Training in progress epoch 2

README.md

@@ -15,13 +15,13 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.4474
-- Train End Logits Accuracy: 0.8623
-- Train Start Logits Accuracy: 0.8979
+- Train Loss: 0.4498
+- Train End Logits Accuracy: 0.8587
+- Train Start Logits Accuracy: 0.9015
 - Validation Loss: 0.4786
 - Validation End Logits Accuracy: 0.8479
 - Validation Start Logits Accuracy: 0.9098
-- Epoch: 1
+- Epoch: 2
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
 | 0.4434     | 0.8624                    | 0.9020                      | 0.4786          | 0.8479                         | 0.9098                           | 0     |
 | 0.4474     | 0.8623                    | 0.8979                      | 0.4786          | 0.8479                         | 0.9098                           | 1     |
+| 0.4498     | 0.8587                    | 0.9015                      | 0.4786          | 0.8479                         | 0.9098                           | 2     |
 
 
 ### Framework versions

train/events.out.tfevents.1693286096.f64460db9a5c.440.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1156744060b671abe18118bf2c5253a53ad432d6001973d9e8753f660195a2
-size 2645650
+oid sha256:e17c9f10ea058d2a840fb3509e6f3b45f646352543f10ce85d3abf5b2dc5e784
+size 2645963

validation/events.out.tfevents.1693286667.f64460db9a5c.440.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c87a668da47dab77c7ca9e5d07d1a477e81d3de849bd556d1e41f7ef55bc0803
-size 1136
+oid sha256:75800ddba1af727801223256ce6fa5e03670e3e5b816239b089dde9c184fc564
+size 1668