End of training

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8129032258064516,
+    "eval_loss": 0.555190920829773,
+    "eval_runtime": 44.3944,
+    "eval_samples_per_second": 3.491,
+    "eval_steps_per_second": 0.451
+}

runs/Aug12_13-36-20_745aca8384a6/events.out.tfevents.1723471022.745aca8384a6.201.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3605f344c5798a30b786c01361bf1b040d85228e695009bd6f769afd0bb9a5
-size 411
+oid sha256:a29f5f4c1663046efe481fb01c6107cc329cb81b276afc071e4d7152175e2e11
+size 734

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8129032258064516,
+    "eval_loss": 0.555190920829773,
+    "eval_runtime": 44.3944,
+    "eval_samples_per_second": 3.491,
+    "eval_steps_per_second": 0.451
+}

trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": 0.8857142857142857,
+  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-114",
+  "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": 6.47936487197876,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.3179,
+      "step": 10
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 7.017707824707031,
+      "learning_rate": 4.81203007518797e-05,
+      "loss": 2.1829,
+      "step": 20
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 8.161763191223145,
+      "learning_rate": 4.43609022556391e-05,
+      "loss": 2.1368,
+      "step": 30
+    },
+    {
+      "epoch": 0.25675675675675674,
+      "eval_accuracy": 0.4714285714285714,
+      "eval_loss": 1.8141530752182007,
+      "eval_runtime": 19.73,
+      "eval_samples_per_second": 3.548,
+      "eval_steps_per_second": 0.456,
+      "step": 38
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 10.2463960647583,
+      "learning_rate": 4.0601503759398494e-05,
+      "loss": 1.9385,
+      "step": 40
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 9.556536674499512,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.5885,
+      "step": 50
+    },
+    {
+      "epoch": 1.1486486486486487,
+      "grad_norm": 10.24481201171875,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 1.2268,
+      "step": 60
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 10.689459800720215,
+      "learning_rate": 2.9323308270676693e-05,
+      "loss": 0.9429,
+      "step": 70
+    },
+    {
+      "epoch": 1.2567567567567568,
+      "eval_accuracy": 0.7142857142857143,
+      "eval_loss": 0.8959183096885681,
+      "eval_runtime": 20.5664,
+      "eval_samples_per_second": 3.404,
+      "eval_steps_per_second": 0.438,
+      "step": 76
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 5.460722923278809,
+      "learning_rate": 2.556390977443609e-05,
+      "loss": 0.8563,
+      "step": 80
+    },
+    {
+      "epoch": 2.0945945945945947,
+      "grad_norm": 6.7798542976379395,
+      "learning_rate": 2.1804511278195487e-05,
+      "loss": 0.7301,
+      "step": 90
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 12.205018043518066,
+      "learning_rate": 1.8045112781954888e-05,
+      "loss": 0.6239,
+      "step": 100
+    },
+    {
+      "epoch": 2.22972972972973,
+      "grad_norm": 6.078609466552734,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.498,
+      "step": 110
+    },
+    {
+      "epoch": 2.2567567567567566,
+      "eval_accuracy": 0.8857142857142857,
+      "eval_loss": 0.48412585258483887,
+      "eval_runtime": 20.7057,
+      "eval_samples_per_second": 3.381,
+      "eval_steps_per_second": 0.435,
+      "step": 114
+    },
+    {
+      "epoch": 3.0405405405405403,
+      "grad_norm": 4.824766635894775,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.388,
+      "step": 120
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 4.048300266265869,
+      "learning_rate": 6.766917293233083e-06,
+      "loss": 0.3201,
+      "step": 130
+    },
+    {
+      "epoch": 3.175675675675676,
+      "grad_norm": 7.941919326782227,
+      "learning_rate": 3.007518796992481e-06,
+      "loss": 0.3668,
+      "step": 140
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8857142857142857,
+      "eval_loss": 0.43238481879234314,
+      "eval_runtime": 19.8295,
+      "eval_samples_per_second": 3.53,
+      "eval_steps_per_second": 0.454,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "step": 148,
+      "total_flos": 1.460491890402263e+18,
+      "train_loss": 1.104080841347978,
+      "train_runtime": 799.4864,
+      "train_samples_per_second": 1.481,
+      "train_steps_per_second": 0.185
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8129032258064516,
+      "eval_loss": 0.5551909804344177,
+      "eval_runtime": 44.289,
+      "eval_samples_per_second": 3.5,
+      "eval_steps_per_second": 0.452,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8129032258064516,
+      "eval_loss": 0.555190920829773,
+      "eval_runtime": 44.3944,
+      "eval_samples_per_second": 3.491,
+      "eval_steps_per_second": 0.451,
+      "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
+}