Upload folder using huggingface_hub

checkpoint-12705/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75532c62421984f08e3d09d85f34bf19eab26ac61356b82939424b4e301f2b46
+oid sha256:c959a6ba121009a188316aa890d943534dd22477e8904387c5ec9e70dbebf827
 size 343365480

checkpoint-12705/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4bd37998c719997c828e214c3fe2ffee0468a4dbb5ce5ad1f8cc4ad8dcae70e
+oid sha256:b1ba795c9afadf70f2e133496d2088ad3f168f5c8781d7998c0b6a49930528b4
 size 686851461

checkpoint-12705/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf55a5da2276b7534d8153631c0fcdf3e8887e15240ea11a4f10ae7a7c154943
+oid sha256:f5d77c214e5c4e324e5854dabe47b4e3d9d2a1ab9dafc3ab550c8ebb323537e8
 size 627

checkpoint-12705/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9104332327842712,
+  "best_metric": 0.8710967302322388,
   "best_model_checkpoint": "cat_breed_image_detection/checkpoint-12705",
   "epoch": 5.0,
   "eval_steps": 500,
@@ -10,227 +10,227 @@
   "log_history": [
     {
       "epoch": 0.19677292404565133,
-      "grad_norm": 10.679129600524902,
-      "learning_rate": 7.715527459502173e-07,
-      "loss": 0.8716,
+      "grad_norm": 9.000396728515625,
+      "learning_rate": 6.751086527064401e-07,
+      "loss": 0.8052,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 12.624375343322754,
-      "learning_rate": 7.399446858949032e-07,
-      "loss": 0.8608,
+      "grad_norm": 10.026116371154785,
+      "learning_rate": 6.474516001580403e-07,
+      "loss": 0.8138,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 12.887909889221191,
-      "learning_rate": 7.08336625839589e-07,
-      "loss": 0.8653,
+      "grad_norm": 10.510950088500977,
+      "learning_rate": 6.197945476096404e-07,
+      "loss": 0.8147,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 14.339140892028809,
-      "learning_rate": 6.76728565784275e-07,
-      "loss": 0.8493,
+      "grad_norm": 11.752729415893555,
+      "learning_rate": 5.921374950612407e-07,
+      "loss": 0.8013,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 10.709071159362793,
-      "learning_rate": 6.451205057289608e-07,
-      "loss": 0.8589,
+      "grad_norm": 14.506450653076172,
+      "learning_rate": 5.644804425128407e-07,
+      "loss": 0.8002,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7400815618541482,
-      "eval_loss": 0.9309104084968567,
-      "eval_model_preparation_time": 0.006,
-      "eval_runtime": 1193.8367,
-      "eval_samples_per_second": 90.786,
-      "eval_steps_per_second": 2.837,
+      "eval_accuracy": 0.7514854591083555,
+      "eval_loss": 0.88564133644104,
+      "eval_model_preparation_time": 0.0062,
+      "eval_runtime": 1238.4254,
+      "eval_samples_per_second": 87.518,
+      "eval_steps_per_second": 2.735,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 8.929093360900879,
-      "learning_rate": 6.135124456736468e-07,
-      "loss": 0.8467,
+      "grad_norm": 12.19202995300293,
+      "learning_rate": 5.368233899644408e-07,
+      "loss": 0.7909,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 11.412522315979004,
-      "learning_rate": 5.819043856183327e-07,
-      "loss": 0.8531,
+      "grad_norm": 8.860201835632324,
+      "learning_rate": 5.091663374160411e-07,
+      "loss": 0.8027,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 12.86628532409668,
-      "learning_rate": 5.502963255630185e-07,
-      "loss": 0.8443,
+      "grad_norm": 11.448163986206055,
+      "learning_rate": 4.815092848676412e-07,
+      "loss": 0.8003,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 10.795392990112305,
-      "learning_rate": 5.186882655077045e-07,
