End of training

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.1,
+    "eval_accuracy": 0.8709677419354839,
+    "eval_loss": 0.4110705554485321,
+    "eval_runtime": 107.0152,
+    "eval_samples_per_second": 1.448,
+    "eval_steps_per_second": 0.093
+}

runs/Feb07_12-27-52_soet-gpu/events.out.tfevents.1707293421.soet-gpu.424037.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c85efb4d4cb47f9570ae85b0fbd448462cad4d8f2e20b7d8f3d14e8d1d0831a
-size 411
+oid sha256:b01a36db3334c2c064ab6dd7b86cac715df0dff76c8b0d0d52a8f1ffcb4dc301
+size 734

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.1,
+    "eval_accuracy": 0.8709677419354839,
+    "eval_loss": 0.4110705554485321,
+    "eval_runtime": 107.0152,
+    "eval_samples_per_second": 1.448,
+    "eval_steps_per_second": 0.093
+}

trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_metric": 0.9285714285714286,
+  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-95",
+  "epoch": 7.101351351351352,
+  "eval_steps": 500,
+  "global_step": 148,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 2.3295,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.3,
+      "eval_loss": 2.117830514907837,
+      "eval_runtime": 48.0965,
+      "eval_samples_per_second": 1.455,
+      "eval_steps_per_second": 0.104,
+      "step": 19
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 4.81203007518797e-05,
+      "loss": 2.2263,
+      "step": 20
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.43609022556391e-05,
+      "loss": 1.991,
+      "step": 30
+    },
+    {
+      "epoch": 1.13,
+      "eval_accuracy": 0.5142857142857142,
+      "eval_loss": 1.5623936653137207,
+      "eval_runtime": 48.3785,
+      "eval_samples_per_second": 1.447,
+      "eval_steps_per_second": 0.103,
+      "step": 38
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 4.0601503759398494e-05,
+      "loss": 1.6098,
+      "step": 40
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 1.227,
+      "step": 50
+    },
+    {
+      "epoch": 2.13,
+      "eval_accuracy": 0.7714285714285715,
+      "eval_loss": 0.8620532155036926,
+      "eval_runtime": 48.4173,
+      "eval_samples_per_second": 1.446,
+      "eval_steps_per_second": 0.103,
+      "step": 57
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 0.8221,
+      "step": 60
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 2.9323308270676693e-05,
+      "loss": 0.5665,
+      "step": 70
+    },
+    {
+      "epoch": 3.13,
+      "eval_accuracy": 0.8,
+      "eval_loss": 0.6211545467376709,
+      "eval_runtime": 48.0404,
+      "eval_samples_per_second": 1.457,
+      "eval_steps_per_second": 0.104,
+      "step": 76
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 2.556390977443609e-05,
+      "loss": 0.4292,
+      "step": 80
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 2.1804511278195487e-05,
+      "loss": 0.3487,
+      "step": 90
+    },
+    {
+      "epoch": 4.13,
+      "eval_accuracy": 0.9285714285714286,
+      "eval_loss": 0.35538002848625183,
+      "eval_runtime": 48.0249,
+      "eval_samples_per_second": 1.458,
+      "eval_steps_per_second": 0.104,
+      "step": 95
+    },
+    {
+      "epoch": 5.03,
+      "learning_rate": 1.8045112781954888e-05,
+      "loss": 0.2808,
+      "step": 100
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.1701,
+      "step": 110
+    },
+    {
+      "epoch": 5.13,
+      "eval_accuracy": 0.8857142857142857,
+      "eval_loss": 0.35967761278152466,
+      "eval_runtime": 47.9921,
+      "eval_samples_per_second": 1.459,
+      "eval_steps_per_second": 0.104,
+      "step": 114
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.1586,
+      "step": 120
+    },
+    {
+      "epoch": 6.11,
+      "learning_rate": 6.766917293233083e-06,
+      "loss": 0.1036,
+      "step": 130
+    },
+    {
+      "epoch": 6.13,
+      "eval_accuracy": 0.9285714285714286,
+      "eval_loss": 0.22771558165550232,
+      "eval_runtime": 47.9689,
+      "eval_samples_per_second": 1.459,
+      "eval_steps_per_second": 0.104,
+      "step": 133
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 3.007518796992481e-06,
+      "loss": 0.089,
+      "step": 140
+    },
+    {
+      "epoch": 7.1,
+      "eval_accuracy": 0.9142857142857143,
+      "eval_loss": 0.19885921478271484,
+      "eval_runtime": 48.0247,
+      "eval_samples_per_second": 1.458,
+      "eval_steps_per_second": 0.104,
+      "step": 148
+    },
+    {
+      "epoch": 7.1,
+      "step": 148,
+      "total_flos": 2.915999166844109e+18,
+      "train_loss": 0.8383703630518269,
+      "train_runtime": 4135.2767,
+      "train_samples_per_second": 0.573,
+      "train_steps_per_second": 0.036
+    },
+    {
+      "epoch": 7.1,
+      "eval_accuracy": 0.8709677419354839,
+      "eval_loss": 0.4110705554485321,
+      "eval_runtime": 106.5714,
+      "eval_samples_per_second": 1.454,
+      "eval_steps_per_second": 0.094,
+      "step": 148
+    },
+    {
+      "epoch": 7.1,
+      "eval_accuracy": 0.8709677419354839,
+      "eval_loss": 0.4110705554485321,
+      "eval_runtime": 107.0152,
+      "eval_samples_per_second": 1.448,
+      "eval_steps_per_second": 0.093,
+      "step": 148
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 148,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "total_flos": 2.915999166844109e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}