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": "4.43.3"
+  "transformers_version": "4.44.0"
 }

checkpoint-7623/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4abfa71d9858cae0e97b49251c8e3dd29f38ff87eb8bcb8e21462a0c0b07382
+oid sha256:d8b56c15d39ce5160f84f1f17315024c754689a542f828d6b5815004aaf55cdc
 size 343365480

checkpoint-7623/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1394e627794640de9f4175eaec400d26690f3f6469e963c89b3aef8e1c9847b
+oid sha256:3a87694ffc521195d54148920564399fd71fcacf481cfbd34a743ba3210e0c87
 size 686851461

checkpoint-7623/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f696e75fe8786dd955df182ba81df65ab470f5e0a95e7c49ab1518f21aa6499f
+oid sha256:42f136621a57d3b2fd8940093b083eb81ea4104d14897e8bdf69e100c3f6ec13
 size 627

checkpoint-7623/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.1867649555206299,
+  "best_metric": 1.0619962215423584,
   "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": 15.461106300354004,
-      "learning_rate": 8.465205334741845e-07,
-      "loss": 1.1454,
+      "grad_norm": 12.01923656463623,
+      "learning_rate": 7.524626964214973e-07,
+      "loss": 1.0123,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 22.293109893798828,
-      "learning_rate": 7.870989040010564e-07,
-      "loss": 1.1528,
+      "grad_norm": 11.533829689025879,
+      "learning_rate": 6.996434702231612e-07,
+      "loss": 1.0073,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 8.640257835388184,
-      "learning_rate": 7.276772745279281e-07,
-      "loss": 1.1559,
+      "grad_norm": 12.163763999938965,
+      "learning_rate": 6.46824244024825e-07,
+      "loss": 1.004,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 11.094526290893555,
-      "learning_rate": 6.682556450547999e-07,
-      "loss": 1.1593,
+      "grad_norm": 8.848891258239746,
+      "learning_rate": 5.940050178264888e-07,
+      "loss": 1.002,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 11.131674766540527,
-      "learning_rate": 6.088340155816718e-07,
-      "loss": 1.1221,
+      "grad_norm": 8.833011627197266,
+      "learning_rate": 5.411857916281527e-07,
+      "loss": 0.9938,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6807554620608208,
-      "eval_loss": 1.2059290409088135,
-      "eval_model_preparation_time": 0.0051,
-      "eval_runtime": 1193.0691,
-      "eval_samples_per_second": 90.845,
-      "eval_steps_per_second": 2.839,
+      "eval_accuracy": 0.7094405078240331,
+      "eval_loss": 1.0737584829330444,
+      "eval_model_preparation_time": 0.0066,
+      "eval_runtime": 1208.9637,
+      "eval_samples_per_second": 89.65,
+      "eval_steps_per_second": 2.802,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 8.923126220703125,
-      "learning_rate": 5.494123861085435e-07,
-      "loss": 1.1413,
+      "grad_norm": 8.953508377075195,
+      "learning_rate": 4.883665654298165e-07,
+      "loss": 0.989,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 9.620901107788086,
-      "learning_rate": 4.899907566354153e-07,
-      "loss": 1.12,
+      "grad_norm": 10.335805892944336,
+      "learning_rate": 4.355473392314803e-07,
+      "loss": 0.9866,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 11.071784019470215,
-      "learning_rate": 4.3056912716228705e-07,
-      "loss": 1.1305,
+      "grad_norm": 11.203774452209473,
+      "learning_rate": 3.8272811303314405e-07,
+      "loss": 0.9972,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 9.808845520019531,
-      "learning_rate": 3.7114749768915883e-07,
-      "loss": 1.1187,
+      "grad_norm": 8.466325759887695,
+      "learning_rate": 3.2990888683480783e-07,
+      "loss": 0.9824,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 8.686152458190918,
-      "learning_rate": 3.117258682160306e-07,
-      "loss": 1.1238,
+      "grad_norm": 7.2133331298828125,
+      "learning_rate": 2.7708966063647166e-07,
+      "loss": 0.9799,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6841415707115441,
-      "eval_loss": 1.19118332862854,
-      "eval_model_preparation_time": 0.0051,
-      "eval_runtime": 1188.9153,
-      "eval_samples_per_second": 91.162,
-      "eval_steps_per_second": 2.849,
+      "eval_accuracy": 0.7116087245349867,
+      "eval_loss": 1.0655748844146729,
+      "eval_model_preparation_time": 0.0066,
+      "eval_runtime": 1248.8826,
+      "eval_samples_per_second": 86.785,
+      "eval_steps_per_second": 2.712,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 9.841617584228516,
-      "learning_rate": 2.523042387429024e-07,
-      "loss": 1.1033,
+      "grad_norm": 6.7830491065979,
+      "learning_rate": 2.2427043443813546e-07,
+      "loss": 0.9948,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 10.633978843688965,
-      "learning_rate": 1.928826092697742e-07,
-      "loss": 1.1176,
+      "grad_norm": 10.073229789733887,
+      "learning_rate": 1.714512082397993e-07,
+      "loss": 0.966,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 8.568585395812988,
-      "learning_rate": 1.3346097979664598e-07,
-      "loss": 1.1193,
+      "grad_norm": 8.630289077758789,
+      "learning_rate": 1.186319820414631e-07,
+      "loss": 0.9904,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 10.57896900177002,
-      "learning_rate": 7.403935032351777e-08,
-      "loss": 1.107,
+      "grad_norm": 9.734028816223145,
+      "learning_rate": 6.58127558431269e-08,
+      "loss": 0.9671,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 9.359890937805176,
-      "learning_rate": 1.4617720850389543e-08,
-      "loss": 1.1133,
+      "grad_norm": 13.89803695678711,
+      "learning_rate": 1.2993529644790705e-08,
+      "loss": 0.9834,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6847412902273399,
-      "eval_loss": 1.1867649555206299,
-      "eval_model_preparation_time": 0.0051,
-      "eval_runtime": 1192.8682,
-      "eval_samples_per_second": 90.86,
-      "eval_steps_per_second": 2.839,
+      "eval_accuracy": 0.712356067316209,
+      "eval_loss": 1.0619962215423584,
+      "eval_model_preparation_time": 0.0066,
+      "eval_runtime": 1239.6344,
+      "eval_samples_per_second": 87.432,
+      "eval_steps_per_second": 2.732,
       "step": 7623
     }
   ],

checkpoint-7623/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ddce706ee826114a81e5dc98c1b4a675a40b3cf07bb0062afea81a5ff747285
+oid sha256:c2d5f7cdc6601635e5f69bc583373e85c4f40edb1fb3b02520e9444e6c5414cd
 size 4667

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a00859aea079c75799c0858b733d733508af5552a18430897062c592a2583a
+oid sha256:d8b56c15d39ce5160f84f1f17315024c754689a542f828d6b5815004aaf55cdc
 size 343365480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6e2b24c2bb418666641ee5942c486949ee0d8efdf7de643fb67fbd8451ce35
+oid sha256:c2d5f7cdc6601635e5f69bc583373e85c4f40edb1fb3b02520e9444e6c5414cd
 size 4667