Training in progress, step 200

README.md

@@ -56,14 +56,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Answer                                                    | Header                                                    | Question                                                  | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:---------------------------------------------------------:|:---------------------------------------------------------:|:---------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 0.0615        | 200.0  | 200  | 0.0001          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0659        | 200.0  | 200  | 0.0001          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
 | 0.0001        | 400.0  | 400  | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
 | 0.0001        | 600.0  | 600  | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
 | 0.0           | 800.0  | 800  | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
 | 0.0           | 1000.0 | 1000 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
 | 0.0           | 1200.0 | 1200 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
-| 0.0028        | 1400.0 | 1400 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
-| 0.0           | 1600.0 | 1600 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0001        | 1400.0 | 1400 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0001        | 1600.0 | 1600 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
 | 0.0           | 1800.0 | 1800 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
 | 0.0           | 2000.0 | 2000 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
 | 0.0           | 2200.0 | 2200 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2} | 1.0               | 1.0            | 1.0        | 1.0              |
@@ -74,5 +74,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.41.2
 - Pytorch 2.3.1+cu121
-- Datasets 2.19.2
+- Datasets 2.20.0
 - Tokenizers 0.19.1

logs/events.out.tfevents.1718783264.Allianz-Editique.3718.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16bdc47b68cb743880d91862e8fc32710d44957006aba32819ff3e3ddc4ab46f
-size 13780
+oid sha256:ef18cf976c43083b07f796fc3da28afca70844164ade3589c7ca7a9f1d4764cc
+size 14134

logs/events.out.tfevents.1718783606.Allianz-Editique.3890.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0203f1568f26f655462ca6add8c4f93bd91d23fc48971b87baf94b42fe4c66a4
+size 5915

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d60336016d7aa19b36feb61d96d874c854c519b2ae7c3c946ea1711c2a1357bc
+oid sha256:dc31f9c4701c96876068f9e6a55fbc7472d1a7ef12cbb44bc33d27221a2f5688
 size 520727564