End of training

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8451612903225807,
+    "eval_loss": 0.4268675744533539,
+    "eval_runtime": 717.6662,
+    "eval_samples_per_second": 0.216,
+    "eval_steps_per_second": 0.028
+}

runs/Sep01_17-12-29_DESKTOP-HH90LF4/events.out.tfevents.1725224525.DESKTOP-HH90LF4.19432.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5041e1f5d0f5765d2d4fdb6a548fc881b17a276ae2158d00c04c1c442a7b188a
-size 411
+oid sha256:2521ed5acc39234128e0b5255f00441ef490b722a117808bca89f217d2ea23fd
+size 734

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8451612903225807,
+    "eval_loss": 0.4268675744533539,
+    "eval_runtime": 717.6662,
+    "eval_samples_per_second": 0.216,
+    "eval_steps_per_second": 0.028
+}

trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": 0.9,
+  "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": 6.637506484985352,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.3291,
+      "step": 10
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 6.818987846374512,
+      "learning_rate": 4.81203007518797e-05,
+      "loss": 2.178,
+      "step": 20
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 7.709394931793213,
+      "learning_rate": 4.43609022556391e-05,
+      "loss": 2.1271,
+      "step": 30
+    },
+    {
+      "epoch": 0.25675675675675674,
+      "eval_accuracy": 0.5857142857142857,
+      "eval_loss": 1.750235676765442,
+      "eval_runtime": 358.5975,
+      "eval_samples_per_second": 0.195,
+      "eval_steps_per_second": 0.025,
+      "step": 38
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 8.947957038879395,
+      "learning_rate": 4.0601503759398494e-05,
+      "loss": 1.9688,
+      "step": 40
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 11.97453498840332,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.6222,
+      "step": 50
+    },
+    {
+      "epoch": 1.1486486486486487,
+      "grad_norm": 11.820381164550781,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 1.3492,
+      "step": 60
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 7.240334510803223,
+      "learning_rate": 2.9323308270676693e-05,
+      "loss": 0.9238,
+      "step": 70
+    },
+    {
+      "epoch": 1.2567567567567568,
+      "eval_accuracy": 0.7285714285714285,
+      "eval_loss": 0.9221255779266357,
+      "eval_runtime": 321.1204,
+      "eval_samples_per_second": 0.218,
+      "eval_steps_per_second": 0.028,
+      "step": 76
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 5.566869258880615,
+      "learning_rate": 2.556390977443609e-05,
+      "loss": 0.8525,
+      "step": 80
+    },
+    {
+      "epoch": 2.0945945945945947,
+      "grad_norm": 7.503639221191406,
+      "learning_rate": 2.1804511278195487e-05,
+      "loss": 0.6129,
+      "step": 90
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 10.933565139770508,
+      "learning_rate": 1.8045112781954888e-05,
+      "loss": 0.5586,
+      "step": 100
+    },
+    {
+      "epoch": 2.22972972972973,
+      "grad_norm": 5.846622943878174,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.4428,
+      "step": 110
+    },
+    {
+      "epoch": 2.2567567567567566,
+      "eval_accuracy": 0.8857142857142857,
+      "eval_loss": 0.5141051411628723,
+      "eval_runtime": 330.1752,
+      "eval_samples_per_second": 0.212,
+      "eval_steps_per_second": 0.027,
+      "step": 114
+    },
+    {
+      "epoch": 3.0405405405405403,
+      "grad_norm": 4.769641876220703,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.356,
+      "step": 120
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 2.704050064086914,
+      "learning_rate": 6.766917293233083e-06,
+      "loss": 0.2795,
+      "step": 130
+    },
+    {
+      "epoch": 3.175675675675676,
+      "grad_norm": 7.3338422775268555,
+      "learning_rate": 3.007518796992481e-06,
+      "loss": 0.3117,
+      "step": 140
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.9,
+      "eval_loss": 0.3816043734550476,
+      "eval_runtime": 328.9172,
+      "eval_samples_per_second": 0.213,
+      "eval_steps_per_second": 0.027,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "step": 148,
+      "total_flos": 1.460491890402263e+18,
+      "train_loss": 1.0890940588873785,
+      "train_runtime": 23791.4908,
+      "train_samples_per_second": 0.05,
+      "train_steps_per_second": 0.006
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8451612903225807,
+      "eval_loss": 0.42686763405799866,
+      "eval_runtime": 730.7575,
+      "eval_samples_per_second": 0.212,
+      "eval_steps_per_second": 0.027,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8451612903225807,
+      "eval_loss": 0.4268675744533539,
+      "eval_runtime": 717.6662,
+      "eval_samples_per_second": 0.216,
+      "eval_steps_per_second": 0.028,
+      "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
+}