Model save

README.md

@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # m2m100_trained
 
 This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.1909
 
 ## Model description
 
@@ -35,26 +33,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 7e-05
+- learning_rate: 5e-05
 - train_batch_size: 4
-- eval_batch_size: 4
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 8
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.06
-- num_epochs: 4
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 0.2521        | 1.0   | 3001  | 0.2594          |
-| 0.1747        | 2.0   | 6002  | 0.2115          |
-| 0.1156        | 3.0   | 9003  | 0.1953          |
-| 0.0747        | 4.0   | 12004 | 0.1909          |
 
 
 ### Framework versions