Training in progress, epoch 0

README.md

@@ -3,6 +3,8 @@ license: cc-by-nc-4.0
 base_model: MCG-NJU/videomae-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: videomae-base-finetuned-subset
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # videomae-base-finetuned-subset
 
 This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9422
+- Accuracy: 0.7011
 
 ## Model description
 
@@ -33,17 +38,63 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 37920
+- training_steps: 2640
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 1.9136        | 0.0254  | 67   | 2.1529          | 0.1096   |
+| 1.9987        | 1.0254  | 134  | 1.9985          | 0.2593   |
+| 1.0754        | 2.0254  | 201  | 2.1637          | 0.1956   |
+| 1.413         | 3.0254  | 268  | 1.9523          | 0.1473   |
+| 1.3047        | 4.0254  | 335  | 2.5442          | 0.1956   |
+| 1.2488        | 5.0254  | 402  | 2.0563          | 0.2330   |
+| 1.0581        | 6.0254  | 469  | 1.9954          | 0.2264   |
+| 0.9165        | 7.0254  | 536  | 1.7661          | 0.2769   |
+| 1.5722        | 8.0254  | 603  | 2.2872          | 0.2264   |
+| 0.9083        | 9.0254  | 670  | 2.1004          | 0.3363   |
+| 0.8093        | 10.0254 | 737  | 1.2497          | 0.6549   |
+| 0.4925        | 11.0254 | 804  | 3.5720          | 0.2813   |
+| 0.4573        | 12.0254 | 871  | 1.5213          | 0.3604   |
+| 1.1082        | 13.0254 | 938  | 1.5453          | 0.5934   |
+| 0.8066        | 14.0254 | 1005 | 2.9169          | 0.2967   |
+| 0.6615        | 15.0254 | 1072 | 2.1412          | 0.5780   |
+| 0.146         | 16.0254 | 1139 | 2.5006          | 0.3978   |
+| 0.3815        | 17.0254 | 1206 | 1.7907          | 0.5956   |
+| 0.2124        | 18.0254 | 1273 | 1.6622          | 0.6527   |
+| 0.5304        | 19.0254 | 1340 | 1.8988          | 0.5956   |
+| 0.1519        | 20.0254 | 1407 | 2.7940          | 0.3934   |
+| 0.486         | 21.0254 | 1474 | 2.6766          | 0.4198   |
+| 0.5502        | 22.0254 | 1541 | 2.3451          | 0.5495   |
+| 0.7527        | 23.0254 | 1608 | 1.7518          | 0.6462   |
+| 0.3194        | 24.0254 | 1675 | 2.0738          | 0.5890   |
+| 0.0189        | 25.0254 | 1742 | 2.9264          | 0.5407   |
+| 0.2928        | 26.0254 | 1809 | 2.5495          | 0.5451   |
+| 0.0036        | 27.0254 | 1876 | 1.8143          | 0.6989   |
+| 0.3772        | 28.0254 | 1943 | 2.2384          | 0.6088   |
+| 0.0044        | 29.0254 | 2010 | 1.7688          | 0.7033   |
+| 0.7291        | 30.0254 | 2077 | 2.0591          | 0.6571   |
+| 0.1553        | 31.0254 | 2144 | 2.0690          | 0.6505   |
+| 0.5454        | 32.0254 | 2211 | 1.8762          | 0.7055   |
+| 0.3096        | 33.0254 | 2278 | 2.2310          | 0.6440   |
+| 0.0053        | 34.0254 | 2345 | 2.0907          | 0.6615   |
+| 0.0024        | 35.0254 | 2412 | 2.4127          | 0.6022   |
+| 0.0022        | 36.0254 | 2479 | 2.0037          | 0.6989   |
+| 0.0026        | 37.0254 | 2546 | 2.0130          | 0.6725   |
+| 0.0013        | 38.0254 | 2613 | 1.9391          | 0.6967   |
+| 0.0017        | 39.0102 | 2640 | 1.9422          | 0.7011   |
+
 
 ### Framework versions
 
-- Transformers 4.44.0
-- Pytorch 2.2.1+cu121
+- Transformers 4.40.2
+- Pytorch 2.0.1+cu117
 - Datasets 2.20.0
 - Tokenizers 0.19.1

