End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/switch-base-8](https://huggingface.co/google/switch-base-8) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1072
-- F1: 89.6358
-- Gen Len: 2.4954
+- Loss: 1.3615
+- F1: 8.0852
+- Gen Len: 2.0
 
 ## Model description
 
@@ -39,8 +39,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0003
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

logs/events.out.tfevents.1727906983.nova22-gpu-1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18eea4c92e7d05fdc270fa38d4136831e00170c817420931cab98c1a40bc4df6
-size 6396
+oid sha256:7ee238e6196bb5f35bef2f08c2045c932eb44bab2ccda5d873869b602dc6d7f8
+size 6951

logs/events.out.tfevents.1727907132.nova22-gpu-1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54628ba4a4e0f65e978ec0b4f7b4e4912216fbecf5f1f18050cbb0731446b93e
+size 40