Training completed

README.md

@@ -18,10 +18,10 @@ 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: 0.5658
-- Rouge1: 0.4914
-- Rouge2: 0.3287
-- Rougel: 0.4691
+- Loss: 0.0538
+- Rouge1: 0.5076
+- Rouge2: 0.2548
+- Rougel: 0.4743
 
 ## Model description
 
@@ -52,13 +52,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
-|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
-| No log        | 0.9935 | 77   | 0.4256          | 0.4794 | 0.3497 | 0.4794 |
-| No log        | 2.0    | 155  | 0.4503          | 0.4979 | 0.3557 | 0.4779 |
-| No log        | 2.9935 | 232  | 0.5194          | 0.4872 | 0.3525 | 0.4827 |
-| No log        | 4.0    | 310  | 0.5605          | 0.4903 | 0.3220 | 0.4649 |
-| No log        | 4.9677 | 385  | 0.5658          | 0.4914 | 0.3287 | 0.4691 |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
+| No log        | 1.0   | 70   | 0.0628          | 0.4870 | 0.2269 | 0.4475 |
+| No log        | 2.0   | 140  | 0.0566          | 0.4913 | 0.2367 | 0.4607 |
+| No log        | 3.0   | 210  | 0.0545          | 0.4972 | 0.2484 | 0.4667 |
+| No log        | 4.0   | 280  | 0.0544          | 0.5023 | 0.2586 | 0.4749 |
+| No log        | 5.0   | 350  | 0.0538          | 0.5076 | 0.2548 | 0.4743 |
 
 
 ### Framework versions