Model save

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8193548387096774,
+    "eval_loss": 0.4508959949016571,
+    "eval_runtime": 15.0463,
+    "eval_samples_per_second": 10.302,
+    "eval_steps_per_second": 1.329
+}

runs/May18_02-46-09_DESKTOP-SGO0ICV/events.out.tfevents.1715972174.DESKTOP-SGO0ICV.40900.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:329efe1368fb3491be978ce51e99fe321cbddce7b006a3b7c2479f143747356c
-size 411
+oid sha256:928b93dfb28b6ce9407e5b552fe6dcb3e9283b729bc29d1b69eeacf50278a8de
+size 734

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8193548387096774,
+    "eval_loss": 0.4508959949016571,
+    "eval_runtime": 15.0463,
+    "eval_samples_per_second": 10.302,
+    "eval_steps_per_second": 1.329
+}

trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": 0.8714285714285714,
+  "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": 6.096624374389648,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.2942,
+      "step": 10
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 7.102034568786621,
+      "learning_rate": 4.81203007518797e-05,
+      "loss": 2.2308,
+      "step": 20
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 7.2539143562316895,
+      "learning_rate": 4.43609022556391e-05,
+      "loss": 2.1149,
+      "step": 30
+    },
+    {
+      "epoch": 0.25675675675675674,
+      "eval_accuracy": 0.5571428571428572,
+      "eval_loss": 1.8154758214950562,
+      "eval_runtime": 10.1069,
+      "eval_samples_per_second": 6.926,
+      "eval_steps_per_second": 0.89,
+      "step": 38
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 25.16826057434082,
+      "learning_rate": 4.0601503759398494e-05,
+      "loss": 1.97,
+      "step": 40
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 10.718199729919434,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.5744,
+      "step": 50
+    },
+    {
+      "epoch": 1.1486486486486487,
+      "grad_norm": 10.61833381652832,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 1.3135,
+      "step": 60
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 8.033047676086426,
+      "learning_rate": 2.9323308270676693e-05,
+      "loss": 0.8974,
+      "step": 70
+    },
+    {
+      "epoch": 1.2567567567567568,
+      "eval_accuracy": 0.5857142857142857,
+      "eval_loss": 1.1256393194198608,
+      "eval_runtime": 9.8133,
+      "eval_samples_per_second": 7.133,
+      "eval_steps_per_second": 0.917,
+      "step": 76
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 8.3702392578125,
+      "learning_rate": 2.556390977443609e-05,
+      "loss": 0.9946,
+      "step": 80
+    },
+    {
+      "epoch": 2.0945945945945947,
+      "grad_norm": 9.561596870422363,
+      "learning_rate": 2.1804511278195487e-05,
+      "loss": 0.7404,
+      "step": 90
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 11.346077919006348,
+      "learning_rate": 1.8045112781954888e-05,
+      "loss": 0.6667,
+      "step": 100
+    },
+    {
+      "epoch": 2.22972972972973,
+      "grad_norm": 7.648571014404297,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.5226,
+      "step": 110
+    },
+    {
+      "epoch": 2.2567567567567566,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.5665245056152344,
+      "eval_runtime": 8.9518,
+      "eval_samples_per_second": 7.82,
+      "eval_steps_per_second": 1.005,
+      "step": 114
+    },
+    {
+      "epoch": 3.0405405405405403,
+      "grad_norm": 3.668431520462036,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.44,
+      "step": 120
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 5.99934720993042,
+      "learning_rate": 6.766917293233083e-06,
+      "loss": 0.3393,
+      "step": 130
+    },
+    {
+      "epoch": 3.175675675675676,
+      "grad_norm": 10.936161994934082,
+      "learning_rate": 3.007518796992481e-06,
+      "loss": 0.3423,
+      "step": 140
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8714285714285714,
+      "eval_loss": 0.47154754400253296,
+      "eval_runtime": 8.8419,
+      "eval_samples_per_second": 7.917,
+      "eval_steps_per_second": 1.018,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "step": 148,
+      "total_flos": 1.460491890402263e+18,
+      "train_loss": 1.128270382816727,
+      "train_runtime": 532.0374,
+      "train_samples_per_second": 2.225,
+      "train_steps_per_second": 0.278
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8193548387096774,
+      "eval_loss": 0.4508959949016571,
+      "eval_runtime": 16.4959,
+      "eval_samples_per_second": 9.396,
+      "eval_steps_per_second": 1.212,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8193548387096774,
+      "eval_loss": 0.4508959949016571,
+      "eval_runtime": 15.0463,
+      "eval_samples_per_second": 10.302,
+      "eval_steps_per_second": 1.329,
+      "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
+}