Upload folder using huggingface_hub

checkpoint-10164/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a00859aea079c75799c0858b733d733508af5552a18430897062c592a2583a
+oid sha256:ae08e577606eeef2b66632cb52d3ed3f9cdb59bca00aac0af10979498ee66c3e
 size 343365480

checkpoint-10164/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2602958179df170d16c212f1771da5e650b0b7e8bbd5cd6dd5b991fffec42de0
+oid sha256:4ff323a157f41953706488c906c873a177bb71114646241f2a8177a740dd2100
 size 686851461

checkpoint-10164/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb792081ca522b9358c97c5042f0451bc7ca5061290fca5dd43951effffcca4
+oid sha256:952f08c40c34eff0831c27c192eb47755e3dde00eeb6f959fc4c352e7864c981
 size 627

checkpoint-10164/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.084580659866333,
+  "best_metric": 1.0084277391433716,
   "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": 8.859833717346191,
-      "learning_rate": 8.599564959462131e-07,
-      "loss": 1.0519,
+      "grad_norm": 13.16645622253418,
+      "learning_rate": 7.644057741744116e-07,
+      "loss": 0.9682,
       "step": 500
     },
     {
       "epoch": 0.39354584809130266,
-      "grad_norm": 10.870162010192871,
-      "learning_rate": 8.154637136642278e-07,
-      "loss": 1.0529,
+      "grad_norm": 13.873289108276367,
+      "learning_rate": 7.248566343682025e-07,
+      "loss": 0.9558,
       "step": 1000
     },
     {
       "epoch": 0.5903187721369539,
-      "grad_norm": 11.251194953918457,
-      "learning_rate": 7.709709313822424e-07,
-      "loss": 1.0397,
+      "grad_norm": 9.378376960754395,
+      "learning_rate": 6.853074945619932e-07,
+      "loss": 0.9563,
       "step": 1500
     },
     {
       "epoch": 0.7870916961826053,
-      "grad_norm": 12.0984468460083,
-      "learning_rate": 7.26478149100257e-07,
-      "loss": 1.0515,
+      "grad_norm": 13.954855918884277,
+      "learning_rate": 6.45758354755784e-07,
+      "loss": 0.9576,
       "step": 2000
     },
     {
       "epoch": 0.9838646202282566,
-      "grad_norm": 7.28156042098999,
-      "learning_rate": 6.819853668182716e-07,
-      "loss": 1.0337,
+      "grad_norm": 8.968609809875488,
+      "learning_rate": 6.062092149495747e-07,
+      "loss": 0.9435,
       "step": 2500
     },
     {
       "epoch": 1.0,
-      "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,
+      "eval_accuracy": 0.7204107617360496,
+      "eval_loss": 1.0221161842346191,
+      "eval_model_preparation_time": 0.0058,
+      "eval_runtime": 1192.8471,
+      "eval_samples_per_second": 90.862,
+      "eval_steps_per_second": 2.839,
       "step": 2541
     },
     {
       "epoch": 1.1806375442739079,
-      "grad_norm": 8.778160095214844,
-      "learning_rate": 6.374925845362863e-07,
-      "loss": 1.0223,
+      "grad_norm": 9.562682151794434,
+      "learning_rate": 5.666600751433656e-07,
+      "loss": 0.9435,
       "step": 3000
     },
     {
       "epoch": 1.3774104683195592,
-      "grad_norm": 8.823763847351074,
-      "learning_rate": 5.929998022543009e-07,
-      "loss": 1.0247,
+      "grad_norm": 7.73732328414917,
+      "learning_rate": 5.271109353371563e-07,
+      "loss": 0.945,
       "step": 3500
     },
     {
       "epoch": 1.5741833923652107,
-      "grad_norm": 9.15168285369873,
-      "learning_rate": 5.485070199723155e-07,
-      "loss": 1.024,
+      "grad_norm": 9.456089973449707,
+      "learning_rate": 4.875617955309472e-07,
+      "loss": 0.9379,
       "step": 4000
     },
     {
       "epoch": 1.770956316410862,
-      "grad_norm": 10.23277473449707,
-      "learning_rate": 5.040142376903302e-07,
-      "loss": 1.0362,
+      "grad_norm": 8.087896347045898,
+      "learning_rate": 4.48012655724738e-07,
+      "loss": 0.93,
       "step": 4500
     },
     {
       "epoch": 1.9677292404565132,
-      "grad_norm": 8.250983238220215,
-      "learning_rate": 4.5952145540834485e-07,
-      "loss": 1.0253,
+      "grad_norm": 11.194710731506348,
+      "learning_rate": 4.0846351591852876e-07,
+      "loss": 0.9457,
       "step": 5000
     },
     {
       "epoch": 2.0,
-      "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,
+      "eval_accuracy": 0.7221822409211692,
+      "eval_loss": 1.0146400928497314,
+      "eval_model_preparation_time": 0.0058,
+      "eval_runtime": 1188.9777,
