Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9285526315789474
+      value: 0.9294736842105263
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [oferweintraub/bert-base-finance-sentiment-noisy-search](https://huggingface.co/oferweintraub/bert-base-finance-sentiment-noisy-search) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9286
+- accuracy: 0.9295
 
 ## Model description
 
@@ -65,11 +65,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.1978   | None       | 0     |
-| 0.9143   | 0.3407     | 0     |
-| 0.9209   | 0.2350     | 1     |
-| 0.9272   | 0.2142     | 2     |
-| 0.9286   | 0.2033     | 3     |
+| 0.2697   | None       | 0     |
+| 0.9113   | 0.3277     | 0     |
+| 0.9212   | 0.2316     | 1     |
+| 0.9261   | 0.2101     | 2     |
+| 0.9295   | 0.1993     | 3     |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e58087b2dfedfd561ef75e305f15acdb8362106caf9652c1ed735c133e6b5674
+oid sha256:f53e79d8e48d60673a3de66d4579a58b7ea11511df095fa4170019b55c4ef4c6
 size 166552