Training in progress, epoch 0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.7935483870967742,
+    "eval_loss": 0.5611749291419983,
+    "eval_runtime": 7.9378,
+    "eval_samples_per_second": 19.527,
+    "eval_steps_per_second": 2.52
+}

config.json

@@ -21,7 +21,7 @@
     "6": "BaseballPitch",
     "7": "Basketball",
     "8": "BasketballDunk",
-    "9": "BenchPress"
+    "9": "BenchPressing"
   },
   "image_size": 224,
   "initializer_range": 0.02,
@@ -36,7 +36,7 @@
     "BaseballPitch": 6,
     "Basketball": 7,
     "BasketballDunk": 8,
-    "BenchPress": 9
+    "BenchPressing": 9
   },
   "layer_norm_eps": 1e-12,
   "model_type": "videomae",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6dad31516a1d4f0721d8cb5abc0d5822f93c5d226b00ad8d4055a06ef96473f
+oid sha256:4d4ce75ce3b999ed10392fc215536f50c47d506f7b60bfb9b66f4a4b8696fea9
 size 344961984

runs/Dec09_21-13-29_psroka/events.out.tfevents.1733775401.psroka.814400.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b002b64532de53ed6b2bfb6634e5270470d59747afde77ecad4d889280be43
-size 411
+oid sha256:288f731d74221fdbb82fa510abf06098a7c4e306c45e9d29461c93738f7af2e5
+size 1057

runs/Dec09_21-13-29_psroka/events.out.tfevents.1733776568.psroka.814400.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e410af8f52e77162f5f71316a7e8356716ef4fa0f9b1e068443a2170f6442c
+size 6684

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.7935483870967742,
+    "eval_loss": 0.5611749291419983,
+    "eval_runtime": 7.9378,
+    "eval_samples_per_second": 19.527,
+    "eval_steps_per_second": 2.52
+}

trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_metric": 0.8,
+  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset\\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": 16.5500545501709,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 2.3071,
+      "step": 10
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 7.210005760192871,
+      "learning_rate": 4.9248120300751884e-05,
+      "loss": 2.2612,
+      "step": 20
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 7.997417449951172,
+      "learning_rate": 4.548872180451128e-05,
+      "loss": 2.1719,
+      "step": 30
+    },
+    {
+      "epoch": 0.25675675675675674,
+      "eval_accuracy": 0.17142857142857143,
+      "eval_loss": 2.0525670051574707,
+      "eval_runtime": 3.6401,
+      "eval_samples_per_second": 19.23,
+      "eval_steps_per_second": 2.472,
+      "step": 38
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 7.0121283531188965,
+      "learning_rate": 4.172932330827068e-05,
+      "loss": 1.9451,
+      "step": 40
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 11.407858848571777,
+      "learning_rate": 3.796992481203008e-05,
+      "loss": 1.7221,
+      "step": 50
+    },
+    {
+      "epoch": 1.1486486486486487,
+      "grad_norm": 14.631987571716309,
+      "learning_rate": 3.421052631578947e-05,
+      "loss": 1.4956,
+      "step": 60
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 9.013343811035156,
+      "learning_rate": 3.0451127819548874e-05,
+      "loss": 1.4069,
+      "step": 70
+    },
+    {
+      "epoch": 1.2567567567567568,
+      "eval_accuracy": 0.4714285714285714,
+      "eval_loss": 1.2280380725860596,
+      "eval_runtime": 3.6911,
+      "eval_samples_per_second": 18.964,
+      "eval_steps_per_second": 2.438,
+      "step": 76
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 9.636581420898438,
+      "learning_rate": 2.6691729323308275e-05,
+      "loss": 0.995,
+      "step": 80
+    },
+    {
+      "epoch": 2.0945945945945947,
+      "grad_norm": 9.935404777526855,
+      "learning_rate": 2.293233082706767e-05,
+      "loss": 0.8051,
+      "step": 90
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 9.97338581085205,
+      "learning_rate": 1.9172932330827066e-05,
+      "loss": 0.8465,
+      "step": 100
+    },
+    {
+      "epoch": 2.22972972972973,
+      "grad_norm": 8.2127103805542,
+      "learning_rate": 1.5413533834586467e-05,
+      "loss": 0.6534,
+      "step": 110
+    },
+    {
+      "epoch": 2.2567567567567566,
+      "eval_accuracy": 0.7,
+      "eval_loss": 0.7263602018356323,
+      "eval_runtime": 3.6476,
+      "eval_samples_per_second": 19.191,
+      "eval_steps_per_second": 2.467,
+      "step": 114
+    },
+    {
+      "epoch": 3.0405405405405403,
+      "grad_norm": 8.435063362121582,
+      "learning_rate": 1.1654135338345864e-05,
+      "loss": 0.5543,
+      "step": 120
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 3.56019926071167,
+      "learning_rate": 7.894736842105263e-06,
+      "loss": 0.4172,
+      "step": 130
+    },
+    {
+      "epoch": 3.175675675675676,
+      "grad_norm": 7.430360317230225,
+      "learning_rate": 4.135338345864662e-06,
+      "loss": 0.3677,
+      "step": 140
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.552931547164917,
+      "eval_runtime": 3.5081,
+      "eval_samples_per_second": 19.954,
+      "eval_steps_per_second": 2.565,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "step": 148,
+      "total_flos": 1.460491890402263e+18,
+      "train_loss": 1.2348162676836993,
+      "train_runtime": 139.5019,
+      "train_samples_per_second": 8.487,
+      "train_steps_per_second": 1.061
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.7935483870967742,
+      "eval_loss": 0.561172604560852,
+      "eval_runtime": 7.6883,
+      "eval_samples_per_second": 20.161,
+      "eval_steps_per_second": 2.601,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.7935483870967742,
+      "eval_loss": 0.5611749291419983,
+      "eval_runtime": 7.9378,
+      "eval_samples_per_second": 19.527,
+      "eval_steps_per_second": 2.52,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.7935483870967742,
+      "eval_loss": 0.5611773133277893,
+      "eval_runtime": 7.4937,
+      "eval_samples_per_second": 20.684,
+      "eval_steps_per_second": 2.669,
+      "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
+}