+      "eval_samples_per_second": 91.157,
+      "eval_steps_per_second": 2.849,
       "step": 5082
     },
     {
       "epoch": 2.1645021645021645,
-      "grad_norm": 11.255722045898438,
-      "learning_rate": 4.150286731263595e-07,
-      "loss": 1.0128,
+      "grad_norm": 9.790952682495117,
+      "learning_rate": 3.6891437611231956e-07,
+      "loss": 0.9299,
       "step": 5500
     },
     {
       "epoch": 2.3612750885478158,
-      "grad_norm": 11.691879272460938,
-      "learning_rate": 3.705358908443741e-07,
-      "loss": 1.0168,
+      "grad_norm": 7.579208850860596,
+      "learning_rate": 3.293652363061103e-07,
+      "loss": 0.9283,
       "step": 6000
     },
     {
       "epoch": 2.558048012593467,
-      "grad_norm": 10.441214561462402,
-      "learning_rate": 3.2604310856238877e-07,
-      "loss": 1.0093,
+      "grad_norm": 8.789483070373535,
+      "learning_rate": 2.898160964999011e-07,
+      "loss": 0.9476,
       "step": 6500
     },
     {
       "epoch": 2.7548209366391183,
-      "grad_norm": 7.868481159210205,
-      "learning_rate": 2.815503262804034e-07,
-      "loss": 1.0133,
+      "grad_norm": 10.544241905212402,
+      "learning_rate": 2.502669566936919e-07,
+      "loss": 0.9228,
       "step": 7000
     },
     {
       "epoch": 2.9515938606847696,
-      "grad_norm": 10.433448791503906,
-      "learning_rate": 2.37057543998418e-07,
-      "loss": 1.0152,
+      "grad_norm": 8.694629669189453,
+      "learning_rate": 2.1071781688748268e-07,
+      "loss": 0.9256,
       "step": 7500
     },
     {
       "epoch": 3.0,
-      "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,
+      "eval_accuracy": 0.7234462651313847,
+      "eval_loss": 1.0090746879577637,
+      "eval_model_preparation_time": 0.0058,
+      "eval_runtime": 1192.9376,
+      "eval_samples_per_second": 90.855,
+      "eval_steps_per_second": 2.839,
       "step": 7623
     },
     {
       "epoch": 3.1483667847304213,
-      "grad_norm": 8.449857711791992,
-      "learning_rate": 1.9256476171643265e-07,
-      "loss": 1.0039,
+      "grad_norm": 9.106084823608398,
+      "learning_rate": 1.7116867708127348e-07,
+      "loss": 0.9313,
       "step": 8000
     },
     {
       "epoch": 3.3451397087760726,
-      "grad_norm": 13.326553344726562,
-      "learning_rate": 1.4807197943444728e-07,
-      "loss": 1.0143,
+      "grad_norm": 14.434243202209473,
+      "learning_rate": 1.3161953727506426e-07,
+      "loss": 0.9245,
       "step": 8500
     },
     {
       "epoch": 3.541912632821724,
-      "grad_norm": 8.523683547973633,
-      "learning_rate": 1.0357919715246192e-07,
-      "loss": 1.0021,
+      "grad_norm": 6.294890880584717,
+      "learning_rate": 9.207039746885504e-08,
+      "loss": 0.9135,
       "step": 9000
     },
     {
       "epoch": 3.738685556867375,
-      "grad_norm": 10.767390251159668,
-      "learning_rate": 5.9086414870476566e-08,
-      "loss": 1.0003,
+      "grad_norm": 9.335221290588379,
+      "learning_rate": 5.2521257662645836e-08,
+      "loss": 0.9349,
       "step": 9500
     },
     {
       "epoch": 3.9354584809130264,
-      "grad_norm": 8.742927551269531,
-      "learning_rate": 1.4593632588491198e-08,
-      "loss": 1.0086,
+      "grad_norm": 8.591920852661133,
+      "learning_rate": 1.297211785643662e-08,
+      "loss": 0.913,
       "step": 10000
     },
     {
       "epoch": 4.0,
-      "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,
+      "eval_accuracy": 0.723907587835843,
+      "eval_loss": 1.0084277391433716,
+      "eval_model_preparation_time": 0.0058,
+      "eval_runtime": 1186.2416,
+      "eval_samples_per_second": 91.368,
+      "eval_steps_per_second": 2.855,
       "step": 10164
     }
   ],

checkpoint-10164/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6e2b24c2bb418666641ee5942c486949ee0d8efdf7de643fb67fbd8451ce35
+oid sha256:ad3477ddc7ea3a5c3236c20065dd22f24f5262766b2c91e1cd0f8c8389a1871c
 size 4667

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f4b9de3ad1c437575d8c1632b8efd35addd79364f6e8707537d1b652985082a
+oid sha256:ae08e577606eeef2b66632cb52d3ed3f9cdb59bca00aac0af10979498ee66c3e
 size 343365480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d5f7cdc6601635e5f69bc583373e85c4f40edb1fb3b02520e9444e6c5414cd
+oid sha256:ad3477ddc7ea3a5c3236c20065dd22f24f5262766b2c91e1cd0f8c8389a1871c
 size 4667