Upload folder using huggingface_hub

checkpoint-22855/config.json

@@ -670,5 +670,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.45.1"
 }

checkpoint-22855/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec58008d55914ed465e2a0ed073cca3a4ef11a24b5da8c5b0920b4af9a18a11e
+oid sha256:734a3722f2f927c2f3be7607f94eb3a054f72007ff6a4a7b77ddac2a53bccf18
 size 344211388

checkpoint-22855/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a3a146be5914ad44805d9d83bfdeb36f331768e2c6587bc6ca0c58cbb784eda
+oid sha256:e373d6549f53843cb1805c28c21b91aca667c2cba95d0f6d77c2fed7602a54ec
 size 688543237

checkpoint-22855/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.12474524974823,
+  "best_metric": 0.6283333897590637,
   "best_model_checkpoint": "car_brands_image_detection/checkpoint-22855",
   "epoch": 7.0,
   "eval_steps": 500,
@@ -10,387 +10,387 @@
   "log_history": [
     {
       "epoch": 0.15313935681470137,
-      "grad_norm": 10.977594375610352,
+      "grad_norm": 13.366690635681152,
       "learning_rate": 6.861872396404297e-07,
-      "loss": 1.0769,
+      "loss": 0.5511,
       "step": 500
     },
     {
       "epoch": 0.30627871362940273,
-      "grad_norm": 11.252737998962402,
+      "grad_norm": 11.934271812438965,
       "learning_rate": 6.708397281297961e-07,
-      "loss": 1.0703,
+      "loss": 0.5487,
       "step": 1000
     },
     {
       "epoch": 0.45941807044410415,
-      "grad_norm": 10.567949295043945,
+      "grad_norm": 9.262362480163574,
       "learning_rate": 6.554922166191625e-07,
-      "loss": 1.0579,
+      "loss": 0.5382,
       "step": 1500
     },
     {
       "epoch": 0.6125574272588055,
-      "grad_norm": 11.23414421081543,
+      "grad_norm": 7.17333459854126,
       "learning_rate": 6.401447051085288e-07,
-      "loss": 1.0463,
+      "loss": 0.561,
       "step": 2000
     },
     {
       "epoch": 0.7656967840735069,
-      "grad_norm": 10.645853996276855,
+      "grad_norm": 12.425559043884277,
       "learning_rate": 6.247971935978952e-07,
-      "loss": 1.0569,
+      "loss": 0.5503,
       "step": 2500
     },
     {
       "epoch": 0.9188361408882083,
-      "grad_norm": 10.294245719909668,
+      "grad_norm": 8.107797622680664,
       "learning_rate": 6.094496820872616e-07,
-      "loss": 1.0543,
+      "loss": 0.5443,
       "step": 3000
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8411953072272721,
-      "eval_loss": 1.2030651569366455,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 687.2885,
-      "eval_samples_per_second": 101.324,
-      "eval_steps_per_second": 12.666,
+      "eval_accuracy": 0.9070922902396645,
+      "eval_loss": 0.6742454767227173,
+      "eval_model_preparation_time": 0.006,
+      "eval_runtime": 684.1135,
+      "eval_samples_per_second": 101.795,
+      "eval_steps_per_second": 12.724,
       "step": 3265
     },
     {
       "epoch": 1.0719754977029097,
-      "grad_norm": 9.816156387329102,
+      "grad_norm": 7.829226493835449,
       "learning_rate": 5.941021705766278e-07,
-      "loss": 1.0425,
+      "loss": 0.534,
       "step": 3500
     },
     {
       "epoch": 1.225114854517611,
-      "grad_norm": 7.021167755126953,
+      "grad_norm": 10.400870323181152,
       "learning_rate": 5.787546590659943e-07,
-      "loss": 1.0385,
+      "loss": 0.5356,
       "step": 4000
     },
     {
       "epoch": 1.3782542113323124,
-      "grad_norm": 14.457579612731934,
+      "grad_norm": 8.150808334350586,
       "learning_rate": 5.634071475553606e-07,
-      "loss": 1.0268,
+      "loss": 0.5218,
       "step": 4500
     },
     {
       "epoch": 1.5313935681470139,
-      "grad_norm": 11.13620376586914,
+      "grad_norm": 15.422158241271973,
       "learning_rate": 5.480596360447269e-07,
-      "loss": 1.0197,
+      "loss": 0.5339,
       "step": 5000
     },
     {
       "epoch": 1.6845329249617151,
-      "grad_norm": 10.852294921875,
+      "grad_norm": 10.069522857666016,
       "learning_rate": 5.327121245340934e-07,
-      "loss": 1.0335,