-      "loss": 0.8317,
+      "grad_norm": 9.734859466552734,
+      "learning_rate": 4.538522323192414e-07,
+      "loss": 0.8022,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 12.041897773742676,
-      "learning_rate": 4.870802054523904e-07,
-      "loss": 0.8554,
+      "grad_norm": 9.481435775756836,
+      "learning_rate": 4.2619517977084157e-07,
+      "loss": 0.7875,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7436983318571007,
-      "eval_loss": 0.9218501448631287,
-      "eval_model_preparation_time": 0.006,
-      "eval_runtime": 1215.8937,
-      "eval_samples_per_second": 89.139,
-      "eval_steps_per_second": 2.786,
+      "eval_accuracy": 0.7534137880129909,
+      "eval_loss": 0.8801298141479492,
+      "eval_model_preparation_time": 0.0062,
+      "eval_runtime": 1238.556,
+      "eval_samples_per_second": 87.508,
+      "eval_steps_per_second": 2.735,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 8.663507461547852,
-      "learning_rate": 4.5547214539707617e-07,
-      "loss": 0.8319,
+      "grad_norm": 11.236846923828125,
+      "learning_rate": 3.9853812722244165e-07,
+      "loss": 0.7785,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 13.493363380432129,
-      "learning_rate": 4.238640853417621e-07,
-      "loss": 0.8396,
+      "grad_norm": 9.055519104003906,
+      "learning_rate": 3.7088107467404185e-07,
+      "loss": 0.7956,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 18.810260772705078,
-      "learning_rate": 3.92256025286448e-07,
-      "loss": 0.8415,
+      "grad_norm": 10.432591438293457,
+      "learning_rate": 3.43224022125642e-07,
+      "loss": 0.7824,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 11.748995780944824,
-      "learning_rate": 3.606479652311339e-07,
-      "loss": 0.8427,
+      "grad_norm": 8.468033790588379,
+      "learning_rate": 3.155669695772422e-07,
+      "loss": 0.7851,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 9.686206817626953,
-      "learning_rate": 3.290399051758198e-07,
-      "loss": 0.8367,
+      "grad_norm": 8.71891975402832,
+      "learning_rate": 2.879099170288424e-07,
+      "loss": 0.8004,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7437629170357248,
-      "eval_loss": 0.9151368737220764,
-      "eval_model_preparation_time": 0.006,
-      "eval_runtime": 1207.1063,
-      "eval_samples_per_second": 89.788,
-      "eval_steps_per_second": 2.806,
+      "eval_accuracy": 0.7529801446708001,
+      "eval_loss": 0.8765186071395874,
+      "eval_model_preparation_time": 0.0062,
+      "eval_runtime": 1241.4441,
+      "eval_samples_per_second": 87.305,
+      "eval_steps_per_second": 2.728,
       "step": 7623
     },
     {
       "epoch": 3.1483667847304213,
-      "grad_norm": 10.070638656616211,
-      "learning_rate": 2.974318451205057e-07,
-      "loss": 0.8266,
+      "grad_norm": 6.379135608673096,
+      "learning_rate": 2.6025286448044247e-07,
+      "loss": 0.7741,
       "step": 8000
     },
     {
       "epoch": 3.3451397087760726,
-      "grad_norm": 8.807821273803711,
-      "learning_rate": 2.658237850651916e-07,
-      "loss": 0.8258,
+      "grad_norm": 10.30756664276123,
+      "learning_rate": 2.3259581193204266e-07,
+      "loss": 0.7964,
       "step": 8500
     },
     {
       "epoch": 3.541912632821724,
-      "grad_norm": 6.973104953765869,
-      "learning_rate": 2.342157250098775e-07,
-      "loss": 0.8382,
+      "grad_norm": 9.697714805603027,
+      "learning_rate": 2.0493875938364283e-07,
+      "loss": 0.7738,
       "step": 9000
     },
     {
       "epoch": 3.738685556867375,
-      "grad_norm": 9.397773742675781,
