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": "4.43.4"
+  "transformers_version": "4.44.0"
 }

checkpoint-10164/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2d129e6ba0d4113eade43c1b58eb17e357e0f6b6a428b367f1cf3b8592b6b5
+oid sha256:75a00859aea079c75799c0858b733d733508af5552a18430897062c592a2583a
 size 343365480

checkpoint-10164/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3b6d29967cfae1ea01210432b9b6c3576033934a676b1b24534c0cac46c942a
+oid sha256:2602958179df170d16c212f1771da5e650b0b7e8bbd5cd6dd5b991fffec42de0
 size 686851461

checkpoint-10164/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.1233651638031006,
+  "best_metric": 1.084580659866333,
   "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": 11.85600471496582,
+      "grad_norm": 8.859833717346191,
       "learning_rate": 8.599564959462131e-07,
-      "loss": 1.0931,
+      "loss": 1.0519,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 6.796216011047363,
+      "grad_norm": 10.870162010192871,
       "learning_rate": 8.154637136642278e-07,
-      "loss": 1.0952,
+      "loss": 1.0529,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 8.564379692077637,
+      "grad_norm": 11.251194953918457,
       "learning_rate": 7.709709313822424e-07,
-      "loss": 1.0814,
+      "loss": 1.0397,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 11.41899299621582,
+      "grad_norm": 12.0984468460083,
       "learning_rate": 7.26478149100257e-07,
-      "loss": 1.0954,
+      "loss": 1.0515,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 8.380097389221191,
+      "grad_norm": 7.28156042098999,
       "learning_rate": 6.819853668182716e-07,
-      "loss": 1.084,
+      "loss": 1.0337,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6954347505166815,
-      "eval_loss": 1.1442592144012451,
-      "eval_model_preparation_time": 0.0055,
-      "eval_runtime": 1212.3183,
-      "eval_samples_per_second": 89.402,
-      "eval_steps_per_second": 2.794,
+      "eval_accuracy": 0.7004354886330085,
+      "eval_loss": 1.1068506240844727,
+      "eval_model_preparation_time": 0.0054,
+      "eval_runtime": 1190.7929,
+      "eval_samples_per_second": 91.018,
+      "eval_steps_per_second": 2.844,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 8.583738327026367,
+      "grad_norm": 8.778160095214844,
       "learning_rate": 6.374925845362863e-07,
-      "loss": 1.0785,
+      "loss": 1.0223,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 6.957513809204102,
+      "grad_norm": 8.823763847351074,
       "learning_rate": 5.929998022543009e-07,
-      "loss": 1.056,
+      "loss": 1.0247,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 10.452813148498535,
+      "grad_norm": 9.15168285369873,
       "learning_rate": 5.485070199723155e-07,
-      "loss": 1.0648,
+      "loss": 1.024,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 10.482475280761719,
+      "grad_norm": 10.23277473449707,
       "learning_rate": 5.040142376903302e-07,
-      "loss": 1.0748,
+      "loss": 1.0362,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 10.342619895935059,
+      "grad_norm": 8.250983238220215,
       "learning_rate": 4.5952145540834485e-07,
-      "loss": 1.0596,
+      "loss": 1.0253,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6959514319456747,
-      "eval_loss": 1.1350406408309937,
-      "eval_model_preparation_time": 0.0055,
-      "eval_runtime": 1195.5546,
-      "eval_samples_per_second": 90.656,
-      "eval_steps_per_second": 2.833,
+      "eval_accuracy": 0.7026590640684972,
+      "eval_loss": 1.09512197971344,
+      "eval_model_preparation_time": 0.0054,
+      "eval_runtime": 1206.999,
+      "eval_samples_per_second": 89.796,
+      "eval_steps_per_second": 2.806,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 16.03907012939453,
+      "grad_norm": 11.255722045898438,
       "learning_rate": 4.150286731263595e-07,
-      "loss": 1.0565,
+      "loss": 1.0128,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 10.92419147491455,
+      "grad_norm": 11.691879272460938,
       "learning_rate": 3.705358908443741e-07,
-      "loss": 1.0416,
+      "loss": 1.0168,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 12.578429222106934,
+      "grad_norm": 10.441214561462402,
       "learning_rate": 3.2604310856238877e-07,
-      "loss": 1.053,
+      "loss": 1.0093,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 8.39530086517334,
+      "grad_norm": 7.868481159210205,
       "learning_rate": 2.815503262804034e-07,
-      "loss": 1.0507,
+      "loss": 1.0133,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 10.037232398986816,
+      "grad_norm": 10.433448791503906,
       "learning_rate": 2.37057543998418e-07,
-      "loss": 1.0628,
+      "loss": 1.0152,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6984887068201948,
-      "eval_loss": 1.1276220083236694,
-      "eval_model_preparation_time": 0.0055,
-      "eval_runtime": 1193.5846,
-      "eval_samples_per_second": 90.805,
-      "eval_steps_per_second": 2.838,
+      "eval_accuracy": 0.7059898139946855,
+      "eval_loss": 1.0874797105789185,
+      "eval_model_preparation_time": 0.0054,
+      "eval_runtime": 1227.8405,
+      "eval_samples_per_second": 88.272,
+      "eval_steps_per_second": 2.759,
       "step": 7623
     },
     {
       "epoch": 3.1483667847304213,
-      "grad_norm": 12.347983360290527,
+      "grad_norm": 8.449857711791992,
       "learning_rate": 1.9256476171643265e-07,
-      "loss": 1.0436,
+      "loss": 1.0039,
       "step": 8000
     },
     {
       "epoch": 3.3451397087760726,
-      "grad_norm": 12.989178657531738,
+      "grad_norm": 13.326553344726562,
       "learning_rate": 1.4807197943444728e-07,
-      "loss": 1.0538,
+      "loss": 1.0143,
       "step": 8500
     },
     {
       "epoch": 3.541912632821724,
-      "grad_norm": 8.557451248168945,
+      "grad_norm": 8.523683547973633,
       "learning_rate": 1.0357919715246192e-07,
-      "loss": 1.0416,
+      "loss": 1.0021,
       "step": 9000
     },
     {
       "epoch": 3.738685556867375,
-      "grad_norm": 9.772086143493652,
+      "grad_norm": 10.767390251159668,
       "learning_rate": 5.9086414870476566e-08,
-      "loss": 1.0454,
+      "loss": 1.0003,
       "step": 9500
     },
     {
       "epoch": 3.9354584809130264,
-      "grad_norm": 9.701172828674316,
+      "grad_norm": 8.742927551269531,
       "learning_rate": 1.4593632588491198e-08,
-      "loss": 1.044,
+      "loss": 1.0086,
       "step": 10000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.7001217891939769,
-      "eval_loss": 1.1233651638031006,
-      "eval_model_preparation_time": 0.0055,
-      "eval_runtime": 1202.0319,
-      "eval_samples_per_second": 90.167,
-      "eval_steps_per_second": 2.818,
+      "eval_accuracy": 0.7055469441984057,
+      "eval_loss": 1.084580659866333,
+      "eval_model_preparation_time": 0.0054,
+      "eval_runtime": 1210.0183,
+      "eval_samples_per_second": 89.572,
+      "eval_steps_per_second": 2.799,
       "step": 10164
     }
   ],

config.json

@@ -120,5 +120,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.43.4"
+  "transformers_version": "4.44.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2d129e6ba0d4113eade43c1b58eb17e357e0f6b6a428b367f1cf3b8592b6b5
+oid sha256:75a00859aea079c75799c0858b733d733508af5552a18430897062c592a2583a
 size 343365480