🍻 cheers

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.7253613666228647,
+    "eval_loss": 0.8540832996368408,
+    "eval_runtime": 14.6956,
+    "eval_samples_per_second": 207.137,
+    "eval_steps_per_second": 25.926,
+    "train_loss": 0.43440550003352524,
+    "train_runtime": 1184.7674,
+    "train_samples_per_second": 102.767,
+    "train_steps_per_second": 3.212
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.7253613666228647,
+    "eval_loss": 0.8540832996368408,
+    "eval_runtime": 14.6956,
+    "eval_samples_per_second": 207.137,
+    "eval_steps_per_second": 25.926
+}

runs/May26_15-57-29_adrian-development/events.out.tfevents.1685110673.adrian-development.6716.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cabfa6aef47aff4e70fcc81c28653192e356ab84311d243553ee149d24e14c8
+size 363

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.43440550003352524,
+    "train_runtime": 1184.7674,
+    "train_samples_per_second": 102.767,
+    "train_steps_per_second": 3.212
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": 0.8540832996368408,
+  "best_model_checkpoint": "Transformers/vit-base-clothing-leafs-example/checkpoint-1000",
+  "epoch": 5.0,
+  "global_step": 3805,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00014743758212877795,
+      "loss": 0.9943,
+      "step": 1000
+    },
+    {
+      "epoch": 1.31,
+      "eval_accuracy": 0.7253613666228647,
+      "eval_loss": 0.8540832996368408,
+      "eval_runtime": 15.2291,
+      "eval_samples_per_second": 199.88,
+      "eval_steps_per_second": 25.018,
+      "step": 1000
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 9.492772667542707e-05,
+      "loss": 0.4591,
+      "step": 2000
+    },
+    {
+      "epoch": 2.63,
+      "eval_accuracy": 0.7437582128777924,
+      "eval_loss": 0.8957909345626831,
+      "eval_runtime": 14.7365,
+      "eval_samples_per_second": 206.562,
+      "eval_steps_per_second": 25.854,
+      "step": 2000
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 4.2417871222076216e-05,
+      "loss": 0.1681,
+      "step": 3000
+    },
+    {
+      "epoch": 3.94,
+      "eval_accuracy": 0.7473718791064389,
+      "eval_loss": 0.9884209632873535,
+      "eval_runtime": 14.6927,
+      "eval_samples_per_second": 207.177,
+      "eval_steps_per_second": 25.931,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "step": 3805,
+      "total_flos": 9.43613651782739e+18,
+      "train_loss": 0.43440550003352524,
+      "train_runtime": 1184.7674,
+      "train_samples_per_second": 102.767,
+      "train_steps_per_second": 3.212
+    }
+  ],
+  "max_steps": 3805,
+  "num_train_epochs": 5,
+  "total_flos": 9.43613651782739e+18,
+  "trial_name": null,
+  "trial_params": null
+}