Model save

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0172
+- Loss: 0.0345
 - Accuracy: 1.0
 
 ## Model description
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.4843        | 1.0   | 44   | 0.0172          | 1.0      |
+| 1.3553        | 1.0   | 44   | 0.0345          | 1.0      |
 
 
 ### Framework versions

trainer_state.json

@@ -10,28 +10,28 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.899039626121521,
+      "grad_norm": 1.05665922164917,
       "learning_rate": 1.282051282051282e-06,
-      "loss": 1.4843,
+      "loss": 1.3553,
       "step": 44
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.01724686101078987,
-      "eval_runtime": 13.6044,
-      "eval_samples_per_second": 2.279,
-      "eval_steps_per_second": 1.176,
+      "eval_loss": 0.0345461443066597,
+      "eval_runtime": 16.214,
+      "eval_samples_per_second": 1.912,
+      "eval_steps_per_second": 0.987,
       "step": 44
     },
     {
       "epoch": 1.0,
       "step": 44,
       "total_flos": 4.386186471218872e+17,
-      "train_loss": 1.484270616011186,
-      "train_runtime": 185.9579,
-      "train_samples_per_second": 1.893,
-      "train_steps_per_second": 0.237
+      "train_loss": 1.3552533063021572,
+      "train_runtime": 194.3952,
+      "train_samples_per_second": 1.811,
+      "train_steps_per_second": 0.226
     }
   ],
   "logging_steps": 500,