End of training

README.md

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0099
+- Loss: 0.0003
 - Recall: 1.0
-- Precision: 0.9565
-- F5: 0.9983
+- Precision: 1.0
+- F5: 1.0
 
 ## Model description
 
@@ -56,9 +56,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Recall | Precision | F5     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|
-| 0.0007        | 1.0   | 100  | 0.0089          | 1.0    | 0.9167    | 0.9965 |
-| 0.0006        | 2.0   | 200  | 0.0143          | 1.0    | 0.9565    | 0.9983 |
-| 0.0209        | 3.0   | 300  | 0.0099          | 1.0    | 0.9565    | 0.9983 |
+| 0.0646        | 1.0   | 100  | 0.0084          | 1.0    | 0.9630    | 0.9985 |
+| 0.0014        | 2.0   | 200  | 0.0003          | 1.0    | 1.0       | 1.0    |
+| 0.0005        | 3.0   | 300  | 0.0003          | 1.0    | 1.0       | 1.0    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ef91a0074cf9dd29436159d242de520766ab2dc69397e616d6ccb3a2ab6eb3
+oid sha256:cbcac3c05e98647c678e60e5ad98444b8f78a38541f9e6c7c9e0eb8b576a92f8
 size 592370940

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb1d413ffa0e523fdf2f1f21a54da1346cab70cd8ff75241d5f79695f678ee21
+oid sha256:50c5bb39a0de301af4f4bda3358efbd4e0a49f4d96b35f7310f6406f725896a0
 size 4920