./google-vit-base-patch16-224-in21k-9H

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5122
+- Loss: 0.8449
 - Accuracy: 0.9877
 
 ## Model description

all_results.json

@@ -1,8 +1,13 @@
 {
     "epoch": 3.0,
+    "eval_accuracy": 0.9876543209876543,
+    "eval_loss": 0.8449140191078186,
+    "eval_runtime": 4.6209,
+    "eval_samples_per_second": 17.529,
+    "eval_steps_per_second": 4.545,
     "total_flos": 1.6948561394167603e+17,
-    "train_loss": 1.5463701361390554,
-    "train_runtime": 160.3132,
-    "train_samples_per_second": 13.642,
-    "train_steps_per_second": 1.366
+    "train_loss": 0.7343477571391623,
+    "train_runtime": 162.6903,
+    "train_samples_per_second": 13.443,
+    "train_steps_per_second": 1.346
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9876543209876543,
+    "eval_loss": 0.8449140191078186,
+    "eval_runtime": 4.6209,
+    "eval_samples_per_second": 17.529,
+    "eval_steps_per_second": 4.545
+}

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 1.6948561394167603e+17,
-    "train_loss": 1.5463701361390554,
-    "train_runtime": 160.3132,
-    "train_samples_per_second": 13.642,
-    "train_steps_per_second": 1.366
+    "train_loss": 0.7343477571391623,
+    "train_runtime": 162.6903,
+    "train_samples_per_second": 13.443,
+    "train_steps_per_second": 1.346
 }

trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.9876543209876543,
+  "best_model_checkpoint": "/content/drive/MyDrive/graduate_design/ViT_train_pictures/output_dir/checkpoint-73",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 219,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9876543209876543,
+      "eval_loss": 0.8449140191078186,
+      "eval_runtime": 4.0408,
+      "eval_samples_per_second": 20.045,
+      "eval_steps_per_second": 5.197,
+      "step": 73
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9876543209876543,
+      "eval_loss": 0.5911225080490112,
+      "eval_runtime": 4.5389,
+      "eval_samples_per_second": 17.846,
+      "eval_steps_per_second": 4.627,
+      "step": 146
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9876543209876543,
+      "eval_loss": 0.5122054219245911,
+      "eval_runtime": 4.2151,
+      "eval_samples_per_second": 19.217,
+      "eval_steps_per_second": 4.982,
+      "step": 219
+    },
+    {
+      "epoch": 3.0,
+      "step": 219,
+      "total_flos": 1.6948561394167603e+17,
+      "train_loss": 0.7343477571391623,
+      "train_runtime": 162.6903,
+      "train_samples_per_second": 13.443,
+      "train_steps_per_second": 1.346
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 219,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.6948561394167603e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}