Upload folder using huggingface_hub

checkpoint-10164/config.json

@@ -120,5 +120,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.42.4"
+  "transformers_version": "4.43.3"
 }

checkpoint-10164/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0df2157bb08488aa22ecdae7586ea53776b24c55d50814bb23e8501642c21d9
+oid sha256:f3a3b372e31df38748987435df2ea69465e5e4c83db458e0fac6563ddd192b1e
 size 343365480

checkpoint-10164/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba4909a0590746ef607d7f9766d9278c841123132ced95fa2d0a5ce64601e496
+oid sha256:a2ca3017d58d7ac3c69a7a111ec51921ac9e6fec103c9fc6f46162f42f15cadb
 size 686851461

checkpoint-10164/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.572628378868103,
+  "best_metric": 1.265008568763733,
   "best_model_checkpoint": "cat_breed_image_detection/checkpoint-10164",
   "epoch": 4.0,
   "eval_steps": 500,
@@ -10,178 +10,182 @@
   "log_history": [
     {
       "epoch": 0.19677292404565133,
-      "grad_norm": 8.132095336914062,
+      "grad_norm": 9.472394943237305,
       "learning_rate": 8.599564959462131e-07,
-      "loss": 1.6107,
+      "loss": 1.2504,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 6.708084583282471,
+      "grad_norm": 13.004825592041016,
       "learning_rate": 8.154637136642278e-07,
-      "loss": 1.5888,
+      "loss": 1.2416,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 7.669999122619629,
+      "grad_norm": 7.997884273529053,
       "learning_rate": 7.709709313822424e-07,
-      "loss": 1.5734,
+      "loss": 1.2367,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 8.473257064819336,
+      "grad_norm": 8.67659854888916,
       "learning_rate": 7.26478149100257e-07,
-      "loss": 1.5921,
+      "loss": 1.2441,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 7.519883155822754,
+      "grad_norm": 10.490302085876465,
       "learning_rate": 6.819853668182716e-07,
-      "loss": 1.5814,
+      "loss": 1.2106,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.583766976675524,
-      "eval_loss": 1.6136096715927124,
-      "eval_runtime": 1206.4218,
-      "eval_samples_per_second": 89.839,
-      "eval_steps_per_second": 2.807,
+      "eval_accuracy": 0.6619519486271036,
+      "eval_loss": 1.2953426837921143,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 1207.1956,
+      "eval_samples_per_second": 89.782,
+      "eval_steps_per_second": 2.806,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 6.776809215545654,
+      "grad_norm": 9.106962203979492,
       "learning_rate": 6.374925845362863e-07,
-      "loss": 1.5698,
+      "loss": 1.2229,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 5.961708068847656,
+      "grad_norm": 6.981090068817139,
       "learning_rate": 5.929998022543009e-07,
-      "loss": 1.5564,
+      "loss": 1.2177,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 7.470553398132324,
+      "grad_norm": 13.470215797424316,
       "learning_rate": 5.485070199723155e-07,
-      "loss": 1.5616,
+      "loss": 1.1995,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 6.852038383483887,
+      "grad_norm": 8.636761665344238,
       "learning_rate": 5.040142376903302e-07,
-      "loss": 1.5534,
+      "loss": 1.2087,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 8.469923973083496,
+      "grad_norm": 9.918224334716797,
       "learning_rate": 4.5952145540834485e-07,
-      "loss": 1.5467,
+      "loss": 1.2103,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5894412459403602,
-      "eval_loss": 1.5893911123275757,
-      "eval_runtime": 1210.5447,
-      "eval_samples_per_second": 89.533,
-      "eval_steps_per_second": 2.798,
+      "eval_accuracy": 0.6657993799822852,
+      "eval_loss": 1.2781411409378052,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 1214.5435,
