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: 0.6466
-- Accuracy: 0.7729
+- Loss: 0.5098
+- Accuracy: 0.8367
 
 ## Model description
 
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 1.0807        | 0.5027 | 184  | 0.0535          | 0.9877   |
-| 0.0103        | 1.4973 | 366  | 0.0050          | 1.0      |
+| 1.0933        | 0.5027 | 184  | 0.0142          | 1.0      |
+| 0.011         | 1.4973 | 366  | 0.0109          | 0.9938   |
 
 
 ### Framework versions

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.4972677595628414,
-    "eval_accuracy": 0.7729083665338645,
-    "eval_loss": 0.6465751528739929,
-    "eval_runtime": 56.8816,
-    "eval_samples_per_second": 4.413,
-    "eval_steps_per_second": 0.563
+    "eval_accuracy": 0.8366533864541833,
+    "eval_loss": 0.5097954869270325,
+    "eval_runtime": 56.3553,
+    "eval_samples_per_second": 4.454,
+    "eval_steps_per_second": 0.568
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0a5a0d39212e1938492feb85a05ba285d0597ebd7b33580eaecada7db7d698
+oid sha256:6a419c0356ec673ca60ebedd8955cf1e61ce1e834b25e0ba0ba0dc28b9bfc0c4
 size 485103024

test_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.4972677595628414,
-    "eval_accuracy": 0.7729083665338645,
-    "eval_loss": 0.6465751528739929,
-    "eval_runtime": 56.8816,
-    "eval_samples_per_second": 4.413,
-    "eval_steps_per_second": 0.563
+    "eval_accuracy": 0.8366533864541833,
+    "eval_loss": 0.5097954869270325,
+    "eval_runtime": 56.3553,
+    "eval_samples_per_second": 4.454,
+    "eval_steps_per_second": 0.568
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": 1.0,
-  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/Timesformer_default_fold_10_10_epoch_noAug_batch8_codecheck/checkpoint-366",
+  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/Timesformer_default_fold_10_10_epoch_noAug_batch8_codecheck/checkpoint-184",
   "epoch": 1.4972677595628414,
   "eval_steps": 500,
   "global_step": 366,
@@ -10,59 +10,59 @@
   "log_history": [
     {
       "epoch": 0.273224043715847,
-      "grad_norm": 2.9251768589019775,
+      "grad_norm": 2.266233444213867,
       "learning_rate": 4.0425531914893614e-05,
-      "loss": 1.0807,
+      "loss": 1.0933,
       "step": 100
     },
     {
       "epoch": 0.5027322404371585,
-      "eval_accuracy": 0.9876543209876543,
-      "eval_loss": 0.05346473678946495,
-      "eval_runtime": 35.9996,
-      "eval_samples_per_second": 4.5,
-      "eval_steps_per_second": 0.583,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.014155284501612186,
+      "eval_runtime": 37.8295,
+      "eval_samples_per_second": 4.282,
+      "eval_steps_per_second": 0.555,
       "step": 184
     },
     {
       "epoch": 1.0437158469945356,
-      "grad_norm": 0.32789137959480286,
+      "grad_norm": 0.3162294626235962,
       "learning_rate": 2.5227963525835867e-05,
-      "loss": 0.0506,
+      "loss": 0.0458,
       "step": 200
     },
     {
       "epoch": 1.3169398907103824,
-      "grad_norm": 0.02562747336924076,
+      "grad_norm": 0.509850263595581,
       "learning_rate": 1.0030395136778116e-05,
-      "loss": 0.0103,
+      "loss": 0.011,
       "step": 300
     },
     {
       "epoch": 1.4972677595628414,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.004981487523764372,
-      "eval_runtime": 37.6527,
-      "eval_samples_per_second": 4.302,
-      "eval_steps_per_second": 0.558,
+      "eval_accuracy": 0.9938271604938271,
+      "eval_loss": 0.010920087806880474,
+      "eval_runtime": 38.0242,
+      "eval_samples_per_second": 4.26,
+      "eval_steps_per_second": 0.552,
       "step": 366
     },
     {
       "epoch": 1.4972677595628414,
       "step": 366,
       "total_flos": 2.5593885881922355e+18,
-      "train_loss": 0.31245257681021926,
-      "train_runtime": 952.1445,
-      "train_samples_per_second": 3.075,
+      "train_loss": 0.3163567338484884,
+      "train_runtime": 953.4888,
+      "train_samples_per_second": 3.071,
       "train_steps_per_second": 0.384
     },
     {
       "epoch": 1.4972677595628414,
-      "eval_accuracy": 0.7729083665338645,
-      "eval_loss": 0.6465751528739929,
-      "eval_runtime": 56.8816,
-      "eval_samples_per_second": 4.413,
-      "eval_steps_per_second": 0.563,
+      "eval_accuracy": 0.8366533864541833,
+      "eval_loss": 0.5097954869270325,
+      "eval_runtime": 56.3553,
+      "eval_samples_per_second": 4.454,
+      "eval_steps_per_second": 0.568,
       "step": 366
     }
   ],