End of training

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [jhu-clsp/mmBERT-base](https://huggingface.co/jhu-clsp/mmBERT-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4678
-- Precision: 0.7161
-- Recall: 0.7207
-- F1: 0.7184
-- Accuracy: 0.8243
+- Loss: 0.7960
+- Precision: 0.6647
+- Recall: 0.7145
+- F1: 0.6887
+- Accuracy: 0.8221
 
 ## Model description
 
@@ -44,7 +44,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 8
 - eval_batch_size: 16
 - seed: 42
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - 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: 0.1
-- num_epochs: 3
+- lr_scheduler_warmup_ratio: 0.15
+- num_epochs: 2
+- label_smoothing_factor: 0.1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.4626        | 1.0   | 342  | 0.4884          | 0.6803    | 0.7225 | 0.7008 | 0.8146   |
-| 0.4385        | 2.0   | 684  | 0.4678          | 0.7161    | 0.7207 | 0.7184 | 0.8243   |
-| 0.4073        | 3.0   | 1026 | 0.4387          | 0.6786    | 0.7252 | 0.7011 | 0.8255   |
+| 0.8178        | 1.0   | 342  | 0.8293          | 0.5955    | 0.7124 | 0.6488 | 0.8050   |
+| 0.7927        | 2.0   | 684  | 0.7960          | 0.6647    | 0.7145 | 0.6887 | 0.8221   |
 
 
 ### Framework versions