Model save

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dandelin/vilt-b32-mlm](https://huggingface.co/dandelin/vilt-b32-mlm) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4644
+- Loss: 38.8391
 
 ## Model description
 
@@ -35,21 +35,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 3e-05
 - train_batch_size: 8
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.4691        | 1.0   | 250  | 0.3940          |
-| 0.3872        | 2.0   | 500  | 0.4159          |
-| 0.3803        | 3.0   | 750  | 0.4644          |
+| No log        | 1.0   | 38   | 118.6701        |
+| 181.5151      | 2.0   | 76   | 62.2544         |
+| 64.466        | 3.0   | 114  | 43.5740         |
+| 40.2832       | 4.0   | 152  | 38.8391         |
 
 
 ### Framework versions

runs/Oct18_10-47-34_4138cf165407/events.out.tfevents.1729248459.4138cf165407.464.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc01edf7acab2074cffc431f13c49889c5f929269e3aef241bf1552c0dadff1
-size 76180
+oid sha256:78288500641c367a349e317dc88fdc9c433900d82c6cbd548cae1381bc627a25
+size 76805