Model save

README.md

@@ -16,8 +16,8 @@ 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: 53.7912
-- Bleu Score: {'bleu': 0.0, 'precisions': [0.5786516853932584, 0.0, 0.0, 0.0], 'brevity_penalty': 0.0015814103520051996, 'length_ratio': 0.13423831070889894, 'translation_length': 712, 'reference_length': 5304}
+- Loss: 54.5580
+- Bleu Score: {'bleu': 0.0, 'precisions': [0.0, 0.0, 0.0, 0.0], 'brevity_penalty': 5.701223175160721e-08, 'length_ratio': 0.05656108597285068, 'translation_length': 300, 'reference_length': 5304}
 
 ## Model description
 
@@ -46,11 +46,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu Score                                                                                                                                                                                           |
-|:-------------:|:-----:|:----:|:---------------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
-| 611.4564      | 1.0   | 63   | 163.9706        | {'bleu': 0.0, 'precisions': [0.0, 0.0, 0.0, 0.0], 'brevity_penalty': 5.701223175160721e-08, 'length_ratio': 0.05656108597285068, 'translation_length': 300, 'reference_length': 5304}                |
-| 130.132       | 2.0   | 126  | 63.4101         | {'bleu': 0.0, 'precisions': [0.6240601503759399, 0.0, 0.0, 0.0], 'brevity_penalty': 0.0035294383040863748, 'length_ratio': 0.1504524886877828, 'translation_length': 798, 'reference_length': 5304}  |
-| 57.0285       | 3.0   | 189  | 53.7912         | {'bleu': 0.0, 'precisions': [0.5786516853932584, 0.0, 0.0, 0.0], 'brevity_penalty': 0.0015814103520051996, 'length_ratio': 0.13423831070889894, 'translation_length': 712, 'reference_length': 5304} |
+| Training Loss | Epoch | Step | Validation Loss | Bleu Score                                                                                                                                                                            |
+|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
+| 620.8193      | 1.0   | 63   | 177.3467        | {'bleu': 0.0, 'precisions': [0.0, 0.0, 0.0, 0.0], 'brevity_penalty': 5.701223175160721e-08, 'length_ratio': 0.05656108597285068, 'translation_length': 300, 'reference_length': 5304} |
+| 140.721       | 2.0   | 126  | 65.7476         | {'bleu': 0.0, 'precisions': [0.0, 0.0, 0.0, 0.0], 'brevity_penalty': 5.701223175160721e-08, 'length_ratio': 0.05656108597285068, 'translation_length': 300, 'reference_length': 5304} |
+| 60.0697       | 3.0   | 189  | 54.5580         | {'bleu': 0.0, 'precisions': [0.0, 0.0, 0.0, 0.0], 'brevity_penalty': 5.701223175160721e-08, 'length_ratio': 0.05656108597285068, 'translation_length': 300, 'reference_length': 5304} |
 
 
 ### Framework versions

runs/Oct20_18-07-40_b943ff2b5783/events.out.tfevents.1729447663.b943ff2b5783.433.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3a0bac245e9c5fc15a01ff86ad465a6840dcc73444a7fd5a0dcce1f6a8921e8
-size 264036
+oid sha256:3b6f83c439b41afc30ddbb11a776df2857aead40a8bb3d268d245e616f2ce981
+size 264661

runs/Oct20_18-07-40_b943ff2b5783/events.out.tfevents.1729448748.b943ff2b5783.433.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6089235bbd2942a115cb1fdfc189bb185f768ed4465b16e3c178274e81ebb07c
+size 359