End of training

README.md

@@ -0,0 +1,62 @@
+---
+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: 0.0130
+- Accuracy: 1.0
+
+## 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: 375
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0087        | 0.8   | 300  | 0.0249          | 1.0      |
+| 0.0048        | 1.2   | 375  | 0.0141          | 1.0      |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 1.13.1+cu117
+- Datasets 2.19.2
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.2,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.012984414584934711,
+    "eval_runtime": 65.2088,
+    "eval_samples_per_second": 1.334,
+    "eval_steps_per_second": 0.337
+}

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": "4.42.4",
+  "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 sha256:8265080ddc6ef3e2065fed6b70bfda4a37c7a8ef4022d7578f93b224a9a32257
+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/Aug20_09-50-05_c25ef2b0d98a/events.out.tfevents.1724147436.c25ef2b0d98a.1374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392235ae198ac069d5252ea915ac388e5e979215aa304b89006e0d5c48306966
+size 24912

runs/Aug20_09-50-05_c25ef2b0d98a/events.out.tfevents.1724148929.c25ef2b0d98a.1374.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c13eb0bf6d734331f79a46cffee99a3b07e7af8a939f16868afd45fd093fbb5
+size 411

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.2,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.012984414584934711,
+    "eval_runtime": 65.2088,
+    "eval_samples_per_second": 1.334,
+    "eval_steps_per_second": 0.337
+}

trainer_state.json

@@ -0,0 +1,328 @@
+{
+  "best_metric": 1.0,
+  "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": 26.50551986694336,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 2.3387,
+      "step": 10
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 30.613746643066406,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 2.0688,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 32.245540618896484,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 2.1429,
+      "step": 30
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 19.39073371887207,
+      "learning_rate": 4.9703264094955494e-05,
+      "loss": 1.3632,
+      "step": 40
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 10.221552848815918,
+      "learning_rate": 4.821958456973294e-05,
+      "loss": 0.8581,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 13.818096160888672,
+      "learning_rate": 4.673590504451038e-05,
+      "loss": 0.862,
+      "step": 60
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 30.478605270385742,
+      "learning_rate": 4.525222551928784e-05,
+      "loss": 0.6552,
+      "step": 70
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.36535993218421936,
+      "learning_rate": 4.3768545994065286e-05,
+      "loss": 0.3451,
+      "step": 80
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 6.710868835449219,
+      "learning_rate": 4.228486646884273e-05,
+      "loss": 0.534,
+      "step": 90
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 25.211732864379883,
+      "learning_rate": 4.080118694362018e-05,
+      "loss": 0.3819,
+      "step": 100
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 7.926482677459717,
+      "learning_rate": 3.9317507418397627e-05,
+      "loss": 0.0965,
+      "step": 110
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.26946061849594116,
+      "learning_rate": 3.783382789317508e-05,
+      "loss": 0.4015,
+      "step": 120
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.7694262266159058,
+      "learning_rate": 3.635014836795252e-05,
+      "loss": 0.2223,
+      "step": 130
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.0302479267120361,
+      "learning_rate": 3.4866468842729974e-05,
+      "loss": 0.3088,
+      "step": 140
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 13.570771217346191,
+      "learning_rate": 3.338278931750742e-05,
+      "loss": 0.1342,
+      "step": 150
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.18270577490329742,
+      "learning_rate": 3.189910979228487e-05,
+      "loss": 0.3541,
+      "step": 160
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 0.24952581524848938,
+      "learning_rate": 3.0415430267062318e-05,
+      "loss": 0.145,
+      "step": 170
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.18914468586444855,
+      "learning_rate": 2.8931750741839762e-05,
+      "loss": 0.2112,
+      "step": 180
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.3731645941734314,
+      "learning_rate": 2.744807121661721e-05,
+      "loss": 0.0727,
+      "step": 190
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.33601468801498413,
+      "learning_rate": 2.5964391691394662e-05,
+      "loss": 0.0327,
+      "step": 200
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.794644355773926,
+      "learning_rate": 2.4480712166172106e-05,
+      "loss": 0.0168,
+      "step": 210
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.25008541345596313,
+      "learning_rate": 2.2997032640949558e-05,
+      "loss": 0.0082,
+      "step": 220
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 0.1409362554550171,
+      "learning_rate": 2.1513353115727002e-05,
+      "loss": 0.0104,
+      "step": 230
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.2816823720932007,
+      "learning_rate": 2.0029673590504454e-05,
+      "loss": 0.0111,
+      "step": 240
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.09208779036998749,
+      "learning_rate": 1.85459940652819e-05,
+      "loss": 0.0078,
+      "step": 250
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.1806335598230362,
+      "learning_rate": 1.706231454005935e-05,
+      "loss": 0.0187,
+      "step": 260
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.12033367902040482,
+      "learning_rate": 1.5578635014836794e-05,
+      "loss": 0.0155,
+      "step": 270
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.18079906702041626,
+      "learning_rate": 1.4094955489614246e-05,
+      "loss": 0.3202,
+      "step": 280
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 0.1464352011680603,
+      "learning_rate": 1.2611275964391692e-05,
+      "loss": 0.0041,
+      "step": 290
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.09388105571269989,
+      "learning_rate": 1.112759643916914e-05,
+      "loss": 0.0087,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.024852987378835678,
+      "eval_runtime": 26.7584,
+      "eval_samples_per_second": 1.383,
+      "eval_steps_per_second": 0.374,
+      "step": 300
+    },
+    {
+      "epoch": 1.0266666666666666,
+      "grad_norm": 0.42200812697410583,
+      "learning_rate": 9.643916913946588e-06,
+      "loss": 0.0057,
+      "step": 310
+    },
+    {
+      "epoch": 1.0533333333333332,
+      "grad_norm": 0.05835086107254028,
+      "learning_rate": 8.160237388724036e-06,
+      "loss": 0.0047,
+      "step": 320
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.12930744886398315,
+      "learning_rate": 6.676557863501484e-06,
+      "loss": 0.0028,
+      "step": 330
+    },
+    {
+      "epoch": 1.1066666666666667,
+      "grad_norm": 0.07907194644212723,
+      "learning_rate": 5.192878338278932e-06,
+      "loss": 0.0033,
+      "step": 340
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.11033826321363449,
+      "learning_rate": 3.7091988130563796e-06,
+      "loss": 0.0035,
+      "step": 350
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.0931745767593384,
+      "learning_rate": 2.225519287833828e-06,
+      "loss": 0.0276,
+      "step": 360
+    },
+    {
+      "epoch": 1.1866666666666668,
+      "grad_norm": 0.21536993980407715,
+      "learning_rate": 7.41839762611276e-07,
+      "loss": 0.0048,
+      "step": 370
+    },
+    {
+      "epoch": 1.2,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.014085639268159866,
+      "eval_runtime": 26.8334,
+      "eval_samples_per_second": 1.379,
+      "eval_steps_per_second": 0.373,
+      "step": 375
+    },
+    {
+      "epoch": 1.2,
+      "step": 375,
+      "total_flos": 9.6083444588544e+17,
+      "train_loss": 0.37345028610527514,
+      "train_runtime": 669.2197,
+      "train_samples_per_second": 0.56,
+      "train_steps_per_second": 0.56
+    },
+    {
+      "epoch": 1.2,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.012984414584934711,
+      "eval_runtime": 65.2088,
+      "eval_samples_per_second": 1.334,
+      "eval_steps_per_second": 0.337,
+      "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 sha256:898f5d908198edd60c2d7aea1a8d2ffcefb83eb529f992b0bbbd46854d9c7e0f
+size 4731