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: 0.4507
-- Train End Logits Accuracy: 0.8620
-- Train Start Logits Accuracy: 0.9018
+- Train Loss: 0.4459
+- Train End Logits Accuracy: 0.8633
+- Train Start Logits Accuracy: 0.8986
 - Validation Loss: 0.4616
 - Validation End Logits Accuracy: 0.8570
 - Validation Start Logits Accuracy: 0.9072
-- Epoch: 1
+- Epoch: 2
 
 ## Model description
 
@@ -49,6 +49,7 @@ The following hyperparameters were used during training:
 |:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
 | 0.4434     | 0.8660                    | 0.9037                      | 0.4616          | 0.8570                         | 0.9072                           | 0     |
 | 0.4507     | 0.8620                    | 0.9018                      | 0.4616          | 0.8570                         | 0.9072                           | 1     |
+| 0.4459     | 0.8633                    | 0.8986                      | 0.4616          | 0.8570                         | 0.9072                           | 2     |
 
 
 ### Framework versions

train/events.out.tfevents.1692008748.f7ac9471e4a4.1550.2.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f01a0eb0bd57870673dd17593de203085e8e19c2646159e40f1d5f457f811d3
-size 2645650
+oid sha256:437255517a96dcfc4be9627e6654f07eadd2bd698057b1cbc284eaf4c610573f
+size 2645963

validation/events.out.tfevents.1692009299.f7ac9471e4a4.1550.3.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7bba97c3bee899bb9fc9d821b873a137c831308ad1a5794429e03312919442
-size 1136
+oid sha256:9c5c7d1102e909b81e5fd5b2570bd21f2afffc257b11e6b3d696359ab2a52747
+size 1668