End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9561
-- Accuracy: 0.6773
+- Loss: 0.8131
+- Accuracy: 0.7849
 
 ## Model description
 
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.8886        | 1.0   | 101  | 0.1661          | 0.9828   |
+| 0.8303        | 1.0   | 101  | 0.1456          | 0.9902   |
 
 
 ### Framework versions

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.6772908366533864,
-    "eval_loss": 0.9560578465461731,
-    "eval_runtime": 55.4125,
-    "eval_samples_per_second": 4.53,
-    "eval_steps_per_second": 0.577
+    "eval_accuracy": 0.7848605577689243,
+    "eval_loss": 0.8131076693534851,
+    "eval_runtime": 54.3415,
+    "eval_samples_per_second": 4.619,
+    "eval_steps_per_second": 0.589
 }

test_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_accuracy": 0.6772908366533864,
-    "eval_loss": 0.9560578465461731,
-    "eval_runtime": 55.4125,
-    "eval_samples_per_second": 4.53,
-    "eval_steps_per_second": 0.577
+    "eval_accuracy": 0.7848605577689243,
+    "eval_loss": 0.8131076693534851,
+    "eval_runtime": 54.3415,
+    "eval_samples_per_second": 4.619,
+    "eval_steps_per_second": 0.589
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9828009828009828,
+  "best_metric": 0.990159901599016,
   "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/Timesformer_default_fold_10_10_epoch_noAug_batch8_codecheck/checkpoint-101",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 0.9900990099009901,
-      "grad_norm": 2.9471566677093506,
+      "grad_norm": 7.038530349731445,
       "learning_rate": 5.555555555555556e-07,
-      "loss": 0.8886,
+      "loss": 0.8303,
       "step": 100
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9828009828009828,
-      "eval_loss": 0.16609854996204376,
-      "eval_runtime": 202.8409,
-      "eval_samples_per_second": 4.013,
-      "eval_steps_per_second": 0.503,
+      "eval_accuracy": 0.990159901599016,
+      "eval_loss": 0.14564795792102814,
+      "eval_runtime": 174.3791,
+      "eval_samples_per_second": 4.662,
+      "eval_steps_per_second": 0.585,
       "step": 101
     },
     {
       "epoch": 1.0,
       "step": 101,
       "total_flos": 7.07971920321577e+17,
-      "train_loss": 0.8806298740281917,
-      "train_runtime": 488.3542,
-      "train_samples_per_second": 1.655,
-      "train_steps_per_second": 0.207
+      "train_loss": 0.8236100951043686,
+      "train_runtime": 432.6459,
+      "train_samples_per_second": 1.868,
+      "train_steps_per_second": 0.233
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6772908366533864,
-      "eval_loss": 0.9560578465461731,
-      "eval_runtime": 55.4125,
-      "eval_samples_per_second": 4.53,
-      "eval_steps_per_second": 0.577,
+      "eval_accuracy": 0.7848605577689243,
+      "eval_loss": 0.8131076693534851,
+      "eval_runtime": 54.3415,
+      "eval_samples_per_second": 4.619,
+      "eval_steps_per_second": 0.589,
       "step": 101
     }
   ],