End of training

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8064516129032258,
+    "eval_loss": 0.5050253868103027,
+    "eval_runtime": 42.166,
+    "eval_samples_per_second": 3.676,
+    "eval_steps_per_second": 0.474
+}

runs/Jan07_06-18-11_6995479044b7/events.out.tfevents.1736231717.6995479044b7.9646.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ee2df2e12c4aa5aa1bced4d4aae0ce6f460b390e0d9b1c8a6b92362ac97b6e4
-size 411
+oid sha256:dda047eb75927500f4d3d23112abc7a4a479c5ccf50da349f5485650cf935ae1
+size 734

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.22972972972973,
+    "eval_accuracy": 0.8064516129032258,
+    "eval_loss": 0.5050253868103027,
+    "eval_runtime": 42.166,
+    "eval_samples_per_second": 3.676,
+    "eval_steps_per_second": 0.474
+}

trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_metric": 0.9428571428571428,
+  "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": 7.131130695343018,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.3604,
+      "step": 10
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 6.723432540893555,
+      "learning_rate": 4.81203007518797e-05,
+      "loss": 2.2745,
+      "step": 20
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 7.238136291503906,
+      "learning_rate": 4.43609022556391e-05,
+      "loss": 2.1705,
+      "step": 30
+    },
+    {
+      "epoch": 0.25675675675675674,
+      "eval_accuracy": 0.42857142857142855,
+      "eval_loss": 1.8774490356445312,
+      "eval_runtime": 19.4551,
+      "eval_samples_per_second": 3.598,
+      "eval_steps_per_second": 0.463,
+      "step": 38
+    },
+    {
+      "epoch": 1.0135135135135136,
+      "grad_norm": 8.964755058288574,
+      "learning_rate": 4.0601503759398494e-05,
+      "loss": 1.9616,
+      "step": 40
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 11.423721313476562,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.5421,
+      "step": 50
+    },
+    {
+      "epoch": 1.1486486486486487,
+      "grad_norm": 15.365297317504883,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 1.3109,
+      "step": 60
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 6.089099407196045,
+      "learning_rate": 2.9323308270676693e-05,
+      "loss": 0.9008,
+      "step": 70
+    },
+    {
+      "epoch": 1.2567567567567568,
+      "eval_accuracy": 0.7714285714285715,
+      "eval_loss": 0.8671557307243347,
+      "eval_runtime": 19.0707,
+      "eval_samples_per_second": 3.671,
+      "eval_steps_per_second": 0.472,
+      "step": 76
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 7.874572277069092,
+      "learning_rate": 2.556390977443609e-05,
+      "loss": 0.8193,
+      "step": 80
+    },
+    {
+      "epoch": 2.0945945945945947,
+      "grad_norm": 15.332853317260742,
+      "learning_rate": 2.1804511278195487e-05,
+      "loss": 0.6854,
+      "step": 90
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 8.194880485534668,
+      "learning_rate": 1.8045112781954888e-05,
+      "loss": 0.5442,
+      "step": 100
+    },
+    {
+      "epoch": 2.22972972972973,
+      "grad_norm": 7.591757774353027,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.4817,
+      "step": 110
+    },
+    {
+      "epoch": 2.2567567567567566,
+      "eval_accuracy": 0.7857142857142857,
+      "eval_loss": 0.5201463103294373,
+      "eval_runtime": 19.906,
+      "eval_samples_per_second": 3.517,
+      "eval_steps_per_second": 0.452,
+      "step": 114
+    },
+    {
+      "epoch": 3.0405405405405403,
+      "grad_norm": 3.142641305923462,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.3976,
+      "step": 120
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 3.1761014461517334,
+      "learning_rate": 6.766917293233083e-06,
+      "loss": 0.2953,
+      "step": 130
+    },
+    {
+      "epoch": 3.175675675675676,
+      "grad_norm": 9.955376625061035,
+      "learning_rate": 3.007518796992481e-06,
+      "loss": 0.3249,
+      "step": 140
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.9428571428571428,
+      "eval_loss": 0.4068930745124817,
+      "eval_runtime": 19.5727,
+      "eval_samples_per_second": 3.576,
+      "eval_steps_per_second": 0.46,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "step": 148,
+      "total_flos": 1.460491890402263e+18,
+      "train_loss": 1.0999058742780943,
+      "train_runtime": 812.3227,
+      "train_samples_per_second": 1.458,
+      "train_steps_per_second": 0.182
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8064516129032258,
+      "eval_loss": 0.5050253868103027,
+      "eval_runtime": 43.3443,
+      "eval_samples_per_second": 3.576,
+      "eval_steps_per_second": 0.461,
+      "step": 148
+    },
+    {
+      "epoch": 3.22972972972973,
+      "eval_accuracy": 0.8064516129032258,
+      "eval_loss": 0.5050253868103027,
+      "eval_runtime": 42.166,
+      "eval_samples_per_second": 3.676,
+      "eval_steps_per_second": 0.474,
+      "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
+}