Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.22972972972973,
-    "eval_accuracy": 0.8193548387096774,
-    "eval_loss": 0.4508959949016571,
-    "eval_runtime": 15.0463,
-    "eval_samples_per_second": 10.302,
-    "eval_steps_per_second": 1.329
+    "eval_accuracy": 0.8580645161290322,
+    "eval_loss": 0.435279905796051,
+    "eval_runtime": 14.7921,
+    "eval_samples_per_second": 10.479,
+    "eval_steps_per_second": 1.352
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456b8867a22b4805a83001a85b58c505242ea7788991e33f3993ff2d0a0226b0
+oid sha256:2656e4d0738206636d0840181342325b915cf2dba42c9e9c55bfbc3ec5250757
 size 344961984

runs/May18_20-17-26_DESKTOP-SGO0ICV/events.out.tfevents.1716035095.DESKTOP-SGO0ICV.14384.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a78ecc30cc65cdd25286f42704e4cf05611cfb97b20ad00838a424007df449
-size 411
+oid sha256:e4b64a4025f1bc0e396263e1235ba68c5a1adf9739164b8ddac4fc8115cd3e0e
+size 734

runs/May18_20-34-00_DESKTOP-SGO0ICV/events.out.tfevents.1716035643.DESKTOP-SGO0ICV.24484.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94136d5bec5eae043d7cff005114b697f1990d9cc437d0888ede9b8752390e8d
+size 6452

