End of training

README.md

@@ -0,0 +1,66 @@
+---
+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_fixed_split_analysis_BDSLW60_3_CLASS
+  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_fixed_split_analysis_BDSLW60_3_CLASS
+
+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: 0.0005
+- 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: 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: 88
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 1.065         | 0.5    | 44   | 0.0014          | 1.0      |
+| 0.0019        | 1.4972 | 88   | 0.0005          | 1.0      |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.1

config.json

@@ -0,0 +1,41 @@
+{
+  "_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": "ac",
+    "1": "aam",
+    "2": "aaple"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "aam": 1,
+    "aaple": 2,
+    "ac": 0
+  },
+  "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
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546c97938e4eeef9b0d6e843ea525cdd61277b4ba0969875647de4c9356c5b5a
+size 344940412

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
+  }
+}

trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 1.0,
+  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/VideoMAE_fixed_split_analysis_BDSLW60_3_CLASS/checkpoint-44",
+  "epoch": 1.4971590909090908,
+  "eval_steps": 500,
+  "global_step": 88,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.7211317420005798,
+      "learning_rate": 2.848101265822785e-05,
+      "loss": 1.065,
+      "step": 44
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0014007322024554014,
+      "eval_runtime": 17.0657,
+      "eval_samples_per_second": 1.817,
+      "eval_steps_per_second": 0.938,
+      "step": 44
+    },
+    {
+      "epoch": 1.4971590909090908,
+      "grad_norm": 0.02409316599369049,
+      "learning_rate": 6.329113924050633e-07,
+      "loss": 0.0019,
+      "step": 88
+    },
+    {
+      "epoch": 1.4971590909090908,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.0005012789042666554,
+      "eval_runtime": 17.1038,
+      "eval_samples_per_second": 1.812,
+      "eval_steps_per_second": 0.935,
+      "step": 88
+    },
+    {
+      "epoch": 1.4971590909090908,
+      "step": 88,
+      "total_flos": 8.759912185417236e+17,
+      "train_loss": 0.5334262637929483,
+      "train_runtime": 356.9505,
+      "train_samples_per_second": 1.972,
+      "train_steps_per_second": 0.247
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 88,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.759912185417236e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ba9d1be32755320296079466b228c3b37d06ca05106e71d9e4c2099dd415c4
+size 5368