Upload folder using huggingface_hub

checkpoint-4560/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cecd28b4d92743518c8f4fb11713818229a881dd452670d73ff23b062afd1f7
+oid sha256:b82b121e7061bd0bde87ba49bbfeee7704af3349887191915398d7cb39368d38
 size 343288572

checkpoint-4560/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5f7399d19831d1ef6e68eb30c8293476e2eeb3519e06665fee27c97a26ee12d
+oid sha256:5e65a1c9bf0821cb2ef6765567cccb96b0339c60d28d494f04e2472b5643d98f
 size 686697605

checkpoint-4560/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481698a62856c54221140971b2e4ad8c29d8b8579a0e38b6957e61736ba1b721
+oid sha256:d8ae9b2155fa2f3fce55e5a56ce3562d69d4df58a9f05348b03d571448ad56a4
 size 627

checkpoint-4560/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.1997283697128296,
+  "best_metric": 1.1146559715270996,
   "best_model_checkpoint": "facial_age_image_detection/checkpoint-4560",
   "epoch": 19.0,
   "eval_steps": 500,
@@ -10,236 +10,236 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5973023164891017,
-      "eval_loss": 1.2148407697677612,
-      "eval_runtime": 107.0191,
-      "eval_samples_per_second": 95.6,
-      "eval_steps_per_second": 2.99,
+      "eval_accuracy": 0.6217378555370932,
+      "eval_loss": 1.1227059364318848,
+      "eval_runtime": 116.8455,
+      "eval_samples_per_second": 87.56,
+      "eval_steps_per_second": 2.739,
       "step": 240
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6003323233310527,
-      "eval_loss": 1.2124874591827393,
-      "eval_runtime": 108.7931,
-      "eval_samples_per_second": 94.041,
-      "eval_steps_per_second": 2.941,
+      "eval_accuracy": 0.6248656045352361,
+      "eval_loss": 1.1205345392227173,
+      "eval_runtime": 101.698,
+      "eval_samples_per_second": 100.602,
+      "eval_steps_per_second": 3.147,
       "step": 480
     },
     {
       "epoch": 2.08,
-      "grad_norm": 10.869218826293945,
-      "learning_rate": 4.526315789473684e-07,
-      "loss": 0.7792,
+      "grad_norm": 14.197029113769531,
+      "learning_rate": 2.7157894736842105e-07,
+      "loss": 0.7372,
       "step": 500
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6001368390186688,
-      "eval_loss": 1.2103016376495361,
-      "eval_runtime": 108.2046,
-      "eval_samples_per_second": 94.552,
-      "eval_steps_per_second": 2.957,
+      "eval_accuracy": 0.6255497996285798,
+      "eval_loss": 1.1209293603897095,
+      "eval_runtime": 102.6145,
+      "eval_samples_per_second": 99.703,
+      "eval_steps_per_second": 3.118,
       "step": 720
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.5932948880852311,
-      "eval_loss": 1.2177255153656006,
-      "eval_runtime": 108.1913,
-      "eval_samples_per_second": 94.564,
-      "eval_steps_per_second": 2.958,
+      "eval_accuracy": 0.6272114162838432,
+      "eval_loss": 1.119669795036316,
+      "eval_runtime": 101.8458,
+      "eval_samples_per_second": 100.456,
+      "eval_steps_per_second": 3.142,
       "step": 960
     },
     {
       "epoch": 4.17,
-      "grad_norm": 7.94642972946167,
-      "learning_rate": 4e-07,
-      "loss": 0.7693,
+      "grad_norm": 13.897222518920898,
+      "learning_rate": 2.4e-07,
+      "loss": 0.7296,
       "step": 1000
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.5987684488319812,
-      "eval_loss": 1.2087459564208984,
-      "eval_runtime": 108.1422,
-      "eval_samples_per_second": 94.607,
-      "eval_steps_per_second": 2.959,
+      "eval_accuracy": 0.6242791515980842,
+      "eval_loss": 1.1204010248184204,
+      "eval_runtime": 103.9165,
+      "eval_samples_per_second": 98.454,
+      "eval_steps_per_second": 3.079,
       "step": 1200
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.5989639331443651,
-      "eval_loss": 1.2106623649597168,
-      "eval_runtime": 108.6434,
-      "eval_samples_per_second": 94.17,
-      "eval_steps_per_second": 2.945,
+      "eval_accuracy": 0.6246701202228521,
+      "eval_loss": 1.1215792894363403,
+      "eval_runtime": 106.6746,
+      "eval_samples_per_second": 95.909,
+      "eval_steps_per_second": 3.0,
       "step": 1440
     },
     {
       "epoch": 6.25,