config.json

@@ -12,87 +12,23 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
-    "0": "01_CASH_HANDED_OVER",
-    "1": "02_CASH_LOCKER_CLOSING",
-    "2": "03_CASH_LOCKER_OPENING",
-    "3": "04_CUSTOMER_BAG_CHECK",
-    "4": "05_EATING_FOOD_IN_STORE_",
-    "5": "07_EMPLOYEE_HIDING_BEHIND_PARCELS",
-    "6": "08_EMPLOYEES_IN_GROUP",
-    "7": "09_EMPLOYEE_SITTING",
-    "8": "10_EMPLOYEE_SLEEPING",
-    "9": "11_EMPLOYEE_USING_LIFT",
-    "10": "12_EMPLOYEE_USING_MOBILE",
-    "11": "13_FIGHTING",
-    "12": "14_FILLING_FEEDBACK",
-    "13": "15_INCHARGE_IN_COUNTER",
-    "14": "16_LOADING",
-    "15": "17_MOPPING_FLOOR",
-    "16": "18_NO_ONE_IN_COUNTER",
-    "17": "19_OTHER_EMPLOYEES_DOING_BILLING",
-    "18": "20_RUNNING",
-    "19": "21_SECURITY_FRISKING",
-    "20": "22_SITTING_IN_COUNTER",
-    "21": "23_SITTING_ON_TABLE",
-    "22": "24_STANDING_ON_TABLE",
-    "23": "25_STORE_CLOSING",
-    "24": "26_STORE_OPENING",
-    "25": "27_TEAM_MEETING",
-    "26": "28_THROWING_BAGS",
-    "27": "29_UNLOADING",
-    "28": "30_NoFight",
-    "29": "31_FIRE_DETECTION",
-    "30": "33_SHOPLIFTING",
-    "31": "34_BILLINGPROCESS",
-    "32": "35_SHOWINGMERCHANDISE",
-    "33": "36_FOLDINGCLOTHES",
-    "34": "37_DELIVERYPRODUCT",
-    "35": "38_CARRYINGCLOTHESBAGS",
-    "36": "40_HIGHFOOTFALL",
-    "37": "41_STOCKINWARD"
+    "0": "08_EMPLOYEES_IN_GROUP",
+    "1": "12_EMPLOYEE_USING_MOBILE",
+    "2": "17_MOPPING_FLOOR",
+    "3": "21_SECURITY_FRISKING",
+    "4": "31_FIRE_DETECTION",
+    "5": "33_SHOPLIFTING"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "01_CASH_HANDED_OVER": 0,
-    "02_CASH_LOCKER_CLOSING": 1,
-    "03_CASH_LOCKER_OPENING": 2,
-    "04_CUSTOMER_BAG_CHECK": 3,
-    "05_EATING_FOOD_IN_STORE_": 4,
-    "07_EMPLOYEE_HIDING_BEHIND_PARCELS": 5,
-    "08_EMPLOYEES_IN_GROUP": 6,
-    "09_EMPLOYEE_SITTING": 7,
-    "10_EMPLOYEE_SLEEPING": 8,
-    "11_EMPLOYEE_USING_LIFT": 9,
-    "12_EMPLOYEE_USING_MOBILE": 10,
-    "13_FIGHTING": 11,
-    "14_FILLING_FEEDBACK": 12,
-    "15_INCHARGE_IN_COUNTER": 13,
-    "16_LOADING": 14,
-    "17_MOPPING_FLOOR": 15,
-    "18_NO_ONE_IN_COUNTER": 16,
-    "19_OTHER_EMPLOYEES_DOING_BILLING": 17,
-    "20_RUNNING": 18,
-    "21_SECURITY_FRISKING": 19,
-    "22_SITTING_IN_COUNTER": 20,
-    "23_SITTING_ON_TABLE": 21,
-    "24_STANDING_ON_TABLE": 22,
-    "25_STORE_CLOSING": 23,
-    "26_STORE_OPENING": 24,
-    "27_TEAM_MEETING": 25,
-    "28_THROWING_BAGS": 26,
-    "29_UNLOADING": 27,
-    "30_NoFight": 28,
-    "31_FIRE_DETECTION": 29,
-    "33_SHOPLIFTING": 30,
-    "34_BILLINGPROCESS": 31,
-    "35_SHOWINGMERCHANDISE": 32,
-    "36_FOLDINGCLOTHES": 33,
-    "37_DELIVERYPRODUCT": 34,
-    "38_CARRYINGCLOTHESBAGS": 35,
-    "40_HIGHFOOTFALL": 36,
-    "41_STOCKINWARD": 37
+    "08_EMPLOYEES_IN_GROUP": 0,
+    "12_EMPLOYEE_USING_MOBILE": 1,
+    "17_MOPPING_FLOOR": 2,
+    "21_SECURITY_FRISKING": 3,
+    "31_FIRE_DETECTION": 4,
+    "33_SHOPLIFTING": 5
   },
   "layer_norm_eps": 1e-12,
   "model_type": "videomae",
@@ -102,9 +38,10 @@
   "num_frames": 16,
   "num_hidden_layers": 12,
   "patch_size": 16,
+  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.0",
+  "transformers_version": "4.40.2",
   "tubelet_size": 2,
   "use_mean_pooling": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5f1318e883106ad5b5ed5348bb2fee4bc507e0a729b8e918967cd76b05ec666
-size 345048120
+oid sha256:b5b6b15df4dfca3158b060a254876f8acab0d345103679bef2aa210411c37057
+size 344949680

preprocessor_config.json

@@ -1,4 +1,20 @@
 {
+  "_valid_processor_keys": [
+    "videos",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
   "crop_size": {
     "height": 224,
     "width": 224

runs/Aug12_15-39-39_surveillance/events.out.tfevents.1723457391.surveillance.95468.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f665acf9940a591fabcb006ba0db11b26381e80f2325ff61d6f8573ba0207e91
+size 20505

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47f0da6ab5aa8218e99facc794e0186f6c4a36936bcb2dba6a54d641612fc738
-size 5240
+oid sha256:d98c485376c1af8a9b392c443d4ff52d023a5d2038846af2832a02236b57028d
+size 4603