu_alloc_delta = 0
-eval_mem_gpu_peaked_delta = 94507520
+
 eval_precision = 0.8479381443298969
-eval_recall = 0.8825107296137339
-eval_runtime = 114.4994
-eval_samples_per_second = 32.751
 
+eval_recall = 0.8825107296137339