Upload folder using huggingface_hub

checkpoint-7623/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62dfc8be86043484d9eaf20856f78629ee851e733dba965646beada2aa0a8e49
+oid sha256:342fd0d652045819eaa7b50802aa55cd6efea8c969aea62fbb0d9f9dd2627d34
 size 343365480

checkpoint-7623/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb453adcd761222b4113170fb483b5b9b6837b2124004e76b7761389266edcb
+oid sha256:9db7852739f634f86458593aa2ef21f3d60a69626c2715f02f5f900b8a863074
 size 686851461

checkpoint-7623/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.3125017881393433,
+  "best_metric": 1.2215194702148438,
   "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": 7.071441173553467,
+      "grad_norm": 13.002593994140625,
       "learning_rate": 8.465205334741845e-07,
-      "loss": 1.2994,
+      "loss": 1.2055,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 9.168732643127441,
+      "grad_norm": 9.049211502075195,
       "learning_rate": 7.870989040010564e-07,
-      "loss": 1.3024,
+      "loss": 1.1934,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 8.262181282043457,
+      "grad_norm": 13.344831466674805,
       "learning_rate": 7.276772745279281e-07,
-      "loss": 1.2652,
+      "loss": 1.179,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 10.966161727905273,
+      "grad_norm": 11.866278648376465,
       "learning_rate": 6.682556450547999e-07,
-      "loss": 1.2789,
+      "loss": 1.1771,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 8.47767448425293,
+      "grad_norm": 8.955316543579102,
       "learning_rate": 6.088340155816718e-07,
-      "loss": 1.269,
+      "loss": 1.1718,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "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,
+      "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,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 14.689343452453613,
+      "grad_norm": 8.82983684539795,
       "learning_rate": 5.494123861085435e-07,
-      "loss": 1.2627,
+      "loss": 1.1671,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 7.966395854949951,
+      "grad_norm": 10.22899055480957,
       "learning_rate": 4.899907566354153e-07,
-      "loss": 1.2615,
+      "loss": 1.1673,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 6.865269184112549,
+      "grad_norm": 7.556177139282227,
       "learning_rate": 4.3056912716228705e-07,
-      "loss": 1.2636,
+      "loss": 1.182,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 9.544075012207031,
+      "grad_norm": 7.892594814300537,
       "learning_rate": 3.7114749768915883e-07,
-      "loss": 1.2484,
+      "loss": 1.1562,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 12.453811645507812,
+      "grad_norm": 7.493433952331543,
       "learning_rate": 3.117258682160306e-07,
-      "loss": 1.264,
+      "loss": 1.1524,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "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,
+      "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,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 9.422158241271973,
+      "grad_norm": 7.134050369262695,
       "learning_rate": 2.523042387429024e-07,
-      "loss": 1.2342,
+      "loss": 1.1482,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 8.495936393737793,
+      "grad_norm": 11.738887786865234,
       "learning_rate": 1.928826092697742e-07,
-      "loss": 1.2448,
+      "loss": 1.1562,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 8.68142318725586,
+      "grad_norm": 8.556049346923828,
       "learning_rate": 1.3346097979664598e-07,
-      "loss": 1.2507,
+      "loss": 1.1478,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 11.802330017089844,
+      "grad_norm": 7.244868755340576,
       "learning_rate": 7.403935032351777e-08,
-      "loss": 1.2448,
+      "loss": 1.1521,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 8.9815673828125,
+      "grad_norm": 10.283246040344238,
       "learning_rate": 1.4617720850389543e-08,
-      "loss": 1.2538,
+      "loss": 1.1567,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "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,
+      "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,
       "step": 7623
     }
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a3b372e31df38748987435df2ea69465e5e4c83db458e0fac6563ddd192b1e
+oid sha256:342fd0d652045819eaa7b50802aa55cd6efea8c969aea62fbb0d9f9dd2627d34
 size 343365480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6e2b24c2bb418666641ee5942c486949ee0d8efdf7de643fb67fbd8451ce35
+oid sha256:2ddce706ee826114a81e5dc98c1b4a675a40b3cf07bb0062afea81a5ff747285
 size 4667