End of training

README.md

@@ -20,13 +20,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-500m-1000g](https://huggingface.co/InstaDeepAI/nucleotide-transformer-500m-1000g) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3625
-- F1 Score: 0.7826
-- Precision: 0.75
-- Recall: 0.8182
-- Accuracy: 0.7458
-- Auc: 0.7890
-- Prc: 0.8030
+- Loss: 1.2825
+- F1 Score: 0.8857
+- Precision: 0.8857
+- Recall: 0.8857
+- Accuracy: 0.8644
+- Auc: 0.875
+- Prc: 0.8717
 
 ## Model description
 
@@ -58,8 +58,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc    | Prc    |
 |:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
-| 0.1744        | 8.3333  | 500  | 2.1832          | 0.7826   | 0.75      | 0.8182 | 0.7458   | 0.7838 | 0.7965 |
-| 0.0           | 16.6667 | 1000 | 2.3625          | 0.7826   | 0.75      | 0.8182 | 0.7458   | 0.7890 | 0.8030 |
+| 0.2054        | 8.3333  | 500  | 1.1524          | 0.8857   | 0.8857    | 0.8857 | 0.8644   | 0.8738 | 0.8703 |
+| 0.0           | 16.6667 | 1000 | 1.2825          | 0.8857   | 0.8857    | 0.8857 | 0.8644   | 0.875  | 0.8717 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e5e477e8ec6e340067a87ac30aa360a7631b2bf90b7e51075cde48ba079d352
+oid sha256:96e3dc611c18f6b399038a5d8b9dcefaf6462f8ee0525e16362e20f40c620096
 size 1921809396