test_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.22972972972973,
-    "eval_accuracy": 0.8193548387096774,
-    "eval_loss": 0.4508959949016571,
-    "eval_runtime": 15.0463,
-    "eval_samples_per_second": 10.302,
-    "eval_steps_per_second": 1.329
+    "eval_accuracy": 0.8580645161290322,
+    "eval_loss": 0.435279905796051,
+    "eval_runtime": 14.7921,
+    "eval_samples_per_second": 10.479,
+    "eval_steps_per_second": 1.352
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8714285714285714,
+  "best_metric": 0.8857142857142857,
   "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset\\checkpoint-148",
   "epoch": 3.22972972972973,
   "eval_steps": 500,
@@ -10,163 +10,163 @@
   "log_history": [
     {
       "epoch": 0.06756756756756757,
-      "grad_norm": 6.096624374389648,
+      "grad_norm": 6.154857635498047,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 2.2942,
+      "loss": 2.326,
       "step": 10
     },
     {
       "epoch": 0.13513513513513514,
-      "grad_norm": 7.102034568786621,
+      "grad_norm": 7.193238735198975,
       "learning_rate": 4.81203007518797e-05,
-      "loss": 2.2308,
+      "loss": 2.2205,
       "step": 20
     },
     {
       "epoch": 0.20270270270270271,
-      "grad_norm": 7.2539143562316895,
+      "grad_norm": 7.481975555419922,
       "learning_rate": 4.43609022556391e-05,
-      "loss": 2.1149,
+      "loss": 2.16,
       "step": 30
     },
     {
       "epoch": 0.25675675675675674,
-      "eval_accuracy": 0.5571428571428572,
-      "eval_loss": 1.8154758214950562,
-      "eval_runtime": 10.1069,
-      "eval_samples_per_second": 6.926,
-      "eval_steps_per_second": 0.89,
+      "eval_accuracy": 0.5,
+      "eval_loss": 1.7993043661117554,
+      "eval_runtime": 6.6774,
+      "eval_samples_per_second": 10.483,
+      "eval_steps_per_second": 1.348,
       "step": 38
     },
     {
       "epoch": 1.0135135135135136,
-      "grad_norm": 25.16826057434082,
+      "grad_norm": 10.227862358093262,
       "learning_rate": 4.0601503759398494e-05,
-      "loss": 1.97,
+      "loss": 1.9946,
       "step": 40
     },
     {
       "epoch": 1.0810810810810811,
-      "grad_norm": 10.718199729919434,
+      "grad_norm": 10.306306838989258,
       "learning_rate": 3.6842105263157895e-05,
-      "loss": 1.5744,
+      "loss": 1.5987,
       "step": 50
     },
     {
       "epoch": 1.1486486486486487,
-      "grad_norm": 10.61833381652832,
+      "grad_norm": 10.154570579528809,
       "learning_rate": 3.3082706766917295e-05,
-      "loss": 1.3135,
+      "loss": 1.197,
       "step": 60
     },
     {
       "epoch": 1.2162162162162162,
-      "grad_norm": 8.033047676086426,
+      "grad_norm": 8.003480911254883,
       "learning_rate": 2.9323308270676693e-05,
-      "loss": 0.8974,
+      "loss": 0.8394,
       "step": 70
     },
     {
       "epoch": 1.2567567567567568,
-      "eval_accuracy": 0.5857142857142857,
-      "eval_loss": 1.1256393194198608,
-      "eval_runtime": 9.8133,
-      "eval_samples_per_second": 7.133,
-      "eval_steps_per_second": 0.917,
+      "eval_accuracy": 0.7,
+      "eval_loss": 0.8820496201515198,
+      "eval_runtime": 6.7555,
+      "eval_samples_per_second": 10.362,
+      "eval_steps_per_second": 1.332,
       "step": 76
     },
     {
       "epoch": 2.027027027027027,
-      "grad_norm": 8.3702392578125,
+      "grad_norm": 6.113378047943115,
       "learning_rate": 2.556390977443609e-05,
-      "loss": 0.9946,
+      "loss": 0.8036,
       "step": 80
     },
     {
       "epoch": 2.0945945945945947,
-      "grad_norm": 9.561596870422363,
+      "grad_norm": 13.039664268493652,
       "learning_rate": 2.1804511278195487e-05,
-      "loss": 0.7404,
+      "loss": 0.5384,
       "step": 90
     },
     {
       "epoch": 2.1621621621621623,
-      "grad_norm": 11.346077919006348,
+      "grad_norm": 14.060022354125977,
       "learning_rate": 1.8045112781954888e-05,
-      "loss": 0.6667,
+      "loss": 0.6038,
       "step": 100
     },
     {
       "epoch": 2.22972972972973,
-      "grad_norm": 7.648571014404297,
+      "grad_norm": 6.143197536468506,
       "learning_rate": 1.4285714285714285e-05,
-      "loss": 0.5226,
+      "loss": 0.4228,
       "step": 110
     },
     {
       "epoch": 2.2567567567567566,
-      "eval_accuracy": 0.8,
-      "eval_loss": 0.5665245056152344,
-      "eval_runtime": 8.9518,
-      "eval_samples_per_second": 7.82,
-      "eval_steps_per_second": 1.005,
+      "eval_accuracy": 0.8428571428571429,
+      "eval_loss": 0.5060061812400818,
+      "eval_runtime": 7.8853,
+      "eval_samples_per_second": 8.877,
+      "eval_steps_per_second": 1.141,
       "step": 114
     },
     {
       "epoch": 3.0405405405405403,
-      "grad_norm": 3.668431520462036,
+      "grad_norm": 5.005883693695068,
       "learning_rate": 1.0526315789473684e-05,
-      "loss": 0.44,
+      "loss": 0.3779,
       "step": 120
     },
     {
       "epoch": 3.108108108108108,
-      "grad_norm": 5.99934720993042,
+      "grad_norm": 4.216254711151123,
       "learning_rate": 6.766917293233083e-06,
-      "loss": 0.3393,
+      "loss": 0.2576,
       "step": 130
     },
     {
       "epoch": 3.175675675675676,
-      "grad_norm": 10.936161994934082,
+      "grad_norm": 8.001497268676758,
       "learning_rate": 3.007518796992481e-06,
-      "loss": 0.3423,
+      "loss": 0.3029,
       "step": 140
     },
     {
       "epoch": 3.22972972972973,
-      "eval_accuracy": 0.8714285714285714,
-      "eval_loss": 0.47154754400253296,
-      "eval_runtime": 8.8419,
-      "eval_samples_per_second": 7.917,
-      "eval_steps_per_second": 1.018,
+      "eval_accuracy": 0.8857142857142857,
+      "eval_loss": 0.38448596000671387,
+      "eval_runtime": 7.6412,
+      "eval_samples_per_second": 9.161,
+      "eval_steps_per_second": 1.178,
       "step": 148
     },
     {
       "epoch": 3.22972972972973,
       "step": 148,
       "total_flos": 1.460491890402263e+18,
-      "train_loss": 1.128270382816727,
-      "train_runtime": 532.0374,
-      "train_samples_per_second": 2.225,
-      "train_steps_per_second": 0.278
+      "train_loss": 1.0705470426662549,
+      "train_runtime": 391.8273,
+      "train_samples_per_second": 3.022,
+      "train_steps_per_second": 0.378
     },
     {
       "epoch": 3.22972972972973,
-      "eval_accuracy": 0.8193548387096774,
-      "eval_loss": 0.4508959949016571,
-      "eval_runtime": 16.4959,
-      "eval_samples_per_second": 9.396,
-      "eval_steps_per_second": 1.212,
+      "eval_accuracy": 0.8580645161290322,
+      "eval_loss": 0.4352799952030182,
+      "eval_runtime": 17.7551,
+      "eval_samples_per_second": 8.73,
+      "eval_steps_per_second": 1.126,
       "step": 148
     },
     {
       "epoch": 3.22972972972973,
-      "eval_accuracy": 0.8193548387096774,
-      "eval_loss": 0.4508959949016571,
-      "eval_runtime": 15.0463,
-      "eval_samples_per_second": 10.302,
-      "eval_steps_per_second": 1.329,
+      "eval_accuracy": 0.8580645161290322,
+      "eval_loss": 0.435279905796051,
+      "eval_runtime": 14.7921,
+      "eval_samples_per_second": 10.479,
+      "eval_steps_per_second": 1.352,
       "step": 148
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ae7d1e946ff595c27ed8a4fae05546b33b5feff6035c6ff808ac569709fedd
+oid sha256:aec101018372389d12675e6abee9e3732d722bb0e3faa26541c126344abc55f2
 size 5176