End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 5.4869
+- Loss: 6.2957
 
 ## Model description
 
@@ -42,22 +42,21 @@ The following hyperparameters were used during training:
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 10
-- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 15   | 5.8127          |
-| No log        | 2.0   | 30   | 5.5716          |
-| No log        | 3.0   | 45   | 5.4681          |
-| No log        | 4.0   | 60   | 5.4220          |
-| No log        | 5.0   | 75   | 5.4095          |
-| No log        | 6.0   | 90   | 5.4248          |
-| No log        | 7.0   | 105  | 5.4380          |
-| No log        | 8.0   | 120  | 5.4627          |
-| No log        | 9.0   | 135  | 5.4778          |
-| No log        | 10.0  | 150  | 5.4869          |
+| No log        | 1.0   | 15   | 5.5286          |
+| No log        | 2.0   | 30   | 5.6499          |
+| No log        | 3.0   | 45   | 5.7365          |
+| No log        | 4.0   | 60   | 5.8599          |
+| No log        | 5.0   | 75   | 5.9417          |
+| No log        | 6.0   | 90   | 6.0606          |
+| No log        | 7.0   | 105  | 6.1215          |
+| No log        | 8.0   | 120  | 6.1976          |
+| No log        | 9.0   | 135  | 6.2711          |
+| No log        | 10.0  | 150  | 6.2957          |
 
 
 ### Framework versions