Upload folder using huggingface_hub

README.md

@@ -0,0 +1,82 @@
+---
+license: cc-by-nc-4.0
+base_model: MCG-NJU/videomae-base
+tags:
+- video-classification
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ucf101_42
+  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. -->
+
+# ucf101_42
+
+This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on the ucf101 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8198
+- Accuracy: 0.8298
+
+## 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: 64
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.01  | 300  | 2.3345          | 0.4887   |
+| No log        | 2.01  | 600  | 1.4956          | 0.6433   |
+| No log        | 3.01  | 900  | 1.1647          | 0.7162   |
+| 1.5784        | 4.01  | 1200 | 1.1531          | 0.7029   |
+| 1.5784        | 5.01  | 1500 | 1.0251          | 0.7334   |
+| 1.5784        | 6.01  | 1800 | 1.0315          | 0.7333   |
+| 0.1821        | 7.01  | 2100 | 0.9787          | 0.7617   |
+| 0.1821        | 8.01  | 2400 | 0.8933          | 0.7838   |
+| 0.1821        | 9.01  | 2700 | 0.8781          | 0.7917   |
+| 0.0651        | 10.01 | 3000 | 0.9051          | 0.7910   |
+| 0.0651        | 11.01 | 3300 | 0.9593          | 0.7900   |
+| 0.0651        | 12.01 | 3600 | 0.8054          | 0.8187   |
+| 0.0651        | 13.01 | 3900 | 0.8679          | 0.8142   |
+| 0.0265        | 14.01 | 4200 | 0.8380          | 0.8208   |
+| 0.0265        | 15.01 | 4500 | 0.8317          | 0.8247   |
+| 0.0265        | 16.01 | 4800 | 0.8027          | 0.8249   |
+| 0.0091        | 17.01 | 5100 | 0.8240          | 0.8255   |
+| 0.0091        | 18.01 | 5400 | 0.8480          | 0.8211   |
+| 0.0091        | 19.01 | 5700 | 0.8198          | 0.8298   |
+| 0.0091        | 19.87 | 5960 | 0.8315          | 0.8283   |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 19.87,
+    "eval_accuracy": 0.8297674418604651,
+    "eval_loss": 0.8198431134223938,
+    "eval_runtime": 374.2016,
+    "eval_samples_per_second": 10.11,
+    "eval_steps_per_second": 0.16,
+    "train_accuracy": 0.9990563070147845,
+    "train_loss": 0.004719822201877832,
+    "train_runtime": 334.4111,
+    "train_samples_per_second": 28.519,
+    "train_steps_per_second": 0.449
+}

