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: 0.2254
-- Train Accuracy: 0.9128
-- Train F1 M: 0.5069
-- Train Precision M: 0.3838
-- Train Recall M: 0.8028
-- Validation Loss: 0.2388
-- Validation Accuracy: 0.9090
-- Validation F1 M: 0.5468
-- Validation Precision M: 0.4009
-- Validation Recall M: 0.9053
-- Epoch: 2
+- Train Loss: 0.1873
+- Train Accuracy: 0.9303
+- Train F1 M: 0.5203
+- Train Precision M: 0.3889
+- Train Recall M: 0.8490
+- Validation Loss: 0.2200
+- Validation Accuracy: 0.9149
+- Validation F1 M: 0.5561
+- Validation Precision M: 0.4075
+- Validation Recall M: 0.9235
+- Epoch: 3
 
 ## Model description
 
@@ -54,6 +54,7 @@ The following hyperparameters were used during training:
 | 0.4434     | 0.8014         | 0.4236     | 0.3661            | 0.5865         | 0.2743          | 0.8872              | 0.4964          | 0.3787                 | 0.7644              | 0     |
 | 0.2804     | 0.8901         | 0.4898     | 0.3778            | 0.7488         | 0.2824          | 0.8879              | 0.5567          | 0.4181                 | 0.8782              | 1     |
 | 0.2254     | 0.9128         | 0.5069     | 0.3838            | 0.8028         | 0.2388          | 0.9090              | 0.5468          | 0.4009                 | 0.9053              | 2     |
+| 0.1873     | 0.9303         | 0.5203     | 0.3889            | 0.8490         | 0.2200          | 0.9149              | 0.5561          | 0.4075                 | 0.9235              | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa616b8a6a18826a0f7d77aa3e6ae5675ac9271ba61b015078d8c00e0df5e49c
+oid sha256:537e2e283c42ae45b995e8cbeae67dd1eea2f4c799efdaea614acc6ffdbfc9a0
 size 1341127728