update model card README.md

README.md

@@ -2,8 +2,6 @@
 license: cc-by-nc-4.0
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: videomae-base-finetuned-basketball-subset-v2
   results: []
@@ -16,8 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0082
-- Accuracy: 1.0
+- eval_loss: 0.9309
+- eval_accuracy: 0.3333
+- eval_runtime: 0.8388
+- eval_samples_per_second: 3.577
+- eval_steps_per_second: 3.577
+- step: 0
 
 ## Model description
 
@@ -45,17 +47,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - training_steps: 816
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.7747        | 0.25  | 202  | 2.5059          | 0.5      |
-| 0.0199        | 1.25  | 404  | 0.0082          | 1.0      |
-| 0.4094        | 2.25  | 606  | 0.0313          | 1.0      |
-| 0.2331        | 3.25  | 808  | 2.7905          | 0.5      |
-| 0.0021        | 4.01  | 816  | 2.7916          | 0.5      |
-
-
 ### Framework versions
 
 - Transformers 4.26.1