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: 2.7548
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 3.0,
-    "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_loss": 2.754795551300049,
+    "eval_runtime": 31.3124,
+    "eval_samples_per_second": 133.493,
+    "eval_steps_per_second": 2.108,
+    "train_loss": 2.096000930889934,
+    "train_runtime": 1266.7348,
+    "train_samples_per_second": 59.394,
+    "train_steps_per_second": 0.928
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "eval_loss": 1.089611530303955,
-    "eval_runtime": 32.1219,
-    "eval_samples_per_second": 130.129,
-    "eval_steps_per_second": 2.055
+    "eval_loss": 2.754795551300049,
+    "eval_runtime": 31.3124,
+    "eval_samples_per_second": 133.493,
+    "eval_steps_per_second": 2.108
 }

runs/Mar07_13-22-46_ae267012f217/events.out.tfevents.1709819116.ae267012f217.5290.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e407db589b62619a63d10d77c1d9f3aa7f5bfa4b9b5c69ba66f480cd0dc3ced1
+size 359

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.5163130573674936,
-    "train_runtime": 1318.4118,
-    "train_samples_per_second": 57.066,
-    "train_steps_per_second": 0.892
+    "train_loss": 2.096000930889934,
+    "train_runtime": 1266.7348,
+    "train_samples_per_second": 59.394,
+    "train_steps_per_second": 0.928
 }

trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.28,
-      "grad_norm": 20.934419631958008,
+      "grad_norm": 22.139713287353516,
       "learning_rate": 2.8741496598639456e-05,
-      "loss": 0.9434,
+      "loss": 2.6574,
       "step": 500
     },
     {
       "epoch": 2.55,
-      "grad_norm": 31.916597366333008,
+      "grad_norm": 28.82680320739746,
       "learning_rate": 7.482993197278912e-06,
-      "loss": 0.2421,
+      "loss": 1.7929,
       "step": 1000
     },
     {
       "epoch": 3.0,
       "step": 1176,
       "total_flos": 4376310425967942.0,
-      "train_loss": 0.5163130573674936,
-      "train_runtime": 1318.4118,
-      "train_samples_per_second": 57.066,
-      "train_steps_per_second": 0.892
+      "train_loss": 2.096000930889934,
+      "train_runtime": 1266.7348,
+      "train_samples_per_second": 59.394,
+      "train_steps_per_second": 0.928
     }
   ],
   "logging_steps": 500,