Upload folder using huggingface_hub

checkpoint-7623/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce8ab6dbce6287960ea5fdf6432aa92c141bb2348dd8f398cd88288f69143a4
+oid sha256:b6dc632b36bf1d57de1137187ecb65d61f8d0e7e44da4ff1872166954cf1b27e
 size 343365480

checkpoint-7623/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2d6db04e237478c0203eb0fc447ab351526e0c29985b727d7453dab5a5cad2
+oid sha256:937e06b36df80b42a99a4fca22ca99b899519df98d0040ceffc85f07a3aefc3e
 size 686851461

checkpoint-7623/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.488718032836914,
+  "best_metric": 1.4409993886947632,
   "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": 8.220705032348633,
+      "grad_norm": 8.759430885314941,
       "learning_rate": 8.465205334741845e-07,
-      "loss": 1.4752,
+      "loss": 1.4398,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 7.696910858154297,
+      "grad_norm": 8.932340621948242,
       "learning_rate": 7.870989040010564e-07,
-      "loss": 1.4833,
+      "loss": 1.4352,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 7.823228359222412,
+      "grad_norm": 9.20963191986084,
       "learning_rate": 7.276772745279281e-07,
-      "loss": 1.4728,
+      "loss": 1.4189,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 6.080297946929932,
+      "grad_norm": 8.43055534362793,
       "learning_rate": 6.682556450547999e-07,
-      "loss": 1.4901,
+      "loss": 1.4281,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 7.583363056182861,
+      "grad_norm": 7.581571578979492,
       "learning_rate": 6.088340155816718e-07,
-      "loss": 1.4755,
+      "loss": 1.4212,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6088537053439622,
-      "eval_loss": 1.5104930400848389,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 1216.8858,
-      "eval_samples_per_second": 89.067,
-      "eval_steps_per_second": 2.783,
+      "eval_accuracy": 0.6224073664009447,
+      "eval_loss": 1.4633311033248901,
+      "eval_model_preparation_time": 0.0052,
+      "eval_runtime": 1196.6375,
+      "eval_samples_per_second": 90.574,
+      "eval_steps_per_second": 2.83,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 9.293631553649902,
+      "grad_norm": 8.631559371948242,
       "learning_rate": 5.494123861085435e-07,
-      "loss": 1.4665,
+      "loss": 1.416,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 8.063645362854004,
+      "grad_norm": 7.313708305358887,
       "learning_rate": 4.899907566354153e-07,
-      "loss": 1.4613,
+      "loss": 1.3983,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 6.942551612854004,
+      "grad_norm": 8.412739753723145,
       "learning_rate": 4.3056912716228705e-07,
-      "loss": 1.4569,
+      "loss": 1.4022,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 11.436430931091309,
+      "grad_norm": 8.88099479675293,
       "learning_rate": 3.7114749768915883e-07,
-      "loss": 1.4412,
+      "loss": 1.4047,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 6.971865177154541,
+      "grad_norm": 6.803462505340576,
       "learning_rate": 3.117258682160306e-07,
-      "loss": 1.4428,
+      "loss": 1.3919,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6121660023619723,
-      "eval_loss": 1.4942480325698853,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 1210.5473,
-      "eval_samples_per_second": 89.533,
-      "eval_steps_per_second": 2.798,
+      "eval_accuracy": 0.6274911426040743,
+      "eval_loss": 1.4468485116958618,
+      "eval_model_preparation_time": 0.0052,
+      "eval_runtime": 1503.5311,
+      "eval_samples_per_second": 72.086,
+      "eval_steps_per_second": 2.253,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 7.25930643081665,
+      "grad_norm": 8.684732437133789,
       "learning_rate": 2.523042387429024e-07,
-      "loss": 1.4412,
+      "loss": 1.4015,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 8.07095718383789,
+      "grad_norm": 9.197487831115723,
       "learning_rate": 1.928826092697742e-07,
-      "loss": 1.4362,
+      "loss": 1.3821,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 8.908621788024902,
+      "grad_norm": 8.341646194458008,
       "learning_rate": 1.3346097979664598e-07,
-      "loss": 1.4375,
+      "loss": 1.3932,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 8.16598129272461,
+      "grad_norm": 11.383636474609375,
       "learning_rate": 7.403935032351777e-08,
-      "loss": 1.4397,
+      "loss": 1.3943,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 9.264542579650879,
+      "grad_norm": 7.704733371734619,
       "learning_rate": 1.4617720850389543e-08,
-      "loss": 1.437,
+      "loss": 1.387,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6130332890463537,
-      "eval_loss": 1.488718032836914,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 1205.355,
-      "eval_samples_per_second": 89.919,
-      "eval_steps_per_second": 2.81,
+      "eval_accuracy": 0.6277218039563035,
+      "eval_loss": 1.4409993886947632,
+      "eval_model_preparation_time": 0.0052,
+      "eval_runtime": 1211.7556,
+      "eval_samples_per_second": 89.444,
+      "eval_steps_per_second": 2.795,
       "step": 7623
     }
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce8ab6dbce6287960ea5fdf6432aa92c141bb2348dd8f398cd88288f69143a4
+oid sha256:b6dc632b36bf1d57de1137187ecb65d61f8d0e7e44da4ff1872166954cf1b27e
 size 343365480