aeg_model_gr_tr_en

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1787
+- Loss: 0.0376
 
 ## Model description
 
@@ -41,15 +41,16 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6879        | 1.0   | 2500 | 0.4444          |
-| 0.2337        | 2.0   | 5000 | 0.1787          |
+| 0.086         | 1.0   | 2100 | 0.0741          |
+| 0.0645        | 2.0   | 4200 | 0.0495          |
+| 0.0654        | 3.0   | 6300 | 0.0376          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f9e6c5594650770fde81a64a271eaf116664f1ef0fd495cbd9e84fea6e0f67d
+oid sha256:858c810cfa1df939ed8fcf9509b39f349ce972d27934524b3500c4b47858092d
 size 2444578688

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa32e706db75f2ab9e3c47c3009d63fb8fc1a2590bd34f6a26f6eaf7e80f01b6
+oid sha256:cbbf63eddb8544f46c879175a555043940416ed482b02d190216bbb76b660245
 size 5304