End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # CLIP_ViT_L_14_PCSP
 
 This model is a fine-tuned version of [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0224
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 100.0,
-    "eval_loss": 0.04353109002113342,
-    "eval_runtime": 0.5545,
-    "eval_samples_per_second": 110.015,
-    "eval_steps_per_second": 7.214,
+    "eval_loss": 0.02241262048482895,
+    "eval_runtime": 0.723,
+    "eval_samples_per_second": 84.367,
+    "eval_steps_per_second": 5.532,
     "total_flos": 4353076050246000.0,
-    "train_loss": 0.4666409730911255,
-    "train_runtime": 540.1503,
-    "train_samples_per_second": 44.802,
-    "train_steps_per_second": 1.481
+    "train_loss": 0.5082710027694702,
+    "train_runtime": 545.8865,
+    "train_samples_per_second": 44.332,
+    "train_steps_per_second": 1.466
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 100.0,
-    "eval_loss": 0.04353109002113342,
-    "eval_runtime": 0.5545,
-    "eval_samples_per_second": 110.015,
-    "eval_steps_per_second": 7.214
+    "eval_loss": 0.02241262048482895,
+    "eval_runtime": 0.723,
+    "eval_samples_per_second": 84.367,
+    "eval_steps_per_second": 5.532
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 100.0,
     "total_flos": 4353076050246000.0,
-    "train_loss": 0.4666409730911255,
-    "train_runtime": 540.1503,
-    "train_samples_per_second": 44.802,
-    "train_steps_per_second": 1.481
+    "train_loss": 0.5082710027694702,
+    "train_runtime": 545.8865,
+    "train_samples_per_second": 44.332,
+    "train_steps_per_second": 1.466
 }

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 62.5,
-      "grad_norm": 5.630551338195801,
+      "grad_norm": 18.85132598876953,
       "learning_rate": 1.8750000000000002e-05,
-      "loss": 0.6576,
+      "loss": 0.7307,
       "step": 500
     },
     {
       "epoch": 100.0,
       "step": 800,
       "total_flos": 4353076050246000.0,
-      "train_loss": 0.4666409730911255,
-      "train_runtime": 540.1503,
-      "train_samples_per_second": 44.802,
-      "train_steps_per_second": 1.481
+      "train_loss": 0.5082710027694702,
+      "train_runtime": 545.8865,
+      "train_samples_per_second": 44.332,
+      "train_steps_per_second": 1.466
     }
   ],
   "logging_steps": 500,