End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.99,
+    "eval_accuracy": 0.6295503211991434,
+    "eval_loss": 1.2569200992584229,
+    "eval_runtime": 567.0498,
+    "eval_samples_per_second": 3.294,
+    "eval_steps_per_second": 0.104,
+    "total_flos": 5.754191243425874e+17,
+    "train_loss": 1.2428720572899128,
+    "train_runtime": 7720.7632,
+    "train_samples_per_second": 0.968,
+    "train_steps_per_second": 0.008
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "eval_accuracy": 0.6295503211991434,
+    "eval_loss": 1.2569200992584229,
+    "eval_runtime": 567.0498,
+    "eval_samples_per_second": 3.294,
+    "eval_steps_per_second": 0.104
+}

runs/Dec18_19-59-57_f7125d28fcdc/events.out.tfevents.1702937909.f7125d28fcdc.42.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf0300d7a7c869b9dbce4bc94ba512e71010848ae22623cbcb2e95fa08227248
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "total_flos": 5.754191243425874e+17,
+    "train_loss": 1.2428720572899128,
+    "train_runtime": 7720.7632,
+    "train_samples_per_second": 0.968,
+    "train_steps_per_second": 0.008
+}

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.6295503211991434,
+  "best_model_checkpoint": "vit-base-patch16-224-finetuned-imagegpt/checkpoint-58",
+  "epoch": 0.9914529914529915,
+  "eval_steps": 500,
+  "global_step": 58,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 2.4078,
+      "step": 10
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.653846153846154e-05,
+      "loss": 1.4401,
+      "step": 20
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.6923076923076923e-05,
+      "loss": 1.0484,
+      "step": 30
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.730769230769231e-05,
+      "loss": 0.8997,
+      "step": 40
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.7934,
+      "step": 50
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.6295503211991434,
+      "eval_loss": 1.2569200992584229,
+      "eval_runtime": 579.0302,
+      "eval_samples_per_second": 3.226,
+      "eval_steps_per_second": 0.102,
+      "step": 58
+    },
+    {
+      "epoch": 0.99,
+      "step": 58,
+      "total_flos": 5.754191243425874e+17,
+      "train_loss": 1.2428720572899128,
+      "train_runtime": 7720.7632,
+      "train_samples_per_second": 0.968,
+      "train_steps_per_second": 0.008
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 58,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 5.754191243425874e+17,
+  "trial_name": null,
+  "trial_params": null
+}