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 [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: 0.0029
+- Loss: 0.0015
 - Accuracy: 1.0
 
 ## Model description
@@ -54,13 +54,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 5.5194        | 0.02   | 7    | 1.2288          | 0.7143   |
-| 3.9958        | 1.0214 | 15   | 0.8649          | 1.0      |
-| 2.9836        | 2.02   | 22   | 0.5277          | 0.9286   |
-| 1.3684        | 3.0214 | 30   | 0.2611          | 1.0      |
-| 0.491         | 4.02   | 37   | 0.0589          | 1.0      |
-| 0.0773        | 5.0214 | 45   | 0.0096          | 1.0      |
-| 0.0159        | 6.02   | 52   | 0.0029          | 1.0      |
+| 6.0723        | 0.02   | 7    | 1.3154          | 0.4286   |
+| 4.5479        | 1.0214 | 15   | 1.0319          | 0.8571   |
+| 3.6957        | 2.02   | 22   | 0.6454          | 0.8571   |
+| 1.7212        | 3.0214 | 30   | 0.2796          | 1.0      |
+| 0.6321        | 4.02   | 37   | 0.0587          | 1.0      |
+| 0.0861        | 5.0214 | 45   | 0.0120          | 1.0      |
+| 0.0166        | 6.02   | 52   | 0.0029          | 1.0      |
+| 0.0047        | 7.0214 | 60   | 0.0018          | 1.0      |
+| 0.0029        | 8.02   | 67   | 0.0015          | 1.0      |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18755bed9fe08242090adee2cd3670f0c33c1c3714820d0ac8c3b7c39e1bdbdc
+oid sha256:953acf335adb8764b7698ed56f60d19e918addc34c4386d841edeb0d032cfdbd
 size 344943488

