Update results.py

results.py

@@ -9,30 +9,59 @@ import plotly.express as px
 
 ##upsampling validation loss graph
 
+import plotly.graph_objects as go
 
-# Load the CSV file
-data = pd.read_csv('data/validation_loss _txt360_vs_fineweb.csv')
-
-# Create a plotly line chart
-fig = go.Figure()
-
-# Add the line for FineWeb-1.5T
-fig.add_trace(go.Scatter(x=data['Step'], y=data['FineWeb-1.5T'], mode='lines', name='FineWeb-1.5T'))
-
-# Add the line for TxT360
-fig.add_trace(go.Scatter(x=data['Step'], y=data['TxT360'], mode='lines', name='TxT360'))
+# Data
+steps = [5000, 10000, 15000, 20000, 25000, 30000, 35000, 40000, 45000, 50000, 
+         55000, 60000, 65000, 70000, 75000, 80000, 85000, 90000, 95000, 100000, 
+         105000, 110000, 115000, 120000, 125000, 130000, 135000, 140000, 145000, 
+         150000, 155000, 160000, 165000, 170000, 175000, 180000, 185000, 190000, 
+         195000, 200000, 205000, 210000, 215000, 220000, 225000, 230000, 235000, 
+         240000, 245000, 250000, 255000, 260000, 265000, 270000, 275000, 280000, 
+         285000]
+
+fineweb = [2.911076784, 2.75819993, 2.647450924, 2.588769436, 2.565514088, 
+           2.527409077, 2.506954193, 2.493706465, 2.478432178, 2.476668596, 
+           2.467983723, 2.4843328, 2.439449787, 2.438807011, 2.426213741, 
+           2.459792614, 2.426000357, 2.403300762, 2.399668455, 2.404176235, 
+           2.39425993, 2.406329632, 2.381269455, 2.387765169, 2.373465776, 
+           2.374938488, 2.379047394, 2.370839834, 2.351930141, 2.35353899, 
+           2.356842279, 2.343327522, 2.335564375, 2.337301254, 2.322228193, 
+           2.323165655, 2.309478998, 2.326301336, 2.314562321, 2.280953169, 
+           2.291109324, 2.298957586, 2.282609463, 2.296112061, 2.286119938, 
+           2.279724598, 2.268625498, 2.27303195, 2.254729986, 2.260175228, 
+           2.248331785, 2.235989809, 2.241044521, 2.242579222, 2.216429472, 
+           2.250077009, 2.224117756]
+
+txt360 = [2.589649677, 2.438303471, 2.383416414, 2.337049007, 2.300292492, 
+          2.29057312, 2.285922527, 2.265408278, 2.245058537, 2.24157238, 
+          2.23307991, 2.232925415, 2.226780653, 2.222440243, 2.194804668, 
+          2.210517406, 2.186522722, 2.185292006, 2.184529305, 2.185826778, 
+          2.171881914, 2.182652235, 2.169103146, 2.162784815, 2.165525436, 
+          2.159037828, 2.164080143, 2.143726826, 2.144924164, 2.138051987, 
+          2.138092995, 2.120969057, None, None, None, None, None, None, None, 
+          None, None, None, None, None, None, None, None, None, None, None, 
+          None, None, None, None, None, None, None, None, None, None]
+
+# Plot
+fig_val = go.Figure()
+
+# Add lines
+fig_val.add_trace(go.Scatter(x=steps, y=fineweb, mode='lines', name='FineWeb-1.5T'))
+fig_val.add_trace(go.Scatter(x=steps, y=txt360, mode='lines', name='TxT360'))
 
 # Update layout
-fig.update_layout(
-    title='Validation Loss Comparison: TxT360 vs FineWeb-1.5T',
+fig_val.update_layout(
+    title='Perplexity Across Steps',
     xaxis_title='Steps',
-    yaxis_title='Validation Loss',
-    legend_title='Dataset',
-    template='plotly_white'
+    yaxis_title='Perplexity',
+    legend_title='Models'
 )
 
+# Show plot
+
 # Show the plot
-validation_loss_graph = fig
+validation_loss_graph = fig_val