End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: bert-base-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # movie-genre-predictions
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.9264
-- Accuracy: 0.3289
+- Loss: 1.6269
+- Accuracy: 0.4435
 
 ## Model description
 
@@ -38,33 +38,25 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 128
+- eval_batch_size: 32
 - seed: 67
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 16
+- num_epochs: 8
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 2.1244        | 1.0   | 2318  | 2.0165          | 0.2812   |
-| 1.8772        | 2.0   | 4636  | 1.8726          | 0.3393   |
-| 1.7305        | 3.0   | 6954  | 1.8347          | 0.3589   |
-| 1.5873        | 4.0   | 9272  | 1.8587          | 0.3631   |
-| 1.4615        | 5.0   | 11590 | 1.9537          | 0.3588   |
-| 1.2914        | 6.0   | 13908 | 2.0050          | 0.3620   |
-| 1.15          | 7.0   | 16226 | 2.1050          | 0.3467   |
-| 1.0332        | 8.0   | 18544 | 2.2455          | 0.3490   |
-| 0.9257        | 9.0   | 20862 | 2.3592          | 0.3357   |
-| 0.8086        | 10.0  | 23180 | 2.4679          | 0.3343   |
-| 0.7231        | 11.0  | 25498 | 2.5798          | 0.3362   |
-| 0.6471        | 12.0  | 27816 | 2.6849          | 0.3335   |
-| 0.5839        | 13.0  | 30134 | 2.7941          | 0.3256   |
-| 0.5238        | 14.0  | 32452 | 2.8416          | 0.3256   |
-| 0.4804        | 15.0  | 34770 | 2.9133          | 0.3297   |
-| 0.4346        | 16.0  | 37088 | 2.9264          | 0.3289   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 290  | 1.6650          | 0.4176   |
+| 1.7904        | 2.0   | 580  | 1.6128          | 0.4340   |
+| 1.7904        | 3.0   | 870  | 1.5912          | 0.4438   |
+| 1.5099        | 4.0   | 1160 | 1.6025          | 0.4418   |
+| 1.5099        | 5.0   | 1450 | 1.6094          | 0.4469   |
+| 1.3965        | 6.0   | 1740 | 1.6154          | 0.4447   |
+| 1.3179        | 7.0   | 2030 | 1.6240          | 0.4430   |
+| 1.3179        | 8.0   | 2320 | 1.6269          | 0.4435   |
 
 
 ### Framework versions