End of training

README.md

@@ -0,0 +1,80 @@
+---
+license: cc-by-nc-4.0
+base_model: MCG-NJU/videomae-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: videomae-base-finetuned-slrbd002
+  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-slrbd002
+
+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: 0.4824
+- Accuracy: 0.875
+
+## 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: 1800
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.6684        | 0.05  | 90   | 3.6696          | 0.025    |
+| 3.4781        | 1.05  | 180  | 3.3494          | 0.1313   |
+| 3.2885        | 2.05  | 270  | 3.1702          | 0.125    |
+| 2.7847        | 3.05  | 360  | 2.7654          | 0.2562   |
+| 2.4107        | 4.05  | 450  | 2.6756          | 0.2437   |
+| 1.7783        | 5.05  | 540  | 1.9950          | 0.4813   |
+| 1.3054        | 6.05  | 630  | 1.4908          | 0.6188   |
+| 0.5868        | 7.05  | 720  | 1.4568          | 0.6188   |
+| 0.4388        | 8.05  | 810  | 0.9511          | 0.7312   |
+| 0.2187        | 9.05  | 900  | 1.1580          | 0.65     |
+| 0.1665        | 10.05 | 990  | 0.6565          | 0.8313   |
+| 0.0959        | 11.05 | 1080 | 0.5731          | 0.8562   |
+| 0.0273        | 12.05 | 1170 | 0.6637          | 0.8063   |
+| 0.02          | 13.05 | 1260 | 0.5048          | 0.875    |
+| 0.0137        | 14.05 | 1350 | 0.4815          | 0.8688   |
+| 0.0261        | 15.05 | 1440 | 0.5649          | 0.8438   |
+| 0.013         | 16.05 | 1530 | 0.5419          | 0.8375   |
+| 0.0123        | 17.05 | 1620 | 0.4864          | 0.8812   |
+| 0.0527        | 18.05 | 1710 | 0.4725          | 0.8875   |
+| 0.011         | 19.05 | 1800 | 0.4824          | 0.875    |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,115 @@
+{
+  "_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": "Reject",
+    "1": "Pass",
+    "2": "Invisible",
+    "3": "Absent",
+    "4": "Torture",
+    "5": "Permission",
+    "6": "Dishonest",
+    "7": "Insult",
+    "8": "Complain",
+    "9": "Hit",
+    "10": "Save",
+    "11": "Bring",
+    "12": "Request",
+    "13": "Start",
+    "14": "Seperate",
+    "15": "Talk",
+    "16": "Turn off the light",
+    "17": "Come",
+    "18": "Lift",
+    "19": "Advise",
+    "20": "Encourage",
+    "21": "Welding",
+    "22": "Trouble",
+    "23": "Crying",
+    "24": "Whisper",
+    "25": "Shave",
+    "26": "Qurbani",
+    "27": "Embrace",
+    "28": "Dig",
+    "29": "Making Noise",
+    "30": "Bath",
+    "31": "Hate",
+    "32": "Sleep",
+    "33": "Rotate",
+    "34": "want",
+    "35": "think",
+    "36": "kiss",
+    "37": "steal",
+    "38": "try",
+    "39": "tear"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Absent": 3,
+    "Advise": 19,
+    "Bath": 30,
+    "Bring": 11,
+    "Come": 17,
+    "Complain": 8,
+    "Crying": 23,
+    "Dig": 28,
+    "Dishonest": 6,
+    "Embrace": 27,
+    "Encourage": 20,
+    "Hate": 31,
+    "Hit": 9,
+    "Insult": 7,
+    "Invisible": 2,
+    "Lift": 18,
+    "Making Noise": 29,
+    "Pass": 1,
+    "Permission": 5,
+    "Qurbani": 26,
+    "Reject": 0,
+    "Request": 12,
+    "Rotate": 33,
+    "Save": 10,
+    "Seperate": 14,
+    "Shave": 25,
+    "Sleep": 32,
+    "Start": 13,
+    "Talk": 15,
+    "Torture": 4,
+    "Trouble": 22,
+    "Turn off the light": 16,
+    "Welding": 21,
+    "Whisper": 24,
+    "kiss": 36,
+    "steal": 37,
+    "tear": 39,
+    "think": 35,
+    "try": 38,
+    "want": 34
+  },
+  "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": "4.35.2",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493a1c344674240bc53614445d53a684f48e7e71b0c63482ba2b481ba7781277
+size 345054272

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,
+  "feature_extractor_type": "VideoMAEFeatureExtractor",
+  "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
+  }
+}

runs/Nov30_19-00-09_c532803dfe77/events.out.tfevents.1701370834.c532803dfe77.353.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d500e53c4f9b20bd4334daf57fb92c129e86c92636ec255f9f27c0a118094e5
+size 40972

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c346463b9e27a68968b27a30fd4eaa034cc097d21ec00f22444443c322e02b
+size 4600