First model version

README.md

@@ -0,0 +1,66 @@
+---
+license: cc-by-nc-4.0
+tags:
+- generated_from_trainer
+- video-classification
+- videomae
+- vision
+metrics:
+- accuracy
+model-index:
+- name: videomae-base-finetuned-ucf101-subset
+  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-ucf101-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: 0.3992
+- Accuracy: 0.8645
+
+## 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: 8
+- eval_batch_size: 8
+- 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: 148
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.1374        | 0.26  | 38   | 1.7413          | 0.5714   |
+| 0.7949        | 1.26  | 76   | 0.7747          | 0.8      |
+| 0.4279        | 2.26  | 114  | 0.4053          | 0.9143   |
+| 0.291         | 3.23  | 148  | 0.3429          | 0.9286   |
+
+
+### Framework versions
+
+- Transformers 4.24.0
+- Pytorch 1.12.1+cu113
+- Datasets 2.6.1
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.23,
+    "eval_accuracy": 0.864516129032258,
+    "eval_loss": 0.3992488980293274,
+    "eval_runtime": 13.7986,
+    "eval_samples_per_second": 11.233,
+    "eval_steps_per_second": 1.449
+}

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-base",
+  "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": "ApplyEyeMakeup",
+    "1": "ApplyLipstick",
+    "2": "Archery",
+    "3": "BabyCrawling",
+    "4": "BalanceBeam",
+    "5": "BandMarching",
+    "6": "BaseballPitch",
+    "7": "Basketball",
+    "8": "BasketballDunk",
+    "9": "BenchPress"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ApplyEyeMakeup": 0,
+    "ApplyLipstick": 1,
+    "Archery": 2,
+    "BabyCrawling": 3,
+    "BalanceBeam": 4,
+    "BandMarching": 5,
+    "BaseballPitch": 6,
+    "Basketball": 7,
+    "BasketballDunk": 8,
+    "BenchPress": 9
+  },
+  "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": "4.24.0",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

preprocessor_config.json

@@ -0,0 +1,18 @@
+{
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "VideoMAEFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cecd2d5e6b441a382f9ac84f44784d4a31821ccf583e946f7eb4ee68c2721829
+size 345001805

runs/Nov09_01-44-16_588d19775fbb/1667958337.1126697/events.out.tfevents.1667958337.588d19775fbb.280.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785d22cecc3d2f9e474ba11b439657b396275adca33fe2a7d12117a69e27b689
+size 5532

runs/Nov09_01-44-16_588d19775fbb/events.out.tfevents.1667958337.588d19775fbb.280.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90202602db02ee3dce0741bbb61f05dc5a4a74fd436e239e87bdf8c1d5976238
+size 7392

runs/Nov09_01-44-16_588d19775fbb/events.out.tfevents.1667958570.588d19775fbb.280.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeadc8c6ad93c9ef712cc667006ee7fa7ec21f9083cf5e46dc9d29257b62eee0
+size 674

runs/Nov10_07-25-30_8182e899e964/1668065304.7947109/events.out.tfevents.1668065304.8182e899e964.107.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b010daab1712000440204600ad83dfa9dfa02fff7075a30323d7a3d3814df4
+size 5532

runs/Nov10_07-25-30_8182e899e964/events.out.tfevents.1668065304.8182e899e964.107.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2c0c160f7f1d3f49c668c19545c8bc63ffa072f37fb7397cc99a5c30debf818
+size 7392

runs/Nov10_07-39-57_8182e899e964/1668066010.4314957/events.out.tfevents.1668066010.8182e899e964.742.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a8e9b2012c46af3bf773de87cd4679a1b253d48dfd3643cd56d2283fb003fd
+size 5532

runs/Nov10_07-39-57_8182e899e964/events.out.tfevents.1668066010.8182e899e964.742.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986313cd0dbc95407bcceedb8204f0caa31a04ab9edf7316733ef272ae34b385
+size 8189

runs/Nov10_07-39-57_8182e899e964/events.out.tfevents.1668066300.8182e899e964.742.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c056c17d5713f6b5fe12c256efc63c372ef10b41440213cacd822a3b2b9bb75
+size 686