-      "grad_norm": 12.206405639648438,
-      "learning_rate": 3.4736842105263157e-07,
-      "loss": 0.7579,
+      "grad_norm": 11.151677131652832,
+      "learning_rate": 2.0842105263157896e-07,
+      "loss": 0.72,
       "step": 1500
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.5941745674909589,
-      "eval_loss": 1.2116234302520752,
-      "eval_runtime": 110.2341,
-      "eval_samples_per_second": 92.812,
-      "eval_steps_per_second": 2.903,
+      "eval_accuracy": 0.6236926986609325,
+      "eval_loss": 1.1201025247573853,
+      "eval_runtime": 102.583,
+      "eval_samples_per_second": 99.734,
+      "eval_steps_per_second": 3.119,
       "step": 1680
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.596520379239566,
-      "eval_loss": 1.209428071975708,
-      "eval_runtime": 109.2117,
-      "eval_samples_per_second": 93.68,
-      "eval_steps_per_second": 2.93,
+      "eval_accuracy": 0.6247678623790441,
+      "eval_loss": 1.1184368133544922,
+      "eval_runtime": 102.2621,
+      "eval_samples_per_second": 100.047,
+      "eval_steps_per_second": 3.129,
       "step": 1920
     },
     {
       "epoch": 8.33,
-      "grad_norm": 13.978309631347656,
-      "learning_rate": 2.947368421052631e-07,
-      "loss": 0.7564,
+      "grad_norm": 13.550016403198242,
+      "learning_rate": 1.7684210526315786e-07,
+      "loss": 0.7137,
       "step": 2000
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.5945655361157267,
-      "eval_loss": 1.207972764968872,
-      "eval_runtime": 109.0595,
-      "eval_samples_per_second": 93.811,
-      "eval_steps_per_second": 2.934,
+      "eval_accuracy": 0.625158831003812,
+      "eval_loss": 1.1169142723083496,
+      "eval_runtime": 101.4179,
+      "eval_samples_per_second": 100.88,
+      "eval_steps_per_second": 3.155,
       "step": 2160
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.5972045743329097,
-      "eval_loss": 1.2053894996643066,
-      "eval_runtime": 108.2001,
-      "eval_samples_per_second": 94.556,
-      "eval_steps_per_second": 2.957,
+      "eval_accuracy": 0.6285798064705307,
+      "eval_loss": 1.1156556606292725,
+      "eval_runtime": 109.0217,
+      "eval_samples_per_second": 93.844,
+      "eval_steps_per_second": 2.935,
       "step": 2400
     },
     {
       "epoch": 10.42,
-      "grad_norm": 13.184745788574219,
-      "learning_rate": 2.4210526315789473e-07,
-      "loss": 0.7462,
+      "grad_norm": 17.68604850769043,
+      "learning_rate": 1.4526315789473685e-07,
+      "loss": 0.715,
       "step": 2500
     },
     {
       "epoch": 11.0,
-      "eval_accuracy": 0.596520379239566,
-      "eval_loss": 1.2063862085342407,
-      "eval_runtime": 109.0351,
-      "eval_samples_per_second": 93.832,
-      "eval_steps_per_second": 2.935,
+      "eval_accuracy": 0.6254520574723879,
+      "eval_loss": 1.1168755292892456,
+      "eval_runtime": 112.108,
+      "eval_samples_per_second": 91.26,
+      "eval_steps_per_second": 2.854,
       "step": 2640
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.5967158635519499,
-      "eval_loss": 1.205006718635559,
-      "eval_runtime": 107.7737,
-      "eval_samples_per_second": 94.93,
-      "eval_steps_per_second": 2.969,
+      "eval_accuracy": 0.6256475417847718,
+      "eval_loss": 1.1173280477523804,
+      "eval_runtime": 111.2518,
+      "eval_samples_per_second": 91.963,
+      "eval_steps_per_second": 2.876,
       "step": 2880
     },
     {
       "epoch": 12.5,
-      "grad_norm": 13.500107765197754,
-      "learning_rate": 1.8947368421052632e-07,
-      "loss": 0.7444,
+      "grad_norm": 13.063650131225586,
+      "learning_rate": 1.1368421052631579e-07,
+      "loss": 0.7087,
       "step": 3000
     },
     {
       "epoch": 13.0,
-      "eval_accuracy": 0.5974000586452937,
-      "eval_loss": 1.2029664516448975,
-      "eval_runtime": 108.3584,
-      "eval_samples_per_second": 94.418,
-      "eval_steps_per_second": 2.953,
+      "eval_accuracy": 0.6273091584400352,
+      "eval_loss": 1.116219162940979,
+      "eval_runtime": 102.5044,
+      "eval_samples_per_second": 99.81,
+      "eval_steps_per_second": 3.122,
       "step": 3120
     },
