gpt_SmallEfficientModel_round1_iter2_loss_average

training_summary_gpt_SmallEfficientModel_round1_iter2_loss_average.txt

@@ -0,0 +1,14 @@
+Model: gpt_SmallEfficientModel
+Optimizer: adamw, LR: 2e-05
+Best Val Loss: 3.6362, Test Loss: 3.6421
+Epoch 1: Train Loss: 0.2744, Val Loss: 4.0079
+Epoch 2: Train Loss: 0.2489, Val Loss: 3.9518
+Epoch 3: Train Loss: 0.2453, Val Loss: 3.8867
+Epoch 4: Train Loss: 0.2400, Val Loss: 3.7853
+Epoch 5: Train Loss: 0.2345, Val Loss: 3.7175
+Epoch 6: Train Loss: 0.2311, Val Loss: 3.6740
+Epoch 7: Train Loss: 0.2292, Val Loss: 3.6579
+Epoch 8: Train Loss: 0.2283, Val Loss: 3.6433
+Epoch 9: Train Loss: 0.2278, Val Loss: 3.6362
+Epoch 10: Train Loss: 0.2276, Val Loss: 3.6429
+Final Test Loss: 3.6421