Model save

README.md

@@ -3,6 +3,9 @@ license: apache-2.0
 base_model: google-bert/bert-base-cased
 tags:
 - generated_from_trainer
+metrics:
+- f1
+- recall
 model-index:
 - name: bert-base-cased
   results: []
@@ -15,10 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9738
-- Icm: 0.0090
-- Icmnorm: 0.5045
-- Fmeasure: 0.6624
+- Loss: 0.6080
+- F1 Macro: 0.9169
+- F1: 0.9466
+- F1 Neg: 0.8872
+- Acc: 0.9275
+- Prec: 0.9380
+- Recall: 0.9554
+- Mcc: 0.8341
+- Millor Epoca: 3
 
 ## Model description
 
@@ -44,16 +52,20 @@ The following hyperparameters were used during training:
 - distributed_type: multi-GPU
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 7
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Icm     | Icmnorm | Fmeasure |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:--------:|
-| 0.6048        | 1.0   | 771  | 0.7006          | -0.0220 | 0.4888  | 0.6544   |
-| 0.2473        | 2.0   | 1542 | 1.4364          | -0.0389 | 0.4803  | 0.6355   |
-| 0.0964        | 3.0   | 2313 | 1.9738          | 0.0090  | 0.5045  | 0.6624   |
+| Training Loss | Epoch | Step  | Validation Loss | F1 Macro | F1     | F1 Neg | Acc    | Prec   | Recall | Mcc    | Millor Epoca |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|:------------:|
+| 0.2756        | 1.0   | 1698  | 0.3780          | 0.9135   | 0.9451 | 0.8819 | 0.925  | 0.9314 | 0.9591 | 0.8279 | 1            |
+| 0.119         | 2.0   | 3396  | 0.5107          | 0.9158   | 0.9436 | 0.8881 | 0.925  | 0.9544 | 0.9331 | 0.8322 | 2            |
+| 0.0398        | 3.0   | 5094  | 0.6080          | 0.9169   | 0.9466 | 0.8872 | 0.9275 | 0.9380 | 0.9554 | 0.8341 | 3            |
+| 0.022         | 4.0   | 6792  | 0.7176          | 0.9152   | 0.9440 | 0.8864 | 0.925  | 0.9476 | 0.9405 | 0.8305 | 3            |
+| 0.0124        | 5.0   | 8490  | 0.8219          | 0.9122   | 0.9423 | 0.8821 | 0.9225 | 0.9440 | 0.9405 | 0.8244 | 3            |
+| 0.0           | 6.0   | 10188 | 1.0603          | 0.9046   | 0.9397 | 0.8696 | 0.9175 | 0.9245 | 0.9554 | 0.8104 | 3            |
+| 0.0018        | 7.0   | 11886 | 0.9280          | 0.9058   | 0.9390 | 0.8726 | 0.9175 | 0.9338 | 0.9442 | 0.8117 | 3            |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65afebadba589e4d251c7ff463a164a4d08a9907ef293ff74dc089222b57545
+oid sha256:bb2003ebc70df477b46421e9d522828ecb22d77c9b2662b79642709c00057067
 size 433270768

runs/Apr26_11-19-57_tardis/events.out.tfevents.1714124576.tardis.176866.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6bb37c89fd2fe157dc98668b70492c13ec2383aac3535dab88042f51f2799e
+size 755