End of training

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: mit
+base_model: google/vivit-b-16x2-kinetics400
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: vivit-b-16x2-kinetics400-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. -->
+
+# vivit-b-16x2-kinetics400-finetuned-ucf101-subset
+
+This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0847
+- Accuracy: 0.9770
+
+## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 375
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.327         | 0.8   | 300  | 0.0413          | 0.9730   |
+| 0.0028        | 1.2   | 375  | 0.0248          | 0.9730   |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 1.13.1+cu117
+- Datasets 3.2.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.2,
+    "eval_accuracy": 0.9770114942528736,
+    "eval_loss": 0.08467210084199905,
+    "eval_runtime": 66.0112,
+    "eval_samples_per_second": 1.318,
+    "eval_steps_per_second": 0.333
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "google/vivit-b-16x2-kinetics400",
+  "architectures": [
+    "VivitForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "hidden_act": "gelu_fast",
+  "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-06,
+  "model_type": "vivit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_frames": 32,
+  "num_hidden_layers": 12,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "tubelet_size": [
+    2,
+    16,
+    16
+  ],
+  "video_size": [
+    32,
+    224,
+    224
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02ecc07cf862d42aad0761e09db3feff691ca431af7684a9f311bf6e1f20490
+size 354639992

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "VivitImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "offset": true,
+  "resample": 2,
+  "rescale_factor": 0.00784313725490196,
+  "size": {
+    "shortest_edge": 224
+  }
+}

runs/Jan04_07-56-11_3c93a9449ec1/events.out.tfevents.1735977375.3c93a9449ec1.266.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5294239d63153b5140e489deea6228633dc922b0a4649a59a77f0c944005819c
+size 25578

runs/Jan04_07-56-11_3c93a9449ec1/events.out.tfevents.1735978156.3c93a9449ec1.266.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:884bbaccd0fb740220f1e67f0fd1e3cd7c99c3856cf73b471cd6f9f367d3a13f
+size 411

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.2,
+    "eval_accuracy": 0.9770114942528736,
+    "eval_loss": 0.08467210084199905,
+    "eval_runtime": 66.0112,
+    "eval_samples_per_second": 1.318,
+    "eval_steps_per_second": 0.333
+}

