End of training

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # clip-vit-large-patch14-finetuned-sofas
 
 This model is a fine-tuned version of [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1527
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 10.0,
-    "eval_loss": 3.532412052154541,
-    "eval_runtime": 10.0151,
+    "eval_loss": 2.1526899337768555,
+    "eval_runtime": 11.0798,
     "eval_samples_per_second": 4.693,
-    "eval_steps_per_second": 0.2,
-    "test_loss": 5.01876974105835,
-    "test_runtime": 20.7585,
-    "test_samples_per_second": 4.673,
-    "test_steps_per_second": 0.193,
-    "train_loss": 1.9417870839436848,
-    "train_runtime": 3223.0323,
-    "train_samples_per_second": 1.176,
-    "train_steps_per_second": 0.037
+    "eval_steps_per_second": 0.181,
+    "test_loss": 2.584235906600952,
+    "test_runtime": 22.1131,
+    "test_samples_per_second": 4.703,
+    "test_steps_per_second": 0.181,
+    "train_loss": 1.5176889692034041,
+    "train_runtime": 3535.8421,
+    "train_samples_per_second": 1.185,
+    "train_steps_per_second": 0.04
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 10.0,
-    "eval_loss": 3.532412052154541,
-    "eval_runtime": 10.0151,
+    "eval_loss": 2.1526899337768555,
+    "eval_runtime": 11.0798,
     "eval_samples_per_second": 4.693,
-    "eval_steps_per_second": 0.2
+    "eval_steps_per_second": 0.181
 }

test_results.json

@@ -1,6 +1,6 @@
 {
-    "test_loss": 5.01876974105835,
-    "test_runtime": 20.7585,
-    "test_samples_per_second": 4.673,
-    "test_steps_per_second": 0.193
+    "test_loss": 2.584235906600952,
+    "test_runtime": 22.1131,
+    "test_samples_per_second": 4.703,
+    "test_steps_per_second": 0.181
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 10.0,
-    "train_loss": 1.9417870839436848,
-    "train_runtime": 3223.0323,
-    "train_samples_per_second": 1.176,
-    "train_steps_per_second": 0.037
+    "train_loss": 1.5176889692034041,
+    "train_runtime": 3535.8421,
+    "train_samples_per_second": 1.185,
+    "train_steps_per_second": 0.04
 }

trainer_state.json

@@ -3,27 +3,27 @@
   "best_model_checkpoint": null,
   "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 10.0,
-      "step": 120,
-      "total_flos": 681742075637700.0,
-      "train_loss": 1.9417870839436848,
-      "train_runtime": 3223.0323,
-      "train_samples_per_second": 1.176,
-      "train_steps_per_second": 0.037
+      "step": 140,
+      "total_flos": 753693745889700.0,
+      "train_loss": 1.5176889692034041,
+      "train_runtime": 3535.8421,
+      "train_samples_per_second": 1.185,
+      "train_steps_per_second": 0.04
     }
   ],
   "logging_steps": 500,
-  "max_steps": 120,
+  "max_steps": 140,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 681742075637700.0,
+  "total_flos": 753693745889700.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null