-      "learning_rate": 2.026076649545634e-07,
-      "loss": 0.8194,
+      "grad_norm": 10.017168045043945,
+      "learning_rate": 1.7728170683524297e-07,
+      "loss": 0.7758,
       "step": 9500
     },
     {
       "epoch": 3.9354584809130264,
-      "grad_norm": 9.227031707763672,
-      "learning_rate": 1.709996048992493e-07,
-      "loss": 0.8333,
+      "grad_norm": 7.619166851043701,
+      "learning_rate": 1.4962465428684314e-07,
+      "loss": 0.7846,
       "step": 10000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.7457742840271627,
-      "eval_loss": 0.9115355610847473,
-      "eval_model_preparation_time": 0.006,
-      "eval_runtime": 1209.7892,
-      "eval_samples_per_second": 89.589,
-      "eval_steps_per_second": 2.8,
+      "eval_accuracy": 0.7548623413049896,
+      "eval_loss": 0.873340904712677,
+      "eval_model_preparation_time": 0.0062,
+      "eval_runtime": 1251.9913,
+      "eval_samples_per_second": 86.569,
+      "eval_steps_per_second": 2.705,
       "step": 10164
     },
     {
       "epoch": 4.132231404958677,
-      "grad_norm": 10.666913032531738,
-      "learning_rate": 1.393915448439352e-07,
-      "loss": 0.8311,
+      "grad_norm": 11.024943351745605,
+      "learning_rate": 1.219676017384433e-07,
+      "loss": 0.7846,
       "step": 10500
     },
     {
       "epoch": 4.329004329004329,
-      "grad_norm": 8.299125671386719,
-      "learning_rate": 1.077834847886211e-07,
-      "loss": 0.8312,
+      "grad_norm": 9.423783302307129,
+      "learning_rate": 9.431054919004346e-08,
+      "loss": 0.7807,
       "step": 11000
     },
     {
       "epoch": 4.525777253049981,
-      "grad_norm": 10.474702835083008,
-      "learning_rate": 7.617542473330699e-08,
-      "loss": 0.8224,
+      "grad_norm": 7.218919277191162,
+      "learning_rate": 6.665349664164362e-08,
+      "loss": 0.7751,
       "step": 11500
     },
     {
       "epoch": 4.7225501770956315,
-      "grad_norm": 9.30624008178711,
-      "learning_rate": 4.4567364677992886e-08,
-      "loss": 0.8169,
+      "grad_norm": 8.869695663452148,
+      "learning_rate": 3.899644409324377e-08,
+      "loss": 0.7814,
       "step": 12000
     },
     {
       "epoch": 4.919323101141283,
-      "grad_norm": 11.784387588500977,
-      "learning_rate": 1.2959304622678783e-08,
-      "loss": 0.8285,
+      "grad_norm": 8.802694320678711,
+      "learning_rate": 1.1339391544843935e-08,
+      "loss": 0.7703,
       "step": 12500
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.7457742840271627,
-      "eval_loss": 0.9104332327842712,
-      "eval_model_preparation_time": 0.006,
-      "eval_runtime": 1215.0134,
-      "eval_samples_per_second": 89.204,
-      "eval_steps_per_second": 2.788,
+      "eval_accuracy": 0.7551852671981104,
+      "eval_loss": 0.8710967302322388,
+      "eval_model_preparation_time": 0.0062,
+      "eval_runtime": 1234.6786,
+      "eval_samples_per_second": 87.783,
+      "eval_steps_per_second": 2.743,
       "step": 12705
     }
   ],

checkpoint-12705/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ccd77f73df11a1333f963ab6437406025cd7af5d1fcfd30d1c335f7e202d63
+oid sha256:24da8bd5bb13554ebf9715f0be1eeb363ad49be1a9401f1cc192f372ad85a4cd
 size 4667

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f5f76ed594c5458daad41141b36146e2d0a921998bf243d95ae59cfca82ab22
+oid sha256:c959a6ba121009a188316aa890d943534dd22477e8904387c5ec9e70dbebf827
 size 343365480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4effe260b7f7ae8ab2fb6d12be59703b8263c3ba152d1823163c4360596c87
+oid sha256:24da8bd5bb13554ebf9715f0be1eeb363ad49be1a9401f1cc192f372ad85a4cd
 size 4667