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-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0305
-- Train Accuracy: 0.9912
-- Train F1 M: 0.5630
-- Train Precision M: 0.4059
-- Train Recall M: 0.9778
-- Validation Loss: 0.0696
-- Validation Accuracy: 0.9779
-- Validation F1 M: 0.5517
-- Validation Precision M: 0.4013
-- Validation Recall M: 0.9580
-- Epoch: 2
+- Train Loss: 0.0150
+- Train Accuracy: 0.9951
+- Train F1 M: 0.5657
+- Train Precision M: 0.4067
+- Train Recall M: 0.9873
+- Validation Loss: 0.1309
+- Validation Accuracy: 0.9655
+- Validation F1 M: 0.5737
+- Validation Precision M: 0.4163
+- Validation Recall M: 0.9980
+- Epoch: 3
 
 ## Model description
 
@@ -54,6 +54,7 @@ The following hyperparameters were used during training:
 | 0.1966     | 0.9215         | 0.4030     | 0.3067            | 0.6414         | 0.0842          | 0.9708              | 0.5427          | 0.4013                 | 0.9115              | 0     |
 | 0.0631     | 0.9799         | 0.5517     | 0.4014            | 0.9425         | 0.0667          | 0.9726              | 0.5583          | 0.4067                 | 0.9621              | 1     |
 | 0.0305     | 0.9912         | 0.5630     | 0.4059            | 0.9778         | 0.0696          | 0.9779              | 0.5517          | 0.4013                 | 0.9580              | 2     |
+| 0.0150     | 0.9951         | 0.5657     | 0.4067            | 0.9873         | 0.1309          | 0.9655              | 0.5737          | 0.4163                 | 0.9980              | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f3906a57c3d0da1bfd7501058e0c1ce89f52fb215f811808be185f65979f47
+oid sha256:6725a30e6f24314b2e26ca0199d3b6fe545f6849354a6a32b6c04a489eb73c47
 size 438223128