+      "eval_samples_per_second": 89.238,
+      "eval_steps_per_second": 2.789,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 6.9930195808410645,
+      "grad_norm": 9.103760719299316,
       "learning_rate": 4.150286731263595e-07,
-      "loss": 1.5455,
+      "loss": 1.2016,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 8.173332214355469,
+      "grad_norm": 9.183661460876465,
       "learning_rate": 3.705358908443741e-07,
-      "loss": 1.5393,
+      "loss": 1.1993,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 5.5481767654418945,
+      "grad_norm": 7.494422912597656,
       "learning_rate": 3.2604310856238877e-07,
-      "loss": 1.5412,
+      "loss": 1.2033,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 6.221193313598633,
+      "grad_norm": 9.207113265991211,
       "learning_rate": 2.815503262804034e-07,
-      "loss": 1.531,
+      "loss": 1.1868,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 6.431015968322754,
+      "grad_norm": 8.814680099487305,
       "learning_rate": 2.37057543998418e-07,
-      "loss": 1.5297,
+      "loss": 1.1994,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5934916592855034,
-      "eval_loss": 1.5773507356643677,
-      "eval_runtime": 1196.383,
-      "eval_samples_per_second": 90.593,
-      "eval_steps_per_second": 2.831,
+      "eval_accuracy": 0.6672848390906407,
+      "eval_loss": 1.2696255445480347,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 1228.8502,
+      "eval_samples_per_second": 88.2,
+      "eval_steps_per_second": 2.756,
       "step": 7623
     },
     {
       "epoch": 3.1483667847304213,
-      "grad_norm": 10.443075180053711,
+      "grad_norm": 10.587736129760742,
       "learning_rate": 1.9256476171643265e-07,
-      "loss": 1.5376,
+      "loss": 1.1888,
       "step": 8000
     },
     {
       "epoch": 3.3451397087760726,
-      "grad_norm": 6.658329010009766,
+      "grad_norm": 7.582997798919678,
       "learning_rate": 1.4807197943444728e-07,
-      "loss": 1.5207,
+      "loss": 1.1889,
       "step": 8500
     },
     {
       "epoch": 3.541912632821724,
-      "grad_norm": 6.124561786651611,
+      "grad_norm": 12.2061128616333,
       "learning_rate": 1.0357919715246192e-07,
-      "loss": 1.5225,
+      "loss": 1.1898,
       "step": 9000
     },
     {
       "epoch": 3.738685556867375,
-      "grad_norm": 7.456569194793701,
+      "grad_norm": 8.521767616271973,
       "learning_rate": 5.9086414870476566e-08,
-      "loss": 1.5198,
+      "loss": 1.1845,
       "step": 9500
     },
     {
       "epoch": 3.9354584809130264,
-      "grad_norm": 6.399494647979736,
+      "grad_norm": 11.329971313476562,
       "learning_rate": 1.4593632588491198e-08,
-      "loss": 1.5279,
+      "loss": 1.1925,
       "step": 10000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5949955713020372,
-      "eval_loss": 1.572628378868103,
-      "eval_runtime": 1198.3774,
-      "eval_samples_per_second": 90.442,
-      "eval_steps_per_second": 2.826,
+      "eval_accuracy": 0.6685027310304104,
+      "eval_loss": 1.265008568763733,
+      "eval_model_preparation_time": 0.0055,
+      "eval_runtime": 1388.927,
+      "eval_samples_per_second": 78.034,
+      "eval_steps_per_second": 2.439,
       "step": 10164
     }
   ],

checkpoint-10164/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7038f06b241e4c336bbada2433c50f59bc04ec8c51993fbe3e8837885274dc54
-size 4603
+oid sha256:9c6e2b24c2bb418666641ee5942c486949ee0d8efdf7de643fb67fbd8451ce35
+size 4667

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62dfc8be86043484d9eaf20856f78629ee851e733dba965646beada2aa0a8e49
+oid sha256:f3a3b372e31df38748987435df2ea69465e5e4c83db458e0fac6563ddd192b1e
 size 343365480

training_args.bin

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