trainer_state.json

@@ -1,133 +1,165 @@
 {
   "best_metric": 1.0,
-  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/VideoMAE_4_CLASS_QUALITY_CHECK/checkpoint-15",
-  "epoch": 6.02,
+  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/VideoMAE_4_CLASS_QUALITY_CHECK/checkpoint-30",
+  "epoch": 8.02,
   "eval_steps": 500,
-  "global_step": 52,
+  "global_step": 67,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.02,
-      "grad_norm": 18.13094711303711,
+      "grad_norm": 17.483346939086914,
       "learning_rate": 1e-05,
-      "loss": 5.5194,
+      "loss": 6.0723,
       "step": 7
     },
     {
       "epoch": 0.02,
-      "eval_accuracy": 0.7142857142857143,
-      "eval_loss": 1.2288295030593872,
-      "eval_runtime": 3.7225,
-      "eval_samples_per_second": 3.761,
-      "eval_steps_per_second": 1.88,
+      "eval_accuracy": 0.42857142857142855,
+      "eval_loss": 1.3153599500656128,
+      "eval_runtime": 2.0006,
+      "eval_samples_per_second": 6.998,
+      "eval_steps_per_second": 3.499,
       "step": 7
     },
     {
       "epoch": 1.0214285714285714,
-      "grad_norm": 24.789016723632812,
+      "grad_norm": 20.505908966064453,
       "learning_rate": 2.1428571428571428e-05,
-      "loss": 3.9958,
+      "loss": 4.5479,
       "step": 15
     },
     {
       "epoch": 1.0214285714285714,
-      "eval_accuracy": 1.0,
-      "eval_loss": 0.8649204969406128,
-      "eval_runtime": 2.6492,
-      "eval_samples_per_second": 5.285,
-      "eval_steps_per_second": 2.642,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 1.0319474935531616,
+      "eval_runtime": 1.9993,
+      "eval_samples_per_second": 7.003,
+      "eval_steps_per_second": 3.501,
       "step": 15
     },
     {
       "epoch": 2.02,
-      "grad_norm": 27.01192283630371,
+      "grad_norm": 27.64762306213379,
       "learning_rate": 3.142857142857143e-05,
-      "loss": 2.9836,
+      "loss": 3.6957,
       "step": 22
     },
     {
       "epoch": 2.02,
-      "eval_accuracy": 0.9285714285714286,
-      "eval_loss": 0.5277099609375,
-      "eval_runtime": 3.371,
-      "eval_samples_per_second": 4.153,
-      "eval_steps_per_second": 2.077,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.6453508734703064,
+      "eval_runtime": 1.9837,
+      "eval_samples_per_second": 7.057,
+      "eval_steps_per_second": 3.529,
       "step": 22
     },
     {
       "epoch": 3.0214285714285714,
-      "grad_norm": 19.976594924926758,
+      "grad_norm": 23.30771827697754,
       "learning_rate": 4.1428571428571437e-05,
-      "loss": 1.3684,
+      "loss": 1.7212,
       "step": 30
     },
     {
       "epoch": 3.0214285714285714,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.2610691487789154,
-      "eval_runtime": 2.7389,
-      "eval_samples_per_second": 5.112,
-      "eval_steps_per_second": 2.556,
+      "eval_loss": 0.2796107828617096,
+      "eval_runtime": 1.9824,
+      "eval_samples_per_second": 7.062,
+      "eval_steps_per_second": 3.531,
       "step": 30
     },
     {
       "epoch": 4.02,
-      "grad_norm": 3.972865104675293,
+      "grad_norm": 4.675124645233154,
       "learning_rate": 4.9841269841269845e-05,
-      "loss": 0.491,
+      "loss": 0.6321,
       "step": 37
     },
     {
       "epoch": 4.02,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.0588662289083004,
-      "eval_runtime": 2.4476,
-      "eval_samples_per_second": 5.72,
-      "eval_steps_per_second": 2.86,
+      "eval_loss": 0.05873652920126915,
+      "eval_runtime": 1.984,
+      "eval_samples_per_second": 7.056,
+      "eval_steps_per_second": 3.528,
       "step": 37
     },
     {
       "epoch": 5.021428571428571,
-      "grad_norm": 0.7364888191223145,
+      "grad_norm": 0.7413554787635803,
       "learning_rate": 4.8571428571428576e-05,
-      "loss": 0.0773,
+      "loss": 0.0861,
       "step": 45
     },
     {
       "epoch": 5.021428571428571,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.00962775107473135,
-      "eval_runtime": 3.1103,
-      "eval_samples_per_second": 4.501,
-      "eval_steps_per_second": 2.251,
+      "eval_loss": 0.012020383961498737,
+      "eval_runtime": 1.9597,
+      "eval_samples_per_second": 7.144,
+      "eval_steps_per_second": 3.572,
       "step": 45
     },
     {
       "epoch": 6.02,
-      "grad_norm": 0.1992603838443756,
+      "grad_norm": 0.23269684612751007,
       "learning_rate": 4.746031746031746e-05,
-      "loss": 0.0159,
+      "loss": 0.0166,
       "step": 52
     },
     {
       "epoch": 6.02,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.002915723016485572,
-      "eval_runtime": 3.1585,
-      "eval_samples_per_second": 4.432,
-      "eval_steps_per_second": 2.216,
+      "eval_loss": 0.002919810125604272,
+      "eval_runtime": 1.9438,
+      "eval_samples_per_second": 7.202,
+      "eval_steps_per_second": 3.601,
       "step": 52
     },
     {
-      "epoch": 6.02,
-      "step": 52,
-      "total_flos": 5.2335646214455296e+17,
-      "train_loss": 2.0500162014594445,
-      "train_runtime": 126.4134,
-      "train_samples_per_second": 22.15,
-      "train_steps_per_second": 2.769
+      "epoch": 7.021428571428571,
+      "grad_norm": 0.06729763746261597,
+      "learning_rate": 4.6190476190476194e-05,
+      "loss": 0.0047,
+      "step": 60
+    },
+    {
+      "epoch": 7.021428571428571,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0018126964569091797,
+      "eval_runtime": 2.0381,
+      "eval_samples_per_second": 6.869,
+      "eval_steps_per_second": 3.435,
+      "step": 60
+    },
+    {
+      "epoch": 8.02,
+      "grad_norm": 0.040539324283599854,
+      "learning_rate": 4.507936507936508e-05,
+      "loss": 0.0029,
+      "step": 67
+    },
+    {
+      "epoch": 8.02,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0014999593840911984,
+      "eval_runtime": 1.9648,
+      "eval_samples_per_second": 7.125,
+      "eval_steps_per_second": 3.563,
+      "step": 67
+    },
+    {
+      "epoch": 8.02,
+      "step": 67,
+      "total_flos": 6.728868799001395e+17,
+      "train_loss": 1.8480051827074877,
+      "train_runtime": 179.1547,
+      "train_samples_per_second": 15.629,
+      "train_steps_per_second": 1.954
     }
   ],
   "logging_steps": 500,
@@ -156,7 +188,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.2335646214455296e+17,
+  "total_flos": 6.728868799001395e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a013d9572411196384a99102848a4781f0c5748dcee7d41055d25cd9caa1f442
+oid sha256:a09d22f455848886a768bd8daad7d2fa4c29ab567a5a5a53ad4ccc1835846b9f
 size 5304