Model save

README.md

@@ -0,0 +1,59 @@
+---
+license: cc-by-nc-4.0
+base_model: archit11/videomae-base-finetuned-ucfcrime-full
+tags:
+- generated_from_trainer
+model-index:
+- name: videomae-base-finetuned-ucfcrime-full2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# videomae-base-finetuned-ucfcrime-full2
+
+This model is a fine-tuned version of [archit11/videomae-base-finetuned-ucfcrime-full](https://huggingface.co/archit11/videomae-base-finetuned-ucfcrime-full) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 2.5014
+- eval_accuracy: 0.225
+- eval_precision: 0.2362
+- eval_recall: 0.1921
+- eval_f1: 0.1788
+- eval_runtime: 1016.7587
+- eval_samples_per_second: 4.878
+- eval_steps_per_second: 1.22
+- step: 0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- 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: 700
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_accuracy": 0.225,
+    "eval_f1": 0.17882905387355633,
+    "eval_loss": 2.501384973526001,
+    "eval_precision": 0.23617900665745273,
+    "eval_recall": 0.19213899602329576,
+    "eval_runtime": 1016.7587,
+    "eval_samples_per_second": 4.878,
+    "eval_steps_per_second": 1.22
+}

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "archit11/videomae-base-finetuned-ucfcrime-full",
+  "architectures": [
+    "VideoMAEForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "decoder_hidden_size": 384,
+  "decoder_intermediate_size": 1536,
+  "decoder_num_attention_heads": 6,
+  "decoder_num_hidden_layers": 4,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Abuse",
+    "1": "Arrest",
+    "2": "Arson",
+    "3": "Assault",
+    "4": "Burglary",
+    "5": "Explosion",
+    "6": "Fighting",
+    "7": "Normal_Videos_for_Event_Recognition",
+    "8": "RoadAccidents",
+    "9": "Robbery",
+    "10": "Shooting",
+    "11": "Shoplifting",
+    "12": "Stealing",
+    "13": "Vandalism"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Abuse": 0,
+    "Arrest": 1,
+    "Arson": 2,
+    "Assault": 3,
+    "Burglary": 4,
+    "Explosion": 5,
+    "Fighting": 6,
+    "Normal_Videos_for_Event_Recognition": 7,
+    "RoadAccidents": 8,
+    "Robbery": 9,
+    "Shooting": 10,
+    "Shoplifting": 11,
+    "Stealing": 12,
+    "Vandalism": 13
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "videomae",
+  "norm_pix_loss": true,
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_frames": 16,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba99a3d4164208683bae69f90dcb21a6f194eb50428952f3f6b6defcc9dcf5ae
+size 344974288

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "VideoMAEImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

runs/Apr02_15-59-10_31ea9200f14f/events.out.tfevents.1712073576.31ea9200f14f.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26693e7bcaf592577abb33334cdcf1af680d1ce917dcb456023bca9bac3f0dc6
+size 9057

runs/Apr02_15-59-10_31ea9200f14f/events.out.tfevents.1712077121.31ea9200f14f.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f0bf8f4b81093e75329c3cd07555cff7a3506e67d0e9d0d0e23cdd32b61b4f
+size 486

test_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_accuracy": 0.225,
+    "eval_f1": 0.17882905387355633,
+    "eval_loss": 2.501384973526001,
+    "eval_precision": 0.23617900665745273,
+    "eval_recall": 0.19213899602329576,
+    "eval_runtime": 1016.7587,
+    "eval_samples_per_second": 4.878,
+    "eval_steps_per_second": 1.22
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a7edbb6f198bf21be6786dbaac65e81365e1d801f2b3997dcf78274b25ac17
+size 4984