update model card README.md

README.md

@@ -1,6 +1,12 @@
 ---
+base_model: allenai/scibert_scivocab_uncased
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
 model-index:
 - name: patentClassfication2
   results: []
@@ -11,7 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # patentClassfication2
 
-This model was trained from scratch on the None dataset.
+This model is a fine-tuned version of [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6263
+- Accuracy: 0.6572
+- F1: 0.6151
+- Precision: 0.6966
+- Recall: 0.5507
 
 ## Model description
 
@@ -30,17 +42,24 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3.250956097988812e-05
+- learning_rate: 2.54241e-05
 - train_batch_size: 8
 - eval_batch_size: 8
-- seed: 48
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 64
+- seed: 41
 - 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: 495
-- num_epochs: 2
+- lr_scheduler_warmup_steps: 24
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.6346        | 1.0   | 4438  | 0.6263          | 0.6572   | 0.6151 | 0.6966    | 0.5507 |
+| 0.5796        | 2.0   | 8876  | 0.6388          | 0.6758   | 0.6833 | 0.6646    | 0.7030 |
+| 0.5268        | 3.0   | 13314 | 0.6567          | 0.6715   | 0.6833 | 0.6565    | 0.7123 |
+
 
 ### Framework versions