End of training

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8903225806451613,
+    "eval_loss": 0.37676411867141724,
+    "eval_runtime": 48.0994,
+    "eval_samples_per_second": 3.222,
+    "eval_steps_per_second": 0.416
+}

runs/Dec11_11-45-54_9c748ae56abe/events.out.tfevents.1733918650.9c748ae56abe.5672.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2554fc5dac95090fad21eb2e1242966ffdb2665ef30ce724422fd4482ef9bd6e
-size 411
+oid sha256:28aa9c4c87476fa8dcb55416a4d3ca4df06b32079819c95ae07dde224ec632bc
+size 734

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8903225806451613,
+    "eval_loss": 0.37676411867141724,
+    "eval_runtime": 48.0994,
+    "eval_samples_per_second": 3.222,
+    "eval_steps_per_second": 0.416
+}

trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": 0.9714285714285714,
+  "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": 8.116050720214844,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.45,
+      "step": 10
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 7.184136390686035,
+      "learning_rate": 4.81203007518797e-05,
+      "loss": 2.2519,
+      "step": 20
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 7.231730937957764,
+      "learning_rate": 4.43609022556391e-05,
+      "loss": 2.1441,
+      "step": 30
+    },
+    {
+      "epoch": 0.25675675675675674,
+      "eval_accuracy": 0.45714285714285713,
+      "eval_loss": 1.8078112602233887,
+      "eval_runtime": 18.0368,
+      "eval_samples_per_second": 3.881,
+      "eval_steps_per_second": 0.499,
+      "step": 38
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 7.591067790985107,
+      "learning_rate": 4.0601503759398494e-05,
+      "loss": 1.9676,
+      "step": 40
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 12.068100929260254,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.5137,
+      "step": 50
+    },
+    {
+      "epoch": 1.1486486486486487,
+      "grad_norm": 10.06794548034668,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 1.2275,
+      "step": 60
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 5.379796504974365,
+      "learning_rate": 2.9323308270676693e-05,
+      "loss": 0.8226,
+      "step": 70
+    },
+    {
+      "epoch": 1.2567567567567568,
+      "eval_accuracy": 0.7428571428571429,
+      "eval_loss": 0.9200405478477478,
+      "eval_runtime": 17.3626,
+      "eval_samples_per_second": 4.032,
+      "eval_steps_per_second": 0.518,
+      "step": 76
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 8.003628730773926,
+      "learning_rate": 2.556390977443609e-05,
+      "loss": 0.8274,
+      "step": 80
+    },
+    {
+      "epoch": 2.0945945945945947,
+      "grad_norm": 15.18116569519043,
+      "learning_rate": 2.1804511278195487e-05,
+      "loss": 0.5729,
+      "step": 90
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 9.584309577941895,
+      "learning_rate": 1.8045112781954888e-05,
+      "loss": 0.4828,
+      "step": 100
+    },
+    {
+      "epoch": 2.22972972972973,
+      "grad_norm": 9.056602478027344,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.423,
+      "step": 110
+    },
+    {
+      "epoch": 2.2567567567567566,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.48607712984085083,
+      "eval_runtime": 17.9908,
+      "eval_samples_per_second": 3.891,
+      "eval_steps_per_second": 0.5,
+      "step": 114
+    },
+    {
+      "epoch": 3.0405405405405403,
+      "grad_norm": 3.3061022758483887,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.3519,
+      "step": 120
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 3.5248923301696777,
+      "learning_rate": 6.766917293233083e-06,
+      "loss": 0.2541,
+      "step": 130
+    },
+    {
+      "epoch": 3.175675675675676,
+      "grad_norm": 11.10520076751709,
+      "learning_rate": 3.007518796992481e-06,
+      "loss": 0.2742,
+      "step": 140
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.9714285714285714,
+      "eval_loss": 0.32414156198501587,
+      "eval_runtime": 19.546,
+      "eval_samples_per_second": 3.581,
+      "eval_steps_per_second": 0.46,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "step": 148,
+      "total_flos": 1.460491890402263e+18,
+      "train_loss": 1.0634757940833632,
+      "train_runtime": 890.5837,
+      "train_samples_per_second": 1.329,
+      "train_steps_per_second": 0.166
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8903225806451613,
+      "eval_loss": 0.3767641484737396,
+      "eval_runtime": 47.7055,
+      "eval_samples_per_second": 3.249,
+      "eval_steps_per_second": 0.419,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8903225806451613,
+      "eval_loss": 0.37676411867141724,
+      "eval_runtime": 48.0994,
+      "eval_samples_per_second": 3.222,
+      "eval_steps_per_second": 0.416,
+      "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
+}