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": "4.43.3"
+  "transformers_version": "4.43.4"
 }

checkpoint-10164/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3a3b372e31df38748987435df2ea69465e5e4c83db458e0fac6563ddd192b1e
+oid sha256:7a2d129e6ba0d4113eade43c1b58eb17e357e0f6b6a428b367f1cf3b8592b6b5
 size 343365480

checkpoint-10164/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2ca3017d58d7ac3c69a7a111ec51921ac9e6fec103c9fc6f46162f42f15cadb
+oid sha256:d3b6d29967cfae1ea01210432b9b6c3576033934a676b1b24534c0cac46c942a
 size 686851461

checkpoint-10164/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.265008568763733,
+  "best_metric": 1.1233651638031006,
   "best_model_checkpoint": "cat_breed_image_detection/checkpoint-10164",
   "epoch": 4.0,
   "eval_steps": 500,
@@ -10,182 +10,182 @@
   "log_history": [
     {
       "epoch": 0.19677292404565133,
-      "grad_norm": 9.472394943237305,
+      "grad_norm": 11.85600471496582,
       "learning_rate": 8.599564959462131e-07,
-      "loss": 1.2504,
+      "loss": 1.0931,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 13.004825592041016,
+      "grad_norm": 6.796216011047363,
       "learning_rate": 8.154637136642278e-07,
-      "loss": 1.2416,
+      "loss": 1.0952,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 7.997884273529053,
+      "grad_norm": 8.564379692077637,
       "learning_rate": 7.709709313822424e-07,
-      "loss": 1.2367,
+      "loss": 1.0814,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 8.67659854888916,
+      "grad_norm": 11.41899299621582,
       "learning_rate": 7.26478149100257e-07,
-      "loss": 1.2441,
+      "loss": 1.0954,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 10.490302085876465,
+      "grad_norm": 8.380097389221191,
       "learning_rate": 6.819853668182716e-07,
-      "loss": 1.2106,
+      "loss": 1.084,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6619519486271036,
-      "eval_loss": 1.2953426837921143,
+      "eval_accuracy": 0.6954347505166815,
+      "eval_loss": 1.1442592144012451,
       "eval_model_preparation_time": 0.0055,
-      "eval_runtime": 1207.1956,
-      "eval_samples_per_second": 89.782,
-      "eval_steps_per_second": 2.806,
+      "eval_runtime": 1212.3183,
+      "eval_samples_per_second": 89.402,
+      "eval_steps_per_second": 2.794,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 9.106962203979492,
+      "grad_norm": 8.583738327026367,
       "learning_rate": 6.374925845362863e-07,
-      "loss": 1.2229,
+      "loss": 1.0785,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 6.981090068817139,
+      "grad_norm": 6.957513809204102,
       "learning_rate": 5.929998022543009e-07,
-      "loss": 1.2177,
+      "loss": 1.056,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 13.470215797424316,
+      "grad_norm": 10.452813148498535,
       "learning_rate": 5.485070199723155e-07,
-      "loss": 1.1995,
+      "loss": 1.0648,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 8.636761665344238,
+      "grad_norm": 10.482475280761719,
       "learning_rate": 5.040142376903302e-07,
-      "loss": 1.2087,
+      "loss": 1.0748,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 9.918224334716797,
+      "grad_norm": 10.342619895935059,
       "learning_rate": 4.5952145540834485e-07,
-      "loss": 1.2103,
+      "loss": 1.0596,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6657993799822852,
-      "eval_loss": 1.2781411409378052,
+      "eval_accuracy": 0.6959514319456747,
+      "eval_loss": 1.1350406408309937,
       "eval_model_preparation_time": 0.0055,
-      "eval_runtime": 1214.5435,
-      "eval_samples_per_second": 89.238,
-      "eval_steps_per_second": 2.789,
+      "eval_runtime": 1195.5546,
+      "eval_samples_per_second": 90.656,
