Training in progress, step 200

README.md

@@ -47,7 +47,6 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- distributed_type: multi-GPU
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - training_steps: 2500
@@ -57,10 +56,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Answer                                                    | Header                                                    | Question                                                  | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:---------------------------------------------------------:|:---------------------------------------------------------:|:---------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 0.07          | 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              |
+| 0.0912        | 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              |
-| 0.0001        | 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           | 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              |
 | 0.0           | 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              |
@@ -75,5 +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.1719323917.Allianz-Editique.1766.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875bc68848ee9bf9259f91e97dc40ddb969529964c978017d8db0ffa61eae8e4
-size 13780
+oid sha256:3e3067420d3e6b6ec12f8d7e424127f0a85a351d1bdad6646c3b701791eb7b9e
+size 14134

logs/events.out.tfevents.1719324305.Allianz-Editique.1842.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:180622f6a913af323ce7245b833d85ba8852d3fe88bc6d60674dc010637384ec
+size 5915

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:141dc17fa3e798f3bb15d8f8049f16143c3144a82b8f6365c88e9868a29ff9b1
+oid sha256:1414e7b30fdaf7989e1fbddb4ec727edef4d8e290ae6b6a453acea7d61463190
 size 520727564