config.json

@@ -0,0 +1,237 @@
+{
+  "_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",
+    "10": "Biking",
+    "11": "Billiards",
+    "12": "BlowDryHair",
+    "13": "BlowingCandles",
+    "14": "BodyWeightSquats",
+    "15": "Bowling",
+    "16": "BoxingPunchingBag",
+    "17": "BoxingSpeedBag",
+    "18": "BreastStroke",
+    "19": "BrushingTeeth",
+    "20": "CleanAndJerk",
+    "21": "CliffDiving",
+    "22": "CricketBowling",
+    "23": "CricketShot",
+    "24": "CuttingInKitchen",
+    "25": "Diving",
+    "26": "Drumming",
+    "27": "Fencing",
+    "28": "FieldHockeyPenalty",
+    "29": "FloorGymnastics",
+    "30": "FrisbeeCatch",
+    "31": "FrontCrawl",
+    "32": "GolfSwing",
+    "33": "Haircut",
+    "34": "Hammering",
+    "35": "HammerThrow",
+    "36": "HandstandPushups",
+    "37": "HandstandWalking",
+    "38": "HeadMassage",
+    "39": "HighJump",
+    "40": "HorseRace",
+    "41": "HorseRiding",
+    "42": "HulaHoop",
+    "43": "IceDancing",
+    "44": "JavelinThrow",
+    "45": "JugglingBalls",
+    "46": "JumpingJack",
+    "47": "JumpRope",
+    "48": "Kayaking",
+    "49": "Knitting",
+    "50": "LongJump",
+    "51": "Lunges",
+    "52": "MilitaryParade",
+    "53": "Mixing",
+    "54": "MoppingFloor",
+    "55": "Nunchucks",
+    "56": "ParallelBars",
+    "57": "PizzaTossing",
+    "58": "PlayingCello",
+    "59": "PlayingDaf",
+    "60": "PlayingDhol",
+    "61": "PlayingFlute",
+    "62": "PlayingGuitar",
+    "63": "PlayingPiano",
+    "64": "PlayingSitar",
+    "65": "PlayingTabla",
+    "66": "PlayingViolin",
+    "67": "PoleVault",
+    "68": "PommelHorse",
+    "69": "PullUps",
+    "70": "Punch",
+    "71": "PushUps",
+    "72": "Rafting",
+    "73": "RockClimbingIndoor",
+    "74": "RopeClimbing",
+    "75": "Rowing",
+    "76": "SalsaSpin",
+    "77": "ShavingBeard",
+    "78": "Shotput",
+    "79": "SkateBoarding",
+    "80": "Skiing",
+    "81": "Skijet",
+    "82": "SkyDiving",
+    "83": "SoccerJuggling",
+    "84": "SoccerPenalty",
+    "85": "StillRings",
+    "86": "SumoWrestling",
+    "87": "Surfing",
+    "88": "Swing",
+    "89": "TableTennisShot",
+    "90": "TaiChi",
+    "91": "TennisSwing",
+    "92": "ThrowDiscus",
+    "93": "TrampolineJumping",
+    "94": "Typing",
+    "95": "UnevenBars",
+    "96": "VolleyballSpiking",
+    "97": "WalkingWithDog",
+    "98": "WallPushups",
+    "99": "WritingOnBoard",
+    "100": "YoYo"
+  },
+  "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,
+    "Biking": 10,
+    "Billiards": 11,
+    "BlowDryHair": 12,
+    "BlowingCandles": 13,
+    "BodyWeightSquats": 14,
+    "Bowling": 15,
+    "BoxingPunchingBag": 16,
+    "BoxingSpeedBag": 17,
+    "BreastStroke": 18,
+    "BrushingTeeth": 19,
+    "CleanAndJerk": 20,
+    "CliffDiving": 21,
+    "CricketBowling": 22,
+    "CricketShot": 23,
+    "CuttingInKitchen": 24,
+    "Diving": 25,
+    "Drumming": 26,
+    "Fencing": 27,
+    "FieldHockeyPenalty": 28,
+    "FloorGymnastics": 29,
+    "FrisbeeCatch": 30,
+    "FrontCrawl": 31,
+    "GolfSwing": 32,
+    "Haircut": 33,
+    "HammerThrow": 35,
+    "Hammering": 34,
+    "HandstandPushups": 36,
+    "HandstandWalking": 37,
+    "HeadMassage": 38,
+    "HighJump": 39,
+    "HorseRace": 40,
+    "HorseRiding": 41,
+    "HulaHoop": 42,
+    "IceDancing": 43,
+    "JavelinThrow": 44,
+    "JugglingBalls": 45,
+    "JumpRope": 47,
+    "JumpingJack": 46,
+    "Kayaking": 48,
+    "Knitting": 49,
+    "LongJump": 50,
+    "Lunges": 51,
+    "MilitaryParade": 52,
+    "Mixing": 53,
+    "MoppingFloor": 54,
+    "Nunchucks": 55,
+    "ParallelBars": 56,
+    "PizzaTossing": 57,
+    "PlayingCello": 58,
+    "PlayingDaf": 59,
+    "PlayingDhol": 60,
+    "PlayingFlute": 61,
+    "PlayingGuitar": 62,
+    "PlayingPiano": 63,
+    "PlayingSitar": 64,
+    "PlayingTabla": 65,
+    "PlayingViolin": 66,
+    "PoleVault": 67,
+    "PommelHorse": 68,
+    "PullUps": 69,
+    "Punch": 70,
+    "PushUps": 71,
+    "Rafting": 72,
+    "RockClimbingIndoor": 73,
+    "RopeClimbing": 74,
+    "Rowing": 75,
+    "SalsaSpin": 76,
+    "ShavingBeard": 77,
+    "Shotput": 78,
+    "SkateBoarding": 79,
+    "Skiing": 80,
+    "Skijet": 81,
+    "SkyDiving": 82,
+    "SoccerJuggling": 83,
+    "SoccerPenalty": 84,
+    "StillRings": 85,
+    "SumoWrestling": 86,
+    "Surfing": 87,
+    "Swing": 88,
+    "TableTennisShot": 89,
+    "TaiChi": 90,
+    "TennisSwing": 91,
+    "ThrowDiscus": 92,
+    "TrampolineJumping": 93,
+    "Typing": 94,
+    "UnevenBars": 95,
+    "VolleyballSpiking": 96,
+    "WalkingWithDog": 97,
+    "WallPushups": 98,
+    "WritingOnBoard": 99,
+    "YoYo": 100
+  },
+  "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": "4.39.3",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 19.87,
+    "eval_accuracy": 0.8297674418604651,
+    "eval_loss": 0.8198431134223938,
+    "eval_runtime": 374.2016,
+    "eval_samples_per_second": 10.11,
+    "eval_steps_per_second": 0.16
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e8d059b3e48ff7a7fff343212f9b78876c22e219c60ac0edc0c737de608c0d9
+size 345241908

