Upload folder using huggingface_hub

checkpoint-7623/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94041a972f43492ea16c781df9db0a19e23b4af5c2c800136aa233f918e8c926
+oid sha256:8a2b797d777af2b0c15e21bb08fc88faaa6156ea9587da60623b25788f0ed759
 size 343365480

checkpoint-7623/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2c525530046d742e8a9c6b684412fe51e5e12a55d61591aae567873f186dc8
+oid sha256:bfd145eaf1a08feb1a9bc5054b41a958c835de0da274a967155c68f79455adcf
 size 686851461

checkpoint-7623/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.832238495349884,
+  "best_metric": 0.8181275725364685,
   "best_model_checkpoint": "cat_breed_image_detection/checkpoint-7623",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,137 +10,137 @@
   "log_history": [
     {
       "epoch": 0.19677292404565133,
-      "grad_norm": 10.799985885620117,
+      "grad_norm": 17.779321670532227,
       "learning_rate": 6.584048593688102e-07,
-      "loss": 0.7525,
+      "loss": 0.7478,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 13.88831615447998,
+      "grad_norm": 19.093740463256836,
       "learning_rate": 6.12188036445266e-07,
-      "loss": 0.7606,
+      "loss": 0.7451,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 10.507097244262695,
+      "grad_norm": 11.988561630249023,
       "learning_rate": 5.659712135217218e-07,
-      "loss": 0.7568,
+      "loss": 0.7481,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 14.891112327575684,
+      "grad_norm": 12.481701850891113,
       "learning_rate": 5.197543905981778e-07,
-      "loss": 0.7615,
+      "loss": 0.7618,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 14.09949016571045,
+      "grad_norm": 13.344101905822754,
       "learning_rate": 4.7353756767463353e-07,
-      "loss": 0.7659,
+      "loss": 0.7418,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7616899173309714,
-      "eval_loss": 0.8394082188606262,
-      "eval_model_preparation_time": 0.0058,
-      "eval_runtime": 1186.6978,
-      "eval_samples_per_second": 91.332,
-      "eval_steps_per_second": 2.854,
+      "eval_accuracy": 0.7666260702686744,
+      "eval_loss": 0.8249521851539612,
+      "eval_model_preparation_time": 0.0075,
+      "eval_runtime": 1189.4277,
+      "eval_samples_per_second": 91.123,
+      "eval_steps_per_second": 2.848,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 12.55162525177002,
+      "grad_norm": 12.604414939880371,
       "learning_rate": 4.273207447510894e-07,
-      "loss": 0.7569,
+      "loss": 0.7428,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 8.38792896270752,
+      "grad_norm": 11.070133209228516,
       "learning_rate": 3.8110392182754523e-07,
-      "loss": 0.7385,
+      "loss": 0.7337,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 14.774518013000488,
+      "grad_norm": 9.148447036743164,
       "learning_rate": 3.34887098904001e-07,
-      "loss": 0.7586,
+      "loss": 0.7423,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 12.208711624145508,
+      "grad_norm": 8.443017959594727,
       "learning_rate": 2.886702759804569e-07,
-      "loss": 0.7445,
+      "loss": 0.7418,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 10.817965507507324,
+      "grad_norm": 12.822120666503906,
       "learning_rate": 2.424534530569127e-07,
-      "loss": 0.7536,
+      "loss": 0.7395,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7624833923826395,
-      "eval_loss": 0.8353193402290344,
-      "eval_model_preparation_time": 0.0058,
-      "eval_runtime": 1195.2016,
-      "eval_samples_per_second": 90.683,
-      "eval_steps_per_second": 2.834,
+      "eval_accuracy": 0.7675948479480366,
+      "eval_loss": 0.819111168384552,
+      "eval_model_preparation_time": 0.0075,
+      "eval_runtime": 1194.3948,
+      "eval_samples_per_second": 90.744,
+      "eval_steps_per_second": 2.836,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 8.807418823242188,
+      "grad_norm": 8.802216529846191,
       "learning_rate": 1.9623663013336853e-07,
-      "loss": 0.75,
+      "loss": 0.7385,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 11.618365287780762,
+      "grad_norm": 11.116040229797363,
       "learning_rate": 1.5001980720982439e-07,
-      "loss": 0.7474,
+      "loss": 0.7243,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 8.761614799499512,
+      "grad_norm": 8.803569793701172,
       "learning_rate": 1.0380298428628021e-07,
-      "loss": 0.7416,
+      "loss": 0.7448,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 10.143717765808105,
+      "grad_norm": 11.275320053100586,
       "learning_rate": 5.7586161362736035e-08,
-      "loss": 0.7421,
+      "loss": 0.7354,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 11.86281967163086,
+      "grad_norm": 12.109325408935547,
       "learning_rate": 1.1369338439191866e-08,
-      "loss": 0.7394,
+      "loss": 0.7297,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7636090197815175,
-      "eval_loss": 0.832238495349884,
-      "eval_model_preparation_time": 0.0058,
-      "eval_runtime": 1186.9177,
-      "eval_samples_per_second": 91.316,
-      "eval_steps_per_second": 2.854,
+      "eval_accuracy": 0.7687481547091821,
+      "eval_loss": 0.8181275725364685,
+      "eval_model_preparation_time": 0.0075,
+      "eval_runtime": 1213.6961,
+      "eval_samples_per_second": 89.301,
+      "eval_steps_per_second": 2.791,
       "step": 7623
     }
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94041a972f43492ea16c781df9db0a19e23b4af5c2c800136aa233f918e8c926
+oid sha256:8a2b797d777af2b0c15e21bb08fc88faaa6156ea9587da60623b25788f0ed759
 size 343365480