Training in progress epoch 3

README.md

@@ -15,17 +15,17 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1392
-- Train Accuracy: 0.9467
-- Train F1 M: 0.5266
-- Train Precision M: 0.3881
-- Train Recall M: 0.8670
-- Validation Loss: 0.2310
-- Validation Accuracy: 0.9057
-- Validation F1 M: 0.5617
-- Validation Precision M: 0.4162
-- Validation Recall M: 0.9092
-- Epoch: 2
+- Train Loss: 0.1136
+- Train Accuracy: 0.9570
+- Train F1 M: 0.5387
+- Train Precision M: 0.3946
+- Train Recall M: 0.9100
+- Validation Loss: 0.2265
+- Validation Accuracy: 0.9228
+- Validation F1 M: 0.5653
+- Validation Precision M: 0.4119
+- Validation Recall M: 0.9501
+- Epoch: 3
 
 ## Model description
 
@@ -54,6 +54,7 @@ The following hyperparameters were used during training:
 | 0.3898     | 0.8294         | 0.3411     | 0.2894            | 0.4810         | 0.2440          | 0.8984              | 0.5087          | 0.3814                 | 0.8079              | 0     |
 | 0.2070     | 0.9228         | 0.4927     | 0.3723            | 0.7869         | 0.1911          | 0.9268              | 0.5222          | 0.3853                 | 0.8520              | 1     |
 | 0.1392     | 0.9467         | 0.5266     | 0.3881            | 0.8670         | 0.2310          | 0.9057              | 0.5617          | 0.4162                 | 0.9092              | 2     |
+| 0.1136     | 0.9570         | 0.5387     | 0.3946            | 0.9100         | 0.2265          | 0.9228              | 0.5653          | 0.4119                 | 0.9501              | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3324851ee0d889d07b04bb635e140732b9ff189a2d07c0944bee523c8519de
+oid sha256:c60a5b2e10f0f7f4cb389979acac3d0d06cee0036ecfeee8f25b8cf22efee2fa
 size 1341127728