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d877d4dfb4c0feb8ae3075126b2ee31ba78f3f5e9f12c115e5ca83858f087eb2
+size 4343128

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7716cc0c5c91dcd533744af3d195c17fb77e98824b97b7dd36f5c6572d1581a8
+size 3853076

preprocessor_config.json

@@ -0,0 +1,42 @@
+{
+  "_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
+  },
+  "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
+  }
+}

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 19.87,
+    "eval_accuracy": 0.8297674418604651,
+    "eval_loss": 0.8198431134223938,
+    "eval_runtime": 374.2016,
+    "eval_samples_per_second": 10.11,
+    "eval_steps_per_second": 0.16
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 19.87,
+    "train_accuracy": 0.9990563070147845,
+    "train_loss": 0.004719822201877832,
+    "train_runtime": 334.4111,
+    "train_samples_per_second": 28.519,
+    "train_steps_per_second": 0.449
+}

trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_metric": 0.8297674418604651,
+  "best_model_checkpoint": "video/train/checkpoint/videomae-base/ucf101_42/checkpoint-5700",
+  "epoch": 19.871751886001675,
+  "eval_steps": 500,
+  "global_step": 5960,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.01,
+      "eval_accuracy": 0.4886511627906977,
+      "eval_loss": 2.334453582763672,
+      "eval_runtime": 390.4063,
+      "eval_samples_per_second": 9.69,
+      "eval_steps_per_second": 0.154,
+      "step": 300
+    },
+    {
+      "epoch": 2.01,
+      "eval_accuracy": 0.6433488372093024,
+      "eval_loss": 1.4956246614456177,
+      "eval_runtime": 378.3625,
+      "eval_samples_per_second": 9.998,
+      "eval_steps_per_second": 0.159,
+      "step": 600
+    },
+    {
+      "epoch": 3.01,
+      "eval_accuracy": 0.7161860465116279,
+      "eval_loss": 1.1646597385406494,
+      "eval_runtime": 374.5393,
+      "eval_samples_per_second": 10.1,
+      "eval_steps_per_second": 0.16,
+      "step": 900
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 6.9290690422058105,
+      "learning_rate": 4.161073825503356e-05,
+      "loss": 1.5784,
+      "step": 1000
+    },
+    {
+      "epoch": 4.01,
+      "eval_accuracy": 0.7028837209302325,
+      "eval_loss": 1.1531013250350952,
+      "eval_runtime": 376.3709,
+      "eval_samples_per_second": 10.051,
+      "eval_steps_per_second": 0.159,
+      "step": 1200
+    },
+    {
+      "epoch": 5.01,
+      "eval_accuracy": 0.7333953488372092,
+      "eval_loss": 1.0251258611679077,
+      "eval_runtime": 377.2789,
+      "eval_samples_per_second": 10.027,
+      "eval_steps_per_second": 0.159,
+      "step": 1500
+    },
+    {
+      "epoch": 6.01,
+      "eval_accuracy": 0.7333023255813953,
+      "eval_loss": 1.031457781791687,
+      "eval_runtime": 376.6891,
+      "eval_samples_per_second": 10.043,
+      "eval_steps_per_second": 0.159,
+      "step": 1800
+    },
+    {
+      "epoch": 6.67,
+      "grad_norm": 7.911869049072266,
+      "learning_rate": 3.3221476510067115e-05,
+      "loss": 0.1821,
+      "step": 2000
+    },
+    {
+      "epoch": 7.01,
+      "eval_accuracy": 0.7616744186046511,
+      "eval_loss": 0.9787126779556274,
+      "eval_runtime": 379.965,
+      "eval_samples_per_second": 9.956,
+      "eval_steps_per_second": 0.158,
+      "step": 2100
+    },
+    {
+      "epoch": 8.01,
+      "eval_accuracy": 0.7838139534883721,
+      "eval_loss": 0.8932655453681946,
+      "eval_runtime": 375.8521,
+      "eval_samples_per_second": 10.065,
+      "eval_steps_per_second": 0.16,
+      "step": 2400
+    },
+    {
+      "epoch": 9.01,
+      "eval_accuracy": 0.7917209302325582,
+      "eval_loss": 0.8780561089515686,
+      "eval_runtime": 373.4872,
+      "eval_samples_per_second": 10.129,
+      "eval_steps_per_second": 0.161,
+      "step": 2700
