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: 0.1312
-- Train Accuracy: 0.9511
-- Train F1 M: 0.5451
-- Train Precision M: 0.3969
-- Train Recall M: 0.9273
-- Validation Loss: 0.2125
-- Validation Accuracy: 0.9307
-- Validation F1 M: 0.5571
-- Validation Precision M: 0.4017
-- Validation Recall M: 0.9523
-- Epoch: 2
+- Train Loss: 0.0871
+- Train Accuracy: 0.9690
+- Train F1 M: 0.5547
+- Train Precision M: 0.4007
+- Train Recall M: 0.9557
+- Validation Loss: 0.2417
+- Validation Accuracy: 0.9301
+- Validation F1 M: 0.5565
+- Validation Precision M: 0.4013
+- Validation Recall M: 0.9547
+- Epoch: 3
 
 ## Model description
 
@@ -54,6 +54,7 @@ The following hyperparameters were used during training:
 | 0.3576     | 0.8399         | 0.4604     | 0.3607            | 0.7042         | 0.2825          | 0.8997              | 0.5635          | 0.4127                 | 0.9300              | 0     |
 | 0.2012     | 0.9274         | 0.5204     | 0.3849            | 0.8616         | 0.2103          | 0.9175              | 0.5451          | 0.3970                 | 0.9095              | 1     |
 | 0.1312     | 0.9511         | 0.5451     | 0.3969            | 0.9273         | 0.2125          | 0.9307              | 0.5571          | 0.4017                 | 0.9523              | 2     |
+| 0.0871     | 0.9690         | 0.5547     | 0.4007            | 0.9557         | 0.2417          | 0.9301              | 0.5565          | 0.4013                 | 0.9547              | 3     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16fd0227a992342dac2209adb316f7c7fd61aa735da6071ab8ab9a72f73024ec
+oid sha256:812c632c4dfcabbd271dff2d5216e69bdea18e3a3d996c51d033c33349e2cad5
 size 438223128