V1.2 model card update

README.md

@@ -2,7 +2,6 @@
 library_name: transformers
 tags:
 - tone
-license: mit
 datasets:
 - Dc-4nderson/tone_dataset
 language:
@@ -33,9 +32,7 @@ motivational
 
 informative
 
-neutral
-
-negative
+optimistic
 
 📊 Dataset
 
@@ -48,37 +45,36 @@ Data includes first-person and third-person statements, anecdotes, factual notes
 
 Base model: distilbert-base-uncased
 
-Optimizer: AdamW (lr=5e-5)
+Optimizer: AdamW (lr=2e-5)
 
 Batch size: 16
 
-Epochs: 8
+Epochs: 5
 
 Loss: CrossEntropy
 
 Metrics: Accuracy + Weighted F1
 
 📈 Validation Metrics
-Epoch	Training Loss	Validation Loss	Accuracy	F1
-1	No log	0.484719	0.894161	0.895220
-2	No log	0.264668	0.923358	0.923200
-3	No log	0.243101	0.930657	0.930599
-4	No log	0.302434	0.916058	0.918166
-5	No log	0.305320	0.923358	0.923836
-6	No log	0.294621	0.916058	0.916176
-7	No log	0.303021	0.919708	0.919583
-8	0.215900	0.298230	0.916058	0.915722
+Epoch	Training Loss	Validation Loss  Accuracy	F1
+1	    No log	          1.260710	     0.801242	  0.784157
+2	    No log	          0.777540	     0.869565	  0.869093
+3	    No log	          0.577972	     0.869565	  0.868584
+4	    No log	          0.481008	     0.900621	  0.900356
+5	    No log	          0.452635	     0.900621	  0.900356
+
 
 Final Training Summary:
 
-TrainOutput(global_step=552, training_loss=0.1959800598198089, 
-metrics={
-  'train_runtime': 39.2397, 
-  'train_samples_per_second': 223.244, 
-  'train_steps_per_second': 14.067, 
-  'total_flos': 290134644572160.0, 
-  'train_loss': 0.1959800598198089, 
-  'epoch': 8.0
+TrainOutput(
+global_step=205, 
+training_loss=0.8436699843988186,
+metrics={'train_runtime': 17.74,
+'train_samples_per_second': 181.229, 
+'train_steps_per_second': 11.556, 
+'total_flos': 106480165436160.0, 
+'train_loss': 0.8436699843988186, 
+'epoch': 5.0
 })
 
 💻 Usage
@@ -94,10 +90,6 @@ Output:
 
 [{'label': 'uplifting'}]
 
-🔖 License
-
-Apache-2.0
-
 👥 Maintainer
 
 Dequan Anderson/ Dc-4nderson