trainer_state.json

@@ -0,0 +1,328 @@
+{
+  "best_metric": 0.972972972972973,
+  "best_model_checkpoint": "vivit-b-16x2-kinetics400-finetuned-ucf101-subset/checkpoint-300",
+  "epoch": 1.2,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 30.73906707763672,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 2.5162,
+      "step": 10
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 30.56110382080078,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 1.974,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 30.580888748168945,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 1.7732,
+      "step": 30
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 24.04612159729004,
+      "learning_rate": 4.9703264094955494e-05,
+      "loss": 1.4326,
+      "step": 40
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 13.380224227905273,
+      "learning_rate": 4.821958456973294e-05,
+      "loss": 0.9701,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 27.399700164794922,
+      "learning_rate": 4.673590504451038e-05,
+      "loss": 0.8552,
+      "step": 60
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 31.170425415039062,
+      "learning_rate": 4.525222551928784e-05,
+      "loss": 0.6236,
+      "step": 70
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.6463847160339355,
+      "learning_rate": 4.3768545994065286e-05,
+      "loss": 0.3492,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 6.623310565948486,
+      "learning_rate": 4.228486646884273e-05,
+      "loss": 0.4079,
+      "step": 90
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 15.640702247619629,
+      "learning_rate": 4.080118694362018e-05,
+      "loss": 0.6108,
+      "step": 100
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 4.277254104614258,
+      "learning_rate": 3.9317507418397627e-05,
+      "loss": 0.0964,
+      "step": 110
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.38755565881729126,
+      "learning_rate": 3.783382789317508e-05,
+      "loss": 0.3366,
+      "step": 120
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.2960447072982788,
+      "learning_rate": 3.635014836795252e-05,
+      "loss": 0.4302,
+      "step": 130
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.9863858222961426,
+      "learning_rate": 3.4866468842729974e-05,
+      "loss": 0.2443,
+      "step": 140
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 16.24022102355957,
+      "learning_rate": 3.338278931750742e-05,
+      "loss": 0.1272,
+      "step": 150
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.1514637470245361,
+      "learning_rate": 3.189910979228487e-05,
+      "loss": 0.4169,
+      "step": 160
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.1362906694412231,
+      "learning_rate": 3.0415430267062318e-05,
+      "loss": 0.1192,
+      "step": 170
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.12466049939393997,
+      "learning_rate": 2.8931750741839762e-05,
+      "loss": 0.4113,
+      "step": 180
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.7614925503730774,
+      "learning_rate": 2.744807121661721e-05,
+      "loss": 0.0469,
+      "step": 190
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.4682028889656067,
+      "learning_rate": 2.5964391691394662e-05,
+      "loss": 0.0311,
+      "step": 200
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.858252227306366,
+      "learning_rate": 2.4480712166172106e-05,
+      "loss": 0.017,
+      "step": 210
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.2377556562423706,
+      "learning_rate": 2.2997032640949558e-05,
+      "loss": 0.0082,
+      "step": 220
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.10321161895990372,
+      "learning_rate": 2.1513353115727002e-05,
+      "loss": 0.0069,
+      "step": 230
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.6798615455627441,
+      "learning_rate": 2.0029673590504454e-05,
+      "loss": 0.0098,
+      "step": 240
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.1340479999780655,
+      "learning_rate": 1.85459940652819e-05,
+      "loss": 0.0083,
+      "step": 250
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.24002894759178162,
+      "learning_rate": 1.706231454005935e-05,
+      "loss": 0.0324,
+      "step": 260
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.1034119501709938,
+      "learning_rate": 1.5578635014836794e-05,
+      "loss": 0.011,
+      "step": 270
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.1348913013935089,
+      "learning_rate": 1.4094955489614246e-05,
+      "loss": 0.2374,
+      "step": 280
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.19884160161018372,
+      "learning_rate": 1.2611275964391692e-05,
+      "loss": 0.0041,
+      "step": 290
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.0887996107339859,
+      "learning_rate": 1.112759643916914e-05,
+      "loss": 0.327,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.972972972972973,
+      "eval_loss": 0.041303958743810654,
+      "eval_runtime": 27.5663,
+      "eval_samples_per_second": 1.342,
+      "eval_steps_per_second": 0.363,
+      "step": 300
+    },
+    {
+      "epoch": 1.0266666666666666,
+      "grad_norm": 0.4455372393131256,
+      "learning_rate": 9.643916913946588e-06,
+      "loss": 0.0062,
+      "step": 310
+    },
+    {
+      "epoch": 1.0533333333333332,
+      "grad_norm": 0.0666133463382721,
+      "learning_rate": 8.160237388724036e-06,
+      "loss": 0.0063,
+      "step": 320
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.16947615146636963,
+      "learning_rate": 6.676557863501484e-06,
+      "loss": 0.0026,
+      "step": 330
+    },
+    {
+      "epoch": 1.1066666666666667,
+      "grad_norm": 0.07509300112724304,
+      "learning_rate": 5.192878338278932e-06,
+      "loss": 0.0029,
+      "step": 340
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.06688421964645386,
+      "learning_rate": 3.7091988130563796e-06,
+      "loss": 0.0038,
+      "step": 350
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.4143649339675903,
+      "learning_rate": 2.225519287833828e-06,
+      "loss": 0.0548,
+      "step": 360
+    },
+    {
+      "epoch": 1.1866666666666668,
+      "grad_norm": 0.1942415088415146,
+      "learning_rate": 7.41839762611276e-07,
+      "loss": 0.0028,
+      "step": 370
+    },
+    {
+      "epoch": 1.2,
+      "eval_accuracy": 0.972972972972973,
+      "eval_loss": 0.024778272956609726,
+      "eval_runtime": 28.2328,
+      "eval_samples_per_second": 1.311,
+      "eval_steps_per_second": 0.354,
+      "step": 375
+    },
+    {
+      "epoch": 1.2,
+      "step": 375,
+      "total_flos": 9.6083444588544e+17,
+      "train_loss": 0.3870846853355567,
+      "train_runtime": 685.2516,
+      "train_samples_per_second": 0.547,
+      "train_steps_per_second": 0.547
+    },
+    {
+      "epoch": 1.2,
+      "eval_accuracy": 0.9770114942528736,
+      "eval_loss": 0.08467210084199905,
+      "eval_runtime": 66.0112,
+      "eval_samples_per_second": 1.318,
+      "eval_steps_per_second": 0.333,
+      "step": 375
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.6083444588544e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed3bb6f76a457d47751569a243e45f065311f9b180cfe548e8d8e50ddbed48a
+size 4987