     {
       "epoch": 14.0,
-      "eval_accuracy": 0.5982797380510214,
-      "eval_loss": 1.2019948959350586,
-      "eval_runtime": 108.2177,
-      "eval_samples_per_second": 94.541,
-      "eval_steps_per_second": 2.957,
+      "eval_accuracy": 0.6236926986609325,
+      "eval_loss": 1.1165720224380493,
+      "eval_runtime": 117.8614,
+      "eval_samples_per_second": 86.805,
+      "eval_steps_per_second": 2.715,
       "step": 3360
     },
     {
       "epoch": 14.58,
-      "grad_norm": 12.818633079528809,
-      "learning_rate": 1.368421052631579e-07,
-      "loss": 0.7402,
+      "grad_norm": 22.076231002807617,
+      "learning_rate": 8.210526315789474e-08,
+      "loss": 0.705,
       "step": 3500
     },
     {
       "epoch": 15.0,
-      "eval_accuracy": 0.5969113478643339,
-      "eval_loss": 1.2034169435501099,
-      "eval_runtime": 107.9426,
-      "eval_samples_per_second": 94.782,
-      "eval_steps_per_second": 2.965,
+      "eval_accuracy": 0.6240836672857003,
+      "eval_loss": 1.1172147989273071,
+      "eval_runtime": 107.0013,
+      "eval_samples_per_second": 95.616,
+      "eval_steps_per_second": 2.991,
       "step": 3600
     },
     {
       "epoch": 16.0,
-      "eval_accuracy": 0.5980842537386375,
-      "eval_loss": 1.2004482746124268,
-      "eval_runtime": 108.7494,
-      "eval_samples_per_second": 94.079,
-      "eval_steps_per_second": 2.943,
+      "eval_accuracy": 0.6259407682533477,
+      "eval_loss": 1.1154069900512695,
+      "eval_runtime": 107.8292,
+      "eval_samples_per_second": 94.882,
+      "eval_steps_per_second": 2.968,
       "step": 3840
     },
     {
       "epoch": 16.67,
-      "grad_norm": 10.575230598449707,
-      "learning_rate": 8.421052631578947e-08,
-      "loss": 0.7357,
+      "grad_norm": 10.493719100952148,
+      "learning_rate": 5.052631578947368e-08,
+      "loss": 0.6994,
       "step": 4000
     },
     {
       "epoch": 17.0,
-      "eval_accuracy": 0.5988661909881732,
-      "eval_loss": 1.2010480165481567,
-      "eval_runtime": 108.3609,
-      "eval_samples_per_second": 94.416,
-      "eval_steps_per_second": 2.953,
+      "eval_accuracy": 0.6261362525657316,
+      "eval_loss": 1.1150434017181396,
+      "eval_runtime": 103.249,
+      "eval_samples_per_second": 99.091,
+      "eval_steps_per_second": 3.099,
       "step": 4080
     },
     {
       "epoch": 18.0,
-      "eval_accuracy": 0.5970090900205258,
-      "eval_loss": 1.2006783485412598,
-      "eval_runtime": 108.1842,
-      "eval_samples_per_second": 94.57,
-      "eval_steps_per_second": 2.958,
+      "eval_accuracy": 0.6241814094418923,
+      "eval_loss": 1.1151177883148193,
+      "eval_runtime": 102.8465,
+      "eval_samples_per_second": 99.478,
+      "eval_steps_per_second": 3.111,
       "step": 4320
     },
     {
       "epoch": 18.75,
-      "grad_norm": 10.900801658630371,
-      "learning_rate": 3.157894736842105e-08,
-      "loss": 0.7376,
+      "grad_norm": 15.010687828063965,
+      "learning_rate": 1.8947368421052632e-08,
+      "loss": 0.7018,
       "step": 4500
     },
     {
       "epoch": 19.0,
-      "eval_accuracy": 0.5974000586452937,
-      "eval_loss": 1.1997283697128296,
-      "eval_runtime": 108.4624,
-      "eval_samples_per_second": 94.328,
-      "eval_steps_per_second": 2.95,
+      "eval_accuracy": 0.6252565731600039,
+      "eval_loss": 1.1146559715270996,
+      "eval_runtime": 104.246,
+      "eval_samples_per_second": 98.143,
+      "eval_steps_per_second": 3.07,
       "step": 4560
     }
   ],

checkpoint-4560/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1720d13f8074df3fb08ee60b875a9df5a8b4161f2f31054e04a3b9fdc006e59a
+oid sha256:68e7e07fa963d2e5d6c71cf1c101cab9d463df433ec5bd73bb81335178bb51b7
 size 4411

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d446592a8713ec044baca3f10db07d050d0d63c2dcc0af7e90747c2f711873
+oid sha256:b82b121e7061bd0bde87ba49bbfeee7704af3349887191915398d7cb39368d38
 size 343288572

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3cbd7e961f520d4cc073622bb190f62bb0989c97e9a4850106ebdbeddcce186
+oid sha256:68e7e07fa963d2e5d6c71cf1c101cab9d463df433ec5bd73bb81335178bb51b7
 size 4411