Training in progress epoch 4

README.md

@@ -15,12 +15,12 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0483
+- Train Loss: 0.0289
 - Train Accuracy: 0.9036
-- Validation Loss: 0.3294
+- Validation Loss: 0.3406
 - Validation Accuracy: 0.9036
-- Train F1 Macro: 0.8947
-- Epoch: 3
+- Train F1 Macro: 0.8935
+- Epoch: 4
 
 ## Model description
 
@@ -50,6 +50,7 @@ The following hyperparameters were used during training:
 | 0.1773     | 0.9            | 0.2750          | 0.9000              | 0.8893         | 1     |
 | 0.0854     | 0.8976         | 0.3135          | 0.8976              | 0.8847         | 2     |
 | 0.0483     | 0.9036         | 0.3294          | 0.9036              | 0.8947         | 3     |
+| 0.0289     | 0.9036         | 0.3406          | 0.9036              | 0.8935         | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d084c7e1a0c748f806c59ed10d7aa1afc79ff7a88f402544d4275db73db53273
+oid sha256:e4ff5ab914002e555457a7100905140ff12f19481bef221175201fc1f5ae29ed
 size 438226204