update model card README.md

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3386
+- Loss: 0.1822
 
 ## Model description
 
@@ -38,21 +38,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 60   | 0.4822          |
-| No log        | 2.0   | 120  | 0.3612          |
-| No log        | 3.0   | 180  | 0.3363          |
-| No log        | 4.0   | 240  | 0.3327          |
-| No log        | 5.0   | 300  | 0.3181          |
-| No log        | 6.0   | 360  | 0.3154          |
-| No log        | 7.0   | 420  | 0.3412          |
-| No log        | 8.0   | 480  | 0.3386          |
+| No log        | 1.0   | 60   | 0.2050          |
+| No log        | 2.0   | 120  | 0.1561          |
+| No log        | 3.0   | 180  | 0.1540          |
+| No log        | 4.0   | 240  | 0.1822          |
 
 
 ### Framework versions