Upload folder using huggingface_hub

checkpoint-5082/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1183fcd5f6581f6bf7320ab4846caae2f35c8f5e2863d46a7403ab92d0dec5
+oid sha256:6f5f76ed594c5458daad41141b36146e2d0a921998bf243d95ae59cfca82ab22
 size 343365480

checkpoint-5082/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa87435227380d8cabc30612501ad49f81b3a3297d23d544642e75be91f98353
+oid sha256:240b4a53496dcb9cdb597454f1147f1081748e8d70ea3d819ce5920c21e2b3e7
 size 686851461

checkpoint-5082/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8993604779243469,
+  "best_metric": 0.8857481479644775,
   "best_model_checkpoint": "cat_breed_image_detection/checkpoint-5082",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,92 +10,92 @@
   "log_history": [
     {
       "epoch": 0.19677292404565133,
-      "grad_norm": 11.84334945678711,
+      "grad_norm": 8.470013618469238,
       "learning_rate": 6.374006359300477e-07,
-      "loss": 0.8246,
+      "loss": 0.8262,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 12.731802940368652,
+      "grad_norm": 10.178301811218262,
       "learning_rate": 5.67845786963434e-07,
-      "loss": 0.8303,
+      "loss": 0.8147,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 11.19770622253418,
+      "grad_norm": 8.706421852111816,
       "learning_rate": 4.982909379968204e-07,
-      "loss": 0.8252,
+      "loss": 0.8178,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 11.920044898986816,
+      "grad_norm": 11.302477836608887,
       "learning_rate": 4.2873608903020664e-07,
-      "loss": 0.8206,
+      "loss": 0.8268,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 12.950881958007812,
+      "grad_norm": 7.3357696533203125,
       "learning_rate": 3.59181240063593e-07,
-      "loss": 0.8357,
+      "loss": 0.8107,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7481362562739888,
-      "eval_loss": 0.9043898582458496,
-      "eval_model_preparation_time": 0.0052,
-      "eval_runtime": 1185.4506,
-      "eval_samples_per_second": 91.429,
-      "eval_steps_per_second": 2.857,
+      "eval_accuracy": 0.750784248597579,
+      "eval_loss": 0.8888508677482605,
+      "eval_model_preparation_time": 0.0072,
+      "eval_runtime": 1235.6701,
+      "eval_samples_per_second": 87.713,
+      "eval_steps_per_second": 2.741,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 9.331716537475586,
+      "grad_norm": 8.730005264282227,
       "learning_rate": 2.896263910969793e-07,
-      "loss": 0.8225,
+      "loss": 0.8139,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 11.117326736450195,
+      "grad_norm": 10.811681747436523,
       "learning_rate": 2.2007154213036567e-07,
-      "loss": 0.8291,
+      "loss": 0.8152,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 12.671438217163086,
+      "grad_norm": 11.135604858398438,
       "learning_rate": 1.5051669316375198e-07,
-      "loss": 0.8123,
+      "loss": 0.8004,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 13.652959823608398,
+      "grad_norm": 17.724515914916992,
       "learning_rate": 8.096184419713831e-08,
-      "loss": 0.8167,
+      "loss": 0.802,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 8.016142845153809,
+      "grad_norm": 16.812559127807617,
       "learning_rate": 1.1406995230524641e-08,
-      "loss": 0.8132,
+      "loss": 0.8072,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7489112784174786,
-      "eval_loss": 0.8993604779243469,
-      "eval_model_preparation_time": 0.0052,
-      "eval_runtime": 1195.3632,
-      "eval_samples_per_second": 90.67,
-      "eval_steps_per_second": 2.833,
+      "eval_accuracy": 0.7516330823737821,
+      "eval_loss": 0.8857481479644775,
+      "eval_model_preparation_time": 0.0072,
+      "eval_runtime": 1238.8905,
+      "eval_samples_per_second": 87.485,
+      "eval_steps_per_second": 2.734,
       "step": 5082
     }
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1183fcd5f6581f6bf7320ab4846caae2f35c8f5e2863d46a7403ab92d0dec5
+oid sha256:6f5f76ed594c5458daad41141b36146e2d0a921998bf243d95ae59cfca82ab22
 size 343365480