End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4249
+- Loss: 0.3928
 
 ## Model description
 
@@ -40,15 +40,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.5148        | 1.0   | 1047 | 0.4258          |
-| 0.3212        | 2.0   | 2094 | 0.3174          |
-| 0.2469        | 3.0   | 3141 | 0.4249          |
+| 0.5122        | 1.0   | 1047 | 0.4682          |
+| 0.3142        | 2.0   | 2094 | 0.3928          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334e24fbb266066709a2dc787133cd43d54ef23164e4b74020bd165027d23c64
+oid sha256:185169f8f55757f9ce8353c7b11af60d1765b93bcb0c178eb07f213bfec76482
 size 903840728

runs/May28_01-49-17_d265e390a061/events.out.tfevents.1716860959.d265e390a061.24.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f93ec7654c40330f5aaeeb288b0594fec7dc0cfad40bd1ef44243c729c303b2
-size 5826
+oid sha256:ffae07b5d76087f116b33f20fa2357d8e6101b8c3f391d35ce22390dcbd20e6d
+size 6451