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 [cambridgeltl/tacl-bert-base-uncased](https://huggingface.co/cambridgeltl/tacl-bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1111
-- Precision: 0.5074
-- Recall: 0.5881
-- F1: 0.5448
+- Loss: 0.1145
+- Precision: 0.5103
+- Recall: 0.5803
+- F1: 0.5431
 
 ## Model description
 
@@ -52,9 +52,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
-| No log        | 1.0   | 306  | 0.0830          | 0.4479    | 0.5367 | 0.4883 |
-| 0.0865        | 2.0   | 612  | 0.0929          | 0.4781    | 0.5632 | 0.5172 |
-| 0.0865        | 3.0   | 918  | 0.1111          | 0.5074    | 0.5881 | 0.5448 |
+| No log        | 1.0   | 306  | 0.0849          | 0.4564    | 0.5632 | 0.5042 |
+| 0.0884        | 2.0   | 612  | 0.0993          | 0.4838    | 0.6037 | 0.5371 |
+| 0.0884        | 3.0   | 918  | 0.1145          | 0.5103    | 0.5803 | 0.5431 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d30a40022552c1abdcb36a31a6cc356fb0fb8b11cc5e97dadcbe9d98196d0d5
+oid sha256:ec77d30f14ef4bb0a5facb849fa92d6c0f02c6d20aae1c4d71a7078e998357dc
 size 435599164

runs/May19_19-06-29_ad9b2bcda10b/events.out.tfevents.1716145590.ad9b2bcda10b.713.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88714b47bb769405d8696d56b144b08faa3bb9e8b42297a1a10d5e90a7245d0d
-size 5424
+oid sha256:013508e291a85ca6f925bea7d6cd0095437a6b84a5cc3559e4ec0ab0abae2805
+size 6618