runs/Nov10_08-33-15_c4cf3c5cebad/1668069370.6992447/events.out.tfevents.1668069370.c4cf3c5cebad.106.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2f269660d721ed7d8f5037d213fffe257babf983e218a2600356f7a3edb9fc
+size 5532

runs/Nov10_08-33-15_c4cf3c5cebad/events.out.tfevents.1668069370.c4cf3c5cebad.106.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f215582c7696516581d0557884dc719df0f5df95022d14c020fce090ac29695
+size 8189

runs/Nov10_08-33-15_c4cf3c5cebad/events.out.tfevents.1668069624.c4cf3c5cebad.106.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def6ccc8a665dfe287bebd0058f98facdb692c8daa39629792cd745da16ed40b
+size 686

test.py

@@ -1 +0,0 @@
-print("Hello world!")

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.23,
+    "eval_accuracy": 0.864516129032258,
+    "eval_loss": 0.3992488980293274,
+    "eval_runtime": 13.7986,
+    "eval_samples_per_second": 11.233,
+    "eval_steps_per_second": 1.449
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": 0.9285714285714286,
+  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148",
+  "epoch": 3.22972972972973,
+  "global_step": 148,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.3623,
+      "step": 10
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.81203007518797e-05,
+      "loss": 2.2155,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.43609022556391e-05,
+      "loss": 2.1374,
+      "step": 30
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.5714285714285714,
+      "eval_loss": 1.7412834167480469,
+      "eval_runtime": 6.1835,
+      "eval_samples_per_second": 11.32,
+      "eval_steps_per_second": 1.455,
+      "step": 38
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 4.0601503759398494e-05,
+      "loss": 1.9183,
+      "step": 40
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.4923,
+      "step": 50
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 1.2149,
+      "step": 60
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2.9323308270676693e-05,
+      "loss": 0.7949,
+      "step": 70
+    },
+    {
+      "epoch": 1.26,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.7746667265892029,
+      "eval_runtime": 6.3565,
+      "eval_samples_per_second": 11.012,
+      "eval_steps_per_second": 1.416,
+      "step": 76
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 2.556390977443609e-05,
+      "loss": 0.8088,
+      "step": 80
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 2.1804511278195487e-05,
+      "loss": 0.535,
+      "step": 90
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.8045112781954888e-05,
+      "loss": 0.5405,
+      "step": 100
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.4279,
+      "step": 110
+    },
+    {
+      "epoch": 2.26,
+      "eval_accuracy": 0.9142857142857143,
+      "eval_loss": 0.4053409993648529,
+      "eval_runtime": 6.2263,
+      "eval_samples_per_second": 11.243,
+      "eval_steps_per_second": 1.445,
+      "step": 114
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.3461,
+      "step": 120
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 6.766917293233083e-06,
+      "loss": 0.2509,
+      "step": 130
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 3.007518796992481e-06,
+      "loss": 0.291,
+      "step": 140
+    },
+    {
+      "epoch": 3.23,
+      "eval_accuracy": 0.9285714285714286,
+      "eval_loss": 0.3428815007209778,
+      "eval_runtime": 6.583,
+      "eval_samples_per_second": 10.633,
+      "eval_steps_per_second": 1.367,
+      "step": 148
+    },
+    {
+      "epoch": 3.23,
+      "step": 148,
+      "total_flos": 1.460491890402263e+18,
+      "train_loss": 1.0492687128685616,
+      "train_runtime": 239.2161,
+      "train_samples_per_second": 4.949,
+      "train_steps_per_second": 0.619
+    },
+    {
+      "epoch": 3.23,
+      "eval_accuracy": 0.864516129032258,
+      "eval_loss": 0.3992488980293274,
+      "eval_runtime": 14.1288,
+      "eval_samples_per_second": 10.971,
+      "eval_steps_per_second": 1.416,
+      "step": 148
+    },
+    {
+      "epoch": 3.23,
+      "eval_accuracy": 0.864516129032258,
+      "eval_loss": 0.3992488980293274,
+      "eval_runtime": 13.7986,
+      "eval_samples_per_second": 11.233,
+      "eval_steps_per_second": 1.449,
+      "step": 148
+    }
+  ],
+  "max_steps": 148,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 1.460491890402263e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:783515ef8fff301b9d5a50cc9d874df1b9e2b1e35dd67319297260f360dadcf8
+size 3439