update model card README.md

README.md

@@ -1,12 +1,6 @@
 ---
-base_model: allenai/longformer-large-4096
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
-- f1
-- precision
-- recall
 model-index:
 - name: patentClassfication2
   results: []
@@ -17,13 +11,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # patentClassfication2
 
-This model is a fine-tuned version of [allenai/longformer-large-4096](https://huggingface.co/allenai/longformer-large-4096) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6395
-- Accuracy: 0.645
-- F1: 0.6764
-- Precision: 0.6214
-- Recall: 0.742
+This model was trained from scratch on the None dataset.
 
 ## Model description
 
@@ -42,25 +30,17 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 7.224533222600416e-06
+- learning_rate: 3.250956097988812e-05
 - train_batch_size: 8
 - eval_batch_size: 8
-- seed: 3
+- seed: 48
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- lr_scheduler_warmup_steps: 371
-- num_epochs: 4
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.6917        | 1.0   | 500  | 0.6714          | 0.595    | 0.64   | 0.576     | 0.72   |
-| 0.6577        | 2.0   | 1000 | 0.6395          | 0.645    | 0.6764 | 0.6214    | 0.742  |
-| 0.536         | 3.0   | 1500 | 0.6535          | 0.675    | 0.6531 | 0.7002    | 0.612  |
-| 0.4025        | 4.0   | 2000 | 0.6808          | 0.686    | 0.6879 | 0.6838    | 0.692  |
-
+- lr_scheduler_warmup_steps: 495
+- num_epochs: 2
 
 ### Framework versions