End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.93,
+    "eval_accuracy": 0.47560975609756095,
+    "eval_loss": 1.578503131866455,
+    "eval_runtime": 3.742,
+    "eval_samples_per_second": 21.914,
+    "eval_steps_per_second": 2.94,
+    "total_flos": 2.613596809351127e+17,
+    "train_loss": 1.7026190439860025,
+    "train_runtime": 204.8067,
+    "train_samples_per_second": 4.761,
+    "train_steps_per_second": 0.146
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.93,
+    "eval_accuracy": 0.47560975609756095,
+    "eval_loss": 1.578503131866455,
+    "eval_runtime": 3.742,
+    "eval_samples_per_second": 21.914,
+    "eval_steps_per_second": 2.94
+}

runs/Feb09_13-22-55_21fd87067db5/events.out.tfevents.1707485233.21fd87067db5.5198.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335b1715a65539ce699c74c23e8f4610cafdc75de539637607d0d0aec45b8aa5
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.93,
+    "total_flos": 2.613596809351127e+17,
+    "train_loss": 1.7026190439860025,
+    "train_runtime": 204.8067,
+    "train_samples_per_second": 4.761,
+    "train_steps_per_second": 0.146
+}

trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": 0.47560975609756095,
+  "best_model_checkpoint": "MRR_image_classification_dit_29_jan_small75-finetuned-eurosat/checkpoint-30",
+  "epoch": 2.926829268292683,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 1.8795,
+      "step": 10
+    },
+    {
+      "epoch": 0.98,
+      "eval_accuracy": 0.3048780487804878,
+      "eval_loss": 1.643699288368225,
+      "eval_runtime": 4.9921,
+      "eval_samples_per_second": 16.426,
+      "eval_steps_per_second": 2.203,
+      "step": 10
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 1.6681,
+      "step": 20
+    },
+    {
+      "epoch": 1.95,
+      "eval_accuracy": 0.4146341463414634,
+      "eval_loss": 1.6445565223693848,
+      "eval_runtime": 3.6492,
+      "eval_samples_per_second": 22.471,
+      "eval_steps_per_second": 3.014,
+      "step": 20
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0,
+      "loss": 1.5603,
+      "step": 30
+    },
+    {
+      "epoch": 2.93,
+      "eval_accuracy": 0.47560975609756095,
+      "eval_loss": 1.578503131866455,
+      "eval_runtime": 3.4871,
+      "eval_samples_per_second": 23.515,
+      "eval_steps_per_second": 3.154,
+      "step": 30
+    },
+    {
+      "epoch": 2.93,
+      "step": 30,
+      "total_flos": 2.613596809351127e+17,
+      "train_loss": 1.7026190439860025,
+      "train_runtime": 204.8067,
+      "train_samples_per_second": 4.761,
+      "train_steps_per_second": 0.146
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 30,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.613596809351127e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}