+    },
+    {
+      "epoch": 10.01,
+      "grad_norm": 0.12537457048892975,
+      "learning_rate": 2.4832214765100674e-05,
+      "loss": 0.0651,
+      "step": 3000
+    },
+    {
+      "epoch": 10.01,
+      "eval_accuracy": 0.7909767441860465,
+      "eval_loss": 0.9051322937011719,
+      "eval_runtime": 375.6037,
+      "eval_samples_per_second": 10.072,
+      "eval_steps_per_second": 0.16,
+      "step": 3000
+    },
+    {
+      "epoch": 11.01,
+      "eval_accuracy": 0.790046511627907,
+      "eval_loss": 0.9593069553375244,
+      "eval_runtime": 375.7576,
+      "eval_samples_per_second": 10.068,
+      "eval_steps_per_second": 0.16,
+      "step": 3300
+    },
+    {
+      "epoch": 12.01,
+      "eval_accuracy": 0.8186976744186046,
+      "eval_loss": 0.8053779602050781,
+      "eval_runtime": 377.8682,
+      "eval_samples_per_second": 10.011,
+      "eval_steps_per_second": 0.159,
+      "step": 3600
+    },
+    {
+      "epoch": 13.01,
+      "eval_accuracy": 0.8142325581395349,
+      "eval_loss": 0.8678916692733765,
+      "eval_runtime": 376.9615,
+      "eval_samples_per_second": 10.036,
+      "eval_steps_per_second": 0.159,
+      "step": 3900
+    },
+    {
+      "epoch": 13.34,
+      "grad_norm": 10.020633697509766,
+      "learning_rate": 1.644295302013423e-05,
+      "loss": 0.0265,
+      "step": 4000
+    },
+    {
+      "epoch": 14.01,
+      "eval_accuracy": 0.8208372093023256,
+      "eval_loss": 0.8379742503166199,
+      "eval_runtime": 373.9706,
+      "eval_samples_per_second": 10.116,
+      "eval_steps_per_second": 0.16,
+      "step": 4200
+    },
+    {
+      "epoch": 15.01,
+      "eval_accuracy": 0.8246511627906977,
+      "eval_loss": 0.8317446708679199,
+      "eval_runtime": 375.9164,
+      "eval_samples_per_second": 10.063,
+      "eval_steps_per_second": 0.16,
+      "step": 4500
+    },
+    {
+      "epoch": 16.01,
+      "eval_accuracy": 0.8249302325581396,
+      "eval_loss": 0.8027446269989014,
+      "eval_runtime": 375.7325,
+      "eval_samples_per_second": 10.068,
+      "eval_steps_per_second": 0.16,
+      "step": 4800
+    },
+    {
+      "epoch": 16.67,
+      "grad_norm": 0.026239760220050812,
+      "learning_rate": 8.053691275167785e-06,
+      "loss": 0.0091,
+      "step": 5000
+    },
+    {
+      "epoch": 17.01,
+      "eval_accuracy": 0.8254883720930233,
+      "eval_loss": 0.8239758610725403,
+      "eval_runtime": 375.8655,
+      "eval_samples_per_second": 10.065,
+      "eval_steps_per_second": 0.16,
+      "step": 5100
+    },
+    {
+      "epoch": 18.01,
+      "eval_accuracy": 0.8211162790697675,
+      "eval_loss": 0.8480401039123535,
+      "eval_runtime": 375.7779,
+      "eval_samples_per_second": 10.067,
+      "eval_steps_per_second": 0.16,
+      "step": 5400
+    },
+    {
+      "epoch": 19.01,
+      "eval_accuracy": 0.8297674418604651,
+      "eval_loss": 0.8198431134223938,
+      "eval_runtime": 372.9411,
+      "eval_samples_per_second": 10.144,
+      "eval_steps_per_second": 0.161,
+      "step": 5700
+    },
+    {
+      "epoch": 19.87,
+      "eval_accuracy": 0.8282790697674418,
+      "eval_loss": 0.8315407037734985,
+      "eval_runtime": 376.729,
+      "eval_samples_per_second": 10.042,
+      "eval_steps_per_second": 0.159,
+      "step": 5960
+    },
+    {
+      "epoch": 19.87,
+      "step": 5960,
+      "total_flos": 2.3636640203347614e+20,
+      "train_loss": 0.3129509675422771,
+      "train_runtime": 26481.3321,
+      "train_samples_per_second": 7.203,
+      "train_steps_per_second": 0.225
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 5960,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 2.3636640203347614e+20,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094ade010886978e5f04bad871ebb4d486ddbf3e9224aee0d2227da3fcde25a1
+size 5048