Upload folder using huggingface_hub

checkpoint-1200/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:880fe2c9c38252240def486ab1893b1f5454a7139a66459fdbd67da86200bf6f
+oid sha256:773dca78e04e7c2fdd11828420779a1f50397cbc9f2eb98691641a8aa2f27a5b
 size 343288572

checkpoint-1200/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca163c50d41a93fca24af63248a4286c375d15f0e13d88e2125e32fdb61dd333
+oid sha256:6fb9b7ead2df23a4abcdfbb4637b532943589ef1ded161f8234644399f295802
 size 686698042

checkpoint-1200/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a3f0e754f92a9ba4f39927b560b1936de6e9d302ea80e42362dd4a3873b661
+oid sha256:b98e8f37e9b343024a717f1b1f96812e3aa6a92d57a322e15eb2f0fe34aaa0ad
 size 14244

checkpoint-1200/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.7509504556655884,
+  "best_metric": 1.5165716409683228,
   "best_model_checkpoint": "facial_age_estimator/checkpoint-1200",
   "epoch": 10.0,
   "eval_steps": 500,
@@ -10,106 +10,106 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.3799237611181703,
-      "eval_loss": 2.010244131088257,
-      "eval_runtime": 89.3663,
-      "eval_samples_per_second": 114.484,
-      "eval_steps_per_second": 1.79,
+      "eval_accuracy": 0.4476590753592024,
+      "eval_loss": 1.694000482559204,
+      "eval_runtime": 87.798,
+      "eval_samples_per_second": 116.529,
+      "eval_steps_per_second": 1.822,
       "step": 120
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.39390088945362134,
-      "eval_loss": 1.9449316263198853,
-      "eval_runtime": 89.1195,
-      "eval_samples_per_second": 114.801,
-      "eval_steps_per_second": 1.795,
+      "eval_accuracy": 0.4534258625745284,
+      "eval_loss": 1.654381275177002,
+      "eval_runtime": 87.4351,
+      "eval_samples_per_second": 117.013,
+      "eval_steps_per_second": 1.83,
       "step": 240
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.41237415697390284,
-      "eval_loss": 1.8914791345596313,
-      "eval_runtime": 89.0642,
-      "eval_samples_per_second": 114.872,
-      "eval_steps_per_second": 1.796,
+      "eval_accuracy": 0.4608542664451178,
+      "eval_loss": 1.618933081626892,
+      "eval_runtime": 87.806,
+      "eval_samples_per_second": 116.518,
+      "eval_steps_per_second": 1.822,
       "step": 360
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.4054344638842733,
-      "eval_loss": 1.8564153909683228,
-      "eval_runtime": 89.6525,
-      "eval_samples_per_second": 114.118,
-      "eval_steps_per_second": 1.785,
+      "eval_accuracy": 0.4673052487537875,
+      "eval_loss": 1.6022893190383911,
+      "eval_runtime": 87.7995,
+      "eval_samples_per_second": 116.527,
+      "eval_steps_per_second": 1.822,
       "step": 480
     },
     {
       "epoch": 4.166666666666667,
-      "grad_norm": 3.723311424255371,
+      "grad_norm": 3.601428747177124,
       "learning_rate": 6.086956521739132e-06,
-      "loss": 1.8165,
+      "loss": 1.5209,
       "step": 500
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.41325383637963053,
-      "eval_loss": 1.8217633962631226,
-      "eval_runtime": 89.4594,
-      "eval_samples_per_second": 114.365,
-      "eval_steps_per_second": 1.789,
+      "eval_accuracy": 0.47023751343954645,
+      "eval_loss": 1.572880744934082,
+      "eval_runtime": 88.2571,
+      "eval_samples_per_second": 115.923,
+      "eval_steps_per_second": 1.813,
       "step": 600
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.4161861010653895,
-      "eval_loss": 1.7974796295166016,
-      "eval_runtime": 90.6881,
-      "eval_samples_per_second": 112.815,
-      "eval_steps_per_second": 1.764,
+      "eval_accuracy": 0.4768839800606001,
+      "eval_loss": 1.5591648817062378,
+      "eval_runtime": 87.4224,
+      "eval_samples_per_second": 117.03,
+      "eval_steps_per_second": 1.83,
       "step": 720
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.41872739712638063,
-      "eval_loss": 1.7807412147521973,
-      "eval_runtime": 89.7218,
-      "eval_samples_per_second": 114.03,
-      "eval_steps_per_second": 1.783,
+      "eval_accuracy": 0.4815756035578145,
+      "eval_loss": 1.5406521558761597,
+      "eval_runtime": 87.5838,
+      "eval_samples_per_second": 116.814,
+      "eval_steps_per_second": 1.827,
       "step": 840
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.4264490274655459,
-      "eval_loss": 1.764231562614441,
-      "eval_runtime": 90.0605,
-      "eval_samples_per_second": 113.601,
-      "eval_steps_per_second": 1.777,
+      "eval_accuracy": 0.48138011924543056,
+      "eval_loss": 1.5303517580032349,
+      "eval_runtime": 87.3649,
+      "eval_samples_per_second": 117.107,
+      "eval_steps_per_second": 1.831,
       "step": 960
     },
     {
       "epoch": 8.333333333333334,
-      "grad_norm": 2.656496286392212,
+      "grad_norm": 4.306453227996826,
       "learning_rate": 1.7391304347826088e-06,
-      "loss": 1.624,
+      "loss": 1.369,
       "step": 1000
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.4291858078389209,
-      "eval_loss": 1.75428307056427,
-      "eval_runtime": 89.3673,
-      "eval_samples_per_second": 114.483,
-      "eval_steps_per_second": 1.79,
+      "eval_accuracy": 0.4878311015541003,
+      "eval_loss": 1.51864492893219,
+      "eval_runtime": 88.2907,
+      "eval_samples_per_second": 115.879,
+      "eval_steps_per_second": 1.812,
       "step": 1080
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.4270354804026977,
-      "eval_loss": 1.7509504556655884,
-      "eval_runtime": 88.7685,
-      "eval_samples_per_second": 115.255,
-      "eval_steps_per_second": 1.802,
+      "eval_accuracy": 0.49086110839605124,
+      "eval_loss": 1.5165716409683228,
+      "eval_runtime": 87.8471,
+      "eval_samples_per_second": 116.464,
+      "eval_steps_per_second": 1.821,
       "step": 1200
     }
   ],
@@ -130,7 +130,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1893383914511053e+19,
+  "total_flos": 1.2071959063022186e+19,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:880fe2c9c38252240def486ab1893b1f5454a7139a66459fdbd67da86200bf6f
+oid sha256:773dca78e04e7c2fdd11828420779a1f50397cbc9f2eb98691641a8aa2f27a5b
 size 343288572