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: 2.6927
 
 ## Model description
 

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 10.0,
-    "eval_loss": 2.9003005027770996,
-    "eval_runtime": 11.5402,
-    "eval_samples_per_second": 4.506,
-    "eval_steps_per_second": 0.173,
-    "test_loss": 3.050781726837158,
-    "test_runtime": 25.3536,
-    "test_samples_per_second": 4.102,
-    "test_steps_per_second": 0.158,
-    "train_loss": 2.9446426391601563,
-    "train_runtime": 3632.8393,
-    "train_samples_per_second": 1.153,
-    "train_steps_per_second": 0.039
+    "eval_loss": 2.6927454471588135,
+    "eval_runtime": 9.9974,
+    "eval_samples_per_second": 4.701,
+    "eval_steps_per_second": 0.2,
+    "test_loss": 2.9896740913391113,
+    "test_runtime": 20.647,
+    "test_samples_per_second": 4.698,
+    "test_steps_per_second": 0.194,
+    "train_loss": 2.822861735026042,
+    "train_runtime": 3007.5818,
+    "train_samples_per_second": 1.26,
+    "train_steps_per_second": 0.04
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 10.0,
-    "eval_loss": 2.9003005027770996,
-    "eval_runtime": 11.5402,
-    "eval_samples_per_second": 4.506,
-    "eval_steps_per_second": 0.173
+    "eval_loss": 2.6927454471588135,
+    "eval_runtime": 9.9974,
+    "eval_samples_per_second": 4.701,
+    "eval_steps_per_second": 0.2
 }

preprocessor_config.json

@@ -1,4 +1,21 @@
 {
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
   "crop_size": {
     "height": 224,
     "width": 224

test_results.json

@@ -1,6 +1,6 @@
 {
-    "test_loss": 3.050781726837158,
-    "test_runtime": 25.3536,
-    "test_samples_per_second": 4.102,
-    "test_steps_per_second": 0.158
+    "test_loss": 2.9896740913391113,
+    "test_runtime": 20.647,
+    "test_samples_per_second": 4.698,
+    "test_steps_per_second": 0.194
 }

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 10.0,
-    "train_loss": 2.9446426391601563,
-    "train_runtime": 3632.8393,
-    "train_samples_per_second": 1.153,
-    "train_steps_per_second": 0.039
+    "train_loss": 2.822861735026042,
+    "train_runtime": 3007.5818,
+    "train_samples_per_second": 1.26,
+    "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": 140,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 10.0,
-      "step": 140,
-      "total_flos": 753693745889700.0,
-      "train_loss": 2.9446426391601563,
-      "train_runtime": 3632.8393,
-      "train_samples_per_second": 1.153,
-      "train_steps_per_second": 0.039
+      "step": 120,
+      "total_flos": 681742075637700.0,
+      "train_loss": 2.822861735026042,
+      "train_runtime": 3007.5818,
+      "train_samples_per_second": 1.26,
+      "train_steps_per_second": 0.04
     }
   ],
   "logging_steps": 500,
-  "max_steps": 140,
+  "max_steps": 120,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 753693745889700.0,
+  "total_flos": 681742075637700.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null