+      "loss": 0.5384,
       "step": 5500
     },
     {
       "epoch": 1.8376722817764164,
-      "grad_norm": 11.98221492767334,
+      "grad_norm": 8.527743339538574,
       "learning_rate": 5.173646130234597e-07,
-      "loss": 1.0241,
+      "loss": 0.5286,
       "step": 6000
     },
     {
       "epoch": 1.9908116385911179,
-      "grad_norm": 10.328956604003906,
+      "grad_norm": 13.6627836227417,
       "learning_rate": 5.020171015128262e-07,
-      "loss": 1.0143,
+      "loss": 0.5228,
       "step": 6500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8442108588578239,
-      "eval_loss": 1.1817330121994019,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 667.4646,
-      "eval_samples_per_second": 104.334,
-      "eval_steps_per_second": 13.042,
+      "eval_accuracy": 0.90901649937535,
+      "eval_loss": 0.6600815057754517,
+      "eval_model_preparation_time": 0.006,
+      "eval_runtime": 684.6003,
+      "eval_samples_per_second": 101.722,
+      "eval_steps_per_second": 12.715,
       "step": 6530
     },
     {
       "epoch": 2.1439509954058193,
-      "grad_norm": 8.650470733642578,
+      "grad_norm": 10.269744873046875,
       "learning_rate": 4.866695900021925e-07,
-      "loss": 1.0117,
+      "loss": 0.5175,
       "step": 7000
     },
     {
       "epoch": 2.2970903522205206,
-      "grad_norm": 10.077228546142578,
+      "grad_norm": 10.207755088806152,
       "learning_rate": 4.713220784915589e-07,
-      "loss": 0.9998,
+      "loss": 0.5207,
       "step": 7500
     },
     {
       "epoch": 2.450229709035222,
-      "grad_norm": 12.940803527832031,
+      "grad_norm": 9.40577507019043,
       "learning_rate": 4.559745669809252e-07,
-      "loss": 1.0062,
+      "loss": 0.5108,
       "step": 8000
     },
     {
       "epoch": 2.6033690658499236,
-      "grad_norm": 13.832907676696777,
+      "grad_norm": 14.63872241973877,
       "learning_rate": 4.406270554702916e-07,
-      "loss": 1.0014,
+      "loss": 0.5157,
       "step": 8500
     },
     {
       "epoch": 2.756508422664625,
-      "grad_norm": 9.304670333862305,
+      "grad_norm": 10.473233222961426,
       "learning_rate": 4.25279543959658e-07,
-      "loss": 0.9983,
+      "loss": 0.5082,
       "step": 9000
     },
     {
       "epoch": 2.909647779479326,
-      "grad_norm": 12.306177139282227,
+      "grad_norm": 9.536513328552246,
       "learning_rate": 4.0993203244902437e-07,
-      "loss": 0.993,
+      "loss": 0.5089,
       "step": 9500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8465802208532575,
-      "eval_loss": 1.1596074104309082,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 677.1878,
-      "eval_samples_per_second": 102.836,
-      "eval_steps_per_second": 12.855,
+      "eval_accuracy": 0.9105817142693031,
+      "eval_loss": 0.6478191614151001,
+      "eval_model_preparation_time": 0.006,
+      "eval_runtime": 690.9545,
+      "eval_samples_per_second": 100.787,
+      "eval_steps_per_second": 12.599,
       "step": 9795
     },
     {
       "epoch": 3.0627871362940278,
-      "grad_norm": 9.197342872619629,
+      "grad_norm": 8.641783714294434,
       "learning_rate": 3.9458452093839065e-07,
-      "loss": 0.994,
+      "loss": 0.5092,
       "step": 10000
     },
     {
       "epoch": 3.215926493108729,
-      "grad_norm": 10.245026588439941,
+      "grad_norm": 19.282365798950195,
       "learning_rate": 3.7923700942775704e-07,
-      "loss": 0.9887,
+      "loss": 0.5005,
       "step": 10500
     },
     {
       "epoch": 3.3690658499234303,
-      "grad_norm": 8.360330581665039,
+      "grad_norm": 11.717490196228027,
       "learning_rate": 3.638894979171234e-07,
-      "loss": 0.9795,
+      "loss": 0.502,
       "step": 11000
     },
     {
       "epoch": 3.522205206738132,
-      "grad_norm": 11.287829399108887,
+      "grad_norm": 5.86570405960083,
       "learning_rate": 3.4854198640648976e-07,
-      "loss": 1.0054,
+      "loss": 0.4932,
       "step": 11500
     },
     {
       "epoch": 3.6753445635528332,
