Model save

README.md

@@ -0,0 +1,74 @@
+---
+library_name: transformers
+license: cc-by-nc-4.0
+base_model: MCG-NJU/videomae-base-finetuned-kinetics
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: VideoMAE_Kinetics_fold__2__BdSLW60_SKF
+  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_Kinetics_fold__2__BdSLW60_SKF
+
+This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0307
+- Accuracy: 0.9925
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- 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: 9030
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 8.3956        | 0.1    | 903  | 0.3172          | 0.9601   |
+| 0.408         | 1.1001 | 1807 | 0.0426          | 0.9888   |
+| 0.0963        | 2.1    | 2710 | 0.0403          | 0.9900   |
+| 0.051         | 3.1001 | 3614 | 0.0611          | 0.9813   |
+| 0.0393        | 4.1    | 4517 | 0.0298          | 0.9950   |
+| 0.0309        | 5.1001 | 5421 | 0.0453          | 0.9863   |
+| 0.0061        | 6.1    | 6324 | 0.0409          | 0.9875   |
+| 0.0122        | 7.1001 | 7228 | 0.0552          | 0.9913   |
+| 0.0039        | 8.1    | 8131 | 0.0272          | 0.9938   |
+| 0.0066        | 9.0995 | 9030 | 0.0307          | 0.9925   |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.1

checkpoint/config.json

@@ -0,0 +1,155 @@
+{
+  "_name_or_path": "MCG-NJU/videomae-base-finetuned-kinetics",
+  "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": "aam",
+    "1": "aaple",
+    "2": "ac",
+    "3": "aids",
+    "4": "alu",
+    "5": "anaros",
+    "6": "angur",
+    "7": "apartment",
+    "8": "attio",
+    "9": "audio cassette",
+    "10": "ayna",
+    "11": "baandej",
+    "12": "baat",
+    "13": "baba",
+    "14": "balti",
+    "15": "balu",
+    "16": "bhai",
+    "17": "biscuts",
+    "18": "bon",
+    "19": "boroi",
+    "20": "bottam",
+    "21": "bou",
+    "22": "cake",
+    "23": "capsule",
+    "24": "cha",
+    "25": "chacha",
+    "26": "chachi",
+    "27": "chadar",
+    "28": "chal",
+    "29": "chikissha",
+    "30": "chini",
+    "31": "chips",
+    "32": "chiruni",
+    "33": "chocolate",
+    "34": "chokh utha",
+    "35": "chosma",
+    "36": "churi",
+    "37": "clip",
+    "38": "cream",
+    "39": "dada",
+    "40": "dadi",
+    "41": "daeitto",
+    "42": "dal",
+    "43": "debor",
+    "44": "denadar",
+    "45": "dengue",
+    "46": "doctor",
+    "47": "dongson",
+    "48": "dulavai",
+    "49": "durbol",
+    "50": "jomoj",
+    "51": "juta",
+    "52": "konna",
+    "53": "maa",
+    "54": "tattha",
+    "55": "toothpaste",
+    "56": "tshirt",
+    "57": "tubelight",
+    "58": "tupi",
+    "59": "tv"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "aam": 0,
+    "aaple": 1,
+    "ac": 2,
+    "aids": 3,
+    "alu": 4,
+    "anaros": 5,
+    "angur": 6,
+    "apartment": 7,
+    "attio": 8,
+    "audio cassette": 9,
+    "ayna": 10,
+    "baandej": 11,
+    "baat": 12,
+    "baba": 13,
+    "balti": 14,
+    "balu": 15,
+    "bhai": 16,
+    "biscuts": 17,
+    "bon": 18,
+    "boroi": 19,
+    "bottam": 20,
+    "bou": 21,
+    "cake": 22,
+    "capsule": 23,
+    "cha": 24,
+    "chacha": 25,
+    "chachi": 26,
+    "chadar": 27,
+    "chal": 28,
+    "chikissha": 29,
+    "chini": 30,
+    "chips": 31,
+    "chiruni": 32,
+    "chocolate": 33,
+    "chokh utha": 34,
+    "chosma": 35,
+    "churi": 36,
+    "clip": 37,
+    "cream": 38,
+    "dada": 39,
+    "dadi": 40,
+    "daeitto": 41,
+    "dal": 42,
+    "debor": 43,
+    "denadar": 44,
+    "dengue": 45,
+    "doctor": 46,
+    "dongson": 47,
+    "dulavai": 48,
+    "durbol": 49,
+    "jomoj": 50,
+    "juta": 51,
+    "konna": 52,
+    "maa": 53,
+    "tattha": 54,
+    "toothpaste": 55,
+    "tshirt": 56,
+    "tubelight": 57,
+    "tupi": 58,
+    "tv": 59
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "videomae",
+  "norm_pix_loss": false,
+  "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": "4.46.1",
+  "tubelet_size": 2,
+  "use_mean_pooling": true
+}

checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccb09cd2dbf0e268ad28604230cd9e174b180d55f16912851dabebe61a0b2678
+size 345115752

checkpoint/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
+  }
+}

checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e84d7b92ddf35c294748ce436b84105af0566d64354ad9929b2f6ff1c9f303d
+size 5368

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf4268e88e3318357e728b7b3c813bc81a63bf6cdf0869fed2c71d755aa243a
+oid sha256:ccb09cd2dbf0e268ad28604230cd9e174b180d55f16912851dabebe61a0b2678
 size 345115752