End of training

README.md

@@ -18,7 +18,7 @@ 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: 0.6406
+- Loss: 0.7382
 - Accuracy: 0.8048
 
 ## Model description
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.0244        | 0.5   | 183  | 0.0312          | 0.9877   |
-| 0.0111        | 1.5   | 366  | 0.0207          | 0.9939   |
+| 1.0414        | 0.5   | 183  | 0.0075          | 1.0      |
+| 0.0111        | 1.5   | 366  | 0.0027          | 1.0      |
 
 
 ### Framework versions

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.5,
     "eval_accuracy": 0.8047808764940239,
-    "eval_loss": 0.640614926815033,
-    "eval_runtime": 64.5118,
-    "eval_samples_per_second": 3.891,
-    "eval_steps_per_second": 0.496
+    "eval_loss": 0.7381597757339478,
+    "eval_runtime": 58.051,
+    "eval_samples_per_second": 4.324,
+    "eval_steps_per_second": 0.551
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a6346112421c3621701659444323e7836d9121a2981417952fdf7f4ebeb3ce
+oid sha256:366f03e10cf6f406036792317ae2bad4ab934fe26c2511592006ed0a8572129f
 size 485103024

test_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.5,
     "eval_accuracy": 0.8047808764940239,
-    "eval_loss": 0.640614926815033,
-    "eval_runtime": 64.5118,
-    "eval_samples_per_second": 3.891,
-    "eval_steps_per_second": 0.496
+    "eval_loss": 0.7381597757339478,
+    "eval_runtime": 58.051,
+    "eval_samples_per_second": 4.324,
+    "eval_steps_per_second": 0.551
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9938650306748467,
-  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/Timesformer_default_fold_10_10_epoch_noAug_batch8_codecheck/checkpoint-366",
+  "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-183",
   "epoch": 1.5,
   "eval_steps": 500,
   "global_step": 366,
@@ -10,59 +10,59 @@
   "log_history": [
     {
       "epoch": 0.273224043715847,
-      "grad_norm": 5.497601509094238,
+      "grad_norm": 4.401360511779785,
       "learning_rate": 4.0425531914893614e-05,
-      "loss": 1.0244,
+      "loss": 1.0414,
       "step": 100
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.9877300613496932,
-      "eval_loss": 0.031168974936008453,
-      "eval_runtime": 39.7326,
-      "eval_samples_per_second": 4.102,
-      "eval_steps_per_second": 0.529,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.007542750798165798,
+      "eval_runtime": 38.4359,
+      "eval_samples_per_second": 4.241,
+      "eval_steps_per_second": 0.546,
       "step": 183
     },
     {
       "epoch": 1.046448087431694,
-      "grad_norm": 0.16856300830841064,
+      "grad_norm": 0.04506819695234299,
       "learning_rate": 2.5227963525835867e-05,
-      "loss": 0.0585,
+      "loss": 0.0493,
       "step": 200
     },
     {
       "epoch": 1.319672131147541,
-      "grad_norm": 0.05752040818333626,
+      "grad_norm": 0.06605596840381622,
       "learning_rate": 1.0030395136778116e-05,
       "loss": 0.0111,
       "step": 300
     },
     {
       "epoch": 1.5,
-      "eval_accuracy": 0.9938650306748467,
-      "eval_loss": 0.020665159448981285,
-      "eval_runtime": 40.6398,
-      "eval_samples_per_second": 4.011,
-      "eval_steps_per_second": 0.517,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0026590945199131966,
+      "eval_runtime": 39.5473,
+      "eval_samples_per_second": 4.122,
+      "eval_steps_per_second": 0.531,
       "step": 366
     },
     {
       "epoch": 1.5,
       "step": 366,
       "total_flos": 2.5655220082940314e+18,
-      "train_loss": 0.2993898896164581,
-      "train_runtime": 1014.911,
-      "train_samples_per_second": 2.885,
-      "train_steps_per_second": 0.361
+      "train_loss": 0.3023283794278004,
+      "train_runtime": 1037.7001,
+      "train_samples_per_second": 2.822,
+      "train_steps_per_second": 0.353
     },
     {
       "epoch": 1.5,
       "eval_accuracy": 0.8047808764940239,
-      "eval_loss": 0.640614926815033,
-      "eval_runtime": 64.5118,
-      "eval_samples_per_second": 3.891,
-      "eval_steps_per_second": 0.496,
+      "eval_loss": 0.7381597757339478,
+      "eval_runtime": 58.051,
+      "eval_samples_per_second": 4.324,
+      "eval_steps_per_second": 0.551,
       "step": 366
     }
   ],