Training completed!

README.md

@@ -1,5 +1,6 @@
 ---
 library_name: transformers
+base_model: sercetexam9/cs221-xlnet-base-cased-finetuned
 tags:
 - generated_from_trainer
 metrics:
@@ -15,12 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # cs221-xlnet-base-cased-finetuned-20-epochs
 
-This model was trained from scratch on the None dataset.
+This model is a fine-tuned version of [sercetexam9/cs221-xlnet-base-cased-finetuned](https://huggingface.co/sercetexam9/cs221-xlnet-base-cased-finetuned) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6676
-- F1: 0.7323
-- Roc Auc: 0.8005
-- Accuracy: 0.4422
+- Loss: 0.4195
+- F1: 0.7215
+- Accuracy: 0.4314
 
 ## Model description
 
@@ -40,21 +40,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - 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: cosine
 - lr_scheduler_warmup_steps: 100
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
-| 0.0327        | 1.0   | 139  | 0.6538          | 0.7090 | 0.7827  | 0.4224   |
-| 0.0168        | 2.0   | 278  | 0.6723          | 0.7309 | 0.8001  | 0.4206   |
-| 0.0192        | 3.0   | 417  | 0.6676          | 0.7323 | 0.8005  | 0.4422   |
+| Training Loss | Epoch | Step | Validation Loss | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
+| 0.1871        | 1.0   | 70   | 0.4195          | 0.7215 | 0.4314   |
+| 0.1906        | 2.0   | 140  | 0.4226          | 0.7209 | 0.4585   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:158bc7279cc2ec54dc707cd102c06e58fb9cf0c7f6dca5f6589aefd951600f81
+oid sha256:055a383d0e192eb7b640714b61e035641f25f25fe483f588e62a2dee9abe4699
 size 469273828