Training in progress epoch 4

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: 0.0845
-- Train Accuracy: 0.9688
-- Train F1 M: 0.5596
-- Train Precision M: 0.4031
-- Train Recall M: 0.9720
-- Validation Loss: 0.2147
-- Validation Accuracy: 0.9222
-- Validation F1 M: 0.5715
-- Validation Precision M: 0.4109
-- Validation Recall M: 0.9829
-- Epoch: 3
+- Train Loss: 0.0547
+- Train Accuracy: 0.9798
+- Train F1 M: 0.5617
+- Train Precision M: 0.4043
+- Train Recall M: 0.9814
+- Validation Loss: 0.2571
+- Validation Accuracy: 0.9215
+- Validation F1 M: 0.5710
+- Validation Precision M: 0.4102
+- Validation Recall M: 0.9854
+- Epoch: 4
 
 ## Model description
 
@@ -55,6 +55,7 @@ The following hyperparameters were used during training:
 | 0.1901     | 0.9290         | 0.5345     | 0.3949            | 0.8907         | 0.2162          | 0.9274              | 0.5642          | 0.4060                 | 0.9693              | 1     |
 | 0.1235     | 0.9545         | 0.5556     | 0.4028            | 0.9576         | 0.1969          | 0.9228              | 0.5681          | 0.4118                 | 0.9651              | 2     |
 | 0.0845     | 0.9688         | 0.5596     | 0.4031            | 0.9720         | 0.2147          | 0.9222              | 0.5715          | 0.4109                 | 0.9829              | 3     |
+| 0.0547     | 0.9798         | 0.5617     | 0.4043            | 0.9814         | 0.2571          | 0.9215              | 0.5710          | 0.4102                 | 0.9854              | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ac1cd61633c5442779cbf60c4cde08ced192068fb761a1a977164bb316a391
+oid sha256:b53c710da6e3f60fb4a8bc38d0b49fdc1c583dec92191f3c346297dc10219b23
 size 1341127728