-      "grad_norm": 9.926981925964355,
+      "grad_norm": 19.602014541625977,
       "learning_rate": 3.3319447489585615e-07,
-      "loss": 0.9681,
+      "loss": 0.5014,
       "step": 12000
     },
     {
       "epoch": 3.8284839203675345,
-      "grad_norm": 12.259571075439453,
+      "grad_norm": 8.634654998779297,
       "learning_rate": 3.1784696338522254e-07,
-      "loss": 0.978,
+      "loss": 0.5099,
       "step": 12500
     },
     {
       "epoch": 3.9816232771822357,
-      "grad_norm": 18.110218048095703,
+      "grad_norm": 10.192227363586426,
       "learning_rate": 3.0249945187458887e-07,
-      "loss": 0.9582,
+      "loss": 0.5002,
       "step": 13000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.848748546073321,
-      "eval_loss": 1.1430388689041138,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 678.3623,
-      "eval_samples_per_second": 102.658,
-      "eval_steps_per_second": 12.832,
+      "eval_accuracy": 0.9107540315053346,
+      "eval_loss": 0.6401029229164124,
+      "eval_model_preparation_time": 0.006,
+      "eval_runtime": 702.914,
+      "eval_samples_per_second": 99.072,
+      "eval_steps_per_second": 12.384,
       "step": 13060
     },
     {
       "epoch": 4.134762633996937,
-      "grad_norm": 7.420970439910889,
+      "grad_norm": 10.418832778930664,
       "learning_rate": 2.8715194036395526e-07,
-      "loss": 0.9722,
+      "loss": 0.4992,
       "step": 13500
     },
     {
       "epoch": 4.287901990811639,
-      "grad_norm": 10.573201179504395,
+      "grad_norm": 12.171610832214355,
       "learning_rate": 2.7180442885332164e-07,
-      "loss": 0.9552,
+      "loss": 0.483,
       "step": 14000
     },
     {
       "epoch": 4.44104134762634,
-      "grad_norm": 11.360106468200684,
+      "grad_norm": 18.0849552154541,
       "learning_rate": 2.56456917342688e-07,
-      "loss": 0.9677,
+      "loss": 0.4865,
       "step": 14500
     },
     {
       "epoch": 4.594180704441041,
-      "grad_norm": 10.936739921569824,
+      "grad_norm": 9.136711120605469,
       "learning_rate": 2.4110940583205437e-07,
-      "loss": 0.9619,
+      "loss": 0.4893,
       "step": 15000
     },
     {
       "epoch": 4.747320061255743,
-      "grad_norm": 11.35300350189209,
+      "grad_norm": 7.19853401184082,
       "learning_rate": 2.2576189432142073e-07,
-      "loss": 0.9664,
+      "loss": 0.4956,
       "step": 15500
     },
     {
       "epoch": 4.900459418070444,
-      "grad_norm": 9.238828659057617,
+      "grad_norm": 9.32518196105957,
       "learning_rate": 2.104143828107871e-07,
-      "loss": 0.9697,
+      "loss": 0.4858,
       "step": 16000
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.8492654977814156,
-      "eval_loss": 1.1333091259002686,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 668.0112,
-      "eval_samples_per_second": 104.248,
-      "eval_steps_per_second": 13.031,
+      "eval_accuracy": 0.9118022946911931,
+      "eval_loss": 0.6333341598510742,
+      "eval_model_preparation_time": 0.006,
+      "eval_runtime": 694.3482,
+      "eval_samples_per_second": 100.294,
+      "eval_steps_per_second": 12.537,
       "step": 16325
     },
     {
       "epoch": 5.053598774885145,
-      "grad_norm": 9.134923934936523,
+      "grad_norm": 6.03609561920166,
       "learning_rate": 1.9506687130015347e-07,
-      "loss": 0.9528,
+      "loss": 0.4907,
       "step": 16500
     },
     {
       "epoch": 5.206738131699847,
-      "grad_norm": 8.237107276916504,
+      "grad_norm": 8.596969604492188,
       "learning_rate": 1.7971935978951984e-07,
-      "loss": 0.9611,
+      "loss": 0.4829,
       "step": 17000
     },
     {
       "epoch": 5.359877488514548,
-      "grad_norm": 9.242733001708984,
+      "grad_norm": 17.825912475585938,
       "learning_rate": 1.643718482788862e-07,
-      "loss": 0.961,
+      "loss": 0.4831,
       "step": 17500
     },
     {
       "epoch": 5.51301684532925,
-      "grad_norm": 10.467522621154785,
+      "grad_norm": 6.781469821929932,
