Upload folder using huggingface_hub

checkpoint-9376/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac667f9891e096b94eec6a038cc2967f2cd9d88254165edf42d05ba621ba1c7a
+oid sha256:1265d8e5a8a363a615898be873c224aebc6f310654bf23b1745da0975a7b7555
 size 343245508

checkpoint-9376/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2297f022db5d3507731ee0645ef4ac9a9d0d10e51c904f9c64f2bb393f4d7fed
+oid sha256:db14e1baf0fce1ab79882476b9e400854724970e5adf6d8b17ef6d264fad3b22
 size 686611898

checkpoint-9376/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19ef57ca7ce01a08a3ddc4d19049becd27a3d4c36511ddeaa3a26bb44693aa91
+oid sha256:162830a25651b28da57d4375090a0500b22eb117bbfd79d4a2bf61dd85a56833
 size 1064

checkpoint-9376/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.0641573667526245,
+  "best_metric": 1.0019118785858154,
   "best_model_checkpoint": "fairface_age_image_detection/checkpoint-9376",
   "epoch": 4.0,
   "eval_steps": 500,
@@ -10,168 +10,168 @@
   "log_history": [
     {
       "epoch": 0.21331058020477817,
-      "grad_norm": 1.7275338172912598,
-      "learning_rate": 2.855243405532919e-06,
-      "loss": 1.8728,
+      "grad_norm": 2.756800413131714,
+      "learning_rate": 5.710486811065838e-06,
+      "loss": 1.7206,
       "step": 500
     },
     {
       "epoch": 0.42662116040955633,
-      "grad_norm": 2.228030204772949,
-      "learning_rate": 2.6944027450139397e-06,
-      "loss": 1.4714,
+      "grad_norm": 3.085395097732544,
+      "learning_rate": 5.3888054900278794e-06,
+      "loss": 1.3151,
       "step": 1000
     },
     {
       "epoch": 0.6399317406143344,
-      "grad_norm": 2.2512168884277344,
-      "learning_rate": 2.5335620844949606e-06,
-      "loss": 1.3358,
+      "grad_norm": 3.533961057662964,
+      "learning_rate": 5.067124168989921e-06,
+      "loss": 1.212,
       "step": 1500
     },
     {
       "epoch": 0.8532423208191127,
-      "grad_norm": 3.124258279800415,
-      "learning_rate": 2.372721423975981e-06,
-      "loss": 1.264,
+      "grad_norm": 5.493643283843994,
+      "learning_rate": 4.745442847951962e-06,
+      "loss": 1.145,
       "step": 2000
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5423,
-      "eval_loss": 1.2151408195495605,
-      "eval_model_preparation_time": 0.0043,
-      "eval_runtime": 907.0206,
-      "eval_samples_per_second": 11.025,
-      "eval_steps_per_second": 1.378,
+      "eval_accuracy": 0.5652,
+      "eval_loss": 1.115075707435608,
+      "eval_model_preparation_time": 0.0037,
+      "eval_runtime": 903.327,
+      "eval_samples_per_second": 11.07,
+      "eval_steps_per_second": 1.384,
       "step": 2344
     },
     {
       "epoch": 1.0665529010238908,
-      "grad_norm": 5.8204874992370605,
-      "learning_rate": 2.211880763457002e-06,
-      "loss": 1.2174,
+      "grad_norm": 5.28899621963501,
+      "learning_rate": 4.423761526914004e-06,
+      "loss": 1.1006,
       "step": 2500
     },
     {
       "epoch": 1.2798634812286689,
-      "grad_norm": 5.175824165344238,
-      "learning_rate": 2.051040102938023e-06,
-      "loss": 1.171,
+      "grad_norm": 6.52961540222168,
+      "learning_rate": 4.102080205876046e-06,
+      "loss": 1.0519,
       "step": 3000
     },
     {
       "epoch": 1.493174061433447,
-      "grad_norm": 3.312744617462158,
-      "learning_rate": 1.8901994424190437e-06,
-      "loss": 1.1425,
+      "grad_norm": 10.652497291564941,
+      "learning_rate": 3.7803988848380875e-06,
+      "loss": 1.0292,
       "step": 3500
     },
     {
       "epoch": 1.7064846416382253,
-      "grad_norm": 4.630620002746582,
-      "learning_rate": 1.7293587819000642e-06,
-      "loss": 1.1267,
+      "grad_norm": 5.245483875274658,
+      "learning_rate": 3.4587175638001284e-06,
+      "loss": 1.016,
       "step": 4000
     },
     {
       "epoch": 1.9197952218430034,
-      "grad_norm": 3.5600452423095703,
-      "learning_rate": 1.5685181213810853e-06,
-      "loss": 1.1051,
+      "grad_norm": 4.070522308349609,
+      "learning_rate": 3.1370362427621706e-06,
+      "loss": 1.0056,
       "step": 4500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5688,
-      "eval_loss": 1.1124917268753052,
-      "eval_model_preparation_time": 0.0043,
-      "eval_runtime": 915.0894,
-      "eval_samples_per_second": 10.928,
-      "eval_steps_per_second": 1.366,
+      "eval_accuracy": 0.5831,
+      "eval_loss": 1.030907392501831,
