Upload folder using huggingface_hub

checkpoint-7623/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:342fd0d652045819eaa7b50802aa55cd6efea8c969aea62fbb0d9f9dd2627d34
+oid sha256:c4abfa71d9858cae0e97b49251c8e3dd29f38ff87eb8bcb8e21462a0c0b07382
 size 343365480

checkpoint-7623/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db7852739f634f86458593aa2ef21f3d60a69626c2715f02f5f900b8a863074
+oid sha256:f1394e627794640de9f4175eaec400d26690f3f6469e963c89b3aef8e1c9847b
 size 686851461

checkpoint-7623/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.2215194702148438,
+  "best_metric": 1.1867649555206299,
   "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": 13.002593994140625,
+      "grad_norm": 15.461106300354004,
       "learning_rate": 8.465205334741845e-07,
-      "loss": 1.2055,
+      "loss": 1.1454,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 9.049211502075195,
+      "grad_norm": 22.293109893798828,
       "learning_rate": 7.870989040010564e-07,
-      "loss": 1.1934,
+      "loss": 1.1528,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 13.344831466674805,
+      "grad_norm": 8.640257835388184,
       "learning_rate": 7.276772745279281e-07,
-      "loss": 1.179,
+      "loss": 1.1559,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 11.866278648376465,
+      "grad_norm": 11.094526290893555,
       "learning_rate": 6.682556450547999e-07,
-      "loss": 1.1771,
+      "loss": 1.1593,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 8.955316543579102,
+      "grad_norm": 11.131674766540527,
       "learning_rate": 6.088340155816718e-07,
-      "loss": 1.1718,
+      "loss": 1.1221,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6744261145556539,
-      "eval_loss": 1.2367281913757324,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 1198.4464,
-      "eval_samples_per_second": 90.437,
-      "eval_steps_per_second": 2.826,
+      "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,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 8.82983684539795,
+      "grad_norm": 8.923126220703125,
       "learning_rate": 5.494123861085435e-07,
-      "loss": 1.1671,
+      "loss": 1.1413,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 10.22899055480957,
+      "grad_norm": 9.620901107788086,
       "learning_rate": 4.899907566354153e-07,
-      "loss": 1.1673,
+      "loss": 1.12,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 7.556177139282227,
+      "grad_norm": 11.071784019470215,
       "learning_rate": 4.3056912716228705e-07,
-      "loss": 1.182,
+      "loss": 1.1305,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 7.892594814300537,
+      "grad_norm": 9.808845520019531,
       "learning_rate": 3.7114749768915883e-07,
-      "loss": 1.1562,
+      "loss": 1.1187,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 7.493433952331543,
+      "grad_norm": 8.686152458190918,
       "learning_rate": 3.117258682160306e-07,
-      "loss": 1.1524,
+      "loss": 1.1238,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.67734167404783,
-      "eval_loss": 1.2256686687469482,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 1196.6469,
-      "eval_samples_per_second": 90.573,
-      "eval_steps_per_second": 2.83,
+      "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,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 7.134050369262695,
+      "grad_norm": 9.841617584228516,
       "learning_rate": 2.523042387429024e-07,
-      "loss": 1.1482,
+      "loss": 1.1033,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 11.738887786865234,
+      "grad_norm": 10.633978843688965,
       "learning_rate": 1.928826092697742e-07,
-      "loss": 1.1562,
+      "loss": 1.1176,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 8.556049346923828,
+      "grad_norm": 8.568585395812988,
       "learning_rate": 1.3346097979664598e-07,
-      "loss": 1.1478,
+      "loss": 1.1193,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 7.244868755340576,
+      "grad_norm": 10.57896900177002,
       "learning_rate": 7.403935032351777e-08,
-      "loss": 1.1521,
+      "loss": 1.107,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 10.283246040344238,
+      "grad_norm": 9.359890937805176,
       "learning_rate": 1.4617720850389543e-08,
-      "loss": 1.1567,
+      "loss": 1.1133,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6776645999409507,
-      "eval_loss": 1.2215194702148438,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 1204.575,
-      "eval_samples_per_second": 89.977,
-      "eval_steps_per_second": 2.812,
+      "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,
       "step": 7623
     }
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:342fd0d652045819eaa7b50802aa55cd6efea8c969aea62fbb0d9f9dd2627d34
+oid sha256:c4abfa71d9858cae0e97b49251c8e3dd29f38ff87eb8bcb8e21462a0c0b07382
 size 343365480