Training in progress, epoch 0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8709677419354839,
+    "eval_loss": 0.43750718235969543,
+    "eval_runtime": 85.0791,
+    "eval_samples_per_second": 1.822,
+    "eval_steps_per_second": 0.235
+}

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": "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-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": "4.46.3",
+  "tubelet_size": 2,
+  "use_mean_pooling": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0290bfefe5382a03ebfa691b6f16d67944ace3eb832871142cc0af4ce57fe270
+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
+  }
+}

runs/Jun19_10-43-34_DESKTOP-SB6JNG7/events.out.tfevents.1750297416.DESKTOP-SB6JNG7.52840.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e1837fe952e626eeef15b4423e1657de57d4375abe49cfdde51909ff81138e
+size 10294

runs/Jun19_10-43-34_DESKTOP-SB6JNG7/events.out.tfevents.1750306258.DESKTOP-SB6JNG7.52840.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf383a3e8381e7bf96e6414b4c1bfa30eb69e9127bb357c65b5fcab04c0a3f7
+size 734

runs/Jun19_13-21-55_DESKTOP-SB6JNG7/events.out.tfevents.1750306917.DESKTOP-SB6JNG7.64600.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb64f6f1d9a4285d46a99a8cdc9ef7763f411411db1a652cdba906fa67f5e73
+size 6697

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8709677419354839,
+    "eval_loss": 0.43750718235969543,
+    "eval_runtime": 85.0791,
+    "eval_samples_per_second": 1.822,
+    "eval_steps_per_second": 0.235
+}

trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": 0.9142857142857143,
+  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset-v1\\checkpoint-148",
+  "epoch": 3.22972972972973,
+  "eval_steps": 500,
+  "global_step": 148,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06756756756756757,
+      "grad_norm": 6.731034755706787,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.3848,
+      "step": 10
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 6.5651068687438965,
+      "learning_rate": 4.81203007518797e-05,
+      "loss": 2.2244,
+      "step": 20
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 7.565842628479004,
+      "learning_rate": 4.43609022556391e-05,
+      "loss": 2.147,
+      "step": 30
+    },
+    {
+      "epoch": 0.25675675675675674,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.824847936630249,
+      "eval_runtime": 33.6828,
+      "eval_samples_per_second": 2.078,
+      "eval_steps_per_second": 0.267,
+      "step": 38
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 10.557822227478027,
+      "learning_rate": 4.0601503759398494e-05,
+      "loss": 1.9194,
+      "step": 40
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 10.348827362060547,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.5348,
+      "step": 50
+    },
+    {
+      "epoch": 1.1486486486486487,
+      "grad_norm": 11.006094932556152,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 1.2304,
+      "step": 60
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 5.256627082824707,
+      "learning_rate": 2.9323308270676693e-05,
+      "loss": 0.8396,
+      "step": 70
+    },
+    {
+      "epoch": 1.2567567567567568,
+      "eval_accuracy": 0.6142857142857143,
+      "eval_loss": 0.9721823334693909,
+      "eval_runtime": 36.3573,
+      "eval_samples_per_second": 1.925,
+      "eval_steps_per_second": 0.248,
+      "step": 76
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 4.99444055557251,
+      "learning_rate": 2.556390977443609e-05,
+      "loss": 0.8093,
+      "step": 80
+    },
+    {
+      "epoch": 2.0945945945945947,
+      "grad_norm": 9.838152885437012,
+      "learning_rate": 2.1804511278195487e-05,
+      "loss": 0.5768,
+      "step": 90
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 9.252472877502441,
+      "learning_rate": 1.8045112781954888e-05,
+      "loss": 0.5616,
+      "step": 100
+    },
+    {
+      "epoch": 2.22972972972973,
+      "grad_norm": 7.304188251495361,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.4296,
+      "step": 110
+    },
+    {
+      "epoch": 2.2567567567567566,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.5079787373542786,
+      "eval_runtime": 40.7547,
+      "eval_samples_per_second": 1.718,
+      "eval_steps_per_second": 0.221,
+      "step": 114
+    },
+    {
+      "epoch": 3.0405405405405403,
+      "grad_norm": 4.385380268096924,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.3622,
+      "step": 120
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 2.2507898807525635,
+      "learning_rate": 6.766917293233083e-06,
+      "loss": 0.283,
+      "step": 130
+    },
+    {
+      "epoch": 3.175675675675676,
+      "grad_norm": 6.637970447540283,
+      "learning_rate": 3.007518796992481e-06,
+      "loss": 0.3317,
+      "step": 140
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.9142857142857143,
+      "eval_loss": 0.3879334330558777,
+      "eval_runtime": 34.481,
+      "eval_samples_per_second": 2.03,
+      "eval_steps_per_second": 0.261,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "step": 148,
+      "total_flos": 1.460491890402263e+18,
+      "train_loss": 1.0702395809663308,
+      "train_runtime": 2008.0611,
+      "train_samples_per_second": 0.59,
+      "train_steps_per_second": 0.074
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8709677419354839,
+      "eval_loss": 0.43750718235969543,
+      "eval_runtime": 85.095,
+      "eval_samples_per_second": 1.821,
+      "eval_steps_per_second": 0.235,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8709677419354839,
+      "eval_loss": 0.43750718235969543,
+      "eval_runtime": 85.0791,
+      "eval_samples_per_second": 1.822,
+      "eval_steps_per_second": 0.235,
+      "step": 148
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 148,
+  "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": 1.460491890402263e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16251de35f4e47caef0b9f54fb7437e00538a304bf33d77db0ded44a78e54174
+size 4923