End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sample.gif filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+license: cc-by-nc-4.0
+base_model: MCG-NJU/videomae-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: working
+  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. -->
+
+# working
+
+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: 2.3559
+- Top 1 Accuracy: 0.1562
+- Top 5 Accuracy: 0.5
+- Top 10 Accuracy: 1.0
+- Accuracy: 0.1562
+- Precision: 0.1367
+- Recall: 0.1562
+- F1: 0.0990
+
+## 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
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 17
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Top 1 Accuracy | Top 5 Accuracy | Top 10 Accuracy | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:--------------:|:---------------:|:--------:|:---------:|:------:|:------:|
+| No log        | 0.4706 | 8    | 2.3478          | 0.0312         | 0.4688         | 1.0             | 0.0312   | 0.0063    | 0.0312 | 0.0104 |
+| No log        | 1.4853 | 17   | 2.3559          | 0.1562         | 0.5            | 1.0             | 0.1562   | 0.1367    | 0.1562 | 0.0990 |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 1.11.0+cu102
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "accuracy": 0.037037037037037035,
+    "f1": 0.005925925925925926,
+    "precision": 0.00322061191626409,
+    "recall": 0.037037037037037035,
+    "top_10_accuracy": 1.0,
+    "top_1_accuracy": 0.037037037037037035,
+    "top_5_accuracy": 0.4074074074074074
+}

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": "accident",
+    "1": "africa",
+    "2": "all",
+    "3": "apple",
+    "4": "basketball",
+    "5": "bed",
+    "6": "before",
+    "7": "bird",
+    "8": "birthday",
+    "9": "black"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "accident": 0,
+    "africa": 1,
+    "all": 2,
+    "apple": 3,
+    "basketball": 4,
+    "bed": 5,
+    "before": 6,
+    "bird": 7,
+    "birthday": 8,
+    "black": 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": "4.44.0",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8768b95b8be983f716c0283a1781f80cc6c7ca066af2cb5672ed3bda23ac109e
+size 344961984

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
+  }
+}

test_results.json

@@ -0,0 +1,9 @@
+{
+    "accuracy": 0.037037037037037035,
+    "f1": 0.005925925925925926,
+    "precision": 0.00322061191626409,
+    "recall": 0.037037037037037035,
+    "top_10_accuracy": 1.0,
+    "top_1_accuracy": 0.037037037037037035,
+    "top_5_accuracy": 0.4074074074074074
+}

trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.15625,
+  "best_model_checkpoint": "/kaggle/working/checkpoint-17",
+  "epoch": 1.4852941176470589,
+  "eval_steps": 500,
+  "global_step": 17,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47058823529411764,
+      "eval_accuracy": 0.03125,
+      "eval_f1": 0.010416666666666666,
+      "eval_loss": 2.347832679748535,
+      "eval_precision": 0.00625,
+      "eval_recall": 0.03125,
+      "eval_runtime": 5.3844,
+      "eval_samples_per_second": 5.943,
+      "eval_steps_per_second": 1.486,
+      "eval_top_10_accuracy": 1.0,
+      "eval_top_1_accuracy": 0.03125,
+      "eval_top_5_accuracy": 0.46875,
+      "step": 8
+    },
+    {
+      "epoch": 1.4852941176470589,
+      "eval_accuracy": 0.15625,
+      "eval_f1": 0.09895833333333333,
+      "eval_loss": 2.3559300899505615,
+      "eval_precision": 0.13671875,
+      "eval_recall": 0.15625,
+      "eval_runtime": 5.5018,
+      "eval_samples_per_second": 5.816,
+      "eval_steps_per_second": 1.454,
+      "eval_top_10_accuracy": 1.0,
+      "eval_top_1_accuracy": 0.15625,
+      "eval_top_5_accuracy": 0.5,
+      "step": 17
+    },
+    {
+      "epoch": 1.4852941176470589,
+      "step": 17,
+      "total_flos": 3.3895374930837504e+17,
+      "train_loss": 2.3516208424287686,
+      "train_runtime": 111.1739,
+      "train_samples_per_second": 2.447,
+      "train_steps_per_second": 0.153
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 17,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 20,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.3895374930837504e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd09c72001d33e2207fee64ce97c506d3b244e526ec1acc22f19198fdddbbcf
+size 4719