Upload folder using huggingface_hub

checkpoint-5082/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-5082/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7003a0eadf95397a8a50c4d5b6dda140f1fdc970f58be43a66e29e8d0c4a3a2f
+oid sha256:6f1183fcd5f6581f6bf7320ab4846caae2f35c8f5e2863d46a7403ab92d0dec5
 size 343365480

checkpoint-5082/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe8d343ac125f37514248c10fadb2a35768dc748fd7759afb20b2f52ee50d7f
+oid sha256:aa87435227380d8cabc30612501ad49f81b3a3297d23d544642e75be91f98353
 size 686851461

checkpoint-5082/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c228636b751722bbb387a2539db2bd56a9f9ad8744932f1bc0e5c9ff72eed43
+oid sha256:bc5f57f3b9cffbc067d8fdc9b3fb6e8bf7658d30d3d2b61372adea86b63719ba
 size 627

checkpoint-5082/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.5357526540756226,
+  "best_metric": 0.8993604779243469,
   "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": 5.552952289581299,
-      "learning_rate": 8.195151033386328e-07,
-      "loss": 1.5186,
+      "grad_norm": 11.84334945678711,
+      "learning_rate": 6.374006359300477e-07,
+      "loss": 0.8246,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 7.020349025726318,
-      "learning_rate": 7.300874403815579e-07,
-      "loss": 1.5185,
+      "grad_norm": 12.731802940368652,
+      "learning_rate": 5.67845786963434e-07,
+      "loss": 0.8303,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 7.434261798858643,
-      "learning_rate": 6.406597774244833e-07,
-      "loss": 1.5257,
+      "grad_norm": 11.19770622253418,
+      "learning_rate": 4.982909379968204e-07,
+      "loss": 0.8252,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 8.402517318725586,
-      "learning_rate": 5.512321144674086e-07,
-      "loss": 1.5192,
+      "grad_norm": 11.920044898986816,
+      "learning_rate": 4.2873608903020664e-07,
+      "loss": 0.8206,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 9.466378211975098,
-      "learning_rate": 4.618044515103339e-07,
-      "loss": 1.5059,
+      "grad_norm": 12.950881958007812,
+      "learning_rate": 3.59181240063593e-07,
+      "loss": 0.8357,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5991567020962504,
-      "eval_loss": 1.54666006565094,
-      "eval_model_preparation_time": 0.0055,
-      "eval_runtime": 1190.6514,
-      "eval_samples_per_second": 91.029,
-      "eval_steps_per_second": 2.845,
+      "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,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 7.1390910148620605,
-      "learning_rate": 3.7237678855325916e-07,
-      "loss": 1.4908,
+      "grad_norm": 9.331716537475586,
+      "learning_rate": 2.896263910969793e-07,
+      "loss": 0.8225,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 7.025146961212158,
-      "learning_rate": 2.8294912559618444e-07,
-      "loss": 1.5019,
+      "grad_norm": 11.117326736450195,
+      "learning_rate": 2.2007154213036567e-07,
+      "loss": 0.8291,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 7.744629383087158,
-      "learning_rate": 1.935214626391097e-07,
-      "loss": 1.4874,
+      "grad_norm": 12.671438217163086,
+      "learning_rate": 1.5051669316375198e-07,
+      "loss": 0.8123,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 6.708190441131592,
-      "learning_rate": 1.0409379968203497e-07,
-      "loss": 1.4976,
+      "grad_norm": 13.652959823608398,
+      "learning_rate": 8.096184419713831e-08,
+      "loss": 0.8167,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 7.407255172729492,
-      "learning_rate": 1.4666136724960254e-08,
-      "loss": 1.4901,
+      "grad_norm": 8.016142845153809,
+      "learning_rate": 1.1406995230524641e-08,
+      "loss": 0.8132,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6043973280188958,
-      "eval_loss": 1.5357526540756226,
-      "eval_model_preparation_time": 0.0055,
-      "eval_runtime": 1207.654,
-      "eval_samples_per_second": 89.748,
-      "eval_steps_per_second": 2.805,
+      "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,
       "step": 5082
     }
   ],

checkpoint-5082/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb650ebbe869db0c430a96f6034c1af5c3c6c6100ab6c3b193ebc3937790a603
+oid sha256:ed4effe260b7f7ae8ab2fb6d12be59703b8263c3ba152d1823163c4360596c87
 size 4667

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75532c62421984f08e3d09d85f34bf19eab26ac61356b82939424b4e301f2b46
+oid sha256:6f1183fcd5f6581f6bf7320ab4846caae2f35c8f5e2863d46a7403ab92d0dec5
 size 343365480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ccd77f73df11a1333f963ab6437406025cd7af5d1fcfd30d1c335f7e202d63
+oid sha256:ed4effe260b7f7ae8ab2fb6d12be59703b8263c3ba152d1823163c4360596c87
 size 4667