End of training

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.7935483870967742,
+    "eval_loss": 0.44589877128601074,
+    "eval_runtime": 67.6453,
+    "eval_samples_per_second": 2.291,
+    "eval_steps_per_second": 0.296
+}

runs/Aug19_18-32-49_415ef5a720f9/events.out.tfevents.1724093647.415ef5a720f9.768.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbcfc611a27638e2d935c7c6eae0793a53e0997269f50485ce3eb8e30919f11e
-size 411
+oid sha256:5c3460c63ec067fd6d1cdbd1a2d8f6efcb473b43da9500a7faa3f13bca77878c
+size 734

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.7935483870967742,
+    "eval_loss": 0.44589877128601074,
+    "eval_runtime": 67.6453,
+    "eval_samples_per_second": 2.291,
+    "eval_steps_per_second": 0.296
+}

trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": 0.8571428571428571,
+  "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": 6.44752311706543,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.3807,
+      "step": 10
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 7.273042678833008,
+      "learning_rate": 4.81203007518797e-05,
+      "loss": 2.2314,
+      "step": 20
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 8.626073837280273,
+      "learning_rate": 4.43609022556391e-05,
+      "loss": 2.1403,
+      "step": 30
+    },
+    {
+      "epoch": 0.25675675675675674,
+      "eval_accuracy": 0.5142857142857142,
+      "eval_loss": 1.7313623428344727,
+      "eval_runtime": 27.8323,
+      "eval_samples_per_second": 2.515,
+      "eval_steps_per_second": 0.323,
+      "step": 38
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 8.909332275390625,
+      "learning_rate": 4.0601503759398494e-05,
+      "loss": 1.9678,
+      "step": 40
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 10.421494483947754,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.5292,
+      "step": 50
+    },
+    {
+      "epoch": 1.1486486486486487,
+      "grad_norm": 14.169832229614258,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 1.2617,
+      "step": 60
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 13.361907005310059,
+      "learning_rate": 2.9323308270676693e-05,
+      "loss": 0.8555,
+      "step": 70
+    },
+    {
+      "epoch": 1.2567567567567568,
+      "eval_accuracy": 0.7571428571428571,
+      "eval_loss": 0.8789704442024231,
+      "eval_runtime": 29.0661,
+      "eval_samples_per_second": 2.408,
+      "eval_steps_per_second": 0.31,
+      "step": 76
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 5.020375728607178,
+      "learning_rate": 2.556390977443609e-05,
+      "loss": 0.8022,
+      "step": 80
+    },
+    {
+      "epoch": 2.0945945945945947,
+      "grad_norm": 7.712170600891113,
+      "learning_rate": 2.1804511278195487e-05,
+      "loss": 0.5757,
+      "step": 90
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 39.42369079589844,
+      "learning_rate": 1.8045112781954888e-05,
+      "loss": 0.5428,
+      "step": 100
+    },
+    {
+      "epoch": 2.22972972972973,
+      "grad_norm": 8.502290725708008,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.4151,
+      "step": 110
+    },
+    {
+      "epoch": 2.2567567567567566,
+      "eval_accuracy": 0.8142857142857143,
+      "eval_loss": 0.44468435645103455,
+      "eval_runtime": 29.8735,
+      "eval_samples_per_second": 2.343,
+      "eval_steps_per_second": 0.301,
+      "step": 114
+    },
+    {
+      "epoch": 3.0405405405405403,
+      "grad_norm": 3.149113893508911,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.3195,
+      "step": 120
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 4.639503002166748,
+      "learning_rate": 6.766917293233083e-06,
+      "loss": 0.2498,
+      "step": 130
+    },
+    {
+      "epoch": 3.175675675675676,
+      "grad_norm": 6.511192798614502,
+      "learning_rate": 3.007518796992481e-06,
+      "loss": 0.3019,
+      "step": 140
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.3518821895122528,
+      "eval_runtime": 30.2532,
+      "eval_samples_per_second": 2.314,
+      "eval_steps_per_second": 0.297,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "step": 148,
+      "total_flos": 1.460491890402263e+18,
+      "train_loss": 1.0669236167057141,
+      "train_runtime": 1173.886,
+      "train_samples_per_second": 1.009,
+      "train_steps_per_second": 0.126
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.7935483870967742,
+      "eval_loss": 0.44589874148368835,
+      "eval_runtime": 68.625,
+      "eval_samples_per_second": 2.259,
+      "eval_steps_per_second": 0.291,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.7935483870967742,
+      "eval_loss": 0.44589877128601074,
+      "eval_runtime": 67.6453,
+      "eval_samples_per_second": 2.291,
+      "eval_steps_per_second": 0.296,
+      "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
+}