       "learning_rate": 1.4902433676825258e-07,
-      "loss": 0.9469,
+      "loss": 0.4901,
       "step": 18000
     },
     {
       "epoch": 5.666156202143951,
-      "grad_norm": 13.296605110168457,
+      "grad_norm": 7.068932056427002,
       "learning_rate": 1.3367682525761894e-07,
-      "loss": 0.9538,
+      "loss": 0.4923,
       "step": 18500
     },
     {
       "epoch": 5.819295558958652,
-      "grad_norm": 8.11686897277832,
+      "grad_norm": 13.472633361816406,
       "learning_rate": 1.183293137469853e-07,
-      "loss": 0.9486,
+      "loss": 0.4845,
       "step": 19000
     },
     {
       "epoch": 5.972434915773354,
-      "grad_norm": 8.29335880279541,
+      "grad_norm": 9.40524673461914,
       "learning_rate": 1.0298180223635168e-07,
-      "loss": 0.9666,
+      "loss": 0.4672,
       "step": 19500
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.8497680897198409,
-      "eval_loss": 1.1270993947982788,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 668.7633,
-      "eval_samples_per_second": 104.131,
-      "eval_steps_per_second": 13.017,
+      "eval_accuracy": 0.9119315326182168,
+      "eval_loss": 0.6297235488891602,
+      "eval_model_preparation_time": 0.006,
+      "eval_runtime": 697.8503,
+      "eval_samples_per_second": 99.791,
+      "eval_steps_per_second": 12.474,
       "step": 19590
     },
     {
       "epoch": 6.1255742725880555,
-      "grad_norm": 14.328752517700195,
+      "grad_norm": 8.320501327514648,
       "learning_rate": 8.763429072571804e-08,
-      "loss": 0.9437,
+      "loss": 0.4753,
       "step": 20000
     },
     {
       "epoch": 6.278713629402756,
-      "grad_norm": 12.567534446716309,
+      "grad_norm": 10.223684310913086,
       "learning_rate": 7.228677921508441e-08,
-      "loss": 0.9583,
+      "loss": 0.4746,
       "step": 20500
     },
     {
       "epoch": 6.431852986217458,
-      "grad_norm": 10.546801567077637,
+      "grad_norm": 12.393083572387695,
       "learning_rate": 5.693926770445078e-08,
-      "loss": 0.9436,
+      "loss": 0.4822,
       "step": 21000
     },
     {
       "epoch": 6.584992343032159,
-      "grad_norm": 9.688272476196289,
+      "grad_norm": 14.066522598266602,
       "learning_rate": 4.159175619381715e-08,
-      "loss": 0.9496,
+      "loss": 0.4865,
       "step": 21500
     },
     {
       "epoch": 6.738131699846861,
-      "grad_norm": 10.878347396850586,
+      "grad_norm": 8.407339096069336,
       "learning_rate": 2.6244244683183514e-08,
-      "loss": 0.9516,
+      "loss": 0.4758,
       "step": 22000
     },
     {
       "epoch": 6.891271056661562,
-      "grad_norm": 9.418506622314453,
+      "grad_norm": 10.466651916503906,
       "learning_rate": 1.0896733172549878e-08,
-      "loss": 0.9518,
+      "loss": 0.4861,
       "step": 22500
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.8505722368213214,
-      "eval_loss": 1.12474524974823,
-      "eval_model_preparation_time": 0.0053,
-      "eval_runtime": 668.4785,
-      "eval_samples_per_second": 104.175,
-      "eval_steps_per_second": 13.022,
+      "eval_accuracy": 0.9121325693935869,
+      "eval_loss": 0.6283333897590637,
+      "eval_model_preparation_time": 0.006,
+      "eval_runtime": 695.1527,
+      "eval_samples_per_second": 100.178,
+      "eval_steps_per_second": 12.522,
       "step": 22855
     }
   ],

checkpoint-22855/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c100526e0b4b24bfa7592465d2fb171f2d02c219dd18fbd5f4fdb665859dc45c
-size 4667
+oid sha256:383bdd66dedd2d02f4607e2845640bf60017805b0ddd9c46c51a7a69f93f2ee7
+size 4731

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe1b038fb0f521f664649f712800fbfe7fa261ad4ca3e25ba1e41967005a47c
+oid sha256:734a3722f2f927c2f3be7607f94eb3a054f72007ff6a4a7b77ddac2a53bccf18
 size 344211388

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c5e5c5924d5e574908eb65d0a1490c65c3fa3d146ca5a04ac236d9a8b5ab276
+oid sha256:383bdd66dedd2d02f4607e2845640bf60017805b0ddd9c46c51a7a69f93f2ee7
 size 4731