update model card README.md

README.md

@@ -19,7 +19,7 @@ model-index:
     metrics:
     - name: Spearmanr
       type: spearmanr
-      value: 0.021589623989593458
+      value: 0.4267265849314744
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [lightonai/RITA_s](https://huggingface.co/lightonai/RITA_s) on the cradle-bio/tape-fluorescence dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6890
-- Spearmanr: 0.0216
+- Loss: 0.7102
+- Spearmanr: 0.4267
 
 ## Model description
 
@@ -52,23 +52,28 @@ The following hyperparameters were used during training:
 - learning_rate: 5e-05
 - train_batch_size: 32
 - eval_batch_size: 32
-- seed: 42
+- seed: 11
 - gradient_accumulation_steps: 128
 - total_train_batch_size: 4096
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Spearmanr |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|
-| 8.0054        | 0.85  | 4    | 6.2486          | 0.1441    |
-| 2.9837        | 1.85  | 8    | 0.8896          | -0.0607   |
-| 0.9845        | 2.85  | 12   | 0.8469          | 0.0705    |
-| 0.9127        | 3.85  | 16   | 0.6862          | 0.0040    |
-| 0.7147        | 4.85  | 20   | 0.6890          | 0.0216    |
+| 4.175         | 0.85  | 4    | 0.8818          | 0.1064    |
+| 1.0481        | 1.85  | 8    | 0.9741          | 0.2075    |
+| 0.959         | 2.85  | 12   | 0.8920          | 0.2026    |
+| 0.9661        | 3.85  | 16   | 0.7124          | 0.0840    |
+| 0.8651        | 4.85  | 20   | 0.7709          | 0.2576    |
+| 0.8415        | 5.85  | 24   | 0.7190          | 0.3494    |
+| 0.8262        | 6.85  | 28   | 0.7110          | 0.3795    |
+| 0.8185        | 7.85  | 32   | 0.7113          | 0.4147    |
+| 0.8173        | 8.85  | 36   | 0.7103          | 0.4245    |
+| 0.6925        | 9.85  | 40   | 0.7102          | 0.4267    |
 
 
 ### Framework versions