Upload folder using huggingface_hub

checkpoint-7623/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2b797d777af2b0c15e21bb08fc88faaa6156ea9587da60623b25788f0ed759
+oid sha256:c7ea1c52d548f69d2ca038efdaf41587698756a14c4248944faf88f391638452
 size 343365480

checkpoint-7623/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd145eaf1a08feb1a9bc5054b41a958c835de0da274a967155c68f79455adcf
+oid sha256:e2abcd237a6a6537467f9e7c25e532002cf7efa9887fcf436e91007c2d764818
 size 686851461

checkpoint-7623/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8181275725364685,
+  "best_metric": 0.8069068789482117,
   "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": 17.779321670532227,
+      "grad_norm": 9.868806838989258,
       "learning_rate": 6.584048593688102e-07,
-      "loss": 0.7478,
+      "loss": 0.7382,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 19.093740463256836,
+      "grad_norm": 9.517308235168457,
       "learning_rate": 6.12188036445266e-07,
-      "loss": 0.7451,
+      "loss": 0.7407,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 11.988561630249023,
+      "grad_norm": 8.953051567077637,
       "learning_rate": 5.659712135217218e-07,
-      "loss": 0.7481,
+      "loss": 0.7344,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 12.481701850891113,
+      "grad_norm": 11.933226585388184,
       "learning_rate": 5.197543905981778e-07,
-      "loss": 0.7618,
+      "loss": 0.7296,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 13.344101905822754,
+      "grad_norm": 10.369135856628418,
       "learning_rate": 4.7353756767463353e-07,
-      "loss": 0.7418,
+      "loss": 0.7334,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "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,
+      "eval_accuracy": 0.7683883229997047,
+      "eval_loss": 0.8134992718696594,
+      "eval_model_preparation_time": 0.0064,
+      "eval_runtime": 1217.5266,
+      "eval_samples_per_second": 89.02,
+      "eval_steps_per_second": 2.782,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 12.604414939880371,
+      "grad_norm": 8.827561378479004,
       "learning_rate": 4.273207447510894e-07,
-      "loss": 0.7428,
+      "loss": 0.7246,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 11.070133209228516,
+      "grad_norm": 13.630207061767578,
       "learning_rate": 3.8110392182754523e-07,
-      "loss": 0.7337,
+      "loss": 0.7408,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 9.148447036743164,
+      "grad_norm": 9.284893989562988,
       "learning_rate": 3.34887098904001e-07,
-      "loss": 0.7423,
+      "loss": 0.7237,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 8.443017959594727,
+      "grad_norm": 11.693731307983398,
       "learning_rate": 2.886702759804569e-07,
-      "loss": 0.7418,
+      "loss": 0.7261,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 12.822120666503906,
+      "grad_norm": 9.744012832641602,
       "learning_rate": 2.424534530569127e-07,
-      "loss": 0.7395,
+      "loss": 0.7188,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "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,
+      "eval_accuracy": 0.7696062149394745,
+      "eval_loss": 0.808617889881134,
+      "eval_model_preparation_time": 0.0064,
+      "eval_runtime": 1216.7178,
+      "eval_samples_per_second": 89.079,
+      "eval_steps_per_second": 2.784,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 8.802216529846191,
+      "grad_norm": 13.421453475952148,
       "learning_rate": 1.9623663013336853e-07,
-      "loss": 0.7385,
+      "loss": 0.7312,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 11.116040229797363,
+      "grad_norm": 13.031763076782227,
       "learning_rate": 1.5001980720982439e-07,
-      "loss": 0.7243,
+      "loss": 0.7223,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 8.803569793701172,
+      "grad_norm": 13.5600004196167,
       "learning_rate": 1.0380298428628021e-07,
-      "loss": 0.7448,
+      "loss": 0.7265,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 11.275320053100586,
+      "grad_norm": 9.442146301269531,
       "learning_rate": 5.7586161362736035e-08,
-      "loss": 0.7354,
+      "loss": 0.7174,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 12.109325408935547,
+      "grad_norm": 9.767436981201172,
       "learning_rate": 1.1369338439191866e-08,
-      "loss": 0.7297,
+      "loss": 0.7124,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "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,
+      "eval_accuracy": 0.7697907440212578,
+      "eval_loss": 0.8069068789482117,
+      "eval_model_preparation_time": 0.0064,
+      "eval_runtime": 1205.4504,
+      "eval_samples_per_second": 89.912,
+      "eval_steps_per_second": 2.81,
       "step": 7623
     }
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2b797d777af2b0c15e21bb08fc88faaa6156ea9587da60623b25788f0ed759
+oid sha256:c7ea1c52d548f69d2ca038efdaf41587698756a14c4248944faf88f391638452
 size 343365480