End of training

README.md

@@ -4,7 +4,7 @@ base_model: roberta-base
 tags:
 - generated_from_trainer
 datasets:
-- sagnikrayc/snli-cf-kaushik
+- RobZamp/sick
 metrics:
 - accuracy
 model-index:
@@ -14,15 +14,15 @@ model-index:
       name: Text Classification
       type: text-classification
     dataset:
-      name: snli-cf-kaushik
-      type: sagnikrayc/snli-cf-kaushik
+      name: sick
+      type: RobZamp/sick
       config: default
       split: validation
       args: default
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.4395
+      value: 0.8787878787878788
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # roberta-base-fp-sick
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the snli-cf-kaushik dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the sick dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1373
-- Accuracy: 0.4395
+- Loss: 0.3257
+- Accuracy: 0.8788
 
 ## Model description
 
@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
 - learning_rate: 2e-05
 - train_batch_size: 64
 - eval_batch_size: 32
-- seed: 33
+- seed: 59
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
@@ -64,9 +64,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 70   | 0.4164          | 0.8485   |
-| No log        | 2.0   | 140  | 0.3497          | 0.8747   |
-| No log        | 3.0   | 210  | 0.3346          | 0.8727   |
+| No log        | 1.0   | 70   | 0.3581          | 0.8768   |
+| No log        | 2.0   | 140  | 0.3995          | 0.8465   |
+| No log        | 3.0   | 210  | 0.3257          | 0.8788   |
 
 
 ### Framework versions