|
Model: gpt_SmallEfficientModel |
|
Optimizer: adamw, LR: 2e-05 |
|
Best Val Loss: 3.4031, Test Loss: 3.3931 |
|
Epoch 1: Train Loss: 5.3849, Val Loss: 4.0624 |
|
Epoch 2: Train Loss: 3.8170, Val Loss: 3.6965 |
|
Epoch 3: Train Loss: 3.6649, Val Loss: 3.6362 |
|
Epoch 4: Train Loss: 3.6286, Val Loss: 3.6178 |
|
Epoch 5: Train Loss: 3.6149, Val Loss: 3.6134 |
|
Epoch 6: Train Loss: 3.6077, Val Loss: 3.6028 |
|
Epoch 7: Train Loss: 3.6005, Val Loss: 3.5969 |
|
Epoch 8: Train Loss: 3.5920, Val Loss: 3.5864 |
|
Epoch 9: Train Loss: 3.5823, Val Loss: 3.5775 |
|
Epoch 10: Train Loss: 3.5706, Val Loss: 3.5647 |
|
Epoch 11: Train Loss: 3.5560, Val Loss: 3.5476 |
|
Epoch 12: Train Loss: 3.5397, Val Loss: 3.5344 |
|
Epoch 13: Train Loss: 3.5237, Val Loss: 3.5192 |
|
Epoch 14: Train Loss: 3.5075, Val Loss: 3.5037 |
|
Epoch 15: Train Loss: 3.4936, Val Loss: 3.4909 |
|
Epoch 16: Train Loss: 3.4802, Val Loss: 3.4773 |
|
Epoch 17: Train Loss: 3.4689, Val Loss: 3.4657 |
|
Epoch 18: Train Loss: 3.4587, Val Loss: 3.4583 |
|
Epoch 19: Train Loss: 3.4497, Val Loss: 3.4535 |
|
Epoch 20: Train Loss: 3.4440, Val Loss: 3.4459 |
|
Epoch 21: Train Loss: 3.4361, Val Loss: 3.4376 |
|
Epoch 22: Train Loss: 3.4308, Val Loss: 3.4336 |
|
Epoch 23: Train Loss: 3.4259, Val Loss: 3.4319 |
|
Epoch 24: Train Loss: 3.4220, Val Loss: 3.4285 |
|
Epoch 25: Train Loss: 3.4180, Val Loss: 3.4233 |
|
Epoch 26: Train Loss: 3.4154, Val Loss: 3.4189 |
|
Epoch 27: Train Loss: 3.4139, Val Loss: 3.4203 |
|
Epoch 28: Train Loss: 3.4102, Val Loss: 3.4189 |
|
Epoch 29: Train Loss: 3.4081, Val Loss: 3.4166 |
|
Epoch 30: Train Loss: 3.4067, Val Loss: 3.4123 |
|
Epoch 31: Train Loss: 3.4055, Val Loss: 3.4117 |
|
Epoch 32: Train Loss: 3.4040, Val Loss: 3.4101 |
|
Epoch 33: Train Loss: 3.4027, Val Loss: 3.4081 |
|
Epoch 34: Train Loss: 3.4014, Val Loss: 3.4103 |
|
Epoch 35: Train Loss: 3.4006, Val Loss: 3.4087 |
|
Epoch 36: Train Loss: 3.4000, Val Loss: 3.4088 |
|
Epoch 37: Train Loss: 3.3995, Val Loss: 3.4087 |
|
Epoch 38: Train Loss: 3.3990, Val Loss: 3.4074 |
|
Epoch 39: Train Loss: 3.3985, Val Loss: 3.4071 |
|
Epoch 40: Train Loss: 3.3981, Val Loss: 3.4089 |
|
Epoch 41: Train Loss: 3.3980, Val Loss: 3.4046 |
|
Epoch 42: Train Loss: 3.3978, Val Loss: 3.4055 |
|
Epoch 43: Train Loss: 3.3973, Val Loss: 3.4067 |
|
Epoch 44: Train Loss: 3.3976, Val Loss: 3.4031 |
|
Epoch 45: Train Loss: 3.3974, Val Loss: 3.4044 |
|
Epoch 46: Train Loss: 3.3968, Val Loss: 3.4044 |
|
Epoch 47: Train Loss: 3.3967, Val Loss: 3.4056 |
|
Epoch 48: Train Loss: 3.3969, Val Loss: 3.4039 |
|
Epoch 49: Train Loss: 3.3966, Val Loss: 3.4050 |
|
Epoch 50: Train Loss: 3.3970, Val Loss: 3.4032 |
|
Final Test Loss: 3.3931 |