Training in progress epoch 4

README.md

@@ -14,16 +14,16 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1028
-- Validation Loss: 0.2179
-- Train Accuracy: 0.9222
-- Train Precision: [0.92357119 0.90951638]
-- Train Precision W: 0.9214
-- Train Recall: [0.98949275 0.56328502]
-- Train Recall W: 0.9222
-- Train F1: [0.95539619 0.69570406]
-- Train F1 W: 0.9144
-- Epoch: 3
+- Train Loss: 0.0554
+- Validation Loss: 0.1492
+- Train Accuracy: 0.9475
+- Train Precision: [0.96816208 0.83641675]
+- Train Precision W: 0.9474
+- Train Recall: [0.96956522 0.82995169]
+- Train Recall W: 0.9475
+- Train F1: [0.96886314 0.83317168]
+- Train F1 W: 0.9474
+- Epoch: 4
 
 ## Model description
 
@@ -52,6 +52,7 @@ The following hyperparameters were used during training:
 | 0.4028     | 0.2959          | 0.8429         | [0.84274809 1.        ] | 0.8676            | [1.         0.00483092] | 0.8429         | [0.91466446 0.00961538] | 0.7718     | 1     |
 | 0.1572     | 0.1686          | 0.9315         | [0.94412331 0.8463357 ] | 0.9287            | [0.97644928 0.69178744] | 0.9315         | [0.96001425 0.76129718] | 0.9286     | 2     |
 | 0.1028     | 0.2179          | 0.9222         | [0.92357119 0.90951638] | 0.9214            | [0.98949275 0.56328502] | 0.9222         | [0.95539619 0.69570406] | 0.9144     | 3     |
+| 0.0554     | 0.1492          | 0.9475         | [0.96816208 0.83641675] | 0.9474            | [0.96956522 0.82995169] | 0.9475         | [0.96886314 0.83317168] | 0.9474     | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad524341f454f097e8fdbdd21cb4b3be00960db47ab6fb47aabfc5338f7b6342
+oid sha256:0b4f72c620b2ac1bc55d72344bb00320a9bd80293d5bf6eccb39aaff59882654
 size 439697688