+      "eval_model_preparation_time": 0.0037,
+      "eval_runtime": 917.4025,
+      "eval_samples_per_second": 10.9,
+      "eval_steps_per_second": 1.363,
       "step": 4688
     },
     {
       "epoch": 2.1331058020477816,
-      "grad_norm": 7.453662395477295,
-      "learning_rate": 1.407677460862106e-06,
-      "loss": 1.0871,
+      "grad_norm": 6.568565845489502,
+      "learning_rate": 2.815354921724212e-06,
+      "loss": 0.9796,
       "step": 5000
     },
     {
       "epoch": 2.34641638225256,
-      "grad_norm": 8.157800674438477,
-      "learning_rate": 1.2468368003431269e-06,
-      "loss": 1.0696,
+      "grad_norm": 10.742039680480957,
+      "learning_rate": 2.4936736006862537e-06,
+      "loss": 0.9587,
       "step": 5500
     },
     {
       "epoch": 2.5597269624573378,
-      "grad_norm": 3.6688616275787354,
-      "learning_rate": 1.0859961398241475e-06,
-      "loss": 1.0571,
+      "grad_norm": 4.3592424392700195,
+      "learning_rate": 2.171992279648295e-06,
+      "loss": 0.9455,
       "step": 6000
     },
     {
       "epoch": 2.773037542662116,
-      "grad_norm": 3.1099190711975098,
-      "learning_rate": 9.251554793051683e-07,
-      "loss": 1.0476,
+      "grad_norm": 5.696556091308594,
+      "learning_rate": 1.8503109586103366e-06,
+      "loss": 0.9363,
       "step": 6500
     },
     {
       "epoch": 2.986348122866894,
-      "grad_norm": 5.784822463989258,
-      "learning_rate": 7.643148187861893e-07,
-      "loss": 1.0407,
+      "grad_norm": 5.746116638183594,
+      "learning_rate": 1.5286296375723786e-06,
+      "loss": 0.9347,
       "step": 7000
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.5756,
-      "eval_loss": 1.0761935710906982,
-      "eval_model_preparation_time": 0.0043,
-      "eval_runtime": 920.0161,
-      "eval_samples_per_second": 10.869,
-      "eval_steps_per_second": 1.359,
+      "eval_accuracy": 0.5883,
+      "eval_loss": 1.0057746171951294,
+      "eval_model_preparation_time": 0.0037,
+      "eval_runtime": 926.1536,
+      "eval_samples_per_second": 10.797,
+      "eval_steps_per_second": 1.35,
       "step": 7032
     },
     {
       "epoch": 3.1996587030716723,
-      "grad_norm": 5.856372833251953,
-      "learning_rate": 6.0347415826721e-07,
-      "loss": 1.0212,
+      "grad_norm": 4.218583106994629,
+      "learning_rate": 1.20694831653442e-06,
+      "loss": 0.9035,
       "step": 7500
     },
     {
       "epoch": 3.4129692832764507,
-      "grad_norm": 5.725022792816162,
-      "learning_rate": 4.426334977482307e-07,
-      "loss": 1.0253,
+      "grad_norm": 6.724698543548584,
+      "learning_rate": 8.852669954964614e-07,
+      "loss": 0.9081,
       "step": 8000
     },
     {
       "epoch": 3.6262798634812285,
-      "grad_norm": 4.74147891998291,
-      "learning_rate": 2.8179283722925154e-07,
-      "loss": 1.0232,
+      "grad_norm": 6.658480167388916,
+      "learning_rate": 5.635856744585031e-07,
+      "loss": 0.905,
       "step": 8500
     },
     {
       "epoch": 3.839590443686007,
-      "grad_norm": 4.050413131713867,
-      "learning_rate": 1.2095217671027237e-07,
-      "loss": 1.0173,
+      "grad_norm": 4.382744789123535,
+      "learning_rate": 2.4190435342054474e-07,
+      "loss": 0.8969,
       "step": 9000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5791,
-      "eval_loss": 1.0641573667526245,
-      "eval_model_preparation_time": 0.0043,
-      "eval_runtime": 919.3696,
-      "eval_samples_per_second": 10.877,
-      "eval_steps_per_second": 1.36,
+      "eval_accuracy": 0.5892,
+      "eval_loss": 1.0019118785858154,
+      "eval_model_preparation_time": 0.0037,
+      "eval_runtime": 929.5968,
+      "eval_samples_per_second": 10.757,
+      "eval_steps_per_second": 1.345,
       "step": 9376
     }
   ],

checkpoint-9376/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f7f93c67bf88403da8f77fa2109e270c1cad6076487c78154dcb74bbd014af
+oid sha256:5ba8df84fa27b6ce1aa5fc9dad74c0fa9ee6fdec46d72d1f00235b986d4684db
 size 5304

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3a725b1119d48b89118403515c77428316605407f871bbc7bba7fb50b32305
+oid sha256:1265d8e5a8a363a615898be873c224aebc6f310654bf23b1745da0975a7b7555
 size 343245508

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ef976af56a6fd0395073925187744ad7c56829cffa99ff2332a90f94307b2
+oid sha256:5ba8df84fa27b6ce1aa5fc9dad74c0fa9ee6fdec46d72d1f00235b986d4684db
 size 5304