Upload folder using huggingface_hub

checkpoint-7623/config.json

@@ -120,5 +120,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.0"
+  "transformers_version": "4.44.2"
 }

checkpoint-7623/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f4b9de3ad1c437575d8c1632b8efd35addd79364f6e8707537d1b652985082a
+oid sha256:94041a972f43492ea16c781df9db0a19e23b4af5c2c800136aa233f918e8c926
 size 343365480

checkpoint-7623/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec5c0fc7da56e53557eaff9d30b9b24fd6a75303f50bb36643296520e5ebae4
+oid sha256:1e2c525530046d742e8a9c6b684412fe51e5e12a55d61591aae567873f186dc8
 size 686851461

checkpoint-7623/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42f136621a57d3b2fd8940093b083eb81ea4104d14897e8bdf69e100c3f6ec13
+oid sha256:6d381fcf0af840337589709e778884ae24e2c6cd781f1b7f6da217674cf6d157
 size 627

checkpoint-7623/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.0335272550582886,
+  "best_metric": 0.832238495349884,
   "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": 8.757041931152344,
-      "learning_rate": 7.524626964214973e-07,
-      "loss": 0.9786,
+      "grad_norm": 10.799985885620117,
+      "learning_rate": 6.584048593688102e-07,
+      "loss": 0.7525,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 8.383247375488281,
-      "learning_rate": 6.996434702231612e-07,
-      "loss": 0.9913,
+      "grad_norm": 13.88831615447998,
+      "learning_rate": 6.12188036445266e-07,
+      "loss": 0.7606,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 11.913640022277832,
-      "learning_rate": 6.46824244024825e-07,
-      "loss": 0.986,
+      "grad_norm": 10.507097244262695,
+      "learning_rate": 5.659712135217218e-07,
+      "loss": 0.7568,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 8.429478645324707,
-      "learning_rate": 5.940050178264888e-07,
-      "loss": 0.9742,
+      "grad_norm": 14.891112327575684,
+      "learning_rate": 5.197543905981778e-07,
+      "loss": 0.7615,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 8.826607704162598,
-      "learning_rate": 5.411857916281527e-07,
-      "loss": 0.9771,
+      "grad_norm": 14.09949016571045,
+      "learning_rate": 4.7353756767463353e-07,
+      "loss": 0.7659,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7168678033658105,
-      "eval_loss": 1.0437126159667969,
-      "eval_model_preparation_time": 0.0056,
-      "eval_runtime": 1253.4528,
-      "eval_samples_per_second": 86.468,
-      "eval_steps_per_second": 2.702,
+      "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,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 11.744253158569336,
-      "learning_rate": 4.883665654298165e-07,
-      "loss": 0.977,
+      "grad_norm": 12.55162525177002,
+      "learning_rate": 4.273207447510894e-07,
+      "loss": 0.7569,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 9.053071022033691,
-      "learning_rate": 4.355473392314803e-07,
-      "loss": 0.9658,
+      "grad_norm": 8.38792896270752,
+      "learning_rate": 3.8110392182754523e-07,
+      "loss": 0.7385,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 10.54920482635498,
-      "learning_rate": 3.8272811303314405e-07,
-      "loss": 0.9709,
+      "grad_norm": 14.774518013000488,
+      "learning_rate": 3.34887098904001e-07,
+      "loss": 0.7586,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 8.325064659118652,
-      "learning_rate": 3.2990888683480783e-07,
-      "loss": 0.9738,
+      "grad_norm": 12.208711624145508,
+      "learning_rate": 2.886702759804569e-07,
+      "loss": 0.7445,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 10.403226852416992,
-      "learning_rate": 2.7708966063647166e-07,
-      "loss": 0.953,
+      "grad_norm": 10.817965507507324,
+      "learning_rate": 2.424534530569127e-07,
+      "loss": 0.7536,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7185377915559492,
-      "eval_loss": 1.0369055271148682,
-      "eval_model_preparation_time": 0.0056,
-      "eval_runtime": 1273.434,
-      "eval_samples_per_second": 85.112,
-      "eval_steps_per_second": 2.66,
+      "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,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 10.920880317687988,
-      "learning_rate": 2.2427043443813546e-07,
-      "loss": 0.9497,
+      "grad_norm": 8.807418823242188,
+      "learning_rate": 1.9623663013336853e-07,
+      "loss": 0.75,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 16.526975631713867,
-      "learning_rate": 1.714512082397993e-07,
-      "loss": 0.9597,
+      "grad_norm": 11.618365287780762,
+      "learning_rate": 1.5001980720982439e-07,
+      "loss": 0.7474,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 9.863446235656738,
-      "learning_rate": 1.186319820414631e-07,
-      "loss": 0.9506,
+      "grad_norm": 8.761614799499512,
+      "learning_rate": 1.0380298428628021e-07,
+      "loss": 0.7416,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 11.81240463256836,
-      "learning_rate": 6.58127558431269e-08,
-      "loss": 0.9705,
+      "grad_norm": 10.143717765808105,
+      "learning_rate": 5.7586161362736035e-08,
+      "loss": 0.7421,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 10.019937515258789,
-      "learning_rate": 1.2993529644790705e-08,
-      "loss": 0.9597,
+      "grad_norm": 11.86281967163086,
+      "learning_rate": 1.1369338439191866e-08,
+      "loss": 0.7394,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7189898878063182,
-      "eval_loss": 1.0335272550582886,
-      "eval_model_preparation_time": 0.0056,
-      "eval_runtime": 1268.3378,
-      "eval_samples_per_second": 85.454,
-      "eval_steps_per_second": 2.67,
+      "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,
       "step": 7623
     }
   ],

checkpoint-7623/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d5f7cdc6601635e5f69bc583373e85c4f40edb1fb3b02520e9444e6c5414cd
+oid sha256:c46896dc6ce144fbab9a60698cf84ee21a3b90e77075f2c78a48583bfaf515f3
 size 4667

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df3ddd9fe71f182f3e23bafb4fb9a307b68b52be0b67299ddeda6bc24a8b22d5
+oid sha256:94041a972f43492ea16c781df9db0a19e23b4af5c2c800136aa233f918e8c926
 size 343365480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24da8bd5bb13554ebf9715f0be1eeb363ad49be1a9401f1cc192f372ad85a4cd
+oid sha256:c46896dc6ce144fbab9a60698cf84ee21a3b90e77075f2c78a48583bfaf515f3
 size 4667