+      "eval_steps_per_second": 2.833,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 9.103760719299316,
+      "grad_norm": 16.03907012939453,
       "learning_rate": 4.150286731263595e-07,
-      "loss": 1.2016,
+      "loss": 1.0565,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 9.183661460876465,
+      "grad_norm": 10.92419147491455,
       "learning_rate": 3.705358908443741e-07,
-      "loss": 1.1993,
+      "loss": 1.0416,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 7.494422912597656,
+      "grad_norm": 12.578429222106934,
       "learning_rate": 3.2604310856238877e-07,
-      "loss": 1.2033,
+      "loss": 1.053,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 9.207113265991211,
+      "grad_norm": 8.39530086517334,
       "learning_rate": 2.815503262804034e-07,
-      "loss": 1.1868,
+      "loss": 1.0507,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 8.814680099487305,
+      "grad_norm": 10.037232398986816,
       "learning_rate": 2.37057543998418e-07,
-      "loss": 1.1994,
+      "loss": 1.0628,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6672848390906407,
-      "eval_loss": 1.2696255445480347,
+      "eval_accuracy": 0.6984887068201948,
+      "eval_loss": 1.1276220083236694,
       "eval_model_preparation_time": 0.0055,
-      "eval_runtime": 1228.8502,
-      "eval_samples_per_second": 88.2,
-      "eval_steps_per_second": 2.756,
+      "eval_runtime": 1193.5846,
+      "eval_samples_per_second": 90.805,
+      "eval_steps_per_second": 2.838,
       "step": 7623
     },
     {
       "epoch": 3.1483667847304213,
-      "grad_norm": 10.587736129760742,
+      "grad_norm": 12.347983360290527,
       "learning_rate": 1.9256476171643265e-07,
-      "loss": 1.1888,
+      "loss": 1.0436,
       "step": 8000
     },
     {
       "epoch": 3.3451397087760726,
-      "grad_norm": 7.582997798919678,
+      "grad_norm": 12.989178657531738,
       "learning_rate": 1.4807197943444728e-07,
-      "loss": 1.1889,
+      "loss": 1.0538,
       "step": 8500
     },
     {
       "epoch": 3.541912632821724,
-      "grad_norm": 12.2061128616333,
+      "grad_norm": 8.557451248168945,
       "learning_rate": 1.0357919715246192e-07,
-      "loss": 1.1898,
+      "loss": 1.0416,
       "step": 9000
     },
     {
       "epoch": 3.738685556867375,
-      "grad_norm": 8.521767616271973,
+      "grad_norm": 9.772086143493652,
       "learning_rate": 5.9086414870476566e-08,
-      "loss": 1.1845,
+      "loss": 1.0454,
       "step": 9500
     },
     {
       "epoch": 3.9354584809130264,
-      "grad_norm": 11.329971313476562,
+      "grad_norm": 9.701172828674316,
       "learning_rate": 1.4593632588491198e-08,
-      "loss": 1.1925,
+      "loss": 1.044,
       "step": 10000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6685027310304104,
-      "eval_loss": 1.265008568763733,
+      "eval_accuracy": 0.7001217891939769,
+      "eval_loss": 1.1233651638031006,
       "eval_model_preparation_time": 0.0055,
-      "eval_runtime": 1388.927,
-      "eval_samples_per_second": 78.034,
-      "eval_steps_per_second": 2.439,
+      "eval_runtime": 1202.0319,
+      "eval_samples_per_second": 90.167,
+      "eval_steps_per_second": 2.818,
       "step": 10164
     }
   ],

config.json

@@ -120,5 +120,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.43.3"
+  "transformers_version": "4.43.4"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6074319abb8cfbc31e72b4d45ee17ea03f9710df791d1661ee9ba1a74a785027
+oid sha256:7a2d129e6ba0d4113eade43c1b58eb17e357e0f6b6a428b367f1cf3b8592b6b5
 size 343365480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa9f0c7be17c246a85b35b1cacecee4f5b32627bf237df20128bcfe78dfeb2a
+oid sha256:9c6e2b24c2bb418666641ee5942c486949ee0d8efdf7de643fb67fbd8451ce35
 size 4667