Upload folder using huggingface_hub

checkpoint-7623/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd04e00ba6e7643aec5b40d05d059e420308f028176d7aa21235597d608bc872
+oid sha256:62dfc8be86043484d9eaf20856f78629ee851e733dba965646beada2aa0a8e49
 size 343365480

checkpoint-7623/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296029dced722c0eae52c2386054b3fbbfb5ca02dca5c8c21e0ba327fed6b49a
+oid sha256:0cb453adcd761222b4113170fb483b5b9b6837b2124004e76b7761389266edcb
 size 686851461

checkpoint-7623/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.394932508468628,
+  "best_metric": 1.3125017881393433,
   "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": 8.009295463562012,
+      "grad_norm": 7.071441173553467,
       "learning_rate": 8.465205334741845e-07,
-      "loss": 1.3833,
+      "loss": 1.2994,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 7.348078727722168,
+      "grad_norm": 9.168732643127441,
       "learning_rate": 7.870989040010564e-07,
-      "loss": 1.377,
+      "loss": 1.3024,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 8.270244598388672,
+      "grad_norm": 8.262181282043457,
       "learning_rate": 7.276772745279281e-07,
-      "loss": 1.3842,
+      "loss": 1.2652,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 6.505548477172852,
+      "grad_norm": 10.966161727905273,
       "learning_rate": 6.682556450547999e-07,
-      "loss": 1.3704,
+      "loss": 1.2789,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 9.899617195129395,
+      "grad_norm": 8.47767448425293,
       "learning_rate": 6.088340155816718e-07,
-      "loss": 1.3789,
+      "loss": 1.269,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6332023176852672,
-      "eval_loss": 1.415798544883728,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 1403.0987,
-      "eval_samples_per_second": 77.246,
-      "eval_steps_per_second": 2.414,
+      "eval_accuracy": 0.6525409654561559,
+      "eval_loss": 1.3324801921844482,
+      "eval_model_preparation_time": 0.0054,
+      "eval_runtime": 1508.0216,
+      "eval_samples_per_second": 71.872,
+      "eval_steps_per_second": 2.246,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 7.209441661834717,
+      "grad_norm": 14.689343452453613,
       "learning_rate": 5.494123861085435e-07,
-      "loss": 1.3551,
+      "loss": 1.2627,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 6.6000471115112305,
+      "grad_norm": 7.966395854949951,
       "learning_rate": 4.899907566354153e-07,
-      "loss": 1.3677,
+      "loss": 1.2615,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 9.57729721069336,
+      "grad_norm": 6.865269184112549,
       "learning_rate": 4.3056912716228705e-07,
-      "loss": 1.3535,
+      "loss": 1.2636,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 6.144454479217529,
+      "grad_norm": 9.544075012207031,
       "learning_rate": 3.7114749768915883e-07,
-      "loss": 1.357,
+      "loss": 1.2484,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 8.755939483642578,
+      "grad_norm": 12.453811645507812,
       "learning_rate": 3.117258682160306e-07,
-      "loss": 1.3443,
+      "loss": 1.264,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.636892899320933,
-      "eval_loss": 1.4011926651000977,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 1242.2087,
-      "eval_samples_per_second": 87.251,
-      "eval_steps_per_second": 2.727,
+      "eval_accuracy": 0.6554196191319752,
+      "eval_loss": 1.3183132410049438,
+      "eval_model_preparation_time": 0.0054,
+      "eval_runtime": 1205.014,
+      "eval_samples_per_second": 89.944,
+      "eval_steps_per_second": 2.811,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 11.363967895507812,
+      "grad_norm": 9.422158241271973,
       "learning_rate": 2.523042387429024e-07,
-      "loss": 1.3423,
+      "loss": 1.2342,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 6.285542964935303,
+      "grad_norm": 8.495936393737793,
       "learning_rate": 1.928826092697742e-07,
-      "loss": 1.3412,
+      "loss": 1.2448,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 7.968774795532227,
+      "grad_norm": 8.68142318725586,
       "learning_rate": 1.3346097979664598e-07,
-      "loss": 1.3396,
+      "loss": 1.2507,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 7.346720218658447,
+      "grad_norm": 11.802330017089844,
       "learning_rate": 7.403935032351777e-08,
-      "loss": 1.3324,
+      "loss": 1.2448,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 8.237432479858398,
+      "grad_norm": 8.9815673828125,
       "learning_rate": 1.4617720850389543e-08,
-      "loss": 1.3485,
+      "loss": 1.2538,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6383137732506643,
-      "eval_loss": 1.394932508468628,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 1219.7548,
-      "eval_samples_per_second": 88.857,
-      "eval_steps_per_second": 2.777,
+      "eval_accuracy": 0.6566928697962799,
+      "eval_loss": 1.3125017881393433,
+      "eval_model_preparation_time": 0.0054,
+      "eval_runtime": 1235.4205,
+      "eval_samples_per_second": 87.73,
+      "eval_steps_per_second": 2.742,
       "step": 7623
     }
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84dfadbc414c2f160344bc94dd4eb530ed85c3aeac5a457bccf53f7beb6a48fe
+oid sha256:62dfc8be86043484d9eaf20856f78629ee851e733dba965646beada2aa0a8e49
 size 343365480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa9f0c7be17c246a85b35b1cacecee4f5b32627bf237df20128bcfe78dfeb2a
+oid sha256:2ddce706ee826114a81e5dc98c1b4a675a40b3cf07bb0062afea81a5ff747285
 size 4667