🍻 cheers

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9924812030075187,
+    "eval_loss": 0.029002541676163673,
+    "eval_runtime": 3.0711,
+    "eval_samples_per_second": 43.308,
+    "eval_steps_per_second": 5.536,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.128345954647431,
+    "train_runtime": 213.2669,
+    "train_samples_per_second": 19.394,
+    "train_steps_per_second": 1.219
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.9924812030075187,
+    "eval_loss": 0.029002541676163673,
+    "eval_runtime": 3.0711,
+    "eval_samples_per_second": 43.308,
+    "eval_steps_per_second": 5.536
+}

runs/Jul16_17-10-39_b4d52368873a/events.out.tfevents.1689527683.b4d52368873a.2423.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3704324925b39615277e74781d58522cc7777d207b9b7965b54365746120af52
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 3.205097416476426e+17,
+    "train_loss": 0.128345954647431,
+    "train_runtime": 213.2669,
+    "train_samples_per_second": 19.394,
+    "train_steps_per_second": 1.219
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": 0.029002541676163673,
+  "best_model_checkpoint": "./vit-base-beans-demo-v5/checkpoint-200",
+  "epoch": 4.0,
+  "global_step": 260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019230769230769233,
+      "loss": 0.8284,
+      "step": 10
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 0.2956,
+      "step": 20
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00017692307692307693,
+      "loss": 0.3667,
+      "step": 30
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.2713,
+      "step": 40
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016153846153846155,
+      "loss": 0.2125,
+      "step": 50
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 0.1852,
+      "step": 60
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00014615384615384615,
+      "loss": 0.1254,
+      "step": 70
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00013923076923076923,
+      "loss": 0.1552,
+      "step": 80
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00013153846153846156,
+      "loss": 0.0474,
+      "step": 90
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00012384615384615385,
+      "loss": 0.1265,
+      "step": 100
+    },
+    {
+      "epoch": 1.54,
+      "eval_accuracy": 0.9774436090225563,
+      "eval_loss": 0.08259306848049164,
+      "eval_runtime": 2.625,
+      "eval_samples_per_second": 50.666,
+      "eval_steps_per_second": 6.476,
+      "step": 100
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00011615384615384617,
+      "loss": 0.1154,
+      "step": 110
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00010846153846153846,
+      "loss": 0.1548,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00010076923076923077,
+      "loss": 0.0739,
+      "step": 130
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.307692307692309e-05,
+      "loss": 0.0507,
+      "step": 140
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.538461538461538e-05,
+      "loss": 0.0479,
+      "step": 150
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.76923076923077e-05,
+      "loss": 0.0475,
+      "step": 160
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7e-05,
+      "loss": 0.0367,
+      "step": 170
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.23076923076923e-05,
+      "loss": 0.0648,
+      "step": 180
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.461538461538461e-05,
+      "loss": 0.0201,
+      "step": 190
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 4.692307692307693e-05,
+      "loss": 0.0417,
+      "step": 200
+    },
+    {
+      "epoch": 3.08,
+      "eval_accuracy": 0.9924812030075187,
+      "eval_loss": 0.029002541676163673,
+      "eval_runtime": 2.6469,
+      "eval_samples_per_second": 50.247,
+      "eval_steps_per_second": 6.423,
+      "step": 200
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 3.923076923076923e-05,
+      "loss": 0.0126,
+      "step": 210
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 3.153846153846154e-05,
+      "loss": 0.0117,
+      "step": 220
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 2.384615384615385e-05,
+      "loss": 0.0109,
+      "step": 230
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 0.0123,
+      "step": 240
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.0113,
+      "step": 250
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 0.0106,
+      "step": 260
+    },
+    {
+      "epoch": 4.0,
+      "step": 260,
+      "total_flos": 3.205097416476426e+17,
+      "train_loss": 0.128345954647431,
+      "train_runtime": 213.2669,
+      "train_samples_per_second": 19.394,
+      "train_steps_per_second": 1.219
+    }
+  ],
+  "max_steps": 260,
+  "num_train_epochs": 4,
+  "total_flos": 3.205097416476426e+17,
+  "trial_name": null,
+  "trial_params": null
+}