End of training

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8129032258064516,
+    "eval_loss": 0.5470468997955322,
+    "eval_runtime": 14.4978,
+    "eval_samples_per_second": 10.691,
+    "eval_steps_per_second": 1.38
+}

runs/Oct14_13-02-27_dc6088e9f91b/events.out.tfevents.1728911194.dc6088e9f91b.3595.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c651a7b34b2f6487f9033e605cd274190363a1a3cb331ae3fa08e9dad05afb8
-size 411
+oid sha256:7efca62560648fef46a332f9d5dc5bac16afd0f68911f193b27915f1137e52fd
+size 734

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8129032258064516,
+    "eval_loss": 0.5470468997955322,
+    "eval_runtime": 14.4978,
+    "eval_samples_per_second": 10.691,
+    "eval_steps_per_second": 1.38
+}

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": 6.49423885345459,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.3757,
+      "step": 10
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 6.615733623504639,
+      "learning_rate": 4.81203007518797e-05,
+      "loss": 2.2277,
+      "step": 20
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 8.014123916625977,
+      "learning_rate": 4.43609022556391e-05,
+      "loss": 2.109,
+      "step": 30
+    },
+    {
+      "epoch": 0.25675675675675674,
+      "eval_accuracy": 0.6,
+      "eval_loss": 1.8528673648834229,
+      "eval_runtime": 6.7471,
+      "eval_samples_per_second": 10.375,
+      "eval_steps_per_second": 1.334,
+      "step": 38
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 14.876914978027344,
+      "learning_rate": 4.0601503759398494e-05,
+      "loss": 1.9624,
+      "step": 40
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 11.556279182434082,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.5381,
+      "step": 50
+    },
+    {
+      "epoch": 1.1486486486486487,
+      "grad_norm": 12.52138900756836,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 1.2444,
+      "step": 60
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 5.785777568817139,
+      "learning_rate": 2.9323308270676693e-05,
+      "loss": 0.9259,
+      "step": 70
+    },
+    {
+      "epoch": 1.2567567567567568,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.2051961421966553,
+      "eval_runtime": 6.2919,
+      "eval_samples_per_second": 11.125,
+      "eval_steps_per_second": 1.43,
+      "step": 76
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 6.8339762687683105,
+      "learning_rate": 2.556390977443609e-05,
+      "loss": 0.8577,
+      "step": 80
+    },
+    {
+      "epoch": 2.0945945945945947,
+      "grad_norm": 11.754122734069824,
+      "learning_rate": 2.1804511278195487e-05,
+      "loss": 0.6724,
+      "step": 90
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 9.548654556274414,
+      "learning_rate": 1.8045112781954888e-05,
+      "loss": 0.6248,
+      "step": 100
+    },
+    {
+      "epoch": 2.22972972972973,
+      "grad_norm": 7.923789024353027,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.4802,
+      "step": 110
+    },
+    {
+      "epoch": 2.2567567567567566,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.6029335856437683,
+      "eval_runtime": 6.1746,
+      "eval_samples_per_second": 11.337,
+      "eval_steps_per_second": 1.458,
+      "step": 114
+    },
+    {
+      "epoch": 3.0405405405405403,
+      "grad_norm": 4.298054218292236,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.3842,
+      "step": 120
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 3.788994312286377,
+      "learning_rate": 6.766917293233083e-06,
+      "loss": 0.2912,
+      "step": 130
+    },
+    {
+      "epoch": 3.175675675675676,
+      "grad_norm": 12.958038330078125,
+      "learning_rate": 3.007518796992481e-06,
+      "loss": 0.3519,
+      "step": 140
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8714285714285714,
+      "eval_loss": 0.4826556146144867,
+      "eval_runtime": 6.6956,
+      "eval_samples_per_second": 10.455,
+      "eval_steps_per_second": 1.344,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "step": 148,
+      "total_flos": 1.460491890402263e+18,
+      "train_loss": 1.1000467377739984,
+      "train_runtime": 221.0945,
+      "train_samples_per_second": 5.355,
+      "train_steps_per_second": 0.669
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8129032258064516,
+      "eval_loss": 0.5470468401908875,
+      "eval_runtime": 14.5546,
+      "eval_samples_per_second": 10.65,
+      "eval_steps_per_second": 1.374,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8129032258064516,
+      "eval_loss": 0.5470468997955322,
+      "eval_runtime": 14.4978,
+      "eval_samples_per_second": 10.691,
+      "eval_steps_per_second": 1.38,
+      "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
+}