End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # category-cleaning-clip-clip-finetuned
 
 This model was trained from scratch on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0896
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 3.0,
-    "eval_loss": 2.754795551300049,
-    "eval_runtime": 32.3618,
-    "eval_samples_per_second": 129.165,
-    "eval_steps_per_second": 2.039,
-    "train_loss": 2.096000930889934,
-    "train_runtime": 1306.2505,
-    "train_samples_per_second": 57.598,
-    "train_steps_per_second": 0.9
+    "eval_loss": 1.089611530303955,
+    "eval_runtime": 32.1219,
+    "eval_samples_per_second": 130.129,
+    "eval_steps_per_second": 2.055,
+    "train_loss": 0.5163130573674936,
+    "train_runtime": 1318.4118,
+    "train_samples_per_second": 57.066,
+    "train_steps_per_second": 0.892
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "eval_loss": 2.754795551300049,
-    "eval_runtime": 32.3618,
-    "eval_samples_per_second": 129.165,
-    "eval_steps_per_second": 2.039
+    "eval_loss": 1.089611530303955,
+    "eval_runtime": 32.1219,
+    "eval_samples_per_second": 130.129,
+    "eval_steps_per_second": 2.055
 }

runs/Mar06_14-18-35_31db2f29a106/events.out.tfevents.1709736148.31db2f29a106.19351.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b766b704d93cf1386da95f6d32c3edc0f9333e169f7b31b4ffef0b1e49767a2a
+size 359

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "train_loss": 2.096000930889934,
-    "train_runtime": 1306.2505,
-    "train_samples_per_second": 57.598,
-    "train_steps_per_second": 0.9
+    "train_loss": 0.5163130573674936,
+    "train_runtime": 1318.4118,
+    "train_samples_per_second": 57.066,
+    "train_steps_per_second": 0.892
 }

trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.28,
-      "grad_norm": 22.139713287353516,
+      "grad_norm": 20.934419631958008,
       "learning_rate": 2.8741496598639456e-05,
-      "loss": 2.6574,
+      "loss": 0.9434,
       "step": 500
     },
     {
       "epoch": 2.55,
-      "grad_norm": 28.82680320739746,
+      "grad_norm": 31.916597366333008,
       "learning_rate": 7.482993197278912e-06,
-      "loss": 1.7929,
+      "loss": 0.2421,
       "step": 1000
     },
     {
       "epoch": 3.0,
       "step": 1176,
       "total_flos": 4376310425967942.0,
-      "train_loss": 2.096000930889934,
-      "train_runtime": 1306.2505,
-      "train_samples_per_second": 57.598,
-      "train_steps_per_second": 0.9
+      "train_loss": 0.5163130573674936,
+      "train_runtime": 1318.4118,
+      "train_samples_per_second": 57.066,
+      "train_steps_per_second": 0.892
     }
   ],
   "logging_steps": 500,