End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6764
-- Accuracy: 0.6
-- F1: 0.7500
+- Loss: 0.5729
+- Accuracy: 0.738
+- F1: 0.8085
 
 ## Model description
 
@@ -38,21 +38,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 5e-06
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.654         | 1.0   | 751  | 0.6321          | 0.67     | 0.7829 |
-| 0.6592        | 2.0   | 1502 | 0.6698          | 0.606    | 0.7528 |
-| 0.6665        | 3.0   | 2253 | 0.6764          | 0.6      | 0.7500 |
+| No log        | 1.0   | 376  | 0.5447          | 0.744    | 0.8210 |
+| 0.5956        | 2.0   | 752  | 0.5605          | 0.731    | 0.8041 |
+| 0.5284        | 3.0   | 1128 | 0.5729          | 0.738    | 0.8085 |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c072faf21c2b87705e443324f375fb2c8b2fb13f56e391d90a3d735f3e80448a
+oid sha256:3f34a2313e716b3f5034a0e045f09d9af6ae1f385feef77e1228762ede299364
 size 498662069

runs/Jun30_09-07-36_75b58f33b246/events.out.tfevents.1688116238.75b58f33b246.4760.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c819d533119fe059c4037b26ab021d6c78067739a75f30778cfed74795eb83de
-size 5105
+oid sha256:dd014c9f69732bea08451109e5b0e96c812b2e495192f61c6c9adb97a1d8766f
+size 5828