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: 0.0818
-- Validation Loss: 0.1851
-- Train Accuracy: 0.9411
-- Train Precision: [0.91691395 1.        ]
-- Train Precision W: 0.9460
-- Train Recall: [1.    0.832]
-- Train Recall W: 0.9411
-- Train F1: [0.95665635 0.90829694]
-- Train F1 W: 0.9397
-- Epoch: 3
+- Train Loss: 0.0511
+- Validation Loss: 0.1053
+- Train Accuracy: 0.9671
+- Train Precision: [0.9526749 0.9978022]
+- Train Precision W: 0.9685
+- Train Recall: [0.99892125 0.908     ]
+- Train Recall W: 0.9671
+- Train F1: [0.97525013 0.95078534]
+- Train F1 W: 0.9667
+- Epoch: 4
 
 ## Model description
 
@@ -52,6 +52,7 @@ The following hyperparameters were used during training:
 | 0.2010     | 0.7379          | 0.7400         | [0.71450617 0.99236641] | 0.8119            | [0.99892125 0.26      ] | 0.7400         | [0.83310841 0.41204437] | 0.6856     | 1     |
 | 0.1127     | 0.4136          | 0.7982         | [0.76339654 0.9953271 ] | 0.8447            | [0.99892125 0.426     ] | 0.7982         | [0.86542056 0.59663866] | 0.7712     | 2     |
 | 0.0818     | 0.1851          | 0.9411         | [0.91691395 1.        ] | 0.9460            | [1.    0.832]           | 0.9411         | [0.95665635 0.90829694] | 0.9397     | 3     |
+| 0.0511     | 0.1053          | 0.9671         | [0.9526749 0.9978022]   | 0.9685            | [0.99892125 0.908     ] | 0.9671         | [0.97525013 0.95078534] | 0.9667     | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c5e8d0af3c121156cef059c098d6cd736747f26b1bdbc819ee17407a404b2e3
+oid sha256:1e980d1c71f4cba9ae27d470f1930d653dfb74c040ec577b6c427